Intent-Based QoS Provisioning With ML for Dynamic Network Conditions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current QoS configuration techniques are static and fail to adapt dynamically to network conditions and application behavior, leading to suboptimal performance, resource wastage, and poor user experience.
Innovation Solution
An intent-based QoS provisioning system that utilizes a machine learning model to process QoS intents, real-time and historical network data, predicting application-specific requirements and adjusting settings like LAS provisioning or slice provisioning to align with network policies and user entitlements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If static QoS configuration techniques are used, then device complexity is reduced, but application performance consistency deteriorates under dynamic network conditions
Solution Approach 1:
The patent implements dynamic QoS provisioning by continuously monitoring network conditions and application performance metrics, then automatically adjusting QoS parameters in real-time. This transforms the static QoS configuration into a dynamic system that adapts to changing network conditions, thereby maintaining application performance consistency without requiring complex manual configuration.
Solution Approach 2:
The system employs feedback mechanisms by collecting performance data from applications and network conditions, analyzing this data through machine learning models, and using the insights to automatically adjust QoS settings. This closed-loop feedback system ensures performance consistency while keeping the configuration process automated and relatively simple.
2Reliability
If dynamic QoS adjustment is implemented, then application performance is improved, but computing resources are consumed
Solution Approach 1:
The system implements self-service through autonomous QoS management where machine learning models automatically analyze network conditions and application requirements, then self-adjust QoS parameters without human intervention. This automation improves application performance while the system intelligently manages its own computing resource consumption by only making adjustments when necessary.
Solution Approach 2:
The patent dynamically changes QoS parameters such as bandwidth allocation, latency thresholds, and priority levels based on real-time analysis. These parameter changes are made selectively and efficiently by machine learning models that identify when adjustments are needed, thereby improving application performance while minimizing unnecessary computing resource consumption.
3Measurement precision
If machine learning models are used for QoS prediction, then QoS provisioning accuracy is improved, but device complexity increases
Solution Approach 1:
The patent employs a universal machine learning framework that handles multiple QoS prediction tasks and different application types through a single integrated system. This multi-functional approach improves prediction accuracy across diverse scenarios while avoiding the need for separate complex systems for each application, thereby managing overall system complexity.
Solution Approach 2:
The machine learning model acts as an intermediary layer between network monitoring and QoS configuration. It processes raw network data and application requirements, transforms them into actionable QoS parameters, and mediates the complex interactions between various system components. This intermediary role improves prediction accuracy while encapsulating complexity within the ML model itself.
Data Source
AI summary
A device may receive one or more quality of service (QoS) characteristics as a QoS intent for an application associated with a network, and may process the QoS intent, real-time network data, and historical network data, with a machine learning model, to predict application-specific QoS requirements. The device may determine a QoS adjustment based on the QoS intent and the QoS requirements, and may cause the network to implement the QoS adjustment.