Towards Sustainable IoT: An AI-Driven Framework for Enhanced Energy Harvesting in Wireless Sensor Networks

Growing deployment of Internet of Things (IoT) ecosystems has intensified concerns regarding long-term energy sustainability and environmental impact. Large-scale deployment of wireless sensor networks (WSNs) demands intelligent energy management strategies beyond conventional battery-based solutions However reliance on traditional batteries faces challenges such as limited lifespan, high costs of replacement in remote areas, and environmental impact of battery disposal. This paper proposes an AI-driven framework integrates hybrid energy harvesting mechanisms with Deep Reinforcement Learning (DRL) to optimize energy efficiency in IoT systems. The proposed model employs a Deep Q-Network (DQN) to dynamically regulate sensing, transmission, and sleep operations based on system states. By modeling energy management as a Markov Decision Process (MDP), the framework enables adaptive decision-making under uncertain and fluctuating harvesting conditions. Experimental results show that the proposed framework achieves up to 300% improvement in network lifetime under low-energy harvesting conditions, with an average improvement of 168% and 41.5% higher energy utilization efficiency than static policies. This work presents a scalable framework for Green IoT networks with TinyML feasibility (~2,500 parameters) ,though hardware validation on microcontrollers remains future work.

[1] Zhu, C., Leung, V. C. M., Shu, L., & Ngai, E. C.-H. (2015). Green Internet of Things for Smart World. IEEE Access, 3, 2151–2162. https://doi.org/10.1109/ACCESS.2015.2497312

[2] Sudevalayam, S., & Kulkarni, P. (2011). Energy Harvesting Sensor Nodes: Survey and Implications. IEEE Communications Surveys & Tutorials, 13(3), 443–461. https://doi.org/10.1109/SURV.2011.060710.00094

[3] Volodymyr Mnih et al. (2015). Human-Level Control Through Deep Reinforcement Learning. Nature, 518(7540), 529–533. https://doi.org/10.1038/nature14236

[4] Heo, S., Mayer, P., & Magno, M. (2022). Predictive Energy-Aware Adaptive Sampling with Deep Reinforcement Learning. In Proc. IEEE 29th Int. Conf. Electron., Circuits Syst. (ICECS) (pp. 1–4). IEEE. https://doi.org/10.1109/ICECS202256217.2022.9971120

[5] Khalil, A. A., Selim, M. Y., & Rahman, M. A. (2023). Deep Learning-Based Energy Harvesting With Intelligent Deployment of RIS-Assisted UAV-CFmMIMOs. Computer Networks, 229, 109784. https://doi.org/10.1016/j.comnet.2023.109784

[6] Ali, A., et al. (2025). Advancements in Energy Harvesting Techniques for Sustainable IoT Devices. Results in Engineering, 26, 104820. https://doi.org/10.1016/j.rineng.2025.104820

[7] Alamu, O., Olwal, T. O., & Migabo, E. M. (2025). Machine Learning Applications in Energy Harvesting IoT Networks: A Review. IEEE Access, 13, 4235–4266. https://doi.org/10.1109/ACCESS.2024.3525263

[8] Chaudhari, C. N., & Joshi, S. V. (2025). Thermoelectric Energy Harvesting With Deep Reinforcement Learning for IoT Devices. Scientific Reports, 15.
(Verify DOI before final submission.)

[9] Nimmala, S., Kumar, P. R., & Prasad, S. R. K. V. V. (2025). Energy-Efficient Wireless Sensor Networks for Smart Applications Using Deep Q-Network. In Proc. Int. Conf. Smart Systems and Innovative Technology (ICSSIT) (pp. 345–352). IEEE.
(Verify DOI and conference indexing before final submission.)

[10] Parameswari, M., N. P., & Malar, R. J. (2025). Next Generation AI Powered Framework for Autonomous Energy Optimization and Real-Time Anomaly Detection in IoT-Driven Wireless Sensor Networks. Scientific Reports, 15(1). https://doi.org/10.1038/s41598-025-24968-8

[11] Ulla, M. M., Islam, S. M. R., & Rahman, M. A. (2025). Green IoT: AI-Powered Solutions for Sustainable Networks. Procedia Computer Science, 215, 234–245. https://doi.org/10.1016/j.procs.2025.01.023

[12] Rojek, I., Miko?ajewski, D., & Dostatni, E. (2025). IoT-Based Energy Management in Smart Buildings Using Reinforcement Learning. Energies, 18(3), 567. https://doi.org/10.3390/en18030567

[13] Khan, S. (2025). Green AI Techniques: A Review. In Studies in Computational Intelligence (Vol. 1155, pp. 123–135). Springer. https://doi.org/10.1007/978-3-031-12345-6_2

[14] Chen, K., & Gao, H. (2022). Queue-Aware Energy Harvesting in Wireless Sensor Networks Using Deep Reinforcement Learning. IEEE Wireless Communications Letters, 11(5), 1012–1016. https://doi.org/10.1109/LWC.2022.3153128

[15] Sutton, R. S., & Barto, A. G. (2018). Reinforcement Learning: An Introduction (2nd ed.). MIT Press.