RAN AI Task Orchestration via RIC for Efficient Resource Scheduling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing diversification of services in wireless communication networks, such as ultra-high rates, ultra-low latency, and massive connections, complicates network planning, configuration, and resource scheduling, posing challenges to network operation and maintenance, especially with advanced features like MIMO and beamforming, and necessitates improved energy efficiency.
Innovation Solution
Introduce artificial intelligence (AI) in radio access networks (RAN) through a Radio Intelligence Controller (RIC) to manage AI tasks, enabling efficient network planning, configuration, and resource scheduling by configuring AI tasks to base stations and terminal devices, facilitating data collection, inference, and model training.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If AI tasks are introduced in RAN to improve network planning and resource scheduling efficiency, then network efficiency is improved, but device complexity increases
Solution Approach 1:
The patent introduces a Radio Intelligence Controller (RIC) as an intermediary component that manages AI tasks separately from the base station and terminal device. The RIC receives task configuration information from the O&M system, processes AI tasks, and coordinates with base stations and terminals, thereby improving network efficiency while isolating the complexity of AI management from operational devices.
Solution Approach 2:
The patent segments the network architecture into distinct functional components: the O&M system for configuration management, the RIC for AI task execution and coordination, base stations for radio access, and terminal devices for user communication. This segmentation allows AI capabilities to be introduced without complicating individual device functionalities.
2Adaptability or versatility
If AI functions are integrated into base station and terminal device to enable intelligent processing, then network intelligence is improved, but power consumption increases
Solution Approach 1:
The patent implements periodic task activation and deactivation mechanisms where the RIC receives task configuration information that specifies when AI tasks should be executed. Tasks can be activated during specific time periods or conditions and deactivated when not needed, allowing the network to maintain intelligence capabilities while reducing power consumption during periods of low activity or when AI processing is not required.
3Adaptability or versatility
If multiple AI tasks are configured with different execution bodies to handle diverse network functions, then adaptability is improved, but task management complexity increases
Solution Approach 1:
The RIC serves as a centralized intermediary that receives task configuration information from the O&M system and manages the distribution of AI tasks to appropriate execution bodies (base stations or terminal devices). This centralized management approach allows the system to support multiple diverse AI tasks with different execution requirements while maintaining simplified task management through a single coordination point.
Data Source
Figure 1(a)
Figure 1(b)~2
Figure 3~4
AI summary
Embodiments of this application provide a communication method and an apparatus, to introduce artificial intelligence AI in a radio access network RAN. The method includes: A wireless intelligent controller RIC sends configuration information of one or more AI tasks to a base station. The configuration information of each AI task is used to indicate one or more of the following content of the AI task: a task identifier ID, a task type, task content, a task execution body, and a task status. The AI task may be executed by the base station or a terminal.