基于IBPSO的非侵入式多负荷投切行为辨识方法

A non-intrusive multi-load switching behavior identification method based on IBPSO

对多负荷投切行为的有效辨识,为了解用户用电行为,实现智能用电提供了有力支撑。首先,为解决多种负荷投切行为的辨识问题,提出改进的二进制粒子群优化算法(Improved Binary Particle Swarm Optimization,IBPSO),并在IBPSO的适应度函数中引入距离测度法。其次,针对单一负荷特征辨识精度并不理想的问题,融合电流谐波和有功功率作为负荷投切行为的特征。仿真结果表明,所提算法对多负荷投切行为的辨识在收敛速度和精度上都有所提高。

The effective identification of multi-load switching behavior provides a powerful support for understanding the electricity behavior of users and achieving smart power consumption. Firstly,an improved binary particle swarm optimization（ IBPSO） algorithm is proposed in order to solve the identification problem of simultaneous switching of multiple loads. And the distance measurement method is introduced as the fitness function of the IBPSO algorithm. Then,for the problem that the identification accuracy of a single load is not ideal,the current harmonic and active power are fused as the characteristics of load switching behavior. Simulation results show that the proposed algorithm improves the convergence speed and accuracy of the identification of multi-load switching behavior.