A novel method for day-ahead solar power prediction based on hidden Markov model and cosine similarity

Abstract

Nowadays, with the emergence of new technologies such as smart grid and increasing the use of renewable energy in the grid, energy prediction has become more important in the electricity industry. Furthermore, with growing the integration of power generated from renewable energy sources into grids, an accurate forecasting tool for the reduction in undesirable effects of this scenario is essential. This study has developed a novel approach based on the hidden Markov model (HMM) for forecasting day-ahead solar power. The aim is to find a pattern of solar power changes at a given time in consecutive days. The proposed approach consists of two steps. In the first step, the cosine similarity is used to determine the similarity of solar power variations on consecutive days to a particular vector. In the second step, the obtained information from the first step is fed to HMM as a feature vector. These data are used for training and forecasting day-ahead solar power. After obtaining the preliminary results of the prediction, two known filters are utilized as post-processing to remove spikes and smooth the results. Finally, the performance of the proposed method is tested on real NREL data. No meteorological data (even solar radiation) are used; moreover, the model is fed only from the solar power of the past 23 days. To evaluate the proposed method, a feed-forward neural network and a simple HMM are examined with the same data and conditions. All three methods are tested with and without the post-processing. The results show that the proposed model is superior to other examined methods in terms of accuracy and computational time.