Sensing-Driven Task Network Selection for 5G OPEX Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In 5G communications systems, there is a lack of coevolution between roles such as closed-loop and open-loop controls, as well as user behavior and network topology, which hinders improvements in operational expenditure (OPEX) and operational network functions (OPNF).
Innovation Solution
A method for training and selecting a task network based on a coevolution mechanism, involving the evolution of individuals within populations through a coevolution process, using a multi-target function to evaluate accuracy, and determining actions based on sensing data to improve network performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If closed-loop control and open-loop control are used in 5G networks, then network control functionality is provided, but operational expenditure (OPEX) is high and operational network functions (OPNF) are not optimized
Solution Approach 1:
The patent implements a coevolution mechanism where closed-loop control continuously monitors network performance and feeds back to the open-loop control for parameter optimization. The system evaluates multiple candidate configurations and selects optimal parameters based on real-time performance feedback, enabling dynamic optimization of OPEX and OPNF without manual intervention.
Solution Approach 2:
The patent transforms static control parameters into dynamic, adaptive parameters through coevolution. The system continuously evolves control strategies by simulating different configurations and selecting those that optimize both OPEX and OPNF, allowing the network to adapt to changing conditions automatically.
2Adaptability or versatility
If network topology is designed to support user behavior requirements, then user experience is improved, but network complexity and resource consumption increase
Solution Approach 1:
The patent optimizes network topology by dynamically adjusting parameters such as node placement, link configurations, and resource allocation based on user behavior patterns. The coevolution mechanism evaluates multiple parameter combinations and selects configurations that achieve high user adaptability while minimizing network complexity through automated parameter optimization.
Solution Approach 2:
The patent creates a universal coevolution framework that can handle diverse user behavior requirements through a single adaptive system. The same evolutionary algorithm optimizes various network parameters (topology, resources, control strategies) to serve multiple user types and service requirements, reducing the need for separate specialized configurations.
Data Source
AI summary
The embodiments of the disclosure provide a method for selecting a task network, a system and a method for determining actions based on sensing data. The method of the embodiments of the disclosure includes: mapping the sensing data into an input feature vector; feeding the input feature vector into a specific task network to generate an output feature vector via the specific task network, in which the specific task network is trained based on a plurality of first individuals and a plurality of second individuals, the first individuals belong to a first population, the second individuals belong to a second population, and the first individuals and the second individuals are evolved via a coevolution process; and determining an output action according to the output feature vector, and setting a second specific individual based on the output action, in which the second specific individual belongs to the second population.