基于遗传优化的非侵入式居民负荷辨识算法

负荷在线监测能够为电网及用户提供即时的用电信息,是支撑能效管理和负荷预测工作的有效手段。传统监测方法采用侵入式设计,难以大范围推广应用,因此非侵入式负荷监测方法(NILM)具有重要研究意义。负荷辨识是非侵入式负荷监测的关键,以典型居民负荷的特性分析为基础,提出了一种基于遗传优化的非侵入式居民负荷辨识算法。该算法基于负荷设备的负荷特性,包括有功功率和电流有效值,利用三种不同的编码方法构造判断负荷运行状态的适应度函数,通过遗传算法寻优,最终确定居民负荷的工作状态,并通过实测数据进行验证。实验结果表明,该算法能够实现居民用户负荷状态的有效辨识,且算法收敛速度较快,准确度高。

A Non-intrusive Residential Load Identification Algorithm Based on Genetic Optimization

Load online monitoring can provide real-time power consumption information for the grid and users , which is an effective method to support energy management and load forecasting work .Traditional method within intrusive mode is difficult to promote a wide range of applications , so non-intrusive load monitoring method ( NILM) has impor-tant significance .Load identification is very important to NILM .Considering the residential load typical characteristic analysis , a non-intrusive residential load identification algorithm based on genetic optimization is proposed .The algo-rithm based on load characteristic , including active power and current effective value , uses three different encoding methods to structure fitness function , and ultimately determines the specific type of load by genetic optimization , and then, the effectiveness of the algorithm is verified by the actual sampling load data .Experimental results show that the algorithm can achieve residential load identification , and improves the speed of constriction and accuracy of the identi-fication.