arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.09623cs.DCcs.AIcs.LGcs.NIcs.PF
收藏

异构边缘-云连续体中的自适应DNN分区与卸载

Adaptive AI Task Partitioning and Safe Offloading in Heterogeneous Edge-Cloud Continuum

Anonymous Institute(匿名机构);Department of Computer and Systems Sciences(计算机与系统科学系)

Akuen Akoi Deng, Eimantas Butkus, Alfreds Lapkovskis, Praveen Kumar Donta

AI总结:

本文提出一种动态分区框架,通过实时评估环境变化优化神经网络层分配,降低能耗和端到端延迟。

摘要:

近年来,人工智能在资源受限的物联网设备上的应用显著增长。然而,现有方法在边缘-云连续体上进行DNN分区和卸载时通常依赖静态方法,忽略了运行时动态。此外,它们通常在模拟环境中评估,而不是在真实硬件上。为了解决这一差距,我们提出了一种框架,动态地将神经网络层分割到异构连续体上。该框架在启动时对模型进行配置,测量节点之间的网络链路条件,并定期重新评估分区以适应环境变化。我们创建了一个物理测试床,包括一个Raspberry Pi边缘设备、一台笔记本电脑的雾和一台高性能台式机作为云。我们对三个广泛采用的卷积神经网络进行了评估:VGG16、AlexNet和MobileNetV2。我们的结果表明,与静态分区基线相比,该框架在能耗和端到端延迟上分别减少了27.09-35.82%和6.34-22.92%。这些发现证实了自适应方法优于静态分区方法。

英文摘要:

In recent years, the use of artificial intelligence on resource-constrained IoT devices has grown significantly. However, existing approaches to AI task partitioning and offloading across the edge-cloud continuum typically rely on static methods that ignore runtime dynamics. Furthermore, they are often evaluated in simulated environments rather than on real hardware. To address this gap, we propose a framework that dynamically splits neural network layers across the heterogeneous continuum. The framework profiles the model at startup, measures network link conditions between nodes, and periodically re-evaluates the partition to adapt to environmental changes. We created a physical testbed comprising a Raspberry Pi edge device, a laptop fog, and a high-performance desktop PC as the cloud. We evaluated the framework over three widely adopted convolutional neural networks: VGG16, AlexNet, and MobileNetV2. Our results show that the framework achieves reductions in energy and end-to-end latency of 27.09--35.82% and 6.34--22.92%, respectively, compared to a static partitioning baseline. These findings confirm the superiority of adaptive to static partitioning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑