Energy-Efficient Federated Learning Framework for Digital Twin-Enabled Industrial Internet of Things

Abstract

The digital twin (DT) bridges the physical world with the digital world in real-time for the Industrial Internet of Things (IIoT) and federated learning (FL) enables edge intelligence services for IIoT under the premise of avoiding privacy leakage. The fusion of two technologies can extremely accelerate the development of Industry 4.0 by enabling instant intelligence services. However, in the resource-constrained IIoT, the energy consumption of performing FL and maintaining the virtual object in the digital space by DT technology become the bottlenecks and can not be ignored. To address these issues, in this paper, we proposed an energy-efficient FL framework for DT-enabled IIoT. In the proposed framework, IIoT devices choose different training methods considering dynamic time-varying environment status to achieve energy-efficient FL, i.e., either train locally or connect to the virtual object by DT in the corresponding server of a small base station (SBS) to train mapped data using computing resources of SBS. Then, we investigate the joint training method selection and resource allocation problem to minimize the energy consumption while satisfying the convergence rate of the training model. Considering the problem is intractable using traditional approaches, we use a deep reinforcement learning (DRL)-based algorithm to solve it. Simulation results show that the proposed framework decreases greatly energy consumption compared with the static framework while satisfying the convergence rate of FL.