Novel Edge Computing Offloading Method Based on Cooperative Optimization Learning Strategy of Whale Group

ABSTRACT With the rapid development of mobile cloud computing, the computational capability of edge devices has gradually attracted attention. Computation offloading is a strategy to improve computational efficiency and resource utilization by transferring computational tasks from the main device to edge devices or cloud nodes. Traditional computation offloading methods may have limitations when facing large‐scale and high‐real‐time tasks. To solve these problems, this article proposes a computation offloading method based on an improved whale optimization learning algorithm. First, the computational requirements of each device are planned using the topological sorting method, and the transmission time, energy consumption, and other parameters are determined. Then, a fitness function that considers both computation time and energy consumption is proposed, and the nonconvexity of this function is proved. Finally, the improved whale optimization learning algorithm is applied to the entire device group to solve the optimal offloading ratio. Experimental results show that our proposed strategy has good performance in reducing latency and energy consumption.