Short-term Electricity Price Forecast of Electricity Market Based on E-BLSTM Model
DOI: 10.23977/acss.2019.31003 | Downloads: 17 | Views: 947
Wang Baoyi 1, Ji Xiaoqiong 1, Zhang Shaomin 1
1 School of Control and Computer Engineering, North China Electric Power University, Baoding, 071003, China
Corresponding AuthorWang Baoyi
The price changes in the electricity market will adversely affect the utility revenue and user cost. The current electricity price forecasting method has a low degree of utilization of its periodic variation law and a short forecast step size, which makes the electricity price forecast have large errors. A two-way LSTM model based on ELU activation function is proposed to predict the short-term electricity price change on the supply side of the power market. The gradient disappearance problem in the back propagation calculation process is optimized by ELU, and the accuracy of electricity price prediction is improved. Experiments on models and algorithms in the electricity price database of the PJM power market in the United States show that compared with the ARIMA and ARMA models, the proposed model has higher accuracy, and the algorithm converges to a lower loss rate, which can provide greater fluctuations in the supply side of the power market. The electricity price is accurately predicted.
KEYWORDSLong-term and short-term memory, deep learning, electricity price forecast, electricity market
CITE THIS PAPER
Baoyi, W., Xiaoqiong, J., Shaomin, Z., Short-term Electricity Price Forecast of Electricity Market Based on E-BLSTM Model, Advances in Computer, Signals and Systems (2019) 3: 15-20. DOI: http://dx.doi.org/10.23977/acss.2019.31003.
 Li M A, Menghua F, Lei G., et al. Latest Development Trends of International Electricity Markets and Their Enlightenment [J]. Automation of Electric Power Systems, 2014, 38(13):1-9.
 Yin J, Wang S, Gong L. The Effects of Factor Market Distortion and Technical Innovation on China’s Electricity Consumption [J]. Journal of Cleaner Production, 2018, 188:195-202.
 Ziel F, Weron R. Day-ahead Electricity Price Forecasting with High-dimensional Structures: Univariate vs. Multivariate Modeling Frameworks [J]. Energy Economics, 2018, 70:396-420.
 Zhao Z , Wang C , Nokleby M , et al. Improving Short-Term Electricity Price Forecasting Using Day-Ahead LMP with ARIMA Models[J]. 2018.
 He Y, Liu R, Li H, et al. Short-term Power Load Probability Density Forecasting Method Using Kernel-based Support Vector Quantile Regression and Copula Theory [J]. Applied Energy, 2017, 185:254-266.
 Xin W, Ji W U, Chao L, et al. Exploring LSTM Based Recurrent Neural Network for Failure Time Series Prediction [J]. Journal of Beijing University of Aeronautics & Astronautics, 2018.
 Anbazhagan S, Kumarappan N. Day-Ahead Deregulated Electricity Market Price Forecasting Using Recurrent Neural Network [J]. IEEE Systems Journal, 2013, 7(4):866-872.
 Karim F., Majumdar S., Darabi H., et al. LSTM Fully Convolutional Networks for Time Series Classification [J]. IEEE Access, 2017, 6(99):1662-1669.
 Djork-Arné Clevert, Unterthiner T., Hochreiter S. Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) [J]. Computer Science, 2015.
 Ide H., Kurita T. Improvement of Learning for CNN with ReLU Activation by Sparse Regularization[C]// International Joint Conference on Neural Networks. IEEE, 2017.