AI-Enhanced Cloud-Edge-Terminal Collaborative Network: Survey, Applications, and Future Directions

The cloud-edge-terminal collaborative network (CETCN) is considered as a novel paradigm for emerging applications owing to its huge potential in providing low-latency and ultra-reliable computing services. However, achieving such benefits is very challenging due to the heterogeneous computing power of terminal devices and the complex environment faced by the CETCN. In particular, the high-dimensional and dynamic environment states cause difficulties for the CETCN to make efficient decisions in terms of task offloading, collaborative caching and mobility management. To this end, artificial intelligence (AI), especially deep reinforcement learning (DRL) has been proven effective in solving sequential decision-making problems in various domains, and offers a promising solution for the above-mentioned issues due to several reasons. Firstly, accurate modelling of the CETCN, which is difficult to obtain for real-world applications, is not required for the DRL-based method. Secondly, DRL can effectively respond to high-dimensional and dynamic tasks through iterative interactions with the environment. Thirdly, due to the complexity of tasks and the differences in resource supply among different vendors, collaboration is required between different vendors to complete tasks. The multi-agent DRL (MADRL) methods are very effective in solving collaborative tasks, where the collaborative tasks can be jointly completed by cloud, edge and terminal devices which provided by different vendors. This survey provides a comprehensive overview regarding the applications of DRL and MADRL in the context of CETCN. The first part of this survey provides a depth overview of the key concepts of the CETCN and the mathematical underpinnings of both DRL and MADRL. Then, we highlight the applications of RL algorithms in solving various challenges within CETCN, such as task offloading, resource allocation, caching and mobility management. In addition, we extend discussion to explore how DRL and MADR