Multi-agent System Techniques Research Articles

Discovering and evaluating organizational knowledge from textual data: Application to crisis management

Crisis management effectiveness relies mainly on the quality of the distributed human organization deployed for saving lives, limiting damage and reducing risks. Organizations set up in this context are not always predefined and static; they could evolve and new forms could emerge since actors, such as volunteers or NGO, could join dynamically to collaborate. To improve crisis resolution effectiveness, it is first important to understand, analyze and evaluate such dynamic organizations in order to adjust crisis management plans and ease coordination among actors. Giving a textual experience feedback from past crisis, the objective of this paper is to discover the organizational structure deployed in the considered crisis and then evaluate it according to a set of criteria. For that purpose, we combine in a coherent framework text and association rule mining for pattern discovery and annotation, and multi-agent system models and techniques for formally building and evaluating organizational structures. We present the OSminer algorithm that discovers association rules based on relevant textual patterns and then builds an organizational structure including three main relations between actors: power, control and coordination. A real-life case study, a flood crisis hitting the south west of France, serves as a basis for testing/experimenting our solution. The organizational structure, discovered in this case study, has 24 actors. Its evaluation indicates its efficiency, but shows that it is neither robust nor flexible. Our findings highlight the potential of our approach to discover and evaluate organizational structures from a text recording interactions between stakeholders in a crisis context.

Multi-agent system implementation in demand response: A literature review and bibliometric evaluation

<abstract> <p>This research provides a comprehensive literature overview and bibliometric evaluation of multi-agent system (MAS) implementation in energy demand response (DR) to identify gaps. The review encompasses 39 relevant papers from searches in three academic databases, focusing on studies published from 2012 to the middle of 2023. The review includes MAS frameworks, optimization algorithms, communication protocols, market structures and evaluation methodologies. Bibliometric analysis of 587 documents from the search on the Scopus database identified prolific authors, influential articles and collaborative networks within the field. The findings reveal growing research interest in implementing an MAS for DR, focusing on integrating intelligent agents into electricity grids to enable effective load management and enhance grid stability. Additionally, the review outlines potential research directions, including exploring advanced MAS techniques, interoperability challenges, policy implications and the integration of renewable energy sources.</p> </abstract>

Large-scale collaborative vehicle routing

AbstractCarriers can remarkably reduce transportation costs and emissions when they collaborate, for example through a platform. Such gains, however, have only been investigated for relatively small problem instances with low numbers of carriers. We develop auction-based methods for large-scale dynamic collaborative pickup and delivery problems, combining techniques of multi-agent systems and combinatorial auctions. We evaluate our approach in terms of both solution quality and possibilities of strategic behaviour using a real-world data set of over 12,000 orders. Hence, this study is (to the best of our knowledge) the first to assess the benefits of large-scale carrier cooperation and to propose an approach for it. First, we use iterative single-order auctions to investigate possible collaboration gains for increasing numbers of carriers. Our results show that travel costs can be reduced by up to 77% when 1000 carriers collaborate, largely increasing the gains that were previously observed in smaller-scale collaboration. We also ensure that individual rationality is guaranteed in each auction. Next, we compare this approach of multiple local auctions with an established central combinatorial auction mechanism and observe that the proposed approach performs better on large-scale instances. Furthermore, to improve solution quality, we integrate the two approaches by allowing small bundle auctions in the multi-agent system. We analyze the circumstances under which bundling is beneficial in a large-scale decentralized system and demonstrate that travel cost gains of up to 13% can be obtained for 1000 carriers. Finally, we investigate whether the system is vulnerable to cheating: we show that misrepresentation of true values by individual participants sometimes can benefit them at the cost of the collective. Although such strategic behaviour is not straightforward, we also discuss different means to prevent it.

A Machine Learning and Multi-Agent Model to Automate Big Data Analytics in Smart Cities

The objective of this paper is to present an architecture to improve the process of automating big data analytics using a multi-agent system and machine learning techniques, to support the processing of real time big data streams and to enhance the process of decision-making for urban planning and management. With the rapidly evolving information technologies, and their utilization in many areas such as smart cities, social networks, urban management and planning, massive data streams are generated and need an efficient approach to deal with. The proposition in this paper adopts the concept of smart data which focuses on the value aspect from big data. The proposed architecture is composed of three layers: data acquisition and storage, data management and processing and the service layer, based on a multi-agent system to automate the big data analytics; the proposed model describe the functionalities of the system and the collaboration between agents, these autonomous entities receive data streams in real time, they perform operations of preprocessing, big data analytics and storage into a Hadoop cluster. The techniques of machine learning are also used to enhance the process of decision making, such the use of classification algorithms to predict habitat type based on the characteristics of a population to help making efficient urban planning decisions. The proposed system can serve as a platform to support data management and to conduct effective decision-making in smart cities.

Improving self-consumption of on-site PV generation through deploying flexibility in building thermal mass

As PV is considered prospective for decarbonizing the building sector, the self-consumption of on-site PV generation, which is susceptible to the temporal mismatch between solar radiation and energy demand, greatly affects the overall performance of improving building autonomy. As an important way to lessen the dependence of the decentralized PV energy system on the grid, internal flexibility from buildings is receiving increasing attention. This research sought to contribute to our understanding of the flexibility potential of Building Thermal Mass (BTM). In this aim, the load-shifting potential of BTM and the impacts on the self-consumption of rooftop PV generation were evaluated in a single-family residential building. To ensure a satisfying accuracy, this research proposed a novel framework that integrates multi-agent system and resistance-capacitance modelling techniques. The proposed methods represent the thermal network by means of circuit analogy and perform indoor thermal control based on stochastic occupant behaviours and appliance usage. The proposed BTM modelling framework is of great potential in flexibility estimation of BTM and could be used to assist the demand-side management.

A Crowdsourcing Approach for Sustainable Last Mile Delivery

Sustainable transportation is one of the major concerns in cities. This concern involves all type of movements motivated by different goals (mobility of citizens, transportation of goods and parcels, etc.). The main goal of this work is to provide an intelligent approach for Sustainable Last Mile Delivery, by reducing (or even deleting) the need of dedicated logistic moves (by cars, and/or trucks). The method attempts to reduce the number of movements originated by the parcels delivery by taking advantage of the citizens’ movements. In this way our proposal follows a crowdsourcing approach, in which the citizens that moves in the city, because of their own needs, become temporal deliverers. The technology behind our approach relays on Multi-agent System techniques and complex network-based algorithms for optimizing sustainable delivery routes. These artificial intelligent approaches help to reduce the complexity of the scenario providing an efficient way to integrate the citizens’ routes that can be executed using the different transportation means and networks available in the city (public system, private transportation, eco-vehicles sharing systems, etc.). A complex network-based algorithm is used for computing and proposing an optimized Sustainable Last Mile Delivery route to the crowd. Moreover, the executed tests show the feasibility of the proposed solution, together with a high reduction of the CO 2 emission coming from the delivery trucks that, in the case studies, are no longer needed for delivery.

Modelling and optimal management of distributed microgrid using multi-agent systems

Electrical systems composed of numerous and usually multifaceted components which are difficult to operate and control by efficient ways at the centralized level having problems such as adaptability, mobility, and fault tolerance. Thus, in recent evaluation, renewable energy resources (RERs) have been considered as clean and cost-effective sources for the generation of electrical power at the distributed level. In this context, the awareness of the microgrids (MGs), as sub level technologies of the central grid, booms particularly because of the precise amenities that they can deliver. Therefore, a novel multi-agent system (MAS) based model and the optimal management of a MG integrated with RERs at distributed level is proposed in this paper. Power generation at distributed level comprises of numerous disseminated energy resources having critical and non-critical loads. A controlled architecture of a MG based on the MAS technique is employed for the finest operations of the MG management and power delivery and also offers intelligence to the MG at distributed level. For validation of the proposed model, the power generation within the MG was evaluated by simulation under the capabilities of RERs power production, critical and non-critical load demands, and several grid instabilities. The simulation results prove that the proposed model for the MG management based on MAS technique at distributed level offers robustness and high-performance supervision and control than centralized arrangements.

Evaluation of Multi-agent Architecture for Structural Damage Detection and Location

In this paper the results of using a Multi-agent system (MAS) for Structural Health Monitoring (SHM) are detailed. A study between different MAS architectures reported in literature is presented in order to select and adapt the most adequate one for SHM tasks. Requirements are established according to recent solutions, where main parameters are type and number of sensors and communication protocols, among others. MAS technique uses several intelligent agents, that are algorithms able to act in a reactive or active way. Their action depends on surrounding environment or collected data. These agents can work in a decentralized way, searching the fulfillment of an individual goal or they can work with another system to achieve a common goal. Decision is based on their internal state (beliefs, goals and commitments). MAS’ effectiveness depends on the interconnection between the agents. Type of agents is defined according to its communication method and protocol, common and individual goals, among others. Decentralization and versatility are two important characteristics of MAS technique useful to solve SHM problem. This is one of the main motivations to consider this technique to be a good approach for the studied problem. A benchmark numerical model, which consists of a metallic framework, was used to validate and demonstrate the feasibility of the selected architecture for SHM

Bargaining agents based system for automatic classification of potential allergens in recipes

The automatic recipe recommendation which take into account the dietary restrictions of users (such as allergies or intolerances) is a complex and open problem. Some of the limitations of the problem is the lack of food databases correctly labeled with its potential allergens and non-unification of this information by companies in the food sector. In the absence of an appropriate solution, people affected by food restrictions cannot use recommender systems, because this recommend them inappropriate recipes. In order to resolve this situation, in this article we propose a solution based on a collaborative multi-agent system, using negotiation and machine learning techniques, is able to detect and label potential allergens in recipes. The proposed system is being employed in receteame.com, a recipe recommendation system which includes persuasive technologies, which are interactive technologies aimed at changing users’ attitudes or behaviors through persuasion and social influence, and social information to improve the recommendations.

FIoT: An agent-based framework for self-adaptive and self-organizing applications based on the Internet of Things

Billions of resources, such as cars, clothes, household appliances and even food are being connected to the Internet forming the Internet of Things (IoT). Subsets of these resources can work together to create new self-regulating IoT applications such as smart health, smart communities and smart homes. However, several challenging issues need to be addressed before this vision of applications based on IoT concepts becomes a reality. Because many IoT applications will be distributed over a large number of interacting devices, centralized control will not be possible and so open problems will need to be solved that relate to building locally operating self-organizing and self-adaptive systems. As an initial step in creating IoT applications with these features, this paper presents a Framework for IoT (FIoT). The approach is based on Multi-Agent Systems (MAS) and Machine Learning Techniques, such as neural networks and evolutionary algorithms. To illustrate the use of FIoT, the paper contains two different IoT applications: (i) Quantified Things and (ii) Smart traffic control. We show how flexible points of our framework are instantiated to generate these IoT application.

Control architecture and design method of reconfigurable manufacturing systems

This paper proposes a control architecture for reconfigurable manufacturing systems and its design method based on Petri nets (Input Output Place Transition and Production Flow Schema), Service-Oriented Architecture and Holonic and Multi-Agent System techniques, among other good practices. The control architecture integrates value-added activities, information and resources. The method considers the exchange of knowledge among heterogeneous business workflow of manufacturing subsystems in different geographical locations, and allows modeling process, product, machine and device control. An example demonstrates advantages of the resulting control system.

Intelligent Control System for Microgrids Using Multiagent System

This paper presents an intelligent control of a microgrid in both grid-connected and islanded modes using the multiagent system (MAS) technique. This intelligent control consists of three levels. The first level is based on local droop control, the second level compensates power balance between the supply and the demand optimally, and the third level is at the system level based on electricity market. An intelligent MAS was developed and implemented based on foundation for intelligent physical agents standards by representing each major autonomous component in the microgrid as an intelligent software agent. The agents interact with each other for making their own decisions locally and optimally. The coordination among the agents ensures power quality, voltage, and frequency of the microgrid by determining the set points that optimize the overall operation of the microgrid. The proposed control architecture and strategies for the real-time control of microgrids were analyzed in detail, and tested under various load conditions and different network configurations. The outcomes of the studies demonstrate the feasibility of the proposed control and strategies, as well as the capability of the MAS technique for the operation of microgrids.

Modeling of reconfigurable distributed manufacturing control systems

This paper presents a method to design a reconfigurable distributed manufacturing control systems which integrates heterogeneous technologies of facilities that are geographically distributed. Due to the heterogeneity of the environment, the method explores concepts of different techniques and takes the best practices from each one. Mechanisms for reconfiguration are proposed using holonic and multi-agent systems techniques. The service-oriented architecture concept is applied to define the interfaces for communication. A combined top-down and bottom- up approach is described using Petri net models. An application example demonstrates the characteristics and advantages of the proposed method, such as autonomy, reactivity, reuse models, interoperability and reconfiguration flexibility.

A Multi-Agent Control for Energy Management in PV/Wind/Fuel Cell/Battery Hybrid Power System

The usage of renewable energy systems increases worldwide due to extinction of conventional sources and also the absence of some serious environmental effects such as global warming, ozone layer depletion etc. These renewable power systems are not able to satisfy the load continuously due to seasonal availability of the resources. A Hybrid Power System (HPS) formed with renewable energy sources are a solution to provide power for stand-alone electrical loads. However, the energy management in HPS is quite complex as it relies on a central controller. This paper proposes a distributed Energy Management System (EMS) to control the energy flow in the PV/Wind/Fuel Cell/Battery HPS based on multi-agent system (MAS) technology. With this concept, a HPS is seen as a collection of different elements called agents, collaborates to reach a global coordination to satisfy the demand in the system. The Algorithm of the Multi-Agent System technique for HPS has been implemented using MATLAB/Simulink environment. The results show that the algorithm is effectively working for a HPS to provide power to the load and control power flow between various elements of the system.

Study for the Distributed Power Grid Faults Diagnose System Based on Mas

The setup structure for the power grid faults diagnose system is analysed, the Multi-Agent System technique is used to the system. The functional modular of the system is transformed into Multi-Agent System, which has the same function as the entity system. The modular of the system can be in reconfiguration state when trouble appears by using Agent technique. The system running mechanism is also given.

Study for Power Grid Fault Diagnosis System Based on Hierarchical Distributed MAS

The setup structure for the power grid faults diagnose system is analysed, the Multi-Agent System technique is used to the system. The functional modular of the system is transformed into Multi-Agent System, which has the same function as the entity system. The modular of the system can be in reconfiguration state when trouble appears by using Agent technique. The system running mechanism is also given.

RAEDSS: An integrated decision support system for regional agricultural economy in China

Recent advances in artificial intelligence, particularly in the field of multi-agent system theory and techniques, offer great promises in the development of decision support systems. This paper designs an agent-based regional agricultural economy decision support system (RAEDSS) to deal with complex decision problems. It introduces the architecture of the system, including interface agents, management agents, functional agents, model agents, information agents and knowledge agents and their interactions. Since dynamic analysis, evaluation, forecast, optimization and decision of regional agricultural economy are the central task of RAEDSS, this paper gives a detailed discussion on the decision processes and internal mechanisms in the system. Meanwhile, agent-based modeling is introduced to simulate and evaluate policy impact on rural development in different scenarios as an important part in RAEDSS. The simulation result shows that this agent-based agricultural development model is able to perform regeneration and is able to produce likely-to-occur projections of reality. The related issue such as building an agent based on the theory of classifier systems is also surveyed.

Maintenance Chain Integration Using Petri-Net Enabled Multiagent System Modeling and Implementation Approach

Engineering asset management (EAM) is a broad discipline and the EAM functions and processes are characterized by its distributed nature. However, engineering asset nowadays mostly relies on self-maintained experiential rule bases and periodic maintenance, which is lacking a collaborative engineering approach. This research proposes a collaborative environment integrated by a service center with domain expertise such as diagnosis, prognosis, and asset operations. The collaborative maintenance chain combines asset operation sites, service center (i.e., maintenance operation coordinator), system provider, first tier collaborators, and maintenance part suppliers. Meanwhile, to realize the automation of communication and negotiation among organizations, multiagent system (MAS) technique is applied to enhance the entire service level. During the MAS design processes, this research combines Prometheus MAS modeling approach with Petri-net modeling methodology and unified modeling language to visualize and rationalize the design processes of MAS. The major contributions of this research include developing a Petri-net enabled Prometheus MAS modeling methodology and constructing a collaborative agent-based maintenance chain framework for integrated EAM.

Security Framework of Cloud Data Storage Based on Multi Agent System Architecture: Semantic Literature Review

The purpose of this literature review is to provide the information about illustrating the usage of Multi-Agent System (MAS) techniques that can be beneficial in cloud computing platform to facilitate security of cloud data storage (CDS) among it. MAS are often distributed and agents have proactive and reactive features which are very useful for cloud data storage security (CDSS). The architecture of the system is formed from a set of agent’s communities. This paper of literature review described on the theoretical concept and approach of a security framework as well as a MAS architecture that could be implemented in cloud platform in order to facilitate security of CDS, on how the MAS technology could be utilized in a cloud platform for serving the security that is developed by using a collaborative environment of Java Agent DEvelopment (JADE). In order to facilitate the huge amount of security, our MAS architecture offered eleven security attributes generated from four main security policies of correctness, integrity, confidentially and availability of users’ data in the cloud. This paper of literature review also describes an approach that allows us to build a security cloud platform using MAS architecture and this architecture tends to use specialized autonomous agents for specific security services and allows agents to interact to facilitate security of CDS.

Design of an agent-based system for improving supply chain strategy

Supply chain managers and decision makers are facing a challenge to develop supply chains that are efficient and economical, with the ability to provide the organisation with added value by simultaneously enhancing the quality of customer service and reducing operation cost. Supply Chain Management has become a major vehicle to gain a competitive advantage in this ever-changing market. It can also make instant improvements to an enterprise's business strategies. Supply chain strategy is not simply derived from the business strategy. It can be the enabler of the business strategy. It promotes good responsiveness to customer demands by shortening the product life cycle throughout the supply pipeline. In this paper, an intelligent agent-based system, named Supply Chain Strategy Improvement System is proposed. Its aim is to provide support to decision-making in matters related to the supply chain strategy by utilising various artificial intelligence techniques, including Multi-agent System techniques, Case-based Reasoning and Online Analytical Processing.