• CSCD核心库收录期刊
  • 中文核心期刊
  • 中国科技核心期刊

Electric Power Construction ›› 2018, Vol. 39 ›› Issue (10): 20-27.doi: 10.3969/j.issn.1000-7229.2018.10.003

Previous Articles     Next Articles

A Long Short Term Memory Based Deep Learning Method for Industrial Load Forecasting

YANG Jiajia1, LIU Guolong2, ZHAO Junhua2, WEN Fushuan3, DONG Zhaoyang1   

  1. 1. School of Electrical Engineering and Telecommunications, University of New South Wales,Sydney 2052, Australia;2. School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen 518100, Guangdong Province, China; 3. College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China
  • Online:2018-10-01
  • Supported by:
    This work is jointly supported by the Training Program of Major Research Plan of National Natural Science Foundation of China (No. 91746118), Shenzhen Municipal Science and Technology Innovation Committee International R&D Project (No. GJHZ20160301165723718) and Basic Research Project (No. JCYJ20170410172224515).

Abstract: Industrial load is mainly determined by the production schedule of a given factory, with a lower correlation to external factors such as temperature, time and demography. Under electricity market environment, accurate forecasting of industrial load is essential for industry end-users to develop profitable transaction plans. Given this background, this paper studied the short-term forecasting of industrial load and proposed a long short term memory (LSTM) network based deep learning algorithm for this purpose. Compared with some existing methods, the proposed LSTM-based deep learning algorithm is improved with respect to the following aspects. First, the proposed algorithm extended the layers of the deep learning network. Thus, both the capability of the network to extract information from historical data and the capability to forecast future load are strengthened. Secondly, the dropout technique is applied to each hidden layer composed of LSTM blocks, where a probability is assigned to a hidden unit in each layer of the network. The dropout technique can prevent the neural network from overfitting through the regularization. Consequently, the overall performance of the neural network is improved. Next, actual historical data of industrial load are used to test the proposed method. Case study results show that the proposed method can significantly improve the forecasting accuracy comparing with the auto-regressive and moving average model (ARMA), K nearest neighbor regression (KNN) and support vector regression (SVR) methods. Besides, the forecasting error measured by the mean absolute percentage error (MAPE) is less than 9% with the proposed forecasting method.

Key words: deep learning, long short term memory (LSTM) network, industrial load, short term load forecasting (STLF)

CLC Number: