Endre søk
Link to record
Permanent link

Direct link
de Oliveira, Roger AlvesORCID iD iconorcid.org/0000-0001-5845-5620
Alternativa namn
Publikasjoner (10 av 30) Visa alla publikasjoner
Alves de Oliveira, R., Malfoy, A. & Rönnberg, S. K. (2024). Deep Anomaly Detection of Voltage Waveform Distortion in the Transmission Grid due to Geomagnetically Induced Currents. IEEE Transactions on Instrumentation and Measurements, 73, Article ID 2509212.
Åpne denne publikasjonen i ny fane eller vindu >>Deep Anomaly Detection of Voltage Waveform Distortion in the Transmission Grid due to Geomagnetically Induced Currents
2024 (engelsk)Inngår i: IEEE Transactions on Instrumentation and Measurements, ISSN 0018-9456, Vol. 73, artikkel-id 2509212Artikkel i tidsskrift (Fagfellevurdert) Published
sted, utgiver, år, opplag, sider
IEEE, 2024
HSV kategori
Forskningsprogram
Elkraftteknik
Identifikatorer
urn:nbn:se:ltu:diva-100715 (URN)10.1109/TIM.2024.3366271 (DOI)2-s2.0-85185388685 (Scopus ID)
Merknad

Validerad;2024;Nivå 2;2024-04-09 (joosat);

Tilgjengelig fra: 2023-08-24 Laget: 2023-08-24 Sist oppdatert: 2024-04-09bibliografisk kontrollert
de Oliveira, R. A., Salles, R. S., Rönnberg, S., de Carli, M. P. & Leborgne, R. C. (2024). Harmonic Anomalies Due to Geomagnetically Induced Currents as a Potential Cause of Protection Mal-Trips at the South Atlantic Anomaly Area. IEEE Transactions on Power Delivery, 39(2), 1124-1136
Åpne denne publikasjonen i ny fane eller vindu >>Harmonic Anomalies Due to Geomagnetically Induced Currents as a Potential Cause of Protection Mal-Trips at the South Atlantic Anomaly Area
Vise andre…
2024 (engelsk)Inngår i: IEEE Transactions on Power Delivery, ISSN 0885-8977, E-ISSN 1937-4208, Vol. 39, nr 2, s. 1124-1136Artikkel i tidsskrift (Fagfellevurdert) Published
sted, utgiver, år, opplag, sider
IEEE, 2024
HSV kategori
Forskningsprogram
Elkraftteknik
Identifikatorer
urn:nbn:se:ltu:diva-100716 (URN)10.1109/TPWRD.2024.3353487 (DOI)2-s2.0-85182951668 (Scopus ID)
Merknad

Validerad;2024;Nivå 2;2024-04-03 (joosat);

Funder: Swedish Energy Agency and Rönnbäret Foundation (24549);

This article has previously appeared as a manuscript in a thesis.

Tilgjengelig fra: 2023-08-24 Laget: 2023-08-24 Sist oppdatert: 2024-04-03bibliografisk kontrollert
de Oliveira, R. A. (2023). Applications of Unsupervised Deep Learning for Analysing Time-Varying Power Quality Big Data. (Doctoral dissertation). Luleå: Luleå University of Technology
Åpne denne publikasjonen i ny fane eller vindu >>Applications of Unsupervised Deep Learning for Analysing Time-Varying Power Quality Big Data
2023 (engelsk)Doktoravhandling, med artikler (Annet vitenskapelig)
Abstract [en]

Continuous power quality monitoring allows grid stakeholders to obtain information about the performance of the network and costumer facilities. Moreover, the analysis of continuous monitoring allows researchers to obtain knowledge on power quality phenomena. Power quality measurements result in a large amount of data. Power quality data can be classified as big data, not only for its volume, but also for the other complexities: velocity, variety, and veracity. Manual analysis of power quality data is possible but time-consuming. Moreover, data reports based on standardized indexes and classical statistical techniques might hide important information of the time-varying behaviour in power quality measurements. Artificial intelligence plays a role in providing automatic tools for proper analytics of big data.  A subset of artificial intelligence called machine learning has enabled computers to learn without explicit programming. Driven by the huge improvements in computer processing, a subset of machine learning based on multiple layers of artificial neural networks has been developed to tackle increasingly complex problems. The so-called deep learning applications teach themselves to perform a specific task by automatically extracting essential features from the raw data. Despite the possibilities of automatic feature extraction, most applications of deep learning to power quality are still the same as expert systems or earliest machine learning tools. Moreover, most of the applications are based on synthetic generated data and supervised techniques. In this context, the main motivation of this thesis is providing a new tool based on unsupervised deep learning to handle analytics of time-varying power quality big data. 

The unsupervised deep learning method proposed in this thesis combines a deep autoencoder with clustering for extracting patterns and anomalies in power quality big data. The deep autoencoder maps the original data to a compressed format that contains the principal features of the data. Automatic results are provided by the deep learning, and inferences can be obtained without requiring prior knowledge of deep learning. The outputs from unsupervised deep learning can serve as a guide for further data analysis, highlighting important time steps within large power quality datasets. By following these indications from the deep learning results, experts gain valuable insights into power quality phenomena, which can be referred to as "learning from deep learning". The interpretation of the deep learning results in this thesis allowed to making proper inferences for patterns and anomalies. For power quality measurements synchronised with 24-h, the results allowed making inferences concerning daily variations, seasonality, and the origins of power quality disturbances. For power quality measurements non-synchronised with 24-h, the results could be interpreted visually through the distribution of the patterns in a physical variable, such as the dynamic operating conditions of an electrical railway power system.

An important contribution of this thesis concerns the physical interpretation of the phenomena is related to the anomalies in harmonics caused by geomagnetically induced currents. An interesting finding by applying the deep anomaly detection to measurements in the Swedish transmission grid is the damping of the anomalies caused by geomagnetically induced currents in the winter due to the heating load. This thesis also demonstrated that the signatures for anomalies in harmonic measurements in a Swedish transmission location are similar to the ones found in a low-latitude transmission location at the South Atlantic Anomaly due to geomagnetically induced currents. Moreover, by cross-checking the anomalies at the South Atlantic Anomaly with protection trips with undetermined causes, this thesis demonstrated that anomaly harmonics due to geomagnetically induced currents can cause protection mal trips.

This thesis demonstrates that unsupervised deep learning can serve as an additional tool for compressing time-varying power quality big data into a more interpretable form. Despite the application of an unsupervised method, power quality experts remain significant in power quality studies. The main conclusion of this thesis is that unsupervised deep learning enhances the understanding of power quality experts and provides a complementary approach for analysing and extracting insights from time-varying power quality big data.

sted, utgiver, år, opplag, sider
Luleå: Luleå University of Technology, 2023
Serie
Doctoral thesis / Luleå University of Technology 1 jan 1997 → …, ISSN 1402-1544
Emneord
power quality, power system harmonics, electric power distribution, interharmonics, big data analytics, pattern analysis, unsupervised learning, deep learning, artificial intelligence, geomagnetically induced currents
HSV kategori
Forskningsprogram
Elkraftteknik
Identifikatorer
urn:nbn:se:ltu:diva-100718 (URN)978-91-8048-353-7 (ISBN)978-91-8048-354-4 (ISBN)
Disputas
2023-10-04, Hörsal A, Luleå tekniska universitet, Skellefteå, 09:00 (engelsk)
Opponent
Veileder
Tilgjengelig fra: 2023-08-25 Laget: 2023-08-24 Sist oppdatert: 2023-09-13bibliografisk kontrollert
Oliveira, R. A. & Bollen, M. H. .. (2023). Deep learning for power quality. Electric power systems research, 214, Article ID 108887.
Åpne denne publikasjonen i ny fane eller vindu >>Deep learning for power quality
2023 (engelsk)Inngår i: Electric power systems research, ISSN 0378-7796, E-ISSN 1873-2046, Vol. 214, artikkel-id 108887Artikkel, forskningsoversikt (Fagfellevurdert) Published
Abstract [en]

This paper aims to introduce deep learning to the power quality community by reviewing the latest applications and discussing the open challenges of this technology. Publications covering deep learning to power quality are stratified in terms of application, type of data, and learning technique. This work shows that the majority of the deep learning applications to power quality are based on unrealistic synthetic data and supervised learning without proper labelling. Some applications with deep learning have already been solved by previous machine learning methods or expert systems. The main barriers to implementing deep learning to power quality are related to lack of novelty, low transparency of the deep learning methods, and lack of benchmark databases. This work also discusses that even with automatic feature extraction by deep learning methods, power quality expert knowledge is still needed to implement and analyse the results. The main research gaps identified in this work are related to the applications of semi-supervised learning, explainable deep learning and hybrid approaches combining deep learning with expert systems. Suggestions for overcoming the present limitations are: providing a stronger collaboration among the grid stakeholders and academy to keep track of power quality events; proper labelling and enlarging of datasets in deep learning methods; explaining the end-to-end decision making of deep learning methods; providing open-access databases for comparison purposes.

sted, utgiver, år, opplag, sider
Elsevier, 2023
Emneord
Artificial intelligence, Data analysis, Deep learning, Machine learning, Power quality
HSV kategori
Forskningsprogram
Elkraftteknik
Identifikatorer
urn:nbn:se:ltu:diva-93726 (URN)10.1016/j.epsr.2022.108887 (DOI)001024999300001 ()2-s2.0-85139840780 (Scopus ID)
Forskningsfinansiär
Swedish Energy Agency
Merknad

Validerad;2022;Nivå 2;2022-10-26 (hanlid)

Tilgjengelig fra: 2022-10-26 Laget: 2022-10-26 Sist oppdatert: 2024-03-07bibliografisk kontrollert
A. Oliveira, R., S. Salles, R. & Rönnberg, S. K. (2023). Deep Learning for Power Quality with Special Reference to Unsupervised Learning. In: 27th International Conference on Electricity Distribution (CIRED 2023): . Paper presented at 27th International Conference and Exhibition on Electricity Distribution (CIRED 2023), Rome, Italy, June 12-15, 2023 (pp. 935-939). IEEE, Article ID 10417.
Åpne denne publikasjonen i ny fane eller vindu >>Deep Learning for Power Quality with Special Reference to Unsupervised Learning
2023 (engelsk)Inngår i: 27th International Conference on Electricity Distribution (CIRED 2023), IEEE, 2023, s. 935-939, artikkel-id 10417Konferansepaper, Publicerat paper (Fagfellevurdert)
sted, utgiver, år, opplag, sider
IEEE, 2023
HSV kategori
Forskningsprogram
Elkraftteknik
Identifikatorer
urn:nbn:se:ltu:diva-100717 (URN)10.1049/icp.2023.0593 (DOI)2-s2.0-85181538517 (Scopus ID)
Konferanse
27th International Conference and Exhibition on Electricity Distribution (CIRED 2023), Rome, Italy, June 12-15, 2023
Merknad

ISBN for host publication: 978-1-83953-855-1;

Tilgjengelig fra: 2023-08-24 Laget: 2023-08-24 Sist oppdatert: 2024-03-11bibliografisk kontrollert
de Oliveira, R. A., Nakhodchi, N., De Souza Salles, R. & Rönnberg, S. K. (2023). Deep Learning Graphical Tool Inspired by Correlation Matrix for Reporting Long-Term Power Quality Data at Multiple Locations of an MV/LV Distribution Grid. In: 27th International Conference on Electricity Distribution (CIRED 2023): . Paper presented at 27th International Conference and Exhibition on Electricity Distribution (CIRED 2023), Rome, Italy, June 12-15, 2023 (pp. 609-613). IEEE, Article ID 10324.
Åpne denne publikasjonen i ny fane eller vindu >>Deep Learning Graphical Tool Inspired by Correlation Matrix for Reporting Long-Term Power Quality Data at Multiple Locations of an MV/LV Distribution Grid
2023 (engelsk)Inngår i: 27th International Conference on Electricity Distribution (CIRED 2023), IEEE, 2023, s. 609-613, artikkel-id 10324Konferansepaper, Publicerat paper (Fagfellevurdert)
sted, utgiver, år, opplag, sider
IEEE, 2023
HSV kategori
Forskningsprogram
Elkraftteknik
Identifikatorer
urn:nbn:se:ltu:diva-103655 (URN)10.1049/icp.2023.0433 (DOI)2-s2.0-85181541951 (Scopus ID)
Konferanse
27th International Conference and Exhibition on Electricity Distribution (CIRED 2023), Rome, Italy, June 12-15, 2023
Merknad

ISBN for host publication: 978-1-83953-855-1

Tilgjengelig fra: 2024-01-15 Laget: 2024-01-15 Sist oppdatert: 2024-02-08bibliografisk kontrollert
Malfoy, A., A. Oliveira, R. & Rönnberg, S. K. (2023). Harmonics in the Transmission and Distribution Grid and their Relation to Geomagnetically Induced Currents. In: 27th International Conference on Electricity Distribution (CIRED 2023): . Paper presented at 27th International Conference and Exhibition on Electricity Distribution (CIRED 2023), Rome, Italy, June 12-15, 2023 (pp. 60-64). IEEE, Article ID 00121.
Åpne denne publikasjonen i ny fane eller vindu >>Harmonics in the Transmission and Distribution Grid and their Relation to Geomagnetically Induced Currents
2023 (engelsk)Inngår i: 27th International Conference on Electricity Distribution (CIRED 2023), IEEE, 2023, s. 60-64, artikkel-id 00121Konferansepaper, Publicerat paper (Fagfellevurdert)
sted, utgiver, år, opplag, sider
IEEE, 2023
HSV kategori
Forskningsprogram
Elkraftteknik
Identifikatorer
urn:nbn:se:ltu:diva-103646 (URN)10.1049/icp.2023.0241 (DOI)2-s2.0-85181532521 (Scopus ID)
Konferanse
27th International Conference and Exhibition on Electricity Distribution (CIRED 2023), Rome, Italy, June 12-15, 2023
Merknad

ISBN for host publication: 978-1-83953-855-1; 

Tilgjengelig fra: 2024-01-16 Laget: 2024-01-16 Sist oppdatert: 2024-03-11bibliografisk kontrollert
Bollen, M. & de Oliveira, R. A. (2023). Power Quality. Wiley Encyclopedia of Electrical and Electronics Engineering
Åpne denne publikasjonen i ny fane eller vindu >>Power Quality
2023 (engelsk)Inngår i: Wiley Encyclopedia of Electrical and Electronics EngineeringArtikkel i tidsskrift (Fagfellevurdert) Published
sted, utgiver, år, opplag, sider
John Wiley & Sons, 2023
HSV kategori
Forskningsprogram
Elkraftteknik
Identifikatorer
urn:nbn:se:ltu:diva-104052 (URN)10.1002/047134608x.w8445 (DOI)
Tilgjengelig fra: 2024-02-01 Laget: 2024-02-01 Sist oppdatert: 2024-04-02
Bagheri, A., de Oliveira, R. A., Bollen, M. H. J. & Gu, I. Y. H. (2022). A Framework Based on Machine Learning for Analytics of Voltage Quality Disturbances. Energies, 15(4), Article ID 1283.
Åpne denne publikasjonen i ny fane eller vindu >>A Framework Based on Machine Learning for Analytics of Voltage Quality Disturbances
2022 (engelsk)Inngår i: Energies, E-ISSN 1996-1073, Vol. 15, nr 4, artikkel-id 1283Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

This paper proposes a machine-learning-based framework for voltage quality analytics, where the space phasor model (SPM) of the three-phase voltages before, during, and after the event is applied as input data. The framework proceeds along with three main steps: (a) event extraction, (b) event characterization, and (c) additional information extraction. During the first step, it utilizes a Gaussian-based anomaly detection (GAD) technique to extract the event data from the recording. Principal component analysis (PCA) is adopted during the second step, where it is shown that the principal components correspond to the semi-minor and semi-major axis of the ellipse formed by the SPM. During the third step, these characteristics are interpreted to extract additional information about the underlying cause of the event. The performance of the framework was verified through experiments conducted on datasets containing synthetic and measured power quality events. The results show that the combination of semi-major axis, semi-minor axis, and direction of the major axis forms a sufficient base to characterize, classify, and eventually extract additional information from recorded event data.

sted, utgiver, år, opplag, sider
MDPI, 2022
Emneord
anomaly detection, machine learning, power quality, principal component analysis, space phasor model
HSV kategori
Forskningsprogram
Elkraftteknik
Identifikatorer
urn:nbn:se:ltu:diva-89920 (URN)10.3390/en15041283 (DOI)000778148300001 ()2-s2.0-85126538910 (Scopus ID)
Forskningsfinansiär
Swedish Energy Agency, P39437-1Swedish Energy Agency, P42979-1Swedish Transport Administration, 36267
Merknad

Validerad;2022;Nivå 2;2022-03-28 (hanlid);

Funder: Energiforsk

Tilgjengelig fra: 2022-03-28 Laget: 2022-03-28 Sist oppdatert: 2023-08-28bibliografisk kontrollert
de Oliveira, R. A., De Souza Salles, R., Bollen, M. H. .. & de Carlí, M. P. (2022). Analysing Waveform Distortion in Wind Power Plants by a Deep Learning-Based Graphical Tool. In: 2022 20th International Conference on Harmonics & Quality of Power (ICHQP) Proceedings: “Power Quality in the Energy Transition”. Paper presented at 20th International Conference on Harmonics & Quality of Power (ICHQP 2022), Naples, Italy, May 29 - June 1, 2022. IEEE
Åpne denne publikasjonen i ny fane eller vindu >>Analysing Waveform Distortion in Wind Power Plants by a Deep Learning-Based Graphical Tool
2022 (engelsk)Inngår i: 2022 20th International Conference on Harmonics & Quality of Power (ICHQP) Proceedings: “Power Quality in the Energy Transition”, IEEE, 2022Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

This work shows an application of a deep learning-based graphical tool for analyzing waveform distortion in wind power plants. The tool consists of a deep autoencoder followed by a clustering algorithm. Previous applications of such a tool have covered harmonic emission which follows daily patterns. The challenge of measurements in wind power plants is the intermittence of the power production, which can vary in a time frame of minutes and hours. To this point, this work proposes a modification of a DL method presented in the literature to address measurements from wind power plants. The method can automatically obtain the number of clusters. The method is applied to harmonic measurements from H2 to H50 and active power in a Brazilian wind power plant. The graphical results allowed obtaining the correlation between patterns of odd and even current harmonic with the active power generated by a wind power plant.

sted, utgiver, år, opplag, sider
IEEE, 2022
Serie
International Conference on Harmonics and Quality of Power, ISSN 1540-6008, E-ISSN 2164-0610
Emneord
wind power generation, waveform distortion, deep learning, machine learning, harmonic analysis
HSV kategori
Forskningsprogram
Elkraftteknik
Identifikatorer
urn:nbn:se:ltu:diva-92107 (URN)10.1109/ICHQP53011.2022.9808731 (DOI)000844604500089 ()2-s2.0-85133765019 (Scopus ID)
Konferanse
20th International Conference on Harmonics & Quality of Power (ICHQP 2022), Naples, Italy, May 29 - June 1, 2022
Forskningsfinansiär
Swedish Energy AgencySwedish Transport Administration
Merknad

ISBN för värdpublikation: 978-1-6654-1639-9

Tilgjengelig fra: 2022-07-07 Laget: 2022-07-07 Sist oppdatert: 2022-09-19bibliografisk kontrollert
Organisasjoner
Identifikatorer
ORCID-id: ORCID iD iconorcid.org/0000-0001-5845-5620