A Collaborative Neurodynamic Optimization Approach to Distributed Nash-Equilibrium Seeking in Multicluster Games With Nonconvex Functions

Zicong Xia; Yang Liu; Wenwu Yu; Jun Wang

doi:10.1109/TCYB.2023.3289712

A Collaborative Neurodynamic Optimization Approach to Distributed Nash-Equilibrium Seeking in Multicluster Games With Nonconvex Functions

Zicong Xia
, Yang Liu^*
, Wenwu Yu
, Jun Wang

^*Corresponding author for this work

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

27 Citations (Scopus)

Abstract

In this article, we propose a collaborative neurodynamic optimization (CNO) method for the distributed seeking of generalized Nash equilibriums (GNEs) in multicluster games with nonconvex functions. Based on an augmented Lagrangian function, we develop a projection neural network for the local search of GNEs, and its convergence to a local GNE is proven. We formulate a global optimization problem to which a global optimal solution is a high-quality local GNE, and we adopt a CNO approach consisting of multiple recurrent neural networks for scattering searches and a metaheuristic rule for reinitializing states. We elaborate on an example of a price-bidding problem in an electricity market to demonstrate the viability of the proposed approach. © 2023 IEEE.

Original language	English
Pages (from-to)	3105-3119
Number of pages	15
Journal	IEEE Transactions on Cybernetics
Volume	54
Issue number	5
Online published	19 Jul 2023
DOIs	https://doi.org/10.1109/TCYB.2023.3289712
Publication status	Published - May 2024

Funding

This work was supported in part by the National Key Research and Development Program of China under Grant 2022ZD0120001; in part by the National Natural Science Foundation of China under Grant 62173308, Grant 62233004, and Grant 62073076; in part by the Natural Science Foundation of Zhejiang Province of China under Grant LR20F030001; in part by the Jinhua Science and Technology Project under Grant 2022-1-042; and in part by the Research Grants Council of the Hong Kong Special Administrative Region of China through the General Research Fund under Grant 11202019.

Research Keywords

Collaboration
Collaborative neurodynamic optimization (CNO)
Convergence
distributed Nash-equilibrium seeking
Games
Metaheuristics
multicluster game
Neurodynamics
nonconvexity
Optimization
Recurrent neural networks
recurrent neural networks (RNNs)

RGC Funding Information

RGC-funded

Access Output

10.1109/TCYB.2023.3289712

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{93cf8c807a3a479d94d6995e72e2603c,

title = "A Collaborative Neurodynamic Optimization Approach to Distributed Nash-Equilibrium Seeking in Multicluster Games With Nonconvex Functions",

abstract = "In this article, we propose a collaborative neurodynamic optimization (CNO) method for the distributed seeking of generalized Nash equilibriums (GNEs) in multicluster games with nonconvex functions. Based on an augmented Lagrangian function, we develop a projection neural network for the local search of GNEs, and its convergence to a local GNE is proven. We formulate a global optimization problem to which a global optimal solution is a high-quality local GNE, and we adopt a CNO approach consisting of multiple recurrent neural networks for scattering searches and a metaheuristic rule for reinitializing states. We elaborate on an example of a price-bidding problem in an electricity market to demonstrate the viability of the proposed approach. {\textcopyright} 2023 IEEE.",

keywords = "Collaboration, Collaborative neurodynamic optimization (CNO), Convergence, distributed Nash-equilibrium seeking, Games, Metaheuristics, multicluster game, Neurodynamics, nonconvexity, Optimization, Recurrent neural networks, recurrent neural networks (RNNs)",

author = "Zicong Xia and Yang Liu and Wenwu Yu and Jun Wang",

year = "2024",

month = may,

doi = "10.1109/TCYB.2023.3289712",

language = "English",

volume = "54",

pages = "3105--3119",

journal = "IEEE Transactions on Cybernetics",

issn = "2168-2267",

publisher = "IEEE",

number = "5",

}

TY - JOUR

T1 - A Collaborative Neurodynamic Optimization Approach to Distributed Nash-Equilibrium Seeking in Multicluster Games With Nonconvex Functions

AU - Xia, Zicong

AU - Liu, Yang

AU - Yu, Wenwu

AU - Wang, Jun

PY - 2024/5

Y1 - 2024/5

N2 - In this article, we propose a collaborative neurodynamic optimization (CNO) method for the distributed seeking of generalized Nash equilibriums (GNEs) in multicluster games with nonconvex functions. Based on an augmented Lagrangian function, we develop a projection neural network for the local search of GNEs, and its convergence to a local GNE is proven. We formulate a global optimization problem to which a global optimal solution is a high-quality local GNE, and we adopt a CNO approach consisting of multiple recurrent neural networks for scattering searches and a metaheuristic rule for reinitializing states. We elaborate on an example of a price-bidding problem in an electricity market to demonstrate the viability of the proposed approach. © 2023 IEEE.

AB - In this article, we propose a collaborative neurodynamic optimization (CNO) method for the distributed seeking of generalized Nash equilibriums (GNEs) in multicluster games with nonconvex functions. Based on an augmented Lagrangian function, we develop a projection neural network for the local search of GNEs, and its convergence to a local GNE is proven. We formulate a global optimization problem to which a global optimal solution is a high-quality local GNE, and we adopt a CNO approach consisting of multiple recurrent neural networks for scattering searches and a metaheuristic rule for reinitializing states. We elaborate on an example of a price-bidding problem in an electricity market to demonstrate the viability of the proposed approach. © 2023 IEEE.

KW - Collaboration

KW - Collaborative neurodynamic optimization (CNO)

KW - Convergence

KW - distributed Nash-equilibrium seeking

KW - Games

KW - Metaheuristics

KW - multicluster game

KW - Neurodynamics

KW - nonconvexity

KW - Optimization

KW - Recurrent neural networks

KW - recurrent neural networks (RNNs)

UR - https://www.scopus.com/pages/publications/85165240700

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85165240700&origin=recordpage

U2 - 10.1109/TCYB.2023.3289712

DO - 10.1109/TCYB.2023.3289712

M3 - RGC 21 - Publication in refereed journal

SN - 2168-2267

VL - 54

SP - 3105

EP - 3119

JO - IEEE Transactions on Cybernetics

JF - IEEE Transactions on Cybernetics

IS - 5

ER -

A Collaborative Neurodynamic Optimization Approach to Distributed Nash-Equilibrium Seeking in Multicluster Games With Nonconvex Functions

Abstract

Funding

Research Keywords

RGC Funding Information

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

GRF: Collaborative Neurodynamic Approaches to Portfolio Optimization

Cite this

A Collaborative Neurodynamic Optimization Approach to Distributed Nash-Equilibrium Seeking in Multicluster Games With Nonconvex Functions

Abstract

Funding

Research Keywords

RGC Funding Information

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Projects

GRF: Collaborative Neurodynamic Approaches to Portfolio Optimization

Cite this