thingsjs towards a flexible and self adaptable middleware
play

ThingsJS: Towards a Flexible and Self-Adaptable Middleware for - PowerPoint PPT Presentation

Oct 15, 2023 •464 likes •855 views

Motivation ThingsJS Scheduling Code Migration Communications ThingsJS: Towards a Flexible and Self-Adaptable Middleware for Dynamic and Heterogeneous IoT Environments Middleware for IoT m4iot@Middleware 2017 Julien Gascon-Samson,

  1. Motivation ThingsJS Scheduling Code Migration Communications ThingsJS: Towards a Flexible and Self-Adaptable Middleware for Dynamic and Heterogeneous IoT Environments Middleware for IoT – m4iot@Middleware 2017 Julien Gascon-Samson, Mohammad Rafiuzzaman, Karthik Pattabiraman University of British Columbia Department of Electrical and Computer Engineering Vancouver, Canada December 11, 2017

  2. Motivation ThingsJS Scheduling Code Migration Communications Motivation 2 World of IoT growing at a very fast pace!

  3. Motivation ThingsJS Scheduling Code Migration Communications Motivation 2 World of IoT growing at a very fast pace! Traditionaly, processing was done in the cloud

  4. Motivation ThingsJS Scheduling Code Migration Communications Motivation 2 World of IoT growing at a very fast pace! Traditionaly, processing was done in the cloud Emerging trend: running applications on the IoT devices themselves (edge) Performance, costs, reliability

  5. Motivation ThingsJS Scheduling Code Migration Communications Goals and Motivation 3 ThingsJS: a framework for developing and deploying high-level applications on IoT devices (edge computing)

  6. Motivation ThingsJS Scheduling Code Migration Communications Goals and Motivation 4 Programmers are typically more productive in higher-level languages JavaScript: strong user base ThingsJS: a framework for developing and deploying high-level applications on IoT devices (edge computing)

  7. Motivation ThingsJS Scheduling Code Migration Communications Goals and Motivation 4 Programmers are typically more productive in higher-level languages JavaScript: strong user base ThingsJS: a framework for developing and deploying high-level applications on IoT devices (edge computing)

  8. Motivation ThingsJS Scheduling Code Migration Communications Goals and Motivation 4 Programmers are typically more productive in higher-level languages JavaScript: strong user base ThingsJS: a framework for JavaScript VMs on IoT developing and deploying Samsung IoT.js high-level applications on IoT devices (edge computing) Intel XDK DukServer Smart.js Node.js on IoT devices

  9. Motivation ThingsJS Scheduling Code Migration Communications Goals and Motivation 4 Programmers are typically Constraints more productive in IoT world is highly higher-level languages heterogeneous! JavaScript: strong user base Different hardware platforms JavaScript VMs on IoT OSes Environments Samsung IoT.js ThingsJS: Declarative Intel XDK language for expressing DukServer constraints Smart.js Over the devices Over the applications Node.js on IoT devices

  10. Motivation ThingsJS Scheduling Code Migration Communications Goals and Motivation 5 Scheduling Given a set of IoT applications (“components”) Given a set of constraints ThingsJS: a framework for ⇓ developing and deploying high-level applications on IoT devices (edge computing) Scheduling Applications 1 on IoT Devices

  11. Motivation ThingsJS Scheduling Code Migration Communications Goals and Motivation 5 Scheduling Given a set of IoT applications (“components”) Given a set of constraints ThingsJS: a framework for ⇓ developing and deploying high-level applications on IoT devices (edge computing) What is the optimal mapping Scheduling Applications 1 of components to devices? on IoT Devices Significant work on scheduling applications in the cloud – idea of scheduling applications in the edge is relatively novel

  12. Motivation ThingsJS Scheduling Code Migration Communications Goals and Motivation 6 Example: motion detection video_camera: tied to ThingsJS: a framework for hardware developing and deploying high-level applications on IoT motion_detect: detects devices (edge computing) motion Scheduling Applications 1 on IoT Devices

  13. Motivation ThingsJS Scheduling Code Migration Communications Goals and Motivation 6 Example: motion detection video_camera: tied to ThingsJS: a framework for hardware developing and deploying high-level applications on IoT motion_detect: detects devices (edge computing) motion Scheduling Applications 1 Some components on IoT Devices can/should be run in the cloud

  14. Motivation ThingsJS Scheduling Code Migration Communications Goals and Motivation 7 Migration ThingsJS: a framework for Conditions change over time developing and deploying IoT devices are high-level applications on IoT resource-constrained devices (edge computing) Scheduling Applications on 1 IoT Devices Migrating IoT 2 Applications

  15. Motivation ThingsJS Scheduling Code Migration Communications Goals and Motivation 7 Migration ThingsJS: a framework for Conditions change over time developing and deploying IoT devices are high-level applications on IoT resource-constrained devices (edge computing) Scheduling Applications on 1 It might be necessary to IoT Devices migrate components Migrating IoT 2 Applications

  16. Motivation ThingsJS Scheduling Code Migration Communications Goals and Motivation 7 Migration ThingsJS: a framework for Conditions change over time developing and deploying IoT devices are high-level applications on IoT resource-constrained devices (edge computing) Scheduling Applications on 1 It might be necessary to IoT Devices migrate components Migrating IoT 2 Prior work: migrating web Applications applications across browsers

  17. Motivation ThingsJS Scheduling Code Migration Communications Goals and Motivation 8 ThingsJS: a framework for Publish/Subcribe - MQTT developing and deploying Publish/subscribe maps well high-level applications on IoT to IoT (MQTT: iso standard) devices (edge computing) Scheduling Applications on 1 IoT Devices Migrating IoT Applications 2 Optimizing the 3 Communications

  18. Motivation ThingsJS Scheduling Code Migration Communications Goals and Motivation 8 ThingsJS: a framework for Publish/Subcribe - MQTT developing and deploying Publish/subscribe maps well high-level applications on IoT to IoT (MQTT: iso standard) devices (edge computing) Scheduling Applications on Significant work in 1 IoT Devices cloud/p2p pub/sub Migrating IoT Applications 2 Optimizing the 3 Communications

  19. Motivation ThingsJS Scheduling Code Migration Communications Goals and Motivation 8 ThingsJS: a framework for Publish/Subcribe - MQTT developing and deploying Publish/subscribe maps well high-level applications on IoT to IoT (MQTT: iso standard) devices (edge computing) Scheduling Applications on Significant work in 1 IoT Devices cloud/p2p pub/sub Migrating IoT Applications 2 Adapting pub/sub Optimizing the 3 architectures for IoT Communications

  20. Motivation ThingsJS Scheduling Code Migration Communications ThingsJS: IoT Runtime Middleware 9 Goals and Motivation 1 ThingsJS: IoT Runtime Middleware 2 Dynamic Scheduling 3 JavaScript Code Migration 4 Inter-Component Communications 5

  21. Motivation ThingsJS Scheduling Code Migration Communications ThingsJS 10

  22. Motivation ThingsJS Scheduling Code Migration Communications ThingsJS Application 11 Source Code: High-Level Language (i.e., Javascript - Node.js) Code written in terms of “components” Constraints: Physical: device-related Logical: component-related

  23. Motivation ThingsJS Scheduling Code Migration Communications ThingsJS Application 11 Source Code: High-Level Language (i.e., Javascript - Node.js) Code written in terms of “components” Constraints: CPU (workload units) Physical: device-related RAM Logical: Available incoming & component-related outgoing bandwidth

  24. Motivation ThingsJS Scheduling Code Migration Communications ThingsJS Application 11 Source Code: High-Level Language (i.e., Javascript - Node.js) Code written in terms of “components” Workload units Constraints: RAM Physical: device-related Incoming & outgoing bandwidth Logical: component-related Inter-component constraints: latency, bandwidth

  25. Motivation ThingsJS Scheduling Code Migration Communications ThingsJS Middleware 12

  26. Motivation ThingsJS Scheduling Code Migration Communications Dynamic Scheduling 13 Goals and Motivation 1 ThingsJS: IoT Runtime Middleware 2 Dynamic Scheduling 3 JavaScript Code Migration 4 Inter-Component Communications 5

  27. Motivation ThingsJS Scheduling Code Migration Communications Scheduling Applications on Things (1) 14 1 Predicting the workload of components Machine-learning Training: Several devices, different load profiles Monitoring performance (execution time) Construction of a model Predicting: Execution time on device With a specific load level 2 Scheduling the placement of components to devices

  28. Motivation ThingsJS Scheduling Code Migration Communications Scheduling Applications on Things (2) 15 1 Predicting the workload of components 2 Scheduling the placement of components to devices Given a set of constraints ...and the prediction model What is the optimal arrangement of components-to-devices? Respecting all constraints SMT Solver Most suitable global solution Rescheduling?

  29. Motivation ThingsJS Scheduling Code Migration Communications ThingsMigrate: Migrating JavaScript IoT Applications 16 Goals and Motivation 1 ThingsJS: IoT Runtime Middleware 2 Dynamic Scheduling 3 JavaScript Code Migration 4 Inter-Component Communications 5

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

1 Research Approach: the Kokyu Flexible Middleware Scheduling/Dispatching Framework Integration

1 Research Approach: the Kokyu Flexible Middleware Scheduling/Dispatching Framework Integration

Motivation for Studying Adaptive Middleware Flexible Scheduling in Middleware for Trends Distributed Rate-Based Real-Time Hardware keeps getting smaller, faster, & cheaper Applications Software keeps getting larger, slower, &

368 views • 5 slides
Framework for Analyzing Modular, Adaptable and Flexible Surface Combatants Dr. Norbert Doerry

Framework for Analyzing Modular, Adaptable and Flexible Surface Combatants Dr. Norbert Doerry

Framework for Analyzing Modular, Adaptable and Flexible Surface Combatants Dr. Norbert Doerry Dr. Philip Koenig SNAME Maritime Convention October 25-27, 2017 Houston, Texas Approved for Public Release 9/1/2017 1 Distribution is Unlimited

186 views • 18 slides
Middleware Chapter 2: Contents - Chapter 2 Understanding middleware Middleware as a

Middleware Chapter 2: Contents - Chapter 2 Understanding middleware Middleware as a

Middleware Chapter 2: Contents - Chapter 2 Understanding middleware Middleware as a programming abstraction Middleware as infrastructure A quick overview of conventional middleware platforms RPC TP Monitors Object

273 views • 24 slides
Generic component-based middleware for a peer-to-peer flexible robot architecture What is MT

Generic component-based middleware for a peer-to-peer flexible robot architecture What is MT

Generic component-based middleware for a peer-to-peer flexible robot architecture What is MT Robot AG? System description Middleware Description Generic Components Communication Patterns Preliminary Results

209 views • 18 slides
Exploiting Constraints to Build a Flexible and Extensible Data Stream Processing Middleware

Exploiting Constraints to Build a Flexible and Extensible Data Stream Processing Middleware

Exploiting Constraints to Build a Flexible and Extensible Data Stream Processing Middleware Workshop on Scalable Stream Processing Systems (SSPS) IPDPS 2010, Atlanta/Georgia, USA 19.04.2010 Nazario Cipriani, Carlos Lbbe, Alexander

450 views • 24 slides
A Flexible Simulator to Evaluate a Power Saving System for HPC Clusters Manuel F. Dolz, Juan C.

A Flexible Simulator to Evaluate a Power Saving System for HPC Clusters Manuel F. Dolz, Juan C.

ACM/IFIP/USENIX 12th International Middleware Conference 2nd International Workshop on Green Computing Middleware A Flexible Simulator to Evaluate a Power Saving System for HPC Clusters Manuel F. Dolz, Juan C. Fern andez, Sergio Iserte,

490 views • 25 slides
Java Middleware Patrick Eugster, Till Bay, Tomas Hruz Java Middleware What is middleware

Java Middleware Patrick Eugster, Till Bay, Tomas Hruz Java Middleware What is middleware

Chair of Software Engineering Languages in Depth Series: Java Programming Prof. Dr. Bertrand Meyer Java Middleware Patrick Eugster, Till Bay, Tomas Hruz Java Middleware What is middleware Client-server communication and method invocation

675 views • 65 slides
EOS: E Exactly xactly- -O Once E nce E- -S Service Middleware ervice Middleware EOS:

EOS: E Exactly xactly- -O Once E nce E- -S Service Middleware ervice Middleware EOS:

EOS: E Exactly xactly- -O Once E nce E- -S Service Middleware ervice Middleware EOS: German Shegalov, Gerhard Weikum Roger Barga, David Lomet (University of Saarland, Germany) (Microsoft Research, U.S.A.) PRESS THE SUBMIT BUTTON ONCE

467 views • 25 slides
Middleware Petr Tma Middleware Petr Tma This is a work in progress material created to

Middleware Petr Tma Middleware Petr Tma This is a work in progress material created to

Middleware Petr Tma Middleware Petr Tma This is a work in progress material created to support the Charles University Middleware lecture. It is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International

965 views • 72 slides
From Middleware Implementor to Middleware User (There and Back Again) Steve Vinoski Member of

From Middleware Implementor to Middleware User (There and Back Again) Steve Vinoski Member of

From Middleware Implementor to Middleware User (There and Back Again) Steve Vinoski Member of Technical Staff Verivue, Inc. Westford, MA USA Middleware 2009 4 December 2009 Friday, December 4, 2009 10 Years of Middleware! ...the 10th

771 views • 45 slides
All In Guiding Principles Commitment to Building Dignity Increase Sense of Ownership Flexible

All In Guiding Principles Commitment to Building Dignity Increase Sense of Ownership Flexible

All In Guiding Principles Commitment to Building Dignity Increase Sense of Ownership Flexible & Adaptable School Facilities School as a Joint Use Community Center Provide Safe Schools Foster Mentorship, Leadership & Reduce Achievement

375 views • 8 slides
Middleware Petr T uma Middleware by Petr T uma This material is a work in progress that

Middleware Petr T uma Middleware by Petr T uma This material is a work in progress that

Middleware Petr T uma Middleware by Petr T uma This material is a work in progress that is provided on a fair use condition to support the Charles University Middleware lecture. It should not be used for any other purpose than to support

1.05k views • 76 slides
Communication Middleware Software Layers 1.1 A distributed system organized as middleware. Note

Communication Middleware Software Layers 1.1 A distributed system organized as middleware. Note

Communication Middleware Software Layers 1.1 A distributed system organized as middleware. Note that the middleware layer extends over multiple machines. 2 Communication Alternatives Raw message passing TCP/IP: reliable byte stream

875 views • 26 slides
DARE: A Standards-based Middleware for Science Gateways http://radical.rutgers.edu EGI

DARE: A Standards-based Middleware for Science Gateways http://radical.rutgers.edu EGI

DARE: A Standards-based Middleware for Science Gateways http://radical.rutgers.edu EGI Manchester 09 th April , 2013 Distributed Application Runtime Environment (DARE) Design Objectives: Separation of Concerns: Agile, flexible user

381 views • 19 slides
NorduGrid NorduGrid collaboration: some history collaboration: some history collaboration: some

NorduGrid NorduGrid collaboration: some history collaboration: some history collaboration: some

NorduGrid NorduGrid and the ARC middleware and the ARC middleware and the ARC middleware NorduGrid NorduGrid and the ARC middleware Gergely Sipos (credits to Oxana Smirnova) MTA SZTAKI, Hungary GridKa School - September 14, 2006 - Karlsruhe

611 views • 24 slides
Entity Resolution: Glue for Middleware Hector Garcia-Molina Stanford University Middleware

Entity Resolution: Glue for Middleware Hector Garcia-Molina Stanford University Middleware

Entity Resolution: Glue for Middleware Hector Garcia-Molina Stanford University Middleware apps middleware ... System n System 1 2 Middleware apps middleware what matches what?? ... System n System 1 3 Matching Execution Level

794 views • 58 slides
Mary Uhl-Bien, Ph.D. BNSF Railway Endowed Professor of Leadership Neeley School of Business at

Mary Uhl-Bien, Ph.D. BNSF Railway Endowed Professor of Leadership Neeley School of Business at

How to Master the Art of Creating Adaptive Spaces Mary Uhl-Bien, Ph.D. BNSF Railway Endowed Professor of Leadership Neeley School of Business at TCU Key Questions What is adaptive space? How do we enable adaptive space (complexity

209 views • 20 slides
Multi-functional Learning Commons Presented by: Janet Nelson, Demco Session Overview: Changing

Multi-functional Learning Commons Presented by: Janet Nelson, Demco Session Overview: Changing

Planning for the Future of K-12 Libraries: Multi-functional Learning Commons Presented by: Janet Nelson, Demco Session Overview: Changing trends in education are driving changes in the library Evolution from book warehouse to

712 views • 50 slides
Learning to Adapt to Dynamic, Real- World Environments Chelsea Finn UC Berkeley Google Brain

Learning to Adapt to Dynamic, Real- World Environments Chelsea Finn UC Berkeley Google Brain

Learning to Adapt to Dynamic, Real- World Environments Chelsea Finn UC Berkeley Google Brain Stanford Savva et al. 19 Photorealistic simulators The real world is unmatched. Unmatched rich, multi-agent interactions diversity in terms of

442 views • 29 slides
DRIZZLE: FAST AND Adaptable STREAM PROCESSING AT SCALE Shivaram Venkataraman, Aurojit Panda, Kay

DRIZZLE: FAST AND Adaptable STREAM PROCESSING AT SCALE Shivaram Venkataraman, Aurojit Panda, Kay

DRIZZLE: FAST AND Adaptable STREAM PROCESSING AT SCALE Shivaram Venkataraman, Aurojit Panda, Kay Ousterhout , Michael Armbrust, Ali Ghodsi, Michael Franklin, Benjamin Recht, Ion Stoica STREAMING WORKLOADS Streaming Trends: Low latency Results

500 views • 35 slides
GCTD COVID-19 REPORT TO GCTD BOARD OF DIRECTORS June 3, 2020 WORKFORCE STATUS 191 Total

GCTD COVID-19 REPORT TO GCTD BOARD OF DIRECTORS June 3, 2020 WORKFORCE STATUS 191 Total

GCTD COVID-19 REPORT TO GCTD BOARD OF DIRECTORS June 3, 2020 WORKFORCE STATUS 191 Total Employees (All Departments) 0 COVID-19 employee positive cases Confirmed or self-reported 19 employees on COVID-19 leave Self-Quarantine or COVID-19

458 views • 17 slides
Comprehensive Airman Fitness (CAF) Newcomers Orientation Air Force Vision and Mission

Comprehensive Airman Fitness (CAF) Newcomers Orientation Air Force Vision and Mission

Comprehensive Airman Fitness (CAF) Newcomers Orientation Air Force Vision and Mission Vision A thriving and resilient Air Force Community ready to meet any challenge Mission Build and sustain a thriving and resilient Air Force

810 views • 52 slides
The Four Levels of Requirements Engineering for and in Dynamic Adaptive Systems Daniel M.

The Four Levels of Requirements Engineering for and in Dynamic Adaptive Systems Daniel M.

The Four Levels of Requirements Engineering for and in Dynamic Adaptive Systems Daniel M. Berry, U Waterloo Betty H.C. Cheng, Michigan State U Ji Zhang, Michigan State U 2005 D.M. Berry, B.H.C. Cheng, & J. Zhang Requirements

961 views • 78 slides
Towards Explicable and Adaptive DDoS Traffic Classification Yebo Feng, Jun Li University of

Towards Explicable and Adaptive DDoS Traffic Classification Yebo Feng, Jun Li University of

The 21st Passive and Active Measurement Conference (PAM 2020) Towards Explicable and Adaptive DDoS Traffic Classification Yebo Feng, Jun Li University of Oregon {yebof, lijun}@cs.uoregon.edu Towards Explicable and Adaptive DDoS Traffic

339 views • 10 slides

More recommend