A Hybrid Strategy Whale Optimization Algorithm for Edge Computing Task Scheduling

For the task scheduling problem in edge computing scenarios, whale optimization algorithm (WOA) can be used to solve this non-deterministic polynomial situation (NP-hard). However, WOA is prone to local extreme values and slow convergence speed. To address these issues, we developed an innovative algorithm incorporating adaptive weights, Levy flight strategies, and Gaussian variation to improve the whale optimization algorithm’s global search capacity and convergence speed, ultimately helping to reduce delays and energy consumption in edge computing task scheduling. We applied the new algorithm to solve edge computing task scheduling problems using Matlab, simulating varying numbers of edge nodes and tasks. Subsequently, we compared our algorithm with four benchmark algorithms, including the original whale algorithm and other improved versions. The results demonstrate that our algorithm outperforms others in relation to optimization delay, energy consumption, and overall efficacy, demonstrating its efficacy in addressing the edge computing task scheduling problem.