A Data Communication Based on Deep Learning Model for Efficient IoT Energy Clustering

The emergence of artificial intelligence, especially, deep learning combined with time series forecasting has attracted increasing attention from academics and researchers in various domains. This paper proposes a novel energy-efficient clustering protocol for data communication, leveraging the DCOPA protocol and incorporating a deep learning model built on a Multilayer Gated Recurrent Unit (GRU) optimized with a Bayesian approach. The core idea is to train the network nodes to reproduce their behaviors during the execution of the DCOPA protocol and create a deep learning model based on the training with the real values of the CHs election rounds generated during many executions of the DCOPA protocol. Hereafter, the deep learning model will be deployed to forecast a future set of CH nodes in each round for the future rounds. Therefore, the large volumes of exchanged data during the clusters' formation will no longer be required. To validate the proposed solution, we conducted a large number of experiments with the DCOPA protocol and recorded the results in a history log. The obtained results are very encouraging to continue this work.

• energy-efficient clustering
• deep learning
• Bayesian optimization
• cluster head selection
• time series forecasting
• data transmission
• wireless sensor networks

• 9 — Industrie, innovation et infrastructure
• 7 — Énergie propre et d’un coût abordable
• 13 — Mesures relatives à la lutte contre les changements climatiques

• Energy Efficient Wireless Sensor Networks
• IoT Networks and Protocols
• Energy Efficiency in Computing
• energy-efficient clustering
• deep learning
• Bayesian optimization
• cluster head selection
• time series forecasting
• data transmission
• wireless sensor networks
• Computer Networks and Communications
• Electrical and Electronic Engineering
• Hardware and Architecture
• Computer Science
• Engineering