Energy-Latency Trade-Off Aware Load Balancing in Fog Computing Using Pareto-DQN Algorithm

Koh, Myungjee (2025) Energy-Latency Trade-Off Aware Load Balancing in Fog Computing Using Pareto-DQN Algorithm. Masters thesis, Dublin, National College of Ireland.

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

Abstract

Fog computing (FC) has emerged as a key paradigm for low-latency application. In contrast to the centralize computing model, a decentralized, heterogeneous FC acts as the intermediate node between the IoT devices and cloud server. Meanwhile, reducing energy consumption in computational infrastructure is directed toward is now of utmost priority. Although Fog computing offers an opportunity to reduce energy consumption by enabling localized processing, it still remains a conflicting nature of two objectives - latency and energy consumption. To address this issue, this paper proposes a dynamic load balancing strategy using Pareto Deep Q-Networks (PDQN) algorithm by focusing on the energy-latency trade-off. The Pareto front is a set of all non-dominate solutions, which directly captures the trade-offs between the objectives. PDQN algorithm integrates a deep reinforcement learning framework with Pareto front guided selection. This novelty lies in its ability to jointly optimize latency and energy objectives dynamically adapting to heterogeneous fog environments. The study contributes not only to achieve optimize among the fog nodes but also to supplement by cloud computing.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Gupta, Shaguna UNSPECIFIED
Subjects:	T Technology > T Technology (General) > Information Technology > Cloud computing Q Science > QA Mathematics > Electronic computers. Computer science > Computer Systems > Computers > Electronic data processing > Electronic data processing--Distributed processing > Edge computing T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science > Computer Systems > Computers > Electronic data processing > Electronic data processing--Distributed processing > Edge computing
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Ciara O'Brien
Date Deposited:	26 Mar 2026 14:31
Last Modified:	26 Mar 2026 14:31
URI:	https://norma.ncirl.ie/id/eprint/9228

Actions (login required)

View Item