Direct Network Routing Node Distribution for Latency Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Direct networks face performance issues such as increased latency and limited bandwidth due to resources being connected to a single routing node or a set of contiguous nodes, which restricts path options and affects overall network efficiency.
Innovation Solution
Each resource is connected to a set of two or more distributed routing nodes within a coordinate space, satisfying inter-node separation criteria to increase path diversity and reduce latency, thereby enhancing network performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If each resource is connected to a single routing node, then the network topology is simple, but the latency increases and bandwidth is limited
Solution Approach 1:
The patent divides the single routing node connection into multiple routing node connections. Each resource is connected to a set of two or more routing nodes instead of a single node, segmenting the communication path into multiple potential routes. This segmentation provides path diversity, allowing messages to be routed through different nodes to avoid congestion and reduce latency.
Solution Approach 2:
The patent transitions from a one-dimensional single-node connection model to a multi-dimensional distributed connection model. By distributing routing nodes across the switching fabric coordinate space and connecting each resource to multiple nodes, the network gains additional routing dimensions and paths, enabling more flexible and efficient message transmission.
2Device complexity
If each resource is connected to a single routing node, then the network structure is simple, but the bandwidth is limited
Solution Approach 1:
The bandwidth limitation is addressed by segmenting the single connection into multiple parallel connections. Each resource connects to multiple routing nodes, creating multiple simultaneous communication channels. This effectively segments the total bandwidth into multiple streams, increasing the aggregate bandwidth available to each resource while maintaining manageable connection structures.
Solution Approach 2:
The patent merges multiple routing node connections for each resource into a unified distributed connection model. By combining connections to multiple routing nodes, the network achieves increased bandwidth through parallel paths while maintaining a structured and manageable connection architecture through the distributed routing node selection criteria.
3Productivity
If routing nodes are distributed with inter-node separation, then path diversity increases and latency decreases, but the network configuration complexity increases
Solution Approach 1:
The patent applies local quality by making each resource's routing node connections unique and optimized for its specific location in the coordinate space. Each resource connects to a distinct set of routing nodes selected based on inter-node separation criteria, creating locally optimized connection patterns that collectively improve overall network performance while maintaining manageable configuration complexity.
Solution Approach 2:
The patent changes the network configuration parameters by introducing distributed routing node selection based on coordinate space separation. Instead of uniform single-node connections, the system uses parameters such as inter-node separation distance and coordinate-based distribution to determine connections, transforming the network from a simple to an optimized configuration that improves message transmission efficiency.
4Quantity of substance
If resources are connected to contiguous routing nodes, then bandwidth increases, but path options are restricted and latency increases
Solution Approach 1:
The patent introduces asymmetry by replacing the symmetric contiguous routing node arrangement with an asymmetric distributed arrangement. Instead of connecting to adjacent nodes in a predictable pattern, resources connect to routing nodes distributed across the coordinate space according to separation criteria. This asymmetric distribution increases both bandwidth through multiple paths and reduces latency by avoiding localized congestion.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A direct network is described in which each resource is connected to a switching fabric via a set of two or more routing nodes. The routing nodes are distributed so as to satisfy at least one inter-node separation criterion. In one case, the separation criterion specifies that, for each resource, a number of routing nodes that share a same coordinate value with another routing node in the set (in a same coordinate dimension) is to be minimized. In some network topologies, such as a torus network, this means a number of unique loops of the direct network to which each resource is connected is to be maximized. The routing provisions described herein offer various performance benefits, such as improved latency-related performance.