Optimizing Load Balancing in Edge Computing: A Novel Algorithm Integrating Grey Wolf Optimizer and Tabu Search

The internet's evolution has highlighted cloud computing's limitations, such as latency and bandwidth issues, prompting interest in edge computing to address these. Effective load balancing is essential to fully leverage edge computing's benefits and improve network service quality. Traditionally, cloud computing load balancing focuses on optimizing data center resources by dynamically adjusting virtual machines. Conversely, edge computing requires load balancing among edge servers, enabling collaboration where less burdened servers assist overloaded ones with task processing. This paper introduces an edge computing load balancing algorithm combining the Grey Wolf Optimizer (GWO) and Tabu Search (TS). GWO provides initial global exploration, and TS refines the solution through local exploitation, balancing exploration and exploitation. Experiments confirm the algorithm's effectiveness in load balancing, response time, and energy efficiency, though further research is needed on its applicability across scenarios.