Research On Cache Placement Strategy Of Content Centric Network

Content centric network is a new architecture of the future Internet. Caching mechanism of the content centric network is that each node in the content centric network has cache space, and each node can cache all objects passing it without distinction. So the caching mechanism will be lead to redundant data and low cache utilization rate. Cache placement strategy is an effective method to solve such problems.According to the existing problems of the content centric network caching, based on detailed analysis of the existing cache placement strategies,a new cache placement strategy is proposed, called optimal cache placement strategy based on prediction.First, the cache placement strategy is converted into an optimization problem, and a new cache model is proposed, called Max-Benefit model. In the model, several factors affecting the cache performance are considered. According to the problem that the accessed frequency of object in the Max-Benefit model can not express the future heat trend of the object, the prediction mechanism is introduced in the model, and the maximize benefit cache placement model based on the prediction is proposed, called PB-Max-Benefit model. Through predicting the future heat trend of the object to cache the most popular content as much as possible so as to avoid the invalid cache and improve cache performance.Second, based on the PB-Max-Benefit model, selection operator, crossover operator and mutation operator of the simple genetic algorithm are improved. The improved genetic algorithm is to increase its convergence rate and avoid falling into local optimal solution of problems so as to improve the performance of solving global optimal solution of the PB-Max-Benefit model.Finally, NS-3 network simulator is used to experiment in the virtual machine. In simulation, the cache hit ratio, invalid cache ratio and average hops are taken as validation indexes. Different cache size, data access model and the network scale are taked as simulation environment. The caching mechanism of the content centric network and an existing cache placement strategy are compared with the optimal cache placement strategy proposed in the paper and the simulation results are obtained. The simulation results are eventually expressed in the form of charts, and the results are analyzed and compared, and the validity of the optimization cache placement strategy based on the prediction proposed in the paper are verified.