MSc diploma with Subject: AI's contribution to the optimization of energy storage systems

Machine Learning Models: Regression, Classification using Kaggle datasets which concern Energy Storage datasets

Context

3 Regression Models 3 Classification Models

Technologies

Language: Python

Libraries: Pandas, Numpy, Scikit-Learn, Keras

Algorithms: Decision Trees, Support Vector Machines, Neural Network, Linear Regression, Random Forest, XGBoost

For Visualization: Matplotlib, Seaborn

Evaluation Metrics: MSE, R-Squared, Accuracy, Precision, Recall, F1-Score

Using the correct values for the corresponding algorithm, the metrics have been optimised. These models are designed to provide high-accuracy forecasts for energy storage systems. Predicting demand patterns and storage energy needs, they enable energy films to:

1. Better Decision-Making on when to store or release energy
2. Minimize Costs using the results of predictions
3. Data-Driven decisions for possible investments