Simulated Mobile User Resource Allocation via Machine Learning Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current network simulation techniques overlook the impact of user velocity and signal attenuation, fail to consider inter-subcarrier interference, and lack cross-layer considerations, leading to inadequate resource allocation and reduced simulated user generation, especially in mobile scenarios.
Innovation Solution
A high-mobility resource allocation system and method that utilizes a machine learning module to optimize carrier aggregation and resource allocation, generating simulated mobile user signals based on location and velocity, and includes a resource-allocation optimizing module to maximize the number of simulated users while ensuring service quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If current simulation channel training methods are used without cross-layer considerations, then the simulation process is simple, but it is difficult to focus on the improvement of user experience and service quality
Solution Approach 1:
The patent changes simulation parameters by introducing cross-layer considerations including user velocity, signal attenuation, inter-subcarrier interference, and channel estimation errors. These parameter changes transform the simulation from a simple model to one that accurately reflects real-world mobile environments, thereby improving service quality assessment.
2Measurement precision
If user velocity and signal attenuation are overlooked in channel simulations, then the simulation process is simpler, but the accuracy of resource allocation for mobile users deteriorates
Solution Approach 1:
The patent introduces velocity and attenuation parameters into the channel simulation model. By incorporating these parameters, the simulation accurately reflects mobile user scenarios where signal characteristics change with motion, thereby improving measurement precision for resource allocation decisions.
Solution Approach 2:
The patent makes the simulation dynamic by incorporating user velocity parameters. Instead of static channel conditions, the simulation now adapts to moving users, allowing resource allocation to account for time-varying channel characteristics experienced in mobile environments.
3Reliability
If inter-subcarrier interference is not considered in resource allocation, then the allocation process is simpler, but the performance of mobile users deteriorates
Solution Approach 1:
The patent introduces inter-subcarrier interference as a parameter in resource allocation. By calculating and considering this interference, the system can make more accurate allocation decisions that protect mobile user performance, especially in high-mobility scenarios where frequency selectivity varies rapidly.
4Measurement precision
If channel estimation errors are not considered in resource allocation for moving users, then the allocation is simpler, but the network performance verification for mobile scenarios becomes inaccurate
Solution Approach 1:
The patent applies beforehand cushioning by pre-calculating and incorporating channel estimation errors into the resource allocation process. This allows the system to compensate for expected inaccuracies in channel knowledge, ensuring that resource allocation remains robust even when channel conditions are not perfectly known, thereby improving mobile scenario verification accuracy.
5Quantity of substance
If the number of simulated users is increased without optimizing resource allocation, then more users can be simulated, but the service quality for each user deteriorates
Solution Approach 1:
The patent uses machine learning to dynamically adjust resource allocation parameters based on user conditions including velocity and channel state. This allows the system to maintain service quality even as the number of simulated users increases, because resources are optimally distributed according to actual needs rather than uniformly allocated.
Solution Approach 2:
The patent makes resource allocation dynamic through machine learning optimization. As users move and channel conditions change, the system continuously adapts resource distribution to maintain service quality for all users, enabling higher user density without quality degradation.
Data Source
AI summary
A high-mobility resource allocation system and method for simulated users are provided, including a base station, antennas and a simulated mobile-user generator. The simulated mobile-user generator organizes a test field by taking the base station as the circle center, and measures and records multiple channel information based on the detection signals of the antennas. The machine learning module is used to perform simulation channel training according to channel information to generate simulated user channels that approximates real-world scenarios. A mobile-user organizing module organizes multiple simulated mobile users and their mobile channel information in the test field based on the simulated user channel, generates multiple simulated mobile user signals, and uses a resource-allocation optimizing module based on simulated mobile user signals, channel interference information upon moving, etc. to maximize the number of simulated mobile users while considering the quality of service.