Cache-Enabled Adaptive Bit Rate Streaming via Deep Self-Transfer Reinforcement Learning

Caching and rate allocation are two promising approaches to support video streaming over wireless networks. However, existing rate allocation designs do not fully exploit the advantages of the two approaches. This paper investigates the problem of cache-enabled video rate allocation. We establish a mathematical model for this problem, and point out that it is difficult to solve it with traditional dynamic programming. Then we propose a deep reinforcement learning approach to solve it. Firstly, we model the problem as a Markov decision problem. Then we present a deep Q-learning algorithm with a special knowledge transfer process to find out an effective allocation policy. Finally, numerical results are given to demonstrate that the proposed solution can effectively maintain high-quality of service. We also investigate the impact of critical parameters on the performance of our algorithm.