Task Offloading Strategy of Multi-Objective Optimization Algorithm Based on Particle Swarm Optimization in Edge Computing

With the rapid development of edge computing and deep learning, the efficient deployment of deep neural networks (DNNs) on resource-constrained terminal devices faces multiple challenges (background), such as execution delay, high energy consumption, and resource allocation costs. This study proposes an improved Multi-Objective Particle Swarm Optimization (MOPSO) algorithm for PSO. Unlike the conventional PSO, our approach integrates a historical optimal solution detection mechanism and a dynamic temperature regulation strategy to overcome its limitations in this application scenario. First, an end–edge–cloud collaborative computing framework is constructed. Within this framework, a multi-objective optimization model is established, aiming to minimize time delay, energy consumption, and cloud configuration cost. To solve this model, an optimization method is designed that integrates a historical optimal solution detection mechanism and a dynamic temperature regulation strategy into the MOPSO algorithm. Experiments on six types of DNNs, including the Visual Geometry Group (VGG) series, have shown that this algorithm reduces execution time by an average of 58.6%, the average energy consumption by 61.8%, and optimizes cloud configuration costs by 36.1% compared to traditional offloading strategies. Its Global Search Capability Index (GSCI) reaches 92.3%, which is 42.6% higher than the standard PSO algorithm. This method provides an efficient, secure, and stable cooperative computing solution for multi-constraint task unloading in an edge computing environment.