Model-based learning of coordinators of the decentralized multi-zone objects control systems
DOI:
https://doi.org/10.31649/1999-9941-2024-60-2-66-76Keywords:
machine learning, distributed control system, decentralized coordination, model-based, learningAbstract
Abstract. Decentralized control systems are gaining more and more expansion, which is due to the increase in the availability and power of microcontrollers. Decentralized control of multi-zone objects is associated with the need to coordinate the local control systems of zones state. Learning systems are preferred for implementation of the coordination methods, as they are able for flexibly adjust to the specifics of control of each zone. However, the training of coordinators is complicated task by the absence at the stage of a system creating of marked datasets for controlled multi-zonal objects. This article considers the creation of a dataset based on a simulation of a decentralized system and four scenarios for training neural coordinators. A model for simulation of a decentralized system was been created on the Scilab/Xcos platform using a pre-built library of blocks for simulating decentralized systems. The scenarios differ depending on the structure of the neural coordinators: a segmented network according to the structure of the coordinator simulation model or an integrated one, as well as on the training strategy: train all the coordinators of the decentralized system in parallel or only one coordinator and then clone the results. Experimental studies of the proposed method of training neural network coordinators, implemented on Python TensorFlow, were conducted. The study showed greater effectiveness of segmented coordinators parallel training. However, in the course of the study, the last step of the scenarios – fine tuning on a real physical object, was not performed. A preliminary evaluation suggests that after such additional training, the advantages of mono-neural coordinators will become more visible, since such additional training will correct the shortcomings of imitation.
References
Aghdam A.G., Miller D.E., & Davison E.J. (2019). Decentralized Control of Large-Scale Systems, Springer, ISBN/EAN: 9781441960146.
Akramizadeh, A., Afshar, A., B Menhaj, M., & Jafari, S. (2010). Model-based Reinforcement Learning in Multiagent Systems in Extensive Forms with Perfect Information. IFAC Proceedings Volumes, Vol. 43, Issue 8, pp. 487–494. Elsevier BV. https://doi.org/10.3182/20100712-3-fr-2020.00080
Bakule, L. (2008). Decentralized control: An overview. Annu. Rev. Control., 32, pp. 87-98. [Online]. Available: https://api.semanticscholar.org/CorpusID:205659095.
Boyd, S., El Ghaoui, L., Feron, E., & Balakrishnan, V. (1994). Linear Matrix Inequalities in System and Control Theory. Society for Industrial and Applied Mathematics. SIAM, Philadelphia, 1994. https://doi.org/10.1137/1.9781611970777
Coordination Control of Distributed Systems. (2015). In J. H. van Schuppen & T. Villa (Eds.), Lecture Notes in Control and Information Sciences. Springer International Publishing. https://doi.org/10.1007/978-3-319-10407-2
Dubovoi V.M. & Yukhymchuk M.S. (2022). Decentralized coordination control of distributed cyber-physical systems with continuous objects, VNTU, Vinnytsia. [in Ukrainian]
Elmahdi, A., Taha, A. F., Sun, D., & Panchal, J. H. (2015). Decentralized Control Framework and Stability Analysis for Networked Control Systems. Journal of Dynamic Systems Measurement and Control, vol. 137. doi: 10.1115/1.4028789.
Ge, X., Han, Q.-L., Ding, L., Wang, Y.-L. & Zhang, X.-M. (2020). Dynamic Event-Triggered Distributed Coordination Control and its Applications: A Survey of Trends and Techniques. IEEE Transactions on Systems, Man, and Cybernetics: Systems. Vol. 50, Number 9, pp. 3112–3125. https://doi.org/10.1109/tsmc.2020.3010825
Gong Z. & Aldeen M. (1997). Stabilization of Decentralized Control Systems, Journal of Mathematical Systems, Estimation, and Control, Vol. 7, No. 1, pp. 1–16,
Jiang, H., Liu, X.-K., He, H., Yuan, C., & Prokhorov, D. (2018). Neural Network Based Distributed Consensus Control for Heterogeneous Multi-agent Systems. In 2018 Annual American Control Conference (ACC). 2018 Annual American Control Conference (ACC). IEEE. pp. 5175–5180. https://doi.org/10.23919/acc.2018.8431744
Katrenko, A.V., & Savka I.V., (2008). Mechanisms of coordination in complex hierarchical systems. Bulletin of Lviv Polytechnic National University . Vol. 631, pp. 156–166. [Online]. Available: http://vlp.com.ua/files/16_1.pdf. [in Ukrainian]
Ladanyuk, A., Shumygai, D. & Boiko, R. (2012). System task of co-ordination in the technological complexes of continuous type. Collected Works of Kirovohrad National Technical University Machinery in agricultural production, industry machine building, automation. Vol. 25-1. pp. 288-294. [Online]. Available: http://dspace.nuft.edu.ua/jspui/bitstream/123456789/4444/1/Sh_3.pdf. [in Ukrainian]
Mirkin B.M. (1992). A new decentralized model reference adaptive control scheme for large scale systems. in Prepr. 4th IFAC International Symposium on Adaptive systems in control and signal processing, Grenoble, France, pp. 645–650.
Shaikh P.H., Nor.B.M., Nallagownden P., Elamvazuthi I., & Ibrahim T. (2014). A Review on Optimized Control Systems for Building Energy and Comfort Control of Smart Sustainable Buildings. Renewable and Sustainable Energy Reviews, Vol. 34, pp. 409–429. https://doi.org/10.1016/j.rser.2014.03.027.
Šiljak, D.D., & Stipanović, D.M. (2000). Robust stabilization of nonlinear systems: The LMI approach. Mathematical Problems in Engineering, vol. 6, pp. 461–493.
Wang, X., Zhang, Z., & Zhang, W. (2022). Model-based Multi-agent Reinforcement Learning: Recent Progress and Prospects (Version 1). arXiv. https://doi.org/10.48550/ARXIV.2203.10603
Yukhymchuk, M., Dubovoi, V., & Kovtun, V. (2022). Decentralized Coordination of Temperature Control in Multiarea Premises. Complexity, vol. 2022, Article ID 2588364. https://doi.org/10.1155/2022/2588364.
Zabet I. & Montazeri M. (2010). Decentralized control and control systems for power industry via multiagent systems technology, in PEOCO 2010 - 4th International Power Engineering and Optimization Conference, Program and Abstracts, pp. 549–556, IEEE. doi: 10.1109/PEOCO.2010.5559254.
Zhang, W., Wang, X., Shen, J., & Zhou, M. (2021). Model-based Multi-agent Policy Optimization with Adaptive Opponent-wise Rollouts (Version 3). arXiv. https://doi.org/10.48550/ARXIV.2105.03363.
Downloads
-
PDF
Downloads: 6
