AGENT-ORIENTED AND SYSTEM-DYNAMIC MODELING IN THE MANAGEMENT OF COMPLEX SYSTEMS

DOI: 10.31673/2786-8362.2024.026791

Abstract

The article is devoted to the
creation of agent-oriented and system-dynamic models, and means of developing compatible problem
solvers of intelligent systems capable of solving complex problems. The main problem considered in the
work is the low consistency of the principles underlying the implementation of various models of problem
solving. As a result, it is significantly difficult to simultaneously use different models of problem solving
in a single system during the execution of the same complex task, it is practically impossible to reuse
technical solutions implemented in any system, in addition, there are actually no complex methods and
tools capable of ensure the process of developing problem solvers at all stages. It is proposed as a basis for
solving the problem of the compatibility of problem solvers to implement a multi-agent approach, and to
divide the process of solving any problem into logically atomic actions that will ensure the compatibility
and modifiability of the solvers. It is proposed to consider the solver as a hierarchical system consisting of
several interconnected levels, which allows for the possibility of independent design, debugging and
verification of components of different levels. The proposed models, methods and tools were used in the
development of a number of protot prescription product types of intelligent educational systems, as well as
a prototype of the automation system of on.

Keywords: automated design system, modeling, task solver, intelligent agent, database

List of used literature:
1. Бідніченко О. Г. Сучасні тенденції розвитку систем автоматизованого комп’ютерного
моделювання. Управління розвитком складних систем. 2022. № 49. С. 59-65.
URL: https://doi.org/10.32347/2412-9933.2022.49.59-65.
2. Discrete-event System Simulation / J. Banks et al. 5th ed. Pearson, 2009. 648 p.
3. Kim S., Chen D. Virtual Reality Simulations in Control Systems Education: A Case Study.
IEEE Transactions on Education. 2019. Vol. 62(4). P. 309-316.
4. A Labview-based Remote Laboratory Experiments for Control Engineering Education /
M. Stefanovic et al. Computer Applications in Engineering Education. 2011. Vol. 19 (3). P. 538-549.
URL: https://doi.org/10.1002/cae.20334.
5. Chen L., Li S. Adaptive E-Learning System for Control Engineering Education Based on Item
Response Theory. IEEE Access. 2019. Vol. 7. P. 60745-60754.
6. Garcia M., Lopez G. Evaluating the Quality of Computer Models in Control Systems
Engineering Education. Journal of Engineering Education. 2020. Vol. 109(1). P.48-69.
7. Suarez R., Bermudez N. Challenges in Real-Time Simulation for Engineering Education.
International Journal of Electrical Engineering Education. 2018. Vol. 55(3). P. 237-253.
8. Kim C., Chen J. Virtual Reality Applications in Engineering Education: A Review. Journal of
Professional Issues in Engineering Education and Practice. 2019. Vol. 145(1). P. 04018014.
9. Chen L., Li S. Adaptive E-Learning System for Control Engineering Education Based on Item
Response Theory. IEEE Access. 2019. Vol. 7. P. 60745-60754.
10. Smith D., Brown T. Artificial Intelligence in Control Systems Education: A Review and Case
Study. IEEE Transactions on Education. 2021. Vol. 64(1). P. 26-36.
URL: https://doi.org/10.3389/fsufs.2021.756584/
11. Actor Pilgrim system. URL: http://simulation.su/static/actor-pilgrim-full-info.html (date of
access 13.10.2024).
12. Three-dimensional Trajectories and Network Analyses of Group Behaviour Within Chimney
Swift Flocks During Approaches to the Roost / D. J. Evangelista et al. Royal Society B: Biological
Sciences. 2017. Vol. 284, no 1849. URL: https://doi.org/10.1098/rspb.2016.2602.
13. Williams R. J., Zipser D. A Learning Algorithm for Continually Running Fully Recurrent
Neural Networks. Neural computation. 1989. Vol. 1. P. 270-280.
14. Hoshen Y. Vain: Attentional Multi-agent Predictive Modeling. 31st Conference on Neural
Information Processing Systems (NIPS 2017), Long Beach, CA, USA. 2017. P. 2701-2711.
15. Ha S., Jeong H. Uncovering Hidden Interactions in Complex Systems Using Deep Learning.
Scientific Reports. 2021. No 12804. URL: https://doi.org/10.1038/s41598-021-91878-w.