TY - JOUR
T1 - Cost-Efficient Service Function Chain Orchestration for Low-Latency Applications in NFV Networks
AU - Sun, Gang
AU - Zhu, Gungyang
AU - Liao, Dan
AU - Yu, Hongfang
AU - Du, Xiaojiang
AU - Guizani, Mohsen
N1 - Publisher Copyright:
© 2007-2012 IEEE.
PY - 2019/12
Y1 - 2019/12
N2 - With the popularization and development of cloud computing, network function virtualization and service function chain (SFC) provisioning have attracted increasing attention from researchers. Excellent and reliable network service is important for network development. Moreover, as the number of network users increases, network service construction costs become very high. Therefore, an efficient algorithm is necessary to provide an SFC with excellent performance and low resource costs. In this paper, we re-examine the problem of optimizing the deployment of an SFC to provide users with excellent and resource-saving network service. We propose a heuristic, closed-loop feedback (CLF) algorithm to find the shortest path to map an SFC. To solve the problem, we introduce and integrate a restricted Boltzmann machine and cross entropy to improve the performance of CLF. Simulation results demonstrate the excellent performance of CLF. The communication delay is reduced by approximately 20%, the accept ratio improves by approximately 15%, and the algorithm running time decreases by approximately 20%. In addition, the resource utilization ratio increases by approximately 15%, and the resource fragmentation ratio decreases by approximately 50%.
AB - With the popularization and development of cloud computing, network function virtualization and service function chain (SFC) provisioning have attracted increasing attention from researchers. Excellent and reliable network service is important for network development. Moreover, as the number of network users increases, network service construction costs become very high. Therefore, an efficient algorithm is necessary to provide an SFC with excellent performance and low resource costs. In this paper, we re-examine the problem of optimizing the deployment of an SFC to provide users with excellent and resource-saving network service. We propose a heuristic, closed-loop feedback (CLF) algorithm to find the shortest path to map an SFC. To solve the problem, we introduce and integrate a restricted Boltzmann machine and cross entropy to improve the performance of CLF. Simulation results demonstrate the excellent performance of CLF. The communication delay is reduced by approximately 20%, the accept ratio improves by approximately 15%, and the algorithm running time decreases by approximately 20%. In addition, the resource utilization ratio increases by approximately 15%, and the resource fragmentation ratio decreases by approximately 50%.
KW - Machine learning
KW - network function virtualization
KW - provisioning
KW - service function chain
UR - http://www.scopus.com/inward/record.url?scp=85058098033&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85058098033&partnerID=8YFLogxK
U2 - 10.1109/JSYST.2018.2879883
DO - 10.1109/JSYST.2018.2879883
M3 - Article
AN - SCOPUS:85058098033
SN - 1932-8184
VL - 13
SP - 3877
EP - 3888
JO - IEEE Systems Journal
JF - IEEE Systems Journal
IS - 4
M1 - 8565965
ER -