Loading...

Job Scheduling for Edge-Cloud Computing in IoT Systems

Sojoudi Haghighi, Majid | 2022

49 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 55758 (05)
  4. University: Sharif University of Technology
  5. Department: Electrical Engineering
  6. Advisor(s): Shah Mansouri, Hamed; Namvar, Mehrzad
  7. Abstract:
  8. IoT-based systems use cloud computing servers that are generally far away from them to perform tasks. Whenever there is a computational task that requires heavy and complex processing, the problem of offloading decision is to identify the best computing server to perform the processing related to this task. Numerous dynamic factors affect the solution to this problem.Optimization in energy consumption of the device that has generated a task alongside reducing its calculation delay can be applied in solving the offloading problem. The optimization problem that is formed to minimize the energy consumption in the offloading decision is an integer programming problem that is generally difficult to solve. Thus, it causes the offloading decision problem which is made under very dynamic conditions to be even more difficult. In order to solve such optimization problem, we need all information to be available in a centralized controller.Fuzzy systems are promising to deal with dynamic conditions and by using them when making offloading decisions, we can enhance the computational task execution and satisfy their constraints. However, in the literature, energy optimization has not been properly addressed as the fuzzy systems are different from classic optimization theory. In this thesis, we intelligently include the optimization of energy consumption in the decisions that are made with the help of fuzzy systems. This enables us to take the advantage of the fuzzy systems while solving the offloading decision problem with the objective of optimizing energy consumption. Through the numerical experiments, we show how our fuzzy-based algorithm reduces the energy consumption.Results further show that the offloading decisions can be made with a 94% accuracy.
  9. Keywords:
  10. Internet of Things ; Fuzzy Systems ; Resources Allocation ; Offloading ; Edge Computing ; Energy Consumption Optimization

 Digital Object List

 Bookmark

No TOC