A Machine Learning-Based Toolbox for P4 Programmable Data-Planes
- 16 May 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network and Service Management
- Vol. 21 (4) , 4450-4465
Abstract
Intelligent data-planes (IDPs) can enhance network service performance and adaptation speed by executing one or more machine learning (ML) models directly on the served flows. The real-time ML inference enables line-speed decision-making for some traffic management functionalities. Due to the inherent scarcity of both the computational and memory resources and the strict high-speed per-packet processing demands, existing IDP deployments either realize only a limited set of ML models such as decision trees, or require substantial modifications in the switch hardware. In this paper, we propose INQ-MLT, a novel ML-based management toolbox to address the aforementioned limitations. INQ-MLT delegates the task of training various ML models to the control-plane. The latter adopts a tailored quantization-aware training process to compensate for the effect of precision loss resulting from quantization. The toolbox then employs a quantization mechanism to transform the trained ML model parameters (e.g., weights and activations) from floating-point representations to compact 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 analyze the performance of INQ-MLT, we quantify the accuracy loss resulting from the quantization step through rigorous theoretical analysis. A proof-of-concept implementation of the proposed toolbox is developed using P4-based software switches. Experiments on two use-cases demonstrate that the deployed quantized models have almost no loss of accuracy when compared to their floating-point counterparts.Keywords
Funding Information
- Discovery Grant from the Natural Sciences and Engineering Research Council of Canada
This publication has 64 references indexed in Scilit:
- A survey on data plane programming with P4: Fundamentals, advances, and applied researchJournal of Network and Computer Applications, 2022
- NNSplit-SØREN: Supporting the model implementation of large neural networks in a programmable data planeComputer Networks, 2022
- Pruning and quantization for deep neural network acceleration: A surveyNeurocomputing, 2021
- Deep Learning for Network Traffic Monitoring and Analysis (NTMA): A SurveyComputer Communications, 2021
- In-band Network Telemetry: A SurveyComputer Networks, 2021
- SwitchTree: in-network computing and traffic analyses with Random ForestsNeural Computing and Applications, 2020
- Towards Minimum Inter-Controller Delay Time in Software Defined NetworkingProcedia Computer Science, 2020
- Deep Learning Approach for Intelligent Intrusion Detection SystemIEEE Access, 2019
- A Survey on Regular Expression Matching for Deep Packet Inspection: Applications, Algorithms, and Hardware PlatformsIEEE Communications Surveys & Tutorials, 2016
- Finite precision error analysis of neural network hardware implementationsIEEE Transactions on Computers, 1993