The Research On Energy Saving Scheme For Future Network

With the rapid growth of users and the continuous expansion of network size,network energy consumption also will show rapid growth.However,on the basis of the traditional network architecture,energy conservation of the network is not effective,because there is no centralized control and management mechanism.SDN based future network architecture is one of the effective solutions to this problem.The main idea of SDN is to separate the control layer and data layer of the network.The control layer can collect the topology of the whole network and the real-time traffic information of each device,so as to find the network topology with the least energy consumption and reduce the network energy consumption.Based on the future network architecture of SDN,this thesis explores the network energy saving solutions under the premise of ensuring that the link capacity is not exceeded,that is,without considering the goal of load balancing,only maximizing the energy saving target is achieved.An energy-saving algorithm based on 0-1 integer linear programming is proposed for this problem.As a result of the large-scale network,the model will become NP-hard problem,resulting in the increased complexity of the algorithm,so this thesis also proposed a heuristic greedy algorithm,which turning off unnecessary network nodes and links to approximate the optimal energy consumption of the network topology.Finally,the proposed two algorithms and traditional local algorithms are compared with the energy efficiency.The simulation results show that the proposed algorithms are superior to the traditional algorithm in energy saving efficiency.On the basis of above algorithms,in order to further solve the problem of network traffic aggregation,we propose n optimization algorithm for load balancing based on energy saving optimization.Aiming at this problem,multi-objective particle swarm load balancing energy saving algorithm is proposed.The simulation results show that the algorithm implements the optimization goal of energy saving and load balancing at the same time,and has lower computation complexity and smaller network latency.