Peak Load Forecasting Using Hierarchical Clustering and RPROP Neural Network
Jin Liu, Yu Feng, Jilai Yu · 2006
In this paper, an approach is proposed for the daily loads prediction during the peak period, which combines the feed-forward neural network (FNN) using the resilient back propagation (RPROP) algorithm with the hierarchical clustering (HC) method. The HC method could offer clustering sets on different layers in selecting daily samples as a peak load pattern. The proposed predicting method proves to be more accurate and more quickly converge of FNN in the peak load forecasting by the simulating results to an actual power grid in China