Design And Prototype Implementation Of Hybrid Topology Management Mechanism In Green Internet

In recent years, the rapid development of Internet has brought great convenience to people's life and work. It also leads to the growth of scale of network and the surge in the number of Internet equipment. The increase of energy consumption by network equipment raised concerns of the public. Because the current network design is accord-ing to the principle of excess supply and redundancy, this leads to its high energy con-sumption and low efficiency. To tackle this problem, the concept of "green internet" was put forward. Its aim is to save the energy consumption of the internet, which is accom-plished by changing the network topology in the green internet, making specific links or nodes sleep or wake up, in order to achieve the purpose of energy saving. This paper puts forward the green internet hybrid topology management mechanism to supervise and control the topology.This paper designs a green internet topology management mechanism. This mech-anism includes information sense module, traffic prediction module, center node elec-tion module, topology clustering module, centralized topology decision-making model, distributed topology decision-making module, link value evaluation module and dor-mancy control module. Information sensing module is used for regular collecting the information of nodes and links such as flow rate, power consumption. Traffic prediction module is based on the historical traffic data to forecast the traffic, and provides the de-cision basis for the topology decision module. Center node election module is used in the topology to choose an appropriate node running the centralized topology deci-sion-making model, to reduce the operational cost of the mechanism. Topology cluster-ing module divides into multiple small topology according to the tightness of the topol-ogy, determing the scope of the distributed topology decision-making module to run. Centralized topology decision-making module based on global information collected on a regular basis, with the method of off-line, controls the link in the between of clusters to sleep or work. Distributed topology decision-making module with the method of on-line controls links in the clusters to sleep and wake up. Link value evaluation module is used to evaluate the value of links from multiple aspects, providing the basis for to-pology decision-making module. Dormancy control module is used to manage links out and join in the topology.This paper implements the green internet hybrid topology management mecha-nism, and a performance evaluation is carried out. Running results show that the hybrid green network Topology management mechanism can effectively reduce the network energy consumption, and network performance is guaranteed at the same time.