An NB-IoT-Based Edge-of-Things Framework for Energy-Efficient Image Transfer.

Muhammad Mahtab Alam,Yannick Le Moullec,Sikandar Zulqarnain Khan

doi:10.3390/s21175929

Muhammad Mahtab Alam, Yannick Le Moullec + Show 1 more

Open Access

https://doi.org/10.3390/s21175929

Copy DOI

Abstract

Machine Learning (ML) techniques can play a pivotal role in energy efficient IoT networks by reducing the unnecessary data from transmission. With such an aim, this work combines a low-power, yet computationally capable processing unit, with an NB-IoT radio into a smart gateway that can run ML algorithms to smart transmit visual data over the NB-IoT network. The proposed smart gateway utilizes supervised and unsupervised ML algorithms to optimize the visual data in terms of their size and quality before being transmitted over the air. This relaxes the channel occupancy from an individual NB-IoT radio, reduces its energy consumption and also minimizes the transmission time of data. Our on-field results indicate up to 93% reductions in the number of NB-IoT radio transmissions, up to 90.5% reductions in the NB-IoT radio energy consumption and up to 90% reductions in the data transmission time.

Highlights

Visual IoT is a paradigm where the environment is meant to be observed by cameraequipped IoT sensor nodes
What could be energy-latency trade-offs from the device and network perspective?. We address these questions by demonstrating a hierarchical smart-gateway-based visual number of radios in the core (NB-IoT) testbed, as shown in Figure 2, where several heterogeneous IoT devices are connected to the gateway through short-range wireless communication technologies such as Bluetooth and Bluetooth low energy (BLE), and ZigBee, etc
Our results showed that potentially significant energy gains can be achieved by eliminating the unwanted data from transmitting over the IoT networks

Summary

Introduction

Visual IoT is a paradigm where the environment is meant to be observed by cameraequipped IoT sensor nodes. We explore the suitability of NB-IoT technology for visual data transfer over the air with a focus on the channel occupancy, power consumption and time needed to transmit visual data from an individual NB-IoT radio. We address these questions by demonstrating a hierarchical smart-gateway-based visual NB-IoT testbed, as shown, where several heterogeneous IoT devices are connected to the gateway through short-range wireless communication technologies such as Bluetooth and Bluetooth low energy (BLE), and ZigBee, etc. Since the gateway node is computationally capable, it carries out a substantial amount of local data processing, i.e., “Edge computing” for more control of data over the air This can compensate for the limited bandwidth and lower data rates of LPWAN technologies, NB-IoT in particular [1]. We illustrate all these aspects through an edge-of-things computing-based NB-IoT framework for an efficient visual data transfer over the air and produce the associated on-field empirical results

Power graph of the BG96module

State-of-the-Art

Contributions

Hardware Architecture of Our Proposed Three Layers Hierarchical Model

Sense and Transmit Algorithm over the DVN

Smart Transmit Algorithm Running over the STN

Computation Cost

Findings

Conclusions