Forecasting of short-term load based on fuzzy clustering and improved BP algorithm

A forecasting of short-term load method combine fuzzy clustering with one of the artificial neural network named BP neural is put forward. To create different typical load curves by means of fuzzy clustering technology which classify the load characteristics curves of different customers. Then take use of the typical curve whose type same with the predicted curve, associated with some factors which influence short-term load forecasting deeper, such as temperature, day type and humidity and so on to build relevant BP neural model. Aiming at the shortage of BP algorithm, the variable learning rate and the additional momentum are adopted to improve BP algorithm and predict short-term load. Through the classification of practical daily load curve samples and forecasting of short-term load proves that the proposed method possesses higher forecasting precision, having the feasibility in practical application.