Multi-Objective Radio Network Optimization for Coverage-Capacity Balance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wireless communication network optimization techniques often focus on a single objective, leading to inefficient and resource-intensive iterative processes that fail to balance conflicting objectives such as coverage and capacity, resulting in suboptimal network performance.
Innovation Solution
Implementing a multi-objective optimization model, such as a reinforcement learning (RL) or multiple-objective evolutionary algorithm (MOEA), to simultaneously optimize multiple network objectives like coverage and capacity by using a reward function and evolutionary operators to generate network configuration parameters that balance trade-offs, guided by a Pareto-optimal front.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If single-objective optimization is used, then optimization process is simple, but network performance is suboptimal due to inability to balance conflicting objectives
Solution Approach 1:
The patent segments the optimization process into multiple independent single-objective optimizations for different network objectives (coverage, capacity, interference). Each objective is optimized separately using simple optimization algorithms, and the results are combined through a multi-objective framework that balances trade-offs. This segmentation allows complex multi-objective optimization to be achieved through composition of simpler components.
Solution Approach 2:
The patent creates a universal optimization framework that can handle multiple network objectives simultaneously. The system uses a common optimization platform that can be configured to optimize for different objectives (coverage, capacity, interference) by simply changing the objective function, making the system multi-functional without requiring separate specialized systems for each objective.
2Adaptability or versatility
If iterative optimization processes are used, then network configuration can be adjusted, but resource consumption increases and time is wasted
Solution Approach 1:
The patent performs preliminary actions by pre-calculating and storing network configuration parameters and their impact on multiple objectives before actual optimization is needed. The system uses pre-computed data about network topology, propagation characteristics, and objective relationships to rapidly determine optimal configurations without performing time-consuming iterative calculations during deployment.
Solution Approach 2:
The patent creates virtual copies of network configurations and their performance characteristics through simulation and modeling. Instead of physically testing every possible configuration through iterative trial-and-error, the system uses simulated copies of network states to evaluate and compare configurations, rapidly identifying optimal solutions without repeated physical implementation.
3Reliability
If network is optimized for single objective, then that objective is achieved, but other objectives suffer from resource allocation conflicts
Solution Approach 1:
The patent converts the harmful interference between objectives into a beneficial trade-off balancing mechanism. Instead of treating objective conflicts as problems to be eliminated, the system uses the interference and resource conflicts as informative signals to identify optimal balance points. The multi-objective framework deliberately considers the negative impact of one objective on others and uses this information to find configurations that achieve acceptable performance across all objectives simultaneously.
Data Source
AI summary
Systems and methods for multi-objective radio network optimization is provided. A system may collect multiple network data packets from network monitoring equipment connected to a communications network. The system may execute a model using the network data packets as input. The model may be an optimization model or a machine learning model. The model may generate network configuration parameters for the communication network. The model may be configured with predetermined weights for multiple performance metrics. The model may be trained to generate the network configuration parameters that optimize multiple performance metrics. The system may adjust the communications network according to the generated network configuration parameters.