Abstract
Managing network performance through Quality of Service (QoS) is essential but challenging due to the dynamic nature of networks and applications. Traditional QoS configurations are often static and manually intensive, leading to frequent errors and inefficiencies, particularly with critical applications. Proposed herein are techniques to facilitate an approach, referred to as Smart Adaptive QoS (SAdQoS) through which telemetry data can be leveraged to build and train machine learning (ML) models tailored to various business needs. These models can be trained on-premise, using real-time telemetry from the network in order to predict traffic patterns and generate adaptive QoS configurations. By automating this process, the techniques proposed herein ensure accurate, dynamic adjustments to network configurations, which can enhance network performance and reliability.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Kajabale, Supriya; Volkov, Roman; and Dunstan, Brett, "TECHNIQUES TO FACILITATE SMART ADAPTIVE QUALITY OF SERVICE", Technical Disclosure Commons, (September 11, 2024)
https://www.tdcommons.org/dpubs_series/7342