Alexey Zhilyaev

Mr. Alexey Zhilyaev

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
12 May 2022 in Mathematics
Verified
Journal Article
Open access
PDF file
VGVladimir Galuzin
Vladimir Galuzin
AGAnastasia Galitskaya
Anastasia Galitskaya
SGSergey Grachev
Sergey Grachev
VLVladimir Larukhin
Vladimir Larukhin
DNDmitry Novichkov
Dmitry Novichkov
AZAlexey Zhilyaev
Alexey Zhilyaev
Digital twins of complex technical objects are widely applied for various domains, rapidly becoming smart, cognitive and autonomous. However, the problem of digital twins for autonomous management of enterprise resources is still not fully researched. In this paper, an autonomous digital twin of enterprise is introduced to provide knowledge-based multi-agent adaptive allocation, scheduling, optimization, monitoring and control of tasks and resources in real time, synchronized with employees’ plans, preferences and competencies via mobile devices. The main requirements for adaptive resource management are analyzed. The authors propose formalized ontological and multi-agent models for developing the autonomous digital twin of enterprise. A method and software toolset for designing the autonomous digital twin of enterprise, applicable for both operational management of tasks and resources and what-if simulations, are developed. The validation of developed methods and toolsets for IT service desk has proved increase in efficiency, as well as savings in time and costs of deliveries for various applications. The paper also outlines a plan for future research, as well as a number of new potential business applications.

3 June 2022 in Mathematics
Verified
Journal Article
Open access
PDF file
GRGeorge Rzevski
George Rzevski
PSPetr Skobelev
Petr Skobelev
AZAlexey Zhilyaev
Alexey Zhilyaev
A new emergent intelligence approach to the design of smart ecosystems, based on the complexity science principles, is introduced and discussed. The smart ecosystem for resource management is defined as a system of autonomous decision-making multi-agent systems capable to allocate resources, plan orders for resources, and to optimize, coordinate, monitor, and control the execution of plans in real time. The emergent intelligence enables software agents to collectively resolve conflicts arising in resource management decisions by reaching a consensus through a process of detecting conflicts and negotiation for finding trade-offs. The key feature of the proposed approach is the ontological model of the enterprise and the method of collective decision-making by software agents that compete or cooperate with each other on the virtual market of the digital ecosystem. Emergent intelligent systems do not require extensive training using a large quantity of data, like conventional artificial intelligence/machine learning systems. The developed model, method, and tool were applied for managing the resources of a factory workshop, a group of small satellites, and some other applications. A comparison of the developed and traditional tools is given. The new metric for measuring the adaptability of emergent intelligence is introduced. The performance of the new model and method are validated by constructing and evaluating large-scale resource management solutions for commercial clients. As demonstrated, the essential benefit is the high adaptability and efficiency of the resource management systems when operating under complex and dynamic market conditions.

1 November 2021 in Automation and Remote Control
Verified
Journal Article
Closed access
PDF file
SGS. P. Grachev
S. P. Grachev
AZAlexey Zhilyaev
Alexey Zhilyaev
VLV. B. Laryukhin
V. B. Laryukhin
DND. E. Novichkov
D. E. Novichkov
VGV. A. Galuzin
V. A. Galuzin
PSPetr Skobelev
Petr Skobelev
We give the statement of the real-time adaptive enterprise resource management problem and provide examples of contemporary adaptive resource management problems in various fields of application, showing the dimension and other features of the problems being solved. Requirements for the solution of the problems under consideration are stated, and general principles improving the resource management adaptability are proposed. Existing approaches are briefly analyzed, and their limitations are highlighted. A new methodology for solving the problems under consideration is proposed, an overview of developments is given, and the first experience of applying this methodology to the creation of intelligent resource management systems is discussed. The possibility of solving extremely complex resource management problems is shown by means of a modified ontology-based concept of the network of needs and capacities. In the framework of this concept, the schedule is constructed as a “competitive equilibrium” in the virtual market of a unified multiagent system, tuned to a specific enterprise with the use of applied ontologies. An example of developing a prototype of an intelligent resource management system for a multisatellite Earth remote sensing constellation and the results of its experimental study are given. An approach to assessing the performance and efficiency of adaptive scheduling models and methods developed for real-time resource management is proposed. Prospects for further development of the approach to solving complex adaptive resource management problems are shown.