基于神经网络的电网工程投资结余率预测研究

Research on Prediction of Investment Surplus Rate in Power Grid Engineering Based on Neural Networks

在碳达峰碳中和的目标下,电力系统的发电方式发生了重要转变,以风电和太阳能为代表的新能源逐渐成为主力电能,建设新型电力系统迫在眉睫。为了进一步控制电网基建工程的投资,提高电网工程投资效率,满足新型电力系统建设的需要,需要对电网工程的投资结余水平进行有效预测和控制。将基于BP神经网络架构,通过对电网基建项目投资的影响因素进行选择,选用粒子群算法(PSO)进行模型优化,构建PSO-BP电网工程投资结余率模型,该模型实现了电网工程投资以及结余率的预测,对优化电网工程投资结构和提高投资效率具有重要意义。

Under the goal of carbon peaking and carbon neutrality,the power generation mode of the power system has undergone important changes,new energy,represented by wind and solar power,has gradually become the main source of electricity,and the construction of new power systems is urgent.In order to further control the investment in power grid infrastructure projects,improve the investment efficiency of power grid projects,and meet the needs of new power system construction,it is necessary to effectively predict and control the investment balance level of power grid projects.Based on the BP neural network architecture,the influencing factors of power grid infrastructure project investment will be selected,and particle swarm optimization(PSO)algorithm will be selected for model optimization to construct a PSO-BP power grid engineering investment surplus rate model.This model realizes the prediction of power grid engineering investment and surplus rate,which is of great significance for optimizing the investment structure of power grid engineering and improving investment efficiency.