Short-term Load Forecasting Based On Fuzzy Neural Network

The level of load forecasting is one of the measures of modernization of power system management. It is important for making plans, distributing electricity. It can help saving the energy source. So load forecasting, especially accurate short-term load forecasting is of great importance to power system. There are many factors that affect system load, such as history data of load, many non-load factors.The dissertation analyzes the meaning and methods of power system load forecasting, explains the general theory and meaning of artificial neural network. Introduces fuzzy theory and studies of fuzzy neural network.Finally, according to the features of power load and considering the combined influence of temperature and day type, an approach based on fuzzy neural network is proposed for short-term load forecasting. After analyzing the original data provided by EUNITE network, and discussing the influencing factors of daily peak load, we chose the appropriate inputs for our network and build a fuzzy neural network forecasting model. Results show that fuzzy neural network is very effective in the short-term load forecasting. The study of influencing factors of short-term load forecasting is also significative.