Enhancing Training Efficiency for Cloud-Edge Collaboration in the Industrial Internet of Things: A Transmission-Centric Approach

With the development of intelligent edge computing (IEC) in industrial IoT (IIoT), there is a growing number of service providers trying to leverage computing resources in the cloud and at the edge to meet the users‘ demand for low latency and high reliability in diversified applications. This evolving landscape necessitates innovative approaches to manage and process the vast amounts of data generated by IIoT devices. Among these approaches, distributed learning frameworks, such as federated learning (FL), have emerged as popular solutions. However, compared to computing, communication remains the primary bottleneck that constrains the speed of federated model training. Most of the previous solutions have focused on reducing communication overhead. Differently, we propose a transmission-centric approach by designing an efficient communication archi-tecture for FL with cloud-edge collaboration, specifically aimed at enhancing communication capabilities through multi-path transmission. We deploy this FL system in a real environment and conduct extensive testing. The results demonstrate that the new approach can significantly reduce communication time in FL setting, thereby enhancing model aggregation efficiency and shortening the overall training duration. Compared to conventional single-path transmission, the proposed solution improves training efficiency by up to 26.4%.

I. Introduction

Toward Industry 4.0 [1], Intelligent Edge Computing (IEC) has become an important issue for the combination of network and computing [2]. With the evolution of network applications, the amount of industrial devices available to meet transmission and computing demand is growing steadily, which is a major force for the explosion of data at the edge. Meanwhile, the cost of time and bandwidth will be expensive if the data processing is offloaded to a remote server. A distinct trend in computing nowadays is that users prefer to push the computing task to the edge of the network rather than the center [3]. This idea is becoming increasingly attractive as the computing and storage capabilities of edge devices increase. On the other hand, 5G can support extreme variations of industrial IoT (IIoT) applications [4]. Edge computing not only offers faster speed and higher efficiency, but also better security for private information. As a combination of edge computing and Artificial Intelligence (AI), IEC brings new opportunities for IIoT [5]. IEC allows AI computing to be done near the user at the edge of the IIoT network, rather than in the cloud. It brings real-time intelligence, increased privacy protection, and enhanced cybersecurity to users, while reducing costs and ensuring continuous improvement of production processes.