GreenPipe：Kubernetes边缘节点上容器化DNN推理的功耗建模
GreenPipe: Power Modeling for Containerized DNN Inference on Kubernetes Edge Nodes
浏览论文内容
中文总结 AI 辅助
针对ARM边缘节点无硬件功耗计数器的DNN推理功耗估计难题，提出GreenPipe流水线构建多资源回归模型，在Raspberry Pi 4上评估显示MAPE优于基线，同时揭示性能-能耗权衡。
中文摘要 AI 辅助
分布式DNN推理越来越多地部署在容器化的边缘-云环境中，工作负载在设备上运行或通过网络暴露给远程客户端。在没有RAPL等硬件功耗计数器的资源受限ARM节点上进行准确的在线功耗估计仍然是一个挑战，仅基于CPU的模型无法捕获多资源行为。我们提出GreenPipe，这是一个自动化的分析-训练-验证流水线，可从外部功率计测量值构建多资源回归模型，并将功耗按比例分配给容器。GreenPipe在K3s边缘-云测试床中的Raspberry Pi 4边缘节点上进行评估，涵盖三种视觉模型、多种精度、线程数以及本地和服务场景下的DNN推理。系统级MAPE为6.3-9.4%，相比仅基于CPU压力和利用率的基线方法，平均MAPE提升26.9%。我们联合报告了每次推理的延迟和能耗，揭示了不同工作负载配置下的性能-能耗权衡。
英文摘要
Distributed DNN inference is increasingly deployed in containerized edge-cloud environments, where workloads run on-device or are exposed to remote clients over the network. Accurate online power estimation on resource-constrained ARM nodes without hardware power counters such as RAPL remains a challenge, and CPU-only models fail to capture multi-resource behavior. We present GreenPipe, an automated profiling-training-validation pipeline that builds multi-resource regression models from external power meter measurements and attributes power to containers proportionally. GreenPipe is evaluated on a Raspberry Pi 4 edge node in a K3s edge-cloud testbed, covering DNN inference with three vision models, multiple precisions, thread counts, and both local and serving scenarios. System-level MAPE is 6.3-9.4%, improving over CPU-stress and utilization-only baselines by 26.9% MAPE on average. We jointly report inference latency and energy per inference, exposing performance-energy trade-offs across workload configurations.
发表机构
- Universitat Politècnica de Catalunya（加泰罗尼亚理工大学）
- Barcelona Supercomputing Center（巴塞罗那超级计算中心）
- University of Oslo（奥斯陆大学）
机构由 AI 辅助整理，请以论文原文为准。
