Optical Communication State Estimation via Random Projection

Solution Overview

Problem

The analysis of constellation data in optical communication quality degradation relies heavily on expert experience and requires a large amount of data, leading to significant computational burdens, with existing methods failing to reduce data amounts effectively.

Innovation Solution

A state estimation system that uses random projection to reduce and conceal the number of data pieces from constellation data, generating learning and identification concealment signals, and employs sparse dictionary learning to estimate the state of optical communication without increasing computational load.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If statistical approach or deep learning is used to estimate quality degradation, then estimation accuracy is improved, but calculation amount becomes enormous

Engineering Contradiction:

Improvequality degradation estimation accuracyVSAvoidcalculation amount

Core Design Contradiction:

Measurement precisionVSPower

Solution Approach 1:

The patent extracts only the essential features from constellation data by using a predefined dictionary of typical quality degradation patterns. Instead of processing the entire dataset through computationally intensive deep learning, the system extracts relevant information by matching observed constellation deviations against the predefined dictionary patterns, significantly reducing calculation requirements while maintaining estimation accuracy.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent transforms the problem from high-dimensional constellation data analysis to a parameter-based matching approach. By representing quality degradation through a limited set of parameters (phase errors, amplitude imbalances, skew) defined in the dictionary, the system changes the analysis from processing raw data points to comparing parameter deviations, thereby reducing computational burden.

Inventive Principle:

Principle #35Parameter changes

2Measurement precision

If deep learning is used to estimate quality degradation, then estimation accuracy is improved, but data processing complexity increases

Engineering Contradiction:

Improvequality degradation estimation accuracyVSAvoiddata processing complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extracts only the essential features from constellation data by using a predefined dictionary of typical quality degradation patterns. Instead of processing the entire dataset through computationally intensive deep learning, the system extracts relevant information by matching observed constellation deviations against the predefined dictionary patterns, significantly reducing calculation requirements while maintaining estimation accuracy.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent transforms the problem from high-dimensional constellation data analysis to a parameter-based matching approach. By representing quality degradation through a limited set of parameters (phase errors, amplitude imbalances, skew) defined in the dictionary, the system changes the analysis from processing raw data points to comparing parameter deviations, thereby reducing computational burden.

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If expert experience is used for constellation data analysis, then analysis accuracy is maintained, but automation level remains low

Engineering Contradiction:

Improveanalysis accuracyVSAvoidautomation level

Core Design Contradiction:

Measurement precisionVSExtent of automation

Solution Approach 1:

The patent creates a simplified copy of expert knowledge by encoding typical quality degradation patterns into a predefined dictionary. Instead of relying on actual expert analysis, the system copies the essential patterns and characteristics that experts would identify, allowing automated comparison against these patterns to achieve accurate quality degradation estimation without requiring expert intervention.

Inventive Principle:

Principle #26Copying

Data Source

PatentUS20240154694A1State estimation system, secret signal generator, state estimation method, secret signal generation program

Publication Date: 2024.05.09 NIPPON TELEGRAPH & TELEPHONE CORP

AI summary

Provided is a concealment signal generation unit that acquires learning constellation data and identification constellation data output from a signal processing circuit for optical communication, reduces and conceals the number of pieces of data from each of the pieces of constellation data through random projection, and generates a learning concealment signal and an identification concealment signal based on each piece of constellation data after the reduction and concealment of the number of pieces of data. Provided are a sparse dictionary learning unit that learns a concealment sparse dictionary using a sparse dictionary learning algorithm based on the learning concealment signal; and an identification unit that estimates a state of the optical communication using the concealment sparse dictionary based on the identification concealment signal.