This letter advocates the use of a Tiny Machine Learning (TinyML) model for energy-efficient semantic data retrieval from the Internet of Things (IoT) devices. In our framework, the edge server (ES) transmits task-related TinyML model before starting data collection so that IoT devices can send only semantically relevant data. However, receiving the ML model and its processing at the IoT devices consumes additional energy. We consider the specific instance of image retrieval and investigate the gain brought by the proposed scheme in terms of energy efficiency, considering both the energy cost of introducing the ML model as well as that of wireless communication. Numerical evaluation shows that, compared to a baseline scheme, the proposed scheme can realize both high retrieval accuracy and high energy efficiency, which reaches up to 70% energy reduction when the number of stored images is sufficiently large. Although focused on image retrieval, our analysis is indicative of a broader set of communication scenarios in which the preemptive transmission of an ML model can increase communication efficiency.

翻译：本文倡导利用微型机器学习模型实现物联网设备的语义数据高效检索。在所提出的框架中，边缘服务器在数据采集开始前先传输与任务相关的微型机器学习模型，使得物联网设备仅需发送语义相关的数据。然而，物联网设备接收并处理该机器学习模型会消耗额外能量。我们以图像检索为例，综合考虑引入机器学习模型的能量开销与无线通信的能量成本，评估了所提方案在能效方面的增益。数值评估表明：与基准方案相比，本方案可在实现高检索精度的同时显著提升能效，当存储图像数量足够大时，能量消耗可降低70%。尽管本文聚焦于图像检索场景，但分析结果表明，在更广泛的通信场景中，预发机器学习模型可有效提升通信效率。