Energy-Efficient Deep Learning Architectures for IoT Devices
Main Article Content
Abstract
The integration of deep learning (DL) into Internet of Things (IoT) devices has enabled advanced functionalities such as real-time object detection, activity recognition, and predictive maintenance. However, the deployment of traditional DL models on resource-constrained IoT hardware presents significant challenges related to energy consumption, memory limitations, and computational capacity. This study investigates energy-efficient deep learning architectures specifically designed for IoT environments, focusing on lightweight models, compression techniques, and hardware acceleration. The research explores methods such as pruning, quantization, and knowledge distillation to optimize inference without compromising performance. It also evaluates popular low-power architectures like MobileNet, SqueezeNet, and Tiny-YOLO across various edge computing platforms. By addressing the trade-offs between accuracy, energy efficiency, and latency, this study contributes to the development of sustainable AI solutions for smart environments. The findings aim to guide the design and deployment of intelligent IoT systems that are both power-efficient and capable of delivering real-time insights.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
References
Akmandor, A. O., Hongxu, Y. I. N., & Jha, N. K. (2018). Smart, secure, yet energy-efficient, internet-of-things sensors. IEEE Transactions on Multi-Scale Computing Systems, 4(4), 914-930.
Alapati, Navya Krishna. (2024). Graph-based Semi-Supervised Learning for Fraud Detection in Finance. International Research Journal of Engineering Science Technology and Innovation. 11. 211-220.
Alapati, Navya Krishna. (2025). Real-time data analytics and processing for adaptive load balancing in cloud infrastructures. World Journal of Advanced Engineering Technology and Sciences. 14. 538-546. 10.30574/wjaets.2025.14.3.0179.
Azar, J., Makhoul, A., Barhamgi, M., & Couturier, R. (2019). An energy efficient IoT data compression approach for edge machine learning. Future Generation Computer Systems, 96, 168-175.
Dabbir, V. R. K. (2024). Applying generative adversarial networks for forecasting sales in retail businesses. International Journal of Creative Research Thoughts, 12(12), 1234–1245.
Dabbir, V. R. K., & Logeshwaran, J. (2025, February). Integrating big data management with machine learning in cloud environments. In Proceedings of the 3rd International Conference on Networks and Cryptology (NETCRYPT-25).
Fanariotis, A., Orphanoudakis, T., Kotrotsios, K., Fotopoulos, V., Keramidas, G., & Karkazis, P. (2023). Power efficient machine learning models deployment on edge IoT devices. Sensors, 23(3), 1595.
Han, T., Muhammad, K., Hussain, T., Lloret, J., & Baik, S. W. (2020). An efficient deep learning framework for intelligent energy management in IoT networks. IEEE Internet of Things Journal, 8(5), 3170-3179.
Jain, N. (2025). Application of deep reinforcement learning for real-time demand response in smart grids. International Research Journal of Modernization in Engineering Technology and Science. https://doi.org/10.56726/IRJMETS6915
Jain, N., & Bej, S. R. (2024). AI-powered cost optimization in IoT: A systematic review of machine learning and predictive analytics in TCO reduction. International Journal of Engineering, Science and Mathematics, 13(12), 64–83.
Jayakumar, H., Raha, A., Kim, Y., Sutar, S., Lee, W. S., & Raghunathan, V. (2016, January). Energy-efficient system design for IoT devices. In 2016 21st Asia and South Pacific design automation conference (ASP-DAC) (pp. 298-301). IEEE.
Kaiser, M., Griessl, R., Kucza, N., Haumann, C., Tigges, L., Mika, K., ... & Heyn, H. (2022, March). VEDLIoT: very efficient deep learning in IoT. In 2022 Design, Automation & Test in Europe Conference & Exhibition (DATE) (pp. 963-968). IEEE.
Kaur, N., & Sood, S. K. (2015). An energy-efficient architecture for the Internet of Things (IoT). IEEE Systems Journal, 11(2), 796-805.
Kim, K., Jang, S. J., Park, J., Lee, E., & Lee, S. S. (2023). Lightweight and energy-efficient deep learning accelerator for real-time object detection on edge devices. Sensors, 23(3), 1185.
Kumar, M., Zhang, X., Liu, L., Wang, Y., & Shi, W. (2020, May). Energy-efficient machine learning on the edges. In 2020 IEEE international parallel and distributed processing symposium Workshops (IPDPSW) (pp. 912-921). IEEE.
Musunuri, A. (2025). Automation at scale: An AI-first approach to data analysis. International Journal of Innovative Research in Computer and Communication Engineering, 13(4), 3035–3043.
Musunuri, A. (2025, January). Enterprise data security and integration with LLMs. International Journal of Innovative Research in Science, Engineering and Technology, 14(1), 156–162. https://doi.org/10.15680/IJIRSET.2025.1401018.
Osta, M., Alameh, M., Younes, H., Ibrahim, A., & Valle, M. (2019, November). Energy efficient implementation of machine learning algorithms on hardware platforms. In 2019 26th IEEE International Conference on Electronics, Circuits and Systems (ICECS) (pp. 21-24). IEEE.
Sharma, P. K. (2025). Real-time fraud detection in banking with generative artificial intelligence. International Journal of Computer Engineering and Technology, 16(1), 1051–1064.
Putra, M. A. P., Hermawan, A. P., Kim, D. S., & Lee, J. M. (2023). Data prediction-based energy-efficient architecture for industrial iot. IEEE Sensors Journal, 23(14), 15856-15866.
Shafique, M., Hafiz, R., Javed, M. U., Abbas, S., Sekanina, L., Vasicek, Z., & Mrazek, V. (2017, July). Adaptive and energy-efficient architectures for machine learning: Challenges, opportunities, and research roadmap. In 2017 IEEE Computer society annual symposium on VLSI (ISVLSI) (pp. 627-632). IEEE.
Shah, S. F. A., Iqbal, M., Aziz, Z., Rana, T. A., Khalid, A., Cheah, Y. N., & Arif, M. (2022). The role of machine learning and the internet of things in smart buildings for energy efficiency. Applied Sciences, 12(15), 7882.
Sharma, P. (2025, March). Integrating generative models in business process automation for cost reduction and efficiency. International Research Journal of Engineering and Technology, 12(3), 450–456.
Singh, N., Jain, N., & Jain, S. (2025). AI and IoT in digital payments: Enhancing security and efficiency with smart devices and intelligent fraud detection. International Research Journal of Modernization in Engineering Technology and Science, 6(12), 982–991. https://doi.org/10.56726/IRJMETS69230
Sunkara, V. L. B. (2025, February). A smart threat detection model for complex routing networks using AI-based recurrent neural networks. International Journal of Computer Engineering & Technology
Sunkara, V. L. B. (2025, March). An intelligent routing framework for high-traffic networks using deep learning. International Journal of Innovative Research in Computer and Communication Engineering.
Tekin, N., Acar, A., Aris, A., Uluagac, A. S., & Gungor, V. C. (2023). Energy consumption of on-device machine learning models for IoT intrusion detection. Internet of Things, 21, 100670.
Venkataramani, S., Roy, K., & Raghunathan, A. (2016, January). Efficient embedded learning for IoT devices. In 2016 21st Asia and South Pacific Design Automation Conference (ASP-DAC) (pp. 308-311). IEEE.