AI-based Energy Model for Adaptive Duty Cycle Scheduling in Wireless Networks
Institute of Electrical and Electronics Engineers Inc.
The vast distribution of low-power devices in IoT applications requires robust communication technologies that ensure high-performance level in terms of QoS, light-weight computation, and security. Advanced wireless technologies (i.e. 5G and 6G) are playing an increasing role in facilitating the deployment of IoT applications. To prolong the network lifetime, energy harvesting is an essential technology in wireless networks. Nevertheless, maintaining energy sustainability is difficult when considering high QoS requirements in IoT. Therefore, an energy management technique that ensures energy efficiency and meets QoS is needed. Energy efficiency in duty cycling solutions needs novel energy management techniques to address these challenges and achieve a trade-off between energy efficiency and delay. Predictive models (i.e., based on AI and ML techniques) represent useful tools that encapsulate the stochastic nature of harvested energy in duty cycle scheduling. The conventional predictive model relies on environmental parameters to estimate the harvested energy. Instead, Artificial Intelligence (AI) allows for recursive prediction models that rely on past behavior of harvested and consumed energy. This is useful to achieve better precision in energy estimation and extend the limit beyond predictive models directed solely for energy sources that exhibit periodic behavior. In this paper, we explore the usage of a ML model to enhance the performance of duty cycle scheduling. The aim is to improve the QoS performance of the proposed solution. To assess the performance of the proposed model, it was simulated using the INET framework of the OMNet++ simulation environment. The results are compared to an enhanced IEEE 802.15.4 MAC protocol from the literature. The results of the comparative study show clear superiority of the proposed AI-based protocol that testified to better use of energy estimation for better management of the duty cycling at the MAC sublayer. © 2021 IEEE.
This conference paper is not available at CUD collection. The version of scholarly record of this paper is published in 2021 International Symposium on Networks, Computers and Communications, ISNCC 2021 (2021), available online at: https://doi.org/10.1109/ISNCC52172.2021.9615752
Artificial Intelligence, Duty Cycle, Energy Harvesting, Internet of Things, Machine Learning, Wireless Sensor Network
Charef, N., Mnaouer, A. B., & Bouachir, O. (2021). AI-based energy model for adaptive duty cycle scheduling in wireless networks. Paper presented at the 2021 International Symposium on Networks, Computers and Communications, ISNCC 2021. https://doi.org/10.1109/ISNCC52172.2021.9615752