Cloud Exchange Management for Latency Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Enterprises face challenges in managing peering agreements between cloud providers, leading to suboptimal traffic latency, as existing solutions require multiple agreements and are not dynamically adaptable to changing traffic patterns.
Innovation Solution
A method and system that utilize a cloud exchange management application to perform traffic latency analytics, identify suitable peering agreements for relocation to a Central office Re-architected as a Data Center (CORD), and establish a private link between the CORD and cloud exchange, allowing seamless migration of peering agreements to improve traffic routing efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple peering agreements are established between cloud providers and cloud exchange, then connectivity between cloud providers is achieved, but traffic latency increases and system complexity increases
Solution Approach 1:
The patent introduces a CORD (Central Office Re-architected as Data Center) as an intermediary node between cloud providers and cloud exchange. The CORD consolidates multiple peering agreements and establishes direct private connections to cloud providers, serving as a mediator that reduces the number of hops and routing complexity in the network path, thereby reducing traffic latency while maintaining connectivity.
Solution Approach 2:
The patent segments the network architecture by separating the CORD function from the cloud exchange. Instead of all cloud providers connecting directly to the cloud exchange, the system divides connections into two segments: cloud providers connect to CORD, and CORD connects to cloud exchange. This segmentation creates optimized direct paths for traffic between cloud providers via CORD, reducing latency.
2Reliability
If multiple peering agreements are established between cloud providers and cloud exchange, then connectivity between cloud providers is achieved, but device complexity increases
Solution Approach 1:
The patent merges multiple peering agreements into a single CORD node. Instead of managing separate peering agreements between each cloud provider and the cloud exchange, the system combines these agreements under the CORD, which then establishes unified direct connections to cloud providers. This merging simplifies the management architecture by centralizing peering relationship control.
Solution Approach 2:
The CORD serves as a universal node that handles multiple functions: it acts as a peering agreement manager, a routing optimizer, and a connection broker between cloud providers and the cloud exchange. This multi-functionality reduces the need for separate specialized components, thereby reducing overall system complexity.
3Loss of time
If peering agreements are moved to CORD, then traffic latency is reduced, but system configuration complexity increases
Solution Approach 1:
The system performs preliminary actions by pre-establishing the CORD infrastructure and pre-configuring direct private connections to cloud providers before traffic patterns require optimization. The CORD is prepared in advance with necessary routing tables and peering agreements, so when latency optimization is needed, the transition is seamless and requires minimal real-time configuration changes.
Data Source
AI summary
A cloud exchange includes a first connection to an enterprise; a first plurality of peering points each to an associated cloud provider of a plurality of cloud providers; a second connection to a Central office Re-architected as a Data Center (CORD) including a set of hardware and/or software from one or more existing data centers that is capable of routing traffic directly between the plurality of cloud providers, wherein the CORD comprises a second plurality of peering points to the plurality of cloud providers; and a cloud exchange management application executed on a computing system configured to cause movement of traffic data between the first plurality of peering points and the second plurality of peering points responsive to one or more of the traffic data trending between two applications in different cloud providers and latency between the two applications in different cloud providers.