Self-Organizing Network Clustering for Dynamic Traffic Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current self-organizing networks (SONs) rely on rudimentary controls and hardcoded rules, failing to optimize user Quality of Experience and adapt to varying network traffic patterns, leading to suboptimal performance and user complaints despite good network performance.
Innovation Solution
The Application Characteristics-Driven (APP)-SON system collects application-level and network-level data to identify key performance indicators, cluster cells based on traffic patterns, and dynamically tune engineering parameters using techniques like Hungarian Algorithm Assisted Clustering and deep neural networks to optimize wireless KPIs and user experience.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If rudimentary controls and hardcoded rules are used in SON, then device complexity is reduced and ease of operation is improved, but network performance optimization and adaptability to varying traffic patterns deteriorate
Solution Approach 1:
The system enables self-service through automated machine learning model training and deployment. The SON system automatically collects network data, trains optimization models, and deploys them without human intervention, allowing the network to self-optimize while maintaining operational simplicity
Solution Approach 2:
The system dynamically changes network parameters based on learned patterns from machine learning models. By continuously adjusting parameters like resource allocation, handover thresholds, and power settings based on real-time data analysis, the system achieves high adaptability while operators simply monitor automated processes
2Device complexity
If traditional SON approaches are used, then device complexity is kept low, but the ability to optimize user Quality of Experience and adapt to dynamic network scenarios deteriorates
Solution Approach 1:
The patent replaces traditional mechanical rule-based control systems with intelligent machine learning-based automated systems. Neural networks and predictive algorithms substitute hardcoded decision-making logic, enabling the network to adapt to complex dynamic scenarios while maintaining system manageability through automated model training and deployment
3Reliability
If automated intelligent SON with machine learning is implemented, then network performance optimization and user Quality of Experience are improved, but device complexity and computational requirements increase
Solution Approach 1:
The system segments the complex machine learning workflow into distinct modular components: data collection modules, model training modules, model evaluation modules, and deployment modules. Each component handles a specific aspect of the optimization process, making the overall complex system manageable through functional segmentation and independent development
Solution Approach 2:
The patent introduces intermediary components such as data preprocessing layers, feature extraction modules, and model abstraction layers that mediate between raw network data and complex machine learning algorithms. These intermediaries simplify the interface between operators and the intelligent system, reducing perceived complexity while maintaining advanced optimization capabilities
Data Source
AI summary
A Self-Organizing Network (SON) collects data pertaining to a first number of cells of a wireless network. The SON splits the collected data into a second number of groups, and, for each of the second number of groups, repeatedly set a third number of clusters to a different number between a low limit and a high limit. The SON, for each of the settings, clusters the cells into the third number of clusters and trains a deep neural network to perform a regression analysis on the third number of clusters. For each of the second number of groups, the SON also determines an optimum number of clusters based on the regression analyses, re-clusters the cells into the optimum number of clusters; and tunes engineering parameters based on the re-clustering to optimize performance of the wireless network and quality of experience pertaining to the wireless network.