Machine Learning and Optimisation (Autumn Semester - 2023, 2024, 2025)

Official Course Link

The objective of this course is to provide a comprehensive understanding of machine learning and optimisation through practice, primarily in the field of smart energy systems, such as buildings. Following are the contents of this course, adapted mainly for time-series data.

• Read the data from static files or using REST APIs
• Data Engineering using the Medallion architecture on local PCs in SQLite databases
• Data Manipulation and Feature Engineering of a dataset
• Supervised Learning (Regression and Classification)
• Unsupervised Learning (Clustering)
• Deep Learning (CNN and LSTM for time-series regression)
• Natural Language Processing (Text Cleaning and Sentiment Analysis)
• Optimisation Algorithms (Linear Optimisation, Genetic Optimisation etc.)
• Use of OMEGAlpes (Generation of Optimization Models As Linear Programming for Energy Systems) for energy optimistaion problems

At the end of the course, students are able to:

• Understand the fundamental principles of machine learning algorithms
• Work with real-world data sets (analyze, understand, predict, prescribe) using data science and artificial intelligence tools
• Select and implement machine learning (or optimisation) method which is appropriate for the problem under consideration (e.g. time-series prediction, clustering of energy consumption profile, optimisation of battery energy for an energy self-consumption case).

Object Oriented Programming in Python (Autumn Semester - 2023)

Official Course Link

The objective of this module is to give a hands-on practice lab to the students for practicing object oriented programming in Python using the provided use-cases. Following are the contents of this course, adapted mainly for time-series data.

• The basic of Python language (Data Types, Collections, Loops)
• Data Manipulation of a dataset using Pandas as a dataframe
• Object Oriented Programming practice in Python

At the end of the course, students are able to use their knowledge for doing OOP in python.