Data and Code for Random Forest Energy Consumption Prediction

This record contains the experimental dataset and source code developed for a Master's degree research project on modular application placement in Cloud Continuum. Research Context:The primary goal of this work was to design, train, and validate Machine Learning (ML) models capable of optimizing the placement of modular applications within a distributed Fog infrastructure. Methodology:The data was generated using the iFogSim2 simulator, covering various scenarios with different placement strategies (such as CB-E, MGA, and Edgewards) and application types (DCNS, VRGame, and Translation Services). The dataset includes 4,194 unique experimental runs, recording 22 features including latency (delay), energy consumption, network usage, and CPU utilization. Contents: Experimental Dataset: A CSV file containing 4,194 rows of simulation results. Colab Notebook: Python code used for data exploration and ML model validation.