Information-centric networking (ICN) allows data to be cached at each node in the network. It is vital in vehicular networks (VNs) to improve caching performance and reduce content delay in high-traffic scenarios. In cooperative VNs, the requested content can be cached in the base station or nearby nodes without fetching the requested content from the server. The existing content popularity approaches face challenges in predicting popular content due to a time-varying environment, resulting in popularity being changed frequently. It is hard to predict such content in highly dynamic vehicular traffic. Therefore, the current approaches are less practical in a realistic scenario. This paper proposes an intelligent caching method for massive traffic in VNs to address these issues based on deep transfer learning (DTL). The primary purpose of this study is to reduce the system cost and content delay by increasing the cache hit rate based on popular data in dynamic traffic. The proposed solution uses a collaborative cache with social interaction among clusters to share the most popular content (MPC). Furthermore, it designs a time-varying mechanism to predict content popularity in a highly dynamic environment and share the widespread knowledge with other target nodes based on DTL. In addition, a content update method is developed to address the content replacement in a cooperative cache environment. Based on thorough analysis and evaluation, similar and dissimilar contents on base stations are classified among source and target clusters. The extensive simulation and experimentation confirm that the developed work achieved better than baseline studies.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Intelligent Caching Based on Popular Content in Vehicular Networks: A Deep Transfer Learning Approach



    Published in:

    Publication date :

    2024-12-01


    Size :

    1886447 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    VeSoNet: Traffic-Aware Content Caching for Vehicular Social Networks Using Deep Reinforcement Learning

    Aung, Nyothiri / Dhelim, Sahraoui / Chen, Liming et al. | IEEE | 2023

    Free access


    ICN Based Efficient Content Caching Scheme for Vehicular Networks

    Gupta, Divya / Rani, Shalli / Singh, Aman et al. | IEEE | 2023



    A Review on AI-Enabled Content Caching in Vehicular Edge Caching and Networks

    Masood, Arooj / Tuan, Do Quang / Lakew, Demeke Shumeye et al. | IEEE | 2023