摘要
负荷模型在电力系统运行的仿真和评估方面起到重大作用。文中对常规前馈神经网络(BP网络)的学习规则、拓扑结构以及激活函数进行改进后,建立适应性BP(Adaptive Back-Propagation简称ABP)网络模型,并由此提出一种新型负荷模型。ABP能够克服常规BP网络的一些缺点,而且该模型因其非结构性且易收敛而优于传统的负荷模型,这样取得的负荷模型比传统的负荷模型更加精确。通过现场实测数据验证了此模型的有效性。同时,对这种方法在传统负荷模型参数辨识方面进行了研究。在对网络结构进行修改后,提出基于线性BP(Linear Back-Propagation,简称LBP)网络的参数辨识方法。LBP负荷模型可以接入到暂态程序中,从而大大减少计算时间。
Load models play an important role in the simulation and evaluation of power system performance. A new load model is proposed, which is based on a particular form of artificial neural networks that we denote as Adaptive Back-Propagation (ABP) Network after modifying revising learning rules, topology structure, activation and error functions. ABP can overcome some of shortcomings of common Back-Propagation (BP) and the ABP load models offer several advantages over traditional load models as they are non-structural and can be derived quickly. The application of the method is illustrated using actual field test data. Load models obtained are shown to replicate the test measurements more closely than that based on traditional load models. Extension of the method to the identification of parameters of the traditional load models is also proposed. It is based on Linear Back-Propagation (LBP) Network. The proposed LBP load model is incorporated in a transient stability program to show that the computational time is significantly reduced.
出处
《中国电机工程学报》
EI
CSCD
北大核心
2004年第12期78-85,共8页
Proceedings of the CSEE
