Cell Energy-Saving Control for Event-Zone Capacity Surges
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Mobile Network Operators face challenges in balancing energy efficiency with capacity demands in crowded event zones, leading to potential service disruptions and regulatory risks, as traditional energy-saving methods often fail to account for predictable capacity surges.
Innovation Solution
A method using a trained graph neural network (GNN) to predict cell utilization levels in event zones, generating inclusion and exclusion lists for energy-saving states based on historical performance metrics, enabling targeted energy conservation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If automated energy saving solutions are implemented by deactivating Radio Network Elements during idle periods, then energy consumption is reduced, but service reliability and capacity availability deteriorate
Solution Approach 1:
The system performs preliminary actions by predicting future capacity demands using machine learning models before energy saving actions are taken. The ML model analyzes historical data and event information to forecast when capacity surges are likely to occur, allowing the system to proactively adjust energy saving strategies in advance rather than reacting after service disruptions occur.
Solution Approach 2:
The energy saving strategy is made dynamic by continuously adjusting it based on predicted capacity demands. The system transitions from static idle-period deactivation to dynamic, prediction-based control that adapts to changing network conditions, event schedules, and predicted user behavior patterns, allowing flexible optimization of both energy saving and service reliability.
2Reliability
If energy efficiency optimization is abandoned in crowded event zones to ensure capacity availability, then service reliability is maintained, but energy consumption increases
Solution Approach 1:
The system applies different energy saving strategies to different locations based on their specific characteristics and event profiles. Instead of uniformly disabling energy optimization across all event zones, the ML model identifies which cells and time periods are most likely to experience capacity surges, allowing localized energy saving actions only in areas and times where they are safe to implement.
Solution Approach 2:
The system changes operational parameters of Radio Network Elements dynamically based on predicted capacity demands. By adjusting parameters such as transmission power, antenna configuration, and resource allocation in response to ML predictions, the system can optimize energy consumption while maintaining capacity availability where needed.
3Loss of energy
If traditional energy-saving methods are used without accounting for predictable capacity surges, then energy consumption is reduced, but service quality deteriorates
Solution Approach 1:
The system incorporates feedback loops where actual network performance data is continuously fed back into the machine learning model to refine predictions. This feedback mechanism allows the system to learn from past events and adjust its predictions and energy saving strategies accordingly, improving both energy efficiency and service quality over time.
Solution Approach 2:
The patent replaces traditional mechanical or rule-based energy saving mechanisms with an intelligent machine learning-based system. Instead of using fixed thresholds or simple timers to determine when to deactivate network elements, the system uses ML models that process complex patterns in historical data and event information to make intelligent predictions about future capacity demands.
Data Source
AI summary
A method for determining energy-savings states of cellular network components comprises retrieving run-time performance metric data for cells in a predetermined area corresponding to an event location; feeding the run-time performance metric data to a trained machine-learning (ML) model; determining, using the trained ML model and the run-time performance metric data, predicted cell utilization levels over a predicted time period; comparing one or more predicted cell utilization levels for each cell to a respective threshold; and building an inclusion list that identifies each cell for which at least one of the respective predicted cell utilization level(s) is/are lower than or equal to the respective threshold(s) and a respective one or more predicted time increments in which the at least one of the respective predicted cell utilization level(s) of a respective cell is/are lower than or equal to the respective threshold(s).