TY - GEN
T1 - Users-Fogs association within a cache context in 5G networks:Coalition game model
AU - Abouaomar, Amine
AU - Elmachkour, Mouna
AU - Kobbane, Abdellatif
AU - Tembine, Hamidou
AU - Ayaida, Marwane
N1 - Funding Information:
ACKNOWLEDGEMENT This work was made possible by the C-Roads France project funded by the European Commission Grant No. 2015-FR-TM-0378-S from the INEA Agency within the 2015 CEF Transport Programme. The statements made herein are solely the responsibility of the authors.
Publisher Copyright:
© 2018 IEEE.
PY - 2018/11/15
Y1 - 2018/11/15
N2 - Content is not always about medias and files, computing tasks output are also a content that can be described, stored and cached. In this paper, we investigated the problem of edge computing and caching in the fog computing networks. In our scenario, we consider the user requests computing tasks from the fog, that the devices could not handle. Moreover, fogs use their storage and computing capabilities to cache the tasks computation results in order to minimize the latency, and use it storage to offload their resources by caching the significant computing tasks output. We propose a clustering method based on the correlation between the tasks and the cached content to decide what fog will give a better service in term of latency to offer better quality of service and experience. The problem of the users-fogs association was formulated as a coalition game between the users and the fogs. Finally, we use the BoltzmannGibbs learning algorithm to make every entity able to learn the best coalition, in order to enhance the convergence of the system to reach a better and optimal stability.
AB - Content is not always about medias and files, computing tasks output are also a content that can be described, stored and cached. In this paper, we investigated the problem of edge computing and caching in the fog computing networks. In our scenario, we consider the user requests computing tasks from the fog, that the devices could not handle. Moreover, fogs use their storage and computing capabilities to cache the tasks computation results in order to minimize the latency, and use it storage to offload their resources by caching the significant computing tasks output. We propose a clustering method based on the correlation between the tasks and the cached content to decide what fog will give a better service in term of latency to offer better quality of service and experience. The problem of the users-fogs association was formulated as a coalition game between the users and the fogs. Finally, we use the BoltzmannGibbs learning algorithm to make every entity able to learn the best coalition, in order to enhance the convergence of the system to reach a better and optimal stability.
KW - 5G
KW - Boltzmann-Gibbs
KW - Clustering
KW - Coalition games
KW - Fog computing
KW - Proactive
KW - tasks caching
UR - http://www.scopus.com/inward/record.url?scp=85059221795&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85059221795&partnerID=8YFLogxK
U2 - 10.1109/ISCC.2018.8538500
DO - 10.1109/ISCC.2018.8538500
M3 - Conference contribution
AN - SCOPUS:85059221795
T3 - Proceedings - IEEE Symposium on Computers and Communications
SP - 14
EP - 19
BT - 2018 IEEE Symposium on Computers and Communications, ISCC 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2018 IEEE Symposium on Computers and Communications, ISCC 2018
Y2 - 25 June 2018 through 28 June 2018
ER -