Edge Machine Learning in 3GPP NB-IoT: Architecture, Applications and Demonstration

The emergence of cellular Internet of Things (IoT) standards such as NB-IoT brings novel opportunities for low-cost wide-area IoT applications. Augmenting massive IoT deployments with Machine Learning (ML) algorithms deployed at the edge enables design and implementation of a novel intelligent IoT services. In this paper, we present an architectural outlook and an overview of our recent activities that target integration of ML modules into the cellular IoT architecture. The three-layer architecture considered in this paper embeds ML modules at the edge devices (ML-EDGE), within the core network (ML-FOG) and at the cloud servers (ML-CLOUD), thus balancing between the system response time and accuracy. We discuss alignment of the proposed architecture with ongoing trends in 3GPP architecture evolution. We design, integrate and demonstrate edge ML use cases relying on our real-world deployment of about 150 static and mobile nodes integrated into the NB-IoT network.