Classification of interfaces on Named Data Networking Using machine learning

NDN (Named Data Network) network is the future network that transforms network communication from sending packets to the destination address to retrieving data (content) identified by name. A forwarding strategy is needed to select the next hop efficiently when forwarding interest. NDN, a data-centric network that can reduce network load (especially on the server side), has been widely developed using Machine Learning (ML) recently. The main factor in using ML is to examine very large data, for example, data in the Forwarding Information Base (FIB) table. The purpose of this study is to classify faces for interests that come to the NDN network and find out that the interests will be forwarded to closer nodes (producers). This research classifies several faces of FIB Classification techniques in Machine Learning are needed to classify the faces based on several interrelated features (variables). The results of the classification that has been carried out, show that the Random Forest classification model has the highest level of accuracy, which is 85,77%.