Abstract
Machine learning (ML) methods are applied to optimal resource control for Network Powered by Computing Infrastructure (NPC)—a new generation computing infrastructure. The relation between the proposed computing infrastructure and the GRID concept is considered. It is shown how ML methods applied to computing infrastructure control make it possible to solve the problems of computing infrastructure control that did not allow the GRID concept to be implemented in full force. As an example, the application of multi-agent optimization methods with reinforcement learning for network resource management is considered. It is shown that multi-agent ML methods increase the speed of distribution of transport flows and ensure optimal NPC network channel load based on uniform load balancing; moreover, such control of network resources is more effective than a centralized approach.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
REFERENCES
R. Smeliansky, “Hierarchical edge computing,” International Conference on Modern Network Technologies, MoNeTec-2018 (Moscow, 2018), pp. 97–105.
R. Smeliansky et al., “On HPC and cloud environments integration,” in Performance Evaluation Models for Distributed Service Networks (Springer Nature, Cham, 2020), Ch. 1.
R. Smeliansky, “Network powered by computing: Next generation of computational infrastructure,” in Edge Computing—Technology, Management and Integration (IntechOpen, 2023), pp. 47–70.
Topology and Orchestration Specification for Cloud Applications. http://docs.oasis-open.org/tosca/TOSCA/v1.0/os/ TOSCA-v1.0-os.html. Accessed March 19, 2024.
"What is serverless computing?" ITPro Today, Dec. 13 (2021). https://www.itprotoday.com/serverless-computing/what-serverless-computing. Accessed March 19, 2024.
I. Foster and. C. Kesselman, The Grid 2: Blueprint for a New Computing Infrastructure (Elsevier, Amsterdam, 2003).
I. Foster and. C. Kesselman, “The history of the grid,” arXiv preprint arXiv:2204.04312 (2022).
Year on Year Performance. https://www.cpubenchmark.net/year-on-year.html. Accessed March 19, 2024.
Charted: The Exponential Growth in AI Computation. https://www.visualcapitalist.com/cp/charted-history-exponential-growth-in-ai-computation/. Accessed March 19, 2024.
“Data transmission: Fantastic rates and new methods,” Yota4All. https://habr.com/ru/companies/yota/articles/283220/. Accessed March 19, 2024.
N. N. Moiseev, Yu. P. Ivanilov, and E. M. Stolyarova, Optimization Methods (Nauka, Moscow, 1978) [in Russian].
S. P. Karimireddy et al. “SCAFFOLD: Stochastic controlled averaging for federated learning,” International Conference on Machine Learning (PMLR, 2020).
T. Vogels, S. P. Karimireddy, and M. Jaggi, “PowerSGD: Practical low-rank gradient compression for distributed optimization,” Advances in Neural Information Processing Systems (2019).
I. Oseledets and E. Tyrtyshnikov, “TT-cross approximation for multidimensional arrays,” Linear Algebra Appl. 432 (1), 70–88 (2010).
J. Gusak et al., “Automated multi-stage compression of neural networks,” in Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (2019).
A. Novikov et al., “Tensorizing neural networks,” Advances in Neural Information Processing Systems (2015), Vol. 28.
Y. Gong et al., “ETTE: Efficient tensor-train-based computing engine for deep neural networks,” Proceedings of the 50th Annual International Symposium on Computer Architecture (2023), pp. 1–13.
R. L. Smeliansky and V. A. Antonenko, Concepts of Software Management and Virtualization of Network Services in Modern Data Transmission Networks (Kurs, Moscow, 2019) [in Russian].
B. Guillermo et al., “Is machine learning ready for traffic engineering optimization?,” 2021 IEEE 29th International Conference on Network Protocols (ICNP) (IEEE, 2021).
Y. Xinyu et al., “Toward packet routing with fully distributed multiagent deep reinforcement learning,” IEEE Transactions on Systems, Man, and Cybernetics: Systems 52 .2 (2020), pp. 855–868.
M. Xuan, Q. Fu, and Y. Chen, “Packet routing with graph attention multi-agent reinforcement learning,” 2021 IEEE Global Communications Conference (GLOBECOM) (IEEE, 2021).
E. Stepanov et al., “On fair traffic allocation and efficient utilization of network resources based on MARL.” https://www.researchgate.net/publication/371166584_On_Fair_Traffic_allocation_and_Efficient_Utilization_of_Network_Resources_based_ on_MARL. Accessed November 14, 2023.
ECMP Load Balancing. https://www.cisco.com/c/en/us/td/docs/ios-xml/ios/ mp_l3_vpns/configuration/xe-3s/asr903/mp-l3-vpns-xe-3s-asr903-book/mp-l3-vpns-xe-3s-asr903-book_c hapter_0100.pdf. Accessed November 14, 2023.
UCMP Load Balancing. https://www.cisco.com/c/en/us/td/docs/ios-xml/ios/mp_l3_vpns/configuration/xe-3s/asr903/17-1-1/b-mpls-l3-vpns-xe-17-1-asr900/m-ucmp.pdf. Accessed November 14, 2023.
ACKNOWLEDGMENTS
The authors are grateful to Academician of the RAS E.E. Tyrtyshnikov and Associate Professor S.A. Matveev for their consultations concerning recent advances in mathematical methods for matrix factorization and representation and to Professor A.I. Gasnikov and Associate Professor A.N. Beznosikov for their consultations on recent advances in mathematical methods for distributed optimization.
Funding
This work was supported by the Program of Development of Moscow State University, project no. 23-Sh03-03.
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
The authors of this work declare that they have no conflicts of interest.
Additional information
Translated by I. Ruzanova
Publisher’s Note.
Pleiades Publishing remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Smeliansky, R.L., Stepanov, E.P. Machine Learning to Control Network Powered by Computing Infrastructure. Dokl. Math. 109, 183–190 (2024). https://doi.org/10.1134/S106456242470193X
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S106456242470193X