A GNN-based Proactive Caching Strategy in NDN Networks

Abstract

As people spend more time watching and sharing videos online, it is critical to provide users with a satisfactory quality of experience (QoE). Leveraging the in-network caching and named-based routing features in Named Data Networks (NDNs), our paper aims to improve user experience through caching. We propose a graph neural network-gain maximization (GNN-GM) cache placement algorithm. First, we use a GNN model to predict users’ ratings of unviewed videos. Second , we consider the total predicted rating of a video as the gain of the cached video. Third, we propose a cache placement algorithm to maximize the caching gain and actively cache videos. Cache replacement is implemented based on the cache gain ranking of videos, with higher cache gain videos replacing lower cache gain videos. We compare GNN-GM with two state-of-the-art caching strategies, namely the NMF-based caching strategy and GNN-CPP. GNN-GM is also compared with two traditional caching strategies, LCE and LRU, LCE and FIFO. We evaluate the five caching strategies using real-world datasets in a tree network topology, a real-world network topology GEANT, and various random topologies. The experimental results show that our caching policy significantly improves cache hit ratio, latency and server load. Notably, GNN-GM achieves a 25% higher cache hit rate, 5% lower latency and 7% lower server load than GNN-CPP in GEANT.

A Study Of Civil Engineering Education At Singapore Nanyang Technology University And At The University Of Florida

“…From Eqs. ( 29) and (30), we can observe that LEGD-AM ensures the adaptability of our service provisioning framework in zero-trust NGN since both the mask and reward function can be flexibly designed according to the latest environment/requirements.…”

“…Peng et al [29] introduced Vertex-GNN and Edge-GNN for resource allocation in wireless networks. Hou et al [30] developed a GNN-based caching scheme for SDN-based networks. Micro-segmentation generation, however, differs from conventional graphical optimizations.…”