Adaptive TCA Thresholding for Dynamic SLA Assurance

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional cloud-based SDN networks face challenges in dynamically managing resource capacity thresholds, leading to inaccurate SLA compliance and reactive management decisions due to static threshold settings that fail to account for dynamic network traffic loads.

Innovation Solution

The implementation of adaptive TCA thresholding systems that utilize machine learning to analyze historical and operational data, match patterns to predict new or adjust existing thresholds based on current conditions, thereby automating resource management and reducing SLA impacts.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If static threshold settings are used for TCA, then device complexity is reduced and ease of operation is improved, but measurement precision deteriorates and reliability worsens due to inaccurate SLA compliance detection under dynamic network conditions

Engineering Contradiction:

Improvethreshold accuracyVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent implements dynamic threshold adjustment by continuously monitoring network traffic patterns and automatically adapting TCA thresholds to current network conditions. The system transitions from static, manually-configured thresholds to dynamic, self-adjusting thresholds that respond to changing traffic loads, thereby maintaining measurement precision without requiring proportional increases in system complexity

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system employs self-learning algorithms that automatically analyze historical TCA data, identify patterns, and adjust thresholds without human intervention. This self-service capability allows the system to maintain high threshold accuracy while minimizing the operational complexity that would otherwise be required for manual threshold management

Inventive Principle:

Principle #25Self-service

2Adaptability or versatility

If static threshold settings are used, then ease of operation is improved, but adaptability deteriorates as the system cannot respond to dynamic network traffic conditions

Engineering Contradiction:

Improvethreshold adaptabilityVSAvoidoperational simplicity

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The system performs preliminary analysis of network traffic patterns and learns optimal threshold settings in advance during low-activity periods. By pre-computing threshold adjustments based on historical data and predicted traffic patterns, the system achieves high adaptability while maintaining operational simplicity, as the actual threshold adjustments are automatically applied without requiring real-time human decision-making

Inventive Principle:

Principle #10Preliminary action

3Productivity

If manual threshold management is used, then device complexity is reduced, but productivity deteriorates due to reactive management and labor burdens

Engineering Contradiction:

Improvemanagement efficiencyVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system implements continuous feedback loops where TCA events, network performance metrics, and threshold violations are monitored and fed back to the threshold adjustment mechanism. This automated feedback system enables proactive threshold optimization, significantly improving management efficiency by eliminating reactive manual interventions while the system complexity remains manageable through modular architecture

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent replaces manual, mechanical threshold management processes with automated computational algorithms and machine learning models. This substitution eliminates labor-intensive reactive management and improves productivity, as the automated system can continuously monitor and adjust thresholds without human intervention, while the complexity is contained within software rather than requiring complex hardware or procedural systems

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

4Reliability

If static thresholds are used, then false positives are reduced through simplicity, but reliability worsens due to inaccurate SLA compliance measurement under varying network loads

Engineering Contradiction:

ImproveSLA compliance accuracyVSAvoidthreshold management complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system dynamically changes threshold parameters based on network conditions, traffic patterns, and learned behavior models. By adjusting threshold values, time windows, and sensitivity parameters according to current network state, the system maintains high SLA compliance measurement accuracy while the modular implementation keeps management complexity manageable through automated parameter adjustment rather than manual configuration

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS11310125B2AI-enabled adaptive TCA thresholding for SLA assurance

Publication Date: 2022.04.19 AT&T INTELLECTUAL PROPERTY I L P

AI summary

Systems and methods for adaptive TCA threshold management are described. A technique can include receiving threshold crossing alert (TCA) data including operational TCA data, determining a TCA prediction trigger based on a current threshold, matching, in response to determining the TCA prediction trigger, the operational TCA data to a pattern from a TCA pattern bank, and calculating a predicted TCA threshold based on the pattern.