首页|Study Results from University of Ottawa Update Understanding of Machine Learning (A Machine Learning-based Toolbox for P4 Programmable Data-planes)
Study Results from University of Ottawa Update Understanding of Machine Learning (A Machine Learning-based Toolbox for P4 Programmable Data-planes)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
2024 OCT 03 (NewsRx)-By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Current study results on Machine Learn ing have been published. According to news reporting originating from Ottawa, Ca nada, by NewsRx correspondents, research stated, "Intelligent dataplanes (IDPs) can enhance network service performance and adaptation speed by executing one o r more machine learning (ML) models directly on the served flows. The real-time ML inference enables line-speed decision-making for some traffic management func tionalities." Financial support for this research came from Natural Sciences and Engineering R esearch Council of Canada (NSERC). Our news editors obtained a quote from the research from the University of Ottaw a, "Due to the inherent scarcity of both the computational and memory resources and the strict high-speed per-packet processing demands, existing IDP deployment s either realize only a limited set of ML models such as decision trees, or requ ire substantial modifications in the switch hardware. In this paper, we propose INQ-MLT, a novel ML-based management toolbox to address the aforementioned limit ations. INQ-MLT delegates the task of training various ML models to the control- plane. The latter adopts a tailored quantization-aware training process to compe nsate for the effect of precision loss resulting from quantization. The toolbox then employs a quantization mechanism to transform the trained ML model paramete rs (e.g., weights and activations) from floating-point representations to compac t low-precision fixed integer values that can be easily processed and stored in the data-plane. Finally, the trained model is deployed into the IDP pipeline by restricting all its inference operations to basic arithmetic operations. To anal yze the performance of INQ-MLT, we quantify the accuracy loss resulting from the quantization step through rigorous theoretical analysis. A proof-of-concept imp lementation of the proposed toolbox is developed using P4-based software switche s."
OttawaCanadaNorth and Central Americ aCyborgsEmerging TechnologiesMachine LearningUniversity of Ottawa
NETL
NSTL
