论文部分内容阅读
电力系统紧急控制是故障消除后保持系统稳定性、防止事故扩大的重要手段。相比于目前电网普遍使用的离线决策,实时紧急控制决策能够提供更准确有效的控制措施。但实时决策对计算速度的要求极高,传统方法无法胜任。基于支持向量机技术,该文研究了电力系统紧急控制实时决策方法,关键在于利用支持向量机从大量的仿真数据中挖掘系统稳定规则,并用于构造可以实时求取的稳定性约束,由此将大量的仿真搜索从实时阶段转移到离线阶段。该文首先建立紧急控制决策的优化模型;然后利用灵敏度方法将模型中的稳定性约束线性化;接着通过改造支持向量机的分类表达式将其用于拟合,提出能够实时求取的稳定裕度指标,实现灵敏度求解;最后在IEEE39节点系统中进行算例仿真,仿真结果显示:所提出的稳定性指标能够准确反映系统的稳定裕度,同时针对不同的失稳状况该文提出的决策方法能有效恢复系统稳定性。
Emergency control of power system is an important means to maintain the system stability and prevent the accident from expanding after the fault is eliminated. Real-time emergency control decisions provide more accurate and effective control than offline decisions commonly used in power grids today. However, real-time decision-making demands very high computational speed and the traditional method can not do it well. Based on support vector machine technology, this paper studies the real-time decision-making method for emergency control of power system. The key is to use the support vector machine to mine the system stability rules from a large amount of simulation data and to construct the stability constraint that can be obtained in real time A large number of simulation search from the real-time stage to the offline stage. Firstly, the optimization model of emergency control decision is established. Then, the stability constraint of the model is linearized by using the sensitivity method. Then the classification expression of SVM is used to fit the model. The stability margin Finally, an example simulation is carried out in the IEEE 39-bus system. The simulation results show that the proposed stability index can accurately reflect the stability margin of the system, and the decision-making method proposed in this paper is different for different instability conditions Can effectively restore system stability.