规模化电动汽车充电负荷预测

Charging load forecasting for large-scale electric vehicle

中文关键词: 电动汽车  负荷预测  电动汽车保有量  Bass 模 型  蒙特卡洛算法

英文关键词: electric vehicle  load forecasting  electric vehicle ownership  Bass model  Monte Carlo algorithm

中文摘要:

      首先基于灰色预测模型、线性回归模型和BP神经网络模型的组合预测模型计算出传统汽车保有量预测曲线，并使用非线性二乘法拟合出基于Bass模型的传统汽车保有量的3个参数值。再通过基于层次分析的德尔菲法，构建传统汽车与电动汽车参数之间的关系，从而得到能预测电动汽车保有量的Bass模型。在保有量预测结果的基础上采用蒙特卡洛算法，结合用户使用电动汽车的起始充电时间、日行驶里程数、电池参数、充电效率等影响因素分别模拟城市中电动私家车，电动公交车与电动出租车的出行习惯，完成电动汽车的负荷预测。应用该方法进行电动汽车负荷预测时精度更高，效果更好。

英文摘要:

      Firstly, based on the combined prediction model of grey prediction model, linear regression model and BP neural network model, the traditional car ownership prediction curve is calculated, and three parameter values of traditional car ownership based on Bass model are fitted by nonlinear square method. Then, through the Delphi method based on AHP, the relationship between parameters of traditional vehicles and electric vehicles is constructed, and the Bass model that can predict the number of electric vehicles is obtained. On the basis of the prediction results of the inventory, the Monte Carlo algorithm is used to simulate the electric private cars,electric buses and electric vehicles in the city by combining the initial charging time, daily mileage, battery parameters, charging efficiency and other influencing factors of the user’s use of electric vehicles. The load prediction of electric vehicles are completed. The application of this method for electric vehicle load prediction has higher accuracy and better effect.