Study of Fault Diagnosis for Power Network Based on MAS

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 (Multi-Agent System) is proposed in this paper. 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 online 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.