Logo: to the web site of Uppsala University

uu.sePublications from Uppsala University
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Plant Performance Monitoring of Concentrated Solar Power Plants
Uppsala University, Disciplinary Domain of Science and Technology, Technology, Department of Materials Science and Engineering.
2022 (English)Independent thesis Advanced level (degree of Master (One Year)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

The Paris Agreement aims to limit global average temperature rise to well below 2°C above pre-industrial levels and "to pursue efforts to limit temperature rise to 1.5°C". To achieve this goal, emission of greenhouse gases must fall to zero in the upcoming few years. This goal can be achieved by empowering the existing renewable energy technologies. One of these technologies is concentrated solar power technology (CSP). CSP plants can be empowered by employing performance monitoring systems at the plant location. There are various performance monitoring systems in place to monitor the key performance indicators of the power plants which help in the optimization and increase in efficiency of operations at a power plant. The traditional approach to develop these performance monitoring systems is to model the entire power plant mathematically and simulate the expected behaviour of the various components of the power plant. The goal of this thesis is to explore an approach that involves the use of a machine learning algorithm to simulate and thus predict the values associated with the key performance indicators of the concentrated solar power tower and the parabolic trough power plant. A Long Short-Term Memory (LSTM) machine learning algorithm has been used to make the predictions of the pre-selected key performance indicators in this study. The predicted values have been compared to the actual values and are evaluated based on the root mean squared error score and the mean absolute error score. 

Place, publisher, year, edition, pages
2022. , p. 101
Series
MATVET Energiteknik
Keywords [en]
Concentrated Solar Power, Machine Learning, Performance Monitoring System
National Category
Energy Engineering
Identifiers
URN: urn:nbn:se:uu:diva-489682OAI: oai:DiVA.org:uu-489682DiVA, id: diva2:1715684
External cooperation
Siemens Energy Unipessoal Lda.
Educational program
Master Programme in Energy Technology
Supervisors
Examiners
Available from: 2022-12-05 Created: 2022-12-02 Last updated: 2022-12-05Bibliographically approved

Open Access in DiVA

No full text in DiVA

By organisation
Department of Materials Science and Engineering
Energy Engineering

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 256 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf