Management and control of Smartgrids and microgrids
General details of the subject
- Face-to-face degree course
Description and contextualization of the subjectSmartgrids should prove to adequately work for tomorrow networks. This requires technical solutions supported by adequate data analysis and mining so that the future network able to face the new requirements, including the integration of renewable based generation, energy storage systems, electric vehicles, and demand response.
Therefore, data mining techniques are introduced in this subject, including supervised and unsupervised classification algorithms applied to Smartgrids concepts. Furthermore, data based decision making will be also covered by means of mathematical optimization.
|AGINAKO BENGOA, NAIARA||University of the Basque Country||Profesorado Adjunto (Ayudante Doctor/A)||Doctor||Bilingual||Science of Computation and Artificial Intelligencefirstname.lastname@example.org|
|ALDASORO MARCELLAN, UNAI||University of the Basque Country||Profesorado Adjunto (Ayudante Doctor/A)||Doctor||Bilingual||Applied Mathematicsemail@example.com|
|Students should have updated knowledge about the advanced working techniques and methodologies related to the field of Smartgrids and distributed generation, particularly from the point of view of their control.||15.0 %|
|Awareness and application of the concepts and specifications of Smartgrids, their topologies, constituent components and basic dimensioning.||10.0 %|
|Developing operational and management strategies, including advanced techniques, for the grid-level regulation of Smartgrids.||30.0 %|
|Assessing and comparing the behaviour of Smartgrids and Microgrids obtained through simulation with different operational and management strategies, and justifying the results obtained.||20.0 %|
|Applying computing and telecommunications tools as a support for control in Smartgrids and Distributed Generation.||10.0 %|
|Students should be able to communicate about the projects carried out working in multidisciplinary and multilingual national and international teams of professionals and researchers operating in the field of Smartgrids.||10.0 %|
|Students should be trained to understand and analyse technical documents, standards and scientific articles on the topic of the Master, and to apply them in the creation of work and research related to the field of Smartgrids.||5.0 %|
|Type||Face-to-face hours||Non face-to-face hours||Total hours|
|Applied classroom-based groups||6||5||11|
|Applied laboratory-based groups||8||15||23|
|Applied computer-based groups||4||7.5||11.5|
|Name||Hours||Percentage of classroom teaching|
|Drawing up reports and presentations||30.0||0 %|
|Expositive classes||24.0||100 %|
|Presentation of projects||3.0||100 %|
|Solving practical cases||21.0||66 %|
|Systematised study||30.5||0 %|
|Name||Minimum weighting||Maximum weighting|
|Drawing up reports and presentations||40.0 %||40.0 %|
|Practical tasks||20.0 %||20.0 %|
|Written examination||40.0 %||40.0 %|
Ordinary call: orientations and renunciationGroup project:
A group project will be carried out where the contents learned in the course will be applied. Each group will deliver a report and will make an oral defense of the work done.
Proposed exercises both face-to-face and non-face-to-face. The the exercises will be carried out individually or in groups.
Theoretical and practical questions that will evaluate the competences to be acquired in the subject.
Final grade for the ordinary call:
40% group project.
20% learning process.
40% written exam.
MINIMUM GRADE: To pass the course it is necessary that the grades of both the project and the written exam are at least 4 points out of 10. If these minimum grades are not obtained, the grade for the ordinary call will be a maximum of 4 (out of 10).
In any case, any student who does not take the written exam will have a grade of NOT PRESENTED.
Extraordinary call: orientations and renunciationA written exam consisting of theoretical and practical questions that will evaluate the content of the course, including the content from the laboratory practices and group project.
Final grade for the extraordinary call:
100% grade of the written exam
TemaryIntroduction to Data Mining
Application of supervised and unsupervised classification algorithms in SmartGrids
Introduction to optimization
Compulsory materialsDocumentation of the course: https://egela.ehu.eus
Basic bibliographyH. Lee Willis Distributed Power Generation: Planning and Evaluation. Marcel Dekker, Inc
R.S. Michalski, I. Bratko, M. Kubat (1998). Machine Learning and Data Mining. Methods and Applications. Wiley.
B. Sierra (2006). Aprendizaje Automático: Conceptos Básicos y Avanzados. Pearson ¿ Prentice Hall.
I.H. Witten, E. Frank (2005). Data Mining: Practical Machine Learning Tools and Techniques. Elsevier, 2nd edition.
B. Korte, J. Vygen (2018) Combinatorial Optimization. Theory and Algorithms. Springer.
In-depth bibliographyCarol L. Stimmel (2014). Big Data Analytics Strategies for the Smart Grid. Auerbach Publications.
M. Conforti, G. Cornujols, G. Zambelli (2014). Interger Programming. Springer
JournalsSmart Grid, IEEE Transactions on Renewable Energy (Elsevier)
Applied Energy (Elsevier)
Information Sciences (Elsevier)
Artificial Intelligence (Elsevier)
Computers and Operations Research (Elsevier)