TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Peer to Peer Offloading with Delayed Feedback: An Adversary Bandit Approach

Tutkimustuotosvertaisarvioitu

Standard

Peer to Peer Offloading with Delayed Feedback : An Adversary Bandit Approach. / Yang, Miao; Zhu, Hongbin; Wang, Haifeng; Koucheryavy, Yevgeni; Samouylov, Konstantin; Qian, Hua.

2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings. IEEE, 2020. s. 5035-5039 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vuosikerta 2020-May).

Tutkimustuotosvertaisarvioitu

Harvard

Yang, M, Zhu, H, Wang, H, Koucheryavy, Y, Samouylov, K & Qian, H 2020, Peer to Peer Offloading with Delayed Feedback: An Adversary Bandit Approach. julkaisussa 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, Vuosikerta. 2020-May, IEEE, Sivut 5035-5039, Barcelona, Espanja, 4/05/20. https://doi.org/10.1109/ICASSP40776.2020.9053680

APA

Yang, M., Zhu, H., Wang, H., Koucheryavy, Y., Samouylov, K., & Qian, H. (2020). Peer to Peer Offloading with Delayed Feedback: An Adversary Bandit Approach. teoksessa 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings (Sivut 5035-5039). (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vuosikerta 2020-May). IEEE. https://doi.org/10.1109/ICASSP40776.2020.9053680

Vancouver

Yang M, Zhu H, Wang H, Koucheryavy Y, Samouylov K, Qian H. Peer to Peer Offloading with Delayed Feedback: An Adversary Bandit Approach. julkaisussa 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings. IEEE. 2020. s. 5035-5039. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP40776.2020.9053680

Author

Yang, Miao ; Zhu, Hongbin ; Wang, Haifeng ; Koucheryavy, Yevgeni ; Samouylov, Konstantin ; Qian, Hua. / Peer to Peer Offloading with Delayed Feedback : An Adversary Bandit Approach. 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings. IEEE, 2020. Sivut 5035-5039 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

Bibtex - Lataa

@inproceedings{385fe5940e644aeda90c0afb3bff02ce,
title = "Peer to Peer Offloading with Delayed Feedback: An Adversary Bandit Approach",
abstract = "Fog computing brings computation and services to the edge of networks enabling real time applications. In order to provide satisfactory quality of experience, the latency of fog networks needs to be minimized. In this paper, we consider a peer computation offloading problem for a fog network with unknown dynamics. Peer competition occurs when different fog nodes offload tasks to the same peer FN. In this paper, the computation offloading problem is modeled as a sequential FN selection problem with delayed feedback. We construct an online learning policy based on the adversary multi-arm bandit framework to deal with peer competition and delayed feedback. Simulation results validate the effectiveness of the proposed policy.",
keywords = "adversary multi-arm bandit, delayed feed-back, Fog computing, reinforcement learning, task offloading",
author = "Miao Yang and Hongbin Zhu and Haifeng Wang and Yevgeni Koucheryavy and Konstantin Samouylov and Hua Qian",
year = "2020",
month = "5",
day = "1",
doi = "10.1109/ICASSP40776.2020.9053680",
language = "English",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "IEEE",
pages = "5035--5039",
booktitle = "2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings",

}

RIS (suitable for import to EndNote) - Lataa

TY - GEN

T1 - Peer to Peer Offloading with Delayed Feedback

T2 - An Adversary Bandit Approach

AU - Yang, Miao

AU - Zhu, Hongbin

AU - Wang, Haifeng

AU - Koucheryavy, Yevgeni

AU - Samouylov, Konstantin

AU - Qian, Hua

PY - 2020/5/1

Y1 - 2020/5/1

N2 - Fog computing brings computation and services to the edge of networks enabling real time applications. In order to provide satisfactory quality of experience, the latency of fog networks needs to be minimized. In this paper, we consider a peer computation offloading problem for a fog network with unknown dynamics. Peer competition occurs when different fog nodes offload tasks to the same peer FN. In this paper, the computation offloading problem is modeled as a sequential FN selection problem with delayed feedback. We construct an online learning policy based on the adversary multi-arm bandit framework to deal with peer competition and delayed feedback. Simulation results validate the effectiveness of the proposed policy.

AB - Fog computing brings computation and services to the edge of networks enabling real time applications. In order to provide satisfactory quality of experience, the latency of fog networks needs to be minimized. In this paper, we consider a peer computation offloading problem for a fog network with unknown dynamics. Peer competition occurs when different fog nodes offload tasks to the same peer FN. In this paper, the computation offloading problem is modeled as a sequential FN selection problem with delayed feedback. We construct an online learning policy based on the adversary multi-arm bandit framework to deal with peer competition and delayed feedback. Simulation results validate the effectiveness of the proposed policy.

KW - adversary multi-arm bandit

KW - delayed feed-back

KW - Fog computing

KW - reinforcement learning

KW - task offloading

U2 - 10.1109/ICASSP40776.2020.9053680

DO - 10.1109/ICASSP40776.2020.9053680

M3 - Conference contribution

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 5035

EP - 5039

BT - 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings

PB - IEEE

ER -