QoE-Aware Application Mapping and Energy-Aware Module Placement in Fog Computing with Offloading

Low, Choon Keat (2025) QoE-Aware Application Mapping and Energy-Aware Module Placement in Fog Computing with Offloading. Doctoral thesis, Tunku Abdul Rahman University of Management and Technology.

Text 48 Low Choon Keat.pdf Restricted to Registered users only Download (5MB)

Abstract

The rapid growth of Internet of Things (IoT) applications has increased the demand for low-latency processing, often causing traditional cloud-based systems to experience delays and reduced Quality of Experience (QoE) for end users. Fog computing addresses these limitations by extending computational resources closer to the network edge. However, existing application placement and resource management approaches in fog environments often fail to jointly optimise QoE, energy consumption, and workload distribution. This study proposes an integrated QoE-aware application deployment framework that incorporates three enhancement mechanisms: a fuzzy logic-based QoE-aware application mapping policy, a Dynamic Voltage and Frequency Scaling (DVFS)-based energy-aware module placement strategy, and an improved computation offloading algorithm. The framework aims to improve execution performance, optimise network usage, and maintain energy efficiency in fog environments. The proposed framework is evaluated using the iFogSim simulator across multiple applications and deployment scenarios. The results show that the QoE-aware method reduces execution time by 18.1% and network usage by 29.8%, with a minor energy increase of 1.26% compared to the Edgeward baseline. When energy-aware techniques are included, execution time improves further by 38.3%, and network usage decreases by 30.3%, although energy consumption increases by 3.39%. The full integration with enhanced offloading achieves the greatest improvements, reducing execution time by 48.6% and network usage by 41.0%, with an energy increase of 3.84%. Overall, the findings indicate that combining QoE-driven placement, energy-aware optimisation, and offloading mechanisms offers significant performance benefits. The integrated framework enhances application responsiveness, supports efficient resource utilisation, and contributes to improved user experience in fog computing environments.