Elastic Cloud Network Topology for Predictive QoE Routing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current network solutions fail to adapt to the highly dynamic enterprise environments where users and applications are increasingly distributed and diverse, leading to suboptimal user quality of experience (QoE) due to inadequate gateway placement and capacity issues, and reliance on Layer 3 metrics that do not represent true application performance.
Innovation Solution
Implement a predictive application aware routing engine using machine learning to optimize network topology based on quality of experience metrics, dynamically adjusting network nodes to meet application requirements and prevent SLA failures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traffic is routed through corporate VPN gateways located in data centers or hub locations, then network security and centralized control are maintained, but user QoE deteriorates due to suboptimal gateway placement and capacity issues
Solution Approach 1:
The patent segments the centralized gateway function into distributed edge computing nodes deployed across multiple geographic locations. This allows traffic to be routed to the nearest edge node rather than through distant central gateways, improving user QoE while maintaining security through distributed enforcement of security policies across the segmented architecture.
Solution Approach 2:
The patent adds a geographic distribution dimension to the network architecture by deploying edge nodes across multiple locations. This transforms the single-dimension centralized gateway model into a multi-dimensional distributed system, enabling users to connect to geographically proximate nodes and improving access performance without sacrificing centralized control capabilities.
2Quantity of substance
If the network system scales up to meet traffic demands, then capacity issues are resolved, but response time increases due to the inability to quickly scale
Solution Approach 1:
The patent implements preliminary action by pre-deploying edge computing nodes across multiple geographic locations before traffic demands arise. This allows the system to immediately route traffic to available edge nodes when demand increases, eliminating the scaling response time delay associated with provisioning new capacity.
Solution Approach 2:
The patent enables dynamic scaling by allowing traffic to be rapidly redistributed across the distributed edge node infrastructure. The system can dynamically adjust traffic routing to utilize available edge nodes without requiring time-consuming physical provisioning, achieving elastic scalability through software-defined traffic management.
3Measurement precision
If SLA monitoring and application aware routing are implemented, then network connectivity is optimized based on Layer 3 metrics, but true application QoE cannot be accurately measured or optimized
Solution Approach 1:
The patent introduces an intermediary application performance monitoring component that sits between the network monitoring system and the actual application traffic. This intermediary captures true application-level performance metrics and QoE data, bridging the gap between network-layer optimization and application-layer performance measurement, enabling accurate QoE assessment that reflects actual user experience.
Solution Approach 2:
The patent changes the measurement parameters from network-layer metrics (Layer 3) to application-layer metrics that directly reflect user experience. By monitoring application-specific performance parameters such as application response time, transaction success rates, and user interaction metrics, the system achieves accurate QoE measurement that cannot be obtained through traditional network metrics alone.
Data Source
AI summary
In one embodiment, a device obtains information regarding a plurality of network nodes of a network via which an online application is accessed. The device uses a prediction model to predict a quality of experience metric for the online application. The device determines, a topology change for the network, based on the quality of experience metric predicted for the online application and the information regarding the plurality of network nodes. The device causes the topology change to be implemented in the network.