The increasing reliance on optical fiber networks for high-speed internet and telecommunication services requires effective fault detection systems to ensure optimal performance and minimize downtime. This research presents a machine learning-based approach for fault detection in optical fiber networks using ensemble methods. The system utilizes three ensemble classifiers: Stacking Classifier, Voting Classifier, and Random Forest. These models are designed to combine multiple machine learning algorithms, including Random Forest (RF), LightGBM, and Adaboost, to improve detection accuracy. The project employs a dataset from Kaggle, which includes network features such as temperature, signal strength, and attenuation, to train the models. The system is developed with a user-friendly interface using HTML, CSS, and JavaScript for the front-end, and Flask with Python for the back-end. The primary goal of this project is to enhance the reliability and performance of optical fiber networks by providing a robust fault detection mechanism. Evaluation metrics like accuracy, precision, recall, and F1-score are used to assess the effectiveness of the models. The results show that ensemble techniques significantly improve fault detection compared to individual models, making this approach a valuable tool for network monitoring and maintenance.

Keywords: Optical Fiber Networks, Fault Detection, Ensemble Machine Learning, Stacking Classifier, Voting Classifier, Random Forest, Performance Evaluation.