Digital twin-assisted semi-federated learning framework for industrial edge intelligence

The rapid development of emerging technologies, such as edge intelligence and digital twins, have added momentum towards the development of the Industrial Internet of Things (IIoT). However, the massive amount of data generated by the IIoT, coupled with heterogeneous computation capacity across IIoT devices, and users' data privacy concerns, have posed challenges towards achieving industrial edge intelligence (IEI). To achieve IEI, in this paper, we propose a semi-federated learning framework where a portion of the data with higher privacy is kept locally and a portion of the less private data can be potentially uploaded to the edge server. In addition, we leverage digital twins to overcome the problem of computation capacity heterogeneity of IIoT devices through the mapping of physical entities. We formulate a synchronization latency minimization problem which jointly optimizes edge association and the proportion of uploaded nonprivate data. As the joint problem is NP-hard and combinatorial and taking into account the reality of large-scale device training, we develop a multi-agent hybrid action deep reinforcement learning (DRL) algorithm to find the optimal solution. Simulation results show that our proposed DRL algorithm can reduce latency and have a better convergence performance for semi-federated learning compared to benchmark algorithms.