Deep Multi-Agent Reinforcement Learning Based Cooperative Edge Caching in Wireless Networks

The growing demand on high-quality and low-latency multimedia services has led to much interest in edge caching techniques. Motivated by this, we in this paper consider edge caching at the base stations with unknown content popularity distributions. To solve the dynamic control problem of making caching decisions, we propose a deep actor-critic reinforcement learning based multi-agent framework with the aim to minimize the overall average transmission delay. To evaluate the proposed framework, we compare the learning-based performance with three other caching policies, namely least recently used (LRU), least frequently used (LFU), and first-in-first-out (FIFO) policies. Through simulation results, performance improvements of the proposed framework over these three caching algorithms have been identified and its superior ability to adapt to varying environments is demonstrated.

[1]  Symeon Chatzinotas,et al.  A deep learning approach for optimizing content delivering in cache-enabled HetNet , 2017, 2017 International Symposium on Wireless Communication Systems (ISWCS).

[2]  Min Sheng,et al.  Learning-Based Content Caching and Sharing for Wireless Networks , 2017, IEEE Transactions on Communications.

[3]  Mykel J. Kochenderfer,et al.  Cooperative Multi-agent Control Using Deep Reinforcement Learning , 2017, AAMAS Workshops.

[4]  Shimon Whiteson,et al.  Learning to Communicate with Deep Multi-Agent Reinforcement Learning , 2016, NIPS.

[5]  June-Koo Kevin Rhee,et al.  Efficient Content Replacement in Wireless Content Delivery Network with Cooperative Caching , 2016, 2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA).

[6]  Yi Wu,et al.  Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments , 2017, NIPS.

[7]  Xuemin Shen,et al.  Cooperative Edge Caching in User-Centric Clustered Mobile Networks , 2017, IEEE Transactions on Mobile Computing.

[8]  Dusit Niyato,et al.  Decentralized Caching for Content Delivery Based on Blockchain: A Game Theoretic Perspective , 2018, 2018 IEEE International Conference on Communications (ICC).

[9]  Jaime Llorca,et al.  A Methodology for the Design of Self-Optimizing, Decentralized Content-Caching Strategies , 2016, IEEE/ACM Transactions on Networking.

[10]  Senem Velipasalar,et al.  Learning-Based Delay-Aware Caching in Wireless D2D Caching Networks , 2018, IEEE Access.

[11]  Mustafa Cenk Gursoy,et al.  A deep reinforcement learning-based framework for content caching , 2017, 2018 52nd Annual Conference on Information Sciences and Systems (CISS).

[12]  Meixia Tao,et al.  Optimal dynamic multicast scheduling for cache-enabled content-centric wireless networks , 2015, 2015 IEEE International Symposium on Information Theory (ISIT).

[13]  Ting He,et al.  On the Complexity of Optimal Request Routing and Content Caching in Heterogeneous Cache Networks , 2017, IEEE/ACM Transactions on Networking.

[14]  Kai Xu,et al.  Joint Replica Server Placement, Content Caching, and Request Load Assignment in Content Delivery Networks , 2018, IEEE Access.