SlideShare a Scribd company logo
1 of 39
Download to read offline
Self-Tuning and
Managing Services
Reza Rahimi, PhD.
Principal Staff Algorithm and Software Architect,
Huawei R&D (Futurewei) Cloud Storage Lab (Global CTO Office),
Santa Clara, USA.
R&D
Self-Tuning and Managing Services
Related Recent R&D Experience
2
QoE-Aware smart home wireless network management and
optimization.
SLA-Aware intelligent cloud management and optimization.
R&D
PhD Topic: QoS-Aware resource management in mobile cloud
computing.
Optimal Algorithm Design
R&D
Low complexity secure code for big data in cloud storage.
5+ Years
R&D
3
PhD. Thesis:
โ€œQoS-Aware Middleware for
Optimal Service Allocation in
Mobile Cloud Computing : An
Opportunistic Approach to Internet
of Thingsโ€
Initial Core Idea
The Next Big
Thing
4
Mobile Cloud Computing (MCC)
Ecosystem
M. Reza Rahimi, Jian Ren, Chi Harold Liu, Athanasios V. Vasilakos, and Nalini Venkatasubramanian, "Mobile Cloud
Computing: A Survey, State of Art and Future Directions", in ACM/Springer Mobile Application and Networks (MONET),
Special Issue on Mobile Cloud Computing, Nov. 2014 (cited : 210+).
Tier 1: Public Cloud
(+) Scalable, Elastic, Available
(+) Fault Tolerant
(-) Price, Delay, Privacy and
Security
Tier 2: Local/Private
Cloud
(+) Low Delay, Low Power,
(+) Privacy and Security,
(- ) Limited Capacity,
IBM: by 2018 61% of
enterprise would be on
tiered cloud
Wired and Wireless
Network Providers
Local and Private
Cloud Providers
Devices, Users
,Apps and Sensors
Public Cloud Providers
Content and Service
Providers
Heavy Reading predicts that
the direct revenue of mobile
cloud market will grow
to about 68 billion $ by 2018.
5
Problem Statement
Context as a Service:
ex: Mobility patterns,
Service Usage in different
location and time,
Group-Aware, Social
Context, โ€ฆ
Network as a
Service:
ex: Wireless
connectivity
(Wi-Fi,
3G/4G/5G,
Bluetooth,โ€ฆ)
Computation
/Storage as a Service
(2-Tier):
ex: computation, Storage,
Platform,..
QoS-Aware Optimal service
allocation for mobile users based on
important criteria like:
Delay
Power
Price
6
Outline
โ€ข Location-Time Workflow
โ€ข QoS and Normalization
โ€ข Group/Single Mobile Applications, Fairness Utility
Problem
Formulation
โ€ข Simulated Annealing Approach
โ€ข Greedy Approach
โ€ข Genetic Algorithm Approach
โ€ข Scalability
Mobility-Aware
Service Allocation
Algorithms
โ€ข Orchestrating all Components in MAPCloud SOA
Architecture.
Middleware
Architecture
โ€ข Performance Results of the Algorithms
Experimental
Results
7
Modeling Services in MCC
โ€ข Applications/System Queries could be modeled as the
Workflow.
โ€ข It consists of number of logical steps known as a Service
with different composition patterns:
S1
S2
S4
S3
S5
S7
S8
S6
0
1
Par1
Par2
3
Start End
S1 S2 S3
S1
S2
S4
S3
S1
S1
S2
S4
S3
SEQ LOOP
AND: CONCURRENT FUNCTIONS XOR: CONDITIONAL FUNCTIONS
k
1
1
P1
P2
๐‘ท๐Ÿ + ๐‘ท๐Ÿ = ๐Ÿ, ๐‘ท๐Ÿ, ๐‘ท๐Ÿ โˆˆ {๐ŸŽ, ๐Ÿ}
8
t1 t2 t4
t3 tN
l2
l1
l3
ln
W1
Wk+1
Wk
Wj+1
Wj
Location-Time Workflow
โ€ข It could be formally defined as:
๐‘พ(๐’–๐’Œ)๐šป
๐‘ณ
โ‰ (๐’˜ ๐’–๐’Œ ๐’•๐’Ž๐Ÿ
๐’๐’๐Ÿ , ๐’˜ ๐’–๐’Œ ๐’•๐’Ž๐Ÿ
๐’๐’๐Ÿ ,โ€ฆ.,๐’˜ ๐’–๐’Œ ๐’•๐’Ž๐’Œ
๐’๐’๐’Œ )
Location-Time Workflow
M. Reza. Rahimi, Nalini Venkatasubramanian, Sharad Mehrotra, Athanasios Vasilakos, "On Optimal and Fair Service
Allocation in Mobile Cloud Computing", in IEEE Transaction on Cloud Computing, 2015.
9
Quality of Service (QoS)
๐’’(๐’–๐’Œ
๐’”๐’Š,๐’๐’‹,๐’•๐’Ž)๐’‘๐’๐’˜๐’†๐’“ power consumed on u cellphone when he is in location l at t using s .
โ€ข The QoS could be defined in two different Levels:
โ€ข Atomic service level
โ€ข Composite service level or workflow level.
โ€ข Atomic service level could be defined as (for power
as an example):
โ€ข The workflow QoS is based on different patterns.
QoS SEQ AND (PAR) XOR (IF-ELSE-THEN) LOOP
๐‘พ๐’‘๐’๐’˜๐’†๐’“
๐’’(๐’–๐’Œ
๐’”๐’Š,๐’๐’‹,๐’•๐’Ž)๐’‘๐’๐’˜๐’†๐’“
๐’Š ๐’
๐’Š ๐Ÿ
๐’’(๐’–๐’Œ
๐’”๐’Š,๐’๐’‹,๐’•๐’Ž)๐’‘๐’๐’˜๐’†๐’“
๐’Š ๐’
๐’Š ๐Ÿ
๐’Ž๐’‚๐’™
๐’Š
๐’’(๐’–๐’Œ
๐’”๐’Š,๐’๐’‹,๐’•๐’Ž)๐’‘๐’๐’˜๐’†๐’“ ๐’’(๐’–๐’Œ
๐’”๐’Š,๐’๐’‹,๐’•๐’Ž)๐’‘๐’๐’˜๐’†๐’“ ร— ๐’Œ
Shivajit Mohapatra, M Reza Rahimi, Nalini Venkatasubramanian, Handbook of Energy-Aware and Green Computing-Two
Volume Set, CRC Press Taylor & Francis Group, 2012 (cited :100+).
10
โ€ข As it can be understood different QoSes have different dimensions
(Price->$, power->joule, delay->s)
โ€ข We need the normalization process to make them comparable.
QoS Normalization
๐‘พ(๐’–๐’Œ)๐œฏ
๐‘ณ
๐’‘๐’๐’˜๐’†๐’“
โ‰
๐‘พ(๐’–๐’Œ)๐œฏ
๐‘ณ
๐’‘๐’๐’˜๐’†๐’“
๐’Ž๐’‚๐’™
โˆ’ ๐‘พ(๐’–๐’Œ)๐œฏ
๐‘ณ
๐’‘๐’๐’˜๐’†๐’“
๐‘พ(๐’–๐’Œ)๐œฏ
๐‘ณ
๐’‘๐’๐’˜๐’†๐’“
๐’Ž๐’‚๐’™
โˆ’ ๐‘พ(๐’–๐’Œ)๐œฏ
๐‘ณ
๐’‘๐’๐’˜๐’†๐’“
๐’Ž๐’Š๐’ , ๐‘พ(๐’–๐’Œ)๐œฏ
๐‘ณ
๐’‘๐’๐’˜๐’†๐’“
๐’Ž๐’‚๐’™
โ‰ 
๐‘พ(๐’–๐’Œ)๐œฏ
๐‘ณ
๐’‘๐’๐’˜๐’†๐’“
๐’Ž๐’Š๐’
๐Ÿ, ๐’†๐’๐’”๐’†
๏ƒผ The normalized power, price and delay is
the real number in interval [0,1].
๏ƒผ The higher the normalized QoS the better
the execution plan is.
11
๐’Ž๐’‚๐’™
๐Ÿ
|๐‘ผ|
๐’Ž๐’Š๐’ ๐‘พ(๐’–๐’Œ)๐šป
๐‘ณ
๐’‘๐’๐’˜๐’†๐’“
, ๐‘พ(๐’–๐’Œ)๐šป
๐‘ณ
๐’‘๐’“๐’Š๐’„๐’†
, ๐‘พ(๐’–๐’Œ)๐šป
๐‘ณ
๐’…๐’†๐’๐’‚๐’š
๐’–๐’Œ
๐‘บ๐’–๐’ƒ๐’‹๐’†๐’„๐’• ๐’•๐’: ๐Ÿ
|๐‘ผ|
๐‘พ(๐’–๐’Œ)๐šป
๐‘ณ
๐’‘๐’๐’˜๐’†๐’“
โ‰ค ๐‘ฉ๐’‘๐’๐’˜๐’†๐’“,
๐Ÿ
|๐‘ผ|
๐‘พ(๐’–๐’Œ)๐šป
๐‘ณ
๐’‘๐’“๐’Š๐’„๐’†
โ‰ค ๐‘ฉ๐’‘๐’“๐’Š๐’„๐’†,
๐Ÿ
|๐‘ผ|
๐‘พ(๐’–๐’Œ)๐šป
๐‘ณ
๐’…๐’†๐’๐’‚๐’š
โ‰ค ๐‘ฉ๐’…๐’†๐’๐’‚๐’š,
๐œฟ โ‰ค ๐‘ช๐’‚๐’‘(๐‘ณ๐’๐’„๐’‚๐’_๐‘ช๐’๐’๐’–๐’…๐’”)
๐œฟ โ‰œ ๐‘ต๐’–๐’Ž๐’ƒ๐’†๐’“ ๐’๐’‡ ๐’Ž๐’๐’ƒ๐’Š๐’๐’† ๐‘ผ๐’”๐’†๐’“๐’” ๐’–๐’”๐’Š๐’๐’ˆ
๐’”๐’†๐’“๐’—๐’Š๐’„๐’†๐’” ๐’๐’ ๐’๐’๐’„๐’‚๐’ ๐’„๐’๐’๐’–๐’…
โˆ€ ๐’–๐’Œ โˆˆ ๐’–๐Ÿ, โ€ฆ , ๐’–|๐‘ผ|
โ€ข In this optimization problem our goal is to maximize the minimum
saving of power, price and delay of the mobile applications.
Optimal Service Allocation for
Single Mobile User
12
๐’Ž๐’‚๐’™
๐Ÿ
|๐‘ฎ|
๐Ÿ
|๐’ˆ๐’Š|
๐’Ž๐’Š๐’ ๐‘พ(๐’–๐’Œ)๐šป
๐‘ณ
๐’‘๐’๐’˜๐’†๐’“
, ๐‘พ(๐’–๐’Œ)๐šป
๐‘ณ
๐’‘๐’“๐’Š๐’„๐’†
, ๐‘พ(๐’–๐’Œ)๐šป
๐‘ณ
๐’…๐’†๐’๐’‚๐’š
๐’–๐’Œโˆˆ๐’ˆ๐’Š
๐’ˆ๐’Šโˆˆ๐‘ฎ
๐‘บ๐’–๐’ƒ๐’‹๐’†๐’„๐’• ๐’•๐’: ๐Ÿ
|๐’ˆ๐’Š|
๐‘พ(๐’ˆ๐’Š)๐šป
๐‘ณ
๐’‘๐’๐’˜๐’†๐’“
โ‰ค ๐‘ฉ๐’‘๐’๐’˜๐’†๐’“,
๐Ÿ
|๐’ˆ๐’Š|
๐‘พ(๐’ˆ๐’Š)๐šป
๐‘ณ
๐’‘๐’“๐’Š๐’„๐’†
โ‰ค ๐‘ฉ๐’‘๐’“๐’Š๐’„๐’†,
๐Ÿ
|๐’ˆ๐’Š|
๐‘พ(๐’ˆ๐’Š)๐šป
๐‘ณ
๐’…๐’†๐’๐’‚๐’š
โ‰ค ๐‘ฉ๐’…๐’†๐’๐’‚๐’š,
๐œฟ โ‰ค ๐‘ช๐’‚๐’‘(๐‘ณ๐’๐’„๐’‚๐’_๐‘ช๐’๐’๐’–๐’…๐’”)
๐œฟ โ‰œ ๐‘ต๐’–๐’Ž๐’ƒ๐’†๐’“ ๐’๐’‡ ๐’Ž๐’๐’ƒ๐’Š๐’๐’† ๐‘ผ๐’”๐’†๐’“๐’” ๐’–๐’”๐’Š๐’๐’ˆ
๐’”๐’†๐’“๐’—๐’Š๐’„๐’†๐’” ๐’๐’ ๐’๐’๐’„๐’‚๐’ ๐’„๐’๐’๐’–๐’…
โˆ€ ๐’–๐’Œ โˆˆ ๐’–๐Ÿ, โ€ฆ , ๐’–|๐‘ผ|
โˆ€ ๐’ˆ๐’Š โˆˆ ๐’ˆ๐’Š, โ€ฆ , ๐’ˆ|๐‘ฎ|
These optimization problems are NP-Hard (Knapsack is the special case)
so we look for heuristic/Approximation to solve them.
Optimal Service Allocation for
Mobile/Social Groups
13
Service Allocation Algorithms for
Single Mobile User and Mobile Group-Social
Applications
Brute-Force Search (BFS)
MuSIC
Genetic Based
Greedy Based (Different
Policies)
Random Service Allocation
(RSA)
โ€ข We start with our main one, which we call it MuSIC: Mobility
Aware Service AllocatIon on Cloud.
โ€ข Its core is based-on simulated annealing approach.
M. Reza. Rahimi, Nalini Venkatasubramanian, Athanasios Vasilakos, "MuSIC: On Mobility-Aware Optimal Service
Allocation in Mobile Cloud Computing", In the IEEE 6th International Conference on Cloud Computing, (Cloud
2013), Silicon Valley, CA, USA, July 2013 (cited : 110+).
Mobility-Aware Service Allocation
Algorithms on 2-Tier Cloud
14
๏ƒผ Partition mobile users and local clouds based on their
proximities and run service allocation algorithms for each
region in parallel (using clustering techniques).
Public Cloud
Local
Cloud
Local
Cloud
Local
Cloud
Local
Cloud
Local
Cloud Local
Cloud
Local
Cloud
Scaling Out MuSIC : Simplified
15
Service 1 Service n
Mobile Users
Pig Latin pseudo codes:
/*Load Data*/
LOAD mobile users , servicesโ€ฆ.
/*Cartesian product to produce solution
space*/
CROSS Mobile users, Service1,โ€ฆ
/*Apply Optimization Constraints to
solution space */
FILTER by Constraints1,โ€ฆ
/*Find Best Solution*/
FOREACH Mobile User GENERATE
utility value
GROUP Solution By Mobile Users
FOREACH Solution GENERATE MAX
Apply System Constraints
Compute UTILITY FUNCTION of
each solution for Mobile Users
GROUP Solutions for each Mobile
Users
Find the MAXIMUM UTILITY for
each Mobile Users and emit as the
best solution
Scalable Brute-Force Search Using
Big Data Processing (Apache Pig)
16
QoS-Aware
Service DB
Mobile User
Log DB
Optimal Service Scheduler
Cloud Service Registry
Mobile
Client
MAPCloud
Web
Service
Interface
MAPCloud
Runtime
Local and
Public
Cloud Pool
MAPCloud LTW
Engine
MAPCloud Web Service Interface
MAPCloud SOAArchitecture
MAPCloud Video
Demo
M. Reza. Rahimi, Nalini Venkatasubramanian, Sharad Mehrotra and Athanasios Vasilakos, "MAPCloud: Mobile Applications
on an Elastic and Scalable 2-Tier Cloud Architecture", In the 5th IEEE/ACM International Conference on Utility and Cloud
Computing (UCC 2012), USA, Nov 2012 (cited : 110+)
17
Experimental and Simulation Results:
Mobile Applications Benchmarks
OCR+ Speech
(OCRS):
Video
Augmented
Reality
(VAR):
You Tube
Link
Multimedia File Sharing (MFS):
Mobile Apps Processing Storage Bandwidth Social Application
OCRS ร— ร—
VAR ร— ร— ร—
MFC ร— ร— ร— ร—
18
Simulation Setup
Amazon
EC2,S3
Local Cloud
1
Local Cloud
5
Local Cloud 2
Local Cloud
7
Local Cloud
4
Local Cloud n
S1
.
.
.
Sn
S1
.
.
.
Sn
S1
.
.
.
Sn
S1
.
.
.
Sn
S1
.
.
.
Sn
large instance:
equivalent to a PC
with
7.5GB of memory,
850 GB of storage
Local Cloud:
64bit Windows dual-
core server,
with 8GB of memory
and 500GB of storage.
LAN Speed
Profiling sample applications has been used to
tune the system Environment.
Java Network simulator
(JNS) and CloudSim
used for modeling the
delay between
Local clouds.
RWP and Manhattan
mobility models are used
as the mobility models
(V[0/ms-10/ms]).
We also add some error
in mobility models to
check the robustness of
service allocation
algorithms.
19
Performance Results
MuSIC, Genetic, Greedy, RSA and G-MuSIC (5-Groups) algorithms average throughput
with uncertainty in LTW prediction in the range of [0%,30%]
20
Scalability Studies
RSA-Par/Pig-Based MuSIC-Par/Pig-Based Greedy-Par/Pig-Based GA-Par/Pig-Based
Single 48% 79% 65% 70%
Group 47% 74% 62% 68%
Settings: 10,000 mobile users, uniformly distributed, 6 different services per mobile users and for each
service we have 10 different candidates (on local or public cloud) # of local clouds: 50 , uniformly distributed
# public cloud :10 amazon Large instance.
In general our parallel version of our algorithm is ~4 times faster
Than Pig-based distributed version.
21
QoE-Aware smart home wireless
network management and optimization.
22
SMART Connectivity
Solution
Providing innovative means of connecting devices and things through new connectivity
paradigm.
2018
Need for a โ€œIntelligentโ€ Networking
2014
Growing โ€œConnected Life โ€œ
Better Coverage
Higher Throughput Lower Interference
Lower Power/Energy
Bad Coverage
Low Throughput High Interference
High Power/Energy
Problem
23
Ambient Network Sensing
UX
Network
Devices
Apps
Vertical Handoffs
(VHOs)
Analytics Interference
Battery Life Service Cost
Context-aware Connectivity Context Aware Handoffs
Predict Quality of Experience
QoE Modeling
Outcome
Core Enabler Services
24
SMART Connectivity Service Diagram
Ambient network and application
sensing
RSSI
Link Speed
YouTube
Event Listener
App
ANS Profiler
647 sec
QoE Analytics
Sample
Predicated
0.425
17 events/sec
-85 dBm
1 Mbps
1.9
1
2
Objective Context
3
5
QoE Scale : 1 for โ€œPoorโ€ to 5 for
โ€œExcellentโ€
Decision Tree
QoE Heat Maps
2.9
1.9
1.2
Initial
Buffering
Time
Buffering
Ratio
Buffering
Frequency
QoE for WiFi1
QoE for WiFi2
QoE for BT
Connect
to WiFi1
6
4
With Technology Usage we Got :
-- increase users QoE (MOS Score) and userโ€™s
engagement up to 30%,
-- energy consumption reduction on smart
devices up to 2x,
-- reduce delay and buffering time up to 4x
25
Got Technology transfer to Samsung
New Acquired Company :
SmartThings
๏ƒ˜ Sensing Dongle,
๏ƒ˜ MIH IEEE 802.21 Implementation
on Linux Kernel
26
SLA-Aware intelligent cloud
management and optimization
R&D
M. Reza. Rahimi, โ€œSelf-Tuning Data Centersโ€, Big Data Innovation Summit, Las Vegas, 2017,
(Keynote Talk).
27
Applications Spectrum
Computing (CPU , GPU, DSP, FPGA,...)
Storage (DRAM, SSD, HDD,..)
Network (Wired, Wi-Fi, 4G,โ€ฆ)
Self-Driving Cars
Robotic/AI Applications
Data Management Systems
Video Streaming/IoT,โ€ฆ
These applications will be
fully or partially supported
by Data Centers Services
(Cloud-Based)
28
Typical Data Center Architecture
As a simple rule of thumb:
Enterprise Data Center Size :
100 Hosts
1000 VMs
~Logs : 40 GB/Day
Data Center
Management
VM-1-k
VM-1-1 VM-2-1
VM-2-m
VM-n-1
VM-n-l
Host 1 Host 2
Host n
logs
logs logs
Storage Pool
Big Data Engineering
and Science
Apps are running
on VMs
29
Some Data Center Management
Challenges/Opportunities
Service Level Agreement (SLA) :
Throughput/Latency (e-commerce applications):
โ–บ 2014 US $304 billion increasing 15.4% yearly in e-commerce,
โ–บ 100ms latency costs 1% decrease in sale,
โ–บ Page loading should be less than 2 seconds per page not to lose
customer, will decrease overall sales by 7%,
Resource Utilization (Capacity Planning) :
โ–บ ~ 90 percent of the VMs utilizes < 15% of assigned Cores/Storage,
โ–บ ~ 90 percent of the VMs only have < 10 IOPS,
Scalable and Elastic (on Demand) :
โ–บ Should know when and how to scale to satisfy SLA dynamically,
30
Energy Efficiency :
โ–บ By 2020 reduction of energy cost 30% based on
European law-Green DC,
โ–บ US data centers consume ~ 90 billion Kilowatt hours annually =
House hold in NY for two years
โ–บ Pollute over 150 million tons of carbon yearly in USA,
โ–บ Average server runs on [12%-18%] of their capacity most of the time
still consuming 30% to 60% of their maximum power consumption.
โ–บ High utilization -> save in power consumption->Low carbon
footprint
Dynamic Service Pricing :
โ–บ Computing, network and storage are utilities for workloads.
โ–บ Should model to find a dynamic way and good policy of pricing in
competitive market of cloud providers while increasing revenue/profit.
Some Data Center Management
Challenges/Opportunities
31
Software Compliance and License :
โ–บ ~ $500,000 spent on software licensing for average size data center,
โ–บ It could be per User/Device/VM/Core/โ€ฆ
โ–บ Different models and policies for license like:
1) Running licensed workload on bare metal (no virtualization),
2) Running licensed workload on dedicated cluster,
3) Migrate licensed workload,
4) โ€ฆ
โ–บ Workloads and cluster growth bring challenges for software license,
โ–บ This bring the challenge how to minimize the cost of software on
data centers and not violate license policy,
Some Data Center Management
Challenges/Opportunities
32
Self-Tuning Data Center : Simplified
Service Flow
VM
Scheduling and
Orchestrating Services
and Resources
Real-time Log and
Monitoring
Service
Watcher and
Policy Service
Recommendation
/Prediction Service
2) Ask correct size, type
And location for resource
Based on request
1) Request resource
3) Correct conf and
resource size and place
4) Allocate required
resources
1) Telemetry and log sending
2) Query logs for policy and
alert checks
4) Check for violation
and warnings
5) Alert of Violation
6) Ask for Recommendation
7 ) Send Recommendations
and Recipes
8 ) Apply Recommendation
Initial
State
Operational and
Recovery State
1 ) Ask Recommendation
For Self-Tune (for example
in low traffic state)
2) Send Tuning Plan
and Recommendation
(like VM migration or
resizing)
3 ) Apply Self-Tuning
recommendation
Self-Tuning
State
3) Collected Data
-- Resource Sizing Tool,
-- Time Series Prediction
(CAP/PERF(IOPS/LAT)),
-- Anomaly detection,
-- Performance Prediction
-- Simulation,
-- โ€ฆ
33
Got Technology transfer to Huawei
eService (๏ƒ Huawei OceanStor DJ)
๏ƒ˜ Scalable, Reliable and Available Telemetry
Platform,
๏ƒ˜ Modeling as a Service :
-- Storage Required Capacity Prediction,
-- Performance Prediction (IOPS/LAT/BW),
-- CACHE Sizing tool for OLTP/VDI/Exchange,
-- โ€ฆ
34
Low Complexity Secure Code for Big Data in
Cloud Storage Systems
R&D
Mohsen Kiskani, Hamid Sadjadpour, M. Reza Rahimi, Fred Etemadieh, "Low Complexity Secure Code
(LCSC) Design for Big Data in Cloud Storage Systems", in IEEE ICC, Kansas City, MO, USA, May
2018.
35
Data
Reliability
Data
Security and
Privacy
Data Replication
or Coding
Encryption/
Decryption
Current
Industry
Approach
Data Reliability +
Security and Privacy
Hybrid Codes
Increased processing speed by ~400%,
100% security in data (SLA),
No more need to use https,
PIR (Private Information Retrieval),
36
Both Encoding and Decoding
will be simple/cheap XOR
operations.
Encoding:
y1 = x3 โจ x4
y2 = x1 โจ x3
y3 = x1 โจ x2
y4 = x2 โจ x3 โจ x4
Decoding:
x1 = y1 โจ y3 โจ y4
x2 = y1 โจ y4
x3 = y1 โจ y2 โจ y3 โจ y4
x4 = y2 โจ y3 โจ y4
Sample Encoding and Decoding
y1 y2 y3 y4
y1 y2 y3 y4
x1 x2 x3 x4
x1 x2 x3 x4
Property Repetition / RAID Erasure / MDS Proposed Coding
Storage overhead Significant Very Small Very Small
Reparability Possible Possible Possible
Security Need Encryption Need Encryption No Encryption
Computational Complexity
comparing encryption
Low high Very Low
37
โ€ข Step 1 : User requests file B1 and sends the decoding
instructions to the storage unit,
โ€ข Step 2 : Storage unit combines the encoded files using the
decoding instructions in the storage processing unit,
โ€ข Step 3 : Storage unit transmits the result to the user,
โ€ข Step 4 : User combines the received data with its own encoded
files and creates B1,
C1
C2
C3
C4
C5
C6
C7
C8
C9
C10
C11
C12
Storage Unit
User
New
Encoding
Scheme
Original Data
B1
B2
B3
B4
B5
B6
๐šบ giCi + g13 C13 + g14
C14+ g15 C15 = B1
Decoding
Instructions
C13 C15
C14
๐šบ giCi
Storage Processing Service
(1)
(2)
(3)
(4)
Service Architecture and Data
Retrieval Process
Conclusion and Future Directions
๏ƒผ Self-tuning and managing services in different application
domains and context.
๏ƒผ Architectural and algorithmic patterns that those systems have
in common and some best practices to solve them.
๏ƒผ More things (physical/virtual) are connected together,
physically/virtually/semantically.
๏ƒผManaging this environment is very challenging for human, need a
way to have autonomous system with low human interaction.
๏ƒผAI/ML/DL and big data processing tools are some of the best
industrial practices to tackle these problems.
๏ƒผ We are in the beginning era of Web 4.0 : Self-tuning and
managing web.
38
39
Thanks ๏Š
Questions?

More Related Content

What's hot

REVIEW PAPER on Scheduling in Cloud Computing
REVIEW PAPER on Scheduling in Cloud ComputingREVIEW PAPER on Scheduling in Cloud Computing
REVIEW PAPER on Scheduling in Cloud ComputingJaya Gautam
ย 
Score based deadline constrained workflow scheduling algorithm for cloud systems
Score based deadline constrained workflow scheduling algorithm for cloud systemsScore based deadline constrained workflow scheduling algorithm for cloud systems
Score based deadline constrained workflow scheduling algorithm for cloud systemsijccsa
ย 
dynamic resource allocation using virtual machines for cloud computing enviro...
dynamic resource allocation using virtual machines for cloud computing enviro...dynamic resource allocation using virtual machines for cloud computing enviro...
dynamic resource allocation using virtual machines for cloud computing enviro...Kumar Goud
ย 
Differentiating Algorithms of Cloud Task Scheduling Based on various Parameters
Differentiating Algorithms of Cloud Task Scheduling Based on various ParametersDifferentiating Algorithms of Cloud Task Scheduling Based on various Parameters
Differentiating Algorithms of Cloud Task Scheduling Based on various Parametersiosrjce
ย 
Detecting Lateral Movement with a Compute-Intense Graph Kernel
Detecting Lateral Movement with a Compute-Intense Graph KernelDetecting Lateral Movement with a Compute-Intense Graph Kernel
Detecting Lateral Movement with a Compute-Intense Graph KernelData Works MD
ย 
Survey on Dynamic Resource Allocation Strategy in Cloud Computing Environment
Survey on Dynamic Resource Allocation Strategy in Cloud Computing EnvironmentSurvey on Dynamic Resource Allocation Strategy in Cloud Computing Environment
Survey on Dynamic Resource Allocation Strategy in Cloud Computing EnvironmentEditor IJCATR
ย 
Learning Software Performance Models for Dynamic and Uncertain Environments
Learning Software Performance Models for Dynamic and Uncertain EnvironmentsLearning Software Performance Models for Dynamic and Uncertain Environments
Learning Software Performance Models for Dynamic and Uncertain EnvironmentsPooyan Jamshidi
ย 
My Dissertation 2016
My Dissertation 2016My Dissertation 2016
My Dissertation 2016Vrushali Lanjewar
ย 
Scheduling in CCE
Scheduling in CCEScheduling in CCE
Scheduling in CCEMayuri Saxena
ย 
Large-Scale Lasso and Elastic-Net Regularized Generalized Linear Models (DB T...
Large-Scale Lasso and Elastic-Net Regularized Generalized Linear Models (DB T...Large-Scale Lasso and Elastic-Net Regularized Generalized Linear Models (DB T...
Large-Scale Lasso and Elastic-Net Regularized Generalized Linear Models (DB T...Spark Summit
ย 
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...AtakanAral
ย 
AN EFFICIENT ALGORITHM FOR THE BURSTING OF SERVICE-BASED APPLICATIONS IN HYB...
 AN EFFICIENT ALGORITHM FOR THE BURSTING OF SERVICE-BASED APPLICATIONS IN HYB... AN EFFICIENT ALGORITHM FOR THE BURSTING OF SERVICE-BASED APPLICATIONS IN HYB...
AN EFFICIENT ALGORITHM FOR THE BURSTING OF SERVICE-BASED APPLICATIONS IN HYB...Nexgen Technology
ย 
Optimal load balancing in cloud computing
Optimal load balancing in cloud computingOptimal load balancing in cloud computing
Optimal load balancing in cloud computingPriyanka Bhowmick
ย 
Configuration Optimization for Big Data Software
Configuration Optimization for Big Data SoftwareConfiguration Optimization for Big Data Software
Configuration Optimization for Big Data SoftwarePooyan Jamshidi
ย 
Adaptive Replication for Elastic Data Stream Processing
Adaptive Replication for Elastic Data Stream ProcessingAdaptive Replication for Elastic Data Stream Processing
Adaptive Replication for Elastic Data Stream ProcessingZbigniew Jerzak
ย 
A performance analysis of OpenStack Cloud vs Real System on Hadoop Clusters
A performance analysis of OpenStack Cloud vs Real System on Hadoop ClustersA performance analysis of OpenStack Cloud vs Real System on Hadoop Clusters
A performance analysis of OpenStack Cloud vs Real System on Hadoop ClustersKumari Surabhi
ย 
Resilient Distributed Datasets
Resilient Distributed DatasetsResilient Distributed Datasets
Resilient Distributed DatasetsGabriele Modena
ย 
Optimization of Continuous Queries in Federated Database and Stream Processin...
Optimization of Continuous Queries in Federated Database and Stream Processin...Optimization of Continuous Queries in Federated Database and Stream Processin...
Optimization of Continuous Queries in Federated Database and Stream Processin...Zbigniew Jerzak
ย 
Energy-aware Task Scheduling using Ant-colony Optimization in cloud
Energy-aware Task Scheduling using Ant-colony Optimization in cloudEnergy-aware Task Scheduling using Ant-colony Optimization in cloud
Energy-aware Task Scheduling using Ant-colony Optimization in cloudLinda J
ย 
Auto-scaling Techniques for Elastic Data Stream Processing
Auto-scaling Techniques for Elastic Data Stream ProcessingAuto-scaling Techniques for Elastic Data Stream Processing
Auto-scaling Techniques for Elastic Data Stream ProcessingZbigniew Jerzak
ย 

What's hot (20)

REVIEW PAPER on Scheduling in Cloud Computing
REVIEW PAPER on Scheduling in Cloud ComputingREVIEW PAPER on Scheduling in Cloud Computing
REVIEW PAPER on Scheduling in Cloud Computing
ย 
Score based deadline constrained workflow scheduling algorithm for cloud systems
Score based deadline constrained workflow scheduling algorithm for cloud systemsScore based deadline constrained workflow scheduling algorithm for cloud systems
Score based deadline constrained workflow scheduling algorithm for cloud systems
ย 
dynamic resource allocation using virtual machines for cloud computing enviro...
dynamic resource allocation using virtual machines for cloud computing enviro...dynamic resource allocation using virtual machines for cloud computing enviro...
dynamic resource allocation using virtual machines for cloud computing enviro...
ย 
Differentiating Algorithms of Cloud Task Scheduling Based on various Parameters
Differentiating Algorithms of Cloud Task Scheduling Based on various ParametersDifferentiating Algorithms of Cloud Task Scheduling Based on various Parameters
Differentiating Algorithms of Cloud Task Scheduling Based on various Parameters
ย 
Detecting Lateral Movement with a Compute-Intense Graph Kernel
Detecting Lateral Movement with a Compute-Intense Graph KernelDetecting Lateral Movement with a Compute-Intense Graph Kernel
Detecting Lateral Movement with a Compute-Intense Graph Kernel
ย 
Survey on Dynamic Resource Allocation Strategy in Cloud Computing Environment
Survey on Dynamic Resource Allocation Strategy in Cloud Computing EnvironmentSurvey on Dynamic Resource Allocation Strategy in Cloud Computing Environment
Survey on Dynamic Resource Allocation Strategy in Cloud Computing Environment
ย 
Learning Software Performance Models for Dynamic and Uncertain Environments
Learning Software Performance Models for Dynamic and Uncertain EnvironmentsLearning Software Performance Models for Dynamic and Uncertain Environments
Learning Software Performance Models for Dynamic and Uncertain Environments
ย 
My Dissertation 2016
My Dissertation 2016My Dissertation 2016
My Dissertation 2016
ย 
Scheduling in CCE
Scheduling in CCEScheduling in CCE
Scheduling in CCE
ย 
Large-Scale Lasso and Elastic-Net Regularized Generalized Linear Models (DB T...
Large-Scale Lasso and Elastic-Net Regularized Generalized Linear Models (DB T...Large-Scale Lasso and Elastic-Net Regularized Generalized Linear Models (DB T...
Large-Scale Lasso and Elastic-Net Regularized Generalized Linear Models (DB T...
ย 
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...
ย 
AN EFFICIENT ALGORITHM FOR THE BURSTING OF SERVICE-BASED APPLICATIONS IN HYB...
 AN EFFICIENT ALGORITHM FOR THE BURSTING OF SERVICE-BASED APPLICATIONS IN HYB... AN EFFICIENT ALGORITHM FOR THE BURSTING OF SERVICE-BASED APPLICATIONS IN HYB...
AN EFFICIENT ALGORITHM FOR THE BURSTING OF SERVICE-BASED APPLICATIONS IN HYB...
ย 
Optimal load balancing in cloud computing
Optimal load balancing in cloud computingOptimal load balancing in cloud computing
Optimal load balancing in cloud computing
ย 
Configuration Optimization for Big Data Software
Configuration Optimization for Big Data SoftwareConfiguration Optimization for Big Data Software
Configuration Optimization for Big Data Software
ย 
Adaptive Replication for Elastic Data Stream Processing
Adaptive Replication for Elastic Data Stream ProcessingAdaptive Replication for Elastic Data Stream Processing
Adaptive Replication for Elastic Data Stream Processing
ย 
A performance analysis of OpenStack Cloud vs Real System on Hadoop Clusters
A performance analysis of OpenStack Cloud vs Real System on Hadoop ClustersA performance analysis of OpenStack Cloud vs Real System on Hadoop Clusters
A performance analysis of OpenStack Cloud vs Real System on Hadoop Clusters
ย 
Resilient Distributed Datasets
Resilient Distributed DatasetsResilient Distributed Datasets
Resilient Distributed Datasets
ย 
Optimization of Continuous Queries in Federated Database and Stream Processin...
Optimization of Continuous Queries in Federated Database and Stream Processin...Optimization of Continuous Queries in Federated Database and Stream Processin...
Optimization of Continuous Queries in Federated Database and Stream Processin...
ย 
Energy-aware Task Scheduling using Ant-colony Optimization in cloud
Energy-aware Task Scheduling using Ant-colony Optimization in cloudEnergy-aware Task Scheduling using Ant-colony Optimization in cloud
Energy-aware Task Scheduling using Ant-colony Optimization in cloud
ย 
Auto-scaling Techniques for Elastic Data Stream Processing
Auto-scaling Techniques for Elastic Data Stream ProcessingAuto-scaling Techniques for Elastic Data Stream Processing
Auto-scaling Techniques for Elastic Data Stream Processing
ย 

Similar to Self-Tuning and Managing Services

Smuggling Multi-Cloud Support into Cloud-native Applications using Elastic Co...
Smuggling Multi-Cloud Support into Cloud-native Applications using Elastic Co...Smuggling Multi-Cloud Support into Cloud-native Applications using Elastic Co...
Smuggling Multi-Cloud Support into Cloud-native Applications using Elastic Co...Nane Kratzke
ย 
Final Year Engineering Projects
Final  Year  Engineering  ProjectsFinal  Year  Engineering  Projects
Final Year Engineering Projectsncct
ย 
Wireless Networks Projects, Network Security Projects, Networking Project
Wireless Networks Projects, Network Security Projects, Networking ProjectWireless Networks Projects, Network Security Projects, Networking Project
Wireless Networks Projects, Network Security Projects, Networking Projectncct
ย 
Polytechnic Projects
Polytechnic ProjectsPolytechnic Projects
Polytechnic Projectsncct
ย 
Best Final Year Projects Latest New Innovative And Ieee 2009 2010 (1)
Best Final Year Projects Latest New Innovative And Ieee 2009 2010 (1)Best Final Year Projects Latest New Innovative And Ieee 2009 2010 (1)
Best Final Year Projects Latest New Innovative And Ieee 2009 2010 (1)ncct
ย 
Software Projects A Sp.Net Projects Ieee Projects Domains
Software Projects A Sp.Net Projects Ieee Projects DomainsSoftware Projects A Sp.Net Projects Ieee Projects Domains
Software Projects A Sp.Net Projects Ieee Projects Domainsncct
ย 
J2 M E Projects, I E E E Projects 2009
J2 M E  Projects,  I E E E  Projects 2009J2 M E  Projects,  I E E E  Projects 2009
J2 M E Projects, I E E E Projects 2009ncct
ย 
Ieee Software Projects Java Projects Ieee Projects Domains
Ieee Software Projects Java Projects Ieee Projects DomainsIeee Software Projects Java Projects Ieee Projects Domains
Ieee Software Projects Java Projects Ieee Projects Domainsncct
ย 
Java Projects Ieee Projects
Java Projects Ieee ProjectsJava Projects Ieee Projects
Java Projects Ieee Projectsncct
ย 
Vb.Net Projects, Final Year Projects
Vb.Net Projects, Final Year ProjectsVb.Net Projects, Final Year Projects
Vb.Net Projects, Final Year Projectsncct
ย 
College Projects, Be Projects, B Tech Projects, Me Projects, M Tech Projects,...
College Projects, Be Projects, B Tech Projects, Me Projects, M Tech Projects,...College Projects, Be Projects, B Tech Projects, Me Projects, M Tech Projects,...
College Projects, Be Projects, B Tech Projects, Me Projects, M Tech Projects,...ncct
ย 
College Projects, Be Projects, B Tech Projects, Me Projects, M Tech Projects,...
College Projects, Be Projects, B Tech Projects, Me Projects, M Tech Projects,...College Projects, Be Projects, B Tech Projects, Me Projects, M Tech Projects,...
College Projects, Be Projects, B Tech Projects, Me Projects, M Tech Projects,...ncct
ย 
Software Projects Asp.Net Java Ncct Chenai
Software Projects Asp.Net Java Ncct ChenaiSoftware Projects Asp.Net Java Ncct Chenai
Software Projects Asp.Net Java Ncct Chenaincct
ย 
A Novel Approach for Workload Optimization and Improving Security in Cloud Co...
A Novel Approach for Workload Optimization and Improving Security in Cloud Co...A Novel Approach for Workload Optimization and Improving Security in Cloud Co...
A Novel Approach for Workload Optimization and Improving Security in Cloud Co...IOSR Journals
ย 
4 Sw 2009 Ieee Abstracts Dot Net, Ncct Chennai
4   Sw   2009 Ieee Abstracts   Dot Net, Ncct Chennai4   Sw   2009 Ieee Abstracts   Dot Net, Ncct Chennai
4 Sw 2009 Ieee Abstracts Dot Net, Ncct Chennaincct
ย 
Middleware para IoT basado en analรญtica de datos
Middleware para IoT basado en analรญtica de datosMiddleware para IoT basado en analรญtica de datos
Middleware para IoT basado en analรญtica de datosFacultad de Informรกtica UCM
ย 
QoS-Aware Middleware for Optimal Service Allocation in Mobile Cloud Computing
QoS-Aware Middleware for Optimal Service Allocation in Mobile Cloud ComputingQoS-Aware Middleware for Optimal Service Allocation in Mobile Cloud Computing
QoS-Aware Middleware for Optimal Service Allocation in Mobile Cloud ComputingReza Rahimi
ย 
Zou Layered VO PDCAT2008 V0.5 Concise
Zou Layered VO PDCAT2008 V0.5 ConciseZou Layered VO PDCAT2008 V0.5 Concise
Zou Layered VO PDCAT2008 V0.5 Conciseyongqiangzou
ย 
Towards a Lightweight Multi-Cloud DSL for Elastic and Transferable Cloud-nati...
Towards a Lightweight Multi-Cloud DSL for Elastic and Transferable Cloud-nati...Towards a Lightweight Multi-Cloud DSL for Elastic and Transferable Cloud-nati...
Towards a Lightweight Multi-Cloud DSL for Elastic and Transferable Cloud-nati...Nane Kratzke
ย 

Similar to Self-Tuning and Managing Services (20)

Smuggling Multi-Cloud Support into Cloud-native Applications using Elastic Co...
Smuggling Multi-Cloud Support into Cloud-native Applications using Elastic Co...Smuggling Multi-Cloud Support into Cloud-native Applications using Elastic Co...
Smuggling Multi-Cloud Support into Cloud-native Applications using Elastic Co...
ย 
Final Year Engineering Projects
Final  Year  Engineering  ProjectsFinal  Year  Engineering  Projects
Final Year Engineering Projects
ย 
Wireless Networks Projects, Network Security Projects, Networking Project
Wireless Networks Projects, Network Security Projects, Networking ProjectWireless Networks Projects, Network Security Projects, Networking Project
Wireless Networks Projects, Network Security Projects, Networking Project
ย 
Polytechnic Projects
Polytechnic ProjectsPolytechnic Projects
Polytechnic Projects
ย 
Best Final Year Projects Latest New Innovative And Ieee 2009 2010 (1)
Best Final Year Projects Latest New Innovative And Ieee 2009 2010 (1)Best Final Year Projects Latest New Innovative And Ieee 2009 2010 (1)
Best Final Year Projects Latest New Innovative And Ieee 2009 2010 (1)
ย 
Software Projects A Sp.Net Projects Ieee Projects Domains
Software Projects A Sp.Net Projects Ieee Projects DomainsSoftware Projects A Sp.Net Projects Ieee Projects Domains
Software Projects A Sp.Net Projects Ieee Projects Domains
ย 
J2 M E Projects, I E E E Projects 2009
J2 M E  Projects,  I E E E  Projects 2009J2 M E  Projects,  I E E E  Projects 2009
J2 M E Projects, I E E E Projects 2009
ย 
Ieee Software Projects Java Projects Ieee Projects Domains
Ieee Software Projects Java Projects Ieee Projects DomainsIeee Software Projects Java Projects Ieee Projects Domains
Ieee Software Projects Java Projects Ieee Projects Domains
ย 
Java Projects Ieee Projects
Java Projects Ieee ProjectsJava Projects Ieee Projects
Java Projects Ieee Projects
ย 
Vb.Net Projects, Final Year Projects
Vb.Net Projects, Final Year ProjectsVb.Net Projects, Final Year Projects
Vb.Net Projects, Final Year Projects
ย 
College Projects, Be Projects, B Tech Projects, Me Projects, M Tech Projects,...
College Projects, Be Projects, B Tech Projects, Me Projects, M Tech Projects,...College Projects, Be Projects, B Tech Projects, Me Projects, M Tech Projects,...
College Projects, Be Projects, B Tech Projects, Me Projects, M Tech Projects,...
ย 
College Projects, Be Projects, B Tech Projects, Me Projects, M Tech Projects,...
College Projects, Be Projects, B Tech Projects, Me Projects, M Tech Projects,...College Projects, Be Projects, B Tech Projects, Me Projects, M Tech Projects,...
College Projects, Be Projects, B Tech Projects, Me Projects, M Tech Projects,...
ย 
Software Projects Asp.Net Java Ncct Chenai
Software Projects Asp.Net Java Ncct ChenaiSoftware Projects Asp.Net Java Ncct Chenai
Software Projects Asp.Net Java Ncct Chenai
ย 
D017212027
D017212027D017212027
D017212027
ย 
A Novel Approach for Workload Optimization and Improving Security in Cloud Co...
A Novel Approach for Workload Optimization and Improving Security in Cloud Co...A Novel Approach for Workload Optimization and Improving Security in Cloud Co...
A Novel Approach for Workload Optimization and Improving Security in Cloud Co...
ย 
4 Sw 2009 Ieee Abstracts Dot Net, Ncct Chennai
4   Sw   2009 Ieee Abstracts   Dot Net, Ncct Chennai4   Sw   2009 Ieee Abstracts   Dot Net, Ncct Chennai
4 Sw 2009 Ieee Abstracts Dot Net, Ncct Chennai
ย 
Middleware para IoT basado en analรญtica de datos
Middleware para IoT basado en analรญtica de datosMiddleware para IoT basado en analรญtica de datos
Middleware para IoT basado en analรญtica de datos
ย 
QoS-Aware Middleware for Optimal Service Allocation in Mobile Cloud Computing
QoS-Aware Middleware for Optimal Service Allocation in Mobile Cloud ComputingQoS-Aware Middleware for Optimal Service Allocation in Mobile Cloud Computing
QoS-Aware Middleware for Optimal Service Allocation in Mobile Cloud Computing
ย 
Zou Layered VO PDCAT2008 V0.5 Concise
Zou Layered VO PDCAT2008 V0.5 ConciseZou Layered VO PDCAT2008 V0.5 Concise
Zou Layered VO PDCAT2008 V0.5 Concise
ย 
Towards a Lightweight Multi-Cloud DSL for Elastic and Transferable Cloud-nati...
Towards a Lightweight Multi-Cloud DSL for Elastic and Transferable Cloud-nati...Towards a Lightweight Multi-Cloud DSL for Elastic and Transferable Cloud-nati...
Towards a Lightweight Multi-Cloud DSL for Elastic and Transferable Cloud-nati...
ย 

More from Reza Rahimi

Boosting Personalization In SaaS Using Machine Learning.pdf
Boosting Personalization  In SaaS Using Machine Learning.pdfBoosting Personalization  In SaaS Using Machine Learning.pdf
Boosting Personalization In SaaS Using Machine Learning.pdfReza Rahimi
ย 
Low Complexity Secure Code Design for Big Data in Cloud Storage Systems
Low Complexity Secure Code Design for Big Data in Cloud Storage SystemsLow Complexity Secure Code Design for Big Data in Cloud Storage Systems
Low Complexity Secure Code Design for Big Data in Cloud Storage SystemsReza Rahimi
ย 
Smart Connectivity
Smart ConnectivitySmart Connectivity
Smart ConnectivityReza Rahimi
ย 
Self-Tuning Data Centers
Self-Tuning Data CentersSelf-Tuning Data Centers
Self-Tuning Data CentersReza Rahimi
ย 
The Next Big Thing in IT
The Next Big Thing in ITThe Next Big Thing in IT
The Next Big Thing in ITReza Rahimi
ย 
On Optimal and Fair Service Allocation in Mobile Cloud Computing
On Optimal and Fair Service Allocation in Mobile Cloud ComputingOn Optimal and Fair Service Allocation in Mobile Cloud Computing
On Optimal and Fair Service Allocation in Mobile Cloud ComputingReza Rahimi
ย 
SMS Spam Filter Design Using R: A Machine Learning Approach
SMS Spam Filter Design Using R: A Machine Learning ApproachSMS Spam Filter Design Using R: A Machine Learning Approach
SMS Spam Filter Design Using R: A Machine Learning ApproachReza Rahimi
ย 
Mobile Applications on an Elastic and Scalable 2-Tier Cloud Architecture
Mobile Applications on an Elastic and Scalable 2-Tier Cloud ArchitectureMobile Applications on an Elastic and Scalable 2-Tier Cloud Architecture
Mobile Applications on an Elastic and Scalable 2-Tier Cloud ArchitectureReza Rahimi
ย 
Exploiting an Elastic 2-Tiered Cloud Architecture for Rich Mobile Applications
Exploiting an Elastic 2-Tiered Cloud Architecture for Rich Mobile ApplicationsExploiting an Elastic 2-Tiered Cloud Architecture for Rich Mobile Applications
Exploiting an Elastic 2-Tiered Cloud Architecture for Rich Mobile ApplicationsReza Rahimi
ย 
Fingerprint High Level Classification
Fingerprint High Level ClassificationFingerprint High Level Classification
Fingerprint High Level ClassificationReza Rahimi
ย 
Linear Programming and its Usage in Approximation Algorithms for NP Hard Opti...
Linear Programming and its Usage in Approximation Algorithms for NP Hard Opti...Linear Programming and its Usage in Approximation Algorithms for NP Hard Opti...
Linear Programming and its Usage in Approximation Algorithms for NP Hard Opti...Reza Rahimi
ย 
Optimizing Multicast Throughput in IP Network
Optimizing Multicast Throughput in IP NetworkOptimizing Multicast Throughput in IP Network
Optimizing Multicast Throughput in IP NetworkReza Rahimi
ย 
The Case for a Signal Oriented Data Stream Management System
The Case for a Signal Oriented Data Stream Management SystemThe Case for a Signal Oriented Data Stream Management System
The Case for a Signal Oriented Data Stream Management SystemReza Rahimi
ย 
Mobile Cloud Computing: Big Picture
Mobile Cloud Computing: Big PictureMobile Cloud Computing: Big Picture
Mobile Cloud Computing: Big PictureReza Rahimi
ย 
Network Information Processing
Network Information ProcessingNetwork Information Processing
Network Information ProcessingReza Rahimi
ย 
Pervasive Image Computation: A Mobile Phone Application for getting Informat...
Pervasive Image Computation: A Mobile  Phone Application for getting Informat...Pervasive Image Computation: A Mobile  Phone Application for getting Informat...
Pervasive Image Computation: A Mobile Phone Application for getting Informat...Reza Rahimi
ย 
Gaussian Integration
Gaussian IntegrationGaussian Integration
Gaussian IntegrationReza Rahimi
ย 
Interactive Proof Systems and An Introduction to PCP
Interactive Proof Systems and An Introduction to PCPInteractive Proof Systems and An Introduction to PCP
Interactive Proof Systems and An Introduction to PCPReza Rahimi
ย 
Quantum Computation and Algorithms
Quantum Computation and Algorithms Quantum Computation and Algorithms
Quantum Computation and Algorithms Reza Rahimi
ย 

More from Reza Rahimi (19)

Boosting Personalization In SaaS Using Machine Learning.pdf
Boosting Personalization  In SaaS Using Machine Learning.pdfBoosting Personalization  In SaaS Using Machine Learning.pdf
Boosting Personalization In SaaS Using Machine Learning.pdf
ย 
Low Complexity Secure Code Design for Big Data in Cloud Storage Systems
Low Complexity Secure Code Design for Big Data in Cloud Storage SystemsLow Complexity Secure Code Design for Big Data in Cloud Storage Systems
Low Complexity Secure Code Design for Big Data in Cloud Storage Systems
ย 
Smart Connectivity
Smart ConnectivitySmart Connectivity
Smart Connectivity
ย 
Self-Tuning Data Centers
Self-Tuning Data CentersSelf-Tuning Data Centers
Self-Tuning Data Centers
ย 
The Next Big Thing in IT
The Next Big Thing in ITThe Next Big Thing in IT
The Next Big Thing in IT
ย 
On Optimal and Fair Service Allocation in Mobile Cloud Computing
On Optimal and Fair Service Allocation in Mobile Cloud ComputingOn Optimal and Fair Service Allocation in Mobile Cloud Computing
On Optimal and Fair Service Allocation in Mobile Cloud Computing
ย 
SMS Spam Filter Design Using R: A Machine Learning Approach
SMS Spam Filter Design Using R: A Machine Learning ApproachSMS Spam Filter Design Using R: A Machine Learning Approach
SMS Spam Filter Design Using R: A Machine Learning Approach
ย 
Mobile Applications on an Elastic and Scalable 2-Tier Cloud Architecture
Mobile Applications on an Elastic and Scalable 2-Tier Cloud ArchitectureMobile Applications on an Elastic and Scalable 2-Tier Cloud Architecture
Mobile Applications on an Elastic and Scalable 2-Tier Cloud Architecture
ย 
Exploiting an Elastic 2-Tiered Cloud Architecture for Rich Mobile Applications
Exploiting an Elastic 2-Tiered Cloud Architecture for Rich Mobile ApplicationsExploiting an Elastic 2-Tiered Cloud Architecture for Rich Mobile Applications
Exploiting an Elastic 2-Tiered Cloud Architecture for Rich Mobile Applications
ย 
Fingerprint High Level Classification
Fingerprint High Level ClassificationFingerprint High Level Classification
Fingerprint High Level Classification
ย 
Linear Programming and its Usage in Approximation Algorithms for NP Hard Opti...
Linear Programming and its Usage in Approximation Algorithms for NP Hard Opti...Linear Programming and its Usage in Approximation Algorithms for NP Hard Opti...
Linear Programming and its Usage in Approximation Algorithms for NP Hard Opti...
ย 
Optimizing Multicast Throughput in IP Network
Optimizing Multicast Throughput in IP NetworkOptimizing Multicast Throughput in IP Network
Optimizing Multicast Throughput in IP Network
ย 
The Case for a Signal Oriented Data Stream Management System
The Case for a Signal Oriented Data Stream Management SystemThe Case for a Signal Oriented Data Stream Management System
The Case for a Signal Oriented Data Stream Management System
ย 
Mobile Cloud Computing: Big Picture
Mobile Cloud Computing: Big PictureMobile Cloud Computing: Big Picture
Mobile Cloud Computing: Big Picture
ย 
Network Information Processing
Network Information ProcessingNetwork Information Processing
Network Information Processing
ย 
Pervasive Image Computation: A Mobile Phone Application for getting Informat...
Pervasive Image Computation: A Mobile  Phone Application for getting Informat...Pervasive Image Computation: A Mobile  Phone Application for getting Informat...
Pervasive Image Computation: A Mobile Phone Application for getting Informat...
ย 
Gaussian Integration
Gaussian IntegrationGaussian Integration
Gaussian Integration
ย 
Interactive Proof Systems and An Introduction to PCP
Interactive Proof Systems and An Introduction to PCPInteractive Proof Systems and An Introduction to PCP
Interactive Proof Systems and An Introduction to PCP
ย 
Quantum Computation and Algorithms
Quantum Computation and Algorithms Quantum Computation and Algorithms
Quantum Computation and Algorithms
ย 

Recently uploaded

MS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectorsMS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectorsNanddeep Nachan
ย 
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Orbitshub
ย 
CNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In PakistanCNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In Pakistandanishmna97
ย 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingEdi Saputra
ย 
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...apidays
ย 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherRemote DBA Services
ย 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesrafiqahmad00786416
ย 
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...apidays
ย 
[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdfSandro Moreira
ย 
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...apidays
ย 
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdfRising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdfOrbitshub
ย 
DBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDropbox
ย 
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWEREMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWERMadyBayot
ย 
Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxRustici Software
ย 
Ransomware_Q4_2023. The report. [EN].pdf
Ransomware_Q4_2023. The report. [EN].pdfRansomware_Q4_2023. The report. [EN].pdf
Ransomware_Q4_2023. The report. [EN].pdfOverkill Security
ย 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MIND CTI
ย 
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...apidays
ย 
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ..."I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...Zilliz
ย 
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Victor Rentea
ย 

Recently uploaded (20)

MS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectorsMS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectors
ย 
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
ย 
CNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In PakistanCNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In Pakistan
ย 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
ย 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
ย 
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
ย 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
ย 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challenges
ย 
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
ย 
[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf
ย 
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
ย 
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdfRising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
ย 
DBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor Presentation
ย 
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWEREMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
ย 
Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptx
ย 
Ransomware_Q4_2023. The report. [EN].pdf
Ransomware_Q4_2023. The report. [EN].pdfRansomware_Q4_2023. The report. [EN].pdf
Ransomware_Q4_2023. The report. [EN].pdf
ย 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024
ย 
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
ย 
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ..."I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
ย 
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
ย 

Self-Tuning and Managing Services

  • 1. Self-Tuning and Managing Services Reza Rahimi, PhD. Principal Staff Algorithm and Software Architect, Huawei R&D (Futurewei) Cloud Storage Lab (Global CTO Office), Santa Clara, USA. R&D
  • 2. Self-Tuning and Managing Services Related Recent R&D Experience 2 QoE-Aware smart home wireless network management and optimization. SLA-Aware intelligent cloud management and optimization. R&D PhD Topic: QoS-Aware resource management in mobile cloud computing. Optimal Algorithm Design R&D Low complexity secure code for big data in cloud storage. 5+ Years R&D
  • 3. 3 PhD. Thesis: โ€œQoS-Aware Middleware for Optimal Service Allocation in Mobile Cloud Computing : An Opportunistic Approach to Internet of Thingsโ€ Initial Core Idea The Next Big Thing
  • 4. 4 Mobile Cloud Computing (MCC) Ecosystem M. Reza Rahimi, Jian Ren, Chi Harold Liu, Athanasios V. Vasilakos, and Nalini Venkatasubramanian, "Mobile Cloud Computing: A Survey, State of Art and Future Directions", in ACM/Springer Mobile Application and Networks (MONET), Special Issue on Mobile Cloud Computing, Nov. 2014 (cited : 210+). Tier 1: Public Cloud (+) Scalable, Elastic, Available (+) Fault Tolerant (-) Price, Delay, Privacy and Security Tier 2: Local/Private Cloud (+) Low Delay, Low Power, (+) Privacy and Security, (- ) Limited Capacity, IBM: by 2018 61% of enterprise would be on tiered cloud Wired and Wireless Network Providers Local and Private Cloud Providers Devices, Users ,Apps and Sensors Public Cloud Providers Content and Service Providers Heavy Reading predicts that the direct revenue of mobile cloud market will grow to about 68 billion $ by 2018.
  • 5. 5 Problem Statement Context as a Service: ex: Mobility patterns, Service Usage in different location and time, Group-Aware, Social Context, โ€ฆ Network as a Service: ex: Wireless connectivity (Wi-Fi, 3G/4G/5G, Bluetooth,โ€ฆ) Computation /Storage as a Service (2-Tier): ex: computation, Storage, Platform,.. QoS-Aware Optimal service allocation for mobile users based on important criteria like: Delay Power Price
  • 6. 6 Outline โ€ข Location-Time Workflow โ€ข QoS and Normalization โ€ข Group/Single Mobile Applications, Fairness Utility Problem Formulation โ€ข Simulated Annealing Approach โ€ข Greedy Approach โ€ข Genetic Algorithm Approach โ€ข Scalability Mobility-Aware Service Allocation Algorithms โ€ข Orchestrating all Components in MAPCloud SOA Architecture. Middleware Architecture โ€ข Performance Results of the Algorithms Experimental Results
  • 7. 7 Modeling Services in MCC โ€ข Applications/System Queries could be modeled as the Workflow. โ€ข It consists of number of logical steps known as a Service with different composition patterns: S1 S2 S4 S3 S5 S7 S8 S6 0 1 Par1 Par2 3 Start End S1 S2 S3 S1 S2 S4 S3 S1 S1 S2 S4 S3 SEQ LOOP AND: CONCURRENT FUNCTIONS XOR: CONDITIONAL FUNCTIONS k 1 1 P1 P2 ๐‘ท๐Ÿ + ๐‘ท๐Ÿ = ๐Ÿ, ๐‘ท๐Ÿ, ๐‘ท๐Ÿ โˆˆ {๐ŸŽ, ๐Ÿ}
  • 8. 8 t1 t2 t4 t3 tN l2 l1 l3 ln W1 Wk+1 Wk Wj+1 Wj Location-Time Workflow โ€ข It could be formally defined as: ๐‘พ(๐’–๐’Œ)๐šป ๐‘ณ โ‰ (๐’˜ ๐’–๐’Œ ๐’•๐’Ž๐Ÿ ๐’๐’๐Ÿ , ๐’˜ ๐’–๐’Œ ๐’•๐’Ž๐Ÿ ๐’๐’๐Ÿ ,โ€ฆ.,๐’˜ ๐’–๐’Œ ๐’•๐’Ž๐’Œ ๐’๐’๐’Œ ) Location-Time Workflow M. Reza. Rahimi, Nalini Venkatasubramanian, Sharad Mehrotra, Athanasios Vasilakos, "On Optimal and Fair Service Allocation in Mobile Cloud Computing", in IEEE Transaction on Cloud Computing, 2015.
  • 9. 9 Quality of Service (QoS) ๐’’(๐’–๐’Œ ๐’”๐’Š,๐’๐’‹,๐’•๐’Ž)๐’‘๐’๐’˜๐’†๐’“ power consumed on u cellphone when he is in location l at t using s . โ€ข The QoS could be defined in two different Levels: โ€ข Atomic service level โ€ข Composite service level or workflow level. โ€ข Atomic service level could be defined as (for power as an example): โ€ข The workflow QoS is based on different patterns. QoS SEQ AND (PAR) XOR (IF-ELSE-THEN) LOOP ๐‘พ๐’‘๐’๐’˜๐’†๐’“ ๐’’(๐’–๐’Œ ๐’”๐’Š,๐’๐’‹,๐’•๐’Ž)๐’‘๐’๐’˜๐’†๐’“ ๐’Š ๐’ ๐’Š ๐Ÿ ๐’’(๐’–๐’Œ ๐’”๐’Š,๐’๐’‹,๐’•๐’Ž)๐’‘๐’๐’˜๐’†๐’“ ๐’Š ๐’ ๐’Š ๐Ÿ ๐’Ž๐’‚๐’™ ๐’Š ๐’’(๐’–๐’Œ ๐’”๐’Š,๐’๐’‹,๐’•๐’Ž)๐’‘๐’๐’˜๐’†๐’“ ๐’’(๐’–๐’Œ ๐’”๐’Š,๐’๐’‹,๐’•๐’Ž)๐’‘๐’๐’˜๐’†๐’“ ร— ๐’Œ Shivajit Mohapatra, M Reza Rahimi, Nalini Venkatasubramanian, Handbook of Energy-Aware and Green Computing-Two Volume Set, CRC Press Taylor & Francis Group, 2012 (cited :100+).
  • 10. 10 โ€ข As it can be understood different QoSes have different dimensions (Price->$, power->joule, delay->s) โ€ข We need the normalization process to make them comparable. QoS Normalization ๐‘พ(๐’–๐’Œ)๐œฏ ๐‘ณ ๐’‘๐’๐’˜๐’†๐’“ โ‰ ๐‘พ(๐’–๐’Œ)๐œฏ ๐‘ณ ๐’‘๐’๐’˜๐’†๐’“ ๐’Ž๐’‚๐’™ โˆ’ ๐‘พ(๐’–๐’Œ)๐œฏ ๐‘ณ ๐’‘๐’๐’˜๐’†๐’“ ๐‘พ(๐’–๐’Œ)๐œฏ ๐‘ณ ๐’‘๐’๐’˜๐’†๐’“ ๐’Ž๐’‚๐’™ โˆ’ ๐‘พ(๐’–๐’Œ)๐œฏ ๐‘ณ ๐’‘๐’๐’˜๐’†๐’“ ๐’Ž๐’Š๐’ , ๐‘พ(๐’–๐’Œ)๐œฏ ๐‘ณ ๐’‘๐’๐’˜๐’†๐’“ ๐’Ž๐’‚๐’™ โ‰  ๐‘พ(๐’–๐’Œ)๐œฏ ๐‘ณ ๐’‘๐’๐’˜๐’†๐’“ ๐’Ž๐’Š๐’ ๐Ÿ, ๐’†๐’๐’”๐’† ๏ƒผ The normalized power, price and delay is the real number in interval [0,1]. ๏ƒผ The higher the normalized QoS the better the execution plan is.
  • 11. 11 ๐’Ž๐’‚๐’™ ๐Ÿ |๐‘ผ| ๐’Ž๐’Š๐’ ๐‘พ(๐’–๐’Œ)๐šป ๐‘ณ ๐’‘๐’๐’˜๐’†๐’“ , ๐‘พ(๐’–๐’Œ)๐šป ๐‘ณ ๐’‘๐’“๐’Š๐’„๐’† , ๐‘พ(๐’–๐’Œ)๐šป ๐‘ณ ๐’…๐’†๐’๐’‚๐’š ๐’–๐’Œ ๐‘บ๐’–๐’ƒ๐’‹๐’†๐’„๐’• ๐’•๐’: ๐Ÿ |๐‘ผ| ๐‘พ(๐’–๐’Œ)๐šป ๐‘ณ ๐’‘๐’๐’˜๐’†๐’“ โ‰ค ๐‘ฉ๐’‘๐’๐’˜๐’†๐’“, ๐Ÿ |๐‘ผ| ๐‘พ(๐’–๐’Œ)๐šป ๐‘ณ ๐’‘๐’“๐’Š๐’„๐’† โ‰ค ๐‘ฉ๐’‘๐’“๐’Š๐’„๐’†, ๐Ÿ |๐‘ผ| ๐‘พ(๐’–๐’Œ)๐šป ๐‘ณ ๐’…๐’†๐’๐’‚๐’š โ‰ค ๐‘ฉ๐’…๐’†๐’๐’‚๐’š, ๐œฟ โ‰ค ๐‘ช๐’‚๐’‘(๐‘ณ๐’๐’„๐’‚๐’_๐‘ช๐’๐’๐’–๐’…๐’”) ๐œฟ โ‰œ ๐‘ต๐’–๐’Ž๐’ƒ๐’†๐’“ ๐’๐’‡ ๐’Ž๐’๐’ƒ๐’Š๐’๐’† ๐‘ผ๐’”๐’†๐’“๐’” ๐’–๐’”๐’Š๐’๐’ˆ ๐’”๐’†๐’“๐’—๐’Š๐’„๐’†๐’” ๐’๐’ ๐’๐’๐’„๐’‚๐’ ๐’„๐’๐’๐’–๐’… โˆ€ ๐’–๐’Œ โˆˆ ๐’–๐Ÿ, โ€ฆ , ๐’–|๐‘ผ| โ€ข In this optimization problem our goal is to maximize the minimum saving of power, price and delay of the mobile applications. Optimal Service Allocation for Single Mobile User
  • 12. 12 ๐’Ž๐’‚๐’™ ๐Ÿ |๐‘ฎ| ๐Ÿ |๐’ˆ๐’Š| ๐’Ž๐’Š๐’ ๐‘พ(๐’–๐’Œ)๐šป ๐‘ณ ๐’‘๐’๐’˜๐’†๐’“ , ๐‘พ(๐’–๐’Œ)๐šป ๐‘ณ ๐’‘๐’“๐’Š๐’„๐’† , ๐‘พ(๐’–๐’Œ)๐šป ๐‘ณ ๐’…๐’†๐’๐’‚๐’š ๐’–๐’Œโˆˆ๐’ˆ๐’Š ๐’ˆ๐’Šโˆˆ๐‘ฎ ๐‘บ๐’–๐’ƒ๐’‹๐’†๐’„๐’• ๐’•๐’: ๐Ÿ |๐’ˆ๐’Š| ๐‘พ(๐’ˆ๐’Š)๐šป ๐‘ณ ๐’‘๐’๐’˜๐’†๐’“ โ‰ค ๐‘ฉ๐’‘๐’๐’˜๐’†๐’“, ๐Ÿ |๐’ˆ๐’Š| ๐‘พ(๐’ˆ๐’Š)๐šป ๐‘ณ ๐’‘๐’“๐’Š๐’„๐’† โ‰ค ๐‘ฉ๐’‘๐’“๐’Š๐’„๐’†, ๐Ÿ |๐’ˆ๐’Š| ๐‘พ(๐’ˆ๐’Š)๐šป ๐‘ณ ๐’…๐’†๐’๐’‚๐’š โ‰ค ๐‘ฉ๐’…๐’†๐’๐’‚๐’š, ๐œฟ โ‰ค ๐‘ช๐’‚๐’‘(๐‘ณ๐’๐’„๐’‚๐’_๐‘ช๐’๐’๐’–๐’…๐’”) ๐œฟ โ‰œ ๐‘ต๐’–๐’Ž๐’ƒ๐’†๐’“ ๐’๐’‡ ๐’Ž๐’๐’ƒ๐’Š๐’๐’† ๐‘ผ๐’”๐’†๐’“๐’” ๐’–๐’”๐’Š๐’๐’ˆ ๐’”๐’†๐’“๐’—๐’Š๐’„๐’†๐’” ๐’๐’ ๐’๐’๐’„๐’‚๐’ ๐’„๐’๐’๐’–๐’… โˆ€ ๐’–๐’Œ โˆˆ ๐’–๐Ÿ, โ€ฆ , ๐’–|๐‘ผ| โˆ€ ๐’ˆ๐’Š โˆˆ ๐’ˆ๐’Š, โ€ฆ , ๐’ˆ|๐‘ฎ| These optimization problems are NP-Hard (Knapsack is the special case) so we look for heuristic/Approximation to solve them. Optimal Service Allocation for Mobile/Social Groups
  • 13. 13 Service Allocation Algorithms for Single Mobile User and Mobile Group-Social Applications Brute-Force Search (BFS) MuSIC Genetic Based Greedy Based (Different Policies) Random Service Allocation (RSA) โ€ข We start with our main one, which we call it MuSIC: Mobility Aware Service AllocatIon on Cloud. โ€ข Its core is based-on simulated annealing approach. M. Reza. Rahimi, Nalini Venkatasubramanian, Athanasios Vasilakos, "MuSIC: On Mobility-Aware Optimal Service Allocation in Mobile Cloud Computing", In the IEEE 6th International Conference on Cloud Computing, (Cloud 2013), Silicon Valley, CA, USA, July 2013 (cited : 110+). Mobility-Aware Service Allocation Algorithms on 2-Tier Cloud
  • 14. 14 ๏ƒผ Partition mobile users and local clouds based on their proximities and run service allocation algorithms for each region in parallel (using clustering techniques). Public Cloud Local Cloud Local Cloud Local Cloud Local Cloud Local Cloud Local Cloud Local Cloud Scaling Out MuSIC : Simplified
  • 15. 15 Service 1 Service n Mobile Users Pig Latin pseudo codes: /*Load Data*/ LOAD mobile users , servicesโ€ฆ. /*Cartesian product to produce solution space*/ CROSS Mobile users, Service1,โ€ฆ /*Apply Optimization Constraints to solution space */ FILTER by Constraints1,โ€ฆ /*Find Best Solution*/ FOREACH Mobile User GENERATE utility value GROUP Solution By Mobile Users FOREACH Solution GENERATE MAX Apply System Constraints Compute UTILITY FUNCTION of each solution for Mobile Users GROUP Solutions for each Mobile Users Find the MAXIMUM UTILITY for each Mobile Users and emit as the best solution Scalable Brute-Force Search Using Big Data Processing (Apache Pig)
  • 16. 16 QoS-Aware Service DB Mobile User Log DB Optimal Service Scheduler Cloud Service Registry Mobile Client MAPCloud Web Service Interface MAPCloud Runtime Local and Public Cloud Pool MAPCloud LTW Engine MAPCloud Web Service Interface MAPCloud SOAArchitecture MAPCloud Video Demo M. Reza. Rahimi, Nalini Venkatasubramanian, Sharad Mehrotra and Athanasios Vasilakos, "MAPCloud: Mobile Applications on an Elastic and Scalable 2-Tier Cloud Architecture", In the 5th IEEE/ACM International Conference on Utility and Cloud Computing (UCC 2012), USA, Nov 2012 (cited : 110+)
  • 17. 17 Experimental and Simulation Results: Mobile Applications Benchmarks OCR+ Speech (OCRS): Video Augmented Reality (VAR): You Tube Link Multimedia File Sharing (MFS): Mobile Apps Processing Storage Bandwidth Social Application OCRS ร— ร— VAR ร— ร— ร— MFC ร— ร— ร— ร—
  • 18. 18 Simulation Setup Amazon EC2,S3 Local Cloud 1 Local Cloud 5 Local Cloud 2 Local Cloud 7 Local Cloud 4 Local Cloud n S1 . . . Sn S1 . . . Sn S1 . . . Sn S1 . . . Sn S1 . . . Sn large instance: equivalent to a PC with 7.5GB of memory, 850 GB of storage Local Cloud: 64bit Windows dual- core server, with 8GB of memory and 500GB of storage. LAN Speed Profiling sample applications has been used to tune the system Environment. Java Network simulator (JNS) and CloudSim used for modeling the delay between Local clouds. RWP and Manhattan mobility models are used as the mobility models (V[0/ms-10/ms]). We also add some error in mobility models to check the robustness of service allocation algorithms.
  • 19. 19 Performance Results MuSIC, Genetic, Greedy, RSA and G-MuSIC (5-Groups) algorithms average throughput with uncertainty in LTW prediction in the range of [0%,30%]
  • 20. 20 Scalability Studies RSA-Par/Pig-Based MuSIC-Par/Pig-Based Greedy-Par/Pig-Based GA-Par/Pig-Based Single 48% 79% 65% 70% Group 47% 74% 62% 68% Settings: 10,000 mobile users, uniformly distributed, 6 different services per mobile users and for each service we have 10 different candidates (on local or public cloud) # of local clouds: 50 , uniformly distributed # public cloud :10 amazon Large instance. In general our parallel version of our algorithm is ~4 times faster Than Pig-based distributed version.
  • 21. 21 QoE-Aware smart home wireless network management and optimization.
  • 22. 22 SMART Connectivity Solution Providing innovative means of connecting devices and things through new connectivity paradigm. 2018 Need for a โ€œIntelligentโ€ Networking 2014 Growing โ€œConnected Life โ€œ Better Coverage Higher Throughput Lower Interference Lower Power/Energy Bad Coverage Low Throughput High Interference High Power/Energy Problem
  • 23. 23 Ambient Network Sensing UX Network Devices Apps Vertical Handoffs (VHOs) Analytics Interference Battery Life Service Cost Context-aware Connectivity Context Aware Handoffs Predict Quality of Experience QoE Modeling Outcome Core Enabler Services
  • 24. 24 SMART Connectivity Service Diagram Ambient network and application sensing RSSI Link Speed YouTube Event Listener App ANS Profiler 647 sec QoE Analytics Sample Predicated 0.425 17 events/sec -85 dBm 1 Mbps 1.9 1 2 Objective Context 3 5 QoE Scale : 1 for โ€œPoorโ€ to 5 for โ€œExcellentโ€ Decision Tree QoE Heat Maps 2.9 1.9 1.2 Initial Buffering Time Buffering Ratio Buffering Frequency QoE for WiFi1 QoE for WiFi2 QoE for BT Connect to WiFi1 6 4 With Technology Usage we Got : -- increase users QoE (MOS Score) and userโ€™s engagement up to 30%, -- energy consumption reduction on smart devices up to 2x, -- reduce delay and buffering time up to 4x
  • 25. 25 Got Technology transfer to Samsung New Acquired Company : SmartThings ๏ƒ˜ Sensing Dongle, ๏ƒ˜ MIH IEEE 802.21 Implementation on Linux Kernel
  • 26. 26 SLA-Aware intelligent cloud management and optimization R&D M. Reza. Rahimi, โ€œSelf-Tuning Data Centersโ€, Big Data Innovation Summit, Las Vegas, 2017, (Keynote Talk).
  • 27. 27 Applications Spectrum Computing (CPU , GPU, DSP, FPGA,...) Storage (DRAM, SSD, HDD,..) Network (Wired, Wi-Fi, 4G,โ€ฆ) Self-Driving Cars Robotic/AI Applications Data Management Systems Video Streaming/IoT,โ€ฆ These applications will be fully or partially supported by Data Centers Services (Cloud-Based)
  • 28. 28 Typical Data Center Architecture As a simple rule of thumb: Enterprise Data Center Size : 100 Hosts 1000 VMs ~Logs : 40 GB/Day Data Center Management VM-1-k VM-1-1 VM-2-1 VM-2-m VM-n-1 VM-n-l Host 1 Host 2 Host n logs logs logs Storage Pool Big Data Engineering and Science Apps are running on VMs
  • 29. 29 Some Data Center Management Challenges/Opportunities Service Level Agreement (SLA) : Throughput/Latency (e-commerce applications): โ–บ 2014 US $304 billion increasing 15.4% yearly in e-commerce, โ–บ 100ms latency costs 1% decrease in sale, โ–บ Page loading should be less than 2 seconds per page not to lose customer, will decrease overall sales by 7%, Resource Utilization (Capacity Planning) : โ–บ ~ 90 percent of the VMs utilizes < 15% of assigned Cores/Storage, โ–บ ~ 90 percent of the VMs only have < 10 IOPS, Scalable and Elastic (on Demand) : โ–บ Should know when and how to scale to satisfy SLA dynamically,
  • 30. 30 Energy Efficiency : โ–บ By 2020 reduction of energy cost 30% based on European law-Green DC, โ–บ US data centers consume ~ 90 billion Kilowatt hours annually = House hold in NY for two years โ–บ Pollute over 150 million tons of carbon yearly in USA, โ–บ Average server runs on [12%-18%] of their capacity most of the time still consuming 30% to 60% of their maximum power consumption. โ–บ High utilization -> save in power consumption->Low carbon footprint Dynamic Service Pricing : โ–บ Computing, network and storage are utilities for workloads. โ–บ Should model to find a dynamic way and good policy of pricing in competitive market of cloud providers while increasing revenue/profit. Some Data Center Management Challenges/Opportunities
  • 31. 31 Software Compliance and License : โ–บ ~ $500,000 spent on software licensing for average size data center, โ–บ It could be per User/Device/VM/Core/โ€ฆ โ–บ Different models and policies for license like: 1) Running licensed workload on bare metal (no virtualization), 2) Running licensed workload on dedicated cluster, 3) Migrate licensed workload, 4) โ€ฆ โ–บ Workloads and cluster growth bring challenges for software license, โ–บ This bring the challenge how to minimize the cost of software on data centers and not violate license policy, Some Data Center Management Challenges/Opportunities
  • 32. 32 Self-Tuning Data Center : Simplified Service Flow VM Scheduling and Orchestrating Services and Resources Real-time Log and Monitoring Service Watcher and Policy Service Recommendation /Prediction Service 2) Ask correct size, type And location for resource Based on request 1) Request resource 3) Correct conf and resource size and place 4) Allocate required resources 1) Telemetry and log sending 2) Query logs for policy and alert checks 4) Check for violation and warnings 5) Alert of Violation 6) Ask for Recommendation 7 ) Send Recommendations and Recipes 8 ) Apply Recommendation Initial State Operational and Recovery State 1 ) Ask Recommendation For Self-Tune (for example in low traffic state) 2) Send Tuning Plan and Recommendation (like VM migration or resizing) 3 ) Apply Self-Tuning recommendation Self-Tuning State 3) Collected Data -- Resource Sizing Tool, -- Time Series Prediction (CAP/PERF(IOPS/LAT)), -- Anomaly detection, -- Performance Prediction -- Simulation, -- โ€ฆ
  • 33. 33 Got Technology transfer to Huawei eService (๏ƒ Huawei OceanStor DJ) ๏ƒ˜ Scalable, Reliable and Available Telemetry Platform, ๏ƒ˜ Modeling as a Service : -- Storage Required Capacity Prediction, -- Performance Prediction (IOPS/LAT/BW), -- CACHE Sizing tool for OLTP/VDI/Exchange, -- โ€ฆ
  • 34. 34 Low Complexity Secure Code for Big Data in Cloud Storage Systems R&D Mohsen Kiskani, Hamid Sadjadpour, M. Reza Rahimi, Fred Etemadieh, "Low Complexity Secure Code (LCSC) Design for Big Data in Cloud Storage Systems", in IEEE ICC, Kansas City, MO, USA, May 2018.
  • 35. 35 Data Reliability Data Security and Privacy Data Replication or Coding Encryption/ Decryption Current Industry Approach Data Reliability + Security and Privacy Hybrid Codes Increased processing speed by ~400%, 100% security in data (SLA), No more need to use https, PIR (Private Information Retrieval),
  • 36. 36 Both Encoding and Decoding will be simple/cheap XOR operations. Encoding: y1 = x3 โจ x4 y2 = x1 โจ x3 y3 = x1 โจ x2 y4 = x2 โจ x3 โจ x4 Decoding: x1 = y1 โจ y3 โจ y4 x2 = y1 โจ y4 x3 = y1 โจ y2 โจ y3 โจ y4 x4 = y2 โจ y3 โจ y4 Sample Encoding and Decoding y1 y2 y3 y4 y1 y2 y3 y4 x1 x2 x3 x4 x1 x2 x3 x4 Property Repetition / RAID Erasure / MDS Proposed Coding Storage overhead Significant Very Small Very Small Reparability Possible Possible Possible Security Need Encryption Need Encryption No Encryption Computational Complexity comparing encryption Low high Very Low
  • 37. 37 โ€ข Step 1 : User requests file B1 and sends the decoding instructions to the storage unit, โ€ข Step 2 : Storage unit combines the encoded files using the decoding instructions in the storage processing unit, โ€ข Step 3 : Storage unit transmits the result to the user, โ€ข Step 4 : User combines the received data with its own encoded files and creates B1, C1 C2 C3 C4 C5 C6 C7 C8 C9 C10 C11 C12 Storage Unit User New Encoding Scheme Original Data B1 B2 B3 B4 B5 B6 ๐šบ giCi + g13 C13 + g14 C14+ g15 C15 = B1 Decoding Instructions C13 C15 C14 ๐šบ giCi Storage Processing Service (1) (2) (3) (4) Service Architecture and Data Retrieval Process
  • 38. Conclusion and Future Directions ๏ƒผ Self-tuning and managing services in different application domains and context. ๏ƒผ Architectural and algorithmic patterns that those systems have in common and some best practices to solve them. ๏ƒผ More things (physical/virtual) are connected together, physically/virtually/semantically. ๏ƒผManaging this environment is very challenging for human, need a way to have autonomous system with low human interaction. ๏ƒผAI/ML/DL and big data processing tools are some of the best industrial practices to tackle these problems. ๏ƒผ We are in the beginning era of Web 4.0 : Self-tuning and managing web. 38