Radio Base Station Resource Allocation via Traffic Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current radio base station technologies face high switching overhead when reallocating resources among multiple base stations, leading to inefficient resource utilization and increased power consumption due to frequent resource switching and inadequate consideration of traffic fluctuations.
Innovation Solution
A radio base station apparatus with a baseband processing pool, traffic history storage, traffic prediction unit, and process resource control unit that predicts traffic fluctuations and dynamically allocates resources among signal processing modules at predetermined intervals, reducing switching overhead and optimizing resource usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If process resources are reallocated frequently to match traffic fluctuations, then resource utilization efficiency is improved, but switching overhead increases
Solution Approach 1:
The system performs preliminary actions by predicting future traffic fluctuations using machine learning models before actual traffic changes occur. This allows process resources to be pre-al located in advance, avoiding the need for frequent reactive reallocations and reducing switching overhead while maintaining high resource utilization efficiency.
2Use of energy by stationary object
If the number of operated process resources is reduced during low traffic, then power consumption is decreased, but service quality may deteriorate
Solution Approach 1:
The system implements feedback mechanisms by continuously monitoring actual traffic conditions and comparing them with predictions. The machine learning models are trained using historical traffic data and performance feedback, enabling the system to dynamically adjust the number of operated process resources while maintaining service quality thresholds, thus reducing power consumption without compromising reliability.
3Productivity
If resource allocation is optimized dynamically, then resource sharing efficiency is improved, but system complexity increases
Solution Approach 1:
The system introduces machine learning models as intermediary components between traffic monitoring and resource allocation decisions. These models process complex traffic patterns and translate them into simplified resource allocation instructions, improving resource sharing efficiency while containing system complexity by delegating computational tasks to specialized algorithms rather than complex control logic.
Data Source
AI summary
Traffic history storage unit (130) stores, as traffic history, traffic results at base station cell radio units (200-1 to 200-n). Traffic database (140) stores traffic data learned on the basis of the traffic history. Traffic prediction unit (150) predicts, on the basis of the traffic data and the traffic history, traffic fluctuation that may occur after a predetermined time interval. Process resource control unit (160) controls, on the basis of the predicted traffic fluctuation, the allocation of process resources in signal processing cards (121-1 to 121-m) at every predetermined time intervals.