Multi-agent System Technology Research Articles

The Role of Multi-Agents in Digital Twin Implementation: Short Survey

In recent years, Digital Twin (DT) technology has emerged as a significant technological advancement. A digital twin is a digital representation of a physical asset that mirrors its data model, behaviour, and interactions with other physical assets. Digital Twin aims at achieving adaptability, seamless data integration, modelling, simulation, automation, and real-time data management. The primary goal of this article is to explore the role of agents in DT implementations, seeking to understand their predominant usage scenarios and purposes. From our perspective, agents serving as intelligent entities play a role in realising the features of DTs. This article also discusses the gaps in DT, highlights future directions, and analyses various technologies integrated with multi-agent systems technologies in DT implementations. Finally, the article briefly discusses an overview of an architecture to implement a DT for smart agriculture with multi-agents.

A Survey of Multi-Agent Systems for Smartgrids

This paper provides a survey of the literature on the application of Multi-agent Systems (MAS) technology for Smartgrids. Smartgrids represent the next generation electric network, as communities are developing self-sufficient and environmentally friendly energy production. As a cyber-physical system, the development of the vision of Smartgrids requires the resolution of major technical problems; this has fed over a decade of research. Due to the stochastic, intermittent nature of renewable energy resources and the heterogeneity of the agents involved in a Smartgrid, demand and supply management, energy trade and control of grid elements constitute great challenges for stable operation. In addition, in order to offer resilience against faults and attacks, Smartgrids should also have restoration, self-recovery and security capabilities. Multi-agent systems (MAS) technology has been a popular approach to deal with these challenges in Smartgrids, due to their ability to support reasoning in a distributed context. This survey reviews the literature concerning the use of MAS models in each of the relevant research areas related to Smartgrids. The survey explores how researchers have utilized agent-based tools and methods to solve the main problems of Smartgrids. The survey also discusses the challenges in the advancement of Smartgrid technology and identifies the open problems for research from the view of multi-agent systems.

Demand Response Strategy Based on the Multi-Agent System and Multiple-Load Participation

In order to improve the utilization of user-side power resources in the distribution network and promote energy conservation, this paper designs a distributed system suitable for power demand response (DR), considering multi-agent system (MAS) technology and consistency algorithms. Due to the frequent changes in the power system structure caused by changes in the load of a large number of users, this paper proposes using cluster partitioning indicators as communication weights between agents, enabling agents to utilize the distribution network for collaborative optimization. In order to achieve the integration of multiple load-side power resources and improve the refinement level of demand-side management (DSM), two types of agents with load aggregator (LA) functions are provided, which adopt the demand response strategies of Time-of-Use (TOU) or Direct Load Control (DLC) and model the uncertainty of individual device states using Monte Carlo method, so that the two typical flexible loads can achieve the target load-reduction requirements under the MAS framework. The research results demonstrate that this method achieves complementary advantages of the two types of loads participating in DR on a time scale, reducing the costs of power companies and saving customers’ electricity bills while peak shaving.

Deep Luenberger observer-based consistency tracking for nonlinear heterogeneous multi-agent systems with uncertain drift dynamics

In recent years, multi-agent systems (MASs) technology, represented by swarms of unmanned aerial vehicles (UAVs), has been continuously developed and become a hot topic in academic research. Combining the theory of deep learning (DL) and Luenberger observer, this paper puts forward the tracking control problem for the nonlinear heterogeneous MASs with uncertain drift dynamics. Concretely, a novel class of deep Luenberger observer (DLO) is constructed for state estimation and a novel deep robust controller (DRC) is designed based on the proposed DLOs. Finally, a numerical simulation demonstrates that the proposed methodology is valid, more general and performs better compared to traditional robust control methods.

A blockchain integration to support failures prediction from log files in multi-agent systems technology

Computer system failures can cause significant financial and reputational damage, making it critical to detect and prevent them before they occur. In this article, we propose a novel approach for predicting system failures based on log file analysis, called MABFailPred. Our approach leverages a Blockchain-based Multi-Agent architecture to analyze execution traces and detect early warning signals for system failure prediction during execution. Moreover, we introduce a new method for extracting log keys called HCLPars. The MABFailPred approach comprises four agents that work together to gather log keys, categorize data, develop a failure model, and make predictions. The use of blockchain ensures that agent and administrator predictions are synchronized, and agent collaboration is coordinated. We validate our approach by applying it to a real-world distributed system and accurately predicting problems before they occur. Our proposed approach represents a significant advancement in the field of system failure prediction, with the potential to enhance the reliability and security of computer systems. By employing a machine learning algorithm, our approach can predict anomalies in real-time and places a strong emphasis on the continuous monitoring of system behavior. The paper includes a validation of the approach using the Hadoop Distributed File System (HDFS) log dataset. According to our findings, the proposed approach achieves superior performance compared to other methods on the same dataset, with a precision of 0.998. This result establishes a new state-of-the-art performance level for the dataset.

Exploring agent-based chatbots: a systematic literature review

In the last decade, conversational agents have been developed and adopted in several application domains, including education, healthcare, finance, and tourism. Nevertheless, chatbots still need to address several limitations and challenges, especially regarding personalization, limited knowledge-sharing capabilities, multi-domain campaign support, real-time monitoring, or integration of chatbot communities. To cope with these limitations, many approaches based on multi-agent systems models and technologies have been proposed in the literature, opening new research directions in this context. To better understand the current panorama of the different chatbot technology solutions employing agent-based methods, this Systematic Literature Review investigates the different application domains, end-users, requirements, objectives, technology readiness levels, designs, strengths, limitations, and future challenges of the solutions found in this scope. The results of this review are intended to provide researchers, software engineers, and innovators with a complete overview of the current state of the art and a discussion of the open challenges.

A Genetic Programming-based Framework for Semi-automated Multi-agent Systems Engineering

With the rise of new technologies, such as Edge computing, Internet of Things, Smart Cities, and Smart Grids, there is a growing need for multi-agent systems (MAS) approaches. Designing multi-agent systems is challenging, and doing this in an automated way is even more so. To address this, we propose a new framework, Evolved Gossip Contracts (EGC). It builds on Gossip Contracts (GC), a decentralised cooperation protocol that is used as the communication mechanism to facilitate self-organisation in a cooperative MAS. GC has several methods that are implemented uniquely, depending on the goal the MAS aims to achieve. The EGC framework uses evolutionary computing to search for the best implementation of these methods. To evaluate EGC, it was used to solve a classical NP-hard optimisation problem, the Bin Packing Problem (BPP). The experimental results show that EGC successfully discovered a decentralised strategy to solve the BPP, which is better than two classical heuristics on test cases similar to those on which it was trained; the improvement is statistically significant. EGC is the first framework that leverages evolutionary computing to semi-automate the discovery of a communication protocol for a MAS that has been shown to be effective at solving an NP-hard problem.

Forecasting methods of intelligent systems technical condition analysis

Modern information processing and control systems reached the level that makes it possible to use detailed information on device and human nervous system functioning. Using a cognitive psychological approach in intelligent systems development, allowed them to imitate human nervous system functions. The development of increasingly powerful intelligent information and control systems with learning and self-learning, including information and measuring systems, is expected as a result.
 They will have enhanced cognitive capabilities due to the stimulation of cognitive functions and processes responsible for perception, learning, thinking, and consciousness in the human nervous system.
 Development of this field allows to develop intelligent systems with thinking and behaviour analysis elements. Adding some creative possibilities, for example, related to automatic hypotheses and models creation and self-learning for new task solving, allows to improve the efficiency of intelligent systems.
 Due to this new approaches to the artificial brain and the artificial nervous system of robots development, which relate not only to artificial intelligence but also to its development in the form of an artificial mind.
 Thus, the main scientific and development task for models, methods, methodics, and algorithms for intelligent systems technical condition forecasting based on soft computing is important and relevant for science and practice.
 Intelligent technologies allowing to develop useful intelligent systems are continuously being improved. Currently, quite powerful tools for implementing the technology of expert systems, fuzzy logic, neural network systems, and multi-agent systems technology are used. They are rapidly improved by adding software packages and hardware tools.
 New technologies are being developed in the so-called neuromorphic systems field that models some brain structures and in the parallel computing and quantum computers field. These technologies aim to raise significantly the intelligence level of systems in the future.

CONCEPTUAL MODEL FOR SCHEDULING AND CONTROL OF PRODUCTION AND LOGISTICS OPERATIONS USING MULTI-AGENT ROBOTIC SYSTEMS AND BLOCKCHAIN

The work proposes a conceptual model called MASBLOCK for scheduling and control of production and logistics operations, the study incorporates multi-agent robotic systems and blockchain technologies applied to industry. The problem identified in the research is the lack of coordination between fixed and mobile robots to develop activities and fulfill tasks in work areas, coupled with the lack or non-existence of secure data management. For this purpose, 22 scientific articles related to the subject have been considered considering three criteria (L), (Q) and (L-Q). A methodology proposed in a traditional model has been analyzed, which has served as a basis to define 5 steps for the creation of the new model, multi-agent system technologies have been incorporated for the coordination of robots and blockchain to perform secure data recording, decentralization and verifiable pose. Thus, the MASBLOCK model has been proposed, which shows an industrial environment where inputs, technologies, fixed and mobile robots interact; which perform multiple tasks, until reaching a validation point that allows to continue with the flow of activities until ending with an output, benefiting the interaction, self-programming and self-regulation of robots and all agents involved in productive and logistic operations, and data security in information management. Keywords: Conceptual model, multi-agent robotic systems, blockchain, industry.

Dynamic Digital Twin and Online Scheduling for Contact Window Resources in Satellite Network

The contact window scheduling technology supports various space mission requirements of the satellite information network. The continuous emergence of new space missions challenges the scarce satellite contact window scheduling. In this paper, We propose a dynamically updated micro-cloud structure based on digital twin and multi-agent system technology. Then, we build an on-satellite autonomous scheduling model based on the micro-cloud structure and design an efficient solution algorithm to solve the maximum revenue problem of inefficient task scheduling caused by the dynamic change of task priority and satellite position over time. Simulation experiments show that the scheme proposed in this paper can significantly improve task scheduling revenue and resource utilization, and have specific enlightening significance for the innovation of satellite task scheduling methods in the future.

Scalable and Cooperative Deep Reinforcement Learning Approaches for Multi-UAV Systems: A Systematic Review

In recent years, the use of multiple unmanned aerial vehicles (UAVs) in various applications has progressively increased thanks to advancements in multi-agent system technology, which enables the accomplishment of complex tasks that require cooperative and coordinated abilities. In this article, multi-UAV applications are grouped into five classes based on their primary task: coverage, adversarial search and game, computational offloading, communication, and target-driven navigation. By employing a systematic review approach, we select the most significant works that use deep reinforcement learning (DRL) techniques for cooperative and scalable multi-UAV systems and discuss their features using extensive and constructive critical reasoning. Finally, we present the most likely and promising research directions by highlighting the limitations of the currently held assumptions and the constraints when dealing with collaborative DRL-based multi-UAV systems. The suggested areas of research can enhance the transfer of knowledge from simulations to real-world environments and can increase the responsiveness and safety of UAV systems.

Flexible Agent Architecture: Mixing Reactive and Deliberative Behaviors in SPADE

Over the years, multi-agent systems (MAS) technologies have shown their usefulness in creating distributed applications focused on autonomous intelligent processes. For this purpose, many frameworks for supporting multi-agent systems have been developed, normally oriented towards a particular type of agent architecture (e.g., reactive or deliberative agents). It is common, for example, for a multi-agent platform supporting the BDI (Belief, Desire, Intention) model to provide this agent model exclusively. In most of the existing agent platforms, it is possible to develop either behavior-based agents or deliberative agents based on the BDI cycle, but not both. In this sense, there is a clear lack of flexibility when agents need to perform part of their decision-making process according to the BDI paradigm and, in parallel, require some other behaviors that do not need such a deliberation process. In this context, this paper proposes the introduction of an agent architecture called Flexible Agent Architecture (FAA) that supports the development of multi-agent systems, where each agent can define its actions in terms of different computational models (BDI, procedural, neural networks, etc.) as behaviors, and combine these behaviors as necessary in order to achieve its goals. The FAA architecture has been integrated into a real agent platform, SPADE, thus extending its original capabilities in order to develop applications featuring reactive, deliberative, and hybrid agents. The integration has also adapted the existing facilities of SPADE to all types of behaviors inside agents, for example, the coordination of agents by using a presence notification mechanism, which is a unique feature of SPADE. The resulting SPADE middleware has been used to implement a case study in a simulated robotics scenario, also shown in the paper.

Adapted Speed System in a Road Bend Situation in VANET Environment

Today, road safety remains a serious concern for governments around the world. In fact, approximately 1.35 million people die and 2–50 million are injured on public roads worldwide each year. Straight bends in road traffic are the main cause of many road accidents, and excessive and inappropriate speed in this very critical area can cause drivers to lose their vehicle stability. For these reasons, new solutions must be considered to stop this disaster and save lives. Therefore, it is necessary to study this topic very carefully and use new technologies such as Vehicle Ad Hoc Networks (VANET), Internet of Things (IoT), Multi-Agent Systems (MAS) and Embedded Systems to create a new system to serve the purpose. Therefore, the efficient and intelligent operation of the VANET network can avoid such problems as it provides drivers with the necessary real-time traffic data. Thus, drivers are able to drive their vehicles under correct and realistic conditions. In this document, we propose a speed adaptation scheme for winding road situations. Our proposed scheme is based on MAS technology, the main goal of which is to provide drivers with the information they need to calculate the speed limit they must not exceed in order to maintain balance in dangerous areas, especially in curves. The proposed scheme provides flexibility, adaptability, and maintainability for traffic information, taking into account the state of infrastructure and metering conditions of the road, as well as the characteristics and behavior of vehicles.

Rapid Deployment Scheme for MAS-based Applications within Industry 4.0 Framework

In the past decades, the trend of Industry 4.0 (I4.0) has been sweeping the world, which implies a huge revolution for the social industrial production patterns. Multiagent system (MAS) technology could provide more flexible and customized manufacturing under the turbulent demand. However, the construction and commissioning of the MAS-based control implementations could be hard tasks for developers.To tackle this problem, a rapid deployment scheme for MAS-based control implementations has been proposed in this paper, which includes three layers: the topology of MAS, the unique control strategy of each entity, and the bottom control system. The communication protocol inside the architecture has been predefined and the interfaces have been reserved for further definition. The proposed deployment scheme is verified through a practical instance of cooperative speeding control. It is believed that the scheme could provide the deployment with high efficiency, versatility, and convenience, which would benefit the industrial manufacturing within Industry 4.0 framework in the near future.

Past, Present and Future Trends in Multi-Agent System Technology

Multi-Agent System (MAS) technology is one of the cores and promising areas in the field of Artificial Intelligence (AI) as well as in the stream of Computer Science. The technology is comprised of multiple decision-making agents that exist in an environment to achieve common or conflicting goals. Multi-Agent System technology has a rapid growth and evolution due to its marvelous features such as flexibility and intelligence that are very useful when solving complex distributed problems. This paper focuses on the history and evolution of MAS technology, present applications, and future trends by addressing more detailed explanations about the foundations or key principles of Multi-Agent System technology such as agents, agent taxonomy, agent communication approaches, MAS development frameworks as well as the history of agent technology. The goal of this paper is to provide broad and comprehensive knowledge about Multi-Agents System technology.

Optimization and Performance Analysis of Fractional Order PID Controller for DC Motor Speed Control

Multi-Agent System (MAS) technology is one of the cores and promising areas in the field of Artificial Intelligence (AI) as well as in the stream of Computer Science. The technology is comprised of multiple decision-making agents that exist in an environment to achieve common or conflicting goals. Multi-Agent System technology has a rapid growth and evolution due to its marvelous features such as flexibility and intelligence that are very useful when solving complex distributed problems. This paper focuses on the history and evolution of MAS technology, present applications, and future trends by addressing more detailed explanations about the foundations or key principles of Multi-Agent System technology such as agents, agent taxonomy, agent communication approaches, MAS development frameworks as well as the history of agent technology. The goal of this paper is to provide broad and comprehensive knowledge about Multi-Agents System technology.

Application Research of Computer Communication Technology in the Development of Artificial Intelligence

With the advent of the 5G communication era, people's life and work are increasingly dependent on computer network information technology. The development and application of artificial intelligence (AI) technology has laid a solid foundation for the security of computer network. One technology plays an indispensable role in the development of this field, that is, computer communication Technology (CCT). Its core function is to support data, collect, analyze and process a large amount of information, and output scientific and reasonable calculation results. As one of the frontier directions, the application range of multi-agent system is more and more extensive. Compared with traditional software systems, multi-agent systems can provide more effective means to solve complex scientific and engineering problems. This paper focuses on the application of the trusted alliance technology of multi-agent system in the context of the Internet of Things, defines the parameters and conditions of some trusted alliances of the intelligent terminal of the Internet of Things, and preliminarily discusses the negotiation strategy of the process of strengthening the alliance. The organic integration of AI technology and computer network technology is a new direction of the intelligent development exploration and research of network technology. This paper studies and analyzes the application of AI in computer network technology in the age of big data.

A smart palletising planning and control model in Logistics 4.0 framework

The paper describes a smart model for palletising as main intra-logistics task for product-on-pallet distribution, and its development in Logistics 4.0 framework aligned to Industry 4.0. The model is developed in holonic paradigm as a 2-layer Holonic Logistics Execution System (HLES) in semi-heterarchical topology. Scheduling of logistics activities and allocation to resources are optimised for global efficiency on compact time periods. The logistics model virtualises physical entities: resources, pallets and orders as holons implemented with digital twin software, and categories of task workloads: resource health monitoring, dispatching and tracking pallet orders, re-assigning jobs at resource failure, which grants reality-awareness and robustness. Global workload optimisation uses Constraint Programming as decision making technology with ILOG optimiser engine as situation-specific solver tool in SaaS cloud model, and delegate multi-agent system (MAS) technology for intelligence distribution. The optimised objective function is a combination of palletising cost weighted by robot speed limits and pallet storage cost in payable stocks. The main constructs are exemplified and validated on a real-life structure with multiple palletising resources in which programmable logic controllers (PLC) coordinate locally the parallel execution of order holons according to their globally optimised sequence.

Blockchain integrated multi-agent system for breast cancer diagnosis

<span>The integration of multi-agent system and blockchain technology can be beneficial to healthcare applications by providing intelligent data analysis with security. This paper presents an architecture that integrates multi-agent learning system and blockchain technology to support breast cancer diagnosis in a secured manner. The proposed system is based on a parallel hybrid fuzzy logic approach for supporting the prediction of breast cancer disease. The proposed system showed a classification accuracy of 96.49% in breast cancer diagnosis when testing with the Wisconsin Diagnostic Breast Cancer dataset. The blockchain is used to provide agent security in the proposed system to ensure that the only trusted and reputed agents are participated in the decision-making process.</span>

Agent-Based Intelligent Decision Support Systems: A Systematic Review

Decision-making complexity, in a distributed environment, is due to hard tasks that a system must resolve. This complexity makes researchers focus on looking for solutions to cope with distributed environment problems. Multiagent system (MAS) technology is one of several proposed solutions. This technology rose the challenge in decision-making applications. To date, no systematic review has been conducting, to the best of the authors’ knowledge, to give an overview of a multiagent-based decision-making system in various areas of science or technology. In this study, we review of 58 studies published from 2007 to 2019. The aim of this article is a critical analysis of recent approaches. We try to survey their impact on practice and research. The analysis of the extracted studies is based on three selection criteria that are defined in the paper. All included studies have analyzed from four different points of view: 1) theoretical view; 2) technical view; 3) agent view; and 4) application view. Moreover, we adopt the SWOT analysis to evaluate studied approaches. Multiagent technology is actually in the process of evolution and enhancement with the appearance of new trends in artificial intelligence, such as neural network and deep learning. The results of this review show suggestions for further research and practice.