Agents In Multi-agent System Research Articles

Active collaboration in relative observation for multi-agent visual simultaneous localization and mapping based on Deep Q Network

This article proposes a unique active relative localization mechanism for multi-agent simultaneous localization and mapping, in which an agent to be observed is considered as a task, and the others who want to assist that agent will perform that task by relative observation. A task allocation algorithm based on deep reinforcement learning is proposed for this mechanism. Each agent can choose whether to localize other agents or to continue independent simultaneous localization and mapping on its own initiative. By this way, the process of each agent simultaneous localization and mapping will be interacted by the collaboration. Firstly, a unique observation function which models the whole multi-agent system is obtained based on ORBSLAM. Secondly, a novel type of Deep Q Network called multi-agent systemDeep Q Network (MAS-DQN) is deployed to learn correspondence between Q value and state–action pair, abstract representation of agents in multi-agent system is learned in the process of collaboration among agents. Finally, each agent must act with a certain degree of freedom according to MAS-DQN. The simulation results of comparative experiments prove that this mechanism improves the efficiency of cooperation in the process of multi-agent simultaneous localization and mapping.

Improving trust and reputation assessment with dynamic behaviour

AbstractTrust between agents in multi-agent systems (MASs) is critical to encourage high levels of cooperation. Existing methods to assess trust and reputation use direct and indirect past experiences about an agent to estimate their future performance; however, these will not always be representative if agents change their behaviour over time.Real-world distributed networks such as online market places, P2P networks, pervasive computing and the Smart Grid can be viewed as MAS. Dynamic agent behaviour in such MAS can arise from seasonal changes, cheaters, supply chain faults, network traffic and many other reasons. However, existing trust and reputation models use limited techniques, such as forgetting factors and sliding windows, to account for dynamic behaviour.In this paper, we propose Reacting and Predicting in Trust and Reputation (RaPTaR), a method to extend existing trust and reputation models to give agents the ability to monitor the output of interactions with a group of agents over time to identify any likely changes in behaviour and adapt accordingly. Additionally, RaPTaR can provide ana prioriestimate of trust when there is little or no interaction data (either because an agent is new or because a detected behaviour change suggests recent past experiences are no longer representative). Our results show that RaPTaR has improved performance compared to existing trust and reputation methods when dynamic behaviour causes the ranking of the best agents to interact with to change.

Modeling the Negotiation of Agents in MAS and Predicting the Performance an SPE Approach

Software performance engineering(SPE) process starts at the early stages of software development life cycle which helps to develop software that meets the performance requirements on time and budget. Multi-Agent Systems(MAS) are comprised of one or more agents who coordinate each other to accomplish some task. The coordination can be achieved through cooperation and negotiation. In the early development stages measuring the negotiation workload and predicting the performance remains an important but largely unsolved problem. The problem of uncertainty regarding the negotiation workload is required to be addressed by estimation techniques. Hence, in this research we developed a probabilistic model for the negotiation scenario among the agents in a given time horizon. The negotiation workload obtained from the probabilistic model is integrated with the representative workload of the agents for predicting the performance of agents in MAS. The tool SMTQA is used for obtaining the performance metrics. Analysis of the execution environment is done by considering various configurations in the hardware resources based on the dynamic workload of the negotiation agents over a time horizon. From the sensitivity analysis, the bottleneck resources are identified and suggestions for improvement are proposed.

Semi-global containment control of discrete-time linear systems with actuator position and rate saturation

In this paper, we study semi-global containment control problem for a multi-agent system in the presence of multiple leader agents. We describe the dynamics of each follower agent in multi-agent system by a general discrete-time linear system subject to both actuator position and rate saturation. By using low gain approach, we construct both a linear state feedback control law and an observer-based output feedback control law for each follower agent. Under some standard assumptions, we provide a sufficient condition to guarantee that the states of follower agents converge to the convex hull formed by the leader agents asymptotically. Finally, we illustrate the theoretical results by numerical simulation results.

ASSESSING PERFORMANCE OF AGENTS IN A MAS: AN EXPERIMENTAL STUDY

A Multi-Agent System (MAS) is understood as a system consisting of interacting autonomous agents. Research on MAS is mainly concerned with functional properties such as coordination, rationality, and knowledge modeling. A very less attention is paid for the research activity on the nonfunctional properties performance, scalability and reliability of the MAS. However, as the MAS technologies have gradually matured to be exploited in building practical distributed applications, the non-functional properties have become increasingly important, and it is now vital to pay attention to the issues of nonfunctional characteristics of agents. We propose to access the performance of agents in MAS and the system is implemented using JADE. The experimental study provides the opportunity for cause and effect relationships. We considered a tiered architecture for the MAS. A tiered design can lessen the overall impact of changes to the application and allows modifying a component without disturbing the next Tier. So with the help of a good deployment plan, we can distribute the layers over multiple physical tiers in distributed computing to implement a better architecture of the system. The case study considered for illustration is Supply-Chain Management and the results obtained are validated with the tool SMTQA.

Consensus of fractional-order multiagent system via sampled-data event-triggered control

This paper investigates the consensus of fractional-order multiagent systems via sampled-data event-triggered control. Firstly, an event-triggered algorithm is defined using sampled states. Thus, Zeno behaviors can be naturally avoided. Then, a distributed control protocol is proposed to ensure the consensus of fractional-order multiagent systems, where each agent updates its current state based on its neighbors’ states at event-triggered instants. Furthermore, the pinning control technology is taken into account to ensure all agents in multiagent systems reach the specified reference state. With the aid of linear matrix inequalities (LMI), some sufficient conditions are obtained to guarantee the consensus of fractional-order multiagent system. Finally, numerical simulations are presented to demonstrate the theoretical analysis.

Protocol and role: abstraction mechanisms in agent oriented programming languages

The language mechanisms protocol and role are used in order to organise the interaction structures between agents in multi-agent systems. Agents are internally organised by means of roles, roles are related as protocols, and agents send messages to each other through their related roles. The comprehensive and complex interaction structures between agents are conceptualised by protocol and role, and these abstraction mechanisms are used in the description of interaction structures. The description of the interaction structures between agents becomes understandable and the development process of multi-agent systems becomes efficient and flexible. The language mechanisms are illustrated by means of a supporting application framework.

Protocol and role: abstraction mechanisms in agent oriented programming languages

The language mechanisms protocol and role are used in order to organise the interaction structures between agents in multi-agent systems. Agents are internally organised by means of roles, roles are related as protocols, and agents send messages to each other through their related roles. The comprehensive and complex interaction structures between agents are conceptualised by protocol and role, and these abstraction mechanisms are used in the description of interaction structures. The description of the interaction structures between agents becomes understandable and the development process of multi-agent systems becomes efficient and flexible. The language mechanisms are illustrated by means of a supporting application framework.

Psychology-Inspired Trust Restoration Framework in Distributed Multiagent Systems

Trust violation during cooperation of autonomous agents in multiagent systems is usually unavoidable and can arise due to a wide number of reasons. From a psychological point of view, the violation of an agent’s trust is a result of one agent (which is a transgressor) expressing a very low weight on the welfare of another agent (which is a victim) by inflicting a high cost for a very small benefit. In order for the victim to make an effective decision about whether to cooperate or punish for the next interaction, a psychological variable called welfare tradeoff ratio (WTR) can be used to upregulate the transgressor’s disposition so that the number of exploitive behaviors that are likely to happen in the future will be decreased. In this paper, we propose computational models of metrics based on the welfare tradeoff ratio along with the way by which multiple metrics can be integrated to provide the final result. Additionally, a number of experiments based on social network analysis are conducted to evaluate the performance of the proposed framework and the results show that by implementing WTR the simulated network is able to deal with different levels of trust violation effectively.

A MAS-Based Cloud Service Brokering System to Respond Security Needs of Cloud Customers

Cloud computing is becoming a key factor in computer science and an important technology for many organizations to deliver different types of services. The companies which provide services to customers are called as cloud service providers. The cloud users (CUs) increase and require secure, reliable and trustworthy cloud service providers (CSPs) from the market. So, it’s a challenge for a new customer to choose the highly secure provider. This paper presents a cloud service brokering system in order to analyze and rank the secured cloud service provider among the available providers list. This model uses an autonomous and flexible agent in multi-agent system (MASs) that have an intelligent behavior and suitable tools for helping the brokering system to assess the security risks for the group of cloud providers which make decision of the more secured provider and justify the business needs of users in terms of security and reliability.

Heuristics-Based Trust Estimation in Multiagent Systems Using Temporal Difference Learning.

The application of multiagent system (MAS) is becoming increasing popular as it allows agents in a system to pool resources together to achieve a common objective. A vital part of the MAS is the teamwork cooperation through the sharing of information and resources among the agents to optimize their efforts in accomplishing given objectives. A critical part of the teamwork effort is the ability to trust each other when executing any task to ensure efficient and successful cooperation. This paper presents the development of a trust estimation model that could empirically evaluate the trust of an agent in MAS. The proposed model is developed using temporal difference learning by incorporating the concept of Markov games and heuristics to estimate trust. Simulation experiments are conducted to test and evaluate the performance of the developed model against some of the recently reported model in the literature. The simulation experiments indicate that the developed model performs better in terms of accuracy and efficiency in estimating trust.

ProMoca: Probabilistic Modeling and Analysis of Agents in Commitment Protocols

Social commitment protocols regulate interactions of agents in multiagent systems. Several methods have been developed to analyze properties of commitment protocols. However, analysis of an agent's behavior in a commitment protocol, which should take into account the agent's goals and beliefs, has received less attention. In this paper we present ProMoca framework to address this issue. Firstly, we develop an expressive formal language to model agents with respect to their commitments. Our language provides dedicated elements to define commitment protocols, and model agents in terms of their goals, behaviors, and beliefs. Furthermore, our language provides probabilistic and non-deterministic elements to model uncertainty in agents' beliefs. Secondly, we identify two essential properties of an agent with respect to a commitment protocol, namely compliance and goal satisfaction. We formalize these properties using a probabilistic variant of linear temporal logic. Thirdly, we adapt a probabilistic model checking algorithm to automatically analyze compliance and goal satisfaction properties. Finally, we present empirical results about efficiency and scalability of ProMoca.

Iterative Learning Control of Energy Management System: Survey on Multi-Agent System Framework

This paper presents a brief survey of recent works on Iterative Learning Control (ILC) of Energy Management System (EMS) based on a framework of Multi-Agent System (MAS). ILC is a control methodology which is especially suitable for dynamical systems whose control tasks are executed in a finite time interval and are repeated over and over. The key idea of ILC is to take available system information in the past and current runs, to generate the control input for the next run. EMS is a computer-based system to monitor energy consumption, control operation, and optimize energy supplies and demands. EMS can be naturally modeled as MAS since each power-generated or power-consumed component of EMS can be cast as agent. Each agent of MAS is a dynamical system itself and has its own target such as tracking desired trajectory and minimizing energy. Moreover, there are common objectives of EMS which aim to attain its energy efficiency, reliability and optimality. Then one agent can cooperate with other agents to achieve some global objectives, in addition to their own local goals, by exchanging information with other agents. Lastly, we will explore some open research problems and their potential applications.

Leader-following consensus of multi-agent systems with limited data rate

This paper investigates the leader-following consensus problem of time-invariant linear multi-agent systems with limited data rate. Based on the idea of assigning a priority level for each agent of the concerned multi-agent system, a novel distributed control law has been proposed. The proposed control law has two distinctive advantages. That is, it is fully distributed in the sense that it does not rely on the eigenvalues of the Laplace matrix associated with the topology. Moreover, the required data rate is independent of the number of agents and remains small even if the number of the agents in multi-agent systems is large. An example is finally given to illustrate the effectiveness of the proposed controller.

Fuzzy-Based Multi-Agent System for Distributed Energy Management in Smart Grids

Energy Management Systems have become an imperative aspect of smart grids, owing to the enormous challenges imposed due to real-time pricing, distributed generation and integration of intermittent renewables. Due to the uncertainty associated with renewable sources and prominent fluctuations in the load demand, it is extremely important to maintain the overall energy balance in such grids. In this paper, the distributed energy management is achieved using a Multi-agent System which provides a flexible and reliable solution to control and manage smart grids. Adaptive fuzzy systems are designed to instill intelligent decision making capability in the agents of multi-agent system. When renewable sources are inadequate, the sustainability of the system is not guaranteed and multi-agent system is capable of deciding the mode of operation such that the system reliability and performance is not compromised. The proposed algorithm maintains power balance in the system and also sustains desired values for the State of Charge of storage units in order to guarantee extended battery life. The Energy management system also implements a cost optimization algorithm based on the Particle Swarm Optimization technique, to minimize operating costs and maximize profits earned by the grid. The proposed energy management algorithm is tested and validated on a practical test system which inherits most of the features of a small-scale smart grid.

Multiagent Systems Based Modeling and Implementation of Dynamic Energy Management of Smart Microgrid Using MACSimJX.

The objective of this paper is implementation of multiagent system (MAS) for the advanced distributed energy management and demand side management of a solar microgrid. Initially, Java agent development environment (JADE) frame work is used to implement MAS based dynamic energy management of solar microgrid. Due to unstable nature of MATLAB, when dealing with multithreading environment, MAS operating in JADE is linked with the MATLAB using a middle ware called Multiagent Control Using Simulink with Jade Extension (MACSimJX). MACSimJX allows the solar microgrid components designed with MATLAB to be controlled by the corresponding agents of MAS. The microgrid environment variables are captured through sensors and given to agents through MATLAB/Simulink and after the agent operations in JADE, the results are given to the actuators through MATLAB for the implementation of dynamic operation in solar microgrid. MAS operating in JADE maximizes operational efficiency of solar microgrid by decentralized approach and increase in runtime efficiency due to JADE. Autonomous demand side management is implemented for optimizing the power exchange between main grid and microgrid with intermittent nature of solar power, randomness of load, and variation of noncritical load and grid price. These dynamics are considered for every time step and complex environment simulation is designed to emulate the distributed microgrid operations and evaluate the impact of agent operations.

Combining reward shaping and hierarchies for scaling to large multiagent systems

AbstractCoordinating the actions of agents in multiagent systems presents a challenging problem, especially as the size of the system is increased and predicting the agent interactions becomes difficult. Many approaches to improving coordination within multiagent systems have been developed including organizational structures, shaped rewards, coordination graphs, heuristic methods, and learning automata. However, each of these approaches still have inherent limitations with respect to coordination and scalability. We explore the potential of synergistically combining existing coordination mechanisms such that they offset each others’ limitations. More specifically, we are interested in combining existing coordination mechanisms in order to achieve improved performance, increased scalability, and reduced coordination complexity in large multiagent systems.In this work, we discuss and demonstrate the individual limitations of two well-known coordination mechanisms. We then provide a methodology for combining the two coordination mechanisms to offset their limitations and improve performance over either method individually. In particular, we combine shaped difference rewards and hierarchical organization in the Defect Combination Problem with up to 10 000 sensing agents. We show that combining hierarchical organization with difference rewards can improve both coordination and scalability by decreasing information overhead, structuring agent-to-agent connectivity and control flow, and improving the individual decision-making capabilities of agents. We show that by combining hierarchies and difference rewards, the information overheads and computational requirements of individual agents can be reduced by as much as 99% while simultaneously increasing the overall system performance. Additionally, we demonstrate the robustness of this approach to handling up to 25% agent failures under various conditions.

Design of Multi-agent Emergency Dispatching Model to Strengthen Resiliency of Taiwan High-speed Rail System

Although HSR (high-speed rail) systems can provide good service quality, such the systems have not been designed to handle disaster-related events very well, i.e., the trains dispatching work during a disaster. In other words, if there is no experienced train dispatchers in the control center of a HSR system, extended delays and possible catastrophic system failures might occur, thus exacerbating the impact caused by the disaster. Recently, a novel approach called the multi-agent system (MAS) is being increasingly used in transportation applications. Within a multi-agent assisted environment, a stakeholder such as train driver and depot manager can consultant with the corresponding MAS agent about the best trains dispatching strategy. The proposed ontology-based, multi-agent model was tested by using Taiwan HSR real dispatching cases. The results show the potential of assisting train dispatchers in handling disaster scenarios in a more efficient and effective way.

Selecting advisor agents using reliability, reputation and risks

This paper presents an enhanced trust model for evaluating and selecting trustworthy advisor agents in multi-agent systems. In particular, the study proposes a computational trust model based on three main components, reliability, reputation and risk of interactions (3-R) in order to select trustworthy advisor agents. These advisors are buyer agents which suggest a trustworthy seller agent for transaction. The 3-R model represents a method for calculating reliability, with each advisor that has similar preferences with the buyer. Experimental results are presented in defense of the proposed approach and to demonstrate the accuracy of the presented model in evaluating the trustworthiness of advisors, even when a social network of advisors contains few numbers of advisors. The proposed 3-R model will be useful for researchers to improve the safety of electronic marketplaces in the case where the buyer agent has no previous experience with sellers, and it has to trust the other buyers as an advisor to make a decision about sellers.

Creation of Calculating Agent in Multi-Agent System of Technological Destination

Creation of Calculating Agent in Multi-Agent System of Technological Destination