Pinning Distributed Synchronization of Stochastic Dynamical Networks: A Mixed Optimization Approach

被引：111

作者：

Tang, Yang ^{[1
,2
]}

Gao, Huijun ^{[3
,4
]}

Lu, Jianquan ^{[5
]}

Kurths, Juergen ^{[1
,2
,6
]}

机构：

[1] Potsdam Inst Climate Impact Res, D-14473 Potsdam, Germany

[2] Humboldt Univ, Inst Phys, D-12489 Berlin, Germany

[3] Harbin Inst Technol, Res Inst Intelligent Control & Syst, Harbin 150080, Peoples R China

[4] King Abdulaziz Univ, Nonlinear Anal & Appl Math Grp, Jeddah 22254, Saudi Arabia

[5] Southeast Univ, Dept Math, Nanjing 210096, Jiangsu, Peoples R China

[6] Univ Aberdeen, Inst Complex Syst & Math Biol, Aberdeen AB24 3UE, Scotland

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS | 2014年 / 25卷 / 10期

基金：

中国国家自然科学基金;

关键词：

Complex networks; evolutionary algorithms (EAs); multiagent systems; neural networks; stochastic disturbances; synchronization; COUPLED NEURAL-NETWORKS; CONSENSUS; PARAMETERS; SYSTEMS; AGENTS;

D O I：

10.1109/TNNLS.2013.2295966

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper is concerned with the problem of pinning synchronization of nonlinear dynamical networks with multiple stochastic disturbances. Two kinds of pinning schemes are considered: 1) pinned nodes are fixed along the time evolution and 2) pinned nodes are switched from time to time according to a set of Bernoulli stochastic variables. Using Lyapunov function methods and stochastic analysis techniques, several easily verifiable criteria are derived for the problem of pinning distributed synchronization. For the case of fixed pinned nodes, a novel mixed optimization method is developed to select the pinned nodes and find feasible solutions, which is composed of a traditional convex optimization method and a constraint optimization evolutionary algorithm. For the case of switching pinning scheme, upper bounds of the convergence rate and the mean control gain are obtained theoretically. Simulation examples are provided to show the advantages of our proposed optimization method over previous ones and verify the effectiveness of the obtained results.

引用

页码：1804 / 1815

页数：12

共 40 条

[1] Radial Basis Function Network Training Using a Nonsymmetric Partition of the Input Space and Particle Swarm Optimization [J].

Alexandridis, Alex ;

Chondrodima, Eva ;

Sarimveis, Haralambos .

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2013, 24 (02) :219-230

[2]

[Anonymous], 1985, Matrix Analysis

[3]

[Anonymous], P IEEE C EV COMP FEB

[4]

[Anonymous], 2007, STOCHASTIC DIFFERENT

[5] Synchronization in complex networks [J].

Arenas, Alex ;

Diaz-Guilera, Albert ;

Kurths, Jurgen ;

Moreno, Yamir ;

Zhou, Changsong .

PHYSICS REPORTS-REVIEW SECTION OF PHYSICS LETTERS, 2008, 469 (03) :93-153

[6] Emergence of scaling in random networks [J].

Barabási, AL ;

Albert, R .

SCIENCE, 1999, 286 (5439) :509-512

[7] Self-adapting control parameters in differential evolution: A comparative study on numerical benchmark problems [J].

Brest, Janez ;

Greiner, Saso ;

Boskovic, Borko ;

Mernik, Marjan ;

Zumer, Vijern .

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, 2006, 10 (06) :646-657

[8] Pinning complex networks by a single controller [J].

Chen, Tianping ;

Liu, Xiwei ;

Lu, Wenlian .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2007, 54 (06) :1317-1326

[9]

Ditto W, 2002, NATURE, V415, P736, DOI 10.1038/415736b

[10] Coordination of groups of mobile autonomous agents using nearest neighbor rules [J].

Jadbabaie, A ;

Lin, J ;

Morse, AS .

IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2003, 48 (06) :988-1001

← 1 2 3 4 →