【Author】
Lu, Yunlong; Huang, Xiaohong; Zhang, Ke; Maharjan, Sabita; Zhang, Yan
【Source】IEEE INTERNET OF THINGS JOURNAL
【Abstract】Emerging technologies, such as mobile-edge computing (MEC) and next-generation communications are crucial for enabling rapid development and deployment of the Internet of Things (IoT). With the increasing scale of IoT networks, how to optimize the network and allocate the limited resources to provide high-quality services remains a major concern. The existing work in this direction mainly relies on models that are of less practical value for resource-limited IoT networks, and can hardly simulate the dynamic systems in real time. In this article, we integrate digital twins with edge networks and propose the digital twin edge networks (DITENs) to fill the gap between physical edge networks and digital systems. Then, we propose a blockchain-empowered federated learning scheme to strengthen communication security and data privacy protection in DITEN. Furthermore, to improve the efficiency of the integrated scheme, we propose an asynchronous aggregation scheme and use digital twin empowered reinforcement learning to schedule relaying users and allocate spectrum resources. Theoretical analysis and numerical results confirm that the proposed scheme can considerably enhance both communication efficiency and data security for IoT applications.
【Keywords】Artificial intelligence; Optimization; Data privacy; Internet of Things; Edge computing; Resource management; Blockchain; communication efficiency; digital twin; edge networks; federated learning
【标题】用于数字孪生边缘网络的高效通信联邦学习和许可区块链
【摘要】移动边缘计算 (MEC) 和下一代通信等新兴技术对于实现物联网 (IoT) 的快速开发和部署至关重要。随着物联网网络规模的不断扩大，如何优化网络并分配有限的资源以提供高质量的服务仍然是一个主要问题。该方向的现有工作主要依赖于对资源有限的物联网网络缺乏实用价值的模型，并且难以实时模拟动态系统。在本文中，我们将数字孪生与边缘网络相结合，并提出数字孪生边缘网络 (DITEN) 来填补物理边缘网络和数字系统之间的空白。然后，我们提出了一种基于区块链的联邦学习方案，以加强 DITEN 中的通信安全和数据隐私保护。此外，为了提高集成方案的效率，我们提出了一种异步聚合方案，并使用数字孪生强化学习来调度中继用户和分配频谱资源。理论分析和数值结果证实，所提出的方案可以显着提高物联网应用的通信效率和数据安全性。
【关键词】人工智能;优化;数据隐私；物联网;边缘计算；资源管理;区块链；沟通效率；数字孪生；边缘网络；联邦学习
评论