Layer-2 Switch Path Selection for Network Congestion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional Ethernet switch devices cause congestion in optical transport networks and hybrid data link layer and optical transport network configurations, especially when handling significant data traffic over large-capacity physical links and geographic areas, due to their lack of path detection, data traffic routing, error control, and quality-of-service intelligence at the data link layer.
Innovation Solution
An optimized layer-2 network switching system that monitors the performance of multiple network paths and selects the optimal path based on latency, congestion, and cost parameters using a path selection heuristic, allowing for intelligent data traffic forwarding.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If traditional Ethernet switch devices forward data traffic frames blindly without considering congestion or cost, then data traffic forwarding simplicity is maintained, but network congestion occurs in optical transport networks
Solution Approach 1:
The patent implements dynamic path selection at the data link layer by monitoring network conditions (congestion, cost, latency) and adapting forwarding decisions in real-time. The system transitions from static blind forwarding to dynamic intelligent forwarding that responds to changing network states, resolving the contradiction between simplicity and efficiency.
Solution Approach 2:
The patent introduces feedback mechanisms where the data link layer device monitors network path performance metrics (congestion levels, cost parameters, latency) and uses this feedback to adjust forwarding decisions. This closed-loop control enables the system to avoid congested paths and select optimal routes, improving network throughput while maintaining operational simplicity through automated decision-making.
2Productivity
If data link layer devices perform path detection and routing intelligence, then network congestion is reduced, but device complexity increases
Solution Approach 1:
The patent enables data link layer devices to perform multiple functions: traditional frame forwarding plus path detection, routing intelligence, congestion monitoring, and quality-of-service management. By making the data link layer device multi-functional, the patent consolidates intelligence that would otherwise require separate network layer components, improving throughput without proportionally increasing device complexity.
Solution Approach 2:
The patent implements preliminary path performance assessment and routing table construction at the data link layer before data traffic needs to be forwarded. By pre-establishing routing intelligence and path knowledge, the device can make efficient forwarding decisions without complex real-time calculations, reducing the operational complexity while maintaining high throughput efficiency.
3Reliability
If network layer performs path detection and routing functions, then data traffic routing intelligence is provided, but overhead is significantly increased
Solution Approach 1:
The patent shifts routing intelligence from the network layer to the data link layer, representing a dimensional change in the network architecture. By moving path detection and routing functions to a lower layer, the patent provides the same reliability benefits with reduced overhead, as data link layer operations are more efficient and have lower processing requirements than network layer operations.
Data Source
AI summary
An exemplary method includes monitoring a performance of at least one of a plurality of layer-2 network paths connecting a layer-2 network switch device to another layer-2 network switch device and selecting an optimal one of the plurality of layer-2 network paths over which to forward data traffic based on a path selection heuristic and the monitored performance of the at least one of the plurality of layer-2 network paths. At least a portion of the exemplary method may be performed by a layer-2 network switching system. In certain embodiments, the selecting of the optimal one of the plurality of layer-2 network paths over which to forward the data traffic is based on at least one of a latency parameter, a congestion parameter, and a cost parameter associated with the at least one of the plurality of layer-2 network paths. Corresponding systems and methods are also disclosed.