Constrained Multi-Objective Decomposition Evolutionary Algorithm for UAVs-Assisted Mobile Edge Computing Networks

The increasing significance of unmanned aerial vehicles (UAVs) in mobile edge computing (MEC) has captured considerable attention. Nevertheless, the effectiveness of UAVs-assisted MEC networks is hampered by challenges such as limited communication capacity and onboard power. To tackle these issues, this study develops a constrained multi-objective optimization model designed to enhance the performance of UAVs-assisted MEC networks, focusing on system capacity, energy consumption, and task latency. As a result, this problem manifests as a complex constrained multi-objective optimization problem. The study then proposes a constrained multi-objective decomposition evolutionary algorithm (CMODEA) with low computational complexity. This algorithm employs an adaptive individual comparison strategy, balancing diversity and convergence, and integrates an optimally guided differential evolution strategy for efficiently approximating optimal solutions. Additionally, it incorporates an adaptive constraint handling method, effectively managing existing constraints. The CMODEA aims to simultaneously optimize system capacity, energy consumption, and task latency while meeting the computational resource requirements of UAVs and ensuring acceptable user task latency levels. Simulation results demonstrate the algorithm’s effectiveness in significantly enhancing capacity, reducing energy consumption and latency, without greatly increasing algorithm complexity.