MLIoT: An End-to-End Machine Learning System for the Internet-of-Things
MLIoT: An End-to-End Machine Learning System for the Internet-of-Things
复制标题
DOI：
10.1145/3450268.3453522
复制
发表时间：
2021-05
期刊：
影响因子：
--
通讯作者：
Sudershan Boovaraghavan;Anurag Maravi;Prahaladha Mallela;Yuvraj Agarwal
中科院分区：
文献类型：
--
作者：
Sudershan Boovaraghavan;Anurag Maravi;Prahaladha Mallela;Yuvraj Agarwal
现代物联网(IoT)应用，从情景感知到语音助手，都依赖于基于ML的培训和服务系统，使用预先训练的模型来提供预测。然而，现实世界的物联网环境是多样化的，拥有丰富的物联网传感器，需要使用相对较少的训练数据为每个设置个性化ML模型。现有的大多数通用ML系统都是针对特定和专用的硬件资源进行优化的，不能适应不断变化的资源和不同的物联网应用需求。为了弥补这一差距，我们提出了MLIoT，这是一个端到端的机器学习系统，旨在支持物联网应用的整个生命周期。MLIoT根据富有表现力的特定于应用的策略自动培训、优化和提供模型，从而适应不同的物联网数据源、物联网任务和计算资源。MLIoT还可以在保持准确性和性能的同时，通过启用重新培训和动态更新提供的模型来适应物联网环境或计算资源的变化。我们对一组基准测试的评估表明，MLIoT可以以可扩展的方式处理多个物联网任务，每个任务都有单独的需求，同时保持高精度和高性能。我们将MLIoT与两个最先进的手动调整系统和一个商业ML系统进行了比较，结果表明，MLIoT在减少或保持延迟的同时，将准确率提高了50%-75%。
Modern Internet of Things (IoT) applications, from contextual sensing to voice assistants, rely on ML-based training and serving systems using pre-trained models to render predictions. However, real-world IoT environments are diverse, with rich IoT sensors and need ML models to be personalized for each setting using relatively less training data. Most existing general-purpose ML systems are optimized for specific and dedicated hardware resources and do not adapt to changing resources and different IoT application requirements. To address this gap, we propose MLIoT, an end-to-end Machine Learning System tailored towards supporting the entire lifecycle of IoT applications. MLIoT adapts to different IoT data sources, IoT tasks, and compute resources by automatically training, optimizing, and serving models based on expressive application-specific policies. MLIoT also adapts to changes in IoT environments or compute resources by enabling re-training, and updating models served on the fly while maintaining accuracy and performance. Our evaluation across a set of benchmarks show that MLIoT can handle multiple IoT tasks, each with individual requirements, in a scalable manner while maintaining high accuracy and performance. We compare MLIoT with two state-of-the-art hand-tuned systems and a commercial ML system showing that MLIoT improves accuracy from 50% - 75% while reducing or maintaining latency.