Skip to main content

A Novel Adaptive Neural Network Constrained Control for Multi-Area Interconnected Power System with Hybrid Energy Storage

Xu, Zezhi, Liu, Jianxing, Yan, Xinggang, Yan, Wenxu (2017) A Novel Adaptive Neural Network Constrained Control for Multi-Area Interconnected Power System with Hybrid Energy Storage. IEEE Transactions on Industrial Electronics, PP (99). p. 1. ISSN 0278-0046. (doi:10.1109/TIE.2017.2767544)

PDF - Author's Accepted Manuscript
Download (725kB) Preview
[img]
Preview
Official URL
http://dx.doi.org/10.1109/TIE.2017.2767544

Abstract

This paper concentrates on the problem of control of a hybrid energy storage system (HESS) for an improved and optimized operation of load-frequency control (LFC) applications. The HESS consists of a supercapacitor served as the main power source, and a fuel cell served as the auxiliary power source. Firstly, a Hammerstein-type neural network (HNN) is proposed to identify the HESS system, which formulates the Hammerstein model with a nonlinear static gain in cascade with a linear dynamic block. It provides the model information for the controller to achieve the adaptive performance. Secondly, a feedforward neural network based on back-propagation training algorithm is designed to formulate the PID-type neural network (PIDNN), which is used for the adaptive control of HESS system. Meanwhile, a dynamic anti-windup signal is designed to solve the operational constraint of the HESS system. Then, an appropriate power reference signal for HESS can be generated. Thirdly, the stability and the convergence of the whole system are proved based on the Lyapunov stability theory. Finally, simulation experiments are followed through on a four-area interconnected power system to demonstrate the effectiveness of the proposed control scheme.

Item Type: Article
DOI/Identification number: 10.1109/TIE.2017.2767544
Subjects: T Technology
Divisions: Faculties > Sciences > School of Engineering and Digital Arts > Instrumentation, Control and Embedded Systems
Depositing User: Xinggang Yan
Date Deposited: 01 Nov 2017 14:19 UTC
Last Modified: 01 Aug 2019 10:42 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/64199 (The current URI for this page, for reference purposes)
Yan, Xinggang: https://orcid.org/0000-0003-2217-8398
  • Depositors only (login required):

Downloads

Downloads per month over past year