Multi-agent System Approach Research Articles

A multi-agent system approach based on cryptographic algorithm for securing communications and protecting stored data in the cloud-computing environment

The cloud computing has been envisioned as the next generation architecture of information technology enterprise. The Internet is indispensable in present days to provide and maintain the data. Such applications can be used by the end-user via the cloud communications without any configuration. Moreover, the user's data files can be accessed from any other computer using the Internet services. The security goal is to save data from threat and vulnerability which is handled by various approaches. The data should be encrypted prior to be transmitted and stored. We aim to propose a solution such that we will encrypt the whole data along with the cryptographic key. This contribution provides a new architecture that combines, obfuscation technique, hybrid encryption algorithms and the homomorphic encryption approaches. The proposed security architecture based on multi-agent system for cloud computing communications and storage environment that takes into account the most known security gaps.

A multi-agent system approach based on cryptographic algorithm for securing communications and protecting stored data in the cloud-computing environment

The cloud computing has been envisioned as the next generation architecture of information technology enterprise. The Internet is indispensable in present days to provide and maintain the data. Such applications can be used by the end-user via the cloud communications without any configuration. Moreover, the user's data files can be accessed from any other computer using the Internet services. The security goal is to save data from threat and vulnerability which is handled by various approaches. The data should be encrypted prior to be transmitted and stored. We aim to propose a solution such that we will encrypt the whole data along with the cryptographic key. This contribution provides a new architecture that combines, obfuscation technique, hybrid encryption algorithms and the homomorphic encryption approaches. The proposed security architecture based on multi-agent system for cloud computing communications and storage environment that takes into account the most known security gaps.

Fault tolerant cooperative control for affine multi-agent systems: An optimal control approach

The goal of this paper is to propose an optimal fault tolerant control (FTC) approach for multi-agent systems (MASs). It is assumed that the agents have identical affine dynamics. The underlying communication topology is assumed to be a directed graph. The concepts of both inverse optimality and partial stability are further employed for designing the control law fully developed in the paper. Firstly, the optimal FTC problem for linear MASs is formulated and then it is extended to MASs with affine nonlinear dynamics. To solve the Hamilton-Jacobi-Bellman (HJB) equation, an Off-policy Reinforcement Learning is used to learn the optimal control law for each agent. Finally, a couple of numerical examples are provided to demonstrate the effectiveness of the proposed scheme.

A simulation environment for polymeric nanoparticles based on multi-agent systems.

Production and characterization of polymeric nanoparticles, as colloidal dispersions, are processes that require time and technical skills to make the results accurate. Computational simulations in nanoscience have been used to help in these processes and provide agility and support to reach results: stability and quality in dispersions. Multi-Agent System for Polymeric Nanoparticles (MASPN) is an innovative and original simulation environment with features to demonstrate interactions of particles from physical-chemical parameters, ensuring Brownian motion of particles and attractive and repulsive behaviour. The MASPN environment has been designed and has been built according to the feature-driven development (FDD), as software methodology, and a multi-agent systems approach. In addition, we have used the event-driven simulation package algs4, the JASON agent building environment, all integrated by Java language. This paper aims to present the relation of the algs4 package and the JASON tool, both integrated into the MASPN environment to generate Brownian motion with elastic and inelastic collisions. The MASPN environment as a simulation tool emerges as a result, including the following features: graphical interface; integrated physical-chemical parameters; Brownian motion; JASON and algs4 integration; and distribution charts (size, zeta potential, and pH).

A human behavior model of multi-agent attention based on actor–observer switching for asynchronous motion tasks with limited field of view

This paper presents an overt visual attention approach for multi-agent systems and asynchronous motion tasks with limited field of view based on human behavior. In a first step, results from a study on human temporal attention switching during a formation task are presented. Three temporally switching human behaviors (observer, actor, idler) are identified and characterized towards distributions of attention foci. In a second step, based on these results, a behavior switching attention strategy is proposed. The strategy is evaluated in simulations of various formation task scenarios illustrating the effectiveness of the approach.

Modeling of individual customer delivery satisfaction: an AutoML and multi-agent system approach

PurposeThe purpose of this paper is to propose an automated machine learning (AutoML) and multi-agent system approach to improve overall product delivery satisfaction under limited resources.Design/methodology/approachAn AutoML method is purposed to model delivery satisfaction of individual customer, and a heuristic method and multi-agent system are proposed to improve overall satisfaction under limited processing capability. A series of simulation experiments have been conducted to illustrate the effectiveness of the proposed methodology.FindingsThe simulated results show that the proposed method can effectively improve overall delivery satisfaction, especially when the demand of customer orders is highly fluctuating and when the customer satisfaction models are highly diversified.Practical implicationsThe proposed framework provides a more dynamic and continuously improving way to model delivery satisfaction of individual customer, thereby supports companies to provide personalized services and develop scalable and flexible business at a lower cost, and ultimately improves the overall quality, efficiency and effectiveness of delivery services.Originality/valueThe proposed methodology utilizes AutoML and multi-agent system to model individual customer delivery satisfaction and improve the overall satisfaction. It can cooperate with the existing delivery resource planning methods to further improve customer delivery satisfaction. The authors propose an AutoML approach to model individual customer delivery satisfaction, which enables continuous update and improvements. The authors propose multi-agent system and a heuristic method to improve overall delivery satisfaction. The numerical results show that the proposed method can improve overall delivery satisfaction with limited processing capability.

A framework for generating and evaluating façade designs using a multi-agent system approach

Digital design paradigms in architecture have been rooted in representational models which are geometry centered and therefore fail to capture building complexity holistically. Due to a lack of computational design methodologies, existing digital design workflows do little in predicting design performance in the early design stage and in most cases analysis and design optimization are done after a design is fixed. This work proposes a new computational design methodology, intended for use in the area of conceptual design of building design. The proposed methodology is implemented into a multi-agent system design toolkit which facilitates the generation of design alternatives using stochastic algorithms and their evaluation using multiple environmental performance metrics. The method allows the user to probabilistically explore the solution space by modeling the design parameters’ architectural design components (i.e. façade panel) into modular programming blocks (agents) which interact in a bottom-up fashion. Different problem requirements (i.e. level of daylight inside a space, openings) described into agents’ behavior allow for the coupling of data from different engineering fields (environmental design, structural design) into the a priori formation of architectural geometry. In the presented design experiment, a façade panel is modeled into an agent-based fashion and the multi-agent system toolkit is used to generate and evolve alternative façade panel configurations based on environmental parameters (daylight, energy consumption). The designer can develop the façade panel geometry, design behaviors, and performance criteria to evaluate the design alternatives. The toolkit relies on modular and functionally specific programming modules (agents), which provide a platform for façade design exploration by combining existing three-dimensional modeling and analysis software.

Intelligent sustainable supplier selection using multi-agent technology: Theory and application for Industry 4.0 supply chains

Abstract Advancements in information and communication systems offer immense opportunities for supply chain intelligence and autonomy establishing stepping stones for Industry 4.0 supply chains (SCs). As a crucial SC decision, sustainable supplier evaluation and selection process have been addressed abundantly in the previous literature. However, this process has not yet been realized within Industry 4.0 SCs where interconnection, real-time information transparency, technical assistance and decentralization of members of a physical system (i.e., supply chain members) are regarded as the main design principles. To narrow the identified gap, a Multi-Agent Systems (MASs) approach is proposed for addressing sustainable supplier evaluation and selection process to provide a proper communication channel, structured information exchange and visibility among suppliers and manufacturers. Furthermore, the application of MASs in this process and their natural applicability as one of the enabling technologies in moving towards Industry 4.0 SCs are investigated in detail. It is found that the proposed approach can help decision-makers inside manufacturing firms to make prompt decisions with less human interactions. The merit of the developed MAS is demonstrated through a real-world implementation on a medical device manufacturer. Finally, the limitations and advantages of the proposed approach are presented together with some remarks for future work.

Method to analyze a local community as a complex adaptive system for resident-centered local community vitalization

A community is a system that cannot exist without the involvement of self-motivated people, and it is composed of humans, “Mono,” “Koto”, and their relationality. “Mono” in Japanese denotes a physically perceived entity (tangible), while “Koto” denotes a cognitively conceived entity (intangible). In other words, a local community is a typical example of a complex adaptive system, and it can be simulated by a suitable model such as multi-agent systems approach; this implies that it is possible to develop a local community as a complex adaptive system using appropriate design and analysis. In this paper, we investigated the methods to analyze a local community. We visualized the day-wise relationships among the experimental participants using the passing-each-other data collected from them. As a result, we confirmed that each participant formed clusters that varied day-wise. We could also confirm several features which helped establish that a local community is a complex adaptive system. Furthermore, the results were strikingly different for a weekday compared to a holiday.

Modelling of a production system using the multi-agent network approach

Since robotic systems become increasingly widespread in manufacturing environments, the need for improving production efficiency is the key factor for applying robots in industry. There are many different reasons involving robots application for manufacturing task realization. The most common reasons include their reliability, high quality of work, flexibility, inherent accuracy and repeatability. The approach to the problem of manufacturing processes robotization has changed a lot over several last years. In this article is presented the approach based on multi-agent systems approach resulting in the application for supporting functioning of the system of robotized manufacturing workcells. Complexity of the components created robotized workcells causes, that already at the design phase, it is necessary to develop models presenting various aspects of their structure and functioning. These models are simplified representation of real systems, allowing predicting some behaviour or responses what leads to systematize knowledge about the designed workcell. All of these factors involve, as the consequence, the additional difficulties associated with the process of decision-making. They concern, among other, on the coordination of components of such distributed system like a workcell and on providing the access to the required information, thereby generating unnecessary costs. The aim of this approach is determining the method for a flexible response and preventing situations that might contribute to delay of the robot task. The virtual system was modelled and simulated in common robot offline programming software.

A distributed approach to model-predictive control of radiant comfort delivery systems in office spaces with localized thermal environments

This paper introduces a new multi-agent system approach to optimal control of high performance buildings and presents algorithms for both distributed system identification and distributed model predictive control (DMPC). For the system identification, each thermal zone is divided into sub-systems, and a parameter set for each sub-system is first estimated individually, and then integrated into an inverse model for the whole thermal zone using the dual decomposition algorithm. For the DMPC, a distributed optimization algorithm inspired by the Proximal Jacobian Alternating Direction Method of Multipliers (PJ-ADMM) is deployed and multiple MPCs run iteratively while exchanging control input information until they converge. The developed algorithms are tested using field data from an occupied open-plan office space with a radiant floor system with distributed sensing, control, and data communication capabilities for localized comfort delivery. With this tractable approach, agents solve individual optimization problems in parallel, through information exchange and broadcasting, with a smaller scale of the input and constraints, facilitating optimal solutions with improved efficiency that are scalable to different building applications. Using a data-driven model and weather forecast, the DMPC controller is implemented to optimize the operation of an air-cooled chiller while providing different operative temperature bounds for each radiant floor loop. The radiant comfort delivery system with predictive control is capable of providing localized thermal environments while achieving significant energy savings. For the system and climate under consideration, results from the building operation during the cooling season, show 27% reduction in electricity consumption compared to baseline feedback control.

A Decentralized Multi-Agent Approach for Service Restoration in Uncertain Environment

This paper proposes a decentralized multiagent system (MAS) approach to solve the service restoration problem considering the uncertainty of load demand and renewable distributed generators (RDGs). Service restoration is formulated as a multi-objective optimization problem and solved by implementing controlled DG islanding using the proposed MAS approach. First, the uncertainty of load demand and RDG generation is forecast by generating scenarios using Monte Carlo simulations. Next, the expected nodes to be restored in an island are determined using a heuristic rule-based technique. Finally, the maximum likelihood of the expected island ranges to be restored are estimated using the maximum likelihood estimation method to assist the utility in decision making. Extensive case studies are conducted on 38 bus and 119 bus distribution system to show the efficacy of the proposed restoration strategy. The use of electric vehicles and battery energy storage as flexible sources of energy to alleviate the uncertainties in the system is also highlighted.

Evaluation of a Multi-Agent System approach to airline disruption management

Each day, airlines face disturbances that disrupt their carefully planned operations. Events like adverse weather conditions, sick crew members, or damaged aircraft often result in delays in the airline's schedule. An airline recovers from such disruptions through the role played by its Airline Operations Control (AOC). A Multi-Agent System (MAS) approach to airline disruption management was recently proposed under the acronym MASDIMA (Multi-Agent System for Disruption Management in AOC). The purpose of this paper is to evaluate this MAS supported AOC approach on its performance and its practical introduction. This is done using a scenario-based analysis to compare the MAS supported policy to human-team based AOC policies. A task-based analysis identifies how well AOC is able to cover a set of tasks using the MAS supported policy. The scenario-based analysis shows that the MAS supported AOC is able to find the optimal solution, and to do this significantly faster. The task-based analysis identified two main challenges for implementing the MAS supported AOC policy: i) to overcome the loss of experience that is caused by significantly automating humans roles in AOC, and ii) to reduce the workload for people that remain in AOC after its introduction. The paper concludes that implementing the MAS supported AOC policy leads to both better and faster resolutions, though the replacement of human roles also poses novel challenges that remain to be resolved: a potential increase in workload for the remaining human role and loss of experience in handling exceptional situations.

Optimal location of PEVCSs using MAS and ER approach

The location of public electric vehicle charging stations (PEVCSs) has a great influence on the operational efficiency of charging stations, charging behaviours of EVs and the power quality of grids. To optimise the PEVCS locations for plug-in electric taxis (PETs), this study proposes to utilise the multi-agent system (MAS) and evidential reasoning (ER) approach. First, an MAS simulation framework for PET operation is proposed to dynamically simulate the PETs' daily operation and estimate the charging demands of PETs, where a variety of agents are built to simulate not only the operation related players but also the operational environments. To accelerate the convergence rate and provide better operational strategies for PETs, a multi-step $Q\lpar \lambda \rpar $Q(λ) learning is developed to make decisions for PET agents whether to find passengers or to charge under various situations. Moreover, a multi-objective model for optimising the location of PEVCSs is developed considering the benefits of PETs and the power grid. Finally, an ER approach is applied to determine the final optimal siting considering the uncertainties of the assessor's cognition. Simulation results have demonstrated that the proposed MAS simulation framework and ER approach can effectively optimise the PEVCS locations.

Outlining a Model of an Intelligent Decision Support System Based on Multi Agents

Performance optimization has become a necessity for the survival of enterprises as emerging technologies continue to impact them. To achieve this goal, decision making, a complex process which depends on big data and human issues, must be effective. As enterprises are being subjected to a multi-faceted pressure, they must ensure the optimization of their performance. This article investigates an intelligent decision support system (IDSS) based on multi agent systems (MAS). Our contribution consists in developing an intelligent model with an IDSS MAS approach that can detect and evaluate changes in both the external environment and the enterprise itself. This model is an adequate management tool for optimal and sustainable performance and offers real-time analytical, prospecting and optimization methods.

Bridging the Gap between ABM and MAS: A Disaster-Rescue Simulation Using Jason and NetLogo

An agent is an autonomous computer system situated in an environment to fulfill a design objective. Multi-Agent Systems aim to solve problems in a flexible and robust way by assembling sets of agents interacting in cooperative or competitive ways for the sake of possibly common objectives. Multi-Agent Systems have been applied to several domains ranging from many industrial sectors, e-commerce, health and even entertainment. Agent-Based Modeling, a sort of Multi-Agent Systems, is a technique used to study complex systems in a wide range of domains. A natural or social system can be represented, modeled and explained through a simulation based on agents and interactions. Such a simulation can comprise a variety of agent architectures like reactive and cognitive agents. Despite cognitive agents being highly relevant to simulate social systems due their capability of modelling aspects of human behaviour ranging from individuals to crowds, they still have not been applied extensively. A challenging and socially relevant domain are the Disaster-Rescue simulations that can benefit from using cognitive agents to develop a realistic simulation. In this paper, a Multi-Agent System applied to the Disaster-Rescue domain involving cognitive agents based on the Belief–Desire–Intention architecture is presented. The system aims to bridge the gap in combining Agent-Based Modelling and Multi-Agent Systems approaches by integrating two major platforms in the field of Agent-Based Modeling and Belief-Desire Intention multi-agent systems, namely, NetLogo and Jason.

Solving task allocation problem in multi Unmanned Aerial Vehicles systems using Swarm intelligence

The envisaged usage of multiple Unmanned Aerial Vehicles (UAVs) to perform cooperative tasks is a promising concept for future autonomous military systems. An important aspect to make this usage a reality is the solution of the task allocation problem in these cooperative systems. This paper addresses the problem of tasks allocation among agents representing UAVs, considering that the tasks are created by a central entity, in which the decision of which task will be performed by each agent is not decided by this central entity, but by the agents themselves. The assumption that tasks are created by a central entity is a reasonable one, given the way strategic planning is carried up in military operations. To enable the UAVs to have the ability to decide which tasks to perform, concepts from swarm intelligence and multi-agent system approach are used. Heuristic methods are commonly used to solve this problem, but they present drawbacks. For example, many tasks end up not begin performed even if the UAVs have enough resources to execute them. To cope with this problem, this paper proposes three algorithm variants that complement each other to form a new method aiming to increase the amount of performed tasks, so that a better task allocation is achieved. Through experiments in a simulated environment, the proposed method was evaluated, yielding enhanced results for the addressed problem compared to existing methods reported in the literature.

A Recommendation System for Cloud Services Selection Based on Intelligent Agents

Objectives: To provide a recommendation system for cloud services selection based on intelligent agents. Methods/ Statistical Analysis: There have been many assortments of research, frameworks, and systems that discussed in many kinds of literature for selection of most advantageous service to fulfill the requirements of consumers. QoS parameters in addition to cloud service related QoS parameters have been used, but an agent-based cloud computing system has been introduced now that facilitate the CSS for better usage and service for the consumer. In this study, we proposed a service selector system on computer trust merit of the cloud purveyor. In previous studies, the authors had used the QoS model to solve the problem of cloud service vendor selection in multidimensional technique but this was not practically approachable. But we implement the multi-agent system (MAS) approach where one agent is liable to intermingle with the client for unambiguous service. MAS have very supple and self-directed nature, due to this quality MAS is the very authentic approach for users. Findings: In this proposal a selection and recommendation methodology implemented using multi-agents paradigm, has been proposed that recommends the most aspirant service from similar grouped services. The experimental output confirms that the proposed methodology can effectively select an optimal required service for end users. Cloud computing system with the help of multi-agents offer better agent-based intelligent cloud solutions for complex computational tasks. Application/Improvements: Multi-agents can be employed as key components for the selection and recommendation of intelligent cloud applications, making cloud infrastructure more autonomous, adaptive, and flexible in resources management, services provisioning and in running large-scale applications. Keywords: Cloud Service Selection, Intelligent Agents, MAS

ICR: information, cluster and route agent based method for efficient routing in VANET

Vehicular Ad-Hoc Network (VANET) is a variety of mobile ad-hoc networks (MANET) that differs from the fact that VANETS communicates between vehicle-to-vehicle and vehicle-to-roadside communication network. VANETs have the possibility to integrate with WiFi, Bluetooth and other connectivity protocols which makes it a new standard. The desired outcome expected from VANET is to communicate between nodes in any environment irrespective of traffic density and vehicle locations. Since vehicular communication is a part of constantly changing environment and it must also operatein urban and rural areas. Taking in mind the large number of nodes that are actually participating in these networks and also the property of high mobility between them, it has resulted in many debates about a feasible routing protocol. This paper introduces a multi-agent system approach to solve the problems faced by vehicular communications since it comprises of more than one agent solve the problem of routing, the resulting protocol gives higher efficiency and better performance on packet delivery and end-to-end packet delay.

A characterization of types of support between structured arguments and their relationship with support in abstract argumentation

Argumentation is an important approach in artificial intelligence and multiagent systems, providing a basis for single agents to make rational decisions, and for groups of agents to reach agreements, as well as a mechanism to underpin a wide range of agent interactions. In such work, a crucial role is played by the notion of attack between arguments, and the notion of attack is well-studied. There is, for example, a range of different approaches to identifying which of a set of arguments should be accepted given the attacks between them. Less well studied is the notion of support between arguments, yet the idea that one argument may support another is very intuitive and seems particularly relevant in the area of decision-making where decision options may have multiple arguments for and against them. In the last decade, the study of support in argumentation has regained attention among researchers, but most approaches address support in the context of abstract argumentation where the elements from which arguments are composed are ignored. In contrast, this paper studies the notion of support between arguments in the context of structured argumentation systems where the elements from which arguments are composed play a crucial role. Different forms of support are presented, each of which takes into account the structure of arguments; and the relationships between these forms of support are studied. Then, the paper investigates whether there is a correspondence between the structured and abstract forms of support, and determines whether the abstract formalisms may be instantiated using concrete forms of support in terms of structured arguments. The conclusion is that support in structured argumentation does not mesh well with support in abstract argumentation, and this suggests that more work is required to develop forms of support in abstract argumentation that model what happens in structured argumentation.