TY - JOUR
T1 - Cognitive Popularity Based AI Service Sharing for Software-Defined Information-Centric Networks
AU - Liao, Siyi
AU - Wu, Jun
AU - Li, Jianhua
AU - Bashir, Ali Kashif
AU - Mumtaz, Shahid
AU - Jolfaei, Alireza
AU - Kvedaraite, Nida
N1 - Funding Information:
Manuscript received January 1, 2020; revised March 13, 2020 and April 17, 2020; accepted April 23, 2020. Date of publication May 11, 2020; date of current version December 30, 2020. This work was supported in part by the National Natural Science Foundation of China under Grant 61972255. Recommended for acceptance by Dr. Huimin Lu. (Corresponding author: Jun Wu.) Siyi Liao, Jun Wu, and Jianhua Li are with the Shanghai Key Laboratory of Integrated Administration Technologies for Information Security, School of Cyber Security, Shanghai Jiao Tong University, Shanghai 200240, China (e-mail: syliao@sjtu.edu.cn; junwuhn@sjtu.edu.cn; lijh888@sjtu.edu.cn).
Publisher Copyright:
© 2013 IEEE.
PY - 2020/10/1
Y1 - 2020/10/1
N2 - As an important architecture of next-generation network, Software-Defined Information-Centric Networking (SD-ICN) enables flexible and fast content sharing in beyond the fifth-generation (B5G). The clear advantages of SD-ICN in fast and efficient content distribution and flexible control make it a perfect platform for solving the rapid sharing and cognitive caching of AI services, including data samples sharing and pre-Trained models transferring. With the explosive growth of decentralized artificial intelligence (AI) services, the training and sharing efficiency of edge AI is affected. Various applications usually request the same AI samples and training models, but the efficient and cognitive sharing of AI services remain unsolved. To address these issues, we propose a cognitive popularity-based AI service distribution architecture based on SD-ICN. First, an SD-ICN enabled edge training scheme is proposed to generate accurate AI service models over decentralized big data samples. Second, Pure Birth Process (PBP) and error correction-based AI service caching and distribution schemes are proposed, which provides user request-oriented cognitive popularity model for caching and distribution optimization. Simulation results indicate the superiority of the proposed architecture, and the proposed cognitive SD-ICN scheme has 62.11% improved to the conventional methods.
AB - As an important architecture of next-generation network, Software-Defined Information-Centric Networking (SD-ICN) enables flexible and fast content sharing in beyond the fifth-generation (B5G). The clear advantages of SD-ICN in fast and efficient content distribution and flexible control make it a perfect platform for solving the rapid sharing and cognitive caching of AI services, including data samples sharing and pre-Trained models transferring. With the explosive growth of decentralized artificial intelligence (AI) services, the training and sharing efficiency of edge AI is affected. Various applications usually request the same AI samples and training models, but the efficient and cognitive sharing of AI services remain unsolved. To address these issues, we propose a cognitive popularity-based AI service distribution architecture based on SD-ICN. First, an SD-ICN enabled edge training scheme is proposed to generate accurate AI service models over decentralized big data samples. Second, Pure Birth Process (PBP) and error correction-based AI service caching and distribution schemes are proposed, which provides user request-oriented cognitive popularity model for caching and distribution optimization. Simulation results indicate the superiority of the proposed architecture, and the proposed cognitive SD-ICN scheme has 62.11% improved to the conventional methods.
KW - Cognitive popularity
KW - decentralized big data
KW - service sharing.
KW - software defined information-centric network (SD-ICN)
UR - http://www.scopus.com/inward/record.url?scp=85087106078&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85087106078&partnerID=8YFLogxK
U2 - 10.1109/TNSE.2020.2993457
DO - 10.1109/TNSE.2020.2993457
M3 - Article
AN - SCOPUS:85087106078
SN - 2327-4697
VL - 7
SP - 2126
EP - 2136
JO - IEEE Transactions on Network Science and Engineering
JF - IEEE Transactions on Network Science and Engineering
IS - 4
M1 - 9091106
ER -