Adaptive Cell On-Off Threshold Control via Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for controlling power consumption in network services by turning cells on or off based on traffic thresholds are limited by the difficulty in predicting peripheral environments, leading to conservative threshold settings that restrict power reduction.
Innovation Solution
An electronic device equipped with a communication circuit, memory for storing a learning model, and a processor that adaptsively applies enhanced learning to determine optimal on/off thresholds for network cells, reducing power consumption while maintaining network performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a low off threshold is configured conservatively to predict peripheral environment, then network performance is maintained, but power consumption reduction is restricted
Solution Approach 1:
The system performs preliminary actions by collecting historical traffic data and training machine learning models in advance to predict future traffic patterns. This allows the network to proactively determine optimal on/off thresholds before actual cell switching occurs, balancing power savings with performance requirements without conservative limitations.
Solution Approach 2:
The system implements feedback mechanisms where machine learning models continuously learn from actual network performance data and traffic patterns. The models are trained using historical data and refined based on observed outcomes, enabling dynamic adjustment of on/off thresholds that adapt to changing conditions while maintaining performance standards.
2Use of energy by moving object
If enhanced learning is applied adaptively to determine off threshold, then power consumption is reduced, but system complexity increases
Solution Approach 1:
The machine learning models operate autonomously to determine cell on/off decisions without requiring manual configuration or complex centralized control. The system self-learns from data and automatically adjusts thresholds, reducing the need for human intervention and simplifying operational complexity despite the sophisticated algorithms involved.
Solution Approach 2:
The patent introduces machine learning models as intermediary components between raw traffic data and cell control decisions. These models process and interpret complex data patterns, transforming them into actionable thresholds, thereby managing system complexity by delegating the analytical burden to specialized algorithms rather than requiring complex control logic throughout the network.
Data Source
AI summary
An electronic device is provided. The electronic device includes a communication circuit, a memory configured to store a learning model, and at least one processor, wherein the at least one processor is configured to obtain data related to a network situation of a base station from the communication circuit, calculate a performance indicator value related to network performance according to a performance indicator, based on the data related to the network situation, train the model, based on the performance indicator value calculated according to the performance indicator, determine an off threshold of traffic for turning off a cell, based on the trained model, and transmit the determined off threshold to the base station via the communication circuit.