在微控制器上实现低功耗交通分类，精度超96%且能耗极低。
Energy-Efficient Deep Learning for Traffic Classification on Microcontrollers
- 设计轻量1D-CNN，通过硬件感知搜索优化模型结构。
- 在ISCX VPN-NonVPN数据集上达96.59%准确率，仅88.26K参数。
- 支持整数8位量化，适合嵌入式设备部署，适合物联网安全场景。
本文提出一种面向资源受限微控制器的实用深度学习方法，用于高效能流量分类（TC），广泛应用于基于物联网的智能系统与通信网络。目标是平衡精度、计算效率与实际可部署性。为此，我们开发了一种轻量级1D-CNN，通过硬件感知神经架构搜索（HW-NAS）优化，其在ISCX VPN-NonVPN数据集上达到96.59%准确率，仅需88.26K参数、最大张量尺寸20.12K、10.08M FLOPs。该模型具备跨任务泛化能力，准确率在94%至99%之间。为实现部署，模型被量化至INT8，相较浮点32位仅损失1-2%精度。我们在STM32F746G-DISCO和Nucleo-F401RE两款微控制器上评估真实推理性能，分别实现31.43ms与115.40ms的推理延迟，单次推理能耗为7.86mJ与29.10mJ。结果证明了设备端加密流量分析的可行性，推动了可扩展、低功耗的物联网安全解决方案。
原文摘要 · Abstract (English)
In this paper, we present a practical deep learning (DL) approach for energy-efficient traffic classification (TC) on resource-limited microcontrollers, which are widely used in IoT-based smart systems and communication networks. Our objective is to balance accuracy, computational efficiency, and real-world deployability. To that end, we develop a lightweight 1D-CNN, optimized via hardware-aware neural architecture search (HW-NAS), which achieves 96.59% accuracy on the ISCX VPN-NonVPN dataset with only 88.26K parameters, a 20.12K maximum tensor size, and 10.08M floating-point operations (FLOPs). Moreover, it generalizes across various TC tasks, with accuracies ranging from 94% to 99%. To enable deployment, the model is quantized to INT8, suffering only a marginal 1-2% accuracy drop relative to its Float32 counterpart. We evaluate real-world inference performance on two microcontrollers: the high-performance STM32F746G-DISCO and the cost-sensitive Nucleo-F401RE. The deployed model achieves inference latencies of 31.43ms and 115.40ms, with energy consumption of 7.86 mJ and 29.10 mJ per inference, respectively. These results demonstrate the feasibility of on-device encrypted traffic analysis, paving the way for scalable, low-power IoT security solutions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。