Home > Published Issues > 2019 > Volume 8, No. 4, July 2019 >

Electricity Load Forecasting in Thailand Using Deep Learning Models

Pyae P. Phyo, Chawalit Jeenanunta, and Kiyota Hashimoto

Pyae P. Phyo 1, Chawalit Jeenanunta 1, and Kiyota Hashimoto 2
1. Sirindhorn Int. Inst. of Technology, Thammasat University, Pathum Thani, Thailand
2. Prince of Songkla University, ESSAND, Phuket, Thailand

Abstract—The objective of this research is to improve the short-term load forecasting accuracy using deep learning models such as long short-term memory (LSTM) and deep belief network (DBN). The required historical data is provided by Electricity Generating Authority of Thailand (EGAT). Long short-term memory model which can learn to store time series data in memory and solve long dependencies problems and deep belief network model are investigated to overcome back propagation problems in the network. The proposed models are trained and tested using the cleaned data during the period of January 2016 to January 2017 by smoothing the raw data. Mean absolute percentage error (MAPE) and root mean square error (RMSE) are used to measure the forecasting accuracy. In this research, the results generated by the LSTM model are compared with those of the DBN model. The results show that the LSTM model execute higher accuracy performance than the DBN model. 

 
Index Terms—short-term electricity load forecasting, long short-term memory, deep belief network, mean absolute percentage error, root mean square error

Cite: Pyae P. Phyo, Chawalit Jeenanunta, and Kiyota Hashimoto, "Electricity Load Forecasting in Thailand Using Deep Learning Models," International Journal of Electrical and Electronic Engineering & Telecommunications,  Vol. 8, No. 4, pp. 221-225, July 2019. Doi: 10.18178/ijeetc.8.4.221-225