Integrated Model Forecasting of Electric Power Loads for Large Consumers Based on Fuzzy RBF Neural Network

Electricity load forecasting is the basis for power grid planning, scheduling and management. As the main and important service targets of power supply enterprises, accurate load forecasting can effectively ensure safe and stable economic operation of power grid. The development and application of data analysis technology provide new ideas and methods for the establishment of load forecasting models. Therefore, this paper applies a method based on fuzzy Radial Basis Function (RBF) neural network to build a comprehensive model of large customer loads. Firstly, the paper analyses the load characteristics of larger consumers, which are grouped by similarity and excluded from the data. Then, a prediction model is established for each type of typical load pattern based on the fuzzy RBF neural network algorithm of conjugate gradient. Next, the weights are determined by hierarchical analysis and entropy weight method to obtain the integrated model prediction. Finally, the reliability of the prediction method in this paper is verified through the analysis of examples.