The rapid proliferation of the Internet of Things (IoT) has created an urgent need for on-device intelligence that balances high computational demands with stringent energy constraints. Existing edge inference frameworks struggle to deploy generative artificial intelligence (AI) models efficiently on low-power devices, often sacrificing fidelity for efficiency or lacking adaptability to dynamic conditions. To address this gap, we propose a generative AI edge inference framework integrating lightweight architecture compression, adaptive quantization, and energy-aware scheduling. Extensive experiments on CIFAR-10, Tiny-ImageNet, and IoT-SensorStream show that our method reduces energy consumption by up to 31% and inference latency by 27% compared with state-of-the-art baselines, while consistently improving generative quality. Robustness tests further confirm resilience under noise, cross-task, and cross-dataset conditions, and ablation studies validate the necessity of each module. Finally, deployment in a hospital IoT laboratory demonstrates real-world feasibility. These results highlight both the theoretical contribution of unifying compression, quantization, and scheduling, and the practical potential for sustainable, scalable, and reliable deployment of generative AI in diverse IoT ecosystems.
Xie et al. (Fri,) studied this question.