Advertisement

Research on Refined Load Forecasting Method Based on Data Mining

  • Yawen XiEmail author
  • Junyong Wu
  • Chen Shi
  • Xiaowen Zhu
  • Ran An
  • Rong Cai
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 925)

Abstract

Load forecasting is a basic work of power system dispatching. With the rapid development of smart grid technology, the accuracy of load forecasting is put forward by increasing demand. Fusion load, weather and other multi-sourced data, a refined load forecasting method of support vector machine (SVM) based on data mining is proposed. Firstly, the history load data is clustered and the operation days are divided into six categories. Then, the load data and weather data such as humidity and temperature are fused together, a refined load forecasting model based on data mining is proposed. And the parameters of the model are optimized globally. Forecasting the load of a prefecture-level city in Zhejiang Province in 2013, the load prediction error of sampling point and daily average load forecasting rate are used as indexes to evaluate the prediction accuracy, the prediction results show that the prediction accuracy of the support vector machine (SVM) refined load forecasting method based on historical data and real-time influencing factors proposed in this paper is significantly higher than that of the traditional load forecasting method.

Keywords

Load forecasting Data mining Support Vector Machines (SVM) Forecasting accuracy 

References

  1. 1.
    Su, X., Liu, T., Cao, H., et al.: Short-term load forecasting method for multi-distributed BP neural network based on Hadoop architecture. Proc. CSEE 37(17), 4966–4973+5216 (2017)Google Scholar
  2. 2.
    Luo, N., Zhu, Y., Du, C.: Application of support vector machine method in electric load forecasting. Power Syst. Technol. 31(S2), 215–218 (2007)Google Scholar
  3. 3.
    Geng, Y., Han, X., Han, L.: Short-term load forecasting based on least squares support vector machine. Power Syst. Technol. 18, 72–76 (2008)Google Scholar
  4. 4.
    Zhang, P., Pan, X., Xue, W.: Short-term load forecasting based on wavelet decomposition, fuzzy gray correlation clustering and BP neural network. Electr. Power Autom. Equip. 32(11), 121–125+141 (2012)Google Scholar
  5. 5.
    Zu, X., Tian, M., Bai, Y.: Short term load forecasting method based on fuzzy clustering and function wavelet kernel regression. Electr. Power Autom. Equip. 36(10), 134–140+165 (2016)Google Scholar
  6. 6.
    Wu, Q., Gao, J., Hou, G., et al.: Short-term load forecasting support vector machine algorithm based on multi-source heterogeneous fusion of load factors. Autom. Electr. Power Syst. 40(15), 67–72+92 (2016)Google Scholar
  7. 7.
    Li, B., Huang, J., Wu, Y., et al.: A short-term load forecasting method based on fractal feature correction of meteorological similar days. Power Syst. Technol. 41(06), 1949–1955 (2017)Google Scholar
  8. 8.
    Tang, J., Liu, J., Yang, K., et al.: Short-term load combination forecasting by grey model and least square support vector machine. Power Syst. Technol. 33(03), 63–68 (2009)Google Scholar
  9. 9.
    Gao, Y., Sun, Y., Yang, W., et al.: Study on short – term forecast of meteorological sensitive load based on new human comfort. Proc. CSEE 37(07), 1946–1955 (2017)Google Scholar
  10. 10.
    Huo, J., Shi, T., Chang, J.: Comparison of random forest and SVM for electrical short-term load forecast with different data sources. In: IEEE International Conference on Software Engineering and Service Science, pp. 1077–1080. IEEE (2017)Google Scholar
  11. 11.
    Ye, N., Liu, Y., Wang, Y.: Short-term power load forecasting based on SVM, pp. 47–51 (2012)Google Scholar
  12. 12.
    Zhang, M.G., Li, L.R.: Short-term load combined forecasting method based on BPNN and LS-SVM. In: Power Engineering and Automation Conference, pp. 319–322. IEEE (2012)Google Scholar
  13. 13.
    Selakov, A., Ilic, S., Vukmirovic, S., et al.: A comparative analysis of SVM and ANN based hybrid model for short term load forecasting. 52(11), 1–5 (2012)Google Scholar
  14. 14.
    Liu, B., Xu, G.: Short-term power load forecasting based on LS-SVM. In: International Conference of Information Science and Management Engineering, pp. 311–314. IEEE Computer Society (2010)Google Scholar
  15. 15.
    Zhang, Q., Liu, T.: Application of SVM and wavelet neural network method for short-term power load forecasting. In: The International Conference on Computer and Automation Engineering, pp. 412–416. IEEE (2010)Google Scholar
  16. 16.
    Niu, D., Liu, D., Chen, G., et al.: Support vector machine models optimized by genetic algorithm for hourly load rolling forecasting. Trans. China Electrotech. Soc. 22(06), 148–153 (2007)Google Scholar
  17. 17.
    Xie, H., Wei, J., Liu, H.: Parameter selection and optimization method of SVM model for short-term load forecasting. Proc. CSEE 26(22), 17–22 (2006)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  • Yawen Xi
    • 1
    Email author
  • Junyong Wu
    • 1
  • Chen Shi
    • 1
  • Xiaowen Zhu
    • 1
  • Ran An
    • 1
  • Rong Cai
    • 2
  1. 1.Electrical Engineering School of Beijing Jiaotong UniversityBeijingChina
  2. 2.ABB China Research InstituteBeijingChina

Personalised recommendations