D2D caching assists mobile edge caching in offloading inter-domain traffic by sharing cached items with nearby users, while its performance relies heavily on caching nodes' sharing willingness. In this article, a Blockchain-based CDM is proposed as an incentive mechanism for the distributed caching system. Under given incentive mechanisms, both D2D and mobile edge caching nodes' willingness is guaranteed by satisfying their expected reward for cache sharing. Besides, for the distributed CDM, content delivery related transactions are executed by smart contracts. To achieve consensus on the transactions and prevent frauds, a consensus protocol among the SCENE is necessary. The pPBFT protocol is proposed to minimize the latency of reaching consensus while guaranteeing its confidence level. We build the model of cache sharing and transaction execution consensus, and we further formulate cache placement and SCENE selection as Markov Decision Process problems. Considering the complexity and dynamics of the problems, a deep reinforcement learning approach is adopted to solve the problems. Simulation results show that, compared to conventional solutions, the proposed schemes achieve efficient traffic offloading, and significantly improve the transaction execution consensus speed.

中文翻译：

---

区块链激励的D2D和移动边缘缓存：深度强化学习方法

D2D缓存通过与附近的用户共享缓存的项来帮助移动边缘缓存减轻域间流量的负担，而其性能在很大程度上取决于缓存节点的共享意愿。在本文中，提出了一种基于区块链的CDM作为分布式缓存系统的激励机制。在给定的激励机制下，D2D和移动边缘缓存节点的意愿都可以通过满足它们对缓存共享的预期奖励来保证。此外，对于分布式CDM，与内容交付相关的交易由智能合约执行。为了在交易上达成共识并防止欺诈，SCENE之间必须达成共识协议。提出了pPBFT协议以最小化达成共识的等待时间，同时保证其置信度。我们建立了缓存共享和事务执行共识的模型，并进一步将缓存放置和SCENE选择公式化为Markov决策过程问题。考虑到问题的复杂性和动态性，采用深度强化学习的方法来解决问题。仿真结果表明，与传统解决方案相比，该方案实现了高效的流量卸载，并显着提高了交易执行共识速度。