Energy Reports (Nov 2021)
Research on power load forecasting model of economic development zone based on neural network
Abstract
The power load forecasting model can calculate the predicted value accurately and quickly, which will be helpful to distribute the power reasonably and improve the stability of the power grid. There are many uncertain factors involved in medium and long-term load forecasting, and the relationship between them is seriously nonlinear and dynamic, so the prediction accuracy of traditional methods is not high. However, dynamic regression neural network can display the dynamic characteristics of the power system more accurately. According to the results of power load characteristic analysis, the article discusses the application of Elman neural network in the medium-term and long-term power load forecasting of an economic development zone in Jiangsu Province, and realizes the complex mapping from the relevant historical power load to the forecasting target. The results show that this power load forecasting method is effective and practical.