부산대학교 도서관

Cache management is an important component in any network and it has even more importance in the Future Internet Architectures (FIAs) including Named Data Networking (NDN), because the caches play the key role in reducing the overall network latency and scalability. In this paper, we discuss the functionality of cache management in NDN, its types as well as its importance for the NDN architecture. In addition, we propose a machine learning-empowered cache management and interests predication for NDN to only preserve the cache only to the secure and really needed data. Our proposal uses Apriori algorithm which is supervised learning algorithm to find the association rules and then to recommend the next requested data. Implementation and experiments on real data traffic depicted that the network’ performance and its influence on the cache increased by 3.2% for two content store sizes of 20 and 40 MB. In addition, a larger cache size of 80 MB shows an increase of the cache hit ratio reaching 90% and hence, clearly reducing the network latency.