Wireless Cell KPI Prediction for Proactive UL Throughput Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods fail to effectively predict and manage uplink (UL) throughput in multi-radio access technology (RAT) environments of 5G networks, particularly in Non-Stand Alone (NSA) and Stand Alone (SA) architectures, and do not provide proactive solutions for spectrum sharing components.
Innovation Solution
A method using machine learning (ML) to analyze key performance indicators (KPIs) and generate predictions of UL throughput degradation, identifying root causes, and applying actuations to prevent degradation, utilizing ensemble ML models like XGBoost, CatBoost, and Light Gradient Boosting for proactive network management.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional predictive ML solutions are used, then UL throughput can be forecasted, but the system cannot proactively prevent degradation before it occurs
Solution Approach 1:
The system performs preliminary actions by identifying root causes of predicted UL throughput degradation and applying corrective actuations before the degradation actually occurs. The proactive ML model forecasts future KPI values and triggers preventive maintenance actions in advance, transforming the system from reactive to proactive management.
Solution Approach 2:
The system applies beforehand cushioning by preparing and applying corrective actuations in advance to counteract predicted UL throughput degradation. This creates a protective buffer that prevents performance deterioration before it impacts users, ensuring smoother transitions and maintaining service quality.
2Measurement precision
If the system monitors and analyzes multiple KPIs to predict UL throughput, then prediction accuracy improves, but system complexity increases
Solution Approach 1:
The system introduces an intermediary ML model that processes multiple KPI inputs and transforms them into actionable predictions. This intermediary layer simplifies the complexity by encapsulating the analysis of multiple parameters within a unified predictive framework, making the system manageable while maintaining high prediction accuracy.
Solution Approach 2:
The ML model serves multiple functions simultaneously: it predicts UL throughput degradation, identifies root causes, and recommends corrective actuations. This multi-functionality reduces overall system complexity by consolidating what would otherwise require separate systems into a single unified proactive ML solution.
3Productivity
If the system applies actuations to prevent UL throughput degradation, then network performance improves, but operational complexity increases
Solution Approach 1:
The system implements self-service by automatically identifying root causes of predicted degradation and applying appropriate corrective actuations without human intervention. The proactive ML model autonomously manages network optimization, reducing operational complexity while maintaining high network performance through automated decision-making and execution.
Data Source
AI summary
A method of managing a wireless communication network includes obtaining data regarding performance of a cell of the wireless communication network, and generating, based on the obtained data, predictions of values of a plurality of key performance indicators (KPIs) of the cell of the wireless communication network that are correlated with uplink (UL) throughput. The method includes generating a prediction that the cell will experience degraded UL throughput at a future time based on the predicted values of the KPIs, and determining, from among the plurality of KPIs, a set of candidate root cause KPIs associated with the predicted degraded UL throughput. The method further includes selecting an actuation based on the determined set of candidate KPIs, and applying the actuation to the wireless communication network.