Cell Condition Detection Using ML Image Conversion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for detecting cell conditions in wireless cellular networks are inadequate due to reliance on rule-based instructions and limited performance metrics, leading to inaccurate and inefficient cell capacity provisioning, which can result in poor user experience and operational inefficiencies.
Innovation Solution
A method involving the training of a classifier model using machine-learning algorithms, specifically deep neural networks, to detect cell conditions by converting time-series data into image data sets, annotating, augmenting, and deploying the model to identify predefined cell conditions, enabling precise detection of cell traffic load issues.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If rule-based instructions with predetermined thresholds are used to detect cell conditions, then the detection method is simple and easy to implement, but the detection accuracy and precision are insufficient
Solution Approach 1:
The patent replaces the mechanical rule-based detection system with a machine learning-based automated system. The classifier model learns patterns from historical performance data and automatically detects cell conditions without relying on predetermined thresholds, thereby improving detection accuracy while maintaining operational simplicity through automated decision-making.
Solution Approach 2:
The patent transforms the detection approach by changing from fixed threshold parameters to dynamic parameters learned from data. The machine learning model adapts detection criteria based on patterns in performance metrics, allowing the system to respond to varying network conditions with improved precision without requiring manual parameter adjustment.
2Measurement precision
If a limited number of common performance metrics are used for cell condition detection, then the analysis process is simple and fast, but the detection precision and ability to identify complex cell load issues are insufficient
Solution Approach 1:
The patent creates a universal detection framework that can handle multiple performance metrics simultaneously. The machine learning classifier is designed to process diverse input features including but not limited to throughput, latency, and error rates, making the system adaptable to various network conditions and cell types without requiring separate detection mechanisms for each metric.
Solution Approach 2:
The patent segments the complex detection task into multiple independent feature extraction steps followed by a unified classification stage. Each performance metric is processed and transformed into meaningful features that feed into the classifier, allowing the system to handle a large number of metrics efficiently by breaking down the analysis into manageable segments.
3Adaptability or versatility
If rule-based detection methods are used, then the system is easy to operate and maintain, but the system cannot adapt to changing network conditions and traffic patterns
Solution Approach 1:
The patent implements a dynamic detection system where the classifier model continuously learns from incoming performance data and adapts to changing network conditions. The system transitions from static rule-based thresholds to dynamic, data-driven decision boundaries that automatically adjust to new traffic patterns, network configurations, and emerging cell condition types without requiring manual reconfiguration.
Solution Approach 2:
The machine learning-based system provides self-service capabilities by automatically learning from historical data and improving its detection accuracy over time without human intervention. The model retrainst itself on new data, automatically adapting to changing network conditions while maintaining operational simplicity for network operators.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Embodiments of the disclosure provide methods, apparatus and computer-readable mediums for the detection of cell conditions in a wireless cellular network, and the training of a classifier model to detect cell conditions in a wireless cellular network. In one embodiment, a method of training a classifier model to detect cell conditions in a wireless cellular network comprises: obtaining time-series data for a plurality of performance metrics for each cell of a plurality of cells of the wireless cellular network; converting the time-series data to respective image data sets for each cell of the plurality of cells; classifying the image data sets into one of a plurality of predefined cell conditions; and applying a machine-learning algorithm to training data comprising the classified image data sets to generate a classifier model for classifying image data sets into one of the plurality of predefined cell conditions.