Safety Evaluation of Microgrid Using Chaotic Time Series and RBF Neural Network

• Published in: IOP conference series. Materials Science and Engineering Vol. 853; no. 1; pp. 12009 - 12016
• Main Authors: Qin, He, Tang, Wenbo
• Format: Journal Article
• Language: English
• Published: IOP Publishing 01.05.2020
• ISSN: 1757-8981; 1757-899X
• DOI: 10.1088/1757-899X/853/1/012009

In order to evaluate safety of the Microgrid(MG) after distributed energy resources and different types of loads accessed in or disconnected, chaotic time series and RBF neural network are essential and beneficial tools. In this paper, Voltage Security Assessment Index(VSAI) is established to assess whether the MG is able to achieve equilibrium state for voltage. The application of Solar Photo Voltaic(SPV) or Wind Turbine(WT) generation alone is tested in the process of the phase space reconstruction and compared to the consorted hybrid example. Chaos algorithm can be used to define and optimal the RBF center and the connection weights of output layer, which can further improve the convergence speed of RBF neural network. Comparing the result of output between actual and prediction in three different conditions, if the difference of their values is above or below a certain threshold, the safety of MG will be judged unsafe. Test is conducted on an autonomous MG bus feeder to verify the usefulness of the posed system. The research conclusion shows that chaotic time series and RBF neural network is effective and feasible for the safety evaluation of MG.