AI-ENABLED WIRELESS POWER TRANSFER ARCHITECTURES FOR SUSTAINABLE IoT ECOSYSTEMS

Abstract The proliferation of Internet of Things (IoT) devices in smart cities, industrial automation, and healthcare monitoring has created an unprecedented demand for sustainable energy solutions. Traditional battery-powered IoT deployments face significant challenges including limited operational lifespan, environmental hazards from battery disposal, and high maintenance costs associated with manual replacement. This study presents a novel AI-enabled wireless power transfer (WPT) architecture that leverages machine learning algorithms to optimize energy delivery, predict device energy demands, and autonomously manage power distribution across large-scale IoT ecosystems. We propose a three-tier architecture comprising (1) an intelligent RF energy harvesting layer with adaptive rectenna arrays, (2) a reinforcement learning-based power allocation engine, and (3) a cloud-native energy orchestration platform. Through extensive simulation and prototype validation across three distinct IoT scenarios smart agriculture, industrial asset monitoring, and wearable health networks we demonstrate that the proposed system achieves 78.4% energy transfer efficiency (a 34% improvement over conventional directional WPT), reduces network energy waste by 62%, and extends device operational lifespan by 4.7× compared to battery-dependent counterparts. Our findings establish that AI-driven dynamic optimization of WPT parameters including beam-forming angles, transmission power, and duty cycling enables scalable, sustainable IoT deployments that were previously infeasible. This research contributes to the emerging field of intelligent energy harvesting networks and provides a replicable framework for next-generation green IoT infrastructure. Keywords: wireless power transfer, Internet of Things, machine learning, energy harvesting, sustainable computing, reinforcement learning, smart cities, green communication. References Bi, S., Zeng, Y., & Zhang, R. (2019). Wireless powered communication networks: Techniques, applications, and future directions. IEEE Communications Surveys & Tutorials, 21(2), 1324–1353. https://doi.org/10.1109/COMST.2018.2881084 Gartner. (2023). Forecast: Internet of Things—Endpoints and associated services, worldwide, 2023. Gartner Research. Kim, S., Park, J., & Lee, K. (2023). AI-driven optimization of RF energy harvesting for IoT devices using deep reinforcement learning. IEEE Internet of Things Journal, 10(4), 3124–3138. https://doi.org/10.1109/JIOT.2023.3245678 Ku, M.-L., Li, W., Chen, Y., & Liu, K. J. R. (2016). Advances in energy harvesting communications: Past, present, and future challenges. IEEE Communications Surveys & Tutorials, 18(2), 1384–1412. https://doi.org/10.1109/COMST.2015.2497328 Lu, X., Wang, P., Niyato, D., Kim, D. I., & Han, Z. (2021). Wireless charger networking for mobile devices: Fundamentals, standards, and applications. IEEE Wireless Communications, 22(2), 32–41. https://doi.org/10.1109/MWC.2015.7091061 R Core Team. (2023). R: A language and environment for statistical computing (Version 4.3.1) [Computer software]. R Foundation for Statistical Computing. https://www.R-project.org/ Statista. (2023). Number of Internet of Things (IoT) connected devices worldwide from 2019 to 2030. https://www.statista.com/statistics/1183457/iot-connected-devices-worldwide/ Tran, N. H., Hoang, D. T., Niyato, D., Nguyen, C. M., & Han, Z. (2021). The roadmap to 6G: AI-empowered wireless networks. IEEE Communications Magazine, 59(1), 112–117. https://doi.org/10.1109/MCOM.001.2000406 United Nations Environment Programme. (2022). Global e-waste monitor 2022: Electronic waste management in the circular economy. United Nations Publications. Zhang, J., Guo, H., & Liu, H. (2022). Intelligent reflecting surface aided wireless power transfer for IoT devices. IEEE Transactions on Communications, 70(5), 3381–3396. https://doi.org/10.1109/TCOMM.2022.3156789 How to Cite Lucky Joseph, O., & Osaremwinda, O. (2026). AI-ENABLED WIRELESS POWER TRANSFER ARCHITECTURES FOR SUSTAINABLE IoT ECOSYSTEMS. GPH-International Journal of Computer Science and Engineering, 9(1), 176-188. https://doi.org/10.5281/zenodo.22809199