TY - GEN
T1 - Network Service Embedding in Multiple Edge Systems
T2 - 2021 IEEE International Conference on Communications, ICC 2021
AU - Tai, Yu Chen
AU - Yen, Li-Hsing
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/6
Y1 - 2021/6
N2 - A service chain (SC) comprises a series of service functions realized as virtualized network functions (VNFs). Each VNF has specific resource, bandwidth, and location requirements. This study assumes multiple SCs to be placed on geo-distributed heterogeneous edge servers owned by multiple edge service providers (ESPs). Each ESP selectively hosts SCs to earn profit. We consider the problem to maximize the total profit (i.e., social welfare) of all ESPs by organizing ESPs into a set of disjoint federations called federation structure. We formulate the problem of finding an optimal federation structure, identify the difficulties in solving the problem, and present two time-efficient heuristics as our approach. Simulation results show that elaborate federation structures do bring in higher social welfare compared with simple all-in or all-out ESP organization. The proposed heuristics can also approximate the optimal result in many cases.
AB - A service chain (SC) comprises a series of service functions realized as virtualized network functions (VNFs). Each VNF has specific resource, bandwidth, and location requirements. This study assumes multiple SCs to be placed on geo-distributed heterogeneous edge servers owned by multiple edge service providers (ESPs). Each ESP selectively hosts SCs to earn profit. We consider the problem to maximize the total profit (i.e., social welfare) of all ESPs by organizing ESPs into a set of disjoint federations called federation structure. We formulate the problem of finding an optimal federation structure, identify the difficulties in solving the problem, and present two time-efficient heuristics as our approach. Simulation results show that elaborate federation structures do bring in higher social welfare compared with simple all-in or all-out ESP organization. The proposed heuristics can also approximate the optimal result in many cases.
UR - http://www.scopus.com/inward/record.url?scp=85115696149&partnerID=8YFLogxK
U2 - 10.1109/ICC42927.2021.9500607
DO - 10.1109/ICC42927.2021.9500607
M3 - Conference contribution
AN - SCOPUS:85115696149
T3 - IEEE International Conference on Communications
BT - ICC 2021 - IEEE International Conference on Communications, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 14 June 2021 through 23 June 2021
ER -