An Optimal Edge Data Caching Scheme Based on Improved Particle Swarm Optimization

ABSTRACT

Mobile Edge Computing (MEC) alleviates the performance bottlenecks of traditional cloud computing in latency‐sensitive scenarios by moving computational resources to network edge nodes. In recent years, numerous research efforts have focused on developing edge data caching (EDC) strategies that enable app vendors to enhance caching performance through the strategic placement of critical data on suitable edge nodes. Despite the widespread adoption of evolutionary algorithms as effective optimization techniques, they have not yet been successfully applied to address the EDC problem. Therefore, this paper represents the first attempt to address the EDC problem by proposing a Particle Swarm Optimization (PSO)‐based EDC approach. More specifically, we model the EDC problem as a Constrained Optimization Problem (COP) and analyze its NP‐hardness. Then, we propose the EDC‐APSO algorithm, which approximates the solution front via evolution and directed mutation. We provide a theoretical analysis of the proposed method and conduct evaluations using a widely used real‐world dataset, comparing it against four representative methods. Experimental results demonstrate that our approach effectively addresses the EDC problem.