Application of Computational Intelligent Technique Based on Combination of Fuzzy Classification and Entropy Theory in Power System
In this paper, a hybrid neural forecasting model with input variables selection and fuzzy clustering technique is presented. Based on entropy theory relevant ones are selected from all load influential factors. Next, considering the features of power load and reduced influential factors, we use fuzzy classification rules to divide the past load data into different network property. Then the representative historical load data samples are selected as the training set for neural network. Finally, Tabu search algorithm based on memory Neural Network forecasting model is constructed which can find global optimal solutions faster than the general Tabu search algorithm. And the effectiveness of the model has been tested using practical daily load data. The simulation results show that the presented intelligent technique for load forecasting can give better performance.
Wei Sun Ming Meng Yujun He
Department of Economics Management North China Electric Power University Baoding, Hebei, 071003, P. Department of Electronic Communication Engineering North China Electric Power University Baoding, He
国际会议
南宁
英文
2007-07-20（万方平台首次上网日期，不代表论文的发表时间）