how to best deploy your fog applications probably
play

How to best deploy your Fog applications, probably Stefano Forti - PowerPoint PPT Presentation

How to best deploy your Fog applications, probably Stefano Forti Ahmad Ibrahim Antonio Brogi 1 st International Conference on Fog and Edge Computing 2017 14 th May 2017 name.surname@di.unipi.it IoT and Cloud Computing 50 billion of connected


  1. How to best deploy your Fog applications, probably Stefano Forti Ahmad Ibrahim Antonio Brogi 1 st International Conference on Fog and Edge Computing 2017 14 th May 2017 name.surname@di.unipi.it

  2. IoT and Cloud Computing 50 billion of connected devices by 2020 • The Cloud alone cannot support the IoT momentum . • There is a need for filtering and processing before the Cloud. 2

  3. Fog Features QoS-awareness • App deployments dynamically adapt to the state of the network. Location-awareness • Position is known so to handle fluid and mobile computation. Context-awareness • Discover and use available resources, cooperating horizontally. 3

  4. Open Problems • How to automatically decide where to deploy each component of an application by exploiting QoS-, location-, and context-awareness? • How to estimate the QoS- assurance of a candidate deployment? 4

  5. Motivating example DataStorage Dashboard VDSL Sat. 3G ThingsController fire video moisture water 5

  6. H OW MANY AND HOW Concretely... POWERFUL F OG NODES DO I NEED TO ADEQUATELY DEPLOY MY APPLICATION ? S HOULD I DEPLOY THIS COMPONENT ONTO THE C LOUD , ONTO A F OG - AS - A -S ERVICE OPENED IN MY CITY OR ON MY PREMISES GATEWAY ? I S THERE ANY COMPONENT I’ D BETTER DEPLOY ON A DIFFERENT NODE AFTER THIS LINK / NODE FAILURE ? 6

  7. D O I HAVE TO UPGRADE Concretely … MY INFRASTRUCTURE IF THE APPLICATION I S IT POSSIBLE TO REQUIREMENTS CHANGE ? REDUCE RESOURCE CONSUMPTION OF SOME F OG NODES , OR AVOID THEM ? W HICH ARE THE ELIGIBLE DEPLOYMENTS THAT COMPLY MOST WITH THE REQUIRED Q O S ? 7

  8. Our Solution Modelling of IoT Algorithms to Evaluation of apps and Fog determine eligible output deployments infrastructures deployments via Monte Carlo 8

  9. Our Prototype https://github.com/di-unipi-socc/FogTorchPI 9

  10. QoS Profiles • A QoS profile is a pair ℓ, 𝑐 ↓ , 𝑐 ↑ A VERAGE DOWNLOAD A VERAGE L ATENCY & UPLOAD BANDWIDTH • They represent latency and bandwidth featured by a link or requested by a software interaction. 10

  11. Application 160 𝑛𝑡, 0.5 𝑁𝑐𝑞𝑡, 0.7 𝑁𝑐𝑞𝑡 SD video 11

  12. Infrastructure 98% ⟨70 𝑛𝑡, 6 𝑁𝑐𝑞𝑡, 0,75 𝑁𝑐𝑞𝑡⟩ 2% 70 𝑛𝑡, 0𝑁𝑐𝑞𝑡, 0 𝑁𝑐𝑞𝑡 Satellite 7M 12

  13. Compatibility ✓ X • A software component is compatible with a Fog or Cloud node when its software and hardware * can support at least that component. ✓ ✓ * Hardware only for Fog nodes. 13

  14. Things Binding • Software components may have Things requests. • Each request is bound to a specific Thing before deployment. ThingsController fire video moisture water 14

  15. Deployment Policy • A start-up sponsored by a specific Cloud provider, • an automated industrial plant, • an invoked third party service ... ...may enforce legal , commercial or political constraints for deploying an application. • We allow specification of a whitelist of nodes permitted for installing each component. 15

  16. Eligible Deployments • An eligible deployment for an application over a Fog infrastructure ensures Bandwidth and Compatibility and Hardware Things latency deployment policies resources binding 16

  17. Backtracking NP-hard Problem* strategy to explore the search space. [Garey, Michael R., and David S. Johnson. Computers and Intractability (1979)] * By reduction from Subgraph Isomorphism. 17 A. Brogi and S. Forti, QoS-aware Deployment of IoT Applications Through the Fog , in IEEE Internet of Things Journal, 2017.

  18. Bird’s eye view https://github.com/di-unipi-socc/FogTorchPI 18

  19. Monte Carlo Simulator Repeat a sufficiently large number of times: 1. Sample a QoS profile for each link in the infrastructure. 2. Run backtracking algorithm. Compute QoS-assurance of generated deployments. 19

  20. FogTorch Π Results W HICH ARE THE ELIGIBLE DEPLOYMENTS THAT COMPLY MOST WITH THE REQUIRED Q O S ? 20

  21. FogTorch Π Results (1) I S IT POSSIBLE TO REDUCE RESOURCE CONSUMPTION OF SOME F OG NODES , OR AVOID THEM ? E.g., avoid using fog_3 for deployment. 21

  22. FogTorch Π Results (1) I S IT POSSIBLE TO REDUCE RESOURCE CONSUMPTION OF SOME F OG NODES , OR AVOID THEM ? E.g., avoid using fog_3 for deployment. ✓ 22

  23. FogTorch Π Results (2) D O I HAVE TO UPGRADE MY INFRASTRUCTURE IF THE APPLICATION REQUIREMENTS CHANGE ? E.g., deploying HD video streaming without upgrade, leads to same QoS-assurance. 23

  24. FogTorch Π Results (2) D O I HAVE TO UPGRADE MY INFRASTRUCTURE IF THE APPLICATION REQUIREMENTS CHANGE ? X Deploying HD video streaming without upgrade, leads to worse QoS-assurance. 24

  25. Results FogTorch Π (3) 25

  26. Results FogTorch Π (3) ✓ 26

  27. Conclusions Determine, simulate QoS- and context- Evaluation of QoS and compare eligible awareness of variations impact deployments deployments based on links data 27

  28. Future Work Design a cost Include multiple Assessment over model to improve and multi-tenant case studies search & evaluation deployments 28

  29. Thanks ! Q&A

  30. Roles and Stakeholders

Recommend


More recommend