Research On Transient Stability Control Of Smart Grid Besed On Neural Network

Smart grid uses some technologies such as digital communication,signal processing,sensing and control to improve the efficiency,reliability and security of power system.A large number of renewable energy access to the grid also contributes to the sustainability of energy.The increasingly integrated high-end information technology with modern power grid has become the cornerstone of real-time monitoring and control system,which provides new ideas for improving the stability of power system,but also becomes the source of new challenges such as network security and uncertainty.In this new environment,the transient stability control of smart grid has become a research hotspot of many scholars.Based on the theory of multiagent system,this paper mainly studies the transient stability control problem of smart grid by using neural network method,which combines the characteristics of deep integration of information system and power system in smart grid,and the characteristics of a variety of low inertia renewable energy sources connected to the grid.The main contents of this paper are as follows:In order to solve the problem that the transient stability control of modern smart grid becomes more complex under the background of deep integration of cyber network and power network,the transient stability control framework of smart grid is designed by using the theory of multi-agent system in this paper.Then,the corresponding nonlinear multi-agent dynamic model of smart grid is established under the framework,and a new distributed controller is proposed.The controller uses the method based on the radial basis function neural network(RBFNN)to approximate the nonlinear term in the power system,and controls the external distributed energy storage system to improve the transient stability of the smart grid.The Lyapunov stability analysis proves the stability of the system,and the adaptive consensus can be guaranteed by using the designed controller.Finally,the feasibility of the proposed control framework and the effectiveness of the distributed controller are verified by simulation experiments.In the framework of multi-agent,this paper further studies the system nonlinearity,parameter uncertainty and external disturbance prevalent in power systems.And a new distributed adaptive controller based on Radial Basis Function Neural Network(RBFNN)is proposed to solving controller performance issues under restricted conditions and enhancing the transient stability of smart grid.The unknown nonlinear term and the external disturbance term in the systems are compensated by using the RBFNN method,and the corresponding adaptive parameter estimation scheme is designed to approximate the ideal weight matrix of the unknown nonlinearity.Distributed controller receives real-time data from PMU through communication network and controls the action of energy storage devices,so that each generator can realize frequency synchronization quickly after disturbance.The convergence of the proposed distributed control method is proved by Lyapunov stability theory.Finally,the effectiveness of the proposed distributed control method and the performance of the controller under restricted conditions are verified by simulation studies.