ML-Based Scheduler for 5G Resource Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current wireless communication systems, particularly 5G NR networks, face challenges in efficiently managing resource allocation across diverse user equipment (UEs) with varying service level requirements and channel conditions, as existing schedulers struggle to meet different types of service level agreements (SLAs) due to heterogeneous network demands.
Innovation Solution
A machine learning-based scheduler (MLBS) is employed to determine sequences of resource assignments, including grants of scheduled resource allocations and modulation coding schemes, based on current channel state information and service level requirements, to optimize resource allocation across UEs with different SLAs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional schedulers are used for resource allocation, then device complexity is reduced, but the ability to meet diverse service level requirements deteriorates
Solution Approach 1:
The patent replaces traditional mechanical scheduling algorithms with a machine learning-based scheduler that uses neural networks to predict optimal resource allocations. This substitution enables the system to handle diverse service level requirements (eVMB, uRLLC, eMTC) more effectively by learning from historical data and adapting to varying channel conditions, while the computational complexity is managed through efficient model deployment on network infrastructure.
Solution Approach 2:
The machine learning scheduler dynamically adjusts resource allocation parameters (time-frequency resources, power, modulation schemes) based on learned patterns from channel state information and service level requirements. This parameter optimization enables the system to adapt to heterogeneous network conditions and meet diverse QoS requirements without requiring complex manual configuration or rule-based scheduling logic.
2Adaptability or versatility
If machine learning based scheduler is employed to meet diverse service level requirements, then adaptability improves, but computational complexity increases
Solution Approach 1:
The patent segments the resource allocation problem into separate machine learning models for different service types (eVMB, uRLLC, eMTC), each trained on specific service level requirements and channel conditions. This segmentation allows each model to specialize in optimizing for its particular service type, improving overall adaptability while managing computational complexity through modular model deployment and independent training processes.
3Reliability
If resource allocation is optimized for heterogeneous networks, then service level requirement satisfaction improves, but processing time increases
Solution Approach 1:
The patent employs preliminary action by pre-training machine learning models offline using historical channel state information and service level requirement data. The models are trained to predict optimal resource allocations for various scenarios, enabling real-time scheduling decisions to be made rapidly during actual network operation. This offline training approach shifts computational burden from real-time processing to preparatory model development, thereby reducing online processing time while maintaining high service level requirement satisfaction.
Data Source
AI summary
Aspects include a machine learning based resource block scheduler configured to meet service level requirements of applications. Aspects include receiving a plurality of scheduling requests each associated with a respective application of a plurality of applications on a plurality of wireless devices, identifying a plurality of current channel state information each associated with one of the plurality of wireless devices, and identifying a plurality of different types of service level requirements each associated with one of the plurality of applications. Further, the aspects include determining, by a machine learning based scheduler based on each of the plurality of current channel state information, a sequence of resource assignments expected to meet the plurality of different types of service level requirements, the sequence of resource assignments including a plurality of grants of a scheduled assignment of a resource, and transmitting respective grants for the respective applications to the wireless devices.