Multi-step short-term power consumption forecasting with a hybrid deep learning strategy

Yan, Ke, Wang, Xudong, Du, Yang, Jin, Ning, Huang, Haichao, and Zhou, Hangxia (2018) Multi-step short-term power consumption forecasting with a hybrid deep learning strategy. Energies, 11. 3089.

[img]
Preview
PDF (Published Version) - Published Version
Available under License Creative Commons Attribution.

Download (2MB) | Preview
View at Publisher Website: https://doi.org/10.3390/en11113089
 
76
723


Abstract

Electric power consumption short-term forecasting for individual households is an important and challenging topic in the fields of AI-enhanced energy saving, smart grid planning, sustainable energy usage and electricity market bidding system design. Due to the variability of each household’s personalized activity, difficulties exist for traditional methods, such as auto-regressive moving average models, machine learning methods and non-deep neural networks, to provide accurate prediction for single household electric power consumption. Recent works show that the long short term memory (LSTM) neural network outperforms most of those traditional methods for power consumption forecasting problems. Nevertheless, two research gaps remain as unsolved problems in the literature. First, the prediction accuracy is still not reaching the practical level for real-world industrial applications. Second, most existing works only work on the one-step forecasting problem; the forecasting time is too short for practical usage. In this study, a hybrid deep learning neural network framework that combines convolutional neural network (CNN) with LSTM is proposed to further improve the prediction accuracy. The original short-term forecasting strategy is extended to a multi-step forecasting strategy to introduce more response time for electricity market bidding. Five real-world household power consumption datasets are studied, the proposed hybrid deep learning neural network outperforms most of the existing approaches, including auto-regressive integrated moving average (ARIMA) model, persistent model, support vector regression (SVR) and LSTM alone. In addition, we show a k-step power consumption forecasting strategy to promote the proposed framework for real-world application usage.

Item ID: 58366
Item Type: Article (Research - C1)
ISSN: 1996-1073
Keywords: electric power consumption; multi-step forecasting; long short term memory; convolutional neural network
Copyright Information: © 2018 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
Funders: National Natural Science Foundation of China (NNSFC), Xi’an Jiaotong-Liverpool University (XJTLU), Jiangsu University (JU) S&T Programme, Natural Science Foundation of Zhejiang Province (NSF-ZP)
Projects and Grants: NNSFC No. 61850410531, NNSFC No. 61602431, NNSFC No. 61803315, XJTLU (RDF-17-01-28), XJTLU (KSF-A-11), JU S&T Programme SBK2018042034, NSF-ZP No. LGF18F020017
Date Deposited: 28 May 2019 23:05
FoR Codes: 40 ENGINEERING > 4008 Electrical engineering > 400805 Electrical energy transmission, networks and systems @ 50%
46 INFORMATION AND COMPUTING SCIENCES > 4611 Machine learning > 461103 Deep learning @ 50%
SEO Codes: 85 ENERGY > 8507 Energy Conservation and Efficiency > 850704 Residential Energy Conservation and Efficiency @ 50%
85 ENERGY > 8506 Energy Storage, Distribution and Supply > 850603 Energy Systems Analysis @ 50%
Downloads: Total: 723
Last 12 Months: 91
More Statistics

Actions (Repository Staff Only)

Item Control Page Item Control Page