Data-Driven Networking With Flow-Specific Ingress Queues
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network architectures face challenges in scalability, versatility, and efficiency due to increasing network load and diverse traffic types, with conventional congestion control mechanisms being slow and ineffective, leading to suboptimal network utilization.
Innovation Solution
A data-driven intelligent networking system with ingress port injection limits that maintains state information of individual packet flows, using flow-specific input queues and acknowledgements to manage traffic dynamically, allowing for fast and accurate congestion control.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional congestion control mechanisms are used, then network architecture simplicity is maintained, but network utilization and responsiveness deteriorate
Solution Approach 1:
The patent segments the network into flow-specific input queues at each switch, allowing independent congestion control for each flow. This segmentation enables fine-grained flow management while maintaining overall network simplicity through distributed implementation.
Solution Approach 2:
The patent implements feedback mechanisms where egress switches send acknowledgments back to ingress switches, enabling dynamic adjustment of injection limits based on actual network conditions. This feedback loop allows the system to respond to congestion in real-time without requiring complex centralized control.
2Measurement precision
If per-flow flow control is implemented, then flow management precision is improved, but device complexity increases
Solution Approach 1:
The patent divides the packet processing function into flow-specific input queues, with each queue managed independently. This segmentation enables precise per-flow control while distributing the complexity across multiple simple queue managers rather than requiring a single complex controller.
Solution Approach 2:
Each flow's injection limit is dynamically adjusted based on its own ACK feedback, making the flow control mechanism self-regulating. The system automatically adapts to congestion conditions without requiring external intervention or complex centralized management.
3Speed
If fast flow control is implemented, then network responsiveness is improved, but state information maintenance complexity increases
Solution Approach 1:
The patent maintains separate state information for each flow in dedicated input queues at every switch. This segmentation allows fast per-flow state tracking without requiring a centralized state database, reducing the complexity burden on any single component.
Solution Approach 2:
The patent continuously updates flow state information as packets are processed and ACKs are received, maintaining current network conditions without interruption. This continuous state maintenance enables rapid response to changing network conditions while keeping the implementation simple through incremental updates rather than comprehensive reevaluation.
Data Source
AI summary
Data-driven intelligent networking systems and methods are provided. The system can accommodate dynamic traffic while applying injection limits to different traffic classes at an ingress edge port. The system can maintain state information of individual packet flows, which can be set up or released dynamically based on injected data. Each flow can be provided with a flow-specific input queue upon arriving at a switch. Packets of a respective flow can be acknowledged after reaching the egress point of the network, and the acknowledgement packets can be sent back to the ingress point of the flow along the same data path. Furthermore, an edge switch can dynamically allocate the ingress port bandwidth among the traffic classes that are active at a given moment.