Sleeping Cell Detection via Power Consumption Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting sleeping cells in cellular networks are complex and inefficient, relying on large data sets and significant resource consumption, making it difficult to identify malfunctioning cells due to hardware or software faults, which can lead to performance degradation or complete service loss.
Innovation Solution
A method using a machine-learning algorithm-based classification model that monitors power consumption patterns of radio transmission points to classify cells as either sleeping or non-sleeping, reducing the need for additional sensors and minimizing signaling overhead, thereby providing a more robust and efficient detection process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional fault detection mechanisms using threshold comparison or KPIs are used, then the detection process is simple, but sleeping cells cannot be detected because performance degradation is gradual and KPIs cannot distinguish sleeping cells from healthy cells with light load
Solution Approach 1:
The patent uses power consumption patterns as a diagnostic indicator (analogous to color change) to detect sleeping cells. Instead of relying on traditional KPIs that cannot distinguish sleeping cells from lightly-loaded cells, the system monitors power consumption characteristics that change when a cell enters a sleeping state, providing a clear visualizable metric for detection
Solution Approach 2:
The patent introduces power consumption monitoring as an intermediary measurement mechanism between the cell state and detection decision. This intermediary metric (power consumption) provides indirect but reliable information about cell health status, bridging the gap between traditional KPIs and actual cell functionality
2Reliability
If N-gram analysis of MDT event sequences is used to detect sleeping cells, then detection capability is improved, but data collection requirements, signaling overhead, storage costs, and processing resources increase significantly
Solution Approach 1:
The patent extracts only the essential feature (power consumption pattern) needed for sleeping cell detection, discarding the need for comprehensive MDT event sequence collection and N-gram analysis. This extraction approach maintains detection capability while eliminating unnecessary data collection, signaling overhead, and processing complexity
Solution Approach 2:
Instead of analyzing complex user event sequences to infer cell status (bottom-up approach), the patent inverts the approach by directly monitoring the cell's power consumption characteristics (top-down approach). This inversion simplifies the detection mechanism while maintaining or improving detection accuracy
3Measurement precision
If multiple sensors and large data sets are used for detection, then measurement precision is improved, but resource consumption and system complexity increase
Solution Approach 1:
The patent leverages the cell's own power consumption data as the detection metric, eliminating the need for external sensors and additional measurement infrastructure. The cell essentially monitors itself through its inherent power consumption characteristics, reducing system complexity and resource requirements while maintaining detection precision
Data Source
AI summary
The disclosure provides methods, apparatus and machine-readable mediums for the detection of sleeping cells in a cellular network. A method of detecting a sleeping cell in a cellular communication network comprises: monitoring power consumption of a radio transmission point of the cellular communication network; providing the power consumption of the radio transmission point as an input to a classification model, developed using a machine-learning algorithm; and obtaining an output from the classification model, the output classifying the radio transmission point as serving one of a sleeping cell and a non-sleeping cell.