Multi-agent Networks Research Articles

Distributed Optimization With Projection-Free Dynamics: A Frank-Wolfe Perspective.

We consider solving distributed constrained optimization in this article. To avoid projection operations due to constraints in the scenario with large-scale variable dimensions, we propose distributed projection-free dynamics by employing the Frank-Wolfe method, also known as the conditional gradient. Technically, we find a feasible descent direction by solving an alternative linear suboptimization. To make the approach available over multiagent networks with weight-balanced digraphs, we design dynamics to simultaneously achieve both the consensus of local decision variables and the global gradient tracking of auxiliary variables. Then, we present the rigorous convergence analysis of the continuous-time dynamical systems. Also, we derive its discrete-time scheme with an accordingly proved convergence rate of O(1/k) . Furthermore, to clarify the advantage of our proposed distributed projection-free dynamics, we make detailed discussions and comparisons with both existing distributed projection-based dynamics and other distributed Frank-Wolfe algorithms.

Composite Optimization With Coupling Constraints via Penalized Proximal Gradient Method in Asynchronous Networks

In this paper, we consider a composite optimization problem with linear coupling constraints in a multi-agent network. In this problem, the agents cooperatively optimize a strongly convex cost function which is the linear sum of individual cost functions composed of smooth and possibly non-smooth components. To solve this problem, we propose an asynchronous penalized proximal gradient (Asyn-PPG) algorithm, a variant of classical proximal gradient method, with the presence of the asynchronous updates of the agents and uniform communication delays in the network. Specifically, we consider a slot-based asynchronous network (SAN), where the whole time domain is split into sequential time slots and each agent is permitted to execute multiple updates during a slot by accessing the historical state information of the agents. By the Asyn-PPG algorithm, an explicit convergence rate can be guaranteed based on deterministic analysis. The feasibility of the proposed algorithm is verified by solving a consensus-based distributed regression problem and a social welfare optimization problem in the electricity market.

Accelerated Decentralized Load Balancing in Multi-Agent Networks

Accelerated Decentralized Load Balancing in Multi-Agent Networks

Distributed Model Predictive Control via Separable Optimization in Multiagent Networks

We present a distributed model predictive control method which enables a group of agents to compute their control inputs locally, while communicating with their neighbors over a communication network. While many distributed model predictive control methods require a central station for some coordination or computation of the optimization variables, our method does not require a central station, making our approach applicable to a variety of communication network topologies. With our method, each agent solves for its control inputs without solving for the control inputs of other agents, allowing for efficient optimization by each agent, unlike some other distributed methods. Further, our method attains linear convergence to the optimal control inputs in convex model predictive control problems, improving upon the sub-linear convergence rates provided by some other distributed methods such as dual decomposition methods. Moreover, our algorithm provides a closed-loop controller for convex model predictive control problems with affine constraints. We demonstrate our method in both convex and non-convex model predictive control problems in wireless transceiver alignment and satellite deployment, where we show robustness of our method to time delays.

Whole-Process Privacy-Preserving and Sybil-Resilient Consensus for Multiagent Networks.

This article is concerned with the co-design of privacy-preserving and resilient consensus protocol for a class of multiagent networks (MANs), where the information exchanges over communication networks among the agents suffer from eavesdropping and Sybil attacks. First, we introduce a new attack model in which an adversarial agent could launch a Sybil attack, generating a large number of spurious entities in the network, thereby gaining disproportionate influence. In this communication framework, a whole-process privacy-preserving mechanism is designed that is capable of protecting both initial and current states of agents. Then, instead of existing methods requiring identifying and mitigating Sybil nodes, a degree-based mean-subsequence-reduced (D-MSR) resilient strategy is implemented, showcasing its significant properties: 1) ensuring the effectiveness of aforementioned designed privacy protection strategy; 2) allowing the network to contain Sybil nodes without elimination; and 3) reaching consensus among the normal agents. Finally, several numerical simulations are provided to validate the effectiveness of the proposed results.

Multi-Agent Transformer Networks With Graph Attention

Multi-Agent Transformer Networks With Graph Attention

Research on the Propagation and Evolution of Multi-agent Collaborative Relationship Networks based on the SIR Model

Research on the Propagation and Evolution of Multi-agent Collaborative Relationship Networks based on the SIR Model

Decentralized Optimal Power Flow for Multi-Agent Active Distribution Networks: A Differentially Private Consensus ADMM Algorithm

Decentralized Optimal Power Flow for Multi-Agent Active Distribution Networks: A Differentially Private Consensus ADMM Algorithm

Diffusion of ESG Behavior Improvement Strategy for New Energy Enterprises under Weighted Benefit Risk Mechanism ——Based on Complex Network Evolution Game

In order to explore the impact of the enterprise's right, responsibility and profit risk mechanism on the enterprise's ESG behavior improvement strategy in the context of carbon emission reduction, this study uses Matlab to build a new energy enterprise cooperation game network model and establish the NW small world initial network. According to the process and result of multi-agent complex network game, this paper analyzes the strategic choice and development factors of ESG behavior in new energy enterprises. It is found that when the awareness of executives increases, the profits of enterprises will increase, but the spread of ESG behavior improvement is not significant; When the competitive intensity of enterprises increases, the profits of enterprises with ESG behavior improvement will decrease, and the diffusion of ESG behavior improvement strategy will be slow. When the price of carbon trading increases, the income of enterprises adopting ESG behavior will increase, but the sensitivity of carbon trading price to the expansion of enterprise network is not significant.

Sustainable Distributed Adaptive Platoon in Multi-Agent Mobile-Edge Computing Networks for Lane Reduction Scenario

Sustainable Distributed Adaptive Platoon in Multi-Agent Mobile-Edge Computing Networks for Lane Reduction Scenario

Adaptive Prescribed-Time Consensus for a Class of Nonlinear Multi-Agent Networks by Bounded Time-Varying Protocols

Adaptive Prescribed-Time Consensus for a Class of Nonlinear Multi-Agent Networks by Bounded Time-Varying Protocols

Cucker–Smale Flocking Behavior for Multiagent Networks With Coopetition Interactions and Communication Delays

Cucker–Smale Flocking Behavior for Multiagent Networks With Coopetition Interactions and Communication Delays

Logarithmically Quantized Distributed Optimization Over Dynamic Multi-Agent Networks

Logarithmically Quantized Distributed Optimization Over Dynamic Multi-Agent Networks

Consensus of Heterogeneous Multi-agent Networks Under Sparse Attacks by Integral Type Observer

Consensus of Heterogeneous Multi-agent Networks Under Sparse Attacks by Integral Type Observer

Uncertainty-Aware Portfolio Management With Risk-Sensitive Multiagent Network.

As deep neural networks (DNNs) have gained considerable attention in recent years, there have been several cases applying DNNs to portfolio management (PM). Although some researchers have experimentally demonstrated its ability to make a profit, it is still insufficient to use in real situations because existing studies have failed to answer how risky investment decisions are. Furthermore, even though the objective of PM is to maximize returns within a risk tolerance, they overlook the predictive uncertainty of DNNs in the process of risk management. To overcome these limitations, we propose a novel framework called risk-sensitive multiagent network (RSMAN), which includes risk-sensitive agents (RSAs) and a risk adaptive portfolio generator (RAPG). Standard DNNs do not understand the risks of their decision, whereas RSA can take risk-sensitive decisions by estimating market uncertainty and parameter uncertainty. Acting as a trader, this agent is trained via reinforcement learning from dynamic trading simulations to estimate the distribution of reward and via unsupervised learning to assess parameter uncertainty without labeled data. We also present an RAPG that can generate a portfolio fitting the user's risk appetite without retraining by exploiting the estimated information from the RSAs. We tested our framework on the U.S. and Korean real financial markets to demonstrate the practicality of the RSMAN.

Event-Triggered Distributed Hypothesis Testing for Multiagent Networks Based on Observations Cumulation.

This article is concerned with the distributed hypothesis testing problem for multiagent networks, where a group of agents aim to learn an optimal hypothesis set via informative observations and event-triggered communication. Within this framework, a new event-triggered distributed hypothesis testing algorithm based on cumulation of historical observations is proposed. Theoretically, it is proven that due to the introduction of cumulation of historical observations, the proposed algorithm can always ensure the convergence whatever the event-triggered parameters are selected. This convergence result is different from that of the existing algorithm without involving historical observations, where the event-triggered parameters should satisfy a specific design condition to ensure the convergence of the algorithm. In addition, an explicit description of the convergence rate of the proposed algorithm is provided. Finally, the effectiveness of the algorithm is demonstrated through simulation examples.

Communication Limited Hybrid Impulsive Control of Fuzzy Time-Delay Multiagent Network

Communication Limited Hybrid Impulsive Control of Fuzzy Time-Delay Multiagent Network

Robust Constraint-Following Control for Networked Multiagent Systems With Uncertainties

Robust Constraint-Following Control for Networked Multiagent Systems With Uncertainties

A Networked Multiagent System for Mobile Wireless Infrastructure on Demand

A Networked Multiagent System for Mobile Wireless Infrastructure on Demand

A novel methodology to evaluate criticality and sensitivity of safety barrier based on multi-agent interaction network

Focusing on the criticality and sensitivity evaluation of safety barriers involved in the complex social-tech system, a Multi-agent Interaction Network (MAIN) analysis is proposed in the present study on the basis of Systems Theoretic Process Analysis (STPA). The task scenario is firstly transferred as control structure by STPA, in which the controller and controlled process are considered as agents. Meanwhile, the basic control loops in the control structure are modeled with the application of Petri net-based association rules to develop the sub-MAINs, which are assembled into the whole MAIN by the network assembly algorithms proposed in this study. Then, a probability flow model characterized by network Green’s function is proposed to quantify the performance indicators of safety barriers, which include but not limited to scarcity, sustainability, saturation, contribution. A task scenario of “anchoring operation” in the maritime industry is selected in this study to illustrate the application of the proposed methodology. The results show that MAIN-based methodology proposed in this study is able to well compensate the constraints of the traditional network analysis and has a great potential for barrier evaluation, as well as the safety barrier management in practical industry.