Emerging applications, such as robot-assisted eldercare and object recognition, generally employ deep learning neural networks (DNNs) and naturally require: i) handling streaming-in inference requests and ii) adapting to possible deployment scenario changes. Online model fine-tuning is widely adopted to satisfy these needs. However, an inappropriate fine-tuning scheme could involve significant energy consumption, making it challenging to deploy on edge devices. In this paper, we propose EdgeOL, an edge online learning framework that optimizes inference accuracy, fine-tuning execution time, and energy efficiency through both inter-tuning and intra-tuning optimizations. Experimental results show that, on average, EdgeOL reduces overall fine-tuning execution time by 64%, energy consumption by 52%, and improves average inference accuracy by 1.75% over the immediate online learning strategy.

翻译：新兴应用，如机器人辅助养老和物体识别，通常采用深度神经网络（DNN），自然要求：i）处理流式推理请求，ii）适应可能的部署场景变化。在线模型微调被广泛采用以满足这些需求。然而，不恰当的微调方案可能导致显著的能量消耗，使其在边缘设备上部署变得困难。本文提出EdgeOL，一种边缘在线学习框架，通过调优间和调优内优化，在推理精度、微调执行时间和能效方面实现优化。实验结果表明，与即时在线学习策略相比，EdgeOL平均减少微调执行时间64%，降低能耗52%，并提升平均推理精度1.75%。