Interval Forecast Method for Wind Power Based on GCN-GRU

Abstract

Interval prediction is to predict the range of power prediction intervals, which can guide electricity production and usage better. To improve further improve the performance of the prediction interval, this paper aims to investigate he wind power interval prediction method based on the lower and upper bound evaluation (LUBE). Firstly, an improved loss function is proposed, which transforms multi-objective optimization problems into single-objective optimization with guidance of mathematical derivation. Afterward, the interval prediction results can be further improved through a combination of graph convolutional network (GCN) and gate recurrent unit (GRU). Then, the tree-structured Parzen estimator (TPE) optimization algorithm optimizes the GCN cell to find the optimal parameter configuration and maximize the performance of the model. Finally, in the experimental part, the proposed GCN-GRU with improved loss function is compared with some current mainstream neural networks. The results show that for any type of network, the improved loss function can obtain prediction intervals with better performance. Especially for the prediction interval based on GCN-GRU, the prediction interval normalized average width (PINAW) and prediction interval relative deviation (PIRD) can reach 6.75% and 46.99%, respectively, while ensuring the given prediction interval nominal confidence (PINC).