Reliable Online Offloading Using Deep Reinforcement Learning In Mobile Edge Computing

Yadav, Kamal Nikhar (2023) Reliable Online Offloading Using Deep Reinforcement Learning In Mobile Edge Computing. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (2MB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

IOT Wireless devices(WDs) are resource constraint and the method that is widely opted to overcome this problem is task offloading. In this research, we consider a system in which there are multiple users in MEC network which has wireless channel that vary with time and stochastic data queues. We aim for designing an algorithm that will take care of online offloading in the least amount of time, while increasing the number of bits processed in given time frame. The algorithm is useful because the offloading decisions in online computation are decided without taking into consideration the future channel states and data queues. This is resolved by using Lyapunovs optimization and Deep Reinforcement learning in the framework called Reliable Online Offloading Using Deep Reinforcement Learning(RDRL). RDRL tackles the problem by first applying Lyapunov optimization on the MINLP problem and convert it into sub-problems. Then, RDRL then uses model-free approach to DRL to solve these sub-problems with low time complexity. The evaluation results show that RDRL achieves good computation rates with stable queues. Alongwith this it has very low time complexity which is advantageous for implementations in real-time decisions based on the environment.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Kazmi, Aqeel UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Cloud computing Q Science > QA Mathematics > Algebra > Algorithms > Computer algorithms T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Telecommunications > Computer networks > Internet of things
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Tamara Malone
Date Deposited:	19 Apr 2023 15:48
Last Modified:	19 Apr 2023 15:48
URI:	https://norma.ncirl.ie/id/eprint/6498

Actions (login required)

View Item