SDN Switch Flow Classification via Decision Tree Model
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In software-defined networking (SDN) systems, the high volume of data flows leads to congestion in the control channel between controllers and switches, resulting in reduced network control efficiency and delayed flow forwarding, affecting user experience.
Innovation Solution
A data transmission method that classifies data flows using a decision tree model on switches within the OpenFlow protocol, where first-class flows are reported to the controller for path computation, and second-class flows are directly transmitted based on local switch information, reducing interactions and optimizing resource usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If all data flows are reported to the central controller for path computation, then optimal path selection is achieved, but control channel congestion occurs and controller efficiency decreases
Solution Approach 1:
The patent segments data flows into two categories: first-class flows (requiring controller intervention for optimal path computation) and second-class flows (handled locally by switches using existing flow table information). This segmentation reduces the volume of flows reported to the controller, alleviating control channel congestion while maintaining optimal path selection for critical flows.
Solution Approach 2:
Switches are empowered to independently handle second-class data flows using local flow table information without requiring controller intervention. This self-service mechanism reduces controller workload and improves overall system efficiency while maintaining acceptable forwarding performance for non-critical flows.
2Extent of automation
If all data flows are reported to the controller, then centralized control capability is maintained, but control channel congestion and delay occur
Solution Approach 1:
The patent divides data flows into first-class and second-class categories, allowing time-sensitive second-class flows to be forwarded immediately by switches using local information, thereby reducing forwarding delay. Centralized control capability is preserved for first-class flows that require optimal path computation.
Solution Approach 2:
Switches pre-load flow table information locally, enabling them to immediately forward second-class flows without waiting for controller responses. This preliminary action reduces forwarding delay while centralized control remains available for first-class flows requiring optimal path selection.
3Speed
If switches use local flow table information for all flows, then forwarding speed increases, but path optimality decreases
Solution Approach 1:
The patent segments flows based on their requirements: second-class flows are handled locally by switches for high-speed forwarding, while first-class flows are reported to the controller for optimal path computation. This ensures that speed-critical flows are forwarded quickly while maintaining optimality for important flows.
Solution Approach 2:
Different forwarding strategies are applied to different flow classes: local switching for second-class flows prioritizing speed, and centralized control for first-class flows prioritizing path optimality. This local quality approach matches the handling method to the specific requirements of each flow type.
Data Source
AI summary
A network data transmission method is provided. A switch device receives one or more data flows, classifies each of the received data flows into one of two classes according to data features of the data flow by using a decision tree model established by a flow table pipeline of the switch device. If a data flow belongs to a first class, the switch device reports the data flow to a controller, so that the controller computes a transmission path for the data flow. If a data flow belongs to a second class, the switch device obtains a transmission path for the data flow according to local flow table information, and transmits the data flow according to the obtained transmission path. Data flows are classified and filtered by using a switch, so as to improve network transmission efficiency while ensuring bearing capability of a network control system.