ClusterSense-FP: A Large-Scale Failure Prediction Dataset for CPU Cluster Infrastructure

The dataset contains operational and performance-related metrics collected from cluster nodes, including CPU utilization, memory usage, disk I/O, network activity, temperature, power consumption, and system health indicators. It aims to support the development of machine learning and artificial intelligence models for early failure detection, predictive maintenance, anomaly detection, and reliability assessment in distributed computing infrastructures.

Researchers and practitioners can utilize this dataset to improve system availability, reduce downtime, and enhance the resilience of large-scale cluster environments.