基于短期电网负荷智能预测算法的新能源调度策略  

New energy dispatching strategy based on short-term grid load intelligent forecasting algorithm

作　　者：常云 苏华堂 王来奎 张鹏 王天佑 CHANG Yun;SU Huatang;WANG Laikui;ZHANG Peng;WANG Tianyou(Pingliang Power Supply Company,State Grid Gansu Electric Power Company,Pingliang 744000,China;Pingliang Kongtong District Power Supply Company,State Grid Gansu Electric Power Company,Pingliang 744000,China)

机构地区：[1]国网甘肃省电力公司平凉供电公司,甘肃平凉744000 [2]国网甘肃省电力公司平凉市崆峒区供电公司,甘肃平凉744000

出　　处：《电子设计工程》2023年第6期85-89,共5页Electronic Design Engineering

基　　金：国网公司科技项目(JL71-15-042)。

摘　　要：针对智能电网的建设发展对负荷预测精度提出了更高要求的现状,提出了一种基于短期电网负荷智能预测算法的新能源调度模型。架构了基于PSO-BPNN的短期电网负荷智能预测算法,利用PSO算法对BPNN模型的初始权值和阈值等参数进行优化,并将日属性、温度、历史负荷等数据作为输入,通过训练后的BPNN模型实现短期电网负荷的精准预测。该模型以运行成本最低以及污染物排放量最少为优化目标,设计了含多类型新能源的微电网多目标调度策略。以某实际微电网的运行数据为样本,进行仿真验证的结果表明,所提算法相比于BPNN算法,在短期电网预测方面具有较高的准确性;所提多目标调度策略相比于单目标调度策略,能够同时降低微电网运行成本与污染物排放量,兼顾经济性和环保性。In view of the current situation that the construction and development of smart grid puts forward higher requirements for load forecasting accuracy,a new energy scheduling model based on shortterm grid load intelligent forecasting algorithm is proposed. The short-term power grid load intelligent forecasting algorithm based on PSO-BPNN is constructed. The PSO algorithm is used to optimize the initial weight,threshold and other parameters of the BPNN model. The daily attribute,temperature,historical load and other data are used as inputs to realize the accurate prediction of short-term power grid load through the trained BPNN model. The model takes the minimum operation cost and pollutant emission as the optimization objectives,and designs a multi-objective scheduling strategy for microgrid with multiple types of new energy. The simulation results show that the proposed algorithm has higher accuracy in short-term power grid prediction than BPNN algorithm. Compared with single objective scheduling strategy,the proposed multi-objective scheduling strategy can reduce the operation cost and pollutant emission of microgrid at the same time,taking into account economy and environmental protection.

关 键 词：负荷预测 PSO BPNN 多目标 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置] TN99[自动化与计算机技术—控制科学与工程]