摘要
输电线路负荷预测的核心任务是根据以前负荷数据的变化规律推断出未来的发展趋势。输电线路负荷预测对于节约用电、发电机组的维护与保养、实行电网经济调度、保障生产和生活用电的稳定都具有重要的意义,是电力系统调度、用电和计划部门的重要工作。文中提出一种基于GA-BP的输电线路负荷预测研究方法,选取了日最高和日最低环境温度作为模型的输入,采用遗传算法对BP神经网络的权值和阈值进行优化,与优化前的BP神经网络相比,提高了预测精度,有效地降低了输电线路负荷预测的误差。
The core task of transmission line load forecasting is to infer the future development trend according to the variation law of previous load data.Transmission line load forecasting plays an important role in power system dispatching,power consumption and planning departments,which is of great significance for power saving,maintenance of generating units,economic dispatch of power grid,and stability of production and domestic power consumption.In this paper,a research method of transmission line load forecasting based on GA-BP was proposed.The daily maximum and minimum ambient temperature were selected as the input of the model,and genetic algorithm was used to optimize the weights and thresholds of BP neural network.Compared with the BP neural network before optimization,the forecasting accuracy of transmission line load was improved and the forecasting error was effectively reduced.
作者
胡永迅
姜媛媛
夏玲
HU Yongxun;JIANG Yuanyuan;XIA Ling(College of Electrical and Information Engineering, Anhui University of Science and Technology, Huainan 232001, China)
出处
《邵阳学院学报（自然科学版）》
2021年第3期44-51,共8页
Journal of Shaoyang University：Natural Science Edition
基金
国家重点研发计划项目(2018YFF0301000)
安徽省高校省级自然科学研究项目(KJ2019ZD12)
安徽理工大学专项基金资助项目(ALW2020YF21)。
关键词
神经网络
遗传算法
输电线路
负荷预测
neural network
genetic algorithm
transmission line
load forecasting
