The paper is devoted to an overview of multi-agent principles, methods, and technologies intended to adaptive real-time data clustering. The proposed methods provide new principles of self-organization of records and clusters, represented by software agents, making it possible to increase the adaptability of different clustering processes significantly. The paper also presents a comparative review of the methods and results recently developed in this area and their industrial applications. An ability of self-organization of items and clusters suggests a new perspective to form groups in a bottom-up online fashion together with continuous adaption previously obtained decisions. Multi-agent technology allows implementing this methodology in a parallel and asynchronous multi-thread manner, providing highly flexible, scalable, and reliable solutions. Industrial applications of the intended for solving too complex engineering problems are discussed together with several practical examples of data clustering in manufacturing applications, such as the pre-analysis of customer datasets in the sales process, pattern discovery, and ongoing forecasting and consolidation of orders and resources in logistics, clustering semantic networks in insurance document processing. Future research is outlined in the areas such as capturing the semantics of problem domains and guided self-organization on the virtual market.
The paper describes an ontological model of a planning object, which provides flexible configuration of multiagent resource management systems. The authors propose using the basic ontology of resource planning and then building it up for significantly different domains. The key concept here is “Task”. A relatively universal agent can be created thanks to formalized description of various classes of tasks based on this concept. It can also be customized to a specific domain area. Based on the ontology, an enterprise knowledge base is created. It contains instances of concepts and relations. The paper also introduces new classes of agents for demand and resource networks. The authors then propose a new method of multi-agent planning using this knowledge base. This approach has been already successfully applied in several domain areas through the developed software package. The paper demonstrates that the use of ontologies can improve the quality and efficiency of planning by taking into account multiple factors in real time, thus reducing the cost of creating and maintaining multi-agent systems, as well as development times and risks.
The paper contributes to design of autonomous cyber-physical multiagent systems for adaptive resource management providing increase of efficiency of business operating in uncertain and dynamic environment. Evolution of multi-agent systems from purely decision-making support and simulation tool to cyber-physical system including Digital Twins and fully autonomous systems is analyzed. The main paper contribution is the proposed conceptual framework for designing autonomous cyber-physical multi-agent systems for adaptive resource management. It is shown in the paper that, in cyber-physical multiagent systems for adaptive resource management, the ontology-customized multi-agent engine and ontology-based model of enterprise are forming ontology-driven “Digital Twin” of the enterprise providing opportunity to combine operational scheduling of resources with ongoing real-time simulations and evolutional re-design of configuration of enterprise resources. The functionality and architecture of the autonomous cyber-physical multi-agent systems for adaptive resource management are developed to support for the full cycle of autonomous decision making on resource management. Time metrics for measuring event-based response time and level of adaptability of autonomous cyberphysical multi-agent systems for adaptive resource management are proposed. Results of developments can be applied for smart transport and smart manufacturing, smart agriculture, smart logistics, smart supply chains, etc.
The growing demand for improving business efficiency requests the development of generic resource management systems applicable for solving a wide range of complex problems with minimum cost and time. However, the classical combinatorial or heuristic methods and tools do not provide adequate solutions for solving complex problems of resource management in real time. That is why we consider multi-agent technology as the core part of such solutions – which helps find the balance of many interests and adapt it in a flexible way to unpredictable events, such as a new order, an unavailable resource, etc. In this paper we introduce the use of ontology for scheduling, which provides the opportunity to create ontological model of the enterprise, develop generic multi-agent scheduler and customize matching requirements for each operation in business or technological processes, for example, for applications in manufacturing, project management, supply chains, etc. Semantic Wikipedia on the top of ontology editor will be discussed to support knowledge base of enterprise for resource management. The example of applications for supply chain of insurance company is presented.
The objective of the paper is to discuss the increasing complexity of modern space traffic in the near-Earth space and outline the new approach for solving the problem. The requirements and functionality of digital platform for traffic management are presented and examples of problem solving are given. The developed approach will create new opportunities for managing space traffic and resources of the mission control centers for a large number of spacecrafts. Possible approaches to description of spacecraft flights are given. Methods and tools for optimizing the use of ground control complexes to manage large-scale orbital groups have been discussed. Creation of the digital platform and eco-system of smart services for space traffic management will solve the most important problem of space traffic management to increase the effectiveness of the created satellites groups and to protect the spacecrafts from space waste and debris.
The article describes the main principles of intelligent real-time resource management systems based on the use of multi-agent technology. Features of the new generation of systems are demonstrated that implement the full cycle of autonomous resource management, from reaction to real-world to monitoring deviations between the plan and the fact on the basis of the developed multi-agent platform. The article also presents several applications of scheduling systems in various areas, including cargo flow management for the International Space Station, workshop management in machine-building enterprises, railway traffic and cargo transportation management. Adaptability of multi-agent systems to external disruptive events is demonstrated. Finally, the similarities between multi-agent systems and non-equilibrium thermodynamics of Ilya Prigogine are described.
In this chapter, the approach for developing multi-agent solutions for solving real-tame scheduling problems will be presented, as well as examples of commercial applications that have been running in day-to-day operations for several years and have produced measurable and proven benefits.
In this paper modern methods of scheduling and resource optimization based on the holonic approach and principles of “Swarm Intelligence” are considered. The developed classes of holonic agents and method of adaptive real time scheduling where every agent is connected with individual satisfaction function by the set of criteria and bonus/penalty function are discussed. In this method the plan is considered as a un-stable equilibrium (consensus) of agents interests in dynamically self-organized network of demands and supply agents. The self-organization of plan demonstrates a “swarm intelligence” by spontaneous autocatalitical reactions and other not-linear behaviours. It is shown that multi-agent technology provides a generic framework for developing and researching various concepts of “Swarm Intelligence” for real time adaptive event-driving scheduling and optimization. The main result of research is the developed approach to evaluate the adaptability of “Swarm Intelligence” by measuring improve of value and transition time from one to another unstable state in case of disruptive events processing. Measuring adaptability helps to manage self-organized systems and provide better quality and efficiency of real time scheduling and optimization. This approach is under implementation in multi-agent platform for adaptive resource scheduling and optimization. The results of first experiments are presented and future steps of research are discussed.
The paper describes a multi-agent system which is capable of achieving its goals under conditions of uncertainty and which exhibits emergent intelligent behaviour such as adaptation, learning and co-evolution with their environment. The intelligence of the scheduler emerges from the horizontal and vertical interaction of its constituent agents balancing their individual and group interests.