Leonid Mokrushin

Leonid Mokrushin

Auto-generated profile, based on publicly available information

Leonid Mokrushin

Ericsson Research, Kista, Sweden

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 October 2023
Verified
Conference Paper
Open access
AKAjay Kattepur
Ajay Kattepur
SMSwarup Kumar Mohalik
Swarup Kumar Mohalik
IBIan Burdick
Ian Burdick
MOMarin Orlic
Marin Orlic
LMLeonid Mokrushin
Leonid Mokrushin
The emergence of 5G allows the network to be sliced to meet multiple service requirements. However, current design systems are policy-driven, which limits the ability to redesign the 5G network adaptively for requirements or traffic patterns. In this paper, we propose Conrad, an autonomous and intent-driven framework that can allocate resources efficiently to meet 5G slice requirements. Via the use of a cognitive intent handling engine, the requirements are transformed to goals that may be solved using machine reasoning techniques. Four agents are registered for forecasting, design planning, evaluation and actuation to enable dynamic re-design of the 5G slices. Exploiting automated planning techniques, proposals are provided to optimally provision the network slice resources. This process is demonstrated over a radio access network (RAN) slicing use case with intents on average expected throughput.

22 November 2023 in Journal of Integrated Design and Process Science
Verified
Journal Article
Closed access
ABAndrii Berezovskyi
Andrii Berezovskyi
LMLeonid Mokrushin
Leonid Mokrushin
FAFredrik Asplund
Fredrik Asplund
JEJad El-Khoury
Jad El-Khoury
RIRafia Inam
Rafia Inam
EFElena Fersman
Elena Fersman
An increase in size and complexity prompts research of autonomous control of connected cyber-physical systems (CPS) at the level of intents (high-level goals). Domain-specific solutions such as intent-based networking, and the next generation of supervisory control and data acquisition and manufacturing execution systems, were influenced by the concept of autonomic computing and Monitor-Analyze-Plan-Execute loops over shared knowledge to introduce such control. However, there is a dearth of knowledge concerning the architectural attributes required to enable autonomic computing at a domain-independent level. CPSs are also often contributed by multiple stakeholders, thereby forming systems of systems in which architectures are by necessity federated. Herein, we apply a systematic approach to develop a taxonomy of such attributes, considering the federated nature of architectures, the need to accommodate heterogeneity and the legacy systems commonly encountered in practice. The proposed taxonomy covers nine key dimensions present within different domains of autonomic computing: knowledge representation, learning, distribution, reactivity, environment observability, information acquisition automation, information analysis automation, decision selection automation, and action implementation automation. The utility of the taxonomy is further demonstrated through an application to architectures across domains and scales.