An Efficient Deep CNN Design for EH Short-Packet Communications in Multihop Cognitive IoT Networks

TL;DR

This paper introduces a deep CNN framework that accurately predicts performance metrics in energy harvesting short-packet IoT communications, reducing computational complexity for real-time applications.

Contribution

It proposes a novel CNN architecture with feature enhancement-collection blocks tailored for EH short-packet IoT networks, achieving high accuracy with lower complexity.

Findings

CNN achieves near-identical BLER and throughput as Sum-EH scheme

Significantly reduces computational complexity for real-time use

Lowest RMSE compared to other neural networks and machine learning methods

Abstract

In this paper, we design an efficient deep convolutional neural network (CNN) to improve and predict the performance of energy harvesting (EH) short-packet communications in multi-hop cognitive Internet-of-Things (IoT) networks. Specifically, we propose a Sum-EH scheme that allows IoT nodes to harvest energy from either a power beacon or primary transmitters to improve not only packet transmissions but also energy harvesting capabilities. We then build a novel deep CNN framework with feature enhancement-collection blocks based on the proposed Sum-EH scheme to simultaneously estimate the block error rate (BLER) and throughput with high accuracy and low execution time. Simulation results show that the proposed CNN framework achieves almost exactly the BLER and throughput of Sum-EH one, while it considerably reduces computational complexity, suggesting a real-time setting for IoT systems under complex scenarios. Moreover, the designed CNN model achieves the root-mean-square-error (RMSE) of ${1.33\times10^{-2}}$ on the considered dataset, which exhibits the lowest RMSE compared to the deep neural network and state-of-the-art machine learning approaches.