TY - JOUR
T1 - Self-adaptive online virtual network migration in network virtualization environments
AU - Zangiabady, Mahboobeh
AU - Garcia-Robledo, Alberto
AU - Gorricho, Juan Luis
AU - Serrat-Fernandez, Joan
AU - Rubio-Loyola, Javier
N1 - Funding Information:
This paper has been supported by the National Council of Research and Technology (CONACYT) through grant FONCICYT/272278 and by the ERANetLAC (Network of the European Union, Latin America, and the Caribbean Countries) through project ELAC2015/T100761. This paper is partially supported also by the MINECO/FEDER through project TEC2015-71329-C2-2-R and by the European Union's Horizon 2020 research and innovation programme through NECOS project under grant agreement no. 777067.
Publisher Copyright:
© 2019 John Wiley & Sons, Ltd.
PY - 2019/9/1
Y1 - 2019/9/1
N2 - In Network Virtualization Environments, the capability of operators to allocate resources in the Substrate Network (SN) to support Virtual Networks (VNs) in an optimal manner is known as Virtual Network Embedding (VNE). In the same context, online VN migration is the process meant to reallocate components of a VN, or even an entire VN among elements of the SN in real time and seamlessly to end-users. Online VNE without VN migration may lead to either over- or under-utilization of the SN resources. However, VN migration is challenging due to its computational cost and the service disruption inherent to VN components reallocation. Online VN migration can reduce migration costs insofar it is triggered proactively, not reactively, at critical times, avoiding the negative effects of both under- and over-triggering. This paper presents a novel online cost-efficient mechanism that self-adaptively learns the exact moments when triggering VN migration is likely to be profitable in the long term. We propose a novel self-adaptive mechanism based on Reinforcement Learning that determines the right trigger online VN migration times, leading to the minimization of migration costs while simultaneously considering the online VNE acceptance ratio.
AB - In Network Virtualization Environments, the capability of operators to allocate resources in the Substrate Network (SN) to support Virtual Networks (VNs) in an optimal manner is known as Virtual Network Embedding (VNE). In the same context, online VN migration is the process meant to reallocate components of a VN, or even an entire VN among elements of the SN in real time and seamlessly to end-users. Online VNE without VN migration may lead to either over- or under-utilization of the SN resources. However, VN migration is challenging due to its computational cost and the service disruption inherent to VN components reallocation. Online VN migration can reduce migration costs insofar it is triggered proactively, not reactively, at critical times, avoiding the negative effects of both under- and over-triggering. This paper presents a novel online cost-efficient mechanism that self-adaptively learns the exact moments when triggering VN migration is likely to be profitable in the long term. We propose a novel self-adaptive mechanism based on Reinforcement Learning that determines the right trigger online VN migration times, leading to the minimization of migration costs while simultaneously considering the online VNE acceptance ratio.
KW - n/a OA procedure
UR - http://www.scopus.com/inward/record.url?scp=85070226715&partnerID=8YFLogxK
U2 - 10.1002/ett.3692
DO - 10.1002/ett.3692
M3 - Article
AN - SCOPUS:85070226715
SN - 2161-5748
VL - 30
JO - Transactions on Emerging Telecommunications Technologies
JF - Transactions on Emerging Telecommunications Technologies
IS - 9
M1 - e3692
ER -