Multi-CDN Streaming Scheduling for Traffic Burst Response
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Live streaming platforms struggle to dynamically balance network capacity, service quality, and operational cost across multiple content delivery networks (CDNs) due to static scheduling rules, which fail to adapt to sudden traffic bursts and changing conditions.
Innovation Solution
A dynamic streaming scheduling system that processes parameters from CDNs into metrics, identifies scheduling scenes, assigns weights to metrics based on the scene, and calculates a scheduling score to allocate content delivery events across CDNs, employing tiered mitigation strategies to manage traffic bursts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If static scheduling rules or single-layer decision-making are used to allocate content among CDNs, then the system is simple to operate, but it cannot adapt to dynamic changes and sudden traffic bursts
Solution Approach 1:
The patent implements a multi-layer scheduling architecture where the global scheduler dynamically adjusts content allocation across CDNs based on real-time traffic patterns, network conditions, and service quality metrics. This dynamic approach replaces static scheduling rules, enabling the system to adapt to sudden traffic bursts and changing conditions while maintaining coordinated decision-making across multiple layers.
Solution Approach 2:
The scheduling system is divided into multiple layers (global scheduler and regional schedulers) that operate independently but coordinate with each other. This segmentation allows each layer to handle specific aspects of scheduling, improving adaptability while managing complexity through modular design. The global scheduler handles overall content allocation, while regional schedulers manage local distribution, enabling scalable adaptation to dynamic changes.
2Reliability
If multi-layer coordinated scheduling is implemented to respond to traffic bursts, then service quality improves, but system complexity increases
Solution Approach 1:
The multi-layer scheduling system segments scheduling functions into global and regional layers, each with specific responsibilities. The global scheduler makes high-level content allocation decisions, while regional schedulers handle local distribution and optimization. This segmentation improves service quality by enabling coordinated responses to traffic bursts while managing complexity through clear separation of concerns and defined interfaces between layers.
Solution Approach 2:
The system implements feedback mechanisms where regional schedulers report local conditions and performance metrics to the global scheduler, which adjusts content allocation accordingly. This feedback loop enables the multi-layer system to maintain high service quality by continuously adapting to changing network conditions and traffic patterns, while the structured feedback process helps manage complexity through automated decision-making.
3Productivity
If dynamic parameter balancing is implemented across multiple CDNs, then productivity improves, but measurement and detection difficulty increases
Solution Approach 1:
The scheduling system implements a unified framework that simultaneously monitors and balances multiple parameters (network capacity, service quality, operational cost) across all CDNs. This universal approach improves productivity by optimizing content delivery efficiency through coordinated parameter balancing, while the integrated monitoring system manages the complexity of tracking multiple parameters through a single cohesive interface and standardized metrics.
Data Source
AI summary
In one embodiment, a method of streaming scheduling for a plurality of content delivery networks includes: for each content delivery network of the plurality of content delivery networks, receiving a plurality of parameters at least from the content delivery network, wherein the plurality of parameters is processed into a plurality of metrics; identifying a scheduling scene for the content delivery network; determining a weight for each metric of the plurality of metrics based on the scheduling scene; determining a scheduling score for the content delivery network based on the plurality of metrics and the respective weights; and based on the scheduling score of each content delivery network of the plurality of content delivery networks, allocating a content delivery event among the plurality of content delivery networks.