Open RAN Busy-Hour Forecasting for Capacity Breach Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cloud-based data and telephone networks face challenges in efficiently managing resources and detecting congestion due to rapidly increasing traffic loads, leading to poor user experiences and infrastructure demands that traditional congestion detection mechanisms are inadequate to address.
Innovation Solution
A system that collects network data, models subscriber growth, and forecasts capacity breaches by identifying busy hours, applying machine learning models to predict future traffic, and recommending infrastructure expansions to prevent overloads.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional congestion detection mechanisms are used, then network monitoring is provided, but they are insufficient to respond to evolving network conditions and predict future congestion points
Solution Approach 1:
The system performs preliminary actions by collecting historical traffic data and building machine learning models that predict future congestion points before they occur. The forecasting mechanism proactively identifies potential capacity breaches and allows preemptive network adjustments, transforming reactive congestion management into proactive prevention.
Solution Approach 2:
The system implements continuous feedback loops where predicted congestion data feeds back into network management decisions. The machine learning models are trained on historical data and continuously refined based on actual network performance, creating a self-improving system that adapts to evolving network conditions and improves detection precision over time.
2Reliability
If network capacity is increased to accommodate growing traffic, then user experience is maintained, but infrastructure costs and network complexity increase
Solution Approach 1:
The system enables dynamic network capacity management by using machine learning predictions to adjust network resources in real-time. Instead of statically over-provisioning infrastructure, the system dynamically allocates capacity based on forecasted demand, maintaining service reliability while avoiding the complexity and cost of permanently expanded infrastructure.
Solution Approach 2:
The system changes network operating parameters based on predictions rather than maintaining fixed capacity levels. By adjusting traffic routing, load balancing, and resource allocation parameters in response to forecasted congestion, the system maintains reliability without requiring permanent infrastructure expansion.
3Measurement precision
If historical traffic data is collected and analyzed, then accurate congestion prediction is achieved, but data processing time and computational resources increase
Solution Approach 1:
The system applies partial action by focusing data analysis on the most relevant features and time periods for prediction. Rather than processing all possible network data equally, the system identifies and analyzes only the critical subsets of historical traffic data that most strongly correlate with future congestion patterns, reducing processing time while maintaining forecast accuracy.
Data Source
AI summary
An example process may detect capacity breaches in an area of interest (AOI) of an open radio access network (RAN). Data is queried for cells in the RAN network over a sampling period to retrieve hourly-traffic data for the cells. Outliers may be removed from the hourly-traffic data for the cells. In the trimmed hourly-traffic data, top-download-traffic hours are identified on different days in the sampling period for each of the cells. The example process may include aggregating the trimmed hourly-traffic data for each of the cells at the top-download-traffic hours to generate busy-hour indicators for each of the cells and busy-hour indicators for sectors associated with cells. The busy-hour indicators may be extrapolated using subscriber growth in the AOI to generate forecast indicators for each of the cells and for the sectors associated with the cells. The forecast indicators are compared to capacity thresholds to forecast capacity breaches.