Mobile Terminal Handover Decisions Using Mobility-Aware Neural Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wireless communication systems face challenges in optimizing mobile terminal handovers due to the trade-off between frequency offset estimation precision for high-speed users and throughput, particularly in heterogeneous UE compositions, leading to sub-optimal cell performance.
Innovation Solution
A neural network-based approach is employed to predict throughput optimization degrees for different cell configurations, allowing for dynamic handover decisions based on terminal mobility profiles, thereby optimizing resource allocation for both high-speed and low-speed users.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If frequency offset estimation precision is improved for high-speed users, then data decoding accuracy is improved, but cell throughput is reduced
Solution Approach 1:
The patent applies dynamics by making the cell configuration adaptive rather than static. The network entity dynamically adjusts cell configuration parameters (such as reference signal density, subcarrier spacing, or cyclic prefix length) based on real-time terminal mobility profiles. This allows the system to optimize frequency offset estimation precision for high-speed users while maintaining efficient throughput for low-speed users, resolving the contradiction between measurement precision and productivity.
Solution Approach 2:
The patent implements local quality by applying different cell configuration parameters to different terminal groups based on their mobility characteristics. High-speed terminals receive configurations optimized for frequency offset estimation (e.g., denser reference signals), while low-speed terminals receive configurations optimized for throughput. This localized optimization resolves the contradiction by allowing each user group to benefit from parameters tailored to their specific needs.
2Reliability
If cell configuration is optimized for high-speed users, then frequency offset compensation is improved, but overall network efficiency is reduced
Solution Approach 1:
The system dynamically adjusts cell configuration based on terminal mobility profiles, switching between configurations optimized for high-speed users (better frequency offset compensation) and low-speed users (higher network efficiency). This dynamic adaptation resolves the contradiction by ensuring each user group operates under optimal conditions for their specific mobility scenario.
Solution Approach 2:
The patent changes physical layer parameters (such as reference signal density, subcarrier spacing, or cyclic prefix configuration) based on terminal speed. For high-speed users, parameters are adjusted to improve frequency offset compensation reliability, while for low-speed users, parameters are optimized for maximum network efficiency. This parameter adaptation resolves the contradiction between reliability and productivity.
3Productivity
If homogeneous UE composition is maintained in each cell, then cell performance is optimized, but handover complexity increases
Solution Approach 1:
The patent uses mobility profile-based parameter changes to enable homogeneous UE composition optimization. By classifying terminals into mobility groups (e.g., high-speed, low-speed, stationary) and applying group-specific cell configurations, the system achieves improved cell performance for homogeneous groups while managing handover complexity through profile-based decision-making rather than exhaustive optimization.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This method enhances cell throughput performance by dynamically allocating resources according to user speed profiles, improving overall network efficiency and reducing errors in data decoding.
Implementation Method 1
predicting, utilizing a trained neural network, for each cell configuration of a plurality of cell configurations related to mobility and throughput balance, a throughput optimization degree for said terminal mobility profile
Implementation Method 2
Even in an ideal case where the local oscillators are perfectly aligned, a frequency offset between transmitter and receiver due to the Doppler effect (i.e. the apparent change in frequency of a wave in relation to an observer moving relative to the wave source) also generates a frequency error
Implementation Method 3
On the receiver side, due to the importance of using low-cost components in the mobile handset (e.g. UE), local oscillator frequency drifts are usually greater than in the radio base station and are typically a function of parameters such as temperature changes and voltage variation. This difference between the reference frequencies is widely referred to as carrier frequency offset (CFO).
Data Source
Figure 1
Figure 2
Figure 3
AI summary
There are provided measures for mobile terminal handover decision optimizations. Such measures exemplarily comprise, e.g. at a network entity of a first network cell providing network access to a terminal, obtaining information indicative of a terminal mobility profile of said terminal, predicting, utilizing a trained neural network, for each cell configuration of a plurality of cell configurations related to mobility and throughput balance, a throughput optimization degree for said terminal mobility profile, selecting, from said plurality of cell configurations, a cell configuration having a highest throughput optimization degree, and deciding, based on said highest throughput optimization degree whether to trigger a handover of said terminal from said first network cell to a second network cell.