Base Station Load Prediction for Adaptive Energy Saving

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing energy-saving methods for base stations are inflexible and inefficient due to reliance on fixed time periods determined by network situations and personnel experience, failing to adapt to variable network environments and real-time service changes, leading to suboptimal energy consumption.

Innovation Solution

An energy-saving method that collects energy-consumption influencing factor data, predicts load trends using machine learning models, and determines tailored energy-saving strategies and effective times based on these predictions to flexibly manage energy consumption.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Use of energy by stationary object

If fixed time periods for energy saving are configured based on network situation and personnel experience, then energy saving can be implemented, but the energy-saving method is inflexible and cannot adapt to variable network environments and real-time service changes

Engineering Contradiction:

Improveenergy consumption of base stationVSAvoidadaptability to network environment changes

Core Design Contradiction:

Use of energy by stationary objectVSAdaptability or versatility

Solution Approach 1:

The patent applies dynamics by transitioning from fixed, static energy-saving time periods to dynamic, real-time energy-saving strategies. The system continuously collects energy-consumption influencing factor data and adjusts energy-saving actions based on current network conditions, service demands, and predicted load trends, making the energy-saving mechanism flexible and adaptive to changing environments.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The patent implements feedback by establishing a closed-loop system that collects energy-consumption influencing factor data from the network, predicts load trends using machine learning models, determines appropriate energy-saving strategies based on predictions, executes these strategies, and continuously monitors the results to refine future decisions. This feedback mechanism enables the system to adapt to variable network environments effectively.

Inventive Principle:

Principle #23Feedback

2Ease of manufacture

If specified configuration of energy-saving time periods is used, then implementation is simple, but it cannot cope with various unexpected events and service changes

Engineering Contradiction:

Improveease of configurationVSAvoidability to handle unexpected events

Core Design Contradiction:

Ease of manufactureVSAdaptability or versatility

Solution Approach 1:

The patent applies self-service by enabling the base station to automatically collect energy-consumption influencing factor data, predict load trends using machine learning models, and determine energy-saving strategies without requiring manual configuration or intervention. The system autonomously adapts to unexpected events and service changes by processing real-time data and adjusting energy-saving actions independently.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent implements parameter changes by using machine learning models to analyze multiple energy-consumption influencing factors and dynamically adjust energy-saving parameters based on predicted load trends. Instead of relying on fixed configurations, the system continuously modifies energy-saving strategies according to changing network conditions, service demands, and environmental factors.

Inventive Principle:

Principle #35Parameter changes

3Productivity

If multiple cells have different energy-saving time periods, then local optimization is possible, but uniform and efficient configuration becomes difficult

Engineering Contradiction:

Improveenergy-saving efficiencyVSAvoidconfiguration complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent applies universality by creating a unified energy-saving management system that can handle multiple cells with different characteristics through a common framework. The machine learning-based prediction and decision-making mechanism works consistently across all cells, automatically adapting to each cell's specific conditions while maintaining uniform configuration management and reducing overall system complexity.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS12501356B2Energy-saving method, base station, control unit, and storage medium

Publication Date: 2025.12.16 ZTE CORP

AI summary

Provided are an energy-saving method, a base station, a control unit, and a storage medium. The method includes: collecting energy-consumption influencing factor data of a target cell; predicting a load trend of the target cell according to the energy-consumption influencing factor data; and determining, according to the load trend, an energy-saving strategy of the target cell and effective time corresponding to the energy-saving strategy and executing the energy-saving strategy according to the effective time.