Modified-LRU Algorithm for Caching on Named Data Network

Abstract

It is estimated that the annual network traffic of the internet will go beyond the threshold. Named Data Network will enter a new era in the world of networks because NDN nodes can store the data that has been requested by consumers in the content store so that one day when the data is requested by another consumer, it will be fast in the distribution of data. There are several optimization techniques based on replacement algorithms, one example is Least Recently Used (LRU), which is more focused on content that is rarely accessed and stores popular content in the content store. But the LRU has a weakness, which is only using the latest reference time and cannot distinguish between frequently or rarely the object being accessed. LRU modification is made to combine frequency and recently files in the decision stage to replace files so that the Modified-LRU can improve performance more optimally. In this paper, it is proposed the Modified-LRU algorithm. Modified-LRU takes an idea of SF-LRU but it is more simple in the process of deleting files. So, it can reduce the processing load. In this paper, the performance of LRU and Modified-LRU are compared. The simulation results show that the Modified-LRU is feasible to improve the LRU performance. The hit ratio is 8.7% greater compared to LRU, reducing delay by 60% and packet drop by 95%.