基于遗传算法优化的复合神经网络在稳定评估中的应用研究  

Application of Compound Neural Network Based Genetic Algorithm Optimizing for Power System Transient Stability Assessment

作　　者：汤必强[1] 陈允平[1] 邓长虹[1] 

机构地区：[1]武汉大学电气工程学院,武汉430072

出　　处：《电力系统及其自动化学报》2004年第1期6-10,18,共6页Proceedings of the CSU-EPSA

摘　　要：提出了一种基于遗传算法优化的复合神经网络的电力系统暂态稳定评估方法。该网络由一个 Kohonen网络和若干径向基函数网络组成。通过遗传算法的优化 ,复合网络的学习性能和聚类能力得到了较大的提高。In this paper,a compound neural network optimized by genetic algorithm for transient stability assessment is proposed.The proposed neural network is composed of a Kohonen network and several radial basis function(RBF)networks.The learning performance and the ability of classification of the compound neural network are largely enhanced by genetic algorithm.And the feasibility of the presented approach is validated by the simulation result of Central China Power Grid.

关 键 词：电力系统 暂态稳定性 稳定评估 复合神经网络 遗传算法 优化 

分 类 号：TM712[电气工程—电力系统及自动化] TP183[自动化与计算机技术—控制理论与控制工程]