MULTIFUNCTIONAL MULTI-AGENT SMART-SYSTEM BASED ON MODIFIED SWARM INTELLIGENCE ALGORITHMS

The article is devoted to the development of multifunctional multi-agent Smart-system for prediction and control of complex objects based on modified swarm intelligence algorithms and artificial immune systems. Modified CPSOIW-CS algorithm has been developed based on cooperative particle swarm optimization with inertia weight (СPSOIW) and clonal selection (CS) algorithm. Preliminary data processing and selection of informative descriptors have been performed based on CPSOIW algorithm. The application of CPSOIW algorithm allows more detailed and fast exploration of multidimensional space and avoid premature convergence. Pattern recognition and prediction have been carried out using CS algorithm. In paper relevance and prospects of the developed system in real production have been shown. The block schema of multifunctional multi-agent Smart-system has been developed. The following agents have been created: database agent, manager agent, assistant agent, ontological agent, cooperative particle swarm agent with inertia weight, pattern recognition agent and prediction evaluation agent, also their functions have been described. The MCPSO (Multi-agent Cooperative Particle Swarm Optimization) software has been developed in Python programming language to process multidimensional data, select informative descriptors and create an optimal set ofparameters characterizing an object and it is a module o f multifunctional multi-agent Smart system.

1. Andreadisa G., Klazogloub P., K. Niotakib, K. D. Bouzakisa Classification and Review of Multi­-Agents Systems in the Manufacturing Section // Procedia Engineering. - 2014. - Vol. 69. - Р. 282-290.

2. Sayda A. F. Multi-agent Systems for Industrial Applications: Design, Development, and Challenges // In book: Multi-Agent Systems - Modeling, Control, Programming, Simulations and Applications. - 2011. - DOI: 10.5772/15696.

3. Quoniam L., Baaziz A. How to use Big Data technologies to optimize operations in Upstream Petroleum Industry // https://hal.archives-ouvertes.fr/hal-00944668/file/Paper_IJI_Baaziz_Quoniam

4. Yaralidarani M., Shahverdi H. An improved Ant Colony Optimization (ACO) technique for estimation of flow functions from core-flood experiments // Journal of Natural Gas Science and Engineering. - 2016. - Vol. 33. - P. 624-633.

5. Nozohour-leilabady B., Fazelabdolabadi B. On the application of artificial bee colony (ABC) algorithm for optimization of well placements in fractured reservoirs; efficiency com parison with the particle swarm optimization (PSO) methodology // Petroleum. - 2016. - Vol. 2, Issue 1. - P. 79-89.

6. Huang S., Tian N., Wang Y., Ji. Z. Particle swarm optimization using multi-information characteristics of all personal-best information // Springer Plus. - 2016. - Vol. 5 (1632). https://doi.org/10.1186/s40064-016-3244-8.

7. Ghaedi M., Ghotbi C., Aminshahidy B. The optimization of gas allocation to a group of wells in a gas lift using an efficient Ant Colony Algorithm (ACO) // Energy Sources, Part A: Recovery, Utilization and Environmental Effects. - 2014. - Vol. 36, Issue 11. - C. 1234-1248.

8. Абрамов А. С. Методы искусственного интеллекта для решения задачи оптимального размещения кустовых площадок и распределения скважин между ними. - 2016. - № 4 (736). - С. 25-29.

9. Self R., Atashnezhad A., Hareland G. Reducing. Drilling Cost by finding Optimal Operational Param eters using Particle Swarm Algorithm // Proc. of Society of Petroleum Engineers Source SPE Deepw ater Drilling and Completions Conference. URL: https://www.researchgate.net/publication/304998993.

10. Zhang J., Ding X. A Multi-Swarm Self-Adaptive and Cooperative Particle Swarm Optimization // Engineering Applications of Artificial Intelligence. - 2011. - Vol. 24, Issue 6. - P. 958-967.

11. Leitao P. Multi-agent Systems in Industry: Current Trends & Future Challenges // Beyond Artificial Intelligence. Topics in Intelligent Engineering and Informatics. - Springer, 2013. - Vol. 4. - P. 197-201.

12. Wang L., Wang Z., Yang R. Intelligent M ultiagent Control System for Energy and Comfort Management in Smart and Sustainable Buildings // IEEE transactions on Smart grid. - 2012. - Vol. 3, No. 2. - P. 605-617.

13. Lindegaard Mikkelsen L., Neumann J. R., Demazeau Y , Jorgensen B. N. Demonstrating Multi layered MAS in Control of Offshore Oil and Gas Production // Advances on Practical Applications of Agents and Multi-Agent Systems. PAAMS 2013. Lecture N otes in Computer Science. - 2013. - Vol. 7879. - P. 300-303.

14. Wu С., Li H., Wu L., Wu Z. Agent Particle Swarm Optimization for Power System Economic Load Dispatch // Journal of Computer and Communications. - 2015. - Vol. 3. - P. 83-89.

15. Li R., Zhan W., Hao Z. Artificial Immune Particle Swarm Optimization Algorithm Based on Clonal Selection // Boletrn Tecnico. - 2017. - Vol. 55, Issue 1. - P. 158-164.

16. Zhang W., Lin J., Jing H., Zhang Q. A Novel Hybrid Clonal Selection Algorithm with Combinatorial Recombination and Modified Hypermutation Operators for Global Optim ization // Computational Intelligence and Neuroscience. - 2016. - http://dx.doi.org/10.1155/2016/6204728.

17. Yang J., Zhu H., Wang Y. An Orthogonal Multi-Swarm Cooperative PSO Algorithm with a Particle Trajectory Knowledge Base // Symmetry. - 2017. - Vol. 9 (1), No. 15. - DOI: 10.3390/sym9010015.

18. Hall M. A. Correlation-based Feature Selection for Machine Learning, Thesis of Doctoral dissertation. - The University o f W aikato, 1999.

19. Ulutas В., Kulturel-Konak S. A review of clonal selection algorithm and its applications // Artificial Intelligence Review. - 2011. - Vol. 36 (2). - P. 117-138.