Dynamic CRE Value Computation in Heterogeneous Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing CRE methods in heterogeneous networks fail to account for dynamic changes in cell and user equipment conditions, leading to suboptimal cell selection and performance in wireless communications networks, especially in dynamic environments like cities with varying traffic and infrastructure.
Innovation Solution
A network node computes a dynamic CRE value using supervised machine learning, based on current conditions such as cell load and radio conditions, to optimize performance by iteratively updating a training data set and improving model accuracy, allowing for optimal cell selection even under changing conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If static CRE values are used in heterogeneous networks, then device complexity is reduced and ease of operation is improved, but network performance deteriorates under dynamic conditions
Solution Approach 1:
The system performs preliminary actions by collecting training data during normal network operation and pre-computing relationships between parameters and performance metrics. This preliminary data collection and model training enables the system to quickly determine optimal CRE values without complex real-time computations, thus improving network performance while maintaining manageable device complexity.
Solution Approach 2:
The network node serves itself by autonomously collecting its own operational data, training its own machine learning model, and determining its own CRE values based on current network conditions. This self-service approach eliminates the need for external complex control systems, improving performance through adaptive optimization while keeping the device complexity within acceptable bounds.
2Adaptability or versatility
If dynamic CRE values are computed using machine learning, then network performance is improved under changing conditions, but device complexity increases
Solution Approach 1:
The system implements dynamics by enabling the CRE values to adapt dynamically to changing network conditions through machine learning. The model is trained on historical data and can dynamically determine optimal CRE values based on current parameters such as cell load and radio conditions, thus achieving high adaptability while managing computational complexity through efficient model structures.
Solution Approach 2:
The system achieves adaptability by monitoring changes in key parameters (cell load, radio conditions, user distribution) and using these parameter changes as inputs to the machine learning model. The model translates these parameter changes into optimized CRE values, allowing the system to adapt to dynamic conditions without requiring overly complex computational mechanisms.
3Reliability
If CRE values are optimized for specific conditions, then network performance is improved, but the system loses versatility across different scenarios
Solution Approach 1:
The machine learning model achieves universality by being trained on diverse training data that encompasses multiple network scenarios, conditions, and parameter combinations. This comprehensive training enables the single model to function effectively across varied conditions, providing optimized CRE values for different scenarios while maintaining a unified system, thus achieving both performance optimization and versatility.
Solution Approach 2:
The system performs preliminary action by collecting a broad range of training data from various network conditions and scenarios before deployment. This preliminary data collection from diverse sources enables the model to learn patterns across different situations, ensuring that the optimized performance achieved for specific conditions during training translates to versatile applicability when the system encounters new scenarios during operation.
Data Source
AI summary
A method in a network node for computing a Cell Range Expansion (CRE) value. The network node obtains a first value of a measure of the performance of the wireless communications network. The network node creates a first relationship relating the first value of the parameter to the first CRE value and the first measure of the performance of the wireless communications network, based on the first value of the parameter and the first value of the measure of the performance. The network node creates a second relationship relating the second value of the parameter to a second CRE value and a second value of the measure of the performance of the wireless communications network, based on the first relationship and on the second value of the parameter. The network node computes the second CRE value based on a second value of the parameter, and the second relationship.