FogMLS: A Labeled Dataset for Machine Learning-Based Resource Scheduling in Heterogeneous IoT-Fog-Cloud Systems.

FogMLS is a labeled dataset designed to support supervised machine learning research in fog computing resource scheduling. The dataset was generated using the FogMLS simulator, a Python-based three-tier IoT-fog-cloud simulation framework that incorporates a Genetic Algorithm scheduler with greedy initialisation. Dataset Structure:- Rows: 5,000 (one per scheduling slot)- Feature columns: 600 (200 task positions x 3 features each)- Label columns: 200 (one resource assignment per task position)- Total columns: 800- Missing values: 0- File format: CSV Features per task position:- Task type code (0-5)- Instruction count in simulation units- Data size in simulation units Label values:- 0: Padding (unused task position)- 1: Cloud server- 2: Fog node 1 (CPU=5 SU, RAM=1000 MB, BW=1 SU)- 3: Fog node 2 (CPU=10 SU, RAM=2000 MB, BW=2 SU)- 4: Fog node 3 (CPU=20 SU, RAM=3000 MB, BW=3 SU) The dataset was validated using a multi-output multi-layer perceptron achieving 96.91% overall accuracy with F1 scores above 0.85 for all four scheduling classes. Label consistency was confirmed across three independent random seeds (42, 123, 456). This dataset accompanies a companion paper currently under review.