基于AFSA-SVM算法的电力系统控制方法研究

电力控制系统是一个非线性、时变系统,常规控制方法难以获得较好的控制效果,提出一种融合人工鱼群算法和支持向量机的电力系统优化控制方法(AFSA-SVMCA)。采用非线性学习能力强的支持向量机对控制器参数进行离散化处理,得到控制规律,将系统超调量引入到控制对象的优化目标函数中,同时采用人工鱼群算法对支持向量机处理后的参数进行在线优化,进一步提高了系统控制性能。仿真结果表明,相对于传统算法,AFSA-SVMCA算法不仅加快控制系统的控制精度,而且超调量小、抗扰动能力强,可以获得高品质的电力系统控制效果。

Power system control method based on AFSA - SVM

Electric control system is a nonlinear and time-varying system, conventional control method is difficult to achieve good control effect, and put forward a kind of fusion of artificial fish algorithm and support vector machine (SVM) power system optimization control method (AFSA - SVMCA). Using nonlinear learning ability of support vector machine to processing of controller parameters, control law, the system overshoot volume is introduced into the optimal objective function of the control object, and using artificial fish algorithm for support vector machine (SVM) on-line optimization of processing parameters, further improve the performance of system control. The simulation results show that compared with traditional algorithm, AFSA - SVMCA algorithm not only speeds up the control precision of the control system, and less overshoot, strong ability to resist disturbance, high quality of power system control effect can be obtained.