Currently there is increasing interest in scientific research on network traffic management for advanced scenarios (e.g. Internet of Everything (IoE), Everything as a Service (XaaS), Smart Cities, and the like) and their respective demands for novel network services. Such networked applications bring massive amounts of traffic data to be processed in real-time, thus driving researchers to develop affordable yet efficient network management systems. In fact, new paradigms, services, and architectures, such as Network Virtualization (NV), Software-Defined Networking (SDN), Distributed Cloud Computing, Network Functions Virtualization (NFV), Service Function Chaining (SFC), etc, will require robust and dynamic capabilities to support a myriad of possibilities for applications from the IoE and XaaS concepts. For example, there is a need for an in-depth understanding of the composition and the dynamics of Internet traffic to perform accurate capacity planning, deploy efficient management policies and pricing strategies, assess protocol performance, and detect abnormalities in such scenarios. Research on measurement, modeling, and analysis of network traffic and infrastructure always face new challenges as new applications are continuously deployed.
In this talk, I will discuss the rise of IoE and XaaS as well as the demand for advanced networking services, paradigms, and architectures (e.g., SDN, NFV). I will give an overview of some challenges, opportunities, and directions in these research topics.
Research Challenges and Opportunities in the Era of the Internet of Everything and Everything as a Service
1. Research Challenges and
Opportunities in the Era of the
Internet of Everything and
Everything as a Service
April 2015
Carleton University - ARS-Lab
Stenio Fernandes
CIn/UFPE, Recife, Brazil
2. Agenda
A bit of technical background
Advanced Networking Architectures
Advanced Scenarios
Internet of Everything (IoE)
Everything as a Service (XaaS)
Smart Cities and Urban Services
Supporting Tools and Techniques
Applied Research
Research Challenges and Opportunities
My R&D Agenda
5. NV: concepts
What is NV?
Decoupling of the services provided by a
(virtualized) network from the physical network
Virtual network is a “container” of network services
(L2 -L7) provisioned by software
Faithful reproduction of services provided by
physical network
Analogy to a VM – complete reproduction of physical
machine (CPU, memory, I/O, etc.)
11. SDN – Motivation
Current networks cannot support this growth!
-Not service-oriented
-Static configuration
-Status not available to apps/users
-Cannot provide dynamic negotiation to users
13. The Need for a New Network
Architecture (The ONF view)
key computing trends:
Changing traffic patterns
contrast to client-server applications
today’s apps access different services
access to content and applications from any type of device, anywhere,
at any time
The rise of cloud services
agility to access applications, infrastructure, and other IT resources on
demand and à la carte
Big data means more bandwidth
Mega datasets is fueling a constant demand for additional network
capacity in the data center
14. Limitations of Current Networking
Technologies (The ONF View)
Meeting current market requirements using device-level
management tools and manual processes
Complexity that leads to stasis
The static nature of networks is in contrast to the dynamic nature of
today’s environment
Inconsistent policies
To implement a network-wide policy, thousands of devices and
mechanisms must be configured
Inability to scale
traffic patterns are dynamic and unpredictable
users with different apps and performance needs
15. SDN (the ONF view)
Emerging network architecture where network
control is decoupled from forwarding and is directly
programmable
can treat the network as a logical or virtual entity
Network intelligence is (logically) centralized
SDN controllers maintains a global view of the network
Network appears to the applications and policy
engines as a single, logical switch
infrastructure gains vendor-independent control over the
entire network from a single logical point
18. Motivation: what drives SDN R&D?
Reduced network costs (CAPEX / OPEX)
Support to Innovative New Products (applications,
services)
Synergy with Cloud Computing Services and
Infrastructure
And most importantly: Real time network
programmability
This is the quest for networks with improved performance
while keeping them simple, scalable, and “ smart”
19.
20. A Simplified View of SDN
1. A network in which the control plane is physically separate
from the forwarding (data) plane
• A single control plane controls several forwarding devices
21. Supporting SDN with OpenFlow
First standard communications interface for SDN
between the control and forwarding layers
It allows direct access to and manipulation of the forwarding
plane of network devices
OpenFlow IS NOT SDN!
22. OF-based SDN Benefits
SDN-based orchestration and management tools
to quickly deploy, configure, and update devices across the entire network
Reduced complexity through automation
develop tools that automate many management tasks
Higher rate of innovation
Allowing operators to program and reprogram the network in real time
Increased network reliability and security
More granular network control
apply policies at a very granular level
Better user experience
Centralized network control and state information
available to higher-level applications
25. Consequences of SDN adoption
1. Hardware and Software from different vendors
2. Simplified Programmability
3. Enable application-level control/programming of
network
4. Enables centralized control, which implies
simplification of network operations
5. Prospective integration with Network Virtualization
technologies (cf. previous section)
29. NFV: Definition
Internet Research Task Force (IRTF): “network
architecture concept that proposes using
virtualization related technologies, to virtualize
entire classes of network node functions into building
blocks that may be connected, or chained, together
to create communication services”
transform the traditional operator networks by evolving
standard virtualization technology
consolidate network equipment types onto industry
standard high volume services, switches and storage
located in a variety of NFV Infrastructure Point of
Presences (NFVI PoPs)
30.
31.
32. NFV: Terminology
NF: Network Function
A functional building block within an operator's
infrastructure
It has well-defined external interfaces and behavior
Network Function Consumer
NFV: NFV-Enabled Equipment
commodity equipment to replace the dedicated
hardware boxes for the network functions
Network Function Provider: a Network Function
Provider (NFP) provides virtual network function
software
33. NFV: Terminology
NFVI: NFV Infrastructure
computing, storage and network resources to
implement the virtual network function
VNF: Virtual Network Function
an implementation of an executable software program
whole or part of an NF that can be deployed in a NFVI
34. NFV: Requirements
Portability: VNF mobility across different
but standard multi-vendor environment
moving a VNF within the NFV framework
with the Service Level Specification (SLA)
requirements including performance,
reliability and security could be a challenge
Performance: Virtualization adds
additional processing overhead and
increases the latency
35. NFV: Requirements
Elasticity: scaling with the SLA
requirements
Resiliency: service availability and fault
management
Security and Service Continuity:
restoration of any ongoing data sessions
should be transparent to the user of NFV
service
36. NFV: Use Cases
Network Function Virtualization Infrastructure as a
Service (NFVIaaS)
Generic IaaS plus NaaS requirement which allows the
telecom operator to build up a VNF cloud on top of their
own DCs Infrastructure
Virtual Network Function as a Service (VNFaaS)
allows the enterprise to merge and/or extend its specific
services / applications into a 3rd party commercial DC
provided by a telecom operator
Virtual Network Platform as a Service (VNPaaS)
37. NFV: Use Cases
Telecom Network Functions Migration
Mobile Core Network functions
IMS functions
Mobile base station functions
Content Delivery Networks (CDN) functions
Home Environment functions
Fixed Access Network functions
42. Everything IS a Service Now
Classic
Software (SaaS)
Platform (PaaS)
Infrastructure (IaaS)
Network Related
Classification (CaaS), Deep Packet Inspection (DPIaaS)
Botnets (BaaS)
Processing Related
Analytics (AaaS)
Intelligence (InaaS)
The list of *aaS is huge and it is growing fast
50. Measurements and Analysis
Formulation of Optimization Problems
Dependability Analysis
Applied Game Theory
Control Theory
…
Supporting Tools and Techniques
51. Measurements
Packet
• More detailed: from link to application layer (with
timestamps)
• Huge storage and processing requirements
• Header or payload (full or partial)
Flow
• Flow summaries
• connection info, number of packets, duration,
volume
• IPFIX/CISCO’s NetFlow v5/v9 records
Aggregate
• SNMP counts
54. Analysis of Packet Traces
IP header
• Traffic volume by IP addresses or ASes
• Burstiness of the stream of packets
• Packet properties (e.g., sizes, out-of-order)
Transport
header
• Traffic breakdown by protocol
• TCP congestion and flow
control
• Number of bytes and packets
per session
Application
header
• URLs, HTTP headers, file type
• DNS queries and responses,
• mobile devices
54
55. REGEX to DFA to DPI Systems
• it’s possible to identify patterns (signatures)
present in the app messages
• Deep Packet Inspection (DPI) systems
• App signatures may be represented by
Regular Expressions (RegEx)
• ReGex may be represented as Finite
Automatons (NFA or DFA)
From the collected data: Packet
payload
58. Core Modelling
• maximize insight into the data set
• extract important variables
• detect outliers and anomalies
• develop parsimonious models
Exploratory
Data
Analysis
• Does the data follow a particular PDF?
• Maximum Likelihood Estimation
• Hypothesis testing
Statistics
Inference
60. Research Challenges and
Opportunities (RCO) - General
IoE, Smart Cities Platforms, and
XaaS
Network Functions Virtualization
/ Service Function Chaining
Virtual Networks / SDN
Optimizations of Canonical
Network Elements and Services
61. Research Challenges and Opportunities
(RCO) - General
Cloud Computing Services promoted huge changes in the
computer networking field
Distributed and hybrid clouds are a reality
Moving massive amount of data to be moved
SDN seems to be a smart solution to address scalability and
other issues for Big Data
NV is available as the supporting technology
IoE and Smart Cities face barriers to full deployment
Opportunities for advanced research is everywhere in those
new scenarios
62. RCO #1: Measurements
Network-wide view
Crucial for
evaluating control
actions
Multiple kinds of
data from multiple
locations
Large scale
Large number of
high-speed links
and routers
Large volume of
measurement data
The “do no harm”
principle (passive
measurements)
Don’t degrade
router performance
Don’t require disabling
key router features
Don’t overload the
network with
measurement data
62
63. RCO #2: Packet Measurements
Building efficient
DPI engines
• 1 packet every 5ns!!!
• Based on DFA/NFA
from regular
expressions that
express application
signatures
• For hardware-based
or commodity
platforms
Update of app
signatures database
• Encrypted traffic is
not possible
• Analysis of packet
payload forbidden in a
number of countries
64. RCO #3: High-Performance Traffic Monitoring
Systems in Virtualized Environments
Large number
of application
signatures
Complexity of
the signature
patterns
Unpredictability of
signature location in
the network flow, as
well as within the
packet payload
Performance
bottlenecks at
Virtualization
levels
65. RCO #4 - SDN/NFV
Elasticity in Distributed Clouds/SDN/NFV
accommodate the increased traffic in a fine-grained manner
VNF was not designed for scaling up/down
SFC considering Dependability Parameters
Optimization of VNF Forwarding Graph
placement problem
Consider multiple stateful and stateless VNF functions
Elasticity in NFV+SDN with Predictable Performance
Elasticity with Reliability
Network Performance
Instantiation and migration of virtual appliances
66. RCO #4 - SDN/NFV
XaaS on top of SDN/Network Virtualization
Infrastructures
67. RCO #4 - SDN/NFV
Northbound (apps) to Southbound (devices)
Understanding of Traffic Patterns
Needs precise classification systems
Needs model building
At high-speed
Real-time
Adapt to abrupt and long-term changes
Cope with millions to billions of flows in short-term
Core challenge: decide which service policy to be
applied to a flow (Classification and optimization
problem)
68. RCO #4 - SDN/NFV
SDN Architecture Design
accommodating consistency, dependability, and scalability
requirements
control plane: centralized or distributed processing?
controller placement problem
How many? Where to place them? How to distribute tasks?
Maximizing fault tolerance and dependable infrastructure
to support high-performance intra-DC data exchange for Big Data
Analytics
Optimized Policy Framework
automatic policy transformation
69. RCO #5 – Designing Platforms to Smart
Cities
Scalable Platforms for Smart Cities
on Top of CC+SDN infrastructures
To support deployment of urban services
Orchestration of services with transparent network
functions into a commodity data center
Joint compute and network virtualization and
programming
Network Functions Live Migration - Allocation /
(Re/De)allocation
72. Topics of Past Research
(with traces of remaining interest)
High-Speed Traffic Measurement
Internet Traffic Modeling and Profiling
Peer-to-Peer Networking
Multimedia Streaming Protocols and Systems
Wireless and Mobile Networking
Performance of Transport Protocols
73. Current Research
Current Team (worldwide): 1 Post-doc, 8 PhD, 7 MSc
Some Graduate Studies Topics
A Game-Theoretic Approach to Vehicular Networks (VANETs)
Protocol Design
A Control-Theoretic Approach to Adaptive Streaming in the
Internet
Data Mining of SDN Controllers Performance
Domain Specific Modeling Languages for SDN
New Architectures for IoE/Smart Cities
Optimal Dependable Service Function Chaining Deployment
74. Current Research
Some Applied Research Projects
Canada-BR: Mining Trajectories on Automatic Identification
System (AIS) Satellite Data
EU-BR: Scalable and Secure Cloud Computing Services for Smart
Cities
France-BR: Measurement and SLA Management of Heterogeneous
Cloud Infrastructures
AR-BR: Traffic Monitoring and Analysis of Dependability in
Virtualized Networks
BR: Smart Tracking – A Business Decision Service Platform based
on Passive Data Collecting and Mobility Analysis of
Traceable Mobile Devices
BR: Mobile Devices Tracking and Positioning in the Context of
Smart Cities
75. Recent Papers
Design and Optimizations for Efficient Regular Expression Matching in DPI
Systems. Computer Communications, 2015
A flexible DHT-based directory service for information management. Peer-
to-Peer Networking and Applications, 2014
Dependable Virtual Network Mapping. Computing, 2014.
Design and analysis of an IEEE 802.21-based mobility management
architecture: a context-aware approach. Wireless Networks, 2012.
Urban Data Collectors: A Pragmatic Approach to Leveraging Urban Sensing,
IEEE Integrated Network Management Symposium 2015, 2015, Ottawa.
Model-Driven Networking: A Novel Approach for SDN Applications
Development. IEEE Integrated Network Management Symp. 2015, Ottawa
76. Work@CarletonU
Combining Expertises
Computer Networking (Measurement, Modeling, and
Analysis)
Modeling and Simulation
Supporting Advanced Research on Simulation
for Novel and Challenging Scenarios
Open to discussions
Help grad students
Helping writing new research proposals
Addressing the challenges of up-to-date scenarios
77. Research Challenges and
Opportunities in the Era of the
Internet of Everything and
Everything as a Service
April 2015
Carleton University - ARS-Lab
Stenio Fernandes
CIn/UFPE, Recife, Brazil
78. Center For Informatics (CIn)
Federal University Of Pernambuco (UFPE)
Recife, Brazil
About
79. CIn/UFPE
• ~42K students, ~1.3K PhD professorsUFPE
• Top 5 CS Graduate Program in Brazil
• Evaluation: CAPES level 6 (scale 1 to 7)
• Top 10 most important CS Research Center in Latin America
Recognition
• ~100 PhD professors
• ~25% BR Research ChairsFaculty
• Computer Science, Computer Engineering,
Information SystemsPrograms
80. 2000+ students
International collaboration:
Europe, Asia, and North America
Research Projects
(Private and Public funded)
CNPq, CAPES, FACEPE
Samsung, Ericsson,
Motorola, Nokia, LG, HP, etc
Recipient of a number of awards:
• 2011 Most Innovative Brazilian
Research Center
• Microsoft Imagine Cup (since 2005)
• ACM Intl. Programming Marathon
Recruitment:
Google, Microsoft, Facebook
CIn/UFPE