Open AccessInvestment Forecast of Power Network Infrastructure Project Based on BP Neural Network
Author(s) -
Yiquan Gao,
Yang Cao,
Jiang Zhe
Publication year - 2019
Publication title -
iop conference series. earth and environmental science
Language(s) - English
Resource type - Journals
eISSN - 1755-1307
pISSN - 1755-1315
DOI - 10.1088/1755-1315/332/4/042021
Subject(s) - investment (military) , grid , power (physics) , electric power , finance , artificial neural network , environmental economics , business , computer science , economics , physics , geometry , mathematics , quantum mechanics , politics , political science , law , machine learning
With the development of China’s economy and society, the demand for electric energy is gradually increasing, and large-scale investment in power grid infrastructure projects is being made. Due to the unreasonable investment plan, the investment balance rate of power grid enterprises in recent years is higher, which is not conducive to the scientific management of enterprises. Therefore, it is necessary to make investment prediction for power grid infrastructure projects in order to achieve the rational management and control of power grid enterprises for infrastructure projects. Based on BP neural network, this paper establishes the investment prediction model of power grid infrastructure projects, chooses the factors that have great influence on power grid infrastructure projects to analyse, and reduces the dimension of each factor based on principal component analysis method, which improves the accuracy and efficiency of the prediction. Finally, the effectiveness and advancement of the model are verified by an example of cable line project investment prediction of a power company. The results show that the prediction accuracy of the model is 93.1%, which can provide guidance for the reasonable formulation of the annual investment plan of power grid enterprises.