The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
MEC(Mobile Edge Computing)는 클라우드 기능을 네트워크 엣지로 마이그레이션해 낮은 지연 시간이 필요한 서비스를 제공하는 핵심 기술이다. 제한된 컴퓨팅 리소스를 가진 모바일 사용자가 작업을 MEC 서버로 오프로드할 때 무선 채널의 잠재적인 낮은 품질에 주목해야 합니다. 전송 신뢰성을 향상시키기 위해서는 현재 채널 품질과 자원 경합을 고려하여 MEC 서버에서 자원 할당을 수행해야 한다. 이러한 리소스 할당을 해결하기 위해 심층 강화 학습(DRL) 접근 방식을 사용하는 여러 작업이 있습니다. 그러나 이러한 접근 방식은 작업을 오프로드하는 고정된 수의 사용자를 고려하며 사용자 이동성으로 인해 사용자 수가 달라지는 상황을 가정하지 않습니다. 본 논문에서는 사용자 수가 변화하는 상황에서 MEC 서버의 자원 할당 문제를 해결하는 온라인 학습 모델인 DMRA-D(Deep Reinforcement Learning Model for MEC Resource Allocation with Dummy)를 제안한다. DMRA-D는 더미 상태/작업을 채택하여 상태/작업 표현을 유지합니다. 따라서 DMRA-D는 작업 중 사용자 수의 변화에 관계없이 하나의 모델을 계속해서 학습할 수 있습니다. 수치 결과에 따르면 DMRA-D는 사용자 수가 다양한 상황에서 학습을 계속하면서 작업 제출 성공률을 향상시키는 것으로 나타났습니다.
Kairi TOKUDA
Kyoto University
Takehiro SATO
Kyoto University
Eiji OKI
Kyoto University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Kairi TOKUDA, Takehiro SATO, Eiji OKI, "Resource Allocation for Mobile Edge Computing System Considering User Mobility with Deep Reinforcement Learning" in IEICE TRANSACTIONS on Communications,
vol. E107-B, no. 1, pp. 173-184, January 2024, doi: 10.1587/transcom.2023EBP3043.
Abstract: Mobile edge computing (MEC) is a key technology for providing services that require low latency by migrating cloud functions to the network edge. The potential low quality of the wireless channel should be noted when mobile users with limited computing resources offload tasks to an MEC server. To improve the transmission reliability, it is necessary to perform resource allocation in an MEC server, taking into account the current channel quality and the resource contention. There are several works that take a deep reinforcement learning (DRL) approach to address such resource allocation. However, these approaches consider a fixed number of users offloading their tasks, and do not assume a situation where the number of users varies due to user mobility. This paper proposes Deep reinforcement learning model for MEC Resource Allocation with Dummy (DMRA-D), an online learning model that addresses the resource allocation in an MEC server under the situation where the number of users varies. By adopting dummy state/action, DMRA-D keeps the state/action representation. Therefore, DMRA-D can continue to learn one model regardless of variation in the number of users during the operation. Numerical results show that DMRA-D improves the success rate of task submission while continuing learning under the situation where the number of users varies.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2023EBP3043/_p
부
@ARTICLE{e107-b_1_173,
author={Kairi TOKUDA, Takehiro SATO, Eiji OKI, },
journal={IEICE TRANSACTIONS on Communications},
title={Resource Allocation for Mobile Edge Computing System Considering User Mobility with Deep Reinforcement Learning},
year={2024},
volume={E107-B},
number={1},
pages={173-184},
abstract={Mobile edge computing (MEC) is a key technology for providing services that require low latency by migrating cloud functions to the network edge. The potential low quality of the wireless channel should be noted when mobile users with limited computing resources offload tasks to an MEC server. To improve the transmission reliability, it is necessary to perform resource allocation in an MEC server, taking into account the current channel quality and the resource contention. There are several works that take a deep reinforcement learning (DRL) approach to address such resource allocation. However, these approaches consider a fixed number of users offloading their tasks, and do not assume a situation where the number of users varies due to user mobility. This paper proposes Deep reinforcement learning model for MEC Resource Allocation with Dummy (DMRA-D), an online learning model that addresses the resource allocation in an MEC server under the situation where the number of users varies. By adopting dummy state/action, DMRA-D keeps the state/action representation. Therefore, DMRA-D can continue to learn one model regardless of variation in the number of users during the operation. Numerical results show that DMRA-D improves the success rate of task submission while continuing learning under the situation where the number of users varies.},
keywords={},
doi={10.1587/transcom.2023EBP3043},
ISSN={1745-1345},
month={January},}
부
TY - JOUR
TI - Resource Allocation for Mobile Edge Computing System Considering User Mobility with Deep Reinforcement Learning
T2 - IEICE TRANSACTIONS on Communications
SP - 173
EP - 184
AU - Kairi TOKUDA
AU - Takehiro SATO
AU - Eiji OKI
PY - 2024
DO - 10.1587/transcom.2023EBP3043
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E107-B
IS - 1
JA - IEICE TRANSACTIONS on Communications
Y1 - January 2024
AB - Mobile edge computing (MEC) is a key technology for providing services that require low latency by migrating cloud functions to the network edge. The potential low quality of the wireless channel should be noted when mobile users with limited computing resources offload tasks to an MEC server. To improve the transmission reliability, it is necessary to perform resource allocation in an MEC server, taking into account the current channel quality and the resource contention. There are several works that take a deep reinforcement learning (DRL) approach to address such resource allocation. However, these approaches consider a fixed number of users offloading their tasks, and do not assume a situation where the number of users varies due to user mobility. This paper proposes Deep reinforcement learning model for MEC Resource Allocation with Dummy (DMRA-D), an online learning model that addresses the resource allocation in an MEC server under the situation where the number of users varies. By adopting dummy state/action, DMRA-D keeps the state/action representation. Therefore, DMRA-D can continue to learn one model regardless of variation in the number of users during the operation. Numerical results show that DMRA-D improves the success rate of task submission while continuing learning under the situation where the number of users varies.
ER -