ML-Based Network Path Mapping for Software Upgrade Validation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing MDA architectures lack comprehensive solutions for validating software upgrades in telecommunication networks, leading to lengthy maintenance windows and manual processes that are inefficient and prone to delays, especially in scenarios with varying network loads, and fail to optimize network path mapping for low-latency and reliable communication.
Innovation Solution
A system and method utilizing machine learning models to predict and validate software upgrades by comparing pre-upgrade and post-upgrade KPIs, and to optimize network path mapping based on network traffic analysis, enabling automated validation and efficient network path determination.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual validation processes are used for software upgrades, then comprehensive checking can be performed, but maintenance time increases and efficiency decreases
Solution Approach 1:
The patent replaces manual validation processes with automated machine learning-based validation systems. The ML model automatically predicts KPIs and compares them against actual post-upgrade metrics, eliminating the need for manual validation while maintaining comprehensive checking capability. This substitution of mechanical/manual operations with automated intelligent systems directly resolves the contradiction between validation reliability and maintenance time.
Solution Approach 2:
The system enables self-service validation where the ML model autonomously performs prediction, comparison, and validation without human intervention. The automated system serves itself by continuously learning from historical data and independently validating software upgrades, thereby reducing maintenance time while preserving validation thoroughness.
2Reliability
If traditional network path selection methods are used, then simple routing decisions can be made, but network performance and latency optimization are insufficient
Solution Approach 1:
The patent changes the parameters used for network path selection from simple static metrics to dynamic ML-predicted KPIs. The system continuously monitors and adjusts path selection based on predicted network conditions, traffic patterns, and performance metrics, enabling optimized routing decisions that improve communication reliability while managing complexity through intelligent automation.
Solution Approach 2:
The system performs preliminary action by using the ML model to predict future network conditions and KPIs before actual traffic flows occur. This predictive capability allows the network to proactively select optimal paths in advance, preventing performance degradation rather than reacting to it, thereby improving reliability while the automation manages the complexity.
3Productivity
If automated validation systems are implemented, then maintenance time is reduced, but system complexity increases
Solution Approach 1:
The ML-based validation system is designed to be universal and multi-functional, handling multiple validation tasks across different software upgrades and network conditions through a single unified model. This universality allows the system to achieve high productivity across diverse scenarios while managing complexity through consolidation rather than proliferation of separate validation mechanisms.
Solution Approach 2:
The system uses copying by leveraging historical KPI data and performance patterns as training data for the ML model. Instead of creating complex validation logic for each scenario, the system copies and learns from past performance patterns, enabling automated high-speed validation while the ML model absorbs the complexity of handling various validation scenarios.
4Reliability
If machine learning models are used for network optimization, then network performance is improved, but computational requirements and processing time increase
Solution Approach 1:
The patent applies partial action by using the ML model to predict only the most critical KPIs relevant to validation and path selection, rather than computing all possible network parameters. This selective prediction approach maintains high network performance reliability by focusing computational energy on the most impactful metrics, thereby reducing overall energy consumption while preserving optimization effectiveness.
Data Source
AI summary
A system and a method for validating software upgrades and optimizing network path mapping are provided. Further, a method for validating a software upgrade and determining network path mapping at a network entity (NE) using a management data analytics service (MDAS) producer is provided. The method includes predicting a set of key performance indicators (KPIs) using a machine learning (ML) model, performing a software upgrade, determining KPIs associated with the NE post-upgrade, comparing the predicted and determined KPIs, and the software upgrade is validated, receiving network traffic information reflecting network performance metrics for various paths, and predicting a plurality of KPIs using the ML model, and determines the optimal network paths based on the predicted KPIs.