Multi-agent Design Research Articles

Collaborative Hyperspectral Image Processing Using Satellite Edge Computing

The advancement of nanosatellite techniques has boosted the growth of satellite-originated data and applications. Satellite edge computing (SEC) is envisioned to provide in-orbit processing of the sensed data to save the scarce terrestrial-satellite communication resources and support mission-critical services. While most of the existing SEC studies mainly focus on general computing tasks, we present a two-tier collaborative processing framework for the important and unique hyperspectral image (HSI) processing task. Our framework carefully selects bands out of the collected HSIs and sends them back for further analysis. We first conduct a comprehensive data analysis to reveal the non-trivial relationship between the band selection and the eventual analytic performance. We then formulate the band selection problem in this collaborative setting as a utility maximization problem that jointly considers the analytic, energy, and communication factors. A novel multi-agent reinforcement learning approach, named MaHSI, is proposed to solve it in the dynamic SEC environment. Our multi-agent design judiciously embeds the complex correlations among bands as collaborations among agents and significantly reduces the exploration space. Extensive experiments on real-world HSI datasets prove that our approach not only outperforms the existing classical band selection algorithms in accuracy and inference speed but also brings the highest utility to the satellites.

Distributed adaptive event-triggered asymptotic tracking control of linear uncertain multiagent systems by using output only

For the robust tracking control problem of multiagent systems with linear uncertainties, most of the existing studies require full state feedback. Moreover, the designed control strategy also uses global information, such as the number of agents or the eigenvalues of the Laplacian matrix, which does not satisfy the distributed requirement for multiagent design. To address these problems, first, a Luenburger observer is designed to observe the full state of the system by using the output information. Second, the constant gain in the traditional distributed observer for estimating exosystem state information is replaced with a time-varying gain that comes from the output of a newly designed filter, which avoids the use of the global information mentioned above. Finally, based on the above observer and adaptive dynamic feedback, an event-triggered output feedback control strategy is given. This control strategy is not only piecewise constant, which is easy to implement, but also makes the robust tracking control error converge asymptotically to zero. Furthermore, it is theoretically proven that each agent does not have Zeno behaviour, and the effectiveness of the designed control strategy is verified with a simulation example.

Visualization of Emergency Evacuation Physical Behavior under Multi-Agent Decision-Making

Emergency evacuation simulation is significant for architectural design and emergency plan implementation. To explore the influence of evacuees’ physical behavior and evacuees’ decisions on the evacuation process, as well as to address the problems of traditional emergency evacuation models with insufficient detail of the situation (realism), low reusability, poor operability, and lack of subsequent scalability, this paper first analyzed pedestrian characteristics in emergencies. To describe pedestrian decision-making in an emergent evacuation situation, a multi-agent design based on decision theory was proposed, solving the multi-agent decision-making problem in an emergency evacuation environment by the A* algorithm. Then the designed multi-agent was embedded into the social force model by AnyLogic software. Finally, the model reproduces the pedestrian evacuation process in an emergency evacuation situation on the built platform, depicting three kinds of typical behaviors: pedestrian partnering, obstacle avoidance, and exit competition. In addition, this study also analyzed a large student apartment building by example and proposed corresponding optimization solutions to improve its evacuation capacity through simulation results.

A Multi-Agent Approach to Binary Classification Using Swarm Intelligence

Wisdom-of-Crowds-Bots (WoC-Bots) are simple, modular agents working together in a multi-agent environment to collectively make binary predictions. The agents represent a knowledge-diverse crowd, with each agent trained on a subset of available information. A honey-bee-derived swarm aggregation mechanism is used to elicit a collective prediction with an associated confidence value from the agents. Due to their multi-agent design, WoC-Bots can be distributed across multiple hardware nodes, include new features without re-training existing agents, and the aggregation mechanism can be used to incorporate predictions from other sources, thus improving overall predictive accuracy of the system. In addition to these advantages, we demonstrate that WoC-Bots are competitive with other top classification methods on three datasets and apply our system to a real-world sports betting problem, producing a consistent return on investment from 1 January 2021 through 15 November 2022 on most major sports.

An Agent-Based Traffic Recommendation System: Revisiting and Revising Urban Traffic Management Strategies

Strategic traffic management is crucial for combating traffic congestion at the macroscopic level. However, such a field is still relatively unexplored, particularly for microscopic control objects, such as intersections and coordinated intersection groups. This article proposes a human-in-the-loop recommendation system for strategic urban traffic management, which follows an agent-based structure. A regional agent dispatcher is defined to assign agents for operation whenever “operation on-demand” is required. Such a requirement is identified by a daily-dependent operational mode on strategic traffic operations at a control object level. The strategic management scheme for each control object is guided by a strategic agent (customized), which is essentially a deep recommender model with a specific architecture. By featuring the multiagent design, a customized operational scheme can be generated at the intersection level, which instructs the corresponding controller to take specific operations. The utility of the recommendation system is demonstrated via a case study using real-world traffic data. In both offline and online evaluations, the system performs consistently at traffic operational recommendations in different scenarios and has the potential to provide more reasonable traffic operational strategies than a human-operated system.

Агентно-ориентированный подход к проектированию гибких производственных систем

The article considers the process of designing modules of a flexible production site using multi-agent technology. For a comprehensive organization of the design, there has been proposed an algorithm of intelligent automated design of the complex technical systems, flexible manufacture systems (FMS) being used as an example. It has been stated that the research at the stages of the conceptual design of the FMS is carried out by collecting prototype variants with using expert knowledge and interaction of agents-designers according to the method of self-realizing computer aided design. Building a distributed system for the intelligent design of a hybrid architecture using the features of agent technology is considered. A flexible manufacture system is chosen as a design object, which is a complex technical object of research, the process of its design is multi-stage and iterative. To design such systems using a common functional model at the initial stage, a set of tasks is defined to facilitate the computing design of the FMS. This approach to the design of FMS requires implementing the solutions of a large number of local problems of different purposes. To solve the local problems of design procedures there has been proposed a multi-agent design technology, where the agent-designer performs a specific local task of the design process. The developed formalisms and algorithms help automate the synthesis of technical objects of the FMS. To build an automated conceptual design system as main decision-making for the multi-agent systems, there has been proposed a technical solution based on the knowledge of intelligent multi-agent systems. Using a multi-agent system makes it possible to build a distributed parallel design system with ability to be transferred to various hardware and software platforms. There has been also proposed the structure of a multi-agent system for the intelligent computer-aided design based on the designer's knowledge base.

Extricating web pages from deep web using deaima architecture

Due to remarkable development of advanced data, it has gotten drawn-out to recover applicable query items from the web crawler. The customary web search tool furnishes pertinent site pages however with the blend of unessential pages with less coverage rate and high slithering time. To overcome the issues, this paper proposes an Intelligent Multi-Agent design that utilizes Differential Evolution Algorithm (DEA) to extricate more pertinent site pages with high coverage rate and less slithering time. Three intelligent agents, specifically, Trajectory pattern mining agent, Query clustering agent and Web page classification agent are employed to track the relevancy of the pages, hidden web links and classify the searchable and non-searchable forms respectively. The extrication of relevant pages is optimized by the DEA algorithm. DEA calculation like selection, crossover and mutation are utilized for optimizing the extraction process. In any case, in Genetic Algorithm (GA) determination of chromosome depends on the wellness esteem, where the low quality chromosomes don't get by in the future. The Differential Evolutionary activity help the helpless chromosome to get by in the opposition and it will create the upgraded results. The learnt by experience of the intelligent agents help to work on the presentation of the framework. The exploration result shows that the proposed architecture gives the high precision and recall ratesover the current web crawlers. The creeping time for recovering the website pages is likewise diminished utilizing the proposed DEAIMA architecture.

Human machine interface (HMI) based on a multi-agent system in a water purification plant

The applications of multi-agent systems (MAS) are growing increasingly in the industrial field due to the advantages inherent to their characteristics and properties, the use of distributed automation architectures, which have satisfactorily solved control problems that its complexity and dynamic behavior have not been properly resolved with other approaches under these conditions, intelligent agents must meet the requirements of current automation systems, such as autonomy, flexibility, reconfiguration, in concurrent and collaborative systems, which traditionally do not have been designed to satisfy these characteristics. In the present work, a distributed architecture is proposed for the design of an intelligent agent in a Human-Machine Interface (HMI) for the supervision of the filtering stage of a water purification plant, characterized by the ability to collaborate with the other agents that make up the entire plant. For the projection and design of the system, the Unified Modeling Language (UML) and Petri nets (PN) are used for the simulation and validation of the system, and the implementation of the agent from macros in C language, starting from a methodology of multi-agent design that is applied in this document. The implementation of the intelligent agent in an HMI associated with multi-agent architecture, which allowed to evaluate its behavior through the analysis of the properties of the PN and experimental tests, demonstrating the correct operation of the device, response times and its dynamic behavior based on of the functional requirements of the water purification plant and comparisons with similar works.

Multi‐agent system for the reactive fleet maintenance support planning of a fleet of mobile cyber–physical systems

Improving the availability and reliability of a fleet of mobile cyber–physical systems as well as the ability to adapt themaintenance planning decisions when facing unexpected events at the fleet level is a major stake faced by the manufacturersand the operators. In the context of this study, the authors propose a reactive multi-agent system model for the fleetmaintenance planning of mobile cyber–physical systems. For that purpose, the ANEMONA multi-agent design methodology isused. In this methodology, the agents are modelled and then their organisational and interaction views are described. Numericalexperiments are carried out in static and dynamic contexts. In a static context, the proposed multi-agent system is comparedwith a mathematical programming model to validate the effectiveness of the former in satisfying the fleet's availability andreliability expectations. In a dynamic context, simulated perturbations are used to illustrate the reactivity of the proposed multi-agent system. Lastly, an application to rail transport for the maintenance of a fleet of trains at Bombardier Transportation Franceis proposed. For that purpose, the proposed multi-agent system is integrated in the model layer of a decision support systemnamed ‘MainFleet’ which is currently under development

Multiple Agent Designs in Conversational Intelligent Tutoring Systems

This article describes designs that use multiple conversational agents within the framework of intelligent tutoring systems. Agents in this case are computerized talking heads or embodied animated avatars that help students learn by performing actions and holding conversations with them in natural language. The earliest conversational intelligent tutoring systems were limited to a single agent that interacted with a student in the role of a teacher or expert. Technological advances have since made possible systems in which multiple agents interact with the learner and each other to model ideal behavior, strategies, reflections, and social interactions. Though still an emerging technology, multi-agent intelligent tutoring systems afford pedagogical benefits that go beyond the capabilities of the single-agent system and have facilitated learning gains on a variety of subject matters and skills, including science, technology, engineering, mathematics, research methods, metacognition, and language comprehension. The present work describes some common multi-agent designs that may be used to achieve a variety of pedagogical goals. We provide examples of how these designs have been implemented in educational or experimental settings and anticipate future use within the field of artificial intelligence.

A multiagent design for self-healing in electric power distribution systems

The out-of-service area after fault should berestored by changing the distribution system configuration by means of switching actions on the feeders. This paper proposes an agent-based approach for service restoration in smart distribution systems with distributed generations (DG). The proposed multi agent has four different types of agents: feeder agents, zone agents, switch agents and DG agents. The agents can communicate and cooperate with each other in order to supply services to out-of-service customers. An artificial neural network has been considered within DG agent to predict the DG generation. The restoration plan is built based on local data considering system conditions, operational constraints and fault location. Different loading conditions have been considered under different scenarios and the result of proposed multi agent approach for each scenario with and without DG have been compared. Simulation results show the efficiency of proposed agent architecture.

Multi-Principal Multi-Agent Contract Design: Theory and Application to Device-to-Device Communications

How to stimulate the devices to participate is a key problem in the device-to-device (D2D) communications, especially when there are multiple base stations in practice. On one hand, the base station needs to lower the price to compete with other base stations for attracting more devices. On the other hand, the base station needs to increase the price to obtain more benefit. In this paper, we propose an optimal multiprincipal multiagent contract design to tackle such a challenge. Specifically, we formulate the multiprincipal contract design problem as a game theoretic optimization problem, where the objective of each principle (base station) through contract design is to maximize its overall utility obtaining from the trade with agents (devices) subject to the individual rationality and incentive compatibility constraints. By solving the game theoretic optimization problems, we can obtain the equilibrium contract where the contracts of different principals reach an equilibrium and any deviation from a single principal will lead to the degradation of its own utility. Moreover, under the equilibrium, both the individual rationality and incentive compatibility constraints are satisfied, i.e., all agents will choose the corresponding contract according to their types to reach the optimal nonnegative utilities. Simulation results show that compared with the monoprincipal contract design, both the utilities of devices and the social welfare can be improved with the multiprincipal contract design.

Multi-agent simulation-based residential electricity pricing schemes design and user selection decision-making

Multi-agent system employs the functions of communication, coordination and cooperation among intelligent agents to help people judge and analyze complex phenomena that cannot be directly observed, and it has become an important tool for solving large-scale complex problems. The problem of demand response (DR) in electric power system is difficult to be modeled due to the complicated environment and continuously evolving subjects. Multi-agent system can simulate the operation mechanism of electric power system, thus playing an important role in solving the DR problems. In this study, based on multi-agent simulation, we establish a multi-agent model of residential power market and propose a satisfaction function of residential users about electricity price. We focus on the interaction process among all the agents of power supply side, selling side and demand side and conduct simulation to obtain the selection and decision-making of residential users on different electricity pricing schemes. The results show that multi-agent system is beneficial to analyze, simulate and solve the DR problem in power market. Also, the satisfaction function of residential users on electricity price can support power selling enterprise to better understand the intention of residential users when choosing electricity pricing schemes and participating in DR program.

User-story driven development of multi-agent systems: A process fragment for agile methods

Agile software development methods are mostly built as a set of managerial guidelines and development concepts on how to handle a software development but are not bounded to software development paradigms like object or agent orientation. Some methods, like eXtreme Programming and SCRUM are driven by operational requirements representation models called User Stories. These User Stories can be used as an anchoring point to agile methods; this means that we could take a User Stories set to drive a software transformation approach embedded in a particular development paradigm. This paper presents a process fragment for Multi-Agent Systems development with agile methods based on User Stories sets. The process fragment indeed takes advantage of an initial set of User Stories to build a reasoning model (called the Rationale Tree; typically several of these are built for a single project) that documents decompositions and means-end alternatives in scenarios for requirements realization. A Rationale Tree can then be aligned with a Multi-Agent design and implemented in an agent-oriented development language. In this paper the transformation is targeted to the JAVA Agent DEvelopment (JADE) framework. The process fragment (at least partially) covers the Requirements Analysis, Multi-Agent System Design and Multi-Agent System Implementation phases. Transformation from one phase to the other is overseen and illustrated on an example.

Sprut ExPro — средство генерации многоагентных систем проектирования в машиностроении. Часть 2

Sprut ExPro — средство генерации многоагентных систем проектирования в машиностроении. Часть 2

Sprut ExPro — средство генерации многоагентных систем проектирования в машиностроении. Часть 1

Sprut ExPro — средство генерации многоагентных систем проектирования в машиностроении. Часть 1

A generative multi-agent design methodology for additively manufactured parts inspired by termite nest building

The geometrical complexity available through additive manufacturing processes requires new tools to help designers maximise its advantages. A termite colony can construct highly complex nests that are optimised for thermoregulation and ventilation. The simple individual behaviour of these termites leads to highly intelligent colony behaviour, allowing nests to be simultaneously designed, optimised and produced. By mimicking termite behaviour, this research has led to a new design methodology using multi-agent algorithms that simultaneously design, structurally optimise and appraise the manufacturability of parts produced by additive manufacturing. A case study demonstrates the generative design of lightweight parts using the multi-agent system.

Multi-agent team for engineering: a machining plan in intelligent manufacturing systems

This paper explores the modelling of technical expertise in metal-cutting processes in a form suitable for the development of computer-aided process planning (CAPP) in intelligent manufacturing systems using agent-oriented software technologies. Focusing on the selection of tools and cutting parameters in the design of machining operations, the ontology for the knowledge domain was first introduced, and then in that context identify and analyse some of the challenges that CAPP presents to the multi-agent system architect. In particular, interactions between operation design and setup design was investigated, issues arising from global impacts of local decisions in plan construction were examine, and differences between software agents and humans in comparable planning roles were discuss. The analysis leads to several multi-agent design patterns that help capture domain-specific know-how and integrate it into efficient team behaviour. A pattern is illustrated with a concrete scenario.

ECOOP: Applying Dynamic Coalition Formation to the Power Regulation Problem in Smart Grids

In this work, we focus on one particular area of the smart grid, namely, the challenges faced by distribution network operators in securing the balance between supply and demand in the intraday market, as a growing number of load‐controllable devices and small‐scale, intermittent generators coming from renewables are expected to pervade the system. We introduce a multiagent design to facilitate coordinating the various actors in the grid. The underpinning of our approach consists of an online cooperation scheme, ECOOP, where agents learn a prediction model regarding potential coalition partners and so can respond in an agile manner to situations that are occurring in the grid, by means of negotiating and formulating speculative solutions, with respect to the estimated behavior of the system. We provide a computational characterization for our solution in terms of complexity, as well as an empirical analysis against real consumption data sets, based on the macro‐model of the Australian energy market, showing a performance improvement of about 17%.

Базовая модель поведения агента в мультиагентной среде проектирования корпусной мебели

Базовая модель поведения агента в мультиагентной среде проектирования корпусной мебели