Recently, blockchain has elicited escalating attention from academia to industry. However, blockchain is still in its initial stage, and remains a great number of non-trivial problems to be delved before being used as a generic platform. The most intractable one is the scalability problem. The deep reinforcement learning empowered adaptivity can help the blockchain network break through the bottleneck. In this paper, we study a deep reinforcement learning empowered adaptivity approach for future blockchain networks, so as to improve the scalability and meet the requirements of different users. Specifically, rather than using one consensus protocol as the best fit one, the blockchain networks launch different consensus protocols, based on users’ quality of service (QoS) requirements. To this end, we quantify four consensus protocols. Additionally, the blockchain networks are heavily hampered by the limited computation and bandwidth resources. We also dynamically allocate computation and bandwidth resources to the blockchain networks. Then we formulate these thress items, i.e., the selection of consensus protocols, computation resource, and network bandwidth resource, as a joint optimization problem. A deep reinforcement learning approach is used to solve this problem. Simulation results are presented to show the effectiveness of our proposed scheme.

中文翻译：

---

深度强化学习增强了未来区块链网络的适应性

最近，区块链引起了学术界和工业界的日益关注。但是，区块链仍处于起步阶段，在用作通用平台之前，仍然有很多非平凡的问题需要研究。最棘手的是可伸缩性问题。深度强化学习授权的适应性可以帮助区块链网络突破瓶颈。在本文中，我们研究了针对未来区块链网络的深度强化学习授权适应性方法，以提高可扩展性并满足不同用户的需求。具体来说，不是使用一种共识协议作为最适合的协议，而是基于用户的服务质量（QoS）要求，区块链网络启动了不同的共识协议。为此，我们量化了四个共识协议。此外，有限的计算和带宽资源严重阻碍了区块链网络的发展。我们还为区块链网络动态分配计算和带宽资源。然后，我们将这些约束项（即共识协议的选择，计算资源和网络带宽资源）表述为联合优化问题。使用深度强化学习方法来解决此问题。仿真结果表明了所提出方案的有效性。作为联合优化问题。使用深度强化学习方法来解决此问题。仿真结果表明了所提出方案的有效性。作为联合优化问题。使用深度强化学习方法来解决此问题。仿真结果表明了所提出方案的有效性。