Without steering wheel and driver’s seat, the self-driving cars will have new interior outlook and spaces that can be used for enhanced infotainment services. For traveling people, self-driving cars will be new places for engaging in infotainment services. Therefore, self-driving cars should determine themselves the infotainment contents that are likely to entertain their passengers. However, the choice of infotainment contents depends on passengers’ features such as age, emotion, and gender. Also, retrieving infotainment contents at data center can hinder infotainment services due to high end-to-end delay. To address these challenges, we propose infotainment caching in self-driving cars, where caching decisions are based on passengers’ features obtained using deep learning. First, we proposed deep learning models to predict the contents need to be cached in self-driving cars and close proximity of self-driving cars in multi-access edge computing servers attached to roadside units. Second, we proposed a communication model for retrieving infotainment contents to cache. Third, we proposed a caching model for retrieved contents. Fourth, we proposed a computation model for the cached contents, where cached contents can be served in different formats/qualities based on demands. Finally, we proposed an optimization problem whose goal is to link the proposed models into one optimization problem that minimizes the content downloading delay. To solve the formulated problem, a block successive majorization-minimization technique is applied. The simulation results show that the accuracy of prediction for the contents that need to be cached is 97.82% and our approach can minimize the delay.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Deep Learning Based Caching for Self-Driving Cars in Multi-Access Edge Computing


    Contributors:


    Publication date :

    2021-05-01


    Size :

    2926346 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Deep Learning Based Self Driving Cars Using Computer Vision

    Bhaggiaraj, S. / Priyadharsini, M. / Karuppasamy, K. et al. | IEEE | 2023


    Multi-task deep learning with optical flow features for self-driving cars

    Hu, Yuan / Shum, Hubert P. H. / Ho, Edmond S. L. | IET | 2021

    Free access

    Multi‐task deep learning with optical flow features for self‐driving cars

    Hu, Yuan / Shum, Hubert P. H. / Ho, Edmond S. L. | Wiley | 2020

    Free access

    Joint caching and computing service placement for edge-enabled IoT based on deep reinforcement learning

    Chen, Y. (Yan) / Sun, Y. (Yanjing) / Yang, B. (Bin) et al. | BASE | 2022

    Free access

    Predicting Steering Actions for Self-Driving Cars Through Deep Learning

    Ou, Chaojie / Bedawi, Safaa Mahmoud / Koesdwiady, Arief B. et al. | IEEE | 2018