Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{206819,
        author = {Varsha Puranik and Subhramanya Bhat},
        title = {Lightweight Model Architectures for Sustainable Edge Analytics},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {no},
        pages = {572-576},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=206819},
        abstract = {The exponential rise in IoT devices has resulted in an increased need for intelligence in the cloud-edge environment in near real-time. However, due to the stringent requirements of edge computing hardware in terms of processing power, memory, and energy available, the use of deep learning networks is restricted. This paper examines the emergence of Lightweight Model Architectures as one of the key enablers of Sustainable Edge Analytics. Specifically, we explore a multi-step strategy involving pruning, quantization, and knowledge distillation for reducing the overhead of machine learning systems. The focus of our investigation is on Green AI with an emphasis on measuring energy efficiency along with accuracy during the design phase. The findings from our experimentation suggest that through hardware-aware design it is possible to realize considerable improvements in terms of energy usage as well as latency without compromising on accuracy levels.},
        keywords = {Cloud-Edge Computing, Deep Compression, Energy Efficiency, Green AI, Knowledge Distillation, Lightweight Architectures, Model Quantization, Neural Network Pruning, Sustainable Computing},
        month = {July},
        }