A Multi-Objective Genetic Algorithm Optimization of Delay and UAV Energy Consumption for Task Offloading in Flying Fog Computing

Abstract

This paper addresses the challenge of efficient task offloading in Fog Computing for Internet of Drones (IoD) applications by introducing a multi-objective optimization framework. Unlike previous studies that optimize either delay or energy consumption in isolation, our approach jointly considers both metrics through a hybrid architecture that combines Fog nodes (UAVs and base stations) with Cloud resources.  We propose and evaluate three multi-objective metaheuristic algorithms – Multi-Objective Particle Swarm Optimization (MOPSO), Multi-Objective Genetic Algorithm (MOGA), and Multi-Objective Ant Colony Optimization (MOACO) – to enhance offloading efficiency. Simulation results show that all three methods improve latency and UAV energy efficiency; however, MOGA consistently achieves the best overall performance in high-resource configurations. These results demonstrate MOGA’s effectiveness in managing the trade-off between offloading delay and energy consumption in dynamic UAV-based networks, confirming its potential for scalable and energy-efficient task offloading in future IoD-Fog Computing environments.