AI-Powered Radio Over-Temperature Handling

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current rule-based systems for managing over-temperature conditions in network node radios are sub-optimal due to static configuration and lack of feedback from internal and external factors, leading to inefficient handling and frequent 'Degraded Cell' alarms, which can result in radio shutdowns.

Innovation Solution

Implementing AI-powered radio over temperature handling using machine-learning models that select and train on diverse data sources, including temperature readings, environmental factors, and network performance indicators to predict and mitigate over-temperature conditions dynamically, optimizing OTH processes and parameters.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a rule-based controller with static configuration is used to manage over-temperature conditions, then the system structure is simple and easy to implement, but the system cannot adapt to dynamic conditions and generates too many 'Degraded Cell' alarms leading to frequent radio shutdowns

Engineering Contradiction:

Improveadaptability to dynamic temperature and traffic conditionsVSAvoidcontroller system complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent transitions from a static rule-based controller to a dynamic AI-powered controller that continuously learns from historical data and adapts its behavior in real-time. The machine learning model processes inputs including ambient temperature, traffic load, and historical alarm patterns to dynamically adjust over-temperature handling strategies, enabling the system to adapt to changing conditions without requiring complex reconfiguration.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system implements feedback mechanisms by collecting and analyzing historical data from previous over-temperature events, alarm patterns, and traffic conditions. This feedback loop enables the machine learning model to refine its predictions and adjustments continuously, improving the controller's adaptability while maintaining manageable complexity through automated learning rather than manual reconfiguration.

Inventive Principle:

Principle #23Feedback

2Reliability

If legacy over-temperature handling functions are used, then the implementation is straightforward with pre-defined rules, but the system generates excessive 'Degraded Cell' alarms that force the radio into self-protection mode and shutdown

Engineering Contradiction:

Improveradio operational reliabilityVSAvoidnumber of 'Degraded Cell' alarms

Core Design Contradiction:

ReliabilityVSObject-generated harmful factors

Solution Approach 1:

The machine learning model performs preliminary analysis by predicting over-temperature conditions and alarm patterns before they occur. By analyzing historical data and identifying patterns, the system can proactively adjust parameters and prevent excessive alarm generation, improving radio reliability while reducing harmful alarm factors through predictive rather than reactive control.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system dynamically changes control parameters such as alarm thresholds, back-off values, and shutdown triggers based on learned patterns from historical data. This adaptive parameter adjustment allows the system to maintain reliability by preventing excessive alarms while avoiding premature shutdowns, optimizing the balance between protection and operational continuity.

Inventive Principle:

Principle #35Parameter changes

3Adaptability or versatility

If multiple over-temperature mitigation functions with multiple parameters are configured, then the system can handle various temperature scenarios, but the configuration becomes complex and difficult to optimize under varying conditions

Engineering Contradiction:

Improvecoverage of temperature handling scenariosVSAvoidconfiguration and optimization difficulty

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The machine learning model performs self-service by automatically optimizing configuration parameters based on historical data and performance feedback. Rather than requiring manual tuning and optimization of multiple mitigation functions, the system self-adjusts parameters such as trigger thresholds, back-off values, and timing parameters, making the complex multi-function system easy to operate while maintaining comprehensive scenario coverage.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent consolidates multiple over-temperature mitigation functions into a unified AI-powered controller that handles diverse scenarios through a single adaptive system. The machine learning model universally applies to various temperature conditions and traffic patterns, eliminating the need for separate optimized configurations for each scenario while maintaining comprehensive coverage through learned generalizable patterns.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS20230328544A1Ai-powered radio over temperature handling

Publication Date: 2023.10.12 TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)

AI summary

A method for mitigating an undesired environmental condition in a communication network radio is provided. The method includes selecting a machine-learning model based on a plurality of data sources and determining a solution to mitigate the undesired environmental condition using the selected machine-learning model. An apparatus corresponding to the method for mitigating an undesired environmental condition is also provided. In addition, a computer storage medium storing a computer program for mitigating an undesired environmental condition in a communication network radio is provided.