Auction Based Resource Allocation In Network Virtualization Environment

Network virtualization, as an emerging technology to solve the ossification problems of current Internet the rigid network, has received many research institutions’attention. Under this background, this paper focuses on the problem of resource allocation in network virtualization environment. The allocation of resources necessary conditions for the normal operation of network services network virtualization environment can ensure a reasonable allocation of network resources in the meet service resource requirements at the same time improve the utilization of network resources. Network virtualization own characteristics, how fair and efficient allocation of resources, improve resource utilization, a key research resource allocation problem. To solve this problem, this paper re-assigned from the allocation of resources as well as resources two angles-depth study of the allocation of resources in the virtual ized environment.(1) Resource allocation algorithmThis paper introduces an InP-SP-End user system model in network virtualization environment, in which we present a bandwidth allocation scheme based on VCG (Vickrey-Clarke-Groves) to maximize the total revenue of SPs by inhibiting selfish action of SPs, and design a Q-learning strategy algorithm in order to obtain optimal bidding strategies for SPs. Simulations and experimental studies demonstrate the effectiveness and the fairness of the proposed scheme, and the convergence of the proposed algorithm.(2) Resource reallocation algorithmIn order to improve the network of virtual environments network resources and allows virtual network service providers maximum of total receipts, this builds the model of resource allocation system, SPs can trade their resources and resource-rich resources SP can be transferred to the SP of a resource shortage. Analysis on the basis of this model and offered two types of network resource allocation scheme: semi-distributed allocation scheme and distributed allocation scheme. These two allocation scheme using price control center and distributed double-auction free trade system respectively, each SP to maximize their revenues of principles based on the current market price for resource transactions. Simulation results show that this proposed half of distributed distribution and distributed by distribution to convergence and eventually reach the optimal allocation of program performance.