Leveraging DVFS for Energy-Efficient and QoS-aware Edge Video Analytics

We present a novel scheduling framework for energy-efficient video analytics at the edge. The proposed approach dynamically adjusts GPU frequency and batch size to optimize inference execution while ensuring QoS compliance. It integrates a priority queue for QoS-aware scheduling and leverages offline profiling and ML-based estimation to select energy-optimal configurations. Based on these configurations, it employs a priority-based scheduler with greedy batching and adaptive waiting strategies to efficiently dispatch inference requests. Experimental evaluation conducted on an NVIDIA Jetson Xavier AGX device demonstrates a ~ 28% improvement in frames served per joule compared to a baseline with no scheduler. This outperforms a static batch scheduler (32 frames per batch) by ~ 15% and a time-triggered scheduler (batch formation every 200 ms) by ~ 29%, while introducing minimal increase in QoS violations (5%) relative to the best-performing policy.