|
Abstract.
Resource allocation directly affects the performance of computing systems, taking into account operating conditions and parametric constraints. The task to be solved in this article is to develop a new method of resource allocation. The proposed method is based on resource allocation, taking into account statistics on the performance of tasks with similar parameters. The object of research is computing systems with nodes of varying performance that process sets of tasks of varying complexity. The subject of the research is models and algorithms for the implementation of the proposed predictive method of resource allocation. The purpose of the work is to increase the efficiency of computer systems. A review and analysis of known methods of resource allocation, their advantages and disadvantages is performed. A method for allocating computing system resources with a predictive component is proposed. Analytical and simulation models have been developed to take into account the calculated and statistical performance of nodes. The research results can be used to build adaptive task allocation systems in modern computing systems.
Keywords:
computing system, resource allocation methods, modelling, load forecasting, statistical data.
DOI 10.14357/20718632260112
EDN TTXDFB
PP. 133-144.
References
1. J. Hoozemans, J. Peltenburg, F. Nonnemacher, A. Hadnagy, Z. Al-Ars, H. P. Hofstee. FPGA Acceleration for Big Data Analytics: Challenges and Opportunities. IEEE Circuits and Systems Magazine. 2021;21(2):30-47. DOI:10.1109/MCAS.2021.3071608. Available from: https://doi.org/10.1109/MCAS.2021.3071608 [Accessed 01 Jun 2025]. 2. Huang, Z., Kuang, Z., Xu, B. et al. Dependency-aware task collaborative offloading and resource allocation in UAV enabled edge computing. Peer-to-Peer Networking and Applications. 2025;18(118):19. DOI 10.1007/s12083-025-01903-2. Available from: https://doi.org/10.1007/s12083-025-01903-2 [Accessed 01 Jun 2025]. 3. Sokolov A. M., Larionov A. A., Vishnevsky V. M., Mukhtarov A. A. Architecture of a distributed system for stream computing with containerization and prioritization of tasks. Informacionny`e texnologii i vy`chislitel`ny`esistemy`. 2023;(4):5-18. (In Russ.). Available from: https://doi.org/10.14357/20718632230401 [Accessed 01 Jun 2025]. 4. Trushkin E.S., Gavrilov A.V., Freyman V.I. Mathematic and simulation modeling for performance assessment of communication devices into computing, information and control and telecommunication systems. Vestnik Permskogo natsionalnogo issledovatelskogo politekhnicheskogo universiteta. Elektrotekhnika, informatsionnie tekhnologii, sistemi upravleniya. 2025;(53):129-156. (In Russ.). DOI 10.15593/2224-9397/2025.1.07. EDN WJQJWL. 5. Saidi, K., Bardou, D. Task scheduling and VM placement to resource allocation in Cloud computing: challenges and opportunities. Cluster Computing. 2023;(26):3069-3087. Available from: https://doi.org/10.1007/s10586-023-04098-4 [Accessed 01 Jun 2025]. 6. Kleiman L.A., Freyman V.I. The method of dynamic distribution of the diagnostic load between information and control systems elements. Proceedings of the 2021 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering. 26-29 Jan, 2021, St. Petersburg, Moscow, Russia. P. 952-955. Available from: https://doi.org/10.1109/ElConRus51938.2021.9396552 [Accessed 03 Jun 2025]. 7. Baranova T.P., Bugerya A.B., Efimkin K.N. Method of balancing the computational load for hybrid computing systems. E`lektronny`e biblioteki. 2021;24(1):42-56. (In Russ.). Available from: https://doi.org/10.26907/1562-5419-2021-24-1-42-56 [Accessed 03 Jun 2025]. 8. Li, J. Distributed data processing and task scheduling based on GPU parallel computing. Neural Comput & Applic. 2025;(37):1757–1769. Available from: https://doi.org/10.1007/s00521-024-10489-4 [Accessed 03 Jun 2025]. 9. Tanenbaum E., Steen M. Raspredelenny`e sistemy`: principy` i paradigmy` = Distributed Systems: Principles and Paradigms. Moscow: DMK Press, 2021. 586 p. (In Russ.). 10. Lyashov E.I. Resource-efficient algorithms for load balancing in distributed microservice architectures. Vestnik nauki. 2025;2(83):629-647. (In Russ.). Available from: https://doi.org/10.24412/2712-8849-2025-283-629-647 [Accessed 03 Jun 2025]. 11. Cao, X., Chen, C., Li, S. et al. Research on computing task scheduling method for distributed heterogeneous parallel systems. Scientific Reports. 2025;15(8937). Available from: https://doi.org/10.1038/s41598-025-94068-0 [Accessed 03 Jun 2025]. 12. Hwang K., Dongarra J. Distributed and Cloud Computing: From Parallel Processing to the Internet of Things. – Elsevier, 2012. 623 p. 13. Bo Tian, M. A. Posypkin, I. Kh. Sigal, Load balancing based on estimates of the algorithmic complexity of subtasks. Informacionny`e texnologii i vy`chislitel`ny`e sistemy`. 2015;(1):10-18. (In Russ.). Available from: http://www.jitcs.ru/index.php?option=com_content&view=article&id=477 [Accessed 04 Jun 2025]. 14. Kousik D., Brototi M., Paramartha D., Jyotsna K. M., Santanu D. A Genetic Algorithm (GA) based Load Balancing Strategy for Cloud Computing. Procedia Technology. 2013;(10):340-347. Available from: https://doi.org/10.1016/j.protcy.2013.12.369 [Accessed 04 Jun 2025]. 15. Moly M.I. Load Balancing Approach and Algorithm in Cloud Computing Environment. American Journal of Engineering Research. 2019;8(4):99-105. Available from: https://www.ajer.org/papers/Vol-8-issue-4/L080499105.pdf [Accessed 04 Jun 2025]. 16. Chandra W., Rita W., Chin-Yin H., Jodi T., Chao-Tung Y. Load Balancing Algorithm in a Software-Defined Network Environment with Round Robin and Least Connections. Smart Grid and Internet of Things. 2023;(557):148-157. Taiwan, Nov. 18-19, 2023. Available from: https://doi.org/10.1007/978-3-031-55976-1_15 [Accessed 04 Jun 2025]. 17. Hulin Jin, Yong Guk Kim, Zhiran Jin, Chunyang Fan, Yonglong Xu. Joint Task Ofoading Based on Distributed Deep Reinforcement Learning Based Genetic Optimization Algorithm for Internet of Vehicles. Journal of Grid Computing. 2024;22(34). Available from: https://doi.org/10.1007/s10723-024-09741-x [Accessed 07 Jun 2025]. 18. Arun K., Nishant G., Aziz N. Bi-LSTM Based Deep Learning Algorithm for NOMA-MIMO Signal Detection System. National Academy Science Letters. 2025;(48):541-544. Available from: https://doi.org/10.1007/s40009-024-01516-y [Accessed 07 Jun 2025]. 19. Yuqing Cheng, Zhiying Cao, Xiuguo Zhang, Qilei Cao, Dezhen Zhang. Multi objective dynamic task scheduling optimization algorithm based on deep reinforcement learning. The Journal of Supercomputing. 2023;(80):6917-6945. Available from: https://doi.org/10.1007/s11227-023-05714-1 [Accessed 07 Jun 2025].
|
