Network Node Cell Capacity Allocation via Neural Network Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In 4G/5G systems, the static cell capacity configuration fails to adapt dynamically to changing cell capacity requirements, leading to inefficient CPU resource usage, waste of resources, and insufficient capacity, resulting in poor user access and throughput.
Innovation Solution
A method involving a network node that acquires cell capacity information, determines predicted cell capacities based on summations satisfying specific conditions, and allocates resources using a neural network model to optimize CPU resource allocation across cells.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If static cell capacity configuration is used, then CPU resource allocation is simplified, but cell capacity requirements cannot adapt dynamically leading to resource waste or insufficiency
Solution Approach 1:
The patent implements dynamic cell capacity configuration by enabling the network node to adjust cell capacity parameters in real-time based on actual network conditions and predictions, transforming the static configuration into a dynamic system that adapts to changing requirements
Solution Approach 2:
The patent employs feedback mechanisms where the network node monitors actual cell capacity requirements and uses this information to adjust configuration parameters, creating a closed-loop system that continuously optimizes resource allocation based on observed performance
2Reliability
If cell capacity is configured for worst case, then reliability is improved, but CPU resource usage increases due to over-provisioning
Solution Approach 1:
The patent changes the configuration parameters from fixed worst-case values to dynamically adjusted values based on actual network conditions, allowing the system to maintain reliability while reducing resource allocation to match real requirements rather than theoretical maximums
Solution Approach 2:
Instead of always allocating full worst-case capacity, the patent applies partial allocation based on actual needs, providing sufficient capacity for current requirements while avoiding the excessive resource consumption that would result from always provisioning for maximum demand
3Productivity
If dynamic cell capacity adjustment is implemented, then resource allocation efficiency is improved, but system complexity increases
Solution Approach 1:
The patent implements self-service mechanisms where the network node automatically monitors, predicts, and adjusts cell capacity parameters without requiring manual intervention, enabling dynamic optimization while keeping operational complexity manageable through automation
Solution Approach 2:
The patent uses prediction mechanisms to determine future cell capacity requirements in advance, allowing the system to proactively adjust configurations before actual demand changes occur, improving responsiveness while maintaining systematic control
Data Source
AI summary
The disclosure relates to a method performed by a network node, comprising acquiring cell capacity information of a plurality of cells corresponding to a Distributed Unit (DU) of a base station. The method comprises determining cell capacity summations corresponding to the DU based on each cell corresponding to different cell capacities, based on the cell capacity information. The method comprises determining a predicted cell capacity of the plurality of cells based on the cell capacity summations, for the base station allocating a cell capacity with respect to each of the plurality of cells according to the predicted cell capacity.