Wireless Root Cause Estimation Using Received Power Time Series

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing communication quality estimation systems, such as the quality estimation apparatus described in Patent Literature 1, are unable to accurately identify the root cause of communication degradation between wireless stations, which hinders effective restoration measures.

Innovation Solution

A model building apparatus and method that utilize machine learning to build an estimation model for identifying the root cause of communication quality degradation by generating input data from time-series received power data, and a root cause estimation apparatus that uses this model to estimate the root cause of degradation based on input data.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If existing communication quality estimation systems are used, then communication quality can be estimated, but the root cause of degradation cannot be identified

Engineering Contradiction:

Improveroot cause identification accuracyVSAvoiddegradation cause information

Core Design Contradiction:

Measurement precisionVSLoss of information

Solution Approach 1:

The patent segments the communication quality degradation problem into multiple root cause categories (distance attenuation, shielding, fading) and uses separate estimation pathways for each, allowing precise identification of the specific cause rather than just overall quality assessment

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces a machine learning estimation model as an intermediary between raw communication data and root cause identification. This model processes time-series data including received power, transmission power, and channel state information to infer the underlying cause of degradation

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If time-series data processing is implemented, then root cause estimation accuracy is improved, but computational complexity increases

Engineering Contradiction:

Improveroot cause estimation accuracyVSAvoiddata processing complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent performs preliminary processing of time-series data by calculating derived parameters (received power, transmission power, channel state information) before feeding them into the estimation model. This preprocessing organizes raw data into meaningful features that the machine learning model can efficiently process

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent transforms raw communication parameters into derived parameters (e.g., calculating received power from signal strength, computing channel state information from transmission characteristics). These parameter transformations create more informative features for the estimation model without requiring complex algorithms

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS12627386B2Model building apparatus and model building method, root cause estimation apparatus and root cause estimation method, and recording medium

Publication Date: 2026.05.12 NEC CORP

AI summary

A model building apparatus includes: an acquisition unit that obtains, from a first wireless station, time-series data of received power of wireless communication between the first wireless station and a second wireless station; a generation unit that generates input data including change data about a degree of a change in the received power per unit time, based on the time-series data; and a building unit that builds the estimation model for estimating the root cause of degradation from the input data, by machine learning using the input data.