Open AccessReliability prediction method and application in distribution system based on genetic algorithm–back‐propagation neural network
Author(s) -
Liu Yiming,
Li Yan,
Sheng Mengyu,
Wang Shaorong
Publication year - 2019
Publication title -
iet generation, transmission and distribution
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.92
H-Index - 110
eISSN - 1751-8695
pISSN - 1751-8687
DOI - 10.1049/iet-gtd.2018.6422
Subject(s) - artificial neural network , reliability (semiconductor) , genetic algorithm , computer science , backpropagation , algorithm , artificial intelligence , machine learning , power (physics) , physics , quantum mechanics
With the continuous expansion of distribution system, the structure of the power grid is becoming increasingly complex, and the limitations of traditional analysis methods are more and more obvious. In this study, a reliability prediction model of the distribution network based on back‐propagation neural network and genetic algorithm is proposed. Strong correlation factors of reliability are extracted as the input of the neural network for training, and the trained model is used to predict the distribution system reliability level in the future. The neural network is improved by momentum and adaptive learning rate, and the initial weight and threshold are optimised by genetic algorithm to realise rapid and accurate prediction. The proposed prediction model is trained and validated by the actual data of Hubei power grid. The prediction results show that the method is effective. The sensitivity analysis of reliability‐related factors is carried out by using the trained network to identify the key indicators that have a greater impact on the reliability of the distribution network. This research can provide the basis for reasonable decision making to improve the reliability of distribution system, and has certain practical significance for a cost–benefit analysis of distribution system reliability.