文献类型：期刊文献

英文题名：Load frequency control by neural-network-based integral sliding mode for nonlinear power systems with wind turbines

作者：Qian, Dianwei[1];Tong, Shiwen[2];Liu, Hong[1];Liu, Xiangjie[1]

第一作者：Qian, Dianwei

通讯作者：Qian, DW[1]

机构：[1]North China Elect Power Univ, Sch Control & Comp Engn, Beijing 102206, Peoples R China;[2]Beijing Union Univ, Coll Automat, Beijing, Peoples R China

第一机构：North China Elect Power Univ, Sch Control & Comp Engn, Beijing 102206, Peoples R China

通讯机构：[1]corresponding author), North China Elect Power Univ, Sch Control & Comp Engn, 2 Beinong Rd, Beijing 102206, Peoples R China.

年份：2016

卷号：173

起止页码：875-885

外文期刊名：NEUROCOMPUTING

收录：;EI(收录号：20153701257630);Scopus(收录号：2-s2.0-84959371915);WOS:【SCI-EXPANDED(收录号:WOS:000366879800042)】；

基金：This work is supported by the National Natural Science Foundation of China under Grant no. 60904008 and the Fundamental Research Funds for the Central Universities under Grant no. 2015MS29.

语种：英文

外文关键词：Load frequency control; Integral sliding mode control; Neural networks; Power systems; Wind turbine

摘要：Load frequency control (LFC) plays an important role in maintaining constant frequency in order to ensure the reliability of power systems. With the large-scale development of sustainable but intermittent sources such as wind and solar, such intermittency challenges the LFC problem. Moreover, the generation rate constraint (GRC) of power systems also complexes the LFC problem. Concerning the constraint, this paper addresses an integral sliding mode control (I-SMC) method for power systems with wind turbines. Since the intermittency of wind farms and the linearization of GRC deteriorate the uncertainties of power systems, sliding-mode-based neural networks are designed to approximate the uncertainties. Weight update formulas of the neural networks are derived from the Lyapunov direct method. The neural-network-based integral sliding mode controller is employed to achieve the LFC problem. By this scheme, not only are the update formulas obtained, but also the control system possesses the asymptotic stability. The simulation results by an interconnected power system illustrate the feasibility and validity of the presented method. (C) 2015 Elsevier B.V. All rights reserved.