基于MAS的电网故障诊断系统的体系结构

Architecture of fault diagnosis for power network based on MAS

在对电网故障诊断理论研究和应用实际现状分析的基础上,提出了一基于MAS(Mu lti-Agent System)的电网故障诊断模型,此模型充分发挥MAS本身固有的协调异构智能体完成共同目标的能力,来充分利用空间分布、性质分层的故障信息,实现在线精确电网故障诊断。MAS诊断模型在电网区域监控中心设置决策A-gent,而按照空间分布的厂站端,设置协作Agent。通过决策Agent和协作Agent之间的合作协商机制,来实现基于区域电网全局各层故障信息的全局最优化诊断结果,即最能够复现电网故障和解释故障现象的诊断结果。此模型可以依托于目前已构建的故障信息网络,通过合作和管理型相结合的协调通讯方式来实现。理论分析和模拟系统测试证明了此诊断模型的可行性、有效性。

On basis of the fundamental researches and the analysis of existing application of the power system fault diagnosis, a model of power network fault diagnosis based on MAS （ Muhi-Agent System） is proposed. MAS has its own inherent coordinated isomerous intelligent bodies. The model exploits the ability these intelligent bodies can achieve the common goals to make full use of the spatial distributed and qualitative layered fault information. Then it can realize the on-line power system fault diagnosis accurately. MAS diagnosis model places the decision-making Agent in the local supervisory control center of the power network and the cooperative Agent in the spatial distributed substation terminal. By use of the negotiatory cooperation mechanism between decision-making Agent and cooperative Agent, the diagnosis results of global optimization based on the fault information of local power networks can be obtained. Supported by the existing fault information network, this model can be achieved by means of cooperative communication. The feasibility and effectiveness of the model are verified with the theoretical analysis and analogue system tests.