Adaptive Multi-agent System Research Articles

Modeling biological memory network by an autonomous and adaptive multi-agent system

At the intersection of computation and cognitive science, graph theory is utilized as a formalized description of complex relationships description of complex relationships and structures, but traditional graph models are static, lack the dynamic and autonomous behaviors of biological neural networks, rely on algorithms with a global view. This study introduces a multi-agent system (MAS) model based on the graph theory, each agent equipped with adaptive learning and decision-making capabilities, thereby facilitating decentralized dynamic information memory, modeling and simulation of the brain’s memory process. This decentralized approach transforms memory storage into the management of MAS paths, with each agent utilizing localized information for the dynamic formation and modification of these paths, different path refers to different memory instance. The model’s unique memory algorithm avoids a global view, instead relying on neighborhood-based interactions to enhance resource utilization. Emulating neuron electrophysiology, each agent’s adaptive learning behavior is represented through a microcircuit centered around a variable resistor. Using principles of Ohm’s and Kirchhoff’s laws, we validated the model’s efficacy in memorizing and retrieving data through computer simulations. This approach offers a plausible neurobiological explanation for memory realization and validates the memory trace theory at a system level.

A Hybrid Optimization Algorithm for Efficient Virtual Machine Migration and Task Scheduling Using a Cloud-Based Adaptive Multi-Agent Deep Deterministic Policy Gradient Technique

This To achieve optimal system performance in the quickly developing field of cloud computing, efficient resource management—which includes accurate job scheduling and optimized Virtual Machine (VM) migration—is essential. The Adaptive Multi-Agent System with Deep Deterministic Policy Gradient (AMS-DDPG) Algorithm is used in this study to propose a cutting-edge hybrid optimization algorithm for effective virtual machine migration and task scheduling. An sophisticated combination of the War Strategy Optimization (WSO) and Rat Swarm Optimizer (RSO) algorithms, the Iterative Concept of War and Rat Swarm (ICWRS) algorithm is the foundation of this technique. Notably, ICWRS optimizes the system with an amazing 93% accuracy, especially for load balancing, job scheduling, and virtual machine migration. The VM migration and task scheduling flexibility and efficiency are greatly improved by the AMS-DDPG technology, which uses a powerful combination of deterministic policy gradient and deep reinforcement learning. By assuring the best possible resource allocation, the Adaptive Multi-Agent System method enhances decision-making even more. Performance in cloud-based virtualized systems is significantly enhanced by our hybrid method, which combines deep learning and multi-agent coordination. Extensive tests that include a detailed comparison with conventional techniques verify the effectiveness of the suggested strategy. As a consequence, our hybrid optimization approach is successful. The findings show significant improvements in system efficiency, shorter job completion times, and optimum resource utilization. Cloud-based systems have unrealized potential for synergistic optimization, as shown by the integration of ICWRS inside the AMS-DDPG framework. Enabling a high-performing and sustainable cloud computing infrastructure that can adapt to the changing needs of modern computing paradigms is made possible by this strategic resource allocation, which is attained via careful computational utilization.

Defining adaption measures for organisational multi-agent systems

Designing adaptive multi-agent Systems (MAS) is a challenging development effort. A key point of adaptive systems is that they provide alternative options for acting and designers have to weight the number and elaboration of these alternatives. Here, we concentrate on organisation-oriented MAS and show that organisational models provide suitable means for identifying key measures of this adaptivity. We derive measures both from the static description of the organisation as well as from the induced adaptation dynamics grounded on a Markovian analysis of the behaviour. These measures allow for a goal-directed planning of adaption.

Efficient Data as a Service in Fog Computing: An Adaptive Multi-Agent Based Approach

Data as a Service (DaaS) offers an effective provisioning model able to exploit the advantages of cloud computing in terms of accessibility and scalability when data providers need to make their data available to different data consumers. Nevertheless, in settings where data are generated at the edge and they need to be propagated (e.g., Industry 4.0, Smart Cities), DaaS model suffers of some limitations: data transfer from the edge to the cloud – and viceversa – could require a significant time and privacy issues could hamper the possibility to move the data. Goal of this paper is to propose a DaaS model based on the Fog Computing paradigm, which combines the advantages of both cloud and edge computing. The proposed solution implements an adaptive multi-agent system where each agent autonomously manages the placement of data in the most convenient location considering the quality of service requirements of the user that it is serving. To guarantee the collaboration of the agents without imposing a centralized control, a reinforcement learning algorithm will be enacted to balance between the local optimum for the single data consumers and the satisfaction of the global requirements of all consumers.

Resilience-by-design in Adaptive Multi-agent Traffic Control Systems

Connected and Autonomous Vehicles (CAVs) with their evolving data gathering capabilities will play a significant role in road safety and efficiency applications supported by Intelligent Transport Systems (ITSs), such as Traffic Signal Control (TSC) for urban traffic congestion management. However, their involvement will expand the space of security vulnerabilities and create larger threat vectors. In this article, we perform the first detailed security analysis and implementation of a new cyber-physical attack category carried out by the network of CAVs against Adaptive Multi-Agent Traffic Signal Control (AMATSC), namely, coordinated Sybil attacks, where vehicles with forged or fake identities try to alter the data collected by the AMATSC algorithms to sabotage their decisions. Consequently, a novel, game-theoretic mitigation approach at the application layer is proposed to minimize the impact of such sophisticated data corruption attacks. The devised minimax game model enables the AMATSC algorithm to generate optimal decisions under a suspected attack, improving its resilience. Extensive experimentation is performed on a traffic dataset provided by the city of Montréal under real-world intersection settings to evaluate the attack impact. Our results improved time loss on attacked intersections by approximately 48.9%. Substantial benefits can be gained from the mitigation, yielding more robust adaptive control of traffic across networked intersections.

Multi-Agent-Based Fault Location and Cyber-Attack Detection in Distribution System

Accurate fault location is challenging due to the distribution network’s various branches, complicated topology, and the increasing penetration of distributed energy resources (DERs). The diagnostics for power system faults are based on fault localization, isolation, and smart power restoration. Adaptive multi-agent systems (MAS) can improve the reliability, speed, selectivity, and robustness of power system protection. This paper proposes a MAS-based adaptive protection mechanism for fault location in smart grid applications. This study developed a novel distributed intelligent-based multi-agent prevention and mitigation technique for power systems against electrical faults and cyber-attacks. Simulation studies are performed on a platform constructed by interconnecting the power distribution system of Kenitra city developed in MATLAB/SIMULINK and the multi-agent system implemented in the JADE platform. The simulation results demonstrate the effectiveness of the proposed technique.

Decentralized optimal management of a large-scale EV fleet: Optimality and computational complexity comparison between an adaptive MAS and MILP

Increasing the penetration of variable and uncertain renewables and electric vehicles in power systems may give rise to problems (such as network congestion and commitment mismatches) if not controlled strategically. This demands control solutions in the form of energy management strategies for active distribution networks which would control the connected distributed energy resources and storage units in real-time to address the mentioned challenges. Centralized strategies may fail to serve this purpose for large-scale distribution networks due to their inherent shortcomings like vulnerability to single point of failures and large computing times. Unlike centralized approaches, decentralized control strategies show more potential. This paper presents one such solution, based on an adaptive multi-agent system, to control a large-scale distribution network in real-time. Its performance is compared with the results obtained with the corresponding centralized optimization problem, modeled as a mixed integer linear programming problem. Both the centralized version and the decentralized multi-agent version of the problem under consideration are presented and a case study is designed for the comparison. The comparison shows that the designed multi-agent system produces a near-optimal solution in real-time while the centralized optimization strategy struggles in terms of computational complexities for larger distribution networks.© 2017 Elsevier Inc. All rights reserved.

Multi-Agent Systems Based Adaptive Protection for Smart Distribution Network

The smart power grid has been developed and improved constantly to be able to incorporate protection, automation, communication, and advanced control methods. As a result, the smart power grid system protection is expected to be modernized and given the ability to handle the future complexity that emanates from the integration of Distributed Generations (DGs). An Adaptive Multi-Agent System (MAS) can enhance power system protection and make it more reliable, faster, selective, and robust. In this paper, a novel MAS-based adaptive protection technique that suits smart grid applications is proposed. The proposed protection technique consists of agents that communicate with each other and their environment. The agents used in the proposed technique are Short Circuit Current Calculation Agent (SCCA), Load Flow Calculation Agent (LFA), Setting Calculation Agent (SCA), Logic and Operating Agent (LOA), Coordination and Optimization Agent (COA), and Network Configuration Mapping Agent (NCMA). The proposed technique can adapt to the changing conditions in the smart grid. The DigSILENT PowerFactory software is used to verify the proposed technique using a real Distribution Network in the Antalya vicinity of Turkey. The achieved results show that the method can provide fast and selective protection for the smart grid with increased integration of DGs.

Multi-Agent Learning for the Inverse Kinematics of a Robotic Arm

This paper presents a solution to the inverse kinematics problem for robotic manipulator based on the Adaptive Multi-Agent System (AMAS) approach. In this research, multi-agent system is in charge of controlling a robot arm with four degrees of freedom (DOF) and two motorized wheels, giving appropriate commands, such as rotation angles and velocities, to reach the desired position and orientation of the end effector. The calculation of commands is directly related to the solving of forward and inverse kinematics. Before the learning process of AMOEBA, the rotational angles, θ values, are encoded into a single number N, this parameter is the desired value that we are going to predict in the predicting stage. During the learning phase, the Agnostic MOdEl Builder by self-Adaptation (AMOEBA) builds context agents, which has local models and is able to self-adapt. After the getting the predicted value, Npred, it will be decoded back to get the set of rotational angles that is given to robot end effector. In addition, the robot with all its physical parameters is modeled and simulated in the Robot Operating System (ROS) environment

An Adaptive Multi-Agent System With Duplex Control Laws for Distributed Resource Allocation

In this paper, we present an adaptive multi-agent system with duplex control laws for non-smooth resource allocation problem, where the decisions are subjected to local constraints and network resource constraints. The multi-agent system based on the distance penalty function method is developed in three sets of coupled differential inclusions or equations, where the last set of differential equations are designated to learn an adaptive penalty vector. In the multi-agent system, proportional and integral controls can be performed from two different layers of the multiplex control network with an independent communication topology at each layer. The existence of equilibrium points and convergence of the multi-agent system are proven for achieving optimal resource allocation starting from any initial resource allocation. Finally, the simulation results of two illustrative examples are discussed to substantiate the theoretical results.

An adaptive multiagent control system for autonomous economic operation and resilience assurance in a hybrid-energy islanded microgrid

Multi-agent control is widely recognized as an effective management system for modern microgrids. This paper proposes a hierarchical distributed multi-agent control system for an islanded microgrid with hybrid-energy resources and a battery-storage bank. The dispatchable dispersed generators are to be online-controlled to stabilize the islanded microgrid and minimize operation cost. A non-dispatchable agent is assigned to each bus with a non-dispatchable generator or a load. A dispatchable agent is assigned to each bus with a dispatchable generator. The control scheme is organized into three layers. The primary control layer comprises only the agent which runs the very fast local voltage/frequency droop-control of the battery-storage bank. It achieves a quasi-instantaneous power balance under any disturbance to maintain the frequency and voltage stability of the microgrid. The secondary control layer is formed by fast control algorithms on the dispatchable agents working at 2 ms time step. It is responsible for regulating the islanded microgrid frequency and voltage at minimum participation time of the battery-storage bank. The tertiary control layer is made by relatively slow control algorithms on the dispatchable agents working at a time step of 200 ms. It copes with the economic operation of the microgrid. Each agent behaves autonomously and shares data with others via communication links. The architecture and control algorithms of each layer are presented. Besides, the coordination protocol between different layers is described. The scheme is implemented by a parallel Matlab-Jade computing setup. Results of a case study islanded microgrid are analysed and compared to literature.

Creating a Modeling Language Based on a New Metamodel for Adaptive Normative Software Agents

The demand for creating increasingly dynamic, autonomous and proactive software systems is challenging for the traditional Multi-agent Systems (MASs) approaches. Such requirement has given rise to adaptive software agents approaches. At the same time, norm is an essential and challenging feature that still tends to be addressed in adaptive MAS. In fact, norms to regulate agent behavior is still a vague concept that has not been properly investigated in terms of modeling and implementation. Even though many researchers have proposed modeling languages to deal with different abstractions, these languages fail to support the modeling of abstractions, such as adaptation and norms. Even more severe is the fact that little has been done to support the systematic design of Adaptive Normative Multi-Agent Systems (ANMASs). To facilitate the design and development of ANMASs, this paper presents a new metamodel, as well as language support, as means to provide tools to enable software developers. The proposed metamodel fosters a better understanding of the way agents are able to change their behaviors to deal with norms and captures interactions between agent’s norms and adaptation. To this end, our research is organized into five steps: (i) a literature review to identify the limitations of existing approaches related to ANMAS modeling; (ii) propose a new metamodel to support adaptative and normative concepts; (iii) propose a new language for modeling ANMASs; (iv) perform a qualitative and quantitative evaluation of the proposed language using a real case scenario, and (v) an empirical evaluation. The proposed metamodel and its associated modeling language advances the state of the art in modeling MASs and the approach is assessed in terms of correctness, time and difficulty. Our initial results revealed that our approach can be feasibly applied in a real world application, and is less difficult to apply and requires less time in comparison with a traditional approach. As software applications become more dynamic and adaptive, we believe it is essential to support developers to model MASs with abstractions such as adaptive agents, norms and their relationships. Such information can be foundational to steer future research on modeling adaptive agents capable of understanding and dealing with norms and adaptation.

An adaptive multi-agent system for task reallocation in a MapReduce job

We study the problem of task reallocation for load-balancing of MapReduce jobs in applications that process large datasets. In this context, we propose a novel strategy based on cooperative agents used to optimize the task scheduling in a single MapReduce job. The novelty of our strategy lies in the ability of agents to identify opportunities within a current unbalanced allocation, which in turn triggers concurrent and one-to-many negotiations amongst agents to locally reallocate some of the tasks within a job. Our contribution is that tasks are reallocated according to the proximity of the resources and they are performed in accordance to the capabilities of the nodes in which agents are situated. To evaluate the adaptivity and responsiveness of our approach, we implement a prototype test-bed and conduct a vast panel of experiments in a heterogeneous environment and by exploring varying hardware configurations. This extensive experimentation reveals that our strategy significantly improves the overall runtime over the classical Hadoop data processing.

SApHESIA: An agent-based model and a criticality-based heuristic for cooperatively coupling SoSs

Abstract Problems to solve nowadays have never been so complex and are continuously increasing in complexity. In this context Systems of Systems (SoS) may be a solution but the study of such systems is far from over. An SoS is a complex system characterized by the particular nature of its components: the latter, which are systems, tend to be managerially and operationally independent as well as geographically distributed. This specific characterization led to re-think research fields of classic systems engineering, such as definition, taxonomy, modeling, architecting, etc. SoS architecting focuses on the way independent components of an SoS can be dynamically structured and can autonomously and efficiently modify their interactions in order to fulfill the goal of the SoS and to cope with the high dynamics of the environment. This paper contributes to the multi-agent and SoS research fields by proposing a new generic SoS model called SApHESIA which considers the SoS main characteristics found in the literature and extends the notion of environment and interactions between component systems. It also proposes a new SoS architecting procedure based on the Adaptive Multi-Agent System (AMAS) approach that advocates full cooperation between all the components of the SoS through the concept of criticality. This criticality is a measure, local to each component, expressing its difficulties to reach its local goals. In this procedure, the SoS architecture evolves to self-adapt to the dynamics of the environment in which it is plunged, while considering the respective local goals of its components. An instantiation of SApHESIA to two distinct cases studies from different domains (logistics and exploratory missions) is done to obtain two SoSs. These two SoS are then coupled to form a new SoS at an upper level. Evaluations of these SoSs show that their cooperation make each of them more efficient.

Adaptive finite-time consensus of a class of disturbed multi-agent systems

In this paper, the finite-time exponential consensus problem is addressed for a class of multi-agent systems against some disturbed factors, which include system uncertainties, communication perturbations, and actuator faults. All disturbed factors are supposed to be influenced by internal and external effects of systems. The internal effects are described in terms of dependency on the system states, while the external actions are restricted by constant bounds. To obtain the information of the rate of dependency on the states and constant bounds, an adaptive mechanism is designed to estimate the rate and bounds. Based on these estimates, a distributed adaptive sliding mode controller is constructed to eliminate the effects of those disturbed factors. Then exponential consensus of the closed-loop adaptive multi-agent system is achieved within a finite time based on Lyapunov stability theory. The efficiency of the developed adaptive consensus control strategy is verified by a coupled system with four F-18 aircrafts of decoupled longitudinal model.

Exploiting of Adaptive Multi Agent System Theory in Modeling and Simulation: A Survey

Exploiting of Adaptive Multi Agent System Theory in Modeling and Simulation: A Survey

КОМПЬЮТЕРНЫЕ СИСТЕМЫ ИНДИВИДУАЛЬНОГО ОБУЧЕНИЯ: ПРЕДПОСЫЛКИ И ПЕРСПЕКТИВЫ

This article discusses the background and perspectives of computer system of individual instruction as a tool to correct some problems of traditional education. The authors: 1) described the socio-economic environment leading to education degradation; 2) showed that the range of individual characteristics of learners could not be reflected by the formal assessment of their academic performance; 3) discussed the results of pedagogical experiment on the usage of individual and project-based learning, where the individual demonstrated the ability to team adaptation. We conclude that computer systems of individual instruction can be developed based on adaptive multiagent e-learning systems, if a detailed design of agents of educator and student, including a model of their interactions are determined.

The Use of Complex Adaptive Theory and Information Technologies to Inform Development Strategies in English Speaking Black Community, Montreal

The Use of Complex Adaptive Theory and Information Technologies to Inform Development Strategies in English Speaking Black Community, Montreal

Real-Time Cascading Failures Prevention for Multiple Contingencies in Smart Grids Through a Multi-Agent System

Cascading failures (CF) is complex in nature and difficult to accurately model or solve mathematically. The current industry approach to preventing CF, which leads to blackout event, involves incurring losses. In this paper, a technique based on an adaptive multi-agent system algorithm is implemented to prevent CF without loss incurrence. The algorithm uses mathematical combinations heuristically selected through the use of sensitivities obtained from the economic dispatch history of the power system to redispatch the power from the generators. This approach enables the implementation of the algorithm on systems of any size. The algorithm is experimentally applied in real-time with the consideration of necessary constraints as it halts the occurrence of CF. The test system is an experimental set up of the generation and transmission side of the IEEE 30-bus system using a reconfigurable smart grid laboratory hardware developed for testing algorithms requiring two-way communication capabilities. It was first showed that the test system will experience CF if nothing is done to prevent CF after the occurrence of a contingency. A detailed experimental analysis of the ensuing blackout event is given. The algorithm was used to prevent CF in the system after the occurrence of N-1 and N-1-1 contingencies. The algorithm was also tested on a larger system, the IEEE 118-bus system, through simulation. The experimental and simulation results affirm the efficacy of the proposed algorithm for systems of any size. In fact, it was discovered from our results that the large number of generators in large systems helps the algorithm converge faster than it does for small systems, which have restricted resources and combinations.

Exploiting the Use of Cooperation in Self-Organizing Reliable Multiagent Systems

In this paper, a novel and cooperative approach is exploited introducing a self-organizing engine to achieve high reliability and availability in multiagent systems. The Adaptive Multiagent Systems theory is applied to design adaptive groups of agents in order to build reliable multiagent systems. According to this theory, adaptiveness is achieved via the cooperative behaviors of agents and their ability to change the communication links autonomously. In this approach, there is not a centralized control mechanism in the multiagent system and there is no need of global knowledge of the system to achieve reliability. This approach was implemented to demonstrate its performance gain in a set of experiments performed under different operating conditions. The experimental results illustrate the effectiveness of this approach.