Abstract
Due to overlay technologies, service providers have a logical view of the underlay network and can optimize the experience quality without modifying the physical network. However, the cross-layer interaction inevitably causes network fluctuation due to their inconsistent optimization objectives. Aside from that, network failures that occur in both layers not only cause network performance degradation but also significantly increase the frequency of cross-layer interaction. These problems make the network fluctuate for a long time, reduce the network performance, and influence the user experience, especially for time-sensitive applications. In this paper, we design a cross-layer architecture in which the logical layer can satisfy the service function chain demands and maximize the user experience and physical layer so it can optimize the overall network performance. Our cross-layer architecture can make proactive corrections in both layers. Furthermore, we investigate the cross-layer interaction and design two strategies to eliminate fluctuations and make the network converge quickly.
Highlights
Related WorkThe Network function virtualization (NFV) framework has attracted a lot of attention, especially in the areas of virtual network functions (VNFs) deployment and service chain resiliency
These problems make the network fluctuate for a long time, reduce the network performance, and influence the user experience, especially for time-sensitive applications
We propose a cross-layer model between low-latency service (LLS) and segment routing with correction (SRC)
Summary
The NFV framework has attracted a lot of attention, especially in the areas of VNF deployment and service chain resiliency. The issues of efficient resource management of NFV, including VNF placement, resource allocation, and flow routing, have been extensively studied in the literature [9]. Fan et al [13] defined an optimal availability-aware SFC mapping problem and presented a novel online algorithm that can minimize physical resource consumption while guaranteeing the required high availability within a polynomial time. Fei et al [14] formulated the VNF provisioning problem so that the cost incurred by inaccurate prediction and VNF deployment would be minimized. Users using our architecture pay attention to how to meet their needs for the SFC and minimize the delay in their use of services. The tasks generated by the logical layer will have the physical layer to complete the transmission, regardless of the SFC requirements and delays
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.