Currently, IoT has become an important carrier of blockchains, which not only makes blockchain more ubiquitous but also improves the security of IoT. Consensus is the core component of blockchains with various forms, which raises the following challenges. Dynamic management and configuration of the consensuses in a blockchain are required because IoT applications have high dynamics. Moreover, an IoT node is usually reutilized by various applications in different blockchains, which means the IoT node should be switched frequently to cross consensuses in different blockchains. To address this, a software-defined blockchain architecture is proposed to realized the dynamic configurations for blockchains. Then a consensus function virtualization approach with application-aware work flow is proposed, which can abstract and manage various consensus resources. Next, a transfer-learning-based intelligent scheme is designed to implement the application- layer packet analysis and perform the efficient management of virtualized consensus resources. Experiment results indicate the feasibility of the proposed scheme. This work is significant in enhancing the flexibility and extendibility of blockchains in IoT.

中文翻译：

---

物联网中软件定义智能区块链的应用感知共识管理


目前，物联网已经成为区块链的重要载体，这不仅让区块链更加无处不在，也提高了物联网的安全性。共识是多种形式的区块链的核心组成部分，这带来了以下挑战。由于物联网应用具有高动态性，因此需要对区块链中的共识进行动态管理和配置。此外，物联网节点通常会被不同区块链中的各种应用重复利用，这意味着物联网节点需要频繁切换以跨不同区块链中的共识。为了解决这个问题，提出了软件定义的区块链架构来实现区块链的动态配置。然后提出了一种具有应用程序感知工作流程的共识功能虚拟化方法，可以抽象和管理各种共识资源。接下来，设计了一种基于迁移学习的智能方案来实现应用层数据包分析，并对虚拟化共识资源进行高效管理。实验结果表明了该方案的可行性。这项工作对于增强物联网区块链的灵活性和可扩展性具有重要意义。