Prediction of photovoltaic power output based on similar day analysis, genetic algorithm and extreme learning machine. (1st August 2020)

• Record Type: Journal Article
• Authors: Zhou, Yi; Zhou, Nanrun; Gong, Lihua; Jiang, Minlin
• Is Part Of: Energy. Volume 204(2020)
• Publication Date: 2020-08-01
• Subjects: Photovoltaic power prediction -- Similar day analysis -- Genetic algorithm -- Extreme learning machine; Power resources -- Periodicals; Power (Mechanics) -- Periodicals; Energy consumption -- Periodicals; 333.7905
• DOI: 10.1016/j.energy.2020.117894
• Languages: English
• ISSNs: 0360-5442

Abstract

Abstract: Recently, many machine learning techniques have been successfully employed in photovoltaic (PV) power output prediction because of their strong non-linear regression capacities. However, single machine learning algorithm does not have stable prediction performance and sufficient generalization capability in the prediction of PV power output. In this work, a hybrid model (SDA-GA-ELM) based on extreme learning machine (ELM), genetic algorithm (GA) and customized similar day analysis (SDA) has been developed to predict hourly PV power output. In the SDA, Pearson correlation coefficient is employed to measure the similarity between different days based on five meteorological factors, and the data samples similar to those from the target forecast day are selected as the training set of ELM. This operation can effectively increase the number of useful samples and reduce the time consumption on training data. In the ELM, the optimal values of the hidden bias and the input weight are searched by GA to improve the prediction accuracy. The performance of the proposed forecast model is evaluated with coefficient of determination ( R 2 ), mean absolute error (MAE) and normalized root mean square error (nRMSE). The results show that the SDA-GA-ELM model has higher accuracy and stability in day-ahead PV power prediction. Highlights: An accurate day-ahead prediction model is proposed for photovoltaic power output. The genetic algorithm is implemented to automatically perform parameter selection. The similar day analysis is designed to improve the quality of training dataset. The proposed SDA-GA-ELM model performs well in accuracy, stability and efficiency.