Similar day selecting based neural network model and its application in short-term load forecasting
Yujun He, Youchan Zhu, Jiancheng Gu, Chengqun Yin · 2005
Short-term load forecasting has always been the essential part of reliable and economic operation in power system. In this paper, a new strategy, suitable for selecting the training set for the neural network is presented. This strategy uses similarity degree parameter to identify the appropriate historical load data as training set for neural network. This similar days selecting method can effectively avoid the problem of holiday and abrupt changes in influential factors, which make some historical load data unlikely for training the network. In addition, a neural network with back propagation momentum training algorithm is proposed for load forecasting in order to reduce training time and improve convergence speed. The effectiveness of the model has been tested using Hebei province daily load data. Using the presented model, the improved forecasting accuracy and learning potency can be achieved.