Change search
Link to record
Permanent link

Direct link
de Oliveira, Roger AlvesORCID iD iconorcid.org/0000-0001-5845-5620
Alternative names
Publications (10 of 30) Show all publications
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.
Open this publication in new window or tab >>Deep Anomaly Detection of Voltage Waveform Distortion in the Transmission Grid due to Geomagnetically Induced Currents
2024 (English)In: IEEE Transactions on Instrumentation and Measurements, ISSN 0018-9456, Vol. 73, article id 2509212Article in journal (Refereed) Published
Place, publisher, year, edition, pages
IEEE, 2024
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Electric Power Engineering
Identifiers
urn:nbn:se:ltu:diva-100715 (URN)10.1109/TIM.2024.3366271 (DOI)2-s2.0-85185388685 (Scopus ID)
Note

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

Available from: 2023-08-24 Created: 2023-08-24 Last updated: 2024-04-09Bibliographically approved
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
Open this publication in new window or tab >>Harmonic Anomalies Due to Geomagnetically Induced Currents as a Potential Cause of Protection Mal-Trips at the South Atlantic Anomaly Area
Show others...
2024 (English)In: IEEE Transactions on Power Delivery, ISSN 0885-8977, E-ISSN 1937-4208, Vol. 39, no 2, p. 1124-1136Article in journal (Refereed) Published
Place, publisher, year, edition, pages
IEEE, 2024
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Electric Power Engineering
Identifiers
urn:nbn:se:ltu:diva-100716 (URN)10.1109/TPWRD.2024.3353487 (DOI)2-s2.0-85182951668 (Scopus ID)
Note

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.

Available from: 2023-08-24 Created: 2023-08-24 Last updated: 2024-04-03Bibliographically approved
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
Open this publication in new window or tab >>Applications of Unsupervised Deep Learning for Analysing Time-Varying Power Quality Big Data
2023 (English)Doctoral thesis, comprehensive summary (Other academic)
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.

Place, publisher, year, edition, pages
Luleå: Luleå University of Technology, 2023
Series
Doctoral thesis / Luleå University of Technology 1 jan 1997 → …, ISSN 1402-1544
Keywords
power quality, power system harmonics, electric power distribution, interharmonics, big data analytics, pattern analysis, unsupervised learning, deep learning, artificial intelligence, geomagnetically induced currents
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Electric Power Engineering
Identifiers
urn:nbn:se:ltu:diva-100718 (URN)978-91-8048-353-7 (ISBN)978-91-8048-354-4 (ISBN)
Public defence
2023-10-04, Hörsal A, Luleå tekniska universitet, Skellefteå, 09:00 (English)
Opponent
Supervisors
Available from: 2023-08-25 Created: 2023-08-24 Last updated: 2023-09-13Bibliographically approved
Oliveira, R. A. & Bollen, M. H. .. (2023). Deep learning for power quality. Electric power systems research, 214, Article ID 108887.
Open this publication in new window or tab >>Deep learning for power quality
2023 (English)In: Electric power systems research, ISSN 0378-7796, E-ISSN 1873-2046, Vol. 214, article id 108887Article, review/survey (Refereed) 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.

Place, publisher, year, edition, pages
Elsevier, 2023
Keywords
Artificial intelligence, Data analysis, Deep learning, Machine learning, Power quality
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering Computer Sciences
Research subject
Electric Power Engineering
Identifiers
urn:nbn:se:ltu:diva-93726 (URN)10.1016/j.epsr.2022.108887 (DOI)001024999300001 ()2-s2.0-85139840780 (Scopus ID)
Funder
Swedish Energy Agency
Note

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

Available from: 2022-10-26 Created: 2022-10-26 Last updated: 2024-03-07Bibliographically approved
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.
Open this publication in new window or tab >>Deep Learning for Power Quality with Special Reference to Unsupervised Learning
2023 (English)In: 27th International Conference on Electricity Distribution (CIRED 2023), IEEE, 2023, p. 935-939, article id 10417Conference paper, Published paper (Refereed)
Place, publisher, year, edition, pages
IEEE, 2023
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering Computer Sciences
Research subject
Electric Power Engineering
Identifiers
urn:nbn:se:ltu:diva-100717 (URN)10.1049/icp.2023.0593 (DOI)2-s2.0-85181538517 (Scopus ID)
Conference
27th International Conference and Exhibition on Electricity Distribution (CIRED 2023), Rome, Italy, June 12-15, 2023
Note

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

Available from: 2023-08-24 Created: 2023-08-24 Last updated: 2024-03-11Bibliographically approved
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.
Open this publication in new window or tab >>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 (English)In: 27th International Conference on Electricity Distribution (CIRED 2023), IEEE, 2023, p. 609-613, article id 10324Conference paper, Published paper (Refereed)
Place, publisher, year, edition, pages
IEEE, 2023
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Electric Power Engineering
Identifiers
urn:nbn:se:ltu:diva-103655 (URN)10.1049/icp.2023.0433 (DOI)2-s2.0-85181541951 (Scopus ID)
Conference
27th International Conference and Exhibition on Electricity Distribution (CIRED 2023), Rome, Italy, June 12-15, 2023
Note

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

Available from: 2024-01-15 Created: 2024-01-15 Last updated: 2024-02-08Bibliographically approved
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.
Open this publication in new window or tab >>Harmonics in the Transmission and Distribution Grid and their Relation to Geomagnetically Induced Currents
2023 (English)In: 27th International Conference on Electricity Distribution (CIRED 2023), IEEE, 2023, p. 60-64, article id 00121Conference paper, Published paper (Refereed)
Place, publisher, year, edition, pages
IEEE, 2023
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering Astronomy, Astrophysics and Cosmology
Research subject
Electric Power Engineering
Identifiers
urn:nbn:se:ltu:diva-103646 (URN)10.1049/icp.2023.0241 (DOI)2-s2.0-85181532521 (Scopus ID)
Conference
27th International Conference and Exhibition on Electricity Distribution (CIRED 2023), Rome, Italy, June 12-15, 2023
Note

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

Available from: 2024-01-16 Created: 2024-01-16 Last updated: 2024-03-11Bibliographically approved
Bollen, M. & de Oliveira, R. A. (2023). Power Quality. Wiley Encyclopedia of Electrical and Electronics Engineering
Open this publication in new window or tab >>Power Quality
2023 (English)In: Wiley Encyclopedia of Electrical and Electronics EngineeringArticle in journal (Refereed) Published
Place, publisher, year, edition, pages
John Wiley & Sons, 2023
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Electric Power Engineering
Identifiers
urn:nbn:se:ltu:diva-104052 (URN)10.1002/047134608x.w8445 (DOI)
Available from: 2024-02-01 Created: 2024-02-01 Last updated: 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.
Open this publication in new window or tab >>A Framework Based on Machine Learning for Analytics of Voltage Quality Disturbances
2022 (English)In: Energies, E-ISSN 1996-1073, Vol. 15, no 4, article id 1283Article in journal (Refereed) 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.

Place, publisher, year, edition, pages
MDPI, 2022
Keywords
anomaly detection, machine learning, power quality, principal component analysis, space phasor model
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Electric Power Engineering
Identifiers
urn:nbn:se:ltu:diva-89920 (URN)10.3390/en15041283 (DOI)000778148300001 ()2-s2.0-85126538910 (Scopus ID)
Funder
Swedish Energy Agency, P39437-1Swedish Energy Agency, P42979-1Swedish Transport Administration, 36267
Note

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

Funder: Energiforsk

Available from: 2022-03-28 Created: 2022-03-28 Last updated: 2023-08-28Bibliographically approved
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
Open this publication in new window or tab >>Analysing Waveform Distortion in Wind Power Plants by a Deep Learning-Based Graphical Tool
2022 (English)In: 2022 20th International Conference on Harmonics & Quality of Power (ICHQP) Proceedings: “Power Quality in the Energy Transition”, IEEE, 2022Conference paper, Published paper (Refereed)
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.

Place, publisher, year, edition, pages
IEEE, 2022
Series
International Conference on Harmonics and Quality of Power, ISSN 1540-6008, E-ISSN 2164-0610
Keywords
wind power generation, waveform distortion, deep learning, machine learning, harmonic analysis
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Electric Power Engineering
Identifiers
urn:nbn:se:ltu:diva-92107 (URN)10.1109/ICHQP53011.2022.9808731 (DOI)000844604500089 ()2-s2.0-85133765019 (Scopus ID)
Conference
20th International Conference on Harmonics & Quality of Power (ICHQP 2022), Naples, Italy, May 29 - June 1, 2022
Funder
Swedish Energy AgencySwedish Transport Administration
Note

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

Available from: 2022-07-07 Created: 2022-07-07 Last updated: 2022-09-19Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0001-5845-5620

Search in DiVA

Show all publications