基于差分进化算法的居民用电负荷分解方法

Differential Evolution Algorithm Based Residential Load Decomposition

针对现有负荷分解方法对设备采样频率要求高、无法有效处理多工作模式电器投入使用的问题,提出一种全新的非侵入式负荷监测与分解方法。该方法将电器的稳态电流作为负荷特征,建立起负荷总电流与各用电器电流之间的数学模型,利用差分进化算法求得各用电器的开启时间系数,进而实现居民侧电力负荷的分解。实验表明,该方法可准确地判断出各类型电器的开启时间和运行模式,并能很好地处理算例中,多个同种电器在同一时段投入使用的情况。该方法所需负荷数据可直接由当前市面上通用的智能电表获得,减少了硬件成本投入。

In order to solve the problems of demanding high frequencey sampling devices and hardness to deal with multi-state appliances effectively in the existed load decomposition methods,a novel non-intrusive residential load monitoring and decomposition（NILMD） method is proposed in this paper.This method considers appliances＇ current as load feature,and establishes a mathematical model between the total current and the currents of each appliance.Then（differential evolution algorithm is applied to search the open time coefficient of each appliance,thus to realize the residential load decomposition.Experimental results show that the proposed method can estimate the open time and operation mode of appliances accurately,and perform well with the conditions when the same kind of appliances are used at the same time period.Meanwhile,the required data can be obtained directly from the universal smart meters on the market,which would reduce the hardware input cost.