数据驱动的区域电网新能源消纳受阻因素智能辨识方法

Data-driven Intelligent Identification Method of Hindering Factors for Renewable Energy Consumption in Regional Power Grids

在构建新型电力系统背景下,我国新能源装机容量不断增长,新能源消纳问题愈加严峻。基于机器学习技术,提出一种区域电网新能源消纳受阻关键因素的智能辨识方法。首先基于实际量测数据与工程经验确定受阻因素的集合;然后基于神经网络挖掘受阻因素与新能源受阻量之间的函数关系,进而利用BP-MIV算法计算各个受阻因素对新能源受阻量的贡献度,以此确定导致新能源受阻的关键因素;最后,基于西北某省级电网实际运行数据进行案例分析,结果表明所提方法支持以数据驱动的方式定量分析影响新能源消纳的关键因素。

In the context of building new-type power system,the problem of renewable energy consumption is becoming more and more serious as the installed capacity of China’s renewable energy continues to grow.Based on machine learning technology,this paper proposes an intelligent identification method of the key factors hindering the renewable energy consumption in regional power grids.Firstly,the set of hindering factors is determined based on the actual measurement data and engineering experience.Then the neural network is used to mine the functional relationship between the hindering factors and the blocked renewable energy.After that,the BP MIV algorithm is used to calculate the contribution of each hindering factor to the blocked renewable energy,so as to determine the key factors leading to the renewable energy obstruction.Finally,a case analysis is carried out based on the actual operation data from a provincial power grid in Northwest China,and the results show that the proposed method can quantitatively analyze the key factors affecting the renewable energy consumption in a data-driven manner.