Degradation Prediction of Semiconductor Lasers Using Conditional Variational Autoencoder

Semiconductor lasers have been rapidly evolving to meet the demands of-generation optical networks. This imposes much more stringent requirements the laser reliability, which are dominated by degradation mechanisms (e.g., degradation) limiting the semiconductor laser lifetime. Physics-based are often used to characterize the degradation behavior, yet explicit domain knowledge and accurate mathematical models required. Building such models can be very challenging due to a lack of a understanding of the complex physical processes inducing the degradation various operating conditions. To overcome the aforementioned limitations, propose a new data-driven approach, extracting useful insights from the monitored data to predict the degradation trend without requiring specific knowledge or using any physical model. The proposed approach is on an unsupervised technique, a conditional variational autoencoder, and using vertical-cavity surface-emitting laser (VCSEL) and tunable edge laser reliability data. The experimental results confirm that our (i) achieves a good degradation prediction and generalization performance yielding an F1 score of 95.3%, (ii) outperforms several baseline ML based detection techniques, and (iii) helps to shorten the aging tests by predicting the failed devices before the end of the test and thereby costs