Work-in-Progress: Making Machine Learning Real-Time Predictable
Work-in-Progress: Making Machine Learning Real-Time Predictable
复制标题
DOI：
10.1109/rtss.2018.00029
复制
发表时间：
2018-12
期刊：
影响因子：
--
通讯作者：
Hang Xu;F. Mueller
中科院分区：
文献类型：
--
作者：
Hang Xu;F. Mueller
边缘计算设备上的机器学习（ML）作为使控制系统更加智能和自主的一种手段，在行业中越来越流行。新的趋势是利用嵌入式边缘设备，因为它们拥有比以前更高的计算能力和更大的内存，以执行以前仅限于云托管部署的ML任务。在这项工作中，我们评估了实时可预测性，并通过比较传统云服务与基于边缘的服务来考虑数据隐私问题。我们通过调查ML问题是否会为一组广泛使用的ML库提供实时可预测的服务，来确定适合边缘设备的ML问题子集。我们专门增强了Caffe库，使其更适合实时可预测性。然后，我们在嵌入式系统上部署具有高准确度分数的ML模型，将其暴露于来自现场的行业传感器数据，以证明其实时处理的有效性和适用性。
Machine learning (ML) on edge computing devices is becoming popular in the industry as a means to make control systems more intelligent and autonomous. The new trend is to utilize embedded edge devices, as they boast higher computational power and larger memories than before, to perform ML tasks that had previously been limited to cloud-hosted deployments. In this work, we assess the real-time predictability and consider data privacy concerns by comparing traditional cloud services with edge-based ones for certain data analytics tasks. We identify the subset of ML problems appropriate for edge devices by investigating if they result in real-time predictable services for a set of widely used ML libraries. We specifically enhance the Caffe library to make it more suitable for real-time predictability. We then deploy ML models with high accuracy scores on an embedded system, exposing it to industry sensor data from the field, to demonstrates its efficacy and suitability for real-time processing.