Dual Switching Matrices for Bursty Data Traffic Handling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Digital transmission networks face inefficiencies in switching data traffic due to bursty data packets, leading to potential data loss and increased latency, particularly when using cell switches, as they struggle to handle variable data rates and high burst intervals, often resulting in dropped packets and increased latency.
Innovation Solution
A network element with dual switching matrices and egress buffers is proposed, where data packets are split and processed by both matrices, allowing for increased switching capacity and reduced latency, and egress buffers manage bursts by storing data during high-rate intervals and transmitting during lower-rate intervals, thereby minimizing data loss and latency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a single switching matrix is used to handle packet traffic, then the device complexity is reduced, but the switching capacity is insufficient to handle bursty data rates without data loss
Solution Approach 1:
The packet traffic flow is segmented into two separate flows, with each flow being processed by a dedicated switching matrix. This segmentation allows the system to handle bursty traffic more effectively by distributing the load across multiple matrices, thereby increasing overall switching capacity without requiring a single overly complex matrix.
Solution Approach 2:
The dual switching matrices are configured to be universal in their capability to handle both packet traffic and TDM traffic. Each matrix can independently process different types of traffic, providing multi-functionality that increases switching capacity while maintaining manageable device complexity through standardized processing units.
2Reliability
If data packets are buffered during high-rate intervals, then data loss is reduced, but latency increases
Solution Approach 1:
The egress buffers are pre-configured and activated only when needed during high-rate intervals. This preliminary preparation allows the system to immediately buffer incoming packets during bursts without introducing unnecessary latency during normal operation, thus preventing data loss while minimizing time loss.
Solution Approach 2:
The buffering mechanism is dynamic, being activated and deactivated based on the current traffic rate. During high-rate intervals, buffering is enabled to prevent data loss; during lower-rate intervals, buffering is disabled or minimized to reduce latency. This dynamic adjustment optimizes both reliability and time performance.
3Productivity
If larger switching matrices are used to handle bursty traffic, then switching capacity increases, but power consumption and cost increase
Solution Approach 1:
Instead of using a single large switching matrix, the system segments the switching function across multiple smaller matrices. This segmentation allows the system to achieve the required switching capacity during bursts while keeping individual matrices smaller and less power-consuming. The segmented approach provides the necessary capacity on-demand without the continuous power overhead of a single large matrix.
Solution Approach 2:
The system discards the idea of continuously operating at peak capacity and instead recovers resources by activating additional switching matrices only when needed during high-rate intervals. This allows the system to maintain high switching capacity when necessary while minimizing power consumption during normal operation by keeping some matrices in a lower-power state.
Data Source
AI summary
A network element for a digital transmission network is proposed. The network element contains two switching matrices for switching data cells, as well as ingress ports that receive TDM traffic flow and packet traffic flow and segment the traffic flows into cells. A control system for controlling the configuration of the ingress ports and the switching matrices controls the ingress ports, in case of no failure of the switching matrices, to forward the TDM traffic flows to both switching matrices and to split the packet traffic flow over the two switching matrices.