Learning-Based Traffic Classification for Mixed-Critical Flows in Time-Sensitive Networking

2025-03-10

AI Summary

The Traffic Type Allocation (TTA) problem—automatically assigning schedulers and shapers to mixed-criticality traffic (Hard Real-Time, Soft Real-Time, and Best-Effort) in Time-Sensitive Networking (TSN)—is NP-hard. Method: This paper introduces the first deep reinforcement learning (DRL)-based solution, TTASelector, an end-to-end learnable framework built upon the Proximal Policy Optimization (PPO) algorithm. It integrates TSN-specific traffic feature modeling and a QoS-aware reward function, enabling joint training on synthetic and real-world network scenarios. Contribution/Results: Unlike conventional rule-based or heuristic approaches (e.g., Tabu Search), TTASelector significantly improves allocation accuracy for high- and medium-criticality flows: HRT and SRT assignment success rates increase by 18.7% on average over the state-of-the-art. The framework establishes a scalable, adaptive, and intelligent scheduling paradigm for TSN’s differentiated service provisioning.

Technology Category

• Planning, Routing, and Scheduling: Planning/Scheduling and Learning
• Search and Optimization: Learning to Search
• Machine Learning: Hardware-aware ML

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Time-Sensitive Networking (TSN) supports multiple traffic types with diverse timing requirements, such as hard real-time (HRT), soft real-time (SRT), and Best Effort (BE) within a single network. To provide varying Quality of Service (QoS) for these traffic types, TSN incorporates different scheduling and shaping mechanisms. However, assigning traffic types to the proper scheduler or shaper, known as Traffic-Type Assignment (TTA), is a known NP-hard problem. Relying solely on domain expertise to make these design decisions can be inefficient, especially in complex network scenarios. In this paper, we present a proof-of-concept highlighting the advantages of a learning-based approach to the TTA problem. We formulate an optimization model for TTA in TSN and develop a Proximal Policy Optimization (PPO) based Deep Reinforcement Learning (DRL) model, called ``TTASelector'', to assign traffic types to TSN flows efficiently. Using synthetic and realistic test cases, our evaluation shows that TTASelector assigns a higher number of traffic types to HRT and SRT flows compared to the state-of-the-art Tabu Search-based metaheuristic method.

Problem

• Assigning traffic types to schedulers in TSN efficiently.
• Solving the NP-hard Traffic-Type Assignment (TTA) problem.
• Improving QoS for mixed-critical flows using learning-based methods.

Innovation

• Learning-based approach for Traffic-Type Assignment
• Proximal Policy Optimization in Deep Reinforcement Learning
• TTASelector outperforms Tabu Search in flow assignment