Adaptive MLP neural network controller for consensus tracking of Multi-Agent systems with application to synchronous generators. (1st December 2021)

• Record Type: Journal Article
• Authors: Sharifi, Alireza; Sharafian, Amin; Ai, Qian
• Is Part Of: Expert systems with applications. Volume 184(2021)
• Publication Date: 2021-12-01
• Subjects: Neural network -- Multi-Agent systems -- Consensus tracking -- Synchronous generator; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2021.115460
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: MLP Neural network is utilized to achieve consensus protocol. The controller is applied on distributed synchronous generator nonlinear Multi-Agent system. A novel weight update law is developed. Lyapunov method guarantees the uniformly ultimately boundedness of consensus error. Abstract: In this study a novel cooperative controller design is developed to tackle the consensus tracking problem of Multi-Agent systems (MAS) based on multilayer perceptron neural network (MLPNN), applied on a distributed synchronous generator (SG) Multi-Agent system in presence of model uncertainties and external disturbances. Application of MLPNN in controller design can lead to smoother system response and can neutralize the impacts of model uncertainties. Furthermore, the proposed method benefits from a novel algorithm formerly known as error backpropagation (BP) algorithm to update and to regulate the weights of MLPNN adaptively based on the principles of consensus error. The proposed strategy can be very effective in control of the distributed SG Multi-Agent system due to its ability for system identification, parameter estimation, and disturbance approximation. Moreover, the utilization of neural networks can meet the criterion to make the consensus error uniformly ultimately bounded. Ultimately, simulation results illustrate the applicability and effectiveness of the novel MLPNN controller to model the system uncertainties and to deal with external disturbances of the distributed SG Multi-Agent system.