CacheIn: A Secure Distributed Multi-layer Mobility-Assisted Edge Intelligence based Caching for Internet of Vehicles

Abstract

This paper investigates the feasibility of cache content prediction and coherence in the context of secure communication and search. We introduce a distributed multi-tier mobility-assisted edge intelligence based caching framework for the Internet of Vehicles (IoVs), called CacheIn. The proposed framework leverages user preferences, data correlations, and mobility information to prefetch content to the IoV edge. To enable content management based on mobility, we propose a novel Normalized Hidden Markov Model (NM-HMM) that anticipates a vehicle's future position. The framework also utilizes a mobility-aware collaborative filtering-based federated learning (FL) technique to enhance cache hit, reduce latency, and protect user privacy. To ensure secure cross-domain data sharing and mitigate the risk of data breaches, we also propose an extended ciphertext policy attribute-based encryption (ECP-ABE) mechanism. Compared to content popularity-based caching schemes, CacheIn achieves up to 80%, 38%, and 55% improvement in cache hit ratio for different cache sizes, vehicle densities, and cache lookup scenarios. Moreover, our approach reduces key generation, encryption, and decryption times by 35 %.