Research on Fog Computing Task Scheduling Based on Improved Gray Wolf Optimization Algorithm

In fog computing environments, inefficient user task scheduling leads to increased latency, which affects system performance. For this reason, a Dynamic Gray Wolf Optimization (DGWO) algorithm is proposed that aims to optimize task execution on fog nodes. The algorithm has minimizing task makespan, reducing cost and reducing energy consumption as an objective function. In the initial phase of the algorithm, the population is initialized by combining a greedy strategy with a stochastic approach to ensure the diversity of the solution set. To enhance the global search capability, the algorithm introduces a nonlinear multiple convergence factor with a dynamic weighting mechanism to avoid premature convergence. Meanwhile, the adaptability and convergence speed of the algorithm are enhanced by the dynamic elite strategy. Simulation results show that compared with other algorithms, the algorithm achieves a balanced improvement in key performance indicators, proving its effectiveness.