Topo-Gram Predictive Flow Positioning for Network SLA Compliance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current networks fail to predictively and proactively manage service level agreement (SLA) constraints, particularly in critical applications like medical and autonomous vehicle systems, where millisecond delays can be life-threatening, requiring a shift from best-effort connectivity to dynamic and elastic networks that are predictive and preemptive.
Innovation Solution
A system and method using a Machine Learning model with in-situ Operations Administration and Management (IOAM) for real-time flow-centric telemetry to create a 'Topo-Gram', a multi-dimensional topological graphical representation, which identifies potential failures and modifies traffic flow paths to prevent SLA deviations by analyzing operational attributes and service level attributes of network elements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If best effort connectivity is used, then network simplicity is maintained, but SLA compliance and reliability deteriorate
Solution Approach 1:
The system performs preliminary actions by continuously collecting network telemetry data, analyzing operational attributes, and identifying potential failure points before they actually occur. The machine learning model predicts future network states and enables preemptive flow repositioning, allowing the network to prevent SLA violations before they happen rather than reacting after failures occur.
Solution Approach 2:
The network monitoring and control functions are segmented into distinct components: telemetry data collection from network elements, machine learning-based predictive analysis, and flow repositioning control. This segmentation allows each component to be optimized independently while working together to achieve reliable SLA-compliant connectivity without overwhelming overall system complexity.
2Reliability
If real-time flow repositioning is implemented, then SLA compliance is improved, but system complexity increases
Solution Approach 1:
A machine learning model serves as an intermediary between raw network telemetry data and flow repositioning decisions. This intermediary analyzes operational attributes, predicts failure risks, and translates complex network states into actionable repositioning commands, simplifying the overall system architecture while enabling sophisticated predictive control.
Solution Approach 2:
The system implements continuous feedback loops where network telemetry data is collected, analyzed by the machine learning model, and used to adjust flow paths. The results of repositioning actions are monitored through ongoing telemetry collection, allowing the system to learn from past performance and continuously optimize SLA compliance while adapting to changing network conditions.
3Measurement precision
If predictive analysis is performed, then flow positioning accuracy is improved, but data processing requirements increase
Solution Approach 1:
The system extracts only the most critical operational attributes from vast amounts of network telemetry data for predictive analysis. By focusing on key indicators of network health and flow performance rather than processing all available data, the system achieves high flow positioning accuracy while minimizing the computational energy required for analysis.
Data Source
AI summary
A system and method predict risks of failure or performance issues in a network to predictively position traffic flows in the network. For a traffic flow through a network, first data accumulated in a header of packets for the traffic flow is obtained, which header is populated by network elements along a path of the traffic flow through the network. Second data is obtained about the network in general including other network elements not along the path of the traffic flow. Machine learning analysis is performed to derive rules that characterize failure or performance risk issues in the network. The rules and topology data describing a topology of the network are applied to a model to create a topological graphical representation indicating failure or performance issues in the network that affect the traffic flow. A path for the traffic flow is modified based on the topological graphical representation.