Power Material Demand Forecasting Method Based on Support Vector Regression Machine

With the increasing demand for electric power, the demand for electric power supplies is also increasing day by day. At the same time, the power industry is faced with many problems such as many suppliers, long procurement cycle, difficult demand forecast and inventory control, which brings great challenges to the demand management and inventory management of power supplies. Accurate electricity material demand forecast can not only ensure the normal operation of the enterprise, but also reduce the inventory cost and improve the competitiveness of the enterprise. In this paper, the demand of power supplies of a power grid enterprise is taken as an example, and based on the demand characteristics of power supplies, a support vector regression model is established to predict it. The prediction results show that most of the materials can be predicted to meet the use requirements except for a few materials that do not have the prediction conditions, and the prediction effect is good, the accuracy can reach 90%, which provides a model reference for the material demand prediction of electric power enterprises.