Intelligent Caching using Continuous Machine Learning in Named Data Networking
Sai Sameer Yanamandra · 2024
Our project focuses on improving Named Data Networking (NDN), an alternative network architecture to traditional IP networks, particularly in unstable conditions where connections frequently drop, and data movement is unpredictable. In NDN, data is cached at various routers across the network, enhancing accessibility even amidst unstable connections. A key challenge we address is determining the optimal level of data redundancy in unstable scenarios. We aim to balance the need for data availability with the risk of excessive data duplication. Our solution involves developing a novel data caching approach for the NDN’s content store based on continuous machine learning. This method employs two primary factors: data properties like the data size and demand frequency and the likelihood of disconnection from other routers storing the same data. We will evaluate our approach using a simulation under various parameters such as network layout, data types, and connection stability, to assess our method’s effectiveness in diverse scenarios. In particular, our method is compared against the common caching heuristics and their hybrid approaches.