Standard

Accelerated Decentralized Load Balancing in Multi-Agent Networks. / Erofeeva, V.; Granichin, O.; Volodina, E.

In: IEEE Access, Vol. 12, 2024, p. 161954-161967.

Research output: Contribution to journalArticlepeer-review

Harvard

APA

Vancouver

Author

Erofeeva, V. ; Granichin, O. ; Volodina, E. / Accelerated Decentralized Load Balancing in Multi-Agent Networks. In: IEEE Access. 2024 ; Vol. 12. pp. 161954-161967.

BibTeX

@article{1c39021300c646e5adf8357b79dc9f1c,
title = "Accelerated Decentralized Load Balancing in Multi-Agent Networks",
abstract = "Decentralized load balancers are gaining in popularity because they offer scalability, resilience, and the ability to handle high-demand workloads in distributed network systems. In practice, decentralized algorithms face such network issues as connection losses, dropped packets during data transmission, network latency. They should also account for the physical limitations of real systems. Existing works primarily consider different meta-heuristic approaches to carry out load balancing. Nevertheless, theoretically grounded algorithms that work under non-stationary conditions are of interest. In this paper, we improve the convergence rate of an existing decentralized load balancing protocol based on Local Voting Protocol (LVP) to obtain a solution that tends towards the optimal load balancing strategy over time. We propose a new Accelerated-LVP protocol and derive its parameters required to achieve the acceleration. The simulation demonstrates superiority of the proposed solution over the existing approaches in terms of convergence rate. In our experiments, we consider two scenarios: steady and bursty. In the first scenario, we observe that, on average, the proposed algorithm achieves the lowest error rate 15% faster than the nearest competitor. In the second scenario, on average, the proposed algorithm achieves an error rate that is 10% less than the nearest competitor. {\textcopyright} 2013 IEEE.",
keywords = "accelerated algorithms, decentralized networks, Load balancing, Local Voting Protocol, multi-agent systems, network disruptions, non-stationary optimization, Accelerated algorithm, Convergence rates, Decentralised, Decentralized networks, Load-Balancing, Local voting protocol, Multiagent systems (MASs), Network disruptions, Non-stationary optimization, Voting protocols",
author = "V. Erofeeva and O. Granichin and E. Volodina",
note = "Export Date: 18 November 2024 Сведения о финансировании: Government Council on Grants, Russian Federation, 000000D730324P540002, 70-2024-000120 Сведения о финансировании: Government Council on Grants, Russian Federation Текст о финансировании 1: The research was carried out within the financial support for the autonomous non-profit organization \u201CAnalytical Center for the Government of the Russian Federation\u201D (Agreement No. 70-2024-000120 dated March 29, 2024, id: 000000D730324P540002).",
year = "2024",
doi = "10.1109/access.2024.3488399",
language = "Английский",
volume = "12",
pages = "161954--161967",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

RIS

TY - JOUR

T1 - Accelerated Decentralized Load Balancing in Multi-Agent Networks

AU - Erofeeva, V.

AU - Granichin, O.

AU - Volodina, E.

N1 - Export Date: 18 November 2024 Сведения о финансировании: Government Council on Grants, Russian Federation, 000000D730324P540002, 70-2024-000120 Сведения о финансировании: Government Council on Grants, Russian Federation Текст о финансировании 1: The research was carried out within the financial support for the autonomous non-profit organization \u201CAnalytical Center for the Government of the Russian Federation\u201D (Agreement No. 70-2024-000120 dated March 29, 2024, id: 000000D730324P540002).

PY - 2024

Y1 - 2024

N2 - Decentralized load balancers are gaining in popularity because they offer scalability, resilience, and the ability to handle high-demand workloads in distributed network systems. In practice, decentralized algorithms face such network issues as connection losses, dropped packets during data transmission, network latency. They should also account for the physical limitations of real systems. Existing works primarily consider different meta-heuristic approaches to carry out load balancing. Nevertheless, theoretically grounded algorithms that work under non-stationary conditions are of interest. In this paper, we improve the convergence rate of an existing decentralized load balancing protocol based on Local Voting Protocol (LVP) to obtain a solution that tends towards the optimal load balancing strategy over time. We propose a new Accelerated-LVP protocol and derive its parameters required to achieve the acceleration. The simulation demonstrates superiority of the proposed solution over the existing approaches in terms of convergence rate. In our experiments, we consider two scenarios: steady and bursty. In the first scenario, we observe that, on average, the proposed algorithm achieves the lowest error rate 15% faster than the nearest competitor. In the second scenario, on average, the proposed algorithm achieves an error rate that is 10% less than the nearest competitor. © 2013 IEEE.

AB - Decentralized load balancers are gaining in popularity because they offer scalability, resilience, and the ability to handle high-demand workloads in distributed network systems. In practice, decentralized algorithms face such network issues as connection losses, dropped packets during data transmission, network latency. They should also account for the physical limitations of real systems. Existing works primarily consider different meta-heuristic approaches to carry out load balancing. Nevertheless, theoretically grounded algorithms that work under non-stationary conditions are of interest. In this paper, we improve the convergence rate of an existing decentralized load balancing protocol based on Local Voting Protocol (LVP) to obtain a solution that tends towards the optimal load balancing strategy over time. We propose a new Accelerated-LVP protocol and derive its parameters required to achieve the acceleration. The simulation demonstrates superiority of the proposed solution over the existing approaches in terms of convergence rate. In our experiments, we consider two scenarios: steady and bursty. In the first scenario, we observe that, on average, the proposed algorithm achieves the lowest error rate 15% faster than the nearest competitor. In the second scenario, on average, the proposed algorithm achieves an error rate that is 10% less than the nearest competitor. © 2013 IEEE.

KW - accelerated algorithms

KW - decentralized networks

KW - Load balancing

KW - Local Voting Protocol

KW - multi-agent systems

KW - network disruptions

KW - non-stationary optimization

KW - Accelerated algorithm

KW - Convergence rates

KW - Decentralised

KW - Decentralized networks

KW - Load-Balancing

KW - Local voting protocol

KW - Multiagent systems (MASs)

KW - Network disruptions

KW - Non-stationary optimization

KW - Voting protocols

UR - https://www.mendeley.com/catalogue/712fff2d-beb9-3dd8-ba88-e986647c2a22/

U2 - 10.1109/access.2024.3488399

DO - 10.1109/access.2024.3488399

M3 - статья

VL - 12

SP - 161954

EP - 161967

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

ER -

ID: 127409083