Lehrinhalte
The analysis and interpretation of data becomes ever more important, also for engineers. Digitalization and Smart Grids are terms to describe a host of novel data-based services in the field of generation, distribution, consumption and marketing of (renewable) energy. The lecture presents the recent developments and their underlying principles of machine learning technology.
For a start we will describe the different problem settings of machine learning in a structured way (classification, regression, clustering, dimensionality reductions, time series models, ) and present for each setting relevant applications from the energy sector (prediction of renewable energy or consumption in multimodal energy systems, fault detection and prediction, data visualization, robust investments decisions, customer analysis, probabilistic load flow, ).
Thereafter we will briefly review necessary tools from optimization and probability theory, as well as introduce probabilistic graphical models. With these tools we will then study for each problem setting one or more machine learning algorithms in detail, together with use cases from the energy domain. Classic algorithms will be developed (e.g. linear regression, k-means, principal component analysis, ) as well as modern ones (e.g. SVMs, Deep Learning, Collaborative filtering, ). Practical exercise with Matlab will deepen the understanding and support students active knowledge (We will offer a Matlab course in the last week of the semester break where we will cover the basics of programming with Matlab).
Literatur
[list]
[*]A Géron: Hands on Machine Learning with scikit-learn and Tensorflow, 2017
[*]Friedman, Hastie, Tibshirani: The elements of statistical learning, 2001
[*]Koller, Friedmann: Graphical Models, 2009
[/list]
Voraussetzungen
[list]
[*]Good knowledge of linear algebra and the foundations of numerical optimization (e.g. from the course 18-st-2010 Energieanagement & Optimierung)
[*]Using Matlab for programming the practical examples should pose no difficulty. A block tutorial on the use of Matlab is offered as 18-st-2030 Matlab Grundkurs.
[/list]
The analysis and interpretation of data becomes ever more important, also for engineers. Digitalization and Smart Grids are terms to describe a host of novel data-based services in the field of generation, distribution, consumption and marketing of (renewable) energy. The lecture presents the recent developments and their underlying principles of machine learning technology.
For a start we will describe the different problem settings of machine learning in a structured way (classification, regression, clustering, dimensionality reductions, time series models, ) and present for each setting relevant applications from the energy sector (prediction of renewable energy or consumption in multimodal energy systems, fault detection and prediction, data visualization, robust investments decisions, customer analysis, probabilistic load flow, ).
Thereafter we will briefly review necessary tools from optimization and probability theory, as well as introduce probabilistic graphical models. With these tools we will then study for each problem setting one or more machine learning algorithms in detail, together with use cases from the energy domain. Classic algorithms will be developed (e.g. linear regression, k-means, principal component analysis, ) as well as modern ones (e.g. SVMs, Deep Learning, Collaborative filtering, ). Practical exercise with Matlab will deepen the understanding and support students active knowledge (We will offer a Matlab course in the last week of the semester break where we will cover the basics of programming with Matlab).
Literatur
[list]
[*]A Géron: Hands on Machine Learning with scikit-learn and Tensorflow, 2017
[*]Friedman, Hastie, Tibshirani: The elements of statistical learning, 2001
[*]Koller, Friedmann: Graphical Models, 2009
[/list]
Voraussetzungen
[list]
[*]Good knowledge of linear algebra and the foundations of numerical optimization (e.g. from the course 18-st-2010 Energieanagement & Optimierung)
[*]Using Matlab for programming the practical examples should pose no difficulty. A block tutorial on the use of Matlab is offered as 18-st-2030 Matlab Grundkurs.
[/list]
- Lehrende: Anonym
- Lehrende: Florian Steinke
Semester: WT 2018/19