OPTIMISING RESOURCE ALLOCATION AND OFFLOADING FOR LONG-TERM LOAD BALANCING SOLUTIONS IN FOG COMPUTING NETWORKS

Abstract

Nowadays, most emerging critical IoT applications have unique requirements and restrictions to operate efficiently; otherwise, they could be useless. Latency is one of these requirements. Fog computing (FC) is the complement system for cloud computing, proving it is the ideal computing environment for critical IoT applications. Distributed computing systems, such as FC, have an inherent problem when the computing units have different computing loads, called load difference problems. Offloading and service placement are some techniques used to fix these problems. Although prevalent offloading is the appropriate technique for this research, its procedures generate hidden costs in a system, such as decision time, distant offloading, and network congestion. Many researchers attempt to reduce these costs to get the results of static offloading (in stable environments). However, this research seeks to overcome the hidden costs in the prevalent offloading techniques to balance the load in a fog environment by utilising the sustainability concept. This research believes that increasing physical resources is the only way to improve efficiency as a long-term solution. The study consists of two consecutive phases. The first phase attempts to find the optimum solution between task offloading and service placement. The solution must revive the low-cost offloading solution. A sustainable load-balancing monitoring system (SlbmS) represents the second phase of this research. It is the comprehensive solution for the optimum solution to release its limitations. SlbmS uses the sustainability concept to solve the problem of the limitation of resources in edge computing using reinforcement learning. The experiment results of the two phases show that hybrid offloading outperforms the service placement policy in the first stage and prevalent offloading in the second stage when utilising the behaviour of static offloading to reduce the offloading costs in unpredictable environments. The study aims to explore a new area of research that attempts to amend the network topology to improve resource provisioning to provide a free resource at the network's edge. This research paved the way for a new dimension of analysis. It is the first research to recommend the physical expansion in the fog layer using the sustainability concept.