Loading...

Modeling and Simulation of Edge Computing Environments via Device-to-Device Communication Method

Mohammadi, Ali | 2021

460 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 53630 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Izadi, Mohammad
  7. Abstract:
  8. In order to use the high performance capabilities of a computing system, first it is required to provide a proper modelling for the job and the system's environment. Second, it is required to design scheduling and offloading algorithms based on the job and the system modeling and third for evaluating the performance of these algorithms. It is needed to either simulate them or prove their approximation factors. This project aims to carry out these three parts for the Edge Computing environment. The laid out model of the system in this thesis consists of many devices that are distributed around the network, which they can execute tasks parallel to each other, and between each two devices there is D2D communication. Both computing speed of devices and communication capacity of links are assumed to be heterogeneous. Additionally, the application program or the job that is needed to be scheduled is modelled as a set of dependent tasks that are represented by a DAG.In the first part of this thesis the Min-Min algorithm has been improved in two steps. The first step is for improving the order of selecting the tasks for scheduling and the second step improves the algorithm by adding the expected data transmission delay to the expected completion time of each task and then a new greedy algorithm for offloading has been designed. Finally, the performance of these algorithms have been evaluated by implementation and simulation. In the second part of the thesis, the similar existing mixed-integer programming of the problem has been reformed and two approximation algorithms with the factors of O(k(n/m+1)) and O((log⁡m )^2) have been provided
  9. Keywords:
  10. Scheduling ; Distributed Computing ; Offloading ; Edge Computing ; Heterogeneous Devices

 Digital Object List