Distributed Buffering for Virtual Concatenation Delay
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing virtually-concatenated data traffic routing techniques require large memory buffers at destination nodes to accommodate differential delays, leading to bottlenecks and inefficiencies in network bandwidth utilization.
Innovation Solution
The technique involves distributing delay across intermediate nodes in the network by buffering traffic at these nodes, reducing the burden on destination nodes and minimizing buffer requirements, allowing for more efficient traffic routing and increased network capacity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If large memory buffers are provided at destination nodes to accommodate differential delays, then traffic can be reassembled correctly, but network bandwidth utilization deteriorates due to bottlenecks
Solution Approach 1:
The patent segments the buffer resource from being concentrated at the destination node and distributes it across intermediate nodes along the path. Each intermediate node buffers a portion of the traffic according to its position in the path, thereby segmenting the overall buffering function. This resolves the contradiction by maintaining reliable reassembly (through distributed buffering) while improving bandwidth utilization (by eliminating the destination bottleneck).
Solution Approach 2:
The patent changes the spatial dimension of buffer placement from a single point (destination node) to multiple points (intermediate nodes) along the path. This dimensional transformation allows traffic to be buffered at different locations, enabling parallel processing and eliminating the single-point bottleneck, thus improving both reliability and bandwidth utilization simultaneously.
2Device complexity
If delay is concentrated at the destination node, then traffic reassembly is simplified, but network flexibility and capacity deteriorate
Solution Approach 1:
The patent segments the delay function across multiple intermediate nodes rather than concentrating it at the destination. Each intermediate node introduces a portion of the total required delay, which simplifies the individual operations at each node while maintaining the overall delay requirement for correct reassembly. This segmentation approach preserves routing flexibility because each node operates independently with a simplified delay function.
Solution Approach 2:
Instead of implementing the complete delay function at the destination node, the patent applies partial delay actions at each intermediate node along the path. The sum of these partial delay actions equals the total required delay, but each individual action is simpler and can be implemented more flexibly, thereby improving routing adaptability while maintaining reassembly correctness.
3Productivity
If virtual concatenation is used to divide traffic into smaller payloads, then bandwidth efficiency improves, but memory buffer requirements at destination nodes increase
Solution Approach 1:
The patent segments both the traffic payload (through virtual concatenation) and the buffer resource (through distribution across intermediate nodes). The traffic is divided into smaller VC-4 payloads that can be efficiently multiplexed, improving bandwidth utilization. Simultaneously, the buffer requirement is segmented and distributed across multiple intermediate nodes, preventing any single node from requiring excessive memory, thus resolving the contradiction between bandwidth efficiency and buffer requirements.
Solution Approach 2:
The patent transforms the buffer requirement from a single-dimension problem (total buffer size at destination) to a multi-dimension problem (distributed buffer sizes across multiple nodes). This allows the system to maintain high bandwidth efficiency through virtual concatenation while distributing the memory burden across the network path, thereby reducing the buffer requirement at any single destination node.
Data Source
AI summary
Network design techniques and techniques for routing virtually-concatenated data traffic in a network in a manner which distributes delay to intermediate nodes of the network are disclosed. For example, in one aspect of the invention, a technique for routing virtually-concatenated data traffic in a network comprising a plurality of nodes comprises, for a given traffic demand to be routed from a source node to a destination node in the network, the following steps/operations. Two or more paths are determined to route the given traffic demand. Each of the two or more paths correspond to a member of a virtually-concatenated group. At least one path of the two or more paths comprises the source node, the destination node and at least one other node coupled between the source node and the destination node. Further, at least a subset of the source node, the destination node and the one other node buffer at least a portion of the given traffic demand such that a delay is distributed over the at least one path. The given traffic demand is routed over the two or more determined paths. The at least one path is preferably the shorter of the two or more determined paths.