Research on Parallel Forecasting Model of Short-Term Power Load Big Data

  • Xin-jia LiEmail author
  • Hong Sun
  • Cheng-liang Wang
  • Si-yu Tao
  • Tao Lei
Conference paper
Part of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST, volume 279)


The parallel prediction model of big data with traditional power load has a low prediction accuracy in different working conditions, so the parallel prediction model of big data for short-term power load is designed. The short-term power load forecasting theory is analyzed, and the short-term power load data are classified to select the short-term power load forecasting theory. The Map/Reduce framework is built on the basis of the theory, and the prediction process is designed through the Map/Reduce framework. The short-term power load data of the subnet and the big data of the short term power load are predicted respectively, and the construction of the parallel prediction model of the short-term power load big data is realized. The experimental results show that the proposed big data parallel prediction model is better than the traditional model, and can be switched under different working conditions, and the deviation between the forecasting curve and the actual load is small, the average deviation is 1.7, and the overall prediction effect is good.


Short-Term load forecasting Big data Electrical load Prediction algorithm 


  1. 1.
    Weekend, J.M.: Short-term load forecasting method combined with multi-algorithm multi-model and online second learning. Comput. Appl. 37(11), 3317–3322 (2017)Google Scholar
  2. 2.
    Xiong, J.H., Niu, X., Zhang, C.G., et al.: Short-term load forecasting based on wavelet transform with Drosophila optimized support vector machines. Power Syst. Prot. Control 45(13), 71–77 (2017)Google Scholar
  3. 3.
    Liu, D.D., Zhu, J.M., Huang, T.T.: Short-term power load forecasting based on time series and grey model. J. Qiqihar Univ. (Natural Science) 33(3), 7–12 (2017)Google Scholar
  4. 4.
    Li, L., Yang, S.F., Qiu, J.P., et al.: Simulation research on power system short term load forecasting method. Comput. Simul. 34(1), 104–108 (2017)CrossRefGoogle Scholar
  5. 5.
    Wang, W.G., Dou, Z.H., Shen, J., et al.: Improved short-term load forecasting based on backstepping theory for fuzzy mean function. Hydroelectric Energy Sci. 14(12), 208–211 (2017)Google Scholar
  6. 6.
    Zhi, L., Guoqiang, S., Zhinong, W., et al.: Short-term load forecasting based on variable selection and Gaussian process regression. Electr. Power Const. 38(2), 122–128 (2017)Google Scholar
  7. 7.
    Song, R.J., Yu, T., Chen, Y.H., et al.: Similarity duplicate records detection algorithm for big data based on MapReduce model. J. Shanghai Jiaotong Univ. 52(2), 214–221 (2018)Google Scholar
  8. 8.
    Xiao, W., Hu, J., Zhou, X.F.: Research review of parallel association rules mining algorithm based on MapReduce computing model. Res. Comput. Appl. 38(1), 132–139 (2018)Google Scholar
  9. 9.
    Lei, J.S., Hao, X., Zhu, G.K.: Short-term power load forecasting based on “layered-pooling” model. Electric Power Constr. 38(1), 68–75 (2017)Google Scholar
  10. 10.
    Su, X., Liu, T.Q., Cao, H.Q., et al.: Short-term load forecasting based on multi-distributed distributed BP neural network based on Hadoop architecture. Proc. CSEE 37(17), 4966–4973 (2017)Google Scholar

Copyright information

© ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2019

Authors and Affiliations

  • Xin-jia Li
    • 1
    Email author
  • Hong Sun
    • 1
  • Cheng-liang Wang
    • 1
  • Si-yu Tao
    • 2
  • Tao Lei
    • 3
  1. 1.Jiangsu Fangtian Power Technology Co., Ltd.NanjingChina
  2. 2.Southeast UniversityNanjingChina
  3. 3.South China Normal UniversityGuangzhouChina

Personalised recommendations