Wireless Access Point Sleep Scheduling for Energy Without Outages

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for switching off radio resources in wireless access points pose a risk of outages when users attempt to connect, necessitating a method to minimize this risk while conserving energy.

Innovation Solution

A method using machine learning to determine optimal standby periods for radio resources by analyzing connection patterns, employing a neural network to predict periods of inactivity and switch off resources accordingly.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of energy

If radio resources are switched off or put into standby mode to conserve energy, then energy consumption is reduced, but the risk of service interruption increases when users attempt to connect

Engineering Contradiction:

Improveenergy consumptionVSAvoidservice continuity

Core Design Contradiction:

Loss of energyVSReliability

Solution Approach 1:

The system performs preliminary learning during a learning period to collect connection information before determining shutdown periods. By analyzing connection patterns in advance and predicting future connectivity needs, the system can confidently switch off radio resources during predicted idle periods without causing service interruptions, thus resolving the contradiction between energy conservation and service reliability

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system continuously monitors connection information and uses machine learning models to predict future connectivity patterns. This feedback mechanism allows the system to adaptively adjust shutdown schedules based on actual usage patterns, ensuring that radio resources remain active when needed while being switched off during predicted idle periods, thereby maintaining service reliability while reducing energy consumption

Inventive Principle:

Principle #23Feedback

2Reliability

If machine learning models are used to predict optimal shutdown periods, then service interruption risk is reduced, but device complexity increases

Engineering Contradiction:

Improveservice continuityVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent introduces a standby module as an intermediary component that houses the machine learning models and prediction algorithms. This modular approach isolates the complexity of the learning system from the core radio resource management functions, making the system more manageable and maintainable while still achieving improved service continuity through accurate predictions

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system uses connection information from the learning period as a template or copy to predict future connectivity patterns. By analyzing historical connection data and creating predictive models based on these patterns, the system can determine shutdown periods without requiring complex real-time analysis, thus reducing overall system complexity while maintaining reliability

Inventive Principle:

Principle #26Copying

Data Source

PatentEP4672098A1Method for managing radio resource donation of wireless access point device, sleep management device, and wireless access point device

Publication Date: 2025.12.31 SAGEMCOM BROADBAND SAS

Figure 1~2
Figure 3~4

AI summary

The invention relates to a method for determining by prediction, using automated machine learning, time ranges (T2) during which a radio interface (R1) of a wireless access point (11) of a communication network (1) can be switched off or put into standby mode, for energy saving purposes.