Keynote

Computing Centric Network — Next Generation Computing Infrastructure

Prof. Ruslan Smelyanskiy(Russia)

The architecture of next-generation computing infrastructure is presented, enabling the implementation of "computing on demand" services. A comparison is made with the GRID computing concept, highlighting the key challenges in its implementation. The necessity of applying machine learning methods to overcome these limitations through automated optimal decision-making is demonstrated. As a primary solution, a combination of software-defined networking (SDN), service virtualization, multi-agent optimization, and reinforcement learning is proposed. The novelty of this approach lies in self-organizing resource distribution without centralized control. Experiments show that the proposed method reduces task allocation time by 203020-30% compared to traditional approaches and ensures uniform channel utilization (load variation coefficient <15< 15%). Thus, the effectiveness of ML-based decentralized management is confirmed.

About the speaker

Ruslan Smelyanskiy avatar

Prof. Ruslan Smelyanskiy

Russia
  • Moscow State University,
    Computer Systems Department
    Professor

Smelyanskiy Ruslan L. – Corresponding Member Russian Academy of Science, Professor, Faculty of Computational Mathematics and Cybernetics, Moscow State University, Nationality: Russia.

Graduated Moscow State University, major – Applied Mathematics (1972-1977), Ph.D. school in 1980. Since 1980 as an assistant professor (1980-1987), associate professor (1987-1991), full professor (since 1991). Faculty of Computational Mathematics and Cybernetics (CMC www.cmc.msu.ru ). Since 2018 – Head of Computer Systems Department at Moscow State University.