Comparative Analysis of Machine Learning Algorithms for Anomaly Detection in Large-Scale Distributed Networks
Rachhapl Singh, Balwinder Kaur · 2025
This chapter presents a comprehensive analysis of machine learning algorithms for anomaly detection in large-scale distributed networks, a critical area in modern network management. As distributed systems, such as cloud computing and IoT, continue to expand, ensuring their security and operational efficiency becomes paramount. The chapter explores various machine learning techniques, evaluating their effectiveness in detecting anomalies such as intrusions, faults, and performance degradation. Key algorithms, including supervised, unsupervised, and reinforcement learning models, are assessed for their ability to identify abnormal patterns in diverse network environments. Emphasis was placed on the challenges of handling large volumes of data, scalability concerns, and real-time processing requirements. The chapter discusses the integration of anomaly detection systems with network monitoring tools to enhance decision-making and response times. Insights provided in this work offer valuable guidance for researchers and practitioners aiming to optimize anomaly detection systems in dynamic, distributed network infrastructures.