AI-Driven 5G Base Station Resource Adaptation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current virtualized 5G RAN implementations are not designed to handle computational resource outages effectively, leading to performance degradation when resources are scarce, as they assume constant availability and lack mechanisms for graceful scaling and resource adjustment.
Innovation Solution
A method and apparatus utilizing an AI engine in the central unit of a base station to learn from computational metrics and adjust the configuration of virtualized network functions, including vertical and horizontal scaling, and determining optimal resource allocation and migration of functions between the central and distributed units using the F1 interface.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If virtualized network functions are deployed in 5G RAN to enable flexible network architecture, then network adaptability and versatility are improved, but reliability deteriorates when computational resources become scarce
Solution Approach 1:
The patent implements dynamic resource allocation and functional split adjustment between CU and DU based on real-time computational resource availability. The system can dynamically migrate network functions between centralized and distributed units, adjusting the functional split point to maintain service continuity during resource constraints, thereby resolving the contradiction between adaptability and reliability.
Solution Approach 2:
The system changes operational parameters by adjusting the degree of centralization versus distribution of network functions. When computational resources are abundant, more functions can be centralized; when resources are scarce, the system shifts to a more distributed mode, changing the operational state to maintain reliability while preserving adaptability.
2Productivity
If computational resources are allocated to handle peak demand, then productivity is improved, but device complexity increases due to resource management overhead
Solution Approach 1:
The patent implements self-service through AI-driven autonomous resource management. The system automatically monitors computational metrics, predicts resource needs, and adjusts functional allocation without manual intervention. This autonomous operation reduces the complexity of resource management while maintaining high productivity through optimized resource utilization.
Solution Approach 2:
The system establishes feedback loops where computational metrics from both CU and DU are continuously monitored and fed back to the AI engine. This feedback enables automatic adjustment of resource allocation, reducing management complexity through closed-loop control while improving productivity through continuous optimization.
3Device complexity
If functional split between CU and DU is fixed, then device complexity is reduced, but adaptability deteriorates when computational resources change
Solution Approach 1:
The patent transitions from a static functional split to a dynamic one where the division of functions between CU and DU can change based on computational resource availability. The AI engine continuously adjusts the functional split point, allowing the system to adapt to changing resource conditions while managing complexity through automated decision-making.
Data Source
AI summary
The present disclosure relates to a method and system for converging a 5th-Generation (5G) communication system for supporting higher data rates beyond a 4th-Generation (4G) system with a technology for Internet of Things (IoT). The system may be applied to intelligent services based on the 5G communication technology and the IoT-related technology, such as smart home, smart building, smart city, smart car, connected car, health care, digital education, smart retail, security and safety services. The method includes a method for configuring a base station in a telecommunication network. The base station includes a central unit (CU) and a distributed unit (DU). The CU is arranged to perform virtualized network functions (VNFs). The CU includes an artificial intelligence (AI) engine operable to learn from computational metrics and to adjust the configuration of various VNFs, wherein an F1 interface is used to exchange computational metrics between the CU and the DU.