Traffic Matrix Prediction for Fast Reroute Path Computation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current telecommunication networks face inefficiencies in switching traffic to backup paths during failures, as pre-computed backup paths may not be optimal due to changes in traffic conditions, leading to potential traffic loss and increased network costs.
Innovation Solution
A system that computes backup path configurations based on end-to-end and primary path traffic estimates for future time periods using machine learning models, such as Gaussian Process Regression, to predict traffic patterns and adjust backup paths proactively, reducing traffic loss and operational costs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If static backup paths are pre-computed, then fast reroute capability is achieved, but optimality is lost due to traffic condition changes
Solution Approach 1:
The patent implements dynamic backup path computation by continuously monitoring traffic conditions and recalculating backup paths in response to changes. The system transitions from static pre-computed paths to dynamically adjusted paths that adapt to current network state, thereby maintaining both fast reroute capability and path optimality simultaneously
Solution Approach 2:
The system employs feedback mechanisms by monitoring actual traffic conditions on primary paths and using this information to adjust backup path configurations. The feedback loop enables the system to detect traffic pattern changes and recompute backup paths accordingly, resolving the contradiction between speed and adaptability
2Adaptability or versatility
If backup paths are adjusted frequently to match traffic changes, then optimality is improved, but computational complexity and processing time increase
Solution Approach 1:
The patent implements periodic monitoring and computation cycles for backup paths. Instead of continuous real-time adjustments, the system performs computations at scheduled intervals or triggered by significant traffic threshold changes, reducing computational complexity while maintaining adequate adaptability to traffic patterns
Solution Approach 2:
The system changes computation parameters dynamically, adjusting the frequency and depth of backup path computations based on current network conditions. During stable periods, computations are performed less frequently, while during periods of significant traffic change, the system intensifies computation activity, thereby balancing optimality with computational complexity
3Reliability
If more capacity is allocated to backup paths to handle peak traffic, then reliability is improved, but network costs increase
Solution Approach 1:
The patent computes and prepares backup path configurations in advance based on predicted traffic patterns. By proactively configuring backup paths before failures occur and adjusting them based on forecasted traffic conditions, the system ensures adequate capacity is available when needed without permanently over-provisioning network resources, thus improving reliability while controlling capacity allocation
Data Source
AI summary
A processing system including at least one processor may obtain traffic measurements for end-to-end paths in a telecommunication network, calculate traffic estimates for the end-to-end paths in future time periods based on the traffic measurements in accordance with at least one machine learning model, calculate traffic estimates for primary paths in the telecommunication network based upon the traffic estimates for the end-to-end paths, compute a backup path configuration for a primary path of the telecommunication network for the future time periods based upon the traffic estimates for the primary paths in the future time periods, detect a change in the backup path configuration for the primary path in a future time period based upon the computing, and adjust a backup path in accordance with the backup path configuration when the change in the backup path configuration is detected.