API for 5G-NR Cell Count and QoS Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In 5G-NR networks, existing technologies face challenges in optimizing the utilization of hardware accelerators, leading to underutilization due to unknown quality of service (QoS) capabilities, resulting in inefficient processing of 5G workloads.
Innovation Solution
The implementation of APIs that communicate between layer 2 and layer 1 of the O-RAN network protocol stack to determine and optimize the utilization of hardware accelerators, allowing applications to identify the maximum number of 5G-NR cells that can be supported while meeting specific QoS requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Power
If hardware accelerators are deployed to process 5G-NR workloads, then processing power and speed are improved, but utilization efficiency deteriorates due to unknown QoS capabilities
Solution Approach 1:
The patent implements a feedback mechanism where the application queries the hardware accelerator's QoS capabilities through an API before workload allocation. The system receives feedback about the maximum number of cells that can be supported at different QoS levels, then adjusts workload distribution accordingly. This closed-loop feedback resolves the contradiction by enabling informed resource allocation that maximizes both processing power utilization and efficiency.
Solution Approach 2:
The patent performs preliminary action by having the application query the hardware accelerator's capabilities in advance of workload submission. The system determines the maximum supported cells and QoS parameters before allocating workloads, ensuring that the hardware accelerator is fully utilized without overloading. This preliminary capability assessment prevents underutilization while maintaining processing power effectiveness.
2Adaptability or versatility
If the number of supported cells is increased to improve network coverage, then service capability is improved, but processing resources are overwhelmed leading to QoS degradation
Solution Approach 1:
The patent implements dynamic adaptation where the application can query and adjust the number of supported cells based on current QoS requirements and hardware capabilities. The system dynamically determines the optimal cell count at different QoS levels (e.g., 64 cells at QoS level 1, 32 cells at QoS level 2) rather than using a fixed configuration. This dynamic approach allows the system to maintain reliability by adjusting service capability to match available processing resources.
Solution Approach 2:
The patent changes key parameters including the number of supported cells, QoS levels, and processing thresholds based on hardware accelerator capabilities. The system modifies these parameters dynamically - for example, reducing the cell count from 64 to 32 when QoS requirements increase - to maintain the reliability-QoS balance while still providing adaptable service capability across different operational conditions.
3Quantity of substance
If processing resources are allocated to support more cells, then network capacity is improved, but memory and time resources are depleted
Solution Approach 1:
The patent applies partial action by allocating processing resources proportionally based on QoS requirements and hardware capabilities rather than maximizing cell count indiscriminately. The system processes a partial set of cells (e.g., 32 out of 64) when high QoS is required, and only processes the maximum capacity (64 cells) when QoS requirements are lower. This partial action approach optimizes the balance between network capacity and resource consumption.
Solution Approach 2:
The patent changes processing parameters including cell count, QoS levels, and resource allocation thresholds based on hardware accelerator capabilities and current workload conditions. By dynamically adjusting these parameters, the system optimizes network capacity utilization while preventing depletion of memory and time resources, achieving efficient resource usage across varying operational demands.
Data Source
AI summary
Apparatuses, systems, and techniques to perform one or more APIs. In at least one embodiment, a processor is to perform an API to indicate a number of 5G-NR cells that are able to be performed concurrently by one or more processors; a processor is to perform an API to indicate whether one or more processors are able to perform a first number of 5G-NR cells concurrently; a processor comprising one or more circuits is to perform an API to indicate whether one or more resources of one or more processors are allocated to perform 5G-NR cells; and/or a processor comprises one or more circuits to perform an API to indicate one or more techniques to be used by one or more processors in performing one or more 5G-NR cells.