Deep Belief Network with Seasonal Decomposition for Solar Power Output Forecasting

Solar power is a type of renewable energy system that uses solar energy to produce electricity, and is regarded as one of the most important power sources in Taiwan. Since sunshine duration affects the amount of energy that can be generated by a solar power, the seasons of the year are important fac...

Full description

Saved in:
Bibliographic Details
Published in:International journal of reliability, quality, and safety engineering quality, and safety engineering, 2019-12, Vol.26 (6), p.1950029
Main Authors: Wang, Ching-Hsin, Lin, Kuo-Ping, Lu, Yu-Ming, Wu, Chih-Feng
Format: Article
Language:English
Subjects:
Alternative energy sources
Artificial intelligence
Autoregressive models
Belief networks
Decomposition
Economic forecasting
Neural networks
Photovoltaic cells
Power sources
Solar energy
Statistical analysis
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Solar power is a type of renewable energy system that uses solar energy to produce electricity, and is regarded as one of the most important power sources in Taiwan. Since sunshine duration affects the amount of energy that can be generated by a solar power, the seasons of the year are important factors that should be considered for accurate solar power prediction. In the last decade, the use of artificial intelligence for forecasting systems have been quite popular, and the deep belief network (DBN) models started getting more attention. In this study, a seasonal deep belief network (SDBN) was developed to forecast monthly solar power output data. The SDBN was constructed by combining seasonal decomposition method and DBN. Further, this study used monthly solar power output data from the Taiwan Power Company. The results indicated that the proposed forecasting system demonstrated a superior performance in terms of forecasting accuracy. Also, the performance of autoregressive integrated moving average (ARIMA), generalized regression neural network (GRNN), and DBN obtained from a separate study were compared to the performance of the proposed SDBN model and showed that the latter was better than the other three models. Thus, the SDBN model can be used as an alternative method for monthly solar power output data forecasting.
ISSN:0218-5393
1793-6446
DOI:10.1142/S0218539319500293