The voltage stability margin is an important load margin measure used in power system operating centers to prevent a voltage collapse. However, oscillatory problems that arise with increasing load can also compromise the performance and stability of the power system. Thus, it is essential to determine a load margin that meets the requirements for voltage stability and small-signal stability in dynamic security assessment. This article proposes to use a artificial neural network, a supervised machine learning technique, to predict the load margin range of the power system considering the requirements of voltage stability and small-signal stability and using data of electrical quantities of certain buses that have a phasor measurement unit. A direct method based on a power systems model that determines the load margin meeting the voltage and small-signal stability requirements will be applied to generate the database for the training and testing stages of artificial neural network. The sequential forward selection algorithm was used in this research to select the buses to have a phasor measurement unit. Case studies are presented and discussed to verify the proposed load margin monitoring system based on artificial neural networks.

电压稳定裕度是电力系统操作中心中用于防止电压崩溃的重要负载裕度度量。但是，随着负载增加而产生的振荡问题也会损害电源系统的性能和稳定性。因此，在动态安全评估中确定满足电压稳定性和小信号稳定性要求的负载裕度至关重要。本文建议使用人工神经网络，一种受监督的机器学习技术，在考虑电压稳定性和小信号稳定性要求的情况下，并使用具有相量的某些总线的电量数据，来预测电力系统的负载裕量范围计量单位。将基于电力系统模型的直接方法来确定满足电压和小信号稳定性要求的负载裕度，以生成用于人工神经网络的训练和测试阶段的数据库。在这项研究中，使用顺序正向选择算法来选择具有相量测量单元的总线。通过案例研究和讨论，以验证提出的基于人工神经网络的负载裕量监控系统。