Open AccessShort-term Transmission Line load and State Evaluation method based on improved gradient lifting Stochastic Forest algorithm
Author(s) -
Peng Xie,
Duan Yuanchuan,
Da Zhang
Publication year - 2021
Publication title -
iop conference series. earth and environmental science
Language(s) - English
Resource type - Journals
eISSN - 1755-1307
pISSN - 1755-1315
DOI - 10.1088/1755-1315/769/4/042109
Subject(s) - computer science , overhead (engineering) , electric power transmission , cluster analysis , electric power system , decision tree , random forest , power transmission , power (physics) , algorithm , data mining , engineering , artificial intelligence , physics , quantum mechanics , electrical engineering , operating system
In order to accurately predict the short-term load change of power system and provide guidance for the safe, economical and efficient operation of power system, a power system load forecasting method which combines fuzzy clustering and random forest regression algorithm is proposed. the rough set is used to construct compensation rules to modify and compensate the prediction results. Based on the analysis of the factors affecting the state of overhead transmission lines, the state quantity system of overhead transmission lines containing 79 state variables is constructed based on the state variables selected by 8 units of the lines and the state quantities of special cases. In the random forest regression prediction, the same kind of data after clustering is used as the training set sample to construct the decision tree. Considering that the stochastic forest regression prediction is conservative and the power system load fluctuates greatly at the peak, the rough set theory is used to generate compensation rules to modify the load forecasting. Accurate state evaluation of overhead transmission lines in the power grid can effectively reduce the failure rate and improve the power supply performance of the system. Finally, an example is given to analyze the actual data of 66 kV voltage grade overhead transmission lines in a city. The results show that the accurate evaluation of the state of overhead transmission lines can be realized by using this method, so as to provide decision support for the operation and regulation of regional power grid.