Intelligent Multi-agent System Research Articles

Importance-driven denial of service attack strategy design against remote state estimation in multi-agent intelligent power systems

This paper introduces a novel importance-driven denial of service (IDoS) attack strategy aimed at impairing the quality of remote estimators for target agents within multi-agent intelligent power systems. The strategy features two key aspects. Firstly, the IDoS attack strategy concentrates on target agents, enabling attackers to determine the voltage sensitivity of each agent based on limited information. By utilizing these sensitivities, the proposed strategy selectively targets agents with high sensitivity to amplify disruption on the target agent. Secondly, unlike most existing denial of service attack strategies that adhere to predefined attack sequences, IDoS attacks can selectively target important packets on highly sensitive agents, causing further disruption to the target agent. Simulation results on the IEEE 39-Bus system demonstrate that, compared to existing denial of service attack strategies, the proposed IDoS attack strategy significantly diminishes the estimation quality of the target agent, confirming its effectiveness from an attacker's perspective.

An intelligent multi-layer, multi-agent MMG framework with amelioration of energy efficiency and future investment outlook, under the deregulated day-ahead and real-time market regime

This paper developed an intelligent multi-agent system (MAS) with a multi-layer framework for multi-microgrids (MMGs) using robust and modern communication patterns for deployed agents to achieve distributed tasks. The MMG paradigm introduces three microgrids (MGs) based on the type of load, working environment, and living habitat: residential, commercial, and industrial. In addition, a day-ahead and real-time model is proposed for day-ahead and real-time signals. Intelligent agents in the multi-layer MAS framework make smart decisions based on multiple algorithms to optimize schedule power and minimize costs, considering demand dispatch and demand response as core components. Maximum renewable energy utilization aims to increase user comfort and reduce greenhouse gas (GHG) emissions. Load agents deployed in each MG ensure maximum efficiency. The proposed framework recommends various tariff rates and tariff adjustment strategies to promote and offer an economic evaluation across the respective indices. To minimize the monopoly of the energy market, an efficient energy market model is developed for the proposed MMG paradigm to maximize the competition by incorporating future and spot-market trading schemes for day-ahead and real-time signals. The comparative analysis indicates optimized results based upon the cost-benefit analysis, cost reduction, power transaction in the market, and maximum utilization of renewable energy resources (RERs).

Modeling and using intelligent multi-agent system in smart city: ontological approach

The article discusses the problems of using intelligent multi-agent systems in solving a set of problems in managing and planning processes in a modern city. The concept of constructing intelligent multi-agent systems in systems that support the concept of a Smart City based on ontological modeling is considered. The proposed approach makes it possible to build formalized ontological models and flexibly configure an intelligent multi-agent system to solve problems of coordinating the work of all services of a modern city. The transition from a city in the usual sense to a Smart City is extremely necessary due to the huge gap between the increased complexity of the political, social and economic environment of modern settlements and the already outdated administrative and technological infrastructure, unable to function effectively in the new conditions. The article shows the need to rethink the key elements and general concept of the Smart City. The definition of a Smart City as a multiagent intelligent system is presented. An ontological approach is described, which involves minimal interference in the work of city services, ensures smooth changes and can be carried out by several teams of specialists in parallel. Currently, the method is used by the authors in a project aimed at developing Smart City – a digital ecosystem of services that allows achieving a synergistic effect between various subsystems (transport, ecology, energy, urban design, etc.).

Efficient and privacy-preserving multi-agent systems for smart city carpooling with k-regret queries and differential privacy

Multi-Agent Systems are characterized by the presence of multiple independent agents and find diverse applications. In the context of smart cities, MAS is employed in traffic management to enhance operational efficiency, optimize resource utilization, and improve the quality of life for residents. This research paper focuses on the design of a multi-agent intelligent scheduling system, where passengers, vehicles, and carpooling platforms serve as intelligent agents. The primary objective of passengers is to identify suitable shared vehicles based on criteria such as waiting time, budget constraints, and willingness to carpool. Vehicles, on the other hand, organize their schedules based on passenger demands and designated routes. The carpooling platform takes into account resource allocation priority and optimization problems to ensure the efficient operation of the system. To address the issue of vehicle ordering, k-regret queries are utilized, while passenger preferences provide insight into determining loss factors. To safeguard privacy, differential privacy techniques and a random response mechanism are employed when dealing with multiple passenger queries. Furthermore, a direction-preserving insertion verification method is implemented to mitigate computational complexity. The effectiveness and efficiency of the proposed approach are validated through experimentation.

Multi-agent Intelligent System Design for Telemedicine Applications to Develop Health Care Systems of Developing Countries

Various factors controlling health care in any country, but still there is a weakness in the infrastructure of health care systems in some developing countries, including many Arab countries, due to the shortage of medical specialists personnel, global economic crisis, and wars and disasters that struck many countries. A crying need for a tele-medical care becomes a necessity, and in order to overcoming this weakness we have proposed a multi-agent intelligent Telemedicine system in this research. The proposed system can help solve the shortage of specialists urgently and at lower costs. Furthermore, it can save the efforts of the patients' expensive travel for treatment abroad. Moreover, it can avoid infections from social closeness in times of disasters and pandemics.
 Nowadays Telemedicine systems have gradually become a popular medical model which have always attracted much attention due to the continuous development of the multi-agents' structure and capabilities of the artificial intelligence systems. So we will focus in the prototype design of our system on the algorithms, techniques and devices that support the multi-agents' structure and AI technologies. The Multi-agent approach happens to be a suitable structure for the development of Telemedicine systems. Worth mentioning it can solve problems that are difficult or impossible for an individual agent or a monolithic system, and the AI capabilities will minimize human errors and improve health care outcomes.
 We will start by a state-of-the-art literature survey as conducted on the E-health system architecture, AI capabilities, and multi-agent platform, and then we will illustrate prototype design of the suggested Multi-agent intelligent system for Telemedicine which will contribute in the development of the health care systems in the developing countries.
 Keywords: Healthcare system; Medical System; Artificial Intelligence; Multi-Agent, Telemedicine; Telehealth.

Students' Performance Prediction in Higher Education Using Multi-Agent Framework-Based Distributed Data Mining Approach

An effective educational program warrants the inclusion of an innovative construction that enhances the higher education efficacy in such a way that accelerates the achievement of desired results and reduces the risk of failures. Educational decision support system has currently been a hot topic in educational systems, facilitating the pupil result monitoring and evaluation to be performed during their development. In this literature survey, the authors have discussed the importance of multi-agent systems and comparative machine learning approaches in EDSS development. They explored the relationship between machine learning and multiagent intelligent systems in literature to conclude their effectiveness in student performance prediction paradigm. They used the PRISMA model for the literature review process. They finalized 18 articles published between 2014-2022 for the survey that match the research objectives.

Multi-agents in transport process control

Abstract. Problem The problem is computer science, car transfer, road maintenance, synergy, principles and paradigms of using car computer systems - ACS. The use of multi-agent systems in the virtual management of the transport process allows improving the quality of transport management. A multi-agent system is a collection of interacting agents that can work together to achieve a common goal. Multi-agent systems can be used for better management of logistics processes, in particular in the field of transport. The role of agents in decision-making, including in real time, is considered, which allows more accurate forecasting and control of the transport process. Goal. The goal is integration of the intelligent multi-agent system (IMAS) and agents in the task of virtual management of transport processes. Results. A program installed on a server that supports Internet functions can potentially be accessed from any workstation. This opens the way to the use of intellectual and production tools by almost all employees of the enterprise at minimal costs. The same application becomes available from any workstation connected to the Internet, which is critical for e-commerce applications. Such an opportunity opens access to applications to corporate partners for creating virtual enterprises and virtual management.

Dynamic Modelling and Numerical Simulation of Formation Control for Intelligent Multi-agent System with Target Geometric Configuration

Swarming motility arise very naturally in biological, physical, social sciences, etc. However, how to realize artificial intelligent self-organizing behavior is still an interesting and challenging task, especially for formation control of multiple agents with special geometric configuration. This work proposes a novel approach of formation control for a multi-agent system with target geometric configuration by combining dynamic model with graph realization. First, the global rigid graph is designed for the target formation pattern, then the interactive relationship and the expected distance between different intelligent agents are identified by the realization of graph. Secondly, the double-integrator dynamic model based on Newtonian mechanics is formulated for inherent driving force caused upon attenuation of potential energy, consistent of movement direction and speed. Thirdly, the stability of swarming motility is proved by Lyapunov’s second method, i.e., the movement of all agents will gradually stabilize to consistency of the movement direction and speed, and realize the target geometric configuration. Finally, numerical simulations of different geometric configurations are performed to verify the theoretical findings.

Simulation of rates of traffic accidents involving unmanned ground vehicles within a transportation system for the ‘smart city’

This article presents an approach to simulation of the rates of road traffic accidents involving unmanned ground vehicles within a multi-agent intelligent transportation system for the ‘smart city.’ A new simulation model of an intelligent transport system has been developed which makes it possible to significantly reduce the number of potential road traffic accidents (TAs) and implements the concept of socially-centered management of the urban economy. The software implementation of such a large-scale agent-based model was carried out using the FLAME GPU framework, which allows us to effectively parallelize the agents’ behaviour logic and consider their individual decision-making systems when modelling the spacial dynamics of an ensemble of unmanned ground vehicles (UGVs) interacting with other road users: the usual manned ground vehicles (MGVs), unexpected obstacles (e.g., pedestrians, etc.). Various scenarios of such agents’ behaviour in an intelligent transportation system are studied, including the occurrence of an accident under certain conditions (e.g., under the high speed and traffic intensity of UGVs, etc.) and various configurations of the digital road network (DRN). We determine the parameter values that provide for the individual decision-making system of UGVs remaining stable with respect to the characteristics of the external environment (including in extreme situations), ensuring the safety of other road users on the scale of the ‘smart city.’

APPLICATION OF CLUSTER ANALYSIS IN SMART GRID NETWORKS

The task of developing and improving intelligent multi-agent control systems, which provide opportunities for intelligent online analysis of the electrical power supply system provided by the smart grid system, is considered. The purpose of the article is the formation of clusters of sections of the electrical network, the initial parameters of which are the main indicators of the quality of electrical energy in accordance with the accepted standards. Total harmonic distortion coefficient of voltages, coefficient of unsymmetry of supply voltages, reactive power of loads are chosen as such parameters. The results of the hierarchical clustering of power supply network sections are summarized in the corresponding dendogram. The method of full connection is used to form a dendogram of sections of the power supply system. This method defines the distance between clusters as the largest distance between any objects in different clusters or the most distant neighbors. The measure of closeness was determined by the Euclidean distance. The obtained treeshaped diagram demonstrates the distribution of the sections of the power supply system into four natural clusters, which visually divides the sections of the power supply system into separate groups according to certain characteristics, namely the main parameters of the quality of the power system. It is shown that the mathematical apparatus of cluster analysis allows solving the problem of classification of sections of the power supply system when the main parameters of the quality of electric energy deviate from the normally permissible values. It is proved that the classification can be carried out not only by one parameter, but also by using a combination of several parameters. The results of the conducted analysis provide an opportunity to further form production rules for the selection of measures to improve the quality of electric energy, which are applied to one or another section of the power supply 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.

Intelligent multi-agent reinforcement learning model for resources allocation in cloud computing

Now more than ever, optimizing resource allocation in cloud computing is becoming more critical due to the growth of cloud computing consumers and meeting the computing demands of modern technology. Cloud infrastructures typically consist of heterogeneous servers, hosting multiple virtual machines with potentially different specifications, and volatile resource usage. This makes the resource allocation face many issues such as energy conservation, fault tolerance, workload balancing, etc. Finding a comprehensive solution that considers all these issues is one of the essential concerns of cloud service providers. This paper presents a new resource allocation model based on an intelligent multi-agent system and reinforcement learning method (IMARM). It combines the multi-agent characteristics and the Q-learning process to improve the performance of cloud resource allocation. IMARM uses the properties of multi-agent systems to dynamically allocate and release resources, thus responding well to changing consumer demands. Meanwhile, the reinforcement learning policy makes virtual machines move to the best state according to the current state environment. Also, we study the impact of IMARM on execution time. The experimental results showed that our proposed solution performs better than other comparable algorithms regarding energy consumption and fault tolerance, with reasonable load balancing and respectful execution time.

Enabling integration and interaction for decentralized artificial intelligence in airline disruption management

Airline disruption management traditionally seeks to address three problem dimensions: aircraft scheduling, crew scheduling, and passenger scheduling, in that order. However, current efforts have, at most, only addressed the first two problem dimensions concurrently and do not account for the propagative effects that uncertain scheduling outcomes in one dimension can have on another dimension. In addition, existing approaches for airline disruption management include human specialists who decide on necessary corrective actions for airline schedule disruptions on the day of operation. However, human specialists are limited in their ability to process copious amounts of information imperative for making robust decisions that simultaneously address all problem dimensions during disruption management. Therefore, there is a need to augment the decision-making capabilities of a human specialist with quantitative and qualitative tools that can rationalize complex interactions amongst all dimensions in airline disruption management, and provide objective insights to the specialists in the airline operations control center. To that effect, we provide a discussion and demonstration of an agnostic and systematic paradigm for enabling expeditious simultaneously-integrated recovery of all problem dimensions during airline disruption management, through an intelligent multi-agent system that employs principles from artificial intelligence and distributed ledger technology. Results indicate that our paradigm for simultaneously-integrated recovery executes in polynomial time and is effective when all the flights in the airline route network are disrupted.

Agents’ ontologies negotiation in cohesive hybrid intelligent multi-agent systems

The paper proposes the model for negotiating intelligent agents’ ontologies in cohesive hybrid intelligent multi-agent systems. Intelligent agent in this study will be called relatively autonomous software entity with developed domain models and goal-setting mechanisms. When such agents have to work together within single hybrid intelligent multi-agent systems to solve some problem, the working process “go wild”, if there are significant differences between the agents’ “points of view” on the domain, goals and rules of joint work. In this regard, in order to reduce labor costs for integrating intelligent agents into a single system, the concept of cohesive hybrid intelligent multi-agent systems was proposed that implement mechanisms for negotiating goals, domain models and building a protocol for solving the problems posed. The presence of these mechanisms is especially important when building intelligent systems from intelligent agents created by various independent development teams.

Intelligent implementation of residential demand response using multiagent system and deep neural networks

AbstractA successful implementation of demand response (DR) always depends on proper policy and their empower technologies. This article proposed an intelligent multiagent system to idealize the residential DR in distributed network. In our model, the primary stakeholders (smart homes and retailers) are demonstrated as a multifunctional intelligent agent. Home agents (HAs) are able to predict and schedule the energy load and retailer agents (RAs) predicts wholesale market price, sells energy to HAs. Both HAs and RAs are modeled to predict the real‐time pricing. Deep neural networks, that is, long short‐term memory network and hybrid CNN‐LSTM are used to predict the electricity load and energy price. Simulation results present good accuracy. Proposed work is compared with existing model w.r.t RMSE, MSE, and MAE. Comparison shows our model outperformed the existing models.

SYSTEM ANALYSIS IN HIERARCHICAL INTELLIGENT MULTI-AGENT SYSTEMS

The system analysis of the hierarchical intelligent multi-agent system in general, as well as its main structural unit, the intelligent agent, its major subsystems identified. As part of the analysis of the computer vision subsystem, it was concluded that the considered sources have insufficiently worked out issues related to the processing of occlusions, with the automation of the process of reconstruction of three-dimensional scenes, with the implementation of the processing of an unstructured set of images. The structure of the block for the reconstruction of three-dimensional scenes is proposed, the implementation of which is aimed at eliminating the indicated problems characteristic of the machine vision subsystem. The analysis of the main methods of implementing unsupervised learning is carried out, based on the results of which it is concluded that it is advisable to use reinforcement learning when implementing systems of this type. Such types of reinforcement learning as hierarchical reinforcement learning and multi-agent reinforcement learning are considered. A method for segmentation of macro actions is proposed, based on the implementation of clustering by the method of label propagation, in which the number of transitions is formalized in the form of weight coefficients of edges.

Development of a multi-agent intelligent system for solving problems of classification and ranking of materials on the Internet

The article proposes an architectural solution for intelligent information systems based on a multi-agent approach and microservice architecture. An example of using the described solution in the development of an automated intelligent search system that solves the problem of thematic classification and ranking of various sources of information on the Internet is given. The advantages and disadvantages of the developed architectural solution are described.

Improving the Maneuverability of Unmanned Vehicles at Various Road Network Configurations

The article presents an approach to improving maneuverability of unmanned ground vehicles (UGVs) interacting with manned ground vehicles (MGVs) within the proposed multi-agent intelligent transport system (MITS) at various configurations of the digital road network. With the developed models, the abilities of improving maneuverability of agent-vehicles in MITS under various control scenarios for the most important characteristics of the system, such as, the arrival intensities of agents, speeds of UGVs and MGVs, clustering methods for the traffic density estimation and intelligent maneuvering are studied. The proposed MITS is implemented based on the reconfigurable digital road network (DRN). There is proposed an approach to improving the maneuverability of the UGVs, aimed to effectively maneuvering in changing lanes and choosing the best routes to bypass traffic congestions and other problem areas with providing the required level of output traffic and minimizing the number of potential traffic accidents in the MITS. The possibilities of improving maneuverability of UGVs at various configurations of the DRN (for example, the roundabouts, "Manhattan Lattice", etc.) are studied.

Robot technological system of analysis of cybersecurity information systems and communication networks

The article presents the authors’ views on the organization of the modern system of cybersecurity. We considered the tasks, assigned to the monitoring subsystem and reconnaissance of cyberspace as a source of preventive hardware and software effects on the opposing side. The shortcomings of the existing structures of such subsystems are analyzed and the requirements to the intelligent automated system of cybersecurity are specified. The article offers hardware and software solutions, based on the development of a mobile robotic system for audit the stability of the network infrastructure and applications to existing and future cyber threats. A variant of the functional scheme of a robotic system with a universal housing is presented and with a set of mechanical drives, depending on the characteristics of the problems to be solved. For providing high functional flexibility and speed of the robotic system it is proposed to use fuzzy neural networks. The union of two independent theories - neural networks and fuzzy logic - allowed creating neural-fuzzy systems, having a high level of intelligence and independence in decision-making. The advantage of hybrid neural-fuzzy technology of modeling and information processing is the ability to view the generated rules and giving them a meaningful linguistic interpretation. A reasonable conclusion is made, that is the main meaning of that is the main meaning of the shift of creation concepts and using of artificial intelligence - transition from individual systems to distributed information processing and the development of multi-agent intelligent systems.

Prediction of the risk of cardiovascular complications with a segmented space of risk factors and synergy channels

To predict coronary heart disease, a basic structure of a multi-agent intelligent system is proposed, which contains “strong” and “weak” classifiers. “Weak” classifiers are divided into four groups, the first of which analyzes data obtained on the basis of traditional risk factors for coronary heart disease, the second - based on the analysis of electrocardiological studies, the third group of “weak” classifiers is designed to diagnose concomitant diseases and syndromes by predictors used the first two groups of agents, and the fourth analyzes environmental risk factors. The intelligent system allows you to manage the decision-making process through a combination of expert assessments, statistical data and current information. Experimental studies of various modifications of the proposed classifier model have been carried out. Analysis of the classification quality indicators in the experimental group of subjects with different ischemic risk indicators showed that taking into account the influence of the introduced risk factors in the control group increases the diagnostic efficiency by seven percent compared to the experimental group, which acts as a background.