Review Article
[Retracted] Deep and Reinforcement Learning Technologies on Internet of Vehicle (IoV) Applications: Current Issues and Future Trends
Table 2
Summary of AI applications for cloud-based IoV frameworks.
| Work | Year | Source | Framework approaches | Features | Advantages |
| Zhang et al. [50] | 2021 | Springer | Resource allocation scheme based on deep RL scheme | Minimum total computing cost for IoV in an edge environment | Effectively allocate the computing resources of IoV | Grigorescu et al. [51] | 2020 | Sensors | Self-driving autonomous vehicles to forecast future traffic demands in IoV | AI inference engines for autonomous driving applications | Mitigating privacy issues and effective path prediction | Claudio et al. [52] | 2020 | IEEE | ML-based framework for IoV edge network | Avoid the abuse of IoV edge computing activities | Improve the performance of control mechanisms in IoV | Ning et al. [53] | 2019 | IEEE | Deep RL for cloud computing-based offloading framework for IoV | Minimize the overall energy consumption | Reduce energy consumption by 60% | Razi et al. [54] | 2018 | IEEE | Data analytics framework for fog-based IoV architecture | Analysis based on DL and deep RL (DRL) | Context-aware services in an IoV environment | Chen et al. [55] | 2018 | Springer | Mobile cloud computing framework | Framework-based deep learning approach | Outperform objects detection rate |
|
|