Optimization of power grid metering material distribution based on improved grey wolf optimizer

With the continuous expansion of electricity consumption scale in Yunnan Power Grid, the demand for metering materials has surged significantly. Traditional material distribution methods face challenges such as constraints from mountainous terrain, stringent timeliness requirements, and significant demand fluctuations. Therefore, optimizing the distribution of power grid metering materials is urgently needed. To address these issues, this paper proposes a multi-objective optimization model that integrates demand forecasting and cost control. First, a Back Propagation (BP) neural network is employed to predict regional material demand, and an optimization model is constructed with the objective of minimizing total costs. To solve the model, an Improved Grey Wolf Optimizer (IGWO) based on a cosine convergence factor and nonlinear position update is designed, and population diversity is enhanced through Tent chaotic mapping. Simulation results show that the improved grey wolf algorithm improves convergence speed by 52.8% and reduces overall costs by 27.4% compared to the traditional algorithm, providing effective support for efficiency improvement and cost control in power grid logistics systems.