基于CPSO-BP神经网络的风电并网暂态电压稳定评估

针对目前传统方法难以快速、准确判断风电并网后系统暂态电压稳定性的问题，提出了一种基于CPSO-BP组合的风电并网暂态电压稳定评估方法。首先采用混沌理论对粒子群算法的不足进行改善，应用改进后的算法对神经网络的初始权值和阈值进行优化，然后利用系统故障前后采集的传统物理量和风电场相关的物理量作为BP神经网络输入特征量进行监督学习，最后将训练得到的模型应用于风电并网系统的暂态电压稳定评估中。利用英格兰10机39节点系统标准算例进行风电并网仿真分析，结果证明了所提方法的有效性。

Transient Voltage Stability Assessment of Power System Integrated with Wind Power Based on CPSO-BP Neural Network

Targeting the problem that traditional methods cannot judge the transient voltage stability of power system integrated wind power quickly and accurately， this paper proposes a method of transient voltage stability assessment of the power system based on CPSO-BP. Firstly， chaos theory is used to improve particle swarm algorithm， and the improved algorithm is applied to optimize the initial weights and thresholds of the neural network. Then the traditional physical quantities collected before and after the system fault and the physical quantities related to wind farm are used as the input characteristic variables of BP neural network for supervised learning. Finally， the trained model is applied to the transient voltage stability assessment of the power system integrated wind power. The standard example of England 10-machine 39-bus system is used to simulate and analyze the process of the wind power integrating into the power system，the results show the effectiveness of the proposed method.