Han Li ^* Shuai Jie Zhu Haoyang Zhao ^* Yanqiang He ^*

• Zhengzhou University of Light Industry, Zhengzhou, China

The widespread use of mobile devices and compute-intensive apps has led to more smart devices being connected to networks, generating significant data. Real-time and efficient execution faces challenges due to limited resources and demanding applications. In response, an Enhanced Whale Optimization Algorithm (EWOA) is proposed for task scheduling in edge computing environments. Firstly, create a multi-objective model based on CPU, memory, time, and resource utilization. Second, this goal model is transformed into solving the whale optimization problem, the fitness function is set up, and applying the chaotic mapping to population initialization and global search phases, thus preserving population variety and preventing premature convergence. To address the issue of slow convergence in the traditional whale algorithm, a nonlinear convergence factor is introduced to adjust the balance between local and global search. The fitness function is optimized so that the task scheduling algorithm can achieve multi-objective optimization. Finally, an experimental environment for edge computing is built, and EWOA is compared and analyzed with ODTS, WOA, HWACO, and CATSA algorithms. The numerous experiment results show that the EWOA algorithm cost is decreased by 29.22%, the average time to completion is decreased by 17.04%, and the node resource utilization is enhanced by 9.5%. However, this study has some limitations, such as the lack of consideration for possible network delays and disconnections caused by user mobility. Despite these limitations, EWOA offers an effective solution for task scheduling in edge computing environments and highlights potential areas for improvement in future research. Future studies will focus on exploring fault-tolerant scheduling techniques that address dynamic user requirements, aiming to enhance the robustness and quality of service in task scheduling.