Open AccessPower Generation Prediction Model Based on Improved PSO-BPNN
Author(s) -
Yu Yan
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2083/3/032060
Subject(s) - particle swarm optimization , electricity generation , electricity , constructive , artificial neural network , computer science , stability (learning theory) , production (economics) , electricity price , mathematical optimization , power (physics) , artificial intelligence , engineering , machine learning , economics , process (computing) , mathematics , microeconomics , physics , quantum mechanics , electrical engineering , operating system
Electricity generation greatly impacts economic development, and electricity is indispensable for production, transportation, and living. Therefore, forecasting electricity generation accurately is of great research significance for the development of the country and the livelihood of the people. Because of the nonlinear relationship between electricity generation and the influencing factors, this paper, supported by the above data in China over the past 20 years, describes a prediction model based on Improved Particle Swarm Optimization (PSO) -- Back Propagation Neural Network (BPNN) to optimize the algorithm about forecasting electricity generation. The experimental results have shown that the accuracy and stability of the prediction model were constructed in this paper, which was improved by about 2%-6% compared with the traditional ones. In addition, the application of this model could provide a constructive theory for some relevant works in the electric-power industry.