Distributed Learning Algorithm for Distributed PV Large-Scale Access to Power Grid Based on Machine Learning

  • Zhen Lei
  • Yong-biao YangEmail author
  • Xiao-hui Xu
Conference paper
Part of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST, volume 301)


Due to the long prediction time and the large range of data filtering, the traditional algorithm has low system operation efficiency. For this reason, distributed learning based on machine learning is widely used to predict the power grid output. First, establish a grid output prediction model to limit the system’s line loss and transformer losses. Secondly, based on the distributed photovoltaic power generation output prediction model, the vector moment method and the information method are used to narrow the search space. Based on the data concentration and fitness function values, the calculation formula of voltage output prediction of distribution network nodes with distributed photovoltaics is derived to realize the power grid output prediction algorithm. Finally, it is proved by experiments that distributed PV large-scale access to power grid output prediction algorithm can effectively improve system operation efficiency.


Operation efficiency Photovoltaic capacity Radial structure Power system 


  1. 1.
    Liu, S., Luo, F., Wang, C., et al.: Calculation method of hosting capacity for distributed grid-connected photovoltaic based on improved big bang-big crunch algorithm. Proceedings of the CSU-EPSA 11, 5–10 (2017)Google Scholar
  2. 2.
    Cheng, M., Dai, X., Wang, S., et al.: Study on voltage characteristics of distributed photovoltaic access to active distribution network. Northeast. Power Technol. 38(5), 2118–2221 (2017)Google Scholar
  3. 3.
    Wang, H., Ge, L., Li, H., et al.: Summary of characteristics analysis and prediction methods of distributed photovoltaic power generation. Electr. Power Constr. 38(7), 2321–2329 (2017)Google Scholar
  4. 4.
    Yang, F., Tian, C., Li, Z., et al.: Distributed photovoltaic spatial-temporal distribution prediction considering space capacity saturation. Power Grid Technol. 23(12), 3917–3925 (2017)Google Scholar
  5. 5.
    Li, L., Wang, J., He, Y., et al.: Multi-point PV-DG day-ahead allocation plan based on K-means clustering particle swarm optimization. High Volt. Technol. 44(4), 1263–1270 (2017)Google Scholar
  6. 6.
    Huang, W., Gao, Y., Zhang, Y., et al.: Limit capacity assessment of distributed photovoltaic access distribution network considering uncertainty. Power Syst. Prot. Control. 11(14), 1453–1654 (2018)Google Scholar
  7. 7.
    Jin, Z., Xiang, T., Chen, H., et al.: Distributed photovoltaic access planning method considering power quality problems [J]. Power system protection and control 45(9), 1231–1238 (2017)Google Scholar
  8. 8.
    Yang, C., Pan, Yu., Zeyang, W., et al.: Output optimization and capacity allocation method of distributed photovoltaic-energy storage system considering power loss. Renew. Energy 35(2), 245–251 (2017)Google Scholar
  9. 9.
    He, X., Zhang, M., Zhu, Y., et al.: Application analysis of centralized and string inverter in photovoltaic power plant. J. Xi’an Polytech. Univ. 04, 443–448 (2018)Google Scholar
  10. 10.
    Zhang, W., Qi, W., Xu, Q., et al.: Study on location and capacity of distributed photovoltaic access distribution network considering time series characteristics. J. Nanjing Norm. Univ. (Eng. Ed.) 17(3), 1122–1128 (2017)Google Scholar

Copyright information

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

Authors and Affiliations

  1. 1.State Grid Jiangsu Electric Power CompanyNanjingChina
  2. 2.Southeast UniversityNanjingChina
  3. 3.China Electric Power Research InstituteNanjingChina

Personalised recommendations