SlideShare a Scribd company logo
1 of 17
Download to read offline
QoA4ML – A Framework for
Supporting Contracts in
Machine Learning Services
Hong-Linh Truong, Minh-Tri Nguyen
Department of Computer Science
https://rdsea.github.io
Outline
▪ Context, scenario and research questions
▪ Key components of the QoA4ML framework
▪ Prototype and experiments
▪ Conclusions and future work
September 9, 2021
IEEE International Conference on Web Services (ICWS) 2021
2
Context
▪ Machine learning as a service becomes popular
▪ ML service providers offer ML services for different consumers
▪ Different stakeholders and interaction models
▪ Two stakeholders engagement: consumer and ML service provider
▪ Three stakeholders engagement: consumer, ML service provider
and ML infrastructure/platform provider
▪ Key issue
▪ How do we support contracts between the ML service provider and
other stakeholders? It is not just about performance!
▪ ML has several distinguishable attributes
September 9, 2021
IEEE International Conference on Web Services (ICWS) 2021
3
Scenario: predictive maintenance in
Base Transceiver Stations (BTS)
▪ Dynamic inference from IoT data about equipment and infrastructure
components in a BTS
September 9, 2021
IEEE International Conference on Web Services (ICWS) 2021
4
Key research questions & our approach
▪ Which are key attributes for ML contracts?
▪ How would ML attributes and constraints be specified?
▪ How would ML-specific attributes/constraints be monitored and
evaluated?
▪ Approach
▪ Focus on ML-specific attributes
▪ Researchers have identified many attributes for ML models and systems
▪ Design ML contract specs suitable for cloud-native services
▪ Constraints, policies and monitoring reports
▪ Monitor ML attributes for contract monitoring
September 9, 2021
IEEE International Conference on Web Services (ICWS) 2021
5
QoA4ML framework – important attributes
for ML-specific contracts
▪ Focus on important categories
▪ Inference Accuracy, Reliability and Elasticity, Quality of Data,
Security and Privacy, Fairness and Interpretability and Cost
September 9, 2021
IEEE International Conference on Web Services (ICWS) 2021
6
QoA4ML specifications
▪ Decoupling attributes/constraints vs policies
▪ Required attributes and their constraints can be changed and
updated at runtime
▪ Policies to check attributes and constraints can be implemented in
different ways
▪ Monitoring probes and other utilities supporting observability
▪ New probes for quality of data and ML models
▪ Need to be instrumented and deployed to capture runtime attributes
▪ Must be well integrated with common monitoring features
September 9, 2021
IEEE International Conference on Web Services (ICWS) 2021
7
QoA4ML
specification -
the initial
implementation
September 9, 2021
IEEE International Conference on Web Services (ICWS) 2021
8
Constraints for the BTS ML service
▪ Use terms in the
QoA4ML specs
▪ Attributes and
constraints can be
changed
September 9, 2021
IEEE International Conference on Web Services (ICWS) 2021
9
Example of policies for validating contract
constraints
▪ Is based on Rego
▪ Can load contract
terms from JSON
and compare with
runtime monitoring
▪ Can be changed at
runtime
September 9, 2021
IEEE International Conference on Web Services (ICWS) 2021
10
Monitoring utilities and Observability
Service
September 9, 2021
IEEE International Conference on Web Services (ICWS) 2021
11
Design for different
engines to be used
Reuse well-known
monitoring systems
Monitor ML-specific
attributes
Current prototype
▪ QoA4ML Specs: initial version based on JSON
▪ Use OPA (https://www.openpolicyagent.org/) as engine
▪ Rego and JSON are used for policies, attributes and constraints
▪ QoA4ML Observability as microservices
▪ Using state-of-the-art monitoring tools like
Prometheus/Grafana
▪ Testing environments
▪ Edge and cloud infrastructures
▪ Source code is currently being pushed into:
▪ https://github.com/rdsea/QoA4ML
September 9, 2021
IEEE International Conference on Web Services (ICWS) 2021
12
Experiments
▪ Dynamic inferences of BTS load of power grid
▪ LSTM, TensorFlow
▪ IoT data from BTS (several months)
▪ Training in cloud and export to the edge (BTS-model-edge)
and retraining several times in the cloud (BTS-model-cloud)
▪ Deployment
▪ Contracts:
▪ ResponseTime
▪ Inference Accuracy
▪ Data Quality
September 9, 2021
IEEE International Conference on Web Services (ICWS) 2021
13
Effect of edge and cloud serving
platform deployment in ML contracts.
September 9, 2021
IEEE International Conference on Web Services (ICWS) 2021
14
Both consumer and service are in the
same edge; 3000 records per 15 minutes
Both consumer and broker are in the same edge
Broker is in the cloud
Impact of violation monitoring
All services in the edge (except the observability)
September 9, 2021
IEEE International Conference on Web Services (ICWS) 2021
15
Help to detect outdated models in ML
services: violation changes when
retraining models
Help to see
correlations
among
attributes:
data quality
and inference
accuracy
Conclusions and future work
▪ QoA4ML is a framework to support ML service contracts
▪ Contract specifications (constraints and policies), tools and services
▪ QoA4ML benefits
▪ Establish contracts, moving to the step of continuous testing and
observability of ML production
▪ Support flexible contracts and policies, enabling reuses and real-
world ML services integration
▪ Future work
▪ Extending ML attributes and specifications; integration with cloud
service contracts; new probes and observability capabilities
September 9, 2021
IEEE International Conference on Web Services (ICWS) 2021
16
Thanks!
Hong-Linh Truong
Department of Computer Science
rdsea.github.io
IEEE International Conference on Web Services (ICWS) 2021
17
September 9, 2021

More Related Content

Similar to QoA4ML – A Framework for Supporting Contracts in Machine Learning Services

CloudE: Standards of Excellence for Ethernet Cloud Connections
CloudE: Standards of Excellence for Ethernet Cloud ConnectionsCloudE: Standards of Excellence for Ethernet Cloud Connections
CloudE: Standards of Excellence for Ethernet Cloud ConnectionsBusiness Cable Collaboration Group
 
Cc unit 2 ppt
Cc unit 2 pptCc unit 2 ppt
Cc unit 2 pptDr VISU P
 
Final Year Project IEEE 2015
Final Year Project IEEE 2015Final Year Project IEEE 2015
Final Year Project IEEE 2015TTA_TNagar
 
Final Year IEEE Project Titles 2015
Final Year IEEE Project Titles 2015Final Year IEEE Project Titles 2015
Final Year IEEE Project Titles 2015TTA_TNagar
 
Performance and Cost Evaluation of an Adaptive Encryption Architecture for Cl...
Performance and Cost Evaluation of an Adaptive Encryption Architecture for Cl...Performance and Cost Evaluation of an Adaptive Encryption Architecture for Cl...
Performance and Cost Evaluation of an Adaptive Encryption Architecture for Cl...Editor IJLRES
 
Machine Learning 5G Federated Learning.pdf
Machine Learning 5G Federated Learning.pdfMachine Learning 5G Federated Learning.pdf
Machine Learning 5G Federated Learning.pdfadeyimikaipaye
 
Capella Days 2021 | An example of model-centric engineering environment with ...
Capella Days 2021 | An example of model-centric engineering environment with ...Capella Days 2021 | An example of model-centric engineering environment with ...
Capella Days 2021 | An example of model-centric engineering environment with ...Obeo
 
DYNAMIC TENANT PROVISIONING AND SERVICE ORCHESTRATION IN HYBRID CLOUD
DYNAMIC TENANT PROVISIONING AND SERVICE ORCHESTRATION IN HYBRID CLOUDDYNAMIC TENANT PROVISIONING AND SERVICE ORCHESTRATION IN HYBRID CLOUD
DYNAMIC TENANT PROVISIONING AND SERVICE ORCHESTRATION IN HYBRID CLOUDijccsa
 
DYNAMIC TENANT PROVISIONING AND SERVICE ORCHESTRATION IN HYBRID CLOUD
DYNAMIC TENANT PROVISIONING AND SERVICE ORCHESTRATION IN HYBRID CLOUDDYNAMIC TENANT PROVISIONING AND SERVICE ORCHESTRATION IN HYBRID CLOUD
DYNAMIC TENANT PROVISIONING AND SERVICE ORCHESTRATION IN HYBRID CLOUDijccsa
 
Resource usage optimization in cloud based networks
Resource usage optimization in cloud based networksResource usage optimization in cloud based networks
Resource usage optimization in cloud based networksDimo Iliev
 
Contemporary Energy Optimization for Mobile and Cloud Environment
Contemporary Energy Optimization for Mobile and Cloud EnvironmentContemporary Energy Optimization for Mobile and Cloud Environment
Contemporary Energy Optimization for Mobile and Cloud Environmentijceronline
 
Software defined networking introduction
Software defined networking introductionSoftware defined networking introduction
Software defined networking introductionEktaSoni20
 
Winds of change from vender lock in to the meta cloud
Winds of change from vender lock in to the meta cloudWinds of change from vender lock in to the meta cloud
Winds of change from vender lock in to the meta cloudMunisekhar Gunapati
 
IWSM2014 MEGSUS14 - GQM on energy for SaaS - CETIC
IWSM2014   MEGSUS14 - GQM on energy for SaaS - CETICIWSM2014   MEGSUS14 - GQM on energy for SaaS - CETIC
IWSM2014 MEGSUS14 - GQM on energy for SaaS - CETICNesma
 
Multiagent multiobjective interaction game system for service provisoning veh...
Multiagent multiobjective interaction game system for service provisoning veh...Multiagent multiobjective interaction game system for service provisoning veh...
Multiagent multiobjective interaction game system for service provisoning veh...redpel dot com
 
Optimal Rate Allocation and Lost Packet Retransmission in Video Streaming
Optimal Rate Allocation and Lost Packet Retransmission in Video StreamingOptimal Rate Allocation and Lost Packet Retransmission in Video Streaming
Optimal Rate Allocation and Lost Packet Retransmission in Video StreamingIRJET Journal
 
My Ph.D. Defense - Software-Defined Systems for Network-Aware Service Compos...
 My Ph.D. Defense - Software-Defined Systems for Network-Aware Service Compos... My Ph.D. Defense - Software-Defined Systems for Network-Aware Service Compos...
My Ph.D. Defense - Software-Defined Systems for Network-Aware Service Compos...Pradeeban Kathiravelu, Ph.D.
 
ISC Cloud13 Sill - Crossing organizational boundaries in cloud computing
ISC Cloud13 Sill - Crossing organizational boundaries in cloud computingISC Cloud13 Sill - Crossing organizational boundaries in cloud computing
ISC Cloud13 Sill - Crossing organizational boundaries in cloud computingAlan Sill
 

Similar to QoA4ML – A Framework for Supporting Contracts in Machine Learning Services (20)

CloudE: Standards of Excellence for Ethernet Cloud Connections
CloudE: Standards of Excellence for Ethernet Cloud ConnectionsCloudE: Standards of Excellence for Ethernet Cloud Connections
CloudE: Standards of Excellence for Ethernet Cloud Connections
 
Cc unit 2 ppt
Cc unit 2 pptCc unit 2 ppt
Cc unit 2 ppt
 
Final Year Project IEEE 2015
Final Year Project IEEE 2015Final Year Project IEEE 2015
Final Year Project IEEE 2015
 
Final Year IEEE Project Titles 2015
Final Year IEEE Project Titles 2015Final Year IEEE Project Titles 2015
Final Year IEEE Project Titles 2015
 
Performance and Cost Evaluation of an Adaptive Encryption Architecture for Cl...
Performance and Cost Evaluation of an Adaptive Encryption Architecture for Cl...Performance and Cost Evaluation of an Adaptive Encryption Architecture for Cl...
Performance and Cost Evaluation of an Adaptive Encryption Architecture for Cl...
 
Machine Learning 5G Federated Learning.pdf
Machine Learning 5G Federated Learning.pdfMachine Learning 5G Federated Learning.pdf
Machine Learning 5G Federated Learning.pdf
 
Capella Days 2021 | An example of model-centric engineering environment with ...
Capella Days 2021 | An example of model-centric engineering environment with ...Capella Days 2021 | An example of model-centric engineering environment with ...
Capella Days 2021 | An example of model-centric engineering environment with ...
 
DYNAMIC TENANT PROVISIONING AND SERVICE ORCHESTRATION IN HYBRID CLOUD
DYNAMIC TENANT PROVISIONING AND SERVICE ORCHESTRATION IN HYBRID CLOUDDYNAMIC TENANT PROVISIONING AND SERVICE ORCHESTRATION IN HYBRID CLOUD
DYNAMIC TENANT PROVISIONING AND SERVICE ORCHESTRATION IN HYBRID CLOUD
 
DYNAMIC TENANT PROVISIONING AND SERVICE ORCHESTRATION IN HYBRID CLOUD
DYNAMIC TENANT PROVISIONING AND SERVICE ORCHESTRATION IN HYBRID CLOUDDYNAMIC TENANT PROVISIONING AND SERVICE ORCHESTRATION IN HYBRID CLOUD
DYNAMIC TENANT PROVISIONING AND SERVICE ORCHESTRATION IN HYBRID CLOUD
 
Resource usage optimization in cloud based networks
Resource usage optimization in cloud based networksResource usage optimization in cloud based networks
Resource usage optimization in cloud based networks
 
Contemporary Energy Optimization for Mobile and Cloud Environment
Contemporary Energy Optimization for Mobile and Cloud EnvironmentContemporary Energy Optimization for Mobile and Cloud Environment
Contemporary Energy Optimization for Mobile and Cloud Environment
 
Software defined networking introduction
Software defined networking introductionSoftware defined networking introduction
Software defined networking introduction
 
Winds of change from vender lock in to the meta cloud
Winds of change from vender lock in to the meta cloudWinds of change from vender lock in to the meta cloud
Winds of change from vender lock in to the meta cloud
 
IWSM2014 MEGSUS14 - GQM on energy for SaaS - CETIC
IWSM2014   MEGSUS14 - GQM on energy for SaaS - CETICIWSM2014   MEGSUS14 - GQM on energy for SaaS - CETIC
IWSM2014 MEGSUS14 - GQM on energy for SaaS - CETIC
 
Multiagent multiobjective interaction game system for service provisoning veh...
Multiagent multiobjective interaction game system for service provisoning veh...Multiagent multiobjective interaction game system for service provisoning veh...
Multiagent multiobjective interaction game system for service provisoning veh...
 
Optimal Rate Allocation and Lost Packet Retransmission in Video Streaming
Optimal Rate Allocation and Lost Packet Retransmission in Video StreamingOptimal Rate Allocation and Lost Packet Retransmission in Video Streaming
Optimal Rate Allocation and Lost Packet Retransmission in Video Streaming
 
My Ph.D. Defense - Software-Defined Systems for Network-Aware Service Compos...
 My Ph.D. Defense - Software-Defined Systems for Network-Aware Service Compos... My Ph.D. Defense - Software-Defined Systems for Network-Aware Service Compos...
My Ph.D. Defense - Software-Defined Systems for Network-Aware Service Compos...
 
QoS in an LTE network
QoS in an LTE networkQoS in an LTE network
QoS in an LTE network
 
ISC Cloud13 Sill - Crossing organizational boundaries in cloud computing
ISC Cloud13 Sill - Crossing organizational boundaries in cloud computingISC Cloud13 Sill - Crossing organizational boundaries in cloud computing
ISC Cloud13 Sill - Crossing organizational boundaries in cloud computing
 
Cloud computing
Cloud computingCloud computing
Cloud computing
 

More from Hong-Linh Truong

Measuring, Quantifying, & Predicting the Cost-Accuracy Tradeoff
Measuring, Quantifying, & Predicting the Cost-Accuracy TradeoffMeasuring, Quantifying, & Predicting the Cost-Accuracy Tradeoff
Measuring, Quantifying, & Predicting the Cost-Accuracy TradeoffHong-Linh Truong
 
DevOps for Dynamic Interoperability of IoT, Edge and Cloud Systems
DevOps for Dynamic Interoperability of IoT, Edge and Cloud SystemsDevOps for Dynamic Interoperability of IoT, Edge and Cloud Systems
DevOps for Dynamic Interoperability of IoT, Edge and Cloud SystemsHong-Linh Truong
 
Dynamic IoT data, protocol, and middleware interoperability with resource sli...
Dynamic IoT data, protocol, and middleware interoperability with resource sli...Dynamic IoT data, protocol, and middleware interoperability with resource sli...
Dynamic IoT data, protocol, and middleware interoperability with resource sli...Hong-Linh Truong
 
Integrated Analytics for IIoT Predictive Maintenance using IoT Big Data Cloud...
Integrated Analytics for IIoT Predictive Maintenance using IoT Big Data Cloud...Integrated Analytics for IIoT Predictive Maintenance using IoT Big Data Cloud...
Integrated Analytics for IIoT Predictive Maintenance using IoT Big Data Cloud...Hong-Linh Truong
 
Modeling and Provisioning IoT Cloud Systems for Testing Uncertainties
Modeling and Provisioning IoT Cloud Systems for Testing UncertaintiesModeling and Provisioning IoT Cloud Systems for Testing Uncertainties
Modeling and Provisioning IoT Cloud Systems for Testing UncertaintiesHong-Linh Truong
 
Characterizing Incidents in Cloud-based IoT Data Analytics
Characterizing Incidents in Cloud-based IoT Data AnalyticsCharacterizing Incidents in Cloud-based IoT Data Analytics
Characterizing Incidents in Cloud-based IoT Data AnalyticsHong-Linh Truong
 
Enabling Edge Analytics of IoT Data: The Case of LoRaWAN
Enabling Edge Analytics of IoT Data: The Case of LoRaWANEnabling Edge Analytics of IoT Data: The Case of LoRaWAN
Enabling Edge Analytics of IoT Data: The Case of LoRaWANHong-Linh Truong
 
Analytics of Performance and Data Quality for Mobile Edge Cloud Applications
Analytics of Performance and Data Quality for Mobile Edge Cloud ApplicationsAnalytics of Performance and Data Quality for Mobile Edge Cloud Applications
Analytics of Performance and Data Quality for Mobile Edge Cloud ApplicationsHong-Linh Truong
 
Testing Uncertainty of Cyber-Physical Systems in IoT Cloud Infrastructures: C...
Testing Uncertainty of Cyber-Physical Systems in IoT Cloud Infrastructures: C...Testing Uncertainty of Cyber-Physical Systems in IoT Cloud Infrastructures: C...
Testing Uncertainty of Cyber-Physical Systems in IoT Cloud Infrastructures: C...Hong-Linh Truong
 
Deep Context-Awareness: Context Coupling and New Types of Context Information...
Deep Context-Awareness: Context Coupling and New Types of Context Information...Deep Context-Awareness: Context Coupling and New Types of Context Information...
Deep Context-Awareness: Context Coupling and New Types of Context Information...Hong-Linh Truong
 
Managing and Testing Ensembles of IoT, Network functions, and Clouds
Managing and Testing Ensembles of IoT, Network functions, and CloudsManaging and Testing Ensembles of IoT, Network functions, and Clouds
Managing and Testing Ensembles of IoT, Network functions, and CloudsHong-Linh Truong
 
Towards a Resource Slice Interoperability Hub for IoT
Towards a Resource Slice Interoperability Hub for IoTTowards a Resource Slice Interoperability Hub for IoT
Towards a Resource Slice Interoperability Hub for IoTHong-Linh Truong
 
On Supporting Contract-aware IoT Dataspace Services
On Supporting Contract-aware IoT Dataspace ServicesOn Supporting Contract-aware IoT Dataspace Services
On Supporting Contract-aware IoT Dataspace ServicesHong-Linh Truong
 
Towards the Realization of Multi-dimensional Elasticity for Distributed Cloud...
Towards the Realization of Multi-dimensional Elasticity for Distributed Cloud...Towards the Realization of Multi-dimensional Elasticity for Distributed Cloud...
Towards the Realization of Multi-dimensional Elasticity for Distributed Cloud...Hong-Linh Truong
 
On Engineering Analytics of Elastic IoT Cloud Systems
On Engineering Analytics of Elastic IoT Cloud SystemsOn Engineering Analytics of Elastic IoT Cloud Systems
On Engineering Analytics of Elastic IoT Cloud SystemsHong-Linh Truong
 
HINC – Harmonizing Diverse Resource Information Across IoT, Network Functions...
HINC – Harmonizing Diverse Resource Information Across IoT, Network Functions...HINC – Harmonizing Diverse Resource Information Across IoT, Network Functions...
HINC – Harmonizing Diverse Resource Information Across IoT, Network Functions...Hong-Linh Truong
 
SINC – An Information-Centric Approach for End-to-End IoT Cloud Resource Prov...
SINC – An Information-Centric Approach for End-to-End IoT Cloud Resource Prov...SINC – An Information-Centric Approach for End-to-End IoT Cloud Resource Prov...
SINC – An Information-Centric Approach for End-to-End IoT Cloud Resource Prov...Hong-Linh Truong
 
Governing Elastic IoT Cloud Systems under Uncertainties
Governing Elastic IoT Cloud Systems under UncertaintiesGoverning Elastic IoT Cloud Systems under Uncertainties
Governing Elastic IoT Cloud Systems under UncertaintiesHong-Linh Truong
 
SmartSociety – A Platform for Collaborative People-Machine Computation
SmartSociety – A Platform for Collaborative People-Machine ComputationSmartSociety – A Platform for Collaborative People-Machine Computation
SmartSociety – A Platform for Collaborative People-Machine ComputationHong-Linh Truong
 
On Developing and Operating of Data Elasticity Management Process
On Developing and Operating of Data Elasticity Management ProcessOn Developing and Operating of Data Elasticity Management Process
On Developing and Operating of Data Elasticity Management ProcessHong-Linh Truong
 

More from Hong-Linh Truong (20)

Measuring, Quantifying, & Predicting the Cost-Accuracy Tradeoff
Measuring, Quantifying, & Predicting the Cost-Accuracy TradeoffMeasuring, Quantifying, & Predicting the Cost-Accuracy Tradeoff
Measuring, Quantifying, & Predicting the Cost-Accuracy Tradeoff
 
DevOps for Dynamic Interoperability of IoT, Edge and Cloud Systems
DevOps for Dynamic Interoperability of IoT, Edge and Cloud SystemsDevOps for Dynamic Interoperability of IoT, Edge and Cloud Systems
DevOps for Dynamic Interoperability of IoT, Edge and Cloud Systems
 
Dynamic IoT data, protocol, and middleware interoperability with resource sli...
Dynamic IoT data, protocol, and middleware interoperability with resource sli...Dynamic IoT data, protocol, and middleware interoperability with resource sli...
Dynamic IoT data, protocol, and middleware interoperability with resource sli...
 
Integrated Analytics for IIoT Predictive Maintenance using IoT Big Data Cloud...
Integrated Analytics for IIoT Predictive Maintenance using IoT Big Data Cloud...Integrated Analytics for IIoT Predictive Maintenance using IoT Big Data Cloud...
Integrated Analytics for IIoT Predictive Maintenance using IoT Big Data Cloud...
 
Modeling and Provisioning IoT Cloud Systems for Testing Uncertainties
Modeling and Provisioning IoT Cloud Systems for Testing UncertaintiesModeling and Provisioning IoT Cloud Systems for Testing Uncertainties
Modeling and Provisioning IoT Cloud Systems for Testing Uncertainties
 
Characterizing Incidents in Cloud-based IoT Data Analytics
Characterizing Incidents in Cloud-based IoT Data AnalyticsCharacterizing Incidents in Cloud-based IoT Data Analytics
Characterizing Incidents in Cloud-based IoT Data Analytics
 
Enabling Edge Analytics of IoT Data: The Case of LoRaWAN
Enabling Edge Analytics of IoT Data: The Case of LoRaWANEnabling Edge Analytics of IoT Data: The Case of LoRaWAN
Enabling Edge Analytics of IoT Data: The Case of LoRaWAN
 
Analytics of Performance and Data Quality for Mobile Edge Cloud Applications
Analytics of Performance and Data Quality for Mobile Edge Cloud ApplicationsAnalytics of Performance and Data Quality for Mobile Edge Cloud Applications
Analytics of Performance and Data Quality for Mobile Edge Cloud Applications
 
Testing Uncertainty of Cyber-Physical Systems in IoT Cloud Infrastructures: C...
Testing Uncertainty of Cyber-Physical Systems in IoT Cloud Infrastructures: C...Testing Uncertainty of Cyber-Physical Systems in IoT Cloud Infrastructures: C...
Testing Uncertainty of Cyber-Physical Systems in IoT Cloud Infrastructures: C...
 
Deep Context-Awareness: Context Coupling and New Types of Context Information...
Deep Context-Awareness: Context Coupling and New Types of Context Information...Deep Context-Awareness: Context Coupling and New Types of Context Information...
Deep Context-Awareness: Context Coupling and New Types of Context Information...
 
Managing and Testing Ensembles of IoT, Network functions, and Clouds
Managing and Testing Ensembles of IoT, Network functions, and CloudsManaging and Testing Ensembles of IoT, Network functions, and Clouds
Managing and Testing Ensembles of IoT, Network functions, and Clouds
 
Towards a Resource Slice Interoperability Hub for IoT
Towards a Resource Slice Interoperability Hub for IoTTowards a Resource Slice Interoperability Hub for IoT
Towards a Resource Slice Interoperability Hub for IoT
 
On Supporting Contract-aware IoT Dataspace Services
On Supporting Contract-aware IoT Dataspace ServicesOn Supporting Contract-aware IoT Dataspace Services
On Supporting Contract-aware IoT Dataspace Services
 
Towards the Realization of Multi-dimensional Elasticity for Distributed Cloud...
Towards the Realization of Multi-dimensional Elasticity for Distributed Cloud...Towards the Realization of Multi-dimensional Elasticity for Distributed Cloud...
Towards the Realization of Multi-dimensional Elasticity for Distributed Cloud...
 
On Engineering Analytics of Elastic IoT Cloud Systems
On Engineering Analytics of Elastic IoT Cloud SystemsOn Engineering Analytics of Elastic IoT Cloud Systems
On Engineering Analytics of Elastic IoT Cloud Systems
 
HINC – Harmonizing Diverse Resource Information Across IoT, Network Functions...
HINC – Harmonizing Diverse Resource Information Across IoT, Network Functions...HINC – Harmonizing Diverse Resource Information Across IoT, Network Functions...
HINC – Harmonizing Diverse Resource Information Across IoT, Network Functions...
 
SINC – An Information-Centric Approach for End-to-End IoT Cloud Resource Prov...
SINC – An Information-Centric Approach for End-to-End IoT Cloud Resource Prov...SINC – An Information-Centric Approach for End-to-End IoT Cloud Resource Prov...
SINC – An Information-Centric Approach for End-to-End IoT Cloud Resource Prov...
 
Governing Elastic IoT Cloud Systems under Uncertainties
Governing Elastic IoT Cloud Systems under UncertaintiesGoverning Elastic IoT Cloud Systems under Uncertainties
Governing Elastic IoT Cloud Systems under Uncertainties
 
SmartSociety – A Platform for Collaborative People-Machine Computation
SmartSociety – A Platform for Collaborative People-Machine ComputationSmartSociety – A Platform for Collaborative People-Machine Computation
SmartSociety – A Platform for Collaborative People-Machine Computation
 
On Developing and Operating of Data Elasticity Management Process
On Developing and Operating of Data Elasticity Management ProcessOn Developing and Operating of Data Elasticity Management Process
On Developing and Operating of Data Elasticity Management Process
 

Recently uploaded

The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...
The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...
The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...ranjana rawat
 
Introduction and different types of Ethernet.pptx
Introduction and different types of Ethernet.pptxIntroduction and different types of Ethernet.pptx
Introduction and different types of Ethernet.pptxupamatechverse
 
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...ranjana rawat
 
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLSMANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLSSIVASHANKAR N
 
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptxDecoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptxJoão Esperancinha
 
Porous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writingPorous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writingrakeshbaidya232001
 
Processing & Properties of Floor and Wall Tiles.pptx
Processing & Properties of Floor and Wall Tiles.pptxProcessing & Properties of Floor and Wall Tiles.pptx
Processing & Properties of Floor and Wall Tiles.pptxpranjaldaimarysona
 
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130Suhani Kapoor
 
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...Christo Ananth
 
Introduction to Multiple Access Protocol.pptx
Introduction to Multiple Access Protocol.pptxIntroduction to Multiple Access Protocol.pptx
Introduction to Multiple Access Protocol.pptxupamatechverse
 
College Call Girls Nashik Nehal 7001305949 Independent Escort Service Nashik
College Call Girls Nashik Nehal 7001305949 Independent Escort Service NashikCollege Call Girls Nashik Nehal 7001305949 Independent Escort Service Nashik
College Call Girls Nashik Nehal 7001305949 Independent Escort Service NashikCall Girls in Nagpur High Profile
 
Introduction to IEEE STANDARDS and its different types.pptx
Introduction to IEEE STANDARDS and its different types.pptxIntroduction to IEEE STANDARDS and its different types.pptx
Introduction to IEEE STANDARDS and its different types.pptxupamatechverse
 
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service NashikCall Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service NashikCall Girls in Nagpur High Profile
 
Extrusion Processes and Their Limitations
Extrusion Processes and Their LimitationsExtrusion Processes and Their Limitations
Extrusion Processes and Their Limitations120cr0395
 
Microscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptxMicroscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptxpurnimasatapathy1234
 
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINEMANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINESIVASHANKAR N
 
Booking open Available Pune Call Girls Koregaon Park 6297143586 Call Hot Ind...
Booking open Available Pune Call Girls Koregaon Park  6297143586 Call Hot Ind...Booking open Available Pune Call Girls Koregaon Park  6297143586 Call Hot Ind...
Booking open Available Pune Call Girls Koregaon Park 6297143586 Call Hot Ind...Call Girls in Nagpur High Profile
 
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...ranjana rawat
 
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICSAPPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICSKurinjimalarL3
 

Recently uploaded (20)

The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...
The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...
The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...
 
Introduction and different types of Ethernet.pptx
Introduction and different types of Ethernet.pptxIntroduction and different types of Ethernet.pptx
Introduction and different types of Ethernet.pptx
 
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
 
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLSMANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
 
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptxDecoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
 
Porous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writingPorous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writing
 
Processing & Properties of Floor and Wall Tiles.pptx
Processing & Properties of Floor and Wall Tiles.pptxProcessing & Properties of Floor and Wall Tiles.pptx
Processing & Properties of Floor and Wall Tiles.pptx
 
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
 
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
 
Introduction to Multiple Access Protocol.pptx
Introduction to Multiple Access Protocol.pptxIntroduction to Multiple Access Protocol.pptx
Introduction to Multiple Access Protocol.pptx
 
College Call Girls Nashik Nehal 7001305949 Independent Escort Service Nashik
College Call Girls Nashik Nehal 7001305949 Independent Escort Service NashikCollege Call Girls Nashik Nehal 7001305949 Independent Escort Service Nashik
College Call Girls Nashik Nehal 7001305949 Independent Escort Service Nashik
 
Introduction to IEEE STANDARDS and its different types.pptx
Introduction to IEEE STANDARDS and its different types.pptxIntroduction to IEEE STANDARDS and its different types.pptx
Introduction to IEEE STANDARDS and its different types.pptx
 
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service NashikCall Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
 
DJARUM4D - SLOT GACOR ONLINE | SLOT DEMO ONLINE
DJARUM4D - SLOT GACOR ONLINE | SLOT DEMO ONLINEDJARUM4D - SLOT GACOR ONLINE | SLOT DEMO ONLINE
DJARUM4D - SLOT GACOR ONLINE | SLOT DEMO ONLINE
 
Extrusion Processes and Their Limitations
Extrusion Processes and Their LimitationsExtrusion Processes and Their Limitations
Extrusion Processes and Their Limitations
 
Microscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptxMicroscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptx
 
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINEMANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
 
Booking open Available Pune Call Girls Koregaon Park 6297143586 Call Hot Ind...
Booking open Available Pune Call Girls Koregaon Park  6297143586 Call Hot Ind...Booking open Available Pune Call Girls Koregaon Park  6297143586 Call Hot Ind...
Booking open Available Pune Call Girls Koregaon Park 6297143586 Call Hot Ind...
 
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
 
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICSAPPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
 

QoA4ML – A Framework for Supporting Contracts in Machine Learning Services

  • 1. QoA4ML – A Framework for Supporting Contracts in Machine Learning Services Hong-Linh Truong, Minh-Tri Nguyen Department of Computer Science https://rdsea.github.io
  • 2. Outline ▪ Context, scenario and research questions ▪ Key components of the QoA4ML framework ▪ Prototype and experiments ▪ Conclusions and future work September 9, 2021 IEEE International Conference on Web Services (ICWS) 2021 2
  • 3. Context ▪ Machine learning as a service becomes popular ▪ ML service providers offer ML services for different consumers ▪ Different stakeholders and interaction models ▪ Two stakeholders engagement: consumer and ML service provider ▪ Three stakeholders engagement: consumer, ML service provider and ML infrastructure/platform provider ▪ Key issue ▪ How do we support contracts between the ML service provider and other stakeholders? It is not just about performance! ▪ ML has several distinguishable attributes September 9, 2021 IEEE International Conference on Web Services (ICWS) 2021 3
  • 4. Scenario: predictive maintenance in Base Transceiver Stations (BTS) ▪ Dynamic inference from IoT data about equipment and infrastructure components in a BTS September 9, 2021 IEEE International Conference on Web Services (ICWS) 2021 4
  • 5. Key research questions & our approach ▪ Which are key attributes for ML contracts? ▪ How would ML attributes and constraints be specified? ▪ How would ML-specific attributes/constraints be monitored and evaluated? ▪ Approach ▪ Focus on ML-specific attributes ▪ Researchers have identified many attributes for ML models and systems ▪ Design ML contract specs suitable for cloud-native services ▪ Constraints, policies and monitoring reports ▪ Monitor ML attributes for contract monitoring September 9, 2021 IEEE International Conference on Web Services (ICWS) 2021 5
  • 6. QoA4ML framework – important attributes for ML-specific contracts ▪ Focus on important categories ▪ Inference Accuracy, Reliability and Elasticity, Quality of Data, Security and Privacy, Fairness and Interpretability and Cost September 9, 2021 IEEE International Conference on Web Services (ICWS) 2021 6
  • 7. QoA4ML specifications ▪ Decoupling attributes/constraints vs policies ▪ Required attributes and their constraints can be changed and updated at runtime ▪ Policies to check attributes and constraints can be implemented in different ways ▪ Monitoring probes and other utilities supporting observability ▪ New probes for quality of data and ML models ▪ Need to be instrumented and deployed to capture runtime attributes ▪ Must be well integrated with common monitoring features September 9, 2021 IEEE International Conference on Web Services (ICWS) 2021 7
  • 8. QoA4ML specification - the initial implementation September 9, 2021 IEEE International Conference on Web Services (ICWS) 2021 8
  • 9. Constraints for the BTS ML service ▪ Use terms in the QoA4ML specs ▪ Attributes and constraints can be changed September 9, 2021 IEEE International Conference on Web Services (ICWS) 2021 9
  • 10. Example of policies for validating contract constraints ▪ Is based on Rego ▪ Can load contract terms from JSON and compare with runtime monitoring ▪ Can be changed at runtime September 9, 2021 IEEE International Conference on Web Services (ICWS) 2021 10
  • 11. Monitoring utilities and Observability Service September 9, 2021 IEEE International Conference on Web Services (ICWS) 2021 11 Design for different engines to be used Reuse well-known monitoring systems Monitor ML-specific attributes
  • 12. Current prototype ▪ QoA4ML Specs: initial version based on JSON ▪ Use OPA (https://www.openpolicyagent.org/) as engine ▪ Rego and JSON are used for policies, attributes and constraints ▪ QoA4ML Observability as microservices ▪ Using state-of-the-art monitoring tools like Prometheus/Grafana ▪ Testing environments ▪ Edge and cloud infrastructures ▪ Source code is currently being pushed into: ▪ https://github.com/rdsea/QoA4ML September 9, 2021 IEEE International Conference on Web Services (ICWS) 2021 12
  • 13. Experiments ▪ Dynamic inferences of BTS load of power grid ▪ LSTM, TensorFlow ▪ IoT data from BTS (several months) ▪ Training in cloud and export to the edge (BTS-model-edge) and retraining several times in the cloud (BTS-model-cloud) ▪ Deployment ▪ Contracts: ▪ ResponseTime ▪ Inference Accuracy ▪ Data Quality September 9, 2021 IEEE International Conference on Web Services (ICWS) 2021 13
  • 14. Effect of edge and cloud serving platform deployment in ML contracts. September 9, 2021 IEEE International Conference on Web Services (ICWS) 2021 14 Both consumer and service are in the same edge; 3000 records per 15 minutes Both consumer and broker are in the same edge Broker is in the cloud
  • 15. Impact of violation monitoring All services in the edge (except the observability) September 9, 2021 IEEE International Conference on Web Services (ICWS) 2021 15 Help to detect outdated models in ML services: violation changes when retraining models Help to see correlations among attributes: data quality and inference accuracy
  • 16. Conclusions and future work ▪ QoA4ML is a framework to support ML service contracts ▪ Contract specifications (constraints and policies), tools and services ▪ QoA4ML benefits ▪ Establish contracts, moving to the step of continuous testing and observability of ML production ▪ Support flexible contracts and policies, enabling reuses and real- world ML services integration ▪ Future work ▪ Extending ML attributes and specifications; integration with cloud service contracts; new probes and observability capabilities September 9, 2021 IEEE International Conference on Web Services (ICWS) 2021 16
  • 17. Thanks! Hong-Linh Truong Department of Computer Science rdsea.github.io IEEE International Conference on Web Services (ICWS) 2021 17 September 9, 2021