基于随机森林的电力系统暂态稳定评估与紧急控制策略

Transient Stability Assessment and Emergency Control Strategy Based on Random Forest in Power System

紧急控制是保证故障后电力系统稳定运行的重要手段。分析电力系统发电机功角、部分母线有功无功与暂态稳定裕度提出一种基于随机森林的暂态稳定裕度评估方法与紧急控制策略制定方案。首先,在离线阶段建立随机森林回归模型,分析发电机功角、有功功率、无功功率等特征量与暂态稳定裕度的映射关系。然后,计算切机、切负荷的灵敏度,选取切除后对系统稳定性有利的发电机和负荷组成紧急控制集合。最后,以切除发电机和负荷容量最小为目标,以稳定约束、最大可控容量和功率平衡构成约束条件,建立紧急控制优化模型,求取最优紧急控制策略。在含风机的16机系统中进行仿真分析,结果表明,提出的暂态稳定裕度评估方法准确有效,根据控制灵敏度制定的紧急控制策略,可以保证系统故障后恢复稳定运行。

Emergency control is an important means to ensure the stable operation of the power system after fault. This paper proposes a method based on the random forest for transient stability assessment and the emergency control strategy. Firstly, the random forest regression model for the system is established in the off-line stage, and the mapping relationship between the transient stability margin and features including the generator angle, the active and reactive power are analyzed. Then, the sensitivities of the generator tripping and the load shedding are calculated, and the generators and loads which are beneficial to the stability of the power system after action are selected to form an emergency control set. Finally, regarding the minimum capacity of the generator tripping and the load shedding as the target of the emergency control, an optimization model of emergency control is established to obtain the optimal emergency control strategy, with the consideration of the constraints of stability constraints, the maximum controllable capacity and the active power balance The sixteen-machine system with wind generators added is used as the test system. The results show that the method proposed in this paper is correct and effective. The emergency control strategy based on the emergency control sensitivity can effectively ensure the system to resume stable operation after fault.