Attention-based Time Series Forecasting with Limited Data

dc.contributor.authorVadström, Gustav
dc.contributor.departmentChalmers tekniska högskola / Institutionen för elektrotekniksv
dc.contributor.examinerMonti, Paolo
dc.contributor.supervisorBanar, Jafar
dc.date.accessioned2024-11-26T12:21:59Z
dc.date.available2024-11-26T12:21:59Z
dc.date.issued2024
dc.date.submitted
dc.description.abstractElectricity outages are common in electrical power systems, and often caused by natural phenomena, human intervention, or faults in electrical components, such as transformers. A small number of these faults can be predicted by analysing the stream of voltage and current. Forecasting faults in electrical power systems can prevent electricity outages that cause production downtime and capital losses. However, data collected in power systems are usually limited and unbalanced because of the very few historical predictable faults. This study focused on evaluating more recently popular attention-based machine learning models for time series prediction in electrical power systems, in a context where data is a significant limitation. The data was real and consisted of disturbances recorded from power systems over sev eral years, along with documented faults. Two different model architectures were evaluated and compared: the Long short-term memory (LSTM) and the transformer. Three different model instances were trained: using features manually extracted from each disturbance recording, using manually extracted features with pre-training on a similar dataset, and using a signal embedding pipeline attached to each model processing raw waveforms. The results from all six training instances showed that the transformer performed better than the LSTM in terms of evaluation metrics, although the LSTM outputs were more interpretable, because the transformer had higher confidence in its outputs even during false predictions. A bottleneck was found in the small sequence lengths, with improvement shown when utilizing pre training on a similar dataset containing longer sequences. The integrated waveform feature embedding also showed improvement over the manually extracted features.
dc.identifier.coursecodeEENX30
dc.identifier.urihttp://hdl.handle.net/20.500.12380/309011
dc.language.isoeng
dc.relation.ispartofseries00000
dc.setspec.uppsokTechnology
dc.subjectComputer
dc.subjectscience
dc.subjectComputer science
dc.subjectengineering
dc.subjectproject
dc.subjectthesis
dc.subjecttime series
dc.subjectelectrical power systems
dc.titleAttention-based Time Series Forecasting with Limited Data
dc.type.degreeExamensarbete för masterexamensv
dc.type.degreeMaster's Thesisen
dc.type.uppsokH
local.programmeData science and AI (MPDSC), MSc
Ladda ner
Original bundle
Visar 1 - 1 av 1
Hämtar...
Bild (thumbnail)
Namn:
Master_s_Thesis_Final_Report.pdf
Storlek:
5.39 MB
Format:
Adobe Portable Document Format
Beskrivning:
License bundle
Visar 1 - 1 av 1
Hämtar...
Bild (thumbnail)
Namn:
license.txt
Storlek:
2.35 KB
Format:
Item-specific license agreed upon to submission
Beskrivning: