SlideShare a Scribd company logo
DeepALM: Holistic optical network monitoring
based on machine learning
7 March 2022
OFC 2022 Demo Zone (M3Z.11)
Sai Kireet Patri, José-Juan Pedreno-Manresa, Joo Cho, Khouloud Abdelli, Carsten Tropschug, Jim Zou, Piotr Rydlichowski
© 2022 ADVA. All rights reserved. Confidential.
2 © 2022 ADVA. All rights reserved.
AGENDA
Motivation
1.
Faults and Monitoring Solutions
2.
DeepALM
3.
Demo Setup
4.
Use Cases and Demo
5.
Conclusions
6.
© 2022 ADVA. All rights reserved. Confidential.
3 © 2022 ADVA. All rights reserved.
Protect communication infrastructure against failures, attacks and natural disasters
Network Resilience is more important than ever
Motivation
Optical JC&S*:
Phase-sensitive OTDR for
infrastructure monitoring
*Joint communicaton & sensing
*koreaherald.com
*nature.com
*Getty Images via bbc.com
© 2022 ADVA. All rights reserved. Confidential.
4 © 2022 ADVA. All rights reserved.
Combined Network Resilience Monitoring is a complex task
• Digital and physical
security is a key
component in networks
of future
• Passive fiber sensors
deployed extensively for
investment protection
• Monitoring large number
of devices for security
incidents can be
challenging
Demand for access to fiber is ever-growing
Motivation
5G Networks Enterprises
Critical Infrastructure
Protection
© 2022 ADVA. All rights reserved. Confidential.
5 © 2022 ADVA. All rights reserved.
Aim: Deploy solutions which reduce overall fault analysis and repair time
Different faults
Faults and Monitoring Solutions
Higher Probability of occurence
More time to
localize issue
Less time to
localize issue
Lower Probability of occurence
*datastrait.com
*emersonenvironcare.com.au
*Wikipedia.org
*Michael Madon, medium.com
*deciso.com
*X Liu et. al
© 2022 ADVA. All rights reserved. Confidential.
6 © 2022 ADVA. All rights reserved.
Aim: Convert collected telemetry and maintenance information into holistic, actionable intelligence
Different monitoring solutions
Faults and Monitoring Solutions
Fiber faults and location can be detected via OTDR trace
Passive, remotely monitored door sensor
states can be detected via OTDR trace
Encryption status of each encryption card can be
monitored to find any issues
Predictive maintenance of deployed lasers can reduce lead
times
Encryption status of each encryption card can be
monitored to find any issues
Fiber faults and location can be detected via OTDR trace
Passive, remotely monitored door sensor
states can be detected via OTDR trace
Predictive maintenance of deployed lasers can reduce lead
times
Encryption status of each encryption card can be
monitored to find any issues
© 2022 ADVA. All rights reserved. Confidential.
7 © 2022 ADVA. All rights reserved.
ML driven data analytics can reduce fault analysis and detection times
• Fiber Monitoring
• Detecting and localizing
fiber cuts via ML-enabled
OTDR monitoring
• Intrusion Detection
• Door sensor state detection
using ML
• Security Info Management
• Encryption Status
monitoring
• Predictive Maintenance
• Laser time to fail prediction
of vendor based aging data
Hetergeneous devices monitored
DeepALM Overview
Holistic
Network
Monitoring
Fiber
Monitoring
Intrusion
Detection
Security
Information
Management
Predictive
Maintenance
© 2022 ADVA. All rights reserved. Confidential.
8 © 2022 ADVA. All rights reserved.
Fiber Monitoring and Intrusion Detection
Security Information Management
Hardware Components
DeepALM Demo Setup
attn
ALM Fiber Spool 20 km Door Sensor
Extra patch cord w. open
connector
FSP3000 R7
5TCE10G-AES
FSP3000 R7
5TCE10G-AES
Alice Bob
© 2022 ADVA. All rights reserved. Confidential.
9 © 2022 ADVA. All rights reserved.
Python Scripts on cloud server enable ETL pipelines
Software Components
DeepALM Demo Setup
ALM
Alice
Bob
OTDR Trace
via SSH
Cloud Server
ML Fiber
Cut
ML Door
Sensor
InfluxDB
Data
Lake
Grafana-based Web
Dashboard
Encryption Status
via SNMP Polling
Encryption Status
via SNMP Polling
ETL Pipeline 1
ETL Pipeline 2
© 2022 ADVA. All rights reserved. Confidential.
10 © 2022 ADVA. All rights reserved.
Fiber Cut Monitoring
Use Case 1
ALM
OTDR monitoring
script generates
signal level at
each distance
point
Pre-processing
functions create
inputs for ML
model
Trained GRU Model [*]
InfluxDB
Grafana
* K. Abdelli, et.al , "Gated Recurrent Unit based Autoencoder for Optical
Link Fault Diagnosis in Passive Optical Networks," ECOC, 2021
© 2022 ADVA. All rights reserved. Confidential.
11 © 2022 ADVA. All rights reserved.
ML model used provides higher fault detection accuracy as compared to conventional methods
Sneak Peak at the ML model
GRU based Autoencoder
* K. Abdelli, et.al , "Gated Recurrent Unit based Autoencoder for
Optical Link Fault Diagnosis in Passive Optical Networks," ECOC,
2021
© 2022 ADVA. All rights reserved. Confidential.
12 © 2022 ADVA. All rights reserved.
Door Sensor Monitoring
Use Case 2
ALM
OTDR monitoring
script generates
signal level at
each distance
point
Pre-processing
functions create
input at fixed
locations for ML
model
InfluxDB
Grafana
Trained GRU Model [*]
© 2022 ADVA. All rights reserved. Confidential.
13 © 2022 ADVA. All rights reserved.
Security Information Management
Use Case 3
SNMP Polling for
Encryption
Module
FSP3000 R7
5TCE10G-AES
Bob
InfluxDB
Grafana
• We simulate a security incident by changing the authentication
password @ Bob
• By forcing key-exchanges, the encryption module will show errors
• These errors are visible on the Grafana dashboard
© 2022 ADVA. All rights reserved. Confidential.
14 © 2022 ADVA. All rights reserved.
DeepALM takes us one step closer to convert data into actionable intelligence
• Proof-of-Concept and data flow
for real-time heterogeneous
device monitoring
• Solution is flexible for adding
more devices and creating
rules/alerts for monitoring
• With larger devices and
datasets, ML enabled data
analytics can provide deeper
insights into faults and
intrusions
• Grafana based front-end
dashboard provide friendly GUI
for data visualization
Conclusions
Holistic
Network
Monitoring
Fiber
Monitoring
Intrusion
Detection
Security
Information
Predictive
Maintenance
Thank you
IMPORTANT NOTICE
ADVA is the exclusive owner or licensee of the content, material, and information in this presentation. Any reproduction, publication or reprint, in whole or in part, is strictly prohibited.
The information in this presentation may not be accurate, complete or up to date, and is provided without warranties or representations of any kind, either express or implied. ADVA shall not be responsible for and disclaims any liability for any loss or damages, including without limitation,
direct, indirect, incidental, consequential and special damages, alleged to have been caused by or in connection with using and/or relying on the information contained in this presentation.
Copyright © for the entire content of this presentation: ADVA.
info@adva.com

More Related Content

What's hot

176960775-Huawei-MA5600T.pdf
176960775-Huawei-MA5600T.pdf176960775-Huawei-MA5600T.pdf
176960775-Huawei-MA5600T.pdf
taha karram
 
TWAMP NOKIA.pdf
TWAMP NOKIA.pdfTWAMP NOKIA.pdf
TWAMP NOKIA.pdf
muhammadrizki938869
 

What's hot (20)

400G High Speed interconnect product guide
400G High Speed interconnect product guide 400G High Speed interconnect product guide
400G High Speed interconnect product guide
 
Gpon fundamentals
Gpon fundamentalsGpon fundamentals
Gpon fundamentals
 
176960775-Huawei-MA5600T.pdf
176960775-Huawei-MA5600T.pdf176960775-Huawei-MA5600T.pdf
176960775-Huawei-MA5600T.pdf
 
Ftth pon training guide part iv
Ftth pon training guide part ivFtth pon training guide part iv
Ftth pon training guide part iv
 
Optical line protection switch and Active Fiber Monitoring System
Optical line protection switch and Active Fiber Monitoring SystemOptical line protection switch and Active Fiber Monitoring System
Optical line protection switch and Active Fiber Monitoring System
 
What is-twamp
What is-twampWhat is-twamp
What is-twamp
 
OTDR-OPTICAL TIME DOMAIN REFLECTOMETER
OTDR-OPTICAL TIME DOMAIN REFLECTOMETEROTDR-OPTICAL TIME DOMAIN REFLECTOMETER
OTDR-OPTICAL TIME DOMAIN REFLECTOMETER
 
optical space division multiplexing
optical space division multiplexingoptical space division multiplexing
optical space division multiplexing
 
Optical Networking & DWDM
Optical Networking & DWDMOptical Networking & DWDM
Optical Networking & DWDM
 
Abstract Fiber Optics
Abstract    Fiber OpticsAbstract    Fiber Optics
Abstract Fiber Optics
 
Optical fiber Communication training ppt
Optical fiber Communication training pptOptical fiber Communication training ppt
Optical fiber Communication training ppt
 
Zigbee- The Future of Data Communications
Zigbee- The Future of Data CommunicationsZigbee- The Future of Data Communications
Zigbee- The Future of Data Communications
 
Fundamental of dwdm
Fundamental of dwdmFundamental of dwdm
Fundamental of dwdm
 
Fttx
FttxFttx
Fttx
 
Gpon fundamentals
Gpon fundamentals Gpon fundamentals
Gpon fundamentals
 
Viavi Perfect OTDR
Viavi Perfect OTDRViavi Perfect OTDR
Viavi Perfect OTDR
 
Single vs. multi-carrier in ROADM networks
Single vs. multi-carrier in ROADM networksSingle vs. multi-carrier in ROADM networks
Single vs. multi-carrier in ROADM networks
 
TWAMP NOKIA.pdf
TWAMP NOKIA.pdfTWAMP NOKIA.pdf
TWAMP NOKIA.pdf
 
An Introduction to 5G and ‘Real’ 5G
An Introduction to 5G and ‘Real’ 5GAn Introduction to 5G and ‘Real’ 5G
An Introduction to 5G and ‘Real’ 5G
 
Dense wavelength division multiplexing
Dense wavelength division multiplexingDense wavelength division multiplexing
Dense wavelength division multiplexing
 

Similar to DeepALM: Holistic optical network monitoring based on machine learning

Study Wireless Security Deployment - PKL
Study Wireless Security Deployment  - PKLStudy Wireless Security Deployment  - PKL
Study Wireless Security Deployment - PKL
Aaron ND Sawmadal
 

Similar to DeepALM: Holistic optical network monitoring based on machine learning (20)

Lightweight Cryptography Algorithms for Security of IoT Devices: A Survey
Lightweight Cryptography Algorithms for Security of IoT Devices: A SurveyLightweight Cryptography Algorithms for Security of IoT Devices: A Survey
Lightweight Cryptography Algorithms for Security of IoT Devices: A Survey
 
20210805 以5 g與邊緣運算技術佈署物聯網
20210805 以5 g與邊緣運算技術佈署物聯網20210805 以5 g與邊緣運算技術佈署物聯網
20210805 以5 g與邊緣運算技術佈署物聯網
 
IoT-Shield: A Novel DDoS Detection Approach for IoT-Based Devices
IoT-Shield: A Novel DDoS Detection Approach for IoT-Based DevicesIoT-Shield: A Novel DDoS Detection Approach for IoT-Based Devices
IoT-Shield: A Novel DDoS Detection Approach for IoT-Based Devices
 
Study Wireless Security Deployment - PKL
Study Wireless Security Deployment  - PKLStudy Wireless Security Deployment  - PKL
Study Wireless Security Deployment - PKL
 
Adoption of Next-Generation 5G Wireless Technology for “Smarter” Grid Design;...
Adoption of Next-Generation 5G Wireless Technology for “Smarter” Grid Design;...Adoption of Next-Generation 5G Wireless Technology for “Smarter” Grid Design;...
Adoption of Next-Generation 5G Wireless Technology for “Smarter” Grid Design;...
 
dan-web5g.pptx
dan-web5g.pptxdan-web5g.pptx
dan-web5g.pptx
 
The need for GBaaS as GPS/GNSS is no longer a reliable source for critical PN...
The need for GBaaS as GPS/GNSS is no longer a reliable source for critical PN...The need for GBaaS as GPS/GNSS is no longer a reliable source for critical PN...
The need for GBaaS as GPS/GNSS is no longer a reliable source for critical PN...
 
Introducing G.metro
Introducing G.metroIntroducing G.metro
Introducing G.metro
 
SECURING AND STRENGTHENING 5G BASED INFRASTRUCTURE USING ML
SECURING AND STRENGTHENING 5G BASED INFRASTRUCTURE USING MLSECURING AND STRENGTHENING 5G BASED INFRASTRUCTURE USING ML
SECURING AND STRENGTHENING 5G BASED INFRASTRUCTURE USING ML
 
IRJET- IOT based Intrusion Detection and Tracking System
IRJET- IOT based Intrusion Detection and Tracking SystemIRJET- IOT based Intrusion Detection and Tracking System
IRJET- IOT based Intrusion Detection and Tracking System
 
Signaling security essentials. Ready, steady, 5G!
 Signaling security essentials. Ready, steady, 5G! Signaling security essentials. Ready, steady, 5G!
Signaling security essentials. Ready, steady, 5G!
 
Accelerating 5G enterprise networks with edge computing and latency assurance
Accelerating 5G enterprise networks with edge computing and latency assuranceAccelerating 5G enterprise networks with edge computing and latency assurance
Accelerating 5G enterprise networks with edge computing and latency assurance
 
Accessing remote networks
Accessing remote networksAccessing remote networks
Accessing remote networks
 
Security in Optical Networks - Useless or Necessary?
Security in Optical Networks - Useless or Necessary?Security in Optical Networks - Useless or Necessary?
Security in Optical Networks - Useless or Necessary?
 
Innovative Low-Cost Perimeter Security Gadget With In-built Mechanism to Ensu...
Innovative Low-Cost Perimeter Security Gadget With In-built Mechanism to Ensu...Innovative Low-Cost Perimeter Security Gadget With In-built Mechanism to Ensu...
Innovative Low-Cost Perimeter Security Gadget With In-built Mechanism to Ensu...
 
INNOVATIVE LOW-COST PERIMETER SECURITY GADGET WITH IN-BUILT MECHANISM TO ENSU...
INNOVATIVE LOW-COST PERIMETER SECURITY GADGET WITH IN-BUILT MECHANISM TO ENSU...INNOVATIVE LOW-COST PERIMETER SECURITY GADGET WITH IN-BUILT MECHANISM TO ENSU...
INNOVATIVE LOW-COST PERIMETER SECURITY GADGET WITH IN-BUILT MECHANISM TO ENSU...
 
ADVA Webinar to Netwell.pdf
ADVA Webinar to Netwell.pdfADVA Webinar to Netwell.pdf
ADVA Webinar to Netwell.pdf
 
Whitepaper perimeter protection
Whitepaper perimeter protectionWhitepaper perimeter protection
Whitepaper perimeter protection
 
Layer 1 Encryption in WDM Transport Systems
Layer 1 Encryption in WDM Transport SystemsLayer 1 Encryption in WDM Transport Systems
Layer 1 Encryption in WDM Transport Systems
 
Secure Dual-mode Robotic Intrusion Detection System for Remote Surveillance
Secure Dual-mode Robotic Intrusion Detection System for Remote SurveillanceSecure Dual-mode Robotic Intrusion Detection System for Remote Surveillance
Secure Dual-mode Robotic Intrusion Detection System for Remote Surveillance
 

More from ADVA

More from ADVA (20)

Industrial optically pumped cesium beam clock
Industrial optically pumped cesium beam clockIndustrial optically pumped cesium beam clock
Industrial optically pumped cesium beam clock
 
Industry's longest holdover with the OSA 3350 SePRC™ optical cesium clock
Industry's longest holdover with the OSA 3350  SePRC™ optical cesium clockIndustry's longest holdover with the OSA 3350  SePRC™ optical cesium clock
Industry's longest holdover with the OSA 3350 SePRC™ optical cesium clock
 
Addressing PNT threats in critical defense infrastructure
Addressing PNT threats in critical defense infrastructureAddressing PNT threats in critical defense infrastructure
Addressing PNT threats in critical defense infrastructure
 
Precise and assured timing for enterprise networks
Precise and assured timing for enterprise networksPrecise and assured timing for enterprise networks
Precise and assured timing for enterprise networks
 
Introducing Ensemble Cloudlet for on-premises cloud demand
Introducing Ensemble Cloudlet for on-premises cloud demandIntroducing Ensemble Cloudlet for on-premises cloud demand
Introducing Ensemble Cloudlet for on-premises cloud demand
 
ePRTC in data centers - GNSS-backup-as-a-service (GBaaS)
ePRTC in data centers - GNSS-backup-as-a-service (GBaaS)ePRTC in data centers - GNSS-backup-as-a-service (GBaaS)
ePRTC in data centers - GNSS-backup-as-a-service (GBaaS)
 
Sync on TAP - Syncing infrastructure with software
Sync on TAP - Syncing infrastructure with softwareSync on TAP - Syncing infrastructure with software
Sync on TAP - Syncing infrastructure with software
 
Meet stringent latency demands with time-sensitive networking
Meet stringent latency demands with time-sensitive networkingMeet stringent latency demands with time-sensitive networking
Meet stringent latency demands with time-sensitive networking
 
Making networks secure with multi-layer encryption
Making networks secure with multi-layer encryptionMaking networks secure with multi-layer encryption
Making networks secure with multi-layer encryption
 
Quantum threat: How to protect your optical network
Quantum threat: How to protect your optical networkQuantum threat: How to protect your optical network
Quantum threat: How to protect your optical network
 
Optical networks and the ecodesign tradeoff between climate change mitigation...
Optical networks and the ecodesign tradeoff between climate change mitigation...Optical networks and the ecodesign tradeoff between climate change mitigation...
Optical networks and the ecodesign tradeoff between climate change mitigation...
 
Trends in next-generation data center interconnects (DCI)
Trends in next-generation data center interconnects (DCI)Trends in next-generation data center interconnects (DCI)
Trends in next-generation data center interconnects (DCI)
 
Open optical edge connecting mobile access networks
Open optical edge connecting mobile access networksOpen optical edge connecting mobile access networks
Open optical edge connecting mobile access networks
 
Introducing Adva Network Security – a trusted German anchor
Introducing Adva Network Security – a trusted German anchorIntroducing Adva Network Security – a trusted German anchor
Introducing Adva Network Security – a trusted German anchor
 
Meet the industry's first pluggable 10G demarcation device
Meet the industry's first pluggable 10G demarcation deviceMeet the industry's first pluggable 10G demarcation device
Meet the industry's first pluggable 10G demarcation device
 
Introducing ADVA AccessWave25™
Introducing ADVA AccessWave25™Introducing ADVA AccessWave25™
Introducing ADVA AccessWave25™
 
10G edge technology for outdoor environments
10G edge technology for outdoor environments10G edge technology for outdoor environments
10G edge technology for outdoor environments
 
The quantum age - secure transport networks
The quantum age - secure transport networksThe quantum age - secure transport networks
The quantum age - secure transport networks
 
From leased lines to optical spectrum services
From leased lines to optical spectrum servicesFrom leased lines to optical spectrum services
From leased lines to optical spectrum services
 
The coherent optical edge
The coherent optical edgeThe coherent optical edge
The coherent optical edge
 

Recently uploaded

Recently uploaded (20)

Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........
 
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered QualitySoftware Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
 
Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*
 
Exploring UiPath Orchestrator API: updates and limits in 2024 🚀
Exploring UiPath Orchestrator API: updates and limits in 2024 🚀Exploring UiPath Orchestrator API: updates and limits in 2024 🚀
Exploring UiPath Orchestrator API: updates and limits in 2024 🚀
 
In-Depth Performance Testing Guide for IT Professionals
In-Depth Performance Testing Guide for IT ProfessionalsIn-Depth Performance Testing Guide for IT Professionals
In-Depth Performance Testing Guide for IT Professionals
 
JMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and GrafanaJMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and Grafana
 
Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...
 
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
 
Unpacking Value Delivery - Agile Oxford Meetup - May 2024.pptx
Unpacking Value Delivery - Agile Oxford Meetup - May 2024.pptxUnpacking Value Delivery - Agile Oxford Meetup - May 2024.pptx
Unpacking Value Delivery - Agile Oxford Meetup - May 2024.pptx
 
Accelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish CachingAccelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish Caching
 
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
 
ODC, Data Fabric and Architecture User Group
ODC, Data Fabric and Architecture User GroupODC, Data Fabric and Architecture User Group
ODC, Data Fabric and Architecture User Group
 
UiPath Test Automation using UiPath Test Suite series, part 1
UiPath Test Automation using UiPath Test Suite series, part 1UiPath Test Automation using UiPath Test Suite series, part 1
UiPath Test Automation using UiPath Test Suite series, part 1
 
IoT Analytics Company Presentation May 2024
IoT Analytics Company Presentation May 2024IoT Analytics Company Presentation May 2024
IoT Analytics Company Presentation May 2024
 
UiPath Test Automation using UiPath Test Suite series, part 2
UiPath Test Automation using UiPath Test Suite series, part 2UiPath Test Automation using UiPath Test Suite series, part 2
UiPath Test Automation using UiPath Test Suite series, part 2
 
When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...
 
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyes
 
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
 
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMsTo Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
 

DeepALM: Holistic optical network monitoring based on machine learning

  • 1. DeepALM: Holistic optical network monitoring based on machine learning 7 March 2022 OFC 2022 Demo Zone (M3Z.11) Sai Kireet Patri, José-Juan Pedreno-Manresa, Joo Cho, Khouloud Abdelli, Carsten Tropschug, Jim Zou, Piotr Rydlichowski
  • 2. © 2022 ADVA. All rights reserved. Confidential. 2 © 2022 ADVA. All rights reserved. AGENDA Motivation 1. Faults and Monitoring Solutions 2. DeepALM 3. Demo Setup 4. Use Cases and Demo 5. Conclusions 6.
  • 3. © 2022 ADVA. All rights reserved. Confidential. 3 © 2022 ADVA. All rights reserved. Protect communication infrastructure against failures, attacks and natural disasters Network Resilience is more important than ever Motivation Optical JC&S*: Phase-sensitive OTDR for infrastructure monitoring *Joint communicaton & sensing *koreaherald.com *nature.com *Getty Images via bbc.com
  • 4. © 2022 ADVA. All rights reserved. Confidential. 4 © 2022 ADVA. All rights reserved. Combined Network Resilience Monitoring is a complex task • Digital and physical security is a key component in networks of future • Passive fiber sensors deployed extensively for investment protection • Monitoring large number of devices for security incidents can be challenging Demand for access to fiber is ever-growing Motivation 5G Networks Enterprises Critical Infrastructure Protection
  • 5. © 2022 ADVA. All rights reserved. Confidential. 5 © 2022 ADVA. All rights reserved. Aim: Deploy solutions which reduce overall fault analysis and repair time Different faults Faults and Monitoring Solutions Higher Probability of occurence More time to localize issue Less time to localize issue Lower Probability of occurence *datastrait.com *emersonenvironcare.com.au *Wikipedia.org *Michael Madon, medium.com *deciso.com *X Liu et. al
  • 6. © 2022 ADVA. All rights reserved. Confidential. 6 © 2022 ADVA. All rights reserved. Aim: Convert collected telemetry and maintenance information into holistic, actionable intelligence Different monitoring solutions Faults and Monitoring Solutions Fiber faults and location can be detected via OTDR trace Passive, remotely monitored door sensor states can be detected via OTDR trace Encryption status of each encryption card can be monitored to find any issues Predictive maintenance of deployed lasers can reduce lead times Encryption status of each encryption card can be monitored to find any issues Fiber faults and location can be detected via OTDR trace Passive, remotely monitored door sensor states can be detected via OTDR trace Predictive maintenance of deployed lasers can reduce lead times Encryption status of each encryption card can be monitored to find any issues
  • 7. © 2022 ADVA. All rights reserved. Confidential. 7 © 2022 ADVA. All rights reserved. ML driven data analytics can reduce fault analysis and detection times • Fiber Monitoring • Detecting and localizing fiber cuts via ML-enabled OTDR monitoring • Intrusion Detection • Door sensor state detection using ML • Security Info Management • Encryption Status monitoring • Predictive Maintenance • Laser time to fail prediction of vendor based aging data Hetergeneous devices monitored DeepALM Overview Holistic Network Monitoring Fiber Monitoring Intrusion Detection Security Information Management Predictive Maintenance
  • 8. © 2022 ADVA. All rights reserved. Confidential. 8 © 2022 ADVA. All rights reserved. Fiber Monitoring and Intrusion Detection Security Information Management Hardware Components DeepALM Demo Setup attn ALM Fiber Spool 20 km Door Sensor Extra patch cord w. open connector FSP3000 R7 5TCE10G-AES FSP3000 R7 5TCE10G-AES Alice Bob
  • 9. © 2022 ADVA. All rights reserved. Confidential. 9 © 2022 ADVA. All rights reserved. Python Scripts on cloud server enable ETL pipelines Software Components DeepALM Demo Setup ALM Alice Bob OTDR Trace via SSH Cloud Server ML Fiber Cut ML Door Sensor InfluxDB Data Lake Grafana-based Web Dashboard Encryption Status via SNMP Polling Encryption Status via SNMP Polling ETL Pipeline 1 ETL Pipeline 2
  • 10. © 2022 ADVA. All rights reserved. Confidential. 10 © 2022 ADVA. All rights reserved. Fiber Cut Monitoring Use Case 1 ALM OTDR monitoring script generates signal level at each distance point Pre-processing functions create inputs for ML model Trained GRU Model [*] InfluxDB Grafana * K. Abdelli, et.al , "Gated Recurrent Unit based Autoencoder for Optical Link Fault Diagnosis in Passive Optical Networks," ECOC, 2021
  • 11. © 2022 ADVA. All rights reserved. Confidential. 11 © 2022 ADVA. All rights reserved. ML model used provides higher fault detection accuracy as compared to conventional methods Sneak Peak at the ML model GRU based Autoencoder * K. Abdelli, et.al , "Gated Recurrent Unit based Autoencoder for Optical Link Fault Diagnosis in Passive Optical Networks," ECOC, 2021
  • 12. © 2022 ADVA. All rights reserved. Confidential. 12 © 2022 ADVA. All rights reserved. Door Sensor Monitoring Use Case 2 ALM OTDR monitoring script generates signal level at each distance point Pre-processing functions create input at fixed locations for ML model InfluxDB Grafana Trained GRU Model [*]
  • 13. © 2022 ADVA. All rights reserved. Confidential. 13 © 2022 ADVA. All rights reserved. Security Information Management Use Case 3 SNMP Polling for Encryption Module FSP3000 R7 5TCE10G-AES Bob InfluxDB Grafana • We simulate a security incident by changing the authentication password @ Bob • By forcing key-exchanges, the encryption module will show errors • These errors are visible on the Grafana dashboard
  • 14. © 2022 ADVA. All rights reserved. Confidential. 14 © 2022 ADVA. All rights reserved. DeepALM takes us one step closer to convert data into actionable intelligence • Proof-of-Concept and data flow for real-time heterogeneous device monitoring • Solution is flexible for adding more devices and creating rules/alerts for monitoring • With larger devices and datasets, ML enabled data analytics can provide deeper insights into faults and intrusions • Grafana based front-end dashboard provide friendly GUI for data visualization Conclusions Holistic Network Monitoring Fiber Monitoring Intrusion Detection Security Information Predictive Maintenance
  • 15. Thank you IMPORTANT NOTICE ADVA is the exclusive owner or licensee of the content, material, and information in this presentation. Any reproduction, publication or reprint, in whole or in part, is strictly prohibited. The information in this presentation may not be accurate, complete or up to date, and is provided without warranties or representations of any kind, either express or implied. ADVA shall not be responsible for and disclaims any liability for any loss or damages, including without limitation, direct, indirect, incidental, consequential and special damages, alleged to have been caused by or in connection with using and/or relying on the information contained in this presentation. Copyright © for the entire content of this presentation: ADVA. info@adva.com