Title :
Joint allocation and scheduling of network resource for multiple control applications in SDN
Author :
Tao Feng ; Jun Bi ; Ke Wang
Author_Institution :
Inst. for Network Sci. & Cyberspace, Tsinghua Univ., Beijing, China
Abstract :
The network resource allocation in SDN for control applications is becoming a key problem in the near future because of the conflict between the need of the flow-level flexibility control and the limited capacity of flow table. Based on the analysis of the difference of the definition of network resource between SDN and traditional IP network, the idea of the integrated allocation of link bandwidth and flow table for multiple control applications in SDN is proposed in this paper. Furthermore, a price-based joint allocation model of network resource in SDN is built by introducing the price for each of the resources, which can get the proportional fair allocation of link bandwidth and the minimum global delay at the same time. We have also designed a popular flow scheduling policy based on the proportional fair allocation of link bandwidth in order to achieve the minimum global delay. A flow scheduling module has been implemented and evaluated in Floodlight, named virtual forwarding space (VFS). VFS can not only implement the fair allocation of link bandwidth and minimum delay flow scheduling in data plane but also accelerate packet forwarding by looking up flow cache in control plane.
Keywords :
bandwidth allocation; computer networks; resource allocation; telecommunication control; SDN; flow level flexibility control; flow scheduling policy; looking up flow cache; minimum global delay; multiple control applications; packet forwarding; price based joint allocation model; proportional fair link bandwidth allocation; resource allocation; resource scheduling; software defined networking; traditional IP network; virtual forwarding space; Bandwidth; Channel allocation; Control systems; Delays; Multiprotocol label switching; Optimization; Resource management; SDN; multiple applications; resource allocation;
Conference_Titel :
Network Operations and Management Symposium (NOMS), 2014 IEEE
Conference_Location :
Krakow
DOI :
10.1109/NOMS.2014.6838242