摘要
电力系统是大规模非线性系统,其不确定性、快速动态等特性一直是稳定控制中难以解决的问题。神经网络控制由于具有自组织性、自适应性、容错性等性能,近年来在控制领域取得了很大的发展。文中介绍了一种新型神经控制器,该控制器应用自适应校正设计的原理,选用基于控制网络的启发式动态规划(Action-DependantHeuristicDynamicProgramming),设计中利用控制网络与校正网络交替训练的方法进行控制器的优化,具有结构简单,不依赖于受控系统的优点,并且能够实现在线学习。以单机无穷大系统为例,在Matlab/Simulink环境中对系统不同运行方式进行仿真,将该神经控制器同传统控制器进行对比,结果显示前者能够对系统振荡进行更好的阻尼,并且对不同工况保持稳定一致的控制效果,体现了很强的鲁棒性。
Power systems containing synchronous machines are large-scale dynamic systems. The uncertainties and nonlinearities associated with such a system are the most challenging problems in power system stability control. Artificial neural networks offer a solution to this problem due to their advantages, such as self-organization, self-adaptivity and fault tolerance. This paper introduces a novel nonlinear optimal neuro-controUer which is based on adaptive critic design and uses the structure of action-dependant heuristic dynamic programming（ADHDP） . The principle of ADHDP is presented. An action network and a critic network are set up in such a way that they basically learn from interactions based on local measurement to optimize the neurocontroller. The ADHDP neurocontroUer has a simple framework and is independent from the system model. A simulation of a single machine infinite bus system is carry out using Matlab/Simulink. The simulation results show that the ADHDP neuro-controUer is superior to the conventional ones at different operation conditions and highly robust.
出处
《现代电力》
2005年第4期7-11,共5页
Modern Electric Power
基金
国家自然科学基金重点资助项目(50323002)
关键词
电力系统
自适应校正设计
启发式动态规划
人工神经网络
动态稳定
power system
adaptive critic design
heuristic dynamic programming
artificial neural network
dynamic stability
