Change search
Refine search result
1 - 30 of 30
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • 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
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 1.
    A. Oliveira, Roger
    et al.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    S. Salles, Rafael
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Rönnberg, Sarah K.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Deep Learning for Power Quality with Special Reference to Unsupervised Learning2023In: 27th International Conference on Electricity Distribution (CIRED 2023), IEEE, 2023, p. 935-939, article id 10417Conference paper (Refereed)
  • 2.
    Ahmed, Kazi Main Uddin
    et al.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    de Oliveira, Roger Alves
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Bollen, Math
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Alvarez, Manuel
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Risk Assessment of Server Outages Due To Voltage Dips In the Internal Power Supply System of a Data Center2021In: CIRED 2021 - The 26th International Conference and Exhibition on Electricity Distribution, Institution of Engineering and Technology, 2021, p. 708-712, article id 0090Conference paper (Refereed)
    Abstract [en]

    The data centers host sensitive electronic devices like servers, memory, hard disks, network devices, etc., which are supplied by the power supply units. The regulated direct current (DC) output of the power supply units fluctuates with input voltage variation since they typically contain single phase switch-mode power supplies. The voltage dips caused by faults in the internal power supply system of the data center can be large enough to violate the Information Technology Industry Council (ITIC) proposed voltage-tolerance guideline. The output of the power supplies, hence the operation of the servers will be interrupted due to such voltage dips. In this paper, the outage probability of the servers caused by the voltage dips are analyzed for different fault location in the internal supply system of a data center.

  • 3.
    Alves de Oliveira, Roger
    et al.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Malfoy, Alex
    School of Engineering, Bordeaux Institute of Technology, Bordeaux, France.
    Rönnberg, Sarah K.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Deep Anomaly Detection of Voltage Waveform Distortion in the Transmission Grid due to Geomagnetically Induced Currents2024In: IEEE Transactions on Instrumentation and Measurements, ISSN 0018-9456, Vol. 73, article id 2509212Article in journal (Refereed)
  • 4.
    Bagheri, Azam
    et al.
    AI & Future Technologies, Industrial and Digital Solutions, ÅF Pöyry AB (Afry), 411 19 Gothenburg, Sweden.
    de Oliveira, Roger Alves
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Bollen, Math H. J.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Gu, Irene Y. H.
    Department Electrical Engineering, Chalmers University of Technology, 412 96 Gothenburg, Sweden.
    A Framework Based on Machine Learning for Analytics of Voltage Quality Disturbances2022In: Energies, E-ISSN 1996-1073, Vol. 15, no 4, article id 1283Article in journal (Refereed)
    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.

  • 5.
    Boeira, Rafael
    et al.
    Universidade Federal do Rio Grande do Sul, Porto Alegre, Brazil.
    Ribeiro, Renata
    Universidade Federal do Rio Grande do Sul, Porto Alegre, Brazil.
    Chouhy Leborgne, Roberto
    Universidade Federal do Rio Grande do Sul, Porto Alegre, Brazil.
    de Oliveira, Roger Alves
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Propagation of Voltage Dips in a Mixed DFIG-PMSG Wind Power Plant2021In: 2021 IEEE PES Innovative Smart Grid Technologies Conference - Latin America (ISGT Latin America), IEEE, 2021Conference paper (Refereed)
    Abstract [en]

    This work assesses the propagation of voltage dips caused by electrical faults in a mixed DFIG-PMSG wind power plant by considering distinct collection transformer connections. Several transmission system operators have required the operation of the wind power plants even during voltage dips. The electronic converters might be affected during the voltage dips. Most of the works which assess this impact applied voltage dips directly to wind turbine terminals. However, the voltage dips which reach the wind turbine terminals are distinct in type of the ones from the transmission level. The reason for this distinction is related to the winding connections of the wind turbines and collection grid transformers. The winding connection of the collection grid varies country by country, i.e some countries apply Yg- Yg and other Yg - A. Faced with this, the consideration of the winding connections might possibly lead to distinct operation of the wind turbines during the voltage dip. Besides, the operation during dips also differs depending on the converter technology. This way, this works aims to analyze how the low-voltage ride-through requirements and the behavior of the wind turbines changes in terms of the collection grid transformer for two technologies of wind turbines: PMSG and DFIG.

  • 6.
    Bollen, Math
    et al.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    de Oliveira, Roger Alves
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Power Quality2023In: Wiley Encyclopedia of Electrical and Electronics EngineeringArticle in journal (Refereed)
  • 7.
    Chen, Cheng
    et al.
    Electric Power Engineering group, KTH Royal Institute of Technology, Stockholm, Sweden.
    de Oliveira, Roger Alves
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Bollen, Math H. J.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Bagheri, Azam
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Power Quality Knowledge Application for Low Voltage Ride Through Studies of Wind Turbine Generator2019In: Proceedings of 2019 IEEE PES Innovative Smart Grid Technologies Europe (ISGT-Europe), IEEE, 2019, article id 106Conference paper (Refereed)
    Abstract [en]

    Low voltage ride through (LVRT) of wind turbines is an important grid integration issue and the subject of many studies. However, in many such studies, the voltage dip waveforms used to test the performance of LVRT methods are not the one that can occur at the terminal of a wind turbine in reality. This paper provides a critical review of existing works and summarizes the power quality knowledge needed to study LVRT. Characteristics of voltage dips at the terminals of a wind turbine generator (WTG) will be analyzed based on realistic wind farm topology and transformer winding configuration. The impact of collection system transformer winding configuration on low voltage ride through of DFIG is revealed for the first time. Also, the impact of phase angle jump (PAJ) is shown in simulation. The changes of PAJ and point on wave (POW) characteristics in propagation between point of common connection (PCC) and terminal are analyzed to inspire further works. These issues are important but widely neglected by current works.

  • 8.
    de Oliveira, Roger Alves
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Applications of Unsupervised Deep Learning for Analysing Time-Varying Power Quality Big Data2023Doctoral 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.

    Download full text (pdf)
    fulltext
  • 9.
    de Oliveira, Roger Alves
    et al.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Bollen, Math
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Dynamic Behaviour of Wind Turbines when Submitted to Distinctly Characterized Voltage Dips2021In: CIRED 2021 - The 26th International Conference and Exhibition on Electricity Distribution, 2021, p. 747-751, article id 0184Conference paper (Refereed)
    Abstract [en]

    This work aims to verify the fault-ride-through (FRT) of a wind turbine (WT) by considering two distinct characterization approaches to obtain synthetic dips from a real measurement. One of the approaches considers a detailed characterization to generate the synthetic dip based on the checklist developed by CIGRE working group C4.110. The other approach considers only magnitude and duration as characteristics of the voltage dip. Such comparison is needed because many FRT studies do not considering the power quality knowledge on voltage dips. The measurement of the voltage dip was obtained in a Swedish wind park. The analysis was conducted for the double-fed-induction-generator (DFIG). The results show that simplified dips can overestimate or underestimate the FRT tests. Also, that even with detailed characterization, some deviation occurs in the FRT tests, pointing out the need for continuous work on this topic.

  • 10.
    de Oliveira, Roger Alves
    et al.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Bollen, Math
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Magnification of Transients at the Voltage Dips Starting and its Impacts on DFIG-based Wind Power Plants2022In: Electric power systems research, ISSN 0378-7796, E-ISSN 1873-2046, Vol. 211, article id 108244Article in journal (Refereed)
    Abstract [en]

    This work shows that transients at voltage dips starting impact fault-ride-through of wind turbines. For fault-ride-through studies and manufacturer tests, it is therefore important to consider these transients and their magnification from the transmission grid through the collection grid to the wind turbines. Fault-ride-through studies in the literature do not consider the transient as a dip characteristic and employ overly-simplified models that do not consider the collection grid. This work studies in detail how the dip-starting transient changes during the propagation from the transmission grid to the wind-turbine terminals. It is also studied how this transient impacts the dynamic behaviour of the wind turbines in terms of the overvoltage on the DC-link of wind turbines based on doubly-fed induction generator (DFIG). The analyses are performed for several realistic configurations of a wind-power plant, all based on an existing installation. The results show that the magnitude of the transient is magnified when the resonant frequency of the collection grid is similar to the oscillation frequency of the transient. Moreover, the higher magnitude of the transient results in a significantly higher overvoltage on the DC-link. This work is the first in power quality literature to cover the collection and internal grid as a factor for the magnification of dip-staring transient. The main finding of this work is that the detailed models of the collection grid and the transients at the voltage dips starting must be not neglected when accessing the LVRT of wind turbines. It is strongly recommended to consider the details of the dip-starting transients and of the collection grid to assess the impact of dips on the wind turbines properly.

  • 11.
    de Oliveira, Roger Alves
    et al.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Bollen, Math
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Cheng, Chen
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Leborgne, Roberto
    Universidade Federal do Rio Grande do Sul.
    Evaluation of the DFIG-based Wind Turbine Subjected to Transformer-energizing Voltage Dips2019Conference paper (Other academic)
    Abstract [en]

    This work evaluates the response of DFIG-based wind turbine under voltage dips caused by transformer energizing. The transformer energizing is part of the normal operation of the power system and it can cause even-harmonic distortion, which could impact the operation of the power converters on the wind turbine. Previous works only considered voltage dips caused by electrical faults, then other causes should be understood to guarantee sufficient fault-right through of wind power installations. In order to address this study, voltage dips measurements with distinct magnitude, harmonic distortion and voltage unbalance are applied to a DFIG model. The impacts on the rotor current, on the DC-link voltage, and on the DFIG active power are analyzed. 

  • 12.
    de Oliveira, Roger Alves
    et al.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Bollen, Math H. J.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Impact of Voltage Dips Originated in the Transmission Grid on EV Charging Stations2022In: 2022 20th International Conference on Harmonics & Quality of Power (ICHQP) Proceedings: “Power Quality in the Energy Transition”, IEEE, 2022Conference paper (Refereed)
    Abstract [en]

    This work aims to verify the impact of voltage dips propagated from the transmission grid on EV charging stations. Previous works in this topic have applied voltage dips directly to the terminals of the EV chargers, i.e. neglecting the transfer between the source of the dip and the EV chargers stations. Moreover, some works limited their analysis by considering only the magnitude and duration of voltage dips. This work aims to verify if the impact of dips on EV charging stations is distinct when considering the propagation and detailed characteristics of the dips. This work shows that the non-consideration of the propagation and detailed characteristics of the voltage dips might underestimate the impact on the EV charging station.

  • 13.
    de Oliveira, Roger Alves
    et al.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Bollen, Math H. J.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Susceptibility of Large Wind Power Plants to Voltage Disturbances – Recommendations to Stakeholders2022In: Journal of Modern Power Systems and Clean Energy, ISSN 2196-5625, E-ISSN 2196-5420, Vol. 10, no 2, p. 416-429Article in journal (Refereed)
    Abstract [en]

    Sufficient fault-ride-through (FRT) of large wind power plants (WPPs) is essential for ensuring transmission-grid operational security. The majority of FRT studies do not include all disturbances originated in the transmission grid or include disturbances not relevant for operational security. Using knowledge of power quality, this paper provides a guide to stakeholders in different aspects of FRT for wind turbines (WTs) and wind power plants. This work details the characteristics of the most common disturbances originated in the transmission grid, how they propagate to the wind turbines terminals, and how they impact the dynamic behavior of a large WPP. This work shows that the details of the voltage disturbances at the WT terminals should be considered and not just the voltage disturbance in the transmission grid. Moreover, detailed representation or characterization of voltage dips is important in FRT studies. The simplified models used in the literature are insufficient. This paper strongly recommends that distinct events and additional characteristics as the phase-angle jump and oscillations in the transition segments are considered in FRT analysis.

  • 14.
    de Oliveira, Roger Alves
    et al.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Cheng, Chen
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Bollen, Math H.J.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Chouhy Leborgne, Roberto
    Universidade Federal do Rio Grande do Sul, Porto Alegre, Brazil .
    Comparative Analysis of Transformer-Energizing and Fault-Caused Voltage Dips on the Dynamic Behavior of DFIG-Based Wind Turbines2020In: Proceedings of 2020 IEEE PES Innovative Smart Grid Technologies Europe (ISGT-Europe) 26-28 October, 2020, IEEE, 2020, p. 589-593Conference paper (Refereed)
    Abstract [en]

    This work compares the response of DFIG-based wind turbines under voltage dips caused by transformer-energizing and caused by an asymmetrical fault. Voltage dips with similar retained voltage and duration and the two distinct causes are applied to an equivalent model of a DFIG-based wind park. The dips are different in terms of harmonic content and unbalance during the recovery after the dip. Due to its slow recovery, the transformer-energizing dip results in longer fluctuation in torque, longer overshoot in DC-link voltage, and longer recovery to the pre-dip active power. Also, due to its harmonic content, the harmonic distortion in the rotor and stator current is higher for the transformer-energizing dip. As the impact is different between the transformer-energizing dip and the fault-caused dip, it is recommended to consider both events separately during low-voltage-ride-through studies.

  • 15.
    de Oliveira, Roger Alves
    et al.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Cheng, Chen
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Bollen, Math H.J.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Chouhy Leborgne, Roberto
    Universidade Federal do Rio Grande do Sul, Porto Alegre, Brazil.
    Short-Term Distortion and Protection Operation in DFIG-Based Wind Parks during Voltage Dips2020In: Proceedings of 2020 IEEE PES Innovative Smart Grid Technologies Europe (ISGT-Europe) 26-28 October, 2020, IEEE, 2020, p. 819-823Conference paper (Refereed)
    Abstract [en]

    Due to the increasing penetration of wind power, grid codes require that the wind farms remain connected to the grid during voltage dips. The harmonic distortion might change during the short-term reduction in the voltage magnitude. Although the distortion only occurs during the short period of the voltage dip, high levels of harmonic might cause mal-operation of the protective devices in a wind power plant. The main negative influence that harmonics can have on wind power plant protection is that it can act unnecessarily. This work analysis the changes in the harmonic content in the voltages and currents during dips in a DFIG-based wind power plant. The results showed that the total harmonic distortion for the voltages in the collector system and at the terminals of the wind turbines increases during asymmetrical dips. The currents were affected for both symmetrical and asymmetrical dips. The third and seventh harmonics were the voltage components that most increased. For the currents, the increase was in the third harmonic and interharmonics.

  • 16.
    de Oliveira, Roger Alves
    et al.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    De Souza Salles, Rafael
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Bollen, Math H.J.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    de Carlí, Miguel P.
    CGT Eletrosul Brazil.
    Analysing Waveform Distortion in Wind Power Plants by a Deep Learning-Based Graphical Tool2022In: 2022 20th International Conference on Harmonics & Quality of Power (ICHQP) Proceedings: “Power Quality in the Energy Transition”, IEEE, 2022Conference 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.

  • 17.
    de Oliveira, Roger Alves
    et al.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Ge, Chenjie
    Chalmers University of Technology, Gothenburg, Sweden.
    Gu, Irene Y.H.
    Chalmers University of Technology, Gothenburg, Sweden.
    Bollen, Math
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Visualizing The Results From Unsupervised Deep Learning For The Analysis Of Power-Quality Data2021In: Cired 2021 - The 26Th International Conference And Exhibition On Electricity Distribution, 2021, p. 653-657, article id 0030Conference paper (Refereed)
    Abstract [en]

    This paper presents a visualisation method, based on deep learning, to assist power engineers in the analysis of large amounts of power-quality data. The method assists in extracting and understanding daily, weekly and seasonal variations in harmonic voltage. Measurements from 10 kV and 0.4 kV in a Swedish distribution network are applied to the deep learning method to obtain daily harmonic patterns and their distribution over the week and the year. The results are presented in graphs that allow interpretation of the results without having to understand the mathematical details of the method. The inferences given by the results demonstrate that the method can become a new tool that compresses power quality big data in a form that is easier to interpret.

  • 18.
    de Oliveira, Roger Alves
    et al.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Nakhodchi, Naser
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    De Souza Salles, Rafael
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Rönnberg, Sarah K.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Deep Learning Graphical Tool Inspired by Correlation Matrix for Reporting Long-Term Power Quality Data at Multiple Locations of an MV/LV Distribution Grid2023In: 27th International Conference on Electricity Distribution (CIRED 2023), IEEE, 2023, p. 609-613, article id 10324Conference paper (Refereed)
  • 19.
    de Oliveira, Roger Alves
    et al.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Ravindran, Vineetha
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Rönnberg, Sarah
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Bollen, Math
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Deep Learning For Pattern Recognition Of Interharmonics In Time-Series And Spectrograms2021In: CIRED 2021 - The 26th International Conference and Exhibition on Electricity Distribution, 2021, p. 738-741Conference paper (Refereed)
    Abstract [en]

    This work applies an unsupervised deep feature learning to finding patterns of interharmonics. The main objectives of this work are to provide an additional graphical tool to handle two distinct data inputs: (a) individual interharmonics components in time-series; (b) broadband spectrum by employing spectrograms. Both data inputs are analysed employing an autoencoder based on convolutional neural networks followed by clustering. The application of the method results in the most common patterns in time-series or spectrograms. Two study cases are presented by applying the method to measurements from solar installations in Finland and Sweden. The results show the usefulness of the method to recognize interharmonics in a single frequency and broadband spectrum.

  • 20.
    de Oliveira, Roger Alves
    et al.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Ravindran, Vineetha
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Rönnberg, Sarah K.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Bollen, Math H.J.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Deep Learning Method With Manual Post-Processing for Identification of Spectral Patterns of Waveform Distortion in PV Installations2021In: IEEE Transactions on Smart Grid, ISSN 1949-3053, E-ISSN 1949-3061, Vol. 12, no 6, p. 5444-5456Article in journal (Refereed)
    Abstract [en]

    This paper proposes a deep learning (DL) method for the identification of spectral patterns of timevarying waveform distortion in photovoltaic (PV) installations. The PQ big data with information on harmonic and/or interharmonics in PV installations is handled by a deep autoencoder followed by feature clustering. Measurements of voltage and current from four distinct PV installations are used to illustrate the method. This paper shows that the DL method can be used as a starting point for further data analysis. The main contributions of the paper include: (a) providing a novel DL method for finding patterns in spectra; (b) guiding the manual post-processing based on the patterns found by the DL method; and (c) obtaining information about the emission from four PV installations.

  • 21.
    de Oliveira, Roger Alves
    et al.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Rönnberg, Sarah K.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Bollen, Math H. J.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Third Harmonic and its Relation to Solar Elevation Angle in a PV Installation with Solar Tracking Systems2022In: 2022 20th International Conference on Harmonics & Quality of Power (ICHQP) Proceedings: “Power Quality in the Energy Transition”, IEEE, 2022Conference paper (Refereed)
    Abstract [en]

    This paper shows an application of a deep learning method to a solar installation with a solar tracking system. The method consists of a deep autoencoder followed by clustering. The deep learning method allows defining the most dominant component in harmonic spectra during long-term measurements. Power Quality measurements were accessed over two years in 3ϕ PV installation of 6 kVA with 2-axis tracking in northern Sweden. The deep learning results indicate that the third harmonic of current is the component that changes most over the two years. This paper demonstrates that there is a correlation between the daily and seasonal variations of the third harmonic with the solar elevation angle at the location. The main conclusion for this cause was associated with the operation of the solar tracking systems which are based on single-phase motors. The paper also discusses the possibility of correlation of the third harmonic with cloud coverage, snow on the panels, and reactive power unbalance.

  • 22.
    de Oliveira, Roger Alves
    et al.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Salles, Rafael S.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Rönnberg, Sarah
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    de Carli, Miguel P.
    Eletrobras at the Generation Departmen in Florianópolis, Brazil.
    Leborgne, Roberto Chouhy
    Universidade Federal do Rio Grande do Sul, Porto Alegre, Brazil.
    Harmonic Anomalies Due to Geomagnetically Induced Currents as a Potential Cause of Protection Mal-Trips at the South Atlantic Anomaly Area2024In: IEEE Transactions on Power Delivery, ISSN 0885-8977, E-ISSN 1937-4208, Vol. 39, no 2, p. 1124-1136Article in journal (Refereed)
  • 23.
    Espin Delgado, Angela
    et al.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Sutaria, Jil
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    de Oliveira, Roger Alves
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Rönnberg, Sarah
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Application of Clustering and Dimensionality Reduction Methods for Finding Patterns on Supraharmonics Data2022In: 2022 20th International Conference on Harmonics & Quality of Power (ICHQP) Proceedings: “Power Quality in the Energy Transition”, IEEE, 2022Conference paper (Refereed)
    Abstract [en]

    Supraharmonics (waveform distortion between 2 and 150 kHz) proliferate in electrical installations due to the increasing use of power electronics converters and power-line communication. Due to the wide range that the supraharmonics cover and the high frequency resolution needed to measure them, a considerable amount of data is acquired. The analysis is usually done manually by experts. More efficient methods for data mapping and analysis are needed. Machine learning methods are explored in this paper for the analysis of supraharmonics data.

  • 24.
    Ge, Chenjie
    et al.
    Department of Electrical Engineering, Chalmers University of Technology, 412 96 Gothenburg, Sweden.
    de Oliveira, Roger Alves
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Gu, Irene Y-Hua
    Department of Electrical Engineering, Chalmers University of Technology, 412 96 Gothenburg, Sweden.
    Bollen, Math H. J.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Deep Feature Clustering for Seeking Patterns in Daily Harmonic Variations2021In: IEEE Transactions on Instrumentation and Measurement, ISSN 0018-9456, E-ISSN 1557-9662, Vol. 70, article id 2501110Article in journal (Refereed)
    Abstract [en]

    This article proposes a novel scheme for analyzing power system measurement data. The main question that we seek answers in this study is on “whether one can find some important patterns that are hidden in the large data of power system measurements such as variational data.” The proposed scheme uses an unsupervised deep feature learning approach by first employing a deep autoencoder (DAE) followed by feature clustering. An analysis is performed by examining the patterns of clusters and reconstructing the representative data sequence for the clustering centers. The scheme is illustrated by applying it to the daily variations of harmonic voltage distortion in a low-voltage network. The main contributions of the article include: 1) providing a new unsupervised deep feature learning approach for seeking possible underlying patterns of power system variation measurements and 2) proposing an effective empirical analysis approach for understanding the measurements through examining the underlying feature clusters and the associated reconstructed data by DAE.

  • 25.
    Ge, Chenjie
    et al.
    Department of Electrical Eng, Chalmers University of Technology, 412 96 Göteborg, Sweden.
    Oliveira, Roger A.D.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Gu, Irene Y.H.
    Department of Electrical Eng, Chalmers University of Technology, 412 96 Göteborg, Sweden.
    Bollen, Math H.J.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Unsupervised deep learning and analysis of harmonic variation patterns using big data from multiple locations2021In: Electric power systems research, ISSN 0378-7796, E-ISSN 1873-2046, Vol. 194, article id 107042Article in journal (Refereed)
    Abstract [en]

    This paper addresses the issue of automatically seeking and identifying daily, weekly and seasonal patterns in harmonic voltage from measurement data at multiple locations. We propose a novel framework that employs deep autoencoder (DAE) followed by k-mean clustering. The DAE is used for extracting principal features from time series of harmonic voltages. A new strategy is used for training the encoder in DAE from data at one selected location that is effective for subsequent feature extraction from data at multiple locations. To analyze the patterns, several empirical analysis approaches are applied on the clustered principal features, including the distribution of daily patterns over the week and the year, representative waveform sequences of individual classes, and feature maps for visualizing high-dimensional feature space through low-dimensional embedding. The proposed scheme has been tested on a dataset containing harmonic measurements at 10 low-voltage locations in Sweden for the whole year of 2017. Results show distinct principal patterns for most harmonics that can be related to the use of equipment causing harmonic distortion. This information can assist network operators in finding the origin of harmonic distortion and deciding about mitigation actions. The proposed scheme is the first to provide a useful analysis tool and insight for finding and analyzing underlying patterns from harmonic variation data at multiple locations.

  • 26.
    Malfoy, Alexandre
    et al.
    Bordeaux Institute of Technology, France.
    A. Oliveira, Roger
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Rönnberg, Sarah K.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Harmonics in the Transmission and Distribution Grid and their Relation to Geomagnetically Induced Currents2023In: 27th International Conference on Electricity Distribution (CIRED 2023), IEEE, 2023, p. 60-64, article id 00121Conference paper (Refereed)
  • 27.
    Nakhodchi, Naser
    et al.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    de Oliveira, Roger Alves
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Bollen, Math
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Graphical Methods For Presenting Time-Varying Harmonics2021In: CIRED 2021 - The 26th International Conference and Exhibition on Electricity Distribution, 2021, p. 678-682, article id 0071Conference paper (Refereed)
    Abstract [en]

    Several tools are available for reducing large quantities of data in order to obtain indices and reporting formats, like IEC 61000-4-30 and the recommendations by CIGRE C4.112. But those methods often suffer from a surplus of information or a lack of information. In this context, this paper introduces a number of alternative graphical methods and visualization techniques and illustrates those using real measurements. The main objective of this work is to show the most appropriate tools to present the variations of harmonics at time-scales from a few cycles through a few years.

  • 28.
    Oliveira, Roger Alves de
    et al.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Bollen, Math H.J.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Deep learning for power quality2023In: Electric power systems research, ISSN 0378-7796, E-ISSN 1873-2046, Vol. 214, article id 108887Article, review/survey (Refereed)
    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.

  • 29.
    Ribeiro, Renata
    et al.
    Universidade Federal do Rio Grande do Sul, Porto Alegre, Brazil.
    Boeira, Rafael
    Universidade Federal do Rio Grande do Sul, Porto Alegre, Brazil.
    Chouhy Leborgne, Roberto
    Universidade Federal do Rio Grande do Sul, Porto Alegre, Brazil.
    de Oliveira, Roger Alves
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Bollen, Math H.J.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Assessment of LVRT Requirements and Dynamic Behavior of a Mixed PMSG/DFIG Wind Power Plant2021In: 2020 IEEE PES Transmission & Distribution Conference and Exhibition - Latin America (T&D LA), IEEE, 2021, p. 737-742Conference paper (Refereed)
    Abstract [en]

    This work assesses the low voltage ride-through requirements and the dynamic behavior of a mixed PMSG/ DFIG wind power plant. Previous works in the literature applied voltage dips seen at the Point of Common Coupling (PCC) of the wind power plant (WPP) directly, which means that the propagation from the transmission grid to the low-voltage level was not considered. This work aims to show the expected operation of a wind power plant when submitted to voltage dips caused by faults at the transmission level, i.e considering the propagation. Equivalent models of a transmission system and a wind power plant were used to generate five types of dips and to access the behavior of the WPP during these events. The results show the expected ranges during the voltage dips for the active power of the generators as well as for overvoltages and overcurrents of the converters.

  • 30.
    Salles, Rafael S.
    et al.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    de Oliveira, Roger Alves
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Rönnberg, Sarah K.
    Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.
    Mariscotti, Andrea
    Department of Electrical, Electronics and Telecommunication Engineering and Naval Architecture (DITEN), University of Genoa, 16145 Genoa, Italy.
    Analytics of Waveform Distortion Variations in Railway Pantograph Measurements by Deep Learning2022In: IEEE Transactions on Instrumentation and Measurement, ISSN 0018-9456, E-ISSN 1557-9662, Vol. 71, article id 2516211Article in journal (Refereed)
    Abstract [en]

    Waveform distortion in general represent a widespread problem in electrified transports due to interference, service disruption, increased losses and ageing of components. Given the multitude of moving sources and the extremely variable operating conditions, short time records must be considered for analysis, and this increases in turn its complexity, from which the need for effective automated processing, as offered by a deep learning (DL) approach. This paper proposes an application of unsupervised DL to measurements of railway pantograph quantities to identify waveform distortion patterns. Data consists of pantograph current from a Swiss 15 kV 16.7 Hz railway system. Three DL input types are considered: waveforms, harmonic spectra, and supraharmonic spectra. The applied DL method applied is the deep autoencoder (DAE) followed by feature clustering, using techniques to define a suitable number of clusters. Short-term distortion is evaluated over sub-10 min intervals of harmonic and supraharmonic spectra down to sub-second intervals. Results are explained among others by connecting the distribution of the clusters (determined by self-supervised method) to the dynamic operating conditions of the rolling stock. Resulting DAE performance are superior in terms of accuracy and comprehensiveness of spectral components compared to a more traditional principal component analysis (PCA) that was chosen as reference for comparison.

1 - 30 of 30
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • 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