More Like this

1. Designing Traffic Management Strategies for a Heterogeneous Traffic Network

   https://doi.org/10.1016/j.ifacol.2022.11.263  

   Shahri, Pouria Karimi; HomChaudhuri, Baisravan; Ghaffari, Azad; Ghasemi, Amir H. (January 2022, IFAC-PapersOnLine)
2. TrafficGAN: Off-Deployment Traffic Estimation with Traffic Generative Adversarial Networks

   https://doi.org/10.1109/ICDM.2019.00193  

   Zhang, Yingxue; Li, Yanhua; Zhou, Xun; Kong, Xiangnan; Luo, Jun (November 2019, 2019 IEEE International Conference on Data Mining (ICDM))
3. Balancing Fairness and Efficiency in Traffic Routing via Interpolated Traffic Assignment

   Jalota, Devansh; Solovey, Kiril; Tsao, Matthew; Zoepf, Stephen; Pavone, Marco (May 2022, Autonomous agents and multiagent systems)
4. MalLight: Influence-Aware Coordinated Traffic Signal Control for Traffic Signal Malfunctions

   https://doi.org/10.1145/3627673.3679605  

   Yang, Qinchen; Xie, Zejun; Wei, Hua; Zhang, Desheng; Yang, Yu (October 2024, ACM)
5. Traffic Refinery: Cost-Aware Data Representation for Machine Learning on Network Traffic

   https://doi.org/10.1145/3491052  

   Bronzino, Francesco; Schmitt, Paul; Ayoubi, Sara; Kim, Hyojoon; Teixeira, Renata; Feamster, Nick (December 2021, Proceedings of the ACM on Measurement and Analysis of Computing Systems)

   Network management often relies on machine learning to make predictions about performance and security from network traffic. Often, the representation of the traffic is as important as the choice of the model. The features that the model relies on, and the representation of those features, ultimately determine model accuracy, as well as where and whether the model can be deployed in practice. Thus, the design and evaluation of these models ultimately requires understanding not only model accuracy but also the systems costs associated with deploying the model in an operational network. Towards this goal, this paper develops a new framework and system that enables a joint evaluation of both the conventional notions of machine learning performance (e.g., model accuracy) and the systems-level costs of different representations of network traffic. We highlight these two dimensions for two practical network management tasks, video streaming quality inference and malware detection, to demonstrate the importance of exploring different representations to find the appropriate operating point. We demonstrate the benefit of exploring a range of representations of network traffic and present Traffic Refinery, a proof-of-concept implementation that both monitors network traffic at 10~Gbps and transforms traffic in real time to produce a variety of feature representations for machine learning. Traffic Refinery both highlights this design space and makes it possible to explore different representations for learning, balancing systems costs related to feature extraction and model training against model accuracy. 

   more » « less