Pyramid Server Topology for Low-Latency Many-to-One Updates
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing server topologies struggle to minimize latency when receiving data inputs from a multitude of end user computing devices to update aggregated values in a central server, particularly in real-time applications like social media and survey platforms, as they introduce unwanted latency with additional servers.
Innovation Solution
A pyramid server topology is implemented, where a principal server is connected to subordinate servers in multiple layers, allowing data aggregation and distribution across these layers to manage simultaneous user updates efficiently, with each layer adding capacity without significantly increasing update time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a mesh network of distributed servers is used to service millions of users, then the system provides optimum failover, but latency increases as additional servers are added into the network
Solution Approach 1:
The system segments the network into hierarchical levels: principal servers at the top, first-tier subordinate servers in the middle, and second-tier subordinate servers at the bottom. This segmentation allows users to connect to the nearest subordinate server, reducing latency while maintaining reliability through the hierarchical structure that provides multiple paths for data flow and failover capability.
2Quantity of substance
If additional servers are added to handle more user connections, then network capacity increases, but latency increases due to additional communication hops
Solution Approach 1:
The patent introduces a hierarchical dimension to the network architecture, organizing servers into multiple tiers (principal, first-tier subordinate, second-tier subordinate) rather than a flat mesh structure. This dimensional organization allows the system to scale capacity by adding servers at lower tiers without proportionally increasing latency, as users can connect to nearby subordinate servers rather than communicating across the entire network.
3Stability of the object's composition
If a single central server handles all user updates, then data consistency is maintained, but the system cannot handle millions of simultaneous updates in near real-time
Solution Approach 1:
The system segments the data handling responsibility across multiple subordinate servers distributed in a hierarchical structure. Each subordinate server manages updates from a specific group of users, aggregating changes before transmitting to principal servers. This segmentation enables parallel processing of updates from millions of users while maintaining data consistency through the structured aggregation and synchronization process.
Data Source
AI summary
The disclosure herein provides a pyramid topology for a communications network in which an authoritative server sits at the top of the pyramid. This is the “principal” server. The principal server connects to a sub-layer of “subordinate” servers (i.e., slave servers). The principal server gathers data from the subordinate servers at a predetermined interval based on the maximum number of connections that can be serviced within the desired timeframe. An additional layer of lower-level subordinate servers can be added under each of the higher-level subordinate servers to increase the network capacity. Additional levels of subordinate servers can be added to further increase the network capacity such that a single network may include a principal server and many cascading levels of subordinate servers to form the pyramid structure.