skip to main content
10.1145/3488933.3488961acmotherconferencesArticle/Chapter ViewAbstractPublication PagesaiprConference Proceedingsconference-collections
research-article

Electricity Consumption Prediction Based on Generative Adversarial Network

Published: 25 February 2022 Publication History

Abstract

Electricity forecasting has an important influence in the development of smart grids. How to improve the forecasting accuracy based on historical electricity data is an important research hotspot. At present, most researches use neural networks to model sequence data to achieve electricity prediction. However, these methods ignore the potential correlations within the sequence data. Therefore, a electricity consumption prediction model based on generative adversarial network is proposed. First, the grey relational analysis method is used to analyze the feature set that affects the user's electricity consumption; secondly, the multi-kernel support vector machine is used as the discriminator, and the bidirectional GRU is used as the generator, and the electricity prediction is realized through mutual confrontation learning between the generator and the discriminator. In the generator design process, on the basis of the bidirectional GRU, a multi-head attention mechanism is introduced to capture the potential dependencies within the sequence to improve the prediction performance of the model. Finally, a verification analysis is carried out based on power data in a certain region of China. Experimental results show that the proposed method can effectively improve the accuracy of electricity prediction.

References

[1]
He Yaoyao, Liu Rui, Han Aoyang. Short-term power load probability density forecasting method based on real-time price and support vector quantile regression [J].Proceedings of the CSEE, 2017,37(3):768-776.
[2]
Sun Guoqiang, Liang Zhi, Yu Nayan, . Prediction of short-term wind power probability density based on EWT and quantile regression forest[J].Electric Power Automation Equipment, 2018, 38(8): 158-165.
[3]
XIA Yaojie. Application of the optimal combined forecasting method in mid-long term power load forecasting[J]. Power Demand Side Management, 2016, 18(4): 18-23.
[4]
JIANG Yan, WANG Shaoyang, FENG Yun. Medium-long term power load forecasting based on recursive right combination model[J]. Proceedings of the CSU-EPSA, 2012, 24(1): 151-155.
[5]
Marino D L, Amarasinghe K, Manic M . Building Energy Load Forecasting using Deep Neural Networks[J]. 2016:7046-7051.
[6]
Zhang Y, Kong W, Dong Z Y, Short-Term Residential Load Forecasting Based on LSTM Recurrent Neural Network[J]. IEEE Transactions on Smart Grid, 2019: 1-11.
[7]
Amarasinghe K, Marino D L, Manic M. Deep neural networks for energy load forecasting[C]// 2017 IEEE 26th International Symposium on Industrial Electronics (ISIE). IEEE, 2017: 1483-1488.
[8]
QIAN ZHI. Short-Term Power Load Forecasting Based on Improved SVR[J]. Electric Power, 2016(8):54-58.
[9]
ZHAO Pei, DAI Yeming. Power Load Forecasting of SVM Based on Real-time Price and Weighted Grey Relational Projection Algorithm[J]. Power System Technology. 2020, 44(04):1325-1332.
[10]
Liu Y, Zhang K, Zhen S, WRL: A Combined Model for Short-Term Load Forecasting. In Web and Big Data -Third International Joint Conference, APWeb-WAIM 2019: 35-42.
[11]
A. Almalaq and G. Edwards. A Review of Deep Learning Methods Applied on Load Forecasting. 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA), Cancun, 2017: 511-516.
[12]
M. Alhussein, K. Aurangzeb and S. I. Haider. Hybrid CNN-LSTM Model for Short-Term Individual Household Load Forecasting[J]. in IEEE Access, 2020(8): 180544-180557.
[13]
Zhao huiru, Zhao yihang, Guo Sen. Short-Term Load Forecasting Based on Complementary Ensemble Empirical Mode Decomposition and Long Short-Term Memory[J]. Electric Power, 2020(6):48-55.
[14]
C. Zheng, J. Zhu. Grey relational analysis of factors affecting ipo pricing in China a-share market. 2017 International Conference on Grey Systems and Intelligent Services (GSIS). 2017: 82-86.
[15]
Wang Jing, Zou Huimin, Qu Dongdong, BaiLi. FINANCIAL TIME SERISE PREDICTION BASED ON EMPIRICAL MODE DECOMPOSITION TO GENERATE ADVERSARIAL NETWORKS[J]. Computer Applications and Software, 2020, 37(05): 293- 297.

Index Terms

  1. Electricity Consumption Prediction Based on Generative Adversarial Network
      Index terms have been assigned to the content through auto-classification.

      Recommendations

      Comments

      Information & Contributors

      Information

      Published In

      cover image ACM Other conferences
      AIPR '21: Proceedings of the 2021 4th International Conference on Artificial Intelligence and Pattern Recognition
      September 2021
      715 pages
      ISBN:9781450384087
      DOI:10.1145/3488933
      Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

      Publisher

      Association for Computing Machinery

      New York, NY, United States

      Publication History

      Published: 25 February 2022

      Permissions

      Request permissions for this article.

      Check for updates

      Author Tags

      1. electricity consumption prediction
      2. grey relational analysis
      3. multi-head attention mechanism, generative adversarial network

      Qualifiers

      • Research-article
      • Research
      • Refereed limited

      Funding Sources

      • the Science and Technology Project of State Grid Shandong Electric Power Company: Research on Characteristics Analysis Technology of Source and Load Electrical Parameters in Spot Market Transactions

      Conference

      AIPR 2021

      Contributors

      Other Metrics

      Bibliometrics & Citations

      Bibliometrics

      Article Metrics

      • 0
        Total Citations
      • 62
        Total Downloads
      • Downloads (Last 12 months)9
      • Downloads (Last 6 weeks)1
      Reflects downloads up to 15 Feb 2025

      Other Metrics

      Citations

      View Options

      Login options

      View options

      PDF

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader

      HTML Format

      View this article in HTML Format.

      HTML Format

      Figures

      Tables

      Media

      Share

      Share

      Share this Publication link

      Share on social media