基于支持向量机的电力系统静态电压稳定评估

Power system steady-state voltage stability assessment based on support vector machine

为了预防电压崩溃,需要评估系统运行状态到电压极限点的距离。该距离通常用潮流方程计算,但对于高维电力系统,这种方法计算速度较慢,难以满足实时电压稳定评估的要求。为减少评估时间,应用快速且可靠的评估技术是很重要的。本文提出了一种基于支持向量机的静态电压稳定评估方法,该方法充分发挥支持向量机在解决高维、非线性和有限样本问题方面体现出的优势,保证了电压稳定评估模型的泛化能力,具有较快的评估速度和较高的预测精度。在WSCC9节点测试系统中的应用结果证明了该方法的有效性。

To prevent voltage collapse, it is necessary to evaluate the distance of the operation state to the voltage collapse point. This distance is calculated with power flow equations normally.The calculation speed of this technique is slow for power system with high dimension, so it is difficult to realize real-time voltage stability assessment. The application of a fast and reliable evaluation technique is very important to diminish the evaluation time. This paper presents a method of model construction for the power system steady-state voltage stability assessment based on support vector machine （SVM）. This method takes full advantage of SVM＇s ability to solve the problem with high dimension, nonlinear and small sample. Hence better generalization ability is guaranteed, and the model works with the quicker assessment speed and the higher forecast precision. The WSCC 9-bus test system is employed to demonstrate the validity of the proposed approach.