Weight-Based Packet Scheduling for Network QoE Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current communication networks face challenges in optimizing Quality of Experience (QoE) due to inadequate differentiation of data packet streams from heterogeneous applications, leading to unfair treatment of packets during network congestion, which results in suboptimal performance for end-users.
Innovation Solution
A weight-based scheduling system that incorporates end-user application awareness by classifying data packets into scheduling groups based on application class or specific applications, using Application Factors (AF) to adjust scheduler weights dynamically, thereby prioritizing data streams effectively.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If data packets from heterogeneous applications are treated equally in the network, then network simplicity is maintained, but Quality of Experience (QoE) optimization is insufficient due to inadequate differentiation of data packet streams
Solution Approach 1:
The patent segments data packets into different scheduling groups based on application characteristics and network conditions. Each scheduling group is assigned different weights to enable differentiated treatment, allowing the system to optimize QoE for specific applications (video, voice, etc.) while maintaining manageable complexity through structured classification
Solution Approach 2:
The patent implements dynamic weight adjustment for scheduling groups based on real-time network conditions and application characteristics. The weights are not static but adapt to changing scenarios, enabling the system to respond to network congestion and prioritize critical applications dynamically without requiring complete system redesign
2Reliability
If all data packets are scheduled with equal priority, then scheduling simplicity is maintained, but performance of critical applications like video and voice deteriorates during network congestion
Solution Approach 1:
The patent applies different scheduling weights to different scheduling groups based on their specific characteristics and requirements. Critical applications like video and voice receive higher weights during congestion, while less critical traffic receives lower weights. This localized differentiation ensures reliable performance for important applications without requiring complex global optimization
Solution Approach 2:
The patent changes the scheduling parameter (weight) based on application type and network conditions. By adjusting the weight parameter dynamically, the system can prioritize critical applications during congestion without fundamentally changing the scheduling mechanism, thus improving reliability while controlling complexity through parameter adjustment rather than structural complexity
3Productivity
If dynamic Application Factors (AF) are used to adjust scheduler weights, then user QoE is maximized in response to network patterns, but system complexity increases due to packet inspection and classification requirements
Solution Approach 1:
The patent performs preliminary classification of data packets into scheduling groups based on application characteristics before scheduling. By pre-categorizing traffic into groups with assigned weights, the system prepares for efficient scheduling without requiring complex real-time decisions during packet transmission, thus improving throughput while managing classification complexity through advance organization
Data Source
AI summary
Systems and methods provide a weight-based scheduling system that incorporates end-user application awareness and can be used with scheduling groups that contain data streams from heterogeneous applications. Individual data queues within a scheduling group can be created based on application class, specific application, individual data streams or some combination thereof. Application information and Application Factors (AF) are used to modify scheduler weights to differentiate between data streams assigned to a scheduling group. Dynamic AF settings may adjust relative importance of user applications to maximize user Quality of Experience (QoE) in response to recurring network patterns, one-time events, application characteristics, protocol characteristics, device characteristics, service level agreements, or combinations thereof. Scheduling weights may be dynamic and incorporate the notions of “duration neglect” and “recency effect” in an end-user's perception of video quality in order to optimally manage video traffic during periods of congestion.