Ensemble Q-Learning Algorithm: An effective and novel approach for task offloading in Edge Computing

Malik, Rakesh (2023) Ensemble Q-Learning Algorithm: An effective and novel approach for task offloading in Edge Computing. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (764kB) | Preview

Abstract

Q-Learning algorithm has emerged as a prominent approach for optimizing task offloading strategies in edge computing environments. Task offloading which is an aspect of edge computing, requires algorithms to strike a balance between resource utilization and power consumption. This research introduces the formulation of an Ensemble Q-Learning algorithm as a solution to improve the efficiency of task offloading mechanisms. Driven by the need to enhance resource utilization and address growing concerns about power consumption the proposed algorithm incorporates a Q-Learning strategy. Taking inspiration from Random Migration, Q-Learning and Graph Convolutional Network (GCN) based Q-Learning, the Ensemble Q-Learning algorithm utilizes replay and buffer mechanisms to enhance adaptability and performance. Simulation results demonstrate a 44% reduction in power consumption compared to existing algorithms confirming the effectiveness of the proposed Ensemble Q-Learning algorithm. The findings align with the research objective of advancing sustainability and resource efficiency in edge computing systems. However, it is important to acknowledge that simulation environments have limitations. Therefore future work aims to refine and validate the proposed algorithm in real world scenarios by considering real time network conditions and evolving edge computing architectures.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Mijumbi, Rashid 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 > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Ciara O'Brien
Date Deposited:	08 Apr 2025 17:51
Last Modified:	08 Apr 2025 17:51
URI:	https://norma.ncirl.ie/id/eprint/7389

Actions (login required)

View Item