Value Optimization Engine for Mobile Network Parameter Tuning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current wireless network optimization methods do not consider customer experience or subscriber value when adjusting network parameters, leading to suboptimal service quality for high-value subscribers, and lack real-time intervention capabilities to improve service quality.
Innovation Solution
The implementation of a Value Optimization Engine (VOE) that receives subscriber performance indicators and network data to optimize access network parameters in real-time, using a cost function that accounts for subscriber values and weights, allowing for dynamic adjustments to improve service quality for high-value subscribers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If network optimization uses static approaches for dimensioning and adjustment of radio resources, then network planning is simpler and more stable, but it cannot meet varying user traffic demands in real-time
Solution Approach 1:
The patent implements dynamic network optimization by continuously monitoring network state data and subscriber performance indicators in real-time, then automatically adjusting radio resource allocation and network parameters based on current conditions and predicted future states, transforming static network configuration into a dynamic adaptive system
Solution Approach 2:
The system uses machine learning models to predict future network states and subscriber performance trends before they occur, allowing the optimization engine to proactively adjust network parameters in advance to prevent performance degradation rather than reacting after problems arise
2Productivity
If network optimization considers only networkwide performance improvement, then overall network efficiency is improved, but high-value subscribers do not receive prioritized service
Solution Approach 1:
The patent applies local quality by differentiating service optimization for different subscriber segments based on their value to the operator. The system identifies high-value subscribers and applies customized optimization strategies tailored to their specific service requirements and performance needs, rather than applying uniform network-wide optimizations
Solution Approach 2:
The optimization system segments subscribers into different value categories and applies distinct cost functions and optimization parameters for each segment. This allows the network to simultaneously optimize for overall network performance while providing prioritized service quality enhancements for high-value subscriber groups
3Area of stationary object
If antenna input power is increased to improve coverage area, then coverage is expanded, but interference to neighboring antennas increases affecting quality of service
Solution Approach 1:
The system dynamically adjusts multiple antenna parameters including input power, tilt angles, and beamwidth based on real-time network state and predicted future conditions. Rather than statically increasing power to expand coverage, the optimization engine fine-tunes parameters to achieve coverage goals while maintaining acceptable interference levels through coordinated multi-parameter adjustment
Solution Approach 2:
The patent implements continuous feedback loops where network performance data and subscriber quality of service metrics are monitored in real-time. This feedback informs the optimization engine to adjust antenna parameters dynamically, reducing power when interference becomes problematic and increasing it when coverage gaps are detected, creating a self-regulating system
Data Source
AI summary
Self-Organizing Network (SON) technology has been developed to make the planning, configuration, management, and self-healing of mobile networks easier and faster, where such planning, configuration and management of the mobile networks are targeted to optimize the value offered to a group of subscribers using criteria such as (a) subscriber type (consumer, corporate, IOT, etc.), (b) service type (mission critical, public safety, VoIP, etc.), (b) subscriber usage volume (high, medium, low), (c) subscriber's requested/subscribed QoS, and (d) subscriber's paying value (i.e., revenue). The same teachings can be extended to also optimize a single subscriber's service or a service type.