PowerLSTM: Power Demand Forecasting Using Long Short-Term Memory Neural Network

• Published in: Advanced Data Mining and Applications Vol. 10604; pp. 727 - 740
• Main Authors: Cheng, Yao, Xu, Chang, Mashima, Daisuke, Thing, Vrizlynn L. L., Wu, Yongdong
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2017; Springer International Publishing
• Series: Lecture Notes in Computer Science
• ISBN: 9783319691787; 3319691783
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-319-69179-4_51

Power demand forecasting is a critical task to achieve efficiency and reliability in the smart grid in terms of demand response and resource allocation. This paper proposes PowerLSTM, a power demand forecasting model based on Long Short-Term Memory (LSTM) neural network. We calculate the feature significance and compact our model by capturing the features with the most important weights. Based on our preliminary study using a public dataset, compared to two recent works based on Gradient Boosting Tree (GBT) and Support Vector Regression (SVR), PowerLSTM demonstrates a decrease of 21.80% and 28.57% in forecasting error, respectively. Our study also reveals that metering/forecasting granularity at once every 30 min can bring higher accuracy than other practical granularity options.