Edge Intelligence-Based Joint Caching and Transmission for QoE-Aware Video Streaming

The integration of mobile edge caching and coordinated multipoint (CoMP) joint transmission (JT) is regarded as a promising method to support high-throughput wireless video streaming in mobile networks. In this paper, we propose a quality of experience (QoE)-aware joint caching and transmission scheme to realize autonomous content caching and spectrum allocating for video streaming. We jointly optimize content placement and spectrum allocation to minimize content delivery delay, taking into account time-varying content popularity, transmission method selection, and different QoE requirements of users. The optimization problem is transformed into a Markov decision process (MDP) in which a reward characterizing content delivery delay and QoE on video streaming is defined. Then, we propose an edge intelligence (EI)-based learning algorithm, named quantum-inspired reinforcement learning (QRL), which exploits quantum parallelism to overcome the “curse of dimensionality”. The optimal policy is obtained in an online fashion with a high learning efficiency. The convergence rate, content delivery delay, and stalling rate are evaluated in the simulations, and the results show the effectiveness of our method.