Change search
Link to record
Permanent link

Direct link
Publications (10 of 15) Show all publications
Bagheri, A., Gu, I. Y. .. & Bollen, M. (2019). Generative Adversarial Model-Guided Deep Active Learning for Voltage Dip Labelling. In: 2019 IEEE Milan PowerTech: . Paper presented at 13th IEEE PowerTech, Milano, Italy, June 23-27, 2019. IEEE
Open this publication in new window or tab >>Generative Adversarial Model-Guided Deep Active Learning for Voltage Dip Labelling
2019 (English)In: 2019 IEEE Milan PowerTech, IEEE, 2019Conference paper, Published paper (Refereed)
Abstract [en]

In many real applications, the ground truths of class labels from voltage dip sequences used for training a voltage dip classification system are unknown, and require manual labelling by human experts. This paper proposes a novel deep active learning method for automatic labelling of voltage dip sequences used for the training process. We propose a novel deep active learning method, guided by a generative adversarial network (GAN), where the generator is formed by modelling data with a Gaussian mixture model and provides the estimated probability distribution function (pdf) where the query criterion of the deep active learning method is built upon. Furthermore, the discriminator is formed by a support vector machine (SVM). The proposed method has been tested on a voltage dip dataset (containing 916 dips) measured in a European country. The experiments have resulted in good performance (classification rate 83% and false alarm 3.2%), which have demonstrated the effectiveness of the proposed method.

Place, publisher, year, edition, pages
IEEE, 2019
Keywords
Automatic Labelling, Deep Active Learning, Deep Learning, Generative-Discriminative Model, Semi-supervised Training, Voltage Dip
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Electric Power Engineering
Identifiers
urn:nbn:se:ltu:diva-76910 (URN)10.1109/PTC.2019.8810499 (DOI)000531166200097 ()2-s2.0-85072337776 (Scopus ID)
Conference
13th IEEE PowerTech, Milano, Italy, June 23-27, 2019
Funder
Swedish Energy Agency
Note

ISBN för värdpublikation: 978-1-5386-4722-6

Available from: 2019-11-28 Created: 2019-11-28 Last updated: 2021-05-12Bibliographically approved
Chen, C., de Oliveira, R. A., Bollen, M. H. J. & Bagheri, A. (2019). Power Quality Knowledge Application for Low Voltage Ride Through Studies of Wind Turbine Generator. In: Proceedings of 2019 IEEE PES Innovative Smart Grid Technologies Europe (ISGT-Europe): . Paper presented at IEEE PES Innovative Smart Grid Technologies Europe (ISGT-Europe 2019), Bucharest, Romania, September 29-October 2, 2019. IEEE, Article ID 106.
Open this publication in new window or tab >>Power Quality Knowledge Application for Low Voltage Ride Through Studies of Wind Turbine Generator
2019 (English)In: Proceedings of 2019 IEEE PES Innovative Smart Grid Technologies Europe (ISGT-Europe), IEEE, 2019, article id 106Conference paper, Published 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.

Place, publisher, year, edition, pages
IEEE, 2019
Keywords
DFIG, power quality, transformer configuration, voltage dip, wind power
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Electric Power Engineering
Identifiers
urn:nbn:se:ltu:diva-83461 (URN)10.1109/ISGTEurope.2019.8905668 (DOI)000550100400211 ()2-s2.0-85075886489 (Scopus ID)
Conference
IEEE PES Innovative Smart Grid Technologies Europe (ISGT-Europe 2019), Bucharest, Romania, September 29-October 2, 2019
Note

ISBN för värdpublikation: 978-1-5386-8218-0

Available from: 2021-03-30 Created: 2021-03-30 Last updated: 2024-03-07Bibliographically approved
Chen, C., Bagheri, A., Bollen, M. & Bongiorno, M. (2019). The impact of voltage dips to low-voltage-ride-through capacity of doubly fed induction generator based wind turbine. In: 2019 IEEE Milan PowerTech: . Paper presented at 13th IEEE PowerTech, Milano, Italy, June 23-27, 2019. IEEE
Open this publication in new window or tab >>The impact of voltage dips to low-voltage-ride-through capacity of doubly fed induction generator based wind turbine
2019 (English)In: 2019 IEEE Milan PowerTech, IEEE, 2019Conference paper, Published paper (Refereed)
Abstract [en]

Double fed induction generators (DFIG) for wind turbines are very sensitive to grid disturbances especially voltage dips. Understanding and improving fault-ride-through (FRT) capacity of wind turbine generators (WTG) demands accurate assessment of the impact of voltage dips. In many FRT requirements, only voltage dip magnitude and duration are considered. However, additional characteristics point-on-wave (POW) and phase-angle-jump (PAJ) have great impact on DFIG. This paper aims to study the behavior of DFIG-based WTGs during various types of voltage dips. PAJ and POW are specifically taken into consideration; intensive simulation tests show that their impact is significant and should be included in FRT studies. Theoretical analysis are also provided to explain the mechanism behind the observed phenomena. And conclusions of paper could be used to provide useful information for FRT related works and other applications.

Place, publisher, year, edition, pages
IEEE, 2019
Keywords
fault-ride-through, voltage dip, point-on-wave, phase-angle-jump, wind power
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Electric Power Engineering
Identifiers
urn:nbn:se:ltu:diva-76907 (URN)10.1109/PTC.2019.8810749 (DOI)000531166202005 ()2-s2.0-85072323606 (Scopus ID)
Conference
13th IEEE PowerTech, Milano, Italy, June 23-27, 2019
Funder
Swedish Energy Agency
Note

ISBN för värdpublikation: 978-1-5386-4722-6

Available from: 2019-11-28 Created: 2019-11-28 Last updated: 2021-05-12Bibliographically approved
Bagheri, A. & Bollen, M. H. . (2019). The Novel Method for Voltage Transient Detection and Characterization. In: 2019 IEEE Milan PowerTech: . Paper presented at 13th IEEE PowerTech, Milano, Italy, June 23-27, 2019. IEEE
Open this publication in new window or tab >>The Novel Method for Voltage Transient Detection and Characterization
2019 (English)In: 2019 IEEE Milan PowerTech, IEEE, 2019Conference paper, Published paper (Refereed)
Abstract [en]

This paper proposes a novel method for voltage transient detection and characterization using space phasor model (SPM) of the three phase-to-neutral voltages as basis. A Gaussian model based anomaly detection technique is used to extract transient samples as anomalous samples. The proposed method introduces and calculates a set of 'single-transient characteristics'(STC) for voltage transient events. This facilitates quantification of transients, leads to additional information about transient origin, and enables comparing different transients. The proposed method is not sensitive to shallow harmonic distortion particularly in deal with oscillating transients.

A number of transients measured at distribution or transmission level have been applied to the proposed method. The simulation results support the effectiveness of the SPM for voltage transient analytics.

Place, publisher, year, edition, pages
IEEE, 2019
Keywords
Anomaly Detection, Gaussian Distribution, Power Quality Analytics, Space Phasor Model, Voltage transient
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Electric Power Engineering
Identifiers
urn:nbn:se:ltu:diva-76911 (URN)10.1109/PTC.2019.8810748 (DOI)000531166202004 ()2-s2.0-85072327526 (Scopus ID)
Conference
13th IEEE PowerTech, Milano, Italy, June 23-27, 2019
Funder
Swedish Energy Agency
Note

ISBN för värdpublikation: 978-1-5386-4722-6

Available from: 2019-11-28 Created: 2019-11-28 Last updated: 2021-05-12Bibliographically approved
Balouji, E., Gu, I. Y. .., Bollen, M., Bagheri, A. & Nazari, M. (2018). A LSTM-based deep learning method with application to voltage dip classification. In: Proceedings of International Conference on Harmonics and Quality of Power, ICHQP: . Paper presented at 18th International Conference on Harmonics and Quality of Power (ICHQP), Ljubljana, Slovenia, 13-16 May 2018. Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE)
Open this publication in new window or tab >>A LSTM-based deep learning method with application to voltage dip classification
Show others...
2018 (English)In: Proceedings of International Conference on Harmonics and Quality of Power, ICHQP, Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE), 2018Conference paper, Published paper (Refereed)
Abstract [en]

In this paper, a deep learning (DL)-based method for automatic feature extraction and classification of voltage dips is proposed. The method consists of a dedicated architecture of Long Short-Term Memory (LSTM), which is a special type of Recurrent Neural Networks (RNNs). A total of 5982 three-phase one-cycle voltage dip RMS sequences, measured from several countries, has been used in our experiments. Our results have shown that the proposed method is able to classify the voltage dips from learned features in LSTM, with 93.40% classification accuracy on the test data set. The developed architecture is shown to be novel for feature learning and classification of voltage dips. Different from the conventional machine learning methods, the proposed method is able to learn dip features without requiring transition-event segmentation, selecting thresholds, and using expert rules or human expert knowledge, when a large amount of measurement data is available. This opens a new possibility of exploiting deep learning technology for power quality data analytics and classification.

Place, publisher, year, edition, pages
Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE), 2018
Series
International Conference on Harmonics and Quality of Power, E-ISSN 1540-6008
Keywords
Artificial intelligence, deep learning, LSTM, RNN, power quality, smart grid, voltage dips
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Electric Power Engineering
Identifiers
urn:nbn:se:ltu:diva-69511 (URN)10.1109/ICHQP.2018.8378893 (DOI)000444771900082 ()2-s2.0-85049260061 (Scopus ID)978-1-5386-0517-2 (ISBN)
Conference
18th International Conference on Harmonics and Quality of Power (ICHQP), Ljubljana, Slovenia, 13-16 May 2018
Available from: 2018-06-14 Created: 2018-06-14 Last updated: 2021-03-22Bibliographically approved
Bagheri, A., Gu, I. Y. .., Bollen, M. & Balouji, E. (2018). A Robust Transform-Domain Deep Convolutional Network for Voltage Dip Classification. IEEE Transactions on Power Delivery, 33(6), 2794-2802
Open this publication in new window or tab >>A Robust Transform-Domain Deep Convolutional Network for Voltage Dip Classification
2018 (English)In: IEEE Transactions on Power Delivery, ISSN 0885-8977, E-ISSN 1937-4208, Vol. 33, no 6, p. 2794-2802Article in journal (Refereed) Published
Abstract [en]

This paper proposes a novel method for voltage dip classification using deep convolutional neural networks. The main contributions of this paper include: (a) to propose a new effective deep convolutional neural network architecture for automatically learning voltage dip features, rather than extracting hand-crafted features; (b) to employ the deep learning in an effective two-dimensional transform domain, under space-phasor model (SPM), for efficient learning of dip features; (c) to characterize voltage dips by two-dimensional SPM-based deep learning, which leads to voltage dip features independent of the duration and sampling frequency of dip recordings; (d) to develop robust automatically-extracted features that are insensitive to training and test datasets measured from different countries/regions.

Experiments were conducted on datasets containing about 6000 measured voltage dips spread over seven classes measured from several different countries. Results have shown good performance of the proposed method: average classification rate is about 97% and false alarm rate is about 0.50%. The test results from the proposed method are compared with the results from two existing dip classification methods. The proposed method is shown to out-perform these existing methods.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2018
Keywords
Power quality, Voltage dip, Machine learning, Deep learning, Convolutional Neural Network
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Electric Power Engineering
Identifiers
urn:nbn:se:ltu:diva-70217 (URN)10.1109/TPWRD.2018.2854677 (DOI)000451230500023 ()2-s2.0-85049802440 (Scopus ID)
Note

Validerad;2018;Nivå 2;2018-12-05 (inah)

Available from: 2018-08-06 Created: 2018-08-06 Last updated: 2023-01-20Bibliographically approved
Bagheri, A. (2018). Artificial Intelligence-Based Characterization and Classification Methods for Power Quality Data Analytics. (Doctoral dissertation). Luleå: Luleå University of Technology
Open this publication in new window or tab >>Artificial Intelligence-Based Characterization and Classification Methods for Power Quality Data Analytics
2018 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

One of the important developments in the electric power system is the fast increasing amount of data. An example of such data is formed by the voltages and currents coming from power-quality measurements. Power quality disturbances like voltage dips, harmonics and voltage transient can have a serious negative impact on the performance of equipment exposed to such disturbances. Voltage dips, short duration reductions in voltage magnitude, are especially considered as important disturbances because they regularly lead to stoppages in industrial process installations and subsequently to high costs.

The overall aim of this dissertation is the development of automatic analysis methods and other methods for extracting information from large amounts of power-quality data. This includes, methods to detect and extract event characteristics from recorded data and classify the events, for instance, based on their origins or their impact on equipment. The classification facilitates further analysis steps including reasoning and interpretation. Once the data corresponding to each class is available, a proper characterization method can be used to create more semantic data useful for information extraction. The resulting information can be used to improve the performance of the whole system, e.g., updating grid-codes, or immunity requirements of sensitive installations or processes.

This dissertation proposes different methods to fulfil each one of the above-mentioned steps. It proposes particularly a space-phasor model (SPM) of the three phase-to-neutral voltages as basis for analytic methods. The SPM is especially suitable as it is a time-domain transform without loss of any information. Another important contribution of the work is that most of the developed methods have been applied to a large dataset of about 6000 real-world voltage dips measured in existing HV and MV power networks.

The main contributions of this dissertation are as follows:

A complete framework has been proposed for automatic voltage quality analysis based on the SPM. The SPM has been used before, but this is the first time it has been used in a framework covering a range of voltage quality disturbances. A Gaussian-based anomaly detection method is used to detect and extract voltage quality disturbances. A principal component analysis (PCA) algorithm is used for event characterization. The obtained single-event characteristics are used to extract additional information like origin, fault type and location. 

Two deep learning-based voltage dip classifier has been developed. In both classifier a 2D convolutional neural network (2D-CNN) architecture has been employed to perform automatic feature extraction task. The soft-max activation function fulfills supervised classification method in first classifier. The second classifier uses a semi-supervised classification method based on generative-discriminative model pairs in active learning context.

The same SPM was shown to enable the effective extraction of dip characteristics for multi-stage voltage dips. Applying the k-means clustering algorithm, the event is clustered into its individual stages. For each stage of the dip, a logistic regression algorithm is used to characterize that stage. The proposed method offers a new solution to the problem with transition segments that is one of the main challenges of existing methods for characterization of multi-stage dips.  

It is also shown in the dissertation that the SPM is an effective method for voltage transient analysis. It is possible to extract corresponding sample data and get appropriate single-event characteristics.

A systematic way has been developed and applied for comparing different sets of voltage dip characteristics. With this method, both measured and synthetic voltage dips are applied to generic models of sensitive loads. The best set of characteristics is the one most accurately reproducing the behavior of equipment when exposed to measured voltage dips.

The dissertation further contains a number of practical applications of the before-mentioned theoretical contributions: a proposal to an international standard-setting group; energy storage for voltage-dip ride-through of microgrids; impact of different voltage dips on wind-power installations.

Place, publisher, year, edition, pages
Luleå: Luleå University of Technology, 2018. p. 213
Series
Doctoral thesis / Luleå University of Technology 1 jan 1997 → …, ISSN 1402-1544
Keywords
Power System, power Quality, Voltage Dip, Big Data, Deep Learning, Machine Learning, Active Learning, Consensus Contriol
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Electric Power Engineering
Identifiers
urn:nbn:se:ltu:diva-71413 (URN)978-91-7790-250-8 (ISBN)978-91-7790-251-5 (ISBN)
Public defence
2018-12-07, Skellefteå Hörsal A193, Skellefteå, 10:00 (English)
Opponent
Supervisors
Available from: 2018-11-01 Created: 2018-11-01 Last updated: 2019-03-04Bibliographically approved
Bagheri, A., Bollen, M. & Gu, I. Y. .. (2018). Improved characterization of multi-stage voltage dips based on the space phasor model. Electric power systems research, 154, 319-328
Open this publication in new window or tab >>Improved characterization of multi-stage voltage dips based on the space phasor model
2018 (English)In: Electric power systems research, ISSN 0378-7796, E-ISSN 1873-2046, Vol. 154, p. 319-328Article in journal (Refereed) Published
Abstract [en]

This paper proposes a method for characterizing voltage dips based on the space phasor model of the three phase-to-neutral voltages, instead of the individual voltages. This has several advantages. Using a K-means clustering algorithm, a multi-stage dip is separated into its individual event segments directly instead of first detecting the transition segments. The logistic regression algorithm fits the best single-segment characteristics to every individual segment, instead of extreme values being used for this, as in earlier methods. The method is validated by applying it to synthetic and measured dips. It can be generalized for application to both single- and multi-stage dips.

Place, publisher, year, edition, pages
Elsevier, 2018
Keywords
Electric power distribution, Electric power transmission, Power quality, Voltage dips, Machine learning algorithms, Clustering algorithms, Logistic regression
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Electric Power Engineering
Identifiers
urn:nbn:se:ltu:diva-65693 (URN)10.1016/j.epsr.2017.09.004 (DOI)000416494800031 ()2-s2.0-85029393979 (Scopus ID)
Note

Validerad;2017;Nivå 2;2017-09-18 (andbra)

Available from: 2017-09-18 Created: 2017-09-18 Last updated: 2021-03-22Bibliographically approved
Bagheri, A. & Bollen, M. (2018). Space Phasor Model Based Monitoring of Voltages in Three Phase Systems. In: Proceedings of International Conference on Harmonics and Quality of Power, ICHQP: . Paper presented at 18th International Conference on Harmonics and Quality of Power (ICHQP 2018), Ljubljana, Slovenia, May 13–16 2018. Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE)
Open this publication in new window or tab >>Space Phasor Model Based Monitoring of Voltages in Three Phase Systems
2018 (English)In: Proceedings of International Conference on Harmonics and Quality of Power, ICHQP, Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE), 2018Conference paper, Published paper (Refereed)
Abstract [en]

This paper proposes a method for monitoring of voltages in three-phase systems using parameters of the ellipse, correspondent to the space phasor model of three-phase voltages. Three main parameters, semi-minor axis, semi-major axis and rotating angle of the ellipse are calculated as single-cycle characteristics. Once these characteristics exceed predefined threshold values, different voltage events are detected. Given whole event data the parameters of the corresponding ellipse are calculated as ‘single-event characteristics’. The proposed method is applied to different measured voltage waveforms. The simulation results confirm that the ellipse parameters are a good basis for both detecting and characterizing voltage events.

Place, publisher, year, edition, pages
Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE), 2018
Series
International Conference on Harmonics and Quality of Power, E-ISSN 1540-6008
Keywords
Power quality, Space phasor model, Principal component analysis, single-event characteristic
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Electric Power Engineering
Identifiers
urn:nbn:se:ltu:diva-68834 (URN)10.1109/ICHQP.2018.8378886 (DOI)000444771900075 ()2-s2.0-85049258564 (Scopus ID)978-1-5386-0517-2 (ISBN)
Conference
18th International Conference on Harmonics and Quality of Power (ICHQP 2018), Ljubljana, Slovenia, May 13–16 2018
Available from: 2018-05-22 Created: 2018-05-22 Last updated: 2021-03-22Bibliographically approved
Wang, Y., Bagheri, A., Bollen, M. & Xiao, X.-X. (2017). Single-Event Characteristics for Voltage Dips in Three-Phase Systems (ed.). IEEE Transactions on Power Delivery, 32(2), 832-840, Article ID 7496837.
Open this publication in new window or tab >>Single-Event Characteristics for Voltage Dips in Three-Phase Systems
2017 (English)In: IEEE Transactions on Power Delivery, ISSN 0885-8977, E-ISSN 1937-4208, Vol. 32, no 2, p. 832-840, article id 7496837Article in journal (Refereed) Published
Abstract [en]

This paper compares different methods for voltage-dip characterization. Those methods are based on earlier proposed algorithms for extracting three-phase characteristics (dip type, characteristic voltage, and so-called “PN factor”). The difference between the 12 methods being studied in this paper is in the way in which the time variation of those characteristics is treated to result in single-event characteristics. The methods are applied to 259 measured voltage dips and the performance of the different methods is compared. It is found that small differences in method can result in big difference in results. From the comparison, two methods are selected and recommended for inclusion in international standards.

Place, publisher, year, edition, pages
IEEE, 2017
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Electric Power Engineering
Identifiers
urn:nbn:se:ltu:diva-3784 (URN)10.1109/TPWRD.2016.2574924 (DOI)000398907100027 ()2-s2.0-85017627635 (Scopus ID)19d9520d-1a96-40e6-89a3-b502db31d0bb (Local ID)19d9520d-1a96-40e6-89a3-b502db31d0bb (Archive number)19d9520d-1a96-40e6-89a3-b502db31d0bb (OAI)
Note

Validerad; 2017; Nivå 2; 2017-03-23 (andbra)

Available from: 2016-09-29 Created: 2016-09-29 Last updated: 2019-03-04Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0001-8504-494X

Search in DiVA

Show all publications