含电动汽车和光伏的配电网空间负荷预测

Spatial Load Forecasting of Distribution Network with Electric Vehicle and Photovoltaic

随着光伏(photovoltaic,PV)的普及和电动汽车(Electric Vehicle,EV)保有量的增加,提出一种同时考虑到EV时空分布和PV出力随机的主动配电网空间负荷预测(Spatial Load Forecasting,SLF)方法。对影响PV出力的各项指标进行详细分析,并采用层次分析法确定不同指标的权重,采用模糊综合评价法确定评价集。其次,结合最小二乘支持向量机(Least Squares Support Vectormachine,LS-SVM)对传统粒子群算法进行改进来配比PV出力情况。然后,根据EV的时空转移概率矩阵采用蒙特卡洛法模拟出EV充电负荷情况。最后,以某规划区为例,根据预测得到的PV出力情况以及EV充电负荷的分布预测出规划区的空间负荷情况,为配电网规划提供指导。

With the popularity of photovoltaic(PV)and the increase of electric vehicle(EV),a spatial load forecasting(SLF)method for active distribution network is proposed,which takes into account both the temporal and spatial distribution of EV and the stochastic output of PV.The indexes that affect PV output are analyzed in detail,and the weight of different indexes is deter⁃mined by AHP,and the evaluation set is determined by fuzzy comprehensive evaluation method.Secondly,combined with least squares support vector machine(LS-SVM),the traditional particle swarm optimization algorithm is improved to match the PV out⁃put.Then,according to the space-time transfer probability matrix of EV,the charging load of EV is simulated by Monte Carlo meth⁃od.Finally,taking a planning area as an example,the spatial load of the planning area is predicted according to the predicted PV output and EV charging load distribution,which provides guidance for distribution network planning.