Solar Power Output Forecasting Using Seasonal Deep Belief Network  
Author Ching-Hsin Wang

 
Co-Author(s) Kuo-Ping Lin; Yu-Ming Lu; Chih-Feng Wu

 
Abstract Solar power is kind of renewable power which is regard as important power sources in Taiwan. This investigation develops a seasonal deep belief network (SDBN) to forecast monthly solar power output data. The construction of the SDBN combines seasonal decomposition method and deep belief network. Monthly solar power output data (from Taiwan Power Company) were used. Empirical results indicate that the proposed forecasting system demonstrates a superior performance in terms of forecasting accuracy. A comparative study has also been introduced showing that the SDBN model performance is better than autoregressive integrated moving average (ARIMA), generalized regression neural network (GRNN), deep belief network (DBN). Thus, the SDBN model is an alternative method for monthly solar power output data forecasting.

 
Keywords Solar power output, forecasting, seasonal deep belief network
   
    Article #:  2446
 
Proceedings ISSAT International Conference on Reliability and Quality in Design 2018
August 2-4, 2018 - Toronto, Ontario, Canada