novtexmechМехатроника, автоматизация, управлениеMekhatronika, Avtomatizatsiya, Upravlenie1684-64272619-1253Commercial Publisher «New Technologies»10.17587/mau.17.37-41novtexmech-249Research ArticleАГЕНТНЫЕ СИСТЕМЫ УПРАВЛЕНИЯ И ПРИНЯТИЯ РЕШЕНИЙAGENT SYSTEMS CONTROL AND DECISION MAKINGПрименение мультиагентной платформы для создания интеллектуальных систем управления ресурсами в реальном времениApplication of the Multi-Agent Platform for Development of Smart Resource Management Systems in Real-TimeМайоровИ. В.MayorovI. V.imayorov@smartsolutions-123.ruНПК "Разумные решения"РоссияSoftware Engineering Company "Smart Solutions" LtdRussian Federation2016280820181713741Copyright © Commercial Publisher «New Technologies», 20182018Commercial Publisher «New Technologies»Commercial Publisher «New Technologies»https://mech.novtex.ru/jour/about/submissions#copyrightNoticehttps://mech.novtex.ru/jour/article/view/249

Рассматривается задача построения и применения мультиагентной платформы для создания интеллектуальных систем управления ресурсами в реальном времени. Предлагается метод многокритериального планирования производственных и транспортных ресурсов на основе модифицированной модели сети потребностей и возможностей (ПВ-сети) предприятий, в котором проводится поочередное улучшение различных критериев в зависимости от ситуации, отражаемой состоянием ресурсов и потоком входящих событий. Агенты ПВ-сети обладают собственными целевыми установками, но способны идти на уступки и компромиссы для достижения интереса системы в целом. Экспериментально показана возможность решения сложных задач управления ресурсами в реальном времени, которые не решаются или плохо решаются классическими методами и известными эвристиками. Разработанный метод и платформа применены при создании промышленных систем управления ресурсами в различных предметных областях, обеспечивая 20...40 %-ное повышение эффективности предприятий.

Problem statement: The paper considers a task of multi-agent platform development for designing smart resource management systems in real time. Multi-agent platform is based on main classes of interacting agents with competing interests represented by satisfaction and penalty functions. Methods: A method of multi-criteria planning of production and transport resources is proposed, based on a modified model of demand and resource network of enterprises, where various criteria are alternately improved depending on the situation reflected by the state of resources and incoming event flow. Every cycle of replanning has two stages: conflict-free planning and proactive schedule improving with conflicts resolutions. Enterprise production orders and industrial/human resources serve as demands and resources, correspondingly. Demand and resource network agents have their own goals but are capable of making a compromise to achieve a common interest of the whole system. Results: The paper experimentally demonstrates the opportunity of solving complex tasks of resource management, which cannot be solved by traditional methods and known heuristics with required quality and efficiency. Practical value: The developed method and platform can be applied when designing industrial systems of resource management in various domains, providing a 20-40 % increase of enterprise efficiency. The following systems has been developed and put into operation: a multi-agent system for scheduling of flight program, cargo flow and resources of the Russian Segment of the International Space Station; a system of railway transportation management; a system for workshop management of a machine-building enterprise; a system of transportation logistics and some others.

мультиагентная платформаподдержка принятия решенийадаптивное планированиемультиагентная технологияпланирование в реальном временипромышленные примененияmulti-agent platformdecision-making supportadaptive planningmulti-agent technologyreal-time planningindustrial applicationsReferencesLeung Y. Handbook of Scheduling: Algorithms, Models and Performance Analysis // CRC Computer and Information Science Series. London: Chapman & Hall / SRC, 2004. 1216 p.Leung Y. Handbook of Scheduling: Algorithms, Models and Performance Analysis // CRC Computer and Information Science Series. London: Chapman & Hall / SRC, 2004. 1216 p.Shirzadeh C., Shadrokh Sh. A Branch and Bound Algorithm for Resource Constrained Project Scheduling Problem subject to Cumulative Resources // World Academy of Science, Engineering and Technology. 2012. Vol. 6. P. 23-28.Shirzadeh C., Shadrokh Sh. A Branch and Bound Algorithm for Resource Constrained Project Scheduling Problem subject to Cumulative Resources // World Academy of Science, Engineering and Technology. 2012. Vol. 6. P. 23-28.Vos S. Meta-heuristics: The State of the Art in Local Search for Planning and Scheduling / A. Nareyek (Ed.). Berlin: Springer-Verlag, 2001. P. 1-23.Vos S. Meta-heuristics: The State of the Art in Local Search for Planning and Scheduling / A. Nareyek (Ed.). Berlin: Springer-Verlag, 2001. P. 1-23.Rolf C. R., Kuchcinski K. Distributed constraint programming with agents // Proc. of 2nd Int. Conf. on Adaptive and Intelligent Systems (ICAIS 2011), September 6-8, 2011, Klagenfurt, Austria. Berlin: Springer-Verlag, 2011. P. 320-331.Rolf C. R., Kuchcinski K. Distributed constraint programming with agents // Proc. of 2nd Int. Conf. on Adaptive and Intelligent Systems (ICAIS 2011), September 6-8, 2011, Klagenfurt, Austria. Berlin: Springer-Verlag, 2011. P. 320-331.Gongfa L. A hybrid particle swarm algorithm to JSP problem // IEIT Journal of Adaptive & Dynamic Computing, 2011. Vol. 2011, N. 3. P. 10-17.Gongfa L. A hybrid particle swarm algorithm to JSP problem // IEIT Journal of Adaptive & Dynamic Computing, 2011. Vol. 2011, N. 3. P. 10-17.Xueni Q., Lau H. An AlS-based Hybrid Algorithm with PSO for Job Shop Scheduling Problem // Proc. of 10th IFAC Workshop on Intelligent Manufacturing Systems, July 1-2, 2010, Lisbon, Portugal. Elsevier Science Direct - IFAC PapersOnline. 2010. P. 371-376.Xueni Q., Lau H. An AlS-based Hybrid Algorithm with PSO for Job Shop Scheduling Problem // Proc. of 10th IFAC Workshop on Intelligent Manufacturing Systems, July 1-2, 2010, Lisbon, Portugal. Elsevier Science Direct - IFAC PapersOnline. 2010. P. 371-376.Pinedo M. Scheduling: Theory, Algorithms, and Systems. Springer, 2012. 676 p.Pinedo M. Scheduling: Theory, Algorithms, and Systems. Springer, 2012. 676 p.Виттих В. А., Скобелев П. О. Метод сопряженных взаимодействий для управления распределением ресурсов в реальном масштабе времени // Автометрия. 2009. № 2. С. 78-87.Виттих В. А., Скобелев П. О. Метод сопряженных взаимодействий для управления распределением ресурсов в реальном масштабе времени // Автометрия. 2009. № 2. С. 78-87.Виттих В. А., Скобелев П. О. Мультиагентные модели взаимодействия для построения сетей потребностей и возможностей в открытых системах // Автоматика и телемеханика. 2003. № 1. С. 177-185.Виттих В. А., Скобелев П. О. Мультиагентные модели взаимодействия для построения сетей потребностей и возможностей в открытых системах // Автоматика и телемеханика. 2003. № 1. С. 177-185.Skobelev P. Multi-Agent Systems for Real Time Adaptive Resource Management. In Industrial Agents: Emerging Applications of Software Agents in Industry. Paulo Leitao, Stamatis Karnouskos (Ed.). Elsevier, 2015. P. 207-230.Skobelev P. Multi-Agent Systems for Real Time Adaptive Resource Management. In Industrial Agents: Emerging Applications of Software Agents in Industry. Paulo Leitao, Stamatis Karnouskos (Ed.). Elsevier, 2015. P. 207-230.Belousov A. A., Skobelev P. O., Stepanov M. E. Network-centric approach to adaptive real-time train scheduling // Proc. of 6th Int. Conf. on Swarm Intelligence (ICSI), 26-29 June, 2015, Beijing, China. Part II. Springer: Lecuture Notes on Computer Science. 2015. Vol. 9141. P. 290-299.Belousov A. A., Skobelev P. O., Stepanov M. E. Network-centric approach to adaptive real-time train scheduling // Proc. of 6th Int. Conf. on Swarm Intelligence (ICSI), 26-29 June, 2015, Beijing, China. Part II. Springer: Lecuture Notes on Computer Science. 2015. Vol. 9141. P. 290-299.Shpilevoy V. et al. Multi-agent system "Smart Factory" for real-time workshop management in aircraft jet engines production // Proc. of 11th IFAC Workshop on Intelligent Manufacturing Systems (IMS'13), May 22-24, 2013, Sao Paulo, Brazil. International Federation of Automatic Control, 2013. P. 204-209.Shpilevoy V. et al. Multi-agent system "Smart Factory" for real-time workshop management in aircraft jet engines production // Proc. of 11th IFAC Workshop on Intelligent Manufacturing Systems (IMS'13), May 22-24, 2013, Sao Paulo, Brazil. International Federation of Automatic Control, 2013. P. 204-209.Skobelev P., Lada A., Mayorov I. Finding an initial plan of transport resources FTL allocation in a special VRP problem using linear programming methods // Proc. of 19th World Multi-Conference on Systemics, Cybernetics and Informatics (WMSCI 2015), July 12-15, 2015, Orlando, Florida, USA. Vol. 1. 2015. International Institute of Informatics and Systemics. P. 16-21.Skobelev P., Lada A., Mayorov I. Finding an initial plan of transport resources FTL allocation in a special VRP problem using linear programming methods // Proc. of 19th World Multi-Conference on Systemics, Cybernetics and Informatics (WMSCI 2015), July 12-15, 2015, Orlando, Florida, USA. Vol. 1. 2015. International Institute of Informatics and Systemics. P. 16-21.

The authors declare that there are no conflicts of interest present.