Anomaly Detection in Time Series of EDFA Pump Currents to Monitor Degeneration Processes using Fuzzy Clustering

TL;DR

This work tackles aging-induced degeneration in EDFA pump currents, which is challenging to detect when operating below maximum output. It introduces a Change Detection Framework that combines entropy-based feature selection, PCA-based feature extraction, and fuzzy clustering variants (FCM, ProbCP, PossCP) to detect anomalies in pump-current time series across arbitrary operating points. Empirical results show that the EA+PCA+PossCP configuration delivers the best generalization and enables early change-point detection, with drift as low as $4.9\%$, outperforming conventional clustering baselines. The approach supports decentralized predictive maintenance for optical networks by reducing dimensionality and providing robust, real-time anomaly detection across diverse operating conditions.

Abstract

This article proposes a novel fuzzy clustering based anomaly detection method for pump current time series of EDFA systems. The proposed change detection framework (CDF) strategically combines the advantages of entropy analysis (EA) and principle component analysis (PCA) with fuzzy clustering procedures. In the framework, EA is applied for dynamic selection of features for reduction of the feature space and increase of computational performance. Furthermore, PCA is utilized to extract features from the raw feature space to enable generalization capability of the subsequent fuzzy clustering procedures. Three different fuzzy clustering methods, more precisely the fuzzy clustering algorithm, a probabilistic clustering algorithm and a possibilistic clustering algorithm are evaluated for performance and generalization. Hence, the proposed framework has the innovative feature to detect changes in pump current time series at an early stage for arbitrary points of operation, compared to state-of-the-art predefined alarms in commercially used EDFAs. Moreover, the approach is implemented and tested using experimental data. In addition, the proposed framework enables further approaches of applying decentralized predictive maintenance for optical fiber networks.

Figures (6)

• Figure 1: Data acquisition setup
• Figure 2: Change detection framework
• Figure 3: Entropy analysis on feature space
• Figure 4: Principle component analysis on feature space
• Figure 5: Training Error of Clustering Procedures