Energies

Editorial

Jump to: Research

2 pages, 160 KiB

Open AccessEditorial

Machine Learning and Data Mining Applications in Power Systems

by Zbigniew Leonowicz and Michal Jasinski

Energies 2022, 15(5), 1676; https://doi.org/10.3390/en15051676 - 24 Feb 2022

Cited by 6 | Viewed by 1880

Abstract

This Special Issue was intended as a forum to advance research and apply machine-learning and data-mining methods in order to facilitate the development of modern electric power systems, grids and devices, smart grids and protection devices, as well as to develop tools for [...] Read more.

This Special Issue was intended as a forum to advance research and apply machine-learning and data-mining methods in order to facilitate the development of modern electric power systems, grids and devices, smart grids and protection devices, as well as to develop tools for more accurate and efficient power system analysis [...] Full article

(This article belongs to the Special Issue Machine Learning and Data Mining Applications in Power Systems)

Research

Jump to: Editorial

22 pages, 890 KiB

Open AccessArticle

Improving Detection of False Data Injection Attacks Using Machine Learning with Feature Selection and Oversampling

by Ajit Kumar, Neetesh Saxena, Souhwan Jung and Bong Jun Choi

Energies 2022, 15(1), 212; https://doi.org/10.3390/en15010212 - 29 Dec 2021

Cited by 11 | Viewed by 2526

Abstract

Critical infrastructures have recently been integrated with digital controls to support intelligent decision making. Although this integration provides various benefits and improvements, it also exposes the system to new cyberattacks. In particular, the injection of false data and commands into communication is one [...] Read more.

Critical infrastructures have recently been integrated with digital controls to support intelligent decision making. Although this integration provides various benefits and improvements, it also exposes the system to new cyberattacks. In particular, the injection of false data and commands into communication is one of the most common and fatal cyberattacks in critical infrastructures. Hence, in this paper, we investigate the effectiveness of machine-learning algorithms in detecting False Data Injection Attacks (FDIAs). In particular, we focus on two of the most widely used critical infrastructures, namely power systems and water treatment plants. This study focuses on tackling two key technical issues: (1) finding the set of best features under a different combination of techniques and (2) resolving the class imbalance problem using oversampling methods. We evaluate the performance of each algorithm in terms of time complexity and detection accuracy to meet the time-critical requirements of critical infrastructures. Moreover, we address the inherent skewed distribution problem and the data imbalance problem commonly found in many critical infrastructure datasets. Our results show that the considered minority oversampling techniques can improve the Area Under Curve (AUC) of GradientBoosting, AdaBoost, and kNN by 10–12%. Full article

(This article belongs to the Special Issue Machine Learning and Data Mining Applications in Power Systems)

► Show Figures

Figure 1

15 pages, 1707 KiB

Open AccessArticle

Intelligent Scheduling of Smart Home Appliances Based on Demand Response Considering the Cost and Peak-to-Average Ratio in Residential Homes

by Nedim Tutkun, Alessandro Burgio, Michal Jasinski, Zbigniew Leonowicz and Elzbieta Jasinska

Energies 2021, 14(24), 8510; https://doi.org/10.3390/en14248510 - 17 Dec 2021

Cited by 16 | Viewed by 5677

Abstract

With recent developments, smart grids assured for residential customers the opportunity to schedule smart home appliances’ operation times to simultaneously reduce both the electricity bill and the PAR based on demand response, as well as increasing user comfort. It is clear that the [...] Read more.

With recent developments, smart grids assured for residential customers the opportunity to schedule smart home appliances’ operation times to simultaneously reduce both the electricity bill and the PAR based on demand response, as well as increasing user comfort. It is clear that the multi-objective combinatorial optimization problem involves constraints and the consumer’s preferences, and the solution to the problem is a difficult task. There have been a limited number of investigations carried out so far to solve the indicated problems using metaheuristic techniques like particle swarm optimization, mixed-integer linear programming, and the grey wolf and crow search optimization algorithms, etc. Due to the on/off control of smart home appliances, binary-coded genetic algorithms seem to be a well-fitted approach to obtain an optimal solution. It can be said that the novelty of this work is to represent the on/off state of the smart home appliance with a binary string which undergoes crossover and mutation operations during the genetic process. Because special binary numbers represent interruptible and uninterruptible smart home appliances, new types of crossover and mutation were developed to find the most convenient solutions to the problem. Although there are a few works which were carried out using the genetic algorithms, the proposed approach is rather distinct from those employed in their work. The designed genetic software runs at least ten times, and the most fitting result is taken as the optimal solution to the indicated problem; in order to ensure the optimal result, the fitness against the generation is plotted in each run, whether it is converged or not. The simulation results are significantly encouraging and meaningful to residential customers and utilities for the achievement of the goal, and they are feasible for a wide-range applications of home energy management systems. Full article

(This article belongs to the Special Issue Machine Learning and Data Mining Applications in Power Systems)

► Show Figures

Figure 1

20 pages, 7136 KiB

Open AccessArticle

Sparse Signal Reconstruction on Fixed and Adaptive Supervised Dictionary Learning for Transient Stability Assessment

by Raoult Teukam Dabou, Innocent Kamwa, Jacques Tagoudjeu and Francis Chuma Mugombozi

Energies 2021, 14(23), 7995; https://doi.org/10.3390/en14237995 - 30 Nov 2021

Cited by 5 | Viewed by 1947

Abstract

Fixed and adaptive supervised dictionary learning (SDL) is proposed in this paper for wide-area stability assessment. Single and hybrid fixed structures are developed based on impulse dictionary (ID), discrete Haar transform (DHT), discrete cosine transform (DCT), discrete sine transform (DST), and discrete wavelet [...] Read more.

Fixed and adaptive supervised dictionary learning (SDL) is proposed in this paper for wide-area stability assessment. Single and hybrid fixed structures are developed based on impulse dictionary (ID), discrete Haar transform (DHT), discrete cosine transform (DCT), discrete sine transform (DST), and discrete wavelet transform (DWT) for sparse features extraction and online transient stability prediction. The fixed structures performance is compared with that obtained from transient K-singular value decomposition (TK-SVD) implemented while adding a stability status term to the optimization problem. Stable and unstable dictionary learning are designed based on datasets recorded by simulating thousands of contingencies with varying faults, load, and generator switching on the IEEE 68-bus test system. This separate supervised learning of stable and unstable scenarios allows determining root mean square error (RMSE), useful for online stability status assessment of new scenarios. With respect to the RMSE performance metric in signal reconstruction-based stability prediction, the present analysis demonstrates that [DWT], [DHT|DWT] and [DST|DHT|DCT] are better stability descriptors compared to K-SVD, [DHT], [DCT], [DCT|DWT], [DHT|DCT], [ID|DCT|DST], and [DWT|DHT|DCT] on test datasets. However, the K-SVD approach is faster to execute in both off-line training and real-time playback while yielding satisfactory accuracy in transient stability prediction (i.e., 7.5-cycles decision window after fault-clearing). Full article

(This article belongs to the Special Issue Machine Learning and Data Mining Applications in Power Systems)

► Show Figures

Figure 1

23 pages, 692 KiB

Open AccessArticle

Isolated Areas Consumption Short-Term Forecasting Method

by Guillaume Guerard, Hugo Pousseur and Ihab Taleb

Energies 2021, 14(23), 7914; https://doi.org/10.3390/en14237914 - 25 Nov 2021

Cited by 1 | Viewed by 1942

Abstract

Forecasting consumption in isolated areas represents a challenging problem typically resolved using deep learning or huge mathematical models with various dimensions. Those models require expertise in metering and algorithms and the equipment needs to be frequently maintained. In the context of the MAESHA [...] Read more.

Forecasting consumption in isolated areas represents a challenging problem typically resolved using deep learning or huge mathematical models with various dimensions. Those models require expertise in metering and algorithms and the equipment needs to be frequently maintained. In the context of the MAESHA H2020 project, most of the consumers and producers are isolated. Forecasting becomes more difficult due to the lack of external data and the significant impact of human behaviors on those small systems. The proposed approach is based on data sequencing, sequential mining, and pattern mining to infer the results into a Hidden Markov Model. It only needs the consumption and production curve as a time series and adapts itself to provide the forecast. Our method gives a better forecast than other prediction machines and deep-learning methods used in literature review. Full article

(This article belongs to the Special Issue Machine Learning and Data Mining Applications in Power Systems)

► Show Figures

Figure 1

15 pages, 1836 KiB

Open AccessArticle

Empirical Analysis of the Impact of COVID-19 Social Distancing on Residential Electricity Consumption Based on Demographic Characteristics and Load Shape

by Minseok Jang, Hyun Cheol Jeong, Taegon Kim, Dong Hee Suh and Sung-Kwan Joo

Energies 2021, 14(22), 7523; https://doi.org/10.3390/en14227523 - 11 Nov 2021

Cited by 10 | Viewed by 2092

Abstract

Since January 2020, the COVID-19 pandemic has been impacting various aspects of people’s daily lives and the economy. The first case of COVID-19 in South Korea was identified on 20 January 2020. The Korean government implemented the first social distancing measures in the [...] Read more.

Since January 2020, the COVID-19 pandemic has been impacting various aspects of people’s daily lives and the economy. The first case of COVID-19 in South Korea was identified on 20 January 2020. The Korean government implemented the first social distancing measures in the first week of March 2020. As a result, energy consumption in the industrial, commercial and educational sectors decreased. On the other hand, residential energy consumption increased as telecommuting work and remote online classes were encouraged. However, the impact of social distancing on residential energy consumption in Korea has not been systematically analyzed. This study attempts to analyze the impact of social distancing implemented as a result of COVID-19 on residential energy consumption with time-varying reproduction numbers of COVID-19. A two-way fixed effect model and demographic characteristics are used to account for the heterogeneity. The changes in household energy consumption by load shape group are also analyzed with the household energy consumption model. There some are key results of COVID-19 impact on household energy consumption. Based on the hourly smart meter data, an average increase of 0.3% in the hourly average energy consumption is caused by a unit increase in the time-varying reproduction number of COVID-19. For each income, mid-income groups show less impact on energy consumption compared to both low-income and high-income groups. In each family member, as the number of family members increases, the change in electricity consumption affected by social distancing tends to decrease. For area groups, large area consumers increase household energy consumption more than other area groups. Lastly, The COVID-19 impact on each load shape is influenced by their energy consumption patterns. Full article

(This article belongs to the Special Issue Machine Learning and Data Mining Applications in Power Systems)

► Show Figures

Figure 1

26 pages, 10372 KiB

Open AccessArticle

The Influence of Power Network Disturbances on Short Delayed Estimation of Fundamental Frequency Based on IpDFT Method with GMSD Windows

by Józef Borkowski, Mirosław Szmajda and Janusz Mroczka

Energies 2021, 14(20), 6465; https://doi.org/10.3390/en14206465 - 9 Oct 2021

Cited by 2 | Viewed by 1625

Abstract

This paper presents an application of the IpDFT spectrum interpolation method to estimate the fundamental frequency of a power waveform. Zero-crossing method (ZC) with signal prefiltering was used as a reference method. Test models of disturbances were applied, based on real disturbances recorded [...] Read more.

This paper presents an application of the IpDFT spectrum interpolation method to estimate the fundamental frequency of a power waveform. Zero-crossing method (ZC) with signal prefiltering was used as a reference method. Test models of disturbances were applied, based on real disturbances recorded in power networks, including voltage harmonics and interharmonics, transient overvoltages, frequency spikes, dips and noise. It was determined that the IpDFT method is characterized by much better dynamic parameters with better estimation precision. In an example, in the presence of interharmonics, the frequency estimation error was three times larger for the reference method than that for the IpDFT method. Furthermore, during the occurrence of fast transient overvoltages, the IpDFT method reached its original accuracy about three times faster than the ZC method. Finally, using IpDFT, it was possible to identify the type of disturbances: impulsive, step changes of frequency or voltage dips. Full article

(This article belongs to the Special Issue Machine Learning and Data Mining Applications in Power Systems)

► Show Figures

Figure 1

19 pages, 6306 KiB

Open AccessArticle

Adaptive Neuro-Fuzzy Inference System-Based Maximum Power Tracking Controller for Variable Speed WECS

by Abrar Ahmed Chhipa, Vinod Kumar, Raghuveer Raj Joshi, Prasun Chakrabarti, Michal Jasinski, Alessandro Burgio, Zbigniew Leonowicz, Elzbieta Jasinska, Rajkumar Soni and Tulika Chakrabarti

Energies 2021, 14(19), 6275; https://doi.org/10.3390/en14196275 - 1 Oct 2021

Cited by 37 | Viewed by 3139

Abstract

This paper proposes an adaptive neuro-fuzzy inference system (ANFIS) maximum power point tracking (MPPT) controller for grid-connected doubly fed induction generator (DFIG)-based wind energy conversion systems (WECS). It aims at extracting maximum power from the wind by tracking the maximum power peak regardless [...] Read more.

This paper proposes an adaptive neuro-fuzzy inference system (ANFIS) maximum power point tracking (MPPT) controller for grid-connected doubly fed induction generator (DFIG)-based wind energy conversion systems (WECS). It aims at extracting maximum power from the wind by tracking the maximum power peak regardless of wind speed. The proposed MPPT controller implements an ANFIS approach with a backpropagation algorithm. The rotor speed acts as an input to the controller and torque reference as the controller’s output, which further inputs the rotor side converter’s speed control loop to control the rotor’s actual speed by adjusting the duty ratio for the rotor side converter. The grid partition method generates input membership functions by uniformly partitioning the input variable ranges and creating a single-output Sugeno fuzzy system. The neural network trained the fuzzy input membership according to the inputs and alter the initial membership functions. The simulation results have been validated on a 2 MW wind turbine using the MATLAB/Simulink environment. The controller’s performance is tested under various wind speed circumstances and compared with the performance of a conventional proportional–integral MPPT controller. The simulation study shows that WECS can operate at its optimum power for the proposed controller’s wide range of input wind speed. Full article

(This article belongs to the Special Issue Machine Learning and Data Mining Applications in Power Systems)

► Show Figures

Figure 1

20 pages, 5380 KiB

Open AccessArticle

Clustering Methods for Power Quality Measurements in Virtual Power Plant

by Fachrizal Aksan, Michał Jasiński, Tomasz Sikorski, Dominika Kaczorowska, Jacek Rezmer, Vishnu Suresh, Zbigniew Leonowicz, Paweł Kostyła, Jarosław Szymańda and Przemysław Janik

Energies 2021, 14(18), 5902; https://doi.org/10.3390/en14185902 - 17 Sep 2021

Cited by 15 | Viewed by 2804

Abstract

In this article, a case study is presented on applying cluster analysis techniques to evaluate the level of power quality (PQ) parameters of a virtual power plant. The conducted research concerns the application of the K-means algorithm in comparison with the agglomerative algorithm [...] Read more.

In this article, a case study is presented on applying cluster analysis techniques to evaluate the level of power quality (PQ) parameters of a virtual power plant. The conducted research concerns the application of the K-means algorithm in comparison with the agglomerative algorithm for PQ data, which have different sizes of features. The object of the study deals with the standardized datasets containing classical PQ parameters from two sub-studies. Moreover, the optimal number of clusters for both algorithms is discussed using the elbow method and a dendrogram. The experimental results show that the dendrogram method requires a long processing time but gives a consistent result of the optimal number of clusters when there are additional parameters. In comparison, the elbow method is easy to compute but gives inconsistent results. According to the Calinski–Harabasz index and silhouette coefficient, the K-means algorithm performs better than the agglomerative algorithm in clustering the data points when there are no additional features of PQ data. Finally, based on the standard EN 50160, the result of the cluster analysis from both algorithms shows that all PQ parameters for each cluster in the two study objects are still below the limit level and work under normal operating conditions. Full article

(This article belongs to the Special Issue Machine Learning and Data Mining Applications in Power Systems)

► Show Figures

Figure 1

21 pages, 11206 KiB

Open AccessArticle

Off-Grid Rural Electrification in India Using Renewable Energy Resources and Different Battery Technologies with a Dynamic Differential Annealed Optimization

by Polamarasetty P Kumar, Vishnu Suresh, Michal Jasinski and Zbigniew Leonowicz

Energies 2021, 14(18), 5866; https://doi.org/10.3390/en14185866 - 16 Sep 2021

Cited by 10 | Viewed by 2718

Abstract

Several families in India live in remote places with no access to grid-connected power supply due to their remoteness. The study area chosen from the Indian state of Odisha does not have an electrical power supply due to its distant location. As a [...] Read more.

Several families in India live in remote places with no access to grid-connected power supply due to their remoteness. The study area chosen from the Indian state of Odisha does not have an electrical power supply due to its distant location. As a result, this study analyzed the electrification process using Renewable Energy (RE) resources available in the locality. However, these RE resources are limited by their dependency on weather conditions and time. So, a robust battery storage system is needed for a continuous power supply. Hence, the Nickel Iron (Ni-Fe), Lithium-Ion (Li-Ion) and Lead Acid (LA) battery technologies have been analyzed to identify a battery technology that is both technologically and economically viable. Using the available RE resources in the study area, such as photovoltaic and biomass energy resources, as well as the various battery technologies, three configurations have been modelled, such as Photovoltaic Panels (PVP)/Biomass Generator(BIOMG)/BATTERY_(Ni-Fe), PV/BIOMG/BATTERY_(Li-Ion) and PVP/BMG/BATTERY_(LA). These three configurations have been examined using nine prominent metaheuristic algorithms, in which the PVP/BIOMG/BATTERY_(Ni-Fe) configuration provided the optimal Life Cycle Cost value of 367,586 USD. Among the all metaheuristic algorithms, the dynamic differential annealed optimization algorithm was given the best Life Cycle Cost values for all of the three configurations. Full article

(This article belongs to the Special Issue Machine Learning and Data Mining Applications in Power Systems)

► Show Figures

Figure 1

19 pages, 4354 KiB

Open AccessArticle

Impact of Harmonic Currents of Nonlinear Loads on Power Quality of a Low Voltage Network–Review and Case Study

by Łukasz Michalec, Michał Jasiński, Tomasz Sikorski, Zbigniew Leonowicz, Łukasz Jasiński and Vishnu Suresh

Energies 2021, 14(12), 3665; https://doi.org/10.3390/en14123665 - 19 Jun 2021

Cited by 56 | Viewed by 6548

Abstract

The paper presents a power-quality analysis in the utility low-voltage network focusing on harmonic currents’ pollution. Usually, to forecast the modern electrical and electronic devices’ contribution to increasing the current total harmonic distortion factor

(T H D_{I})

and exceeding the [...] Read more.

The paper presents a power-quality analysis in the utility low-voltage network focusing on harmonic currents’ pollution. Usually, to forecast the modern electrical and electronic devices’ contribution to increasing the current total harmonic distortion factor

(T H D_{I})

and exceeding the regulation limit, analyses based on tests and models of individual devices are conducted. In this article, a composite approach was applied. The performance of harmonic currents produced by sets of devices commonly used in commercial and residential facilities’ nonlinear loads was investigated. The measurements were conducted with the class A PQ analyzer (FLUKE 435) and dedicated to the specialized PC software. The experimental tests show that the harmonic currents produced by multiple types of nonlinear loads tend to reduce the current total harmonic distortion factor

(T H D_{I})

. The changes of harmonic content caused by summation and/or cancellation effects in total current drawn from the grid by nonlinear loads should be a key factor in harmonic currents’ pollution study. Proper forecasting of the level of harmonic currents injected into the utility grid helps to maintain the quality of electricity at an appropriate level and reduce active power losses, which have a direct impact on the price of electricity generation. Full article

(This article belongs to the Special Issue Machine Learning and Data Mining Applications in Power Systems)

► Show Figures

Figure 1

14 pages, 1742 KiB

Open AccessFeature PaperArticle

A Case Study on Data Mining Application in a Virtual Power Plant: Cluster Analysis of Power Quality Measurements

by Michał Jasiński, Tomasz Sikorski, Dominika Kaczorowska, Jacek Rezmer, Vishnu Suresh, Zbigniew Leonowicz, Paweł Kostyła, Jarosław Szymańda, Przemysław Janik, Jacek Bieńkowski and Przemysław Prus

Energies 2021, 14(4), 974; https://doi.org/10.3390/en14040974 - 12 Feb 2021

Cited by 10 | Viewed by 2692

Abstract

One of the recent trends that concern renewable energy sources and energy storage systems is the concept of virtual power plants (VPP). The majority of research now focuses on analyzing case studies of VPP in different issues. This article presents the investigation that [...] Read more.

One of the recent trends that concern renewable energy sources and energy storage systems is the concept of virtual power plants (VPP). The majority of research now focuses on analyzing case studies of VPP in different issues. This article presents the investigation that is based on a real VPP. That VPP operates in Poland and consists of hydropower plants (HPP), as well as energy storage systems (ESS). For specific analysis, cluster analysis, as a representative technique of data mining, was selected for power quality (PQ) issues. The used data represents 26 weeks of PQ multipoint synchronic measurements for 5 related to VPP points. The investigation discusses different input databases for cluster analysis. Moreover, as an extension to using classical PQ parameters as an input, the application of the global index was proposed. This enables the reduction of the size of the input database with maintaining the data features for cluster analysis. Moreover, the problem of the optimal number of cluster selection is discussed. Finally, the assessment of clustering results was performed to assess the VPP impact on PQ level. Full article

(This article belongs to the Special Issue Machine Learning and Data Mining Applications in Power Systems)

► Show Figures

Figure 1

13 pages, 1550 KiB

Open AccessArticle

A Case Study on a Hierarchical Clustering Application in a Virtual Power Plant: Detection of Specific Working Conditions from Power Quality Data

by Michał Jasiński, Tomasz Sikorski, Dominika Kaczorowska, Jacek Rezmer, Vishnu Suresh, Zbigniew Leonowicz, Paweł Kostyła, Jarosław Szymańda, Przemysław Janik, Jacek Bieńkowski and Przemysław Prus

Energies 2021, 14(4), 907; https://doi.org/10.3390/en14040907 - 9 Feb 2021

Cited by 8 | Viewed by 3066

Abstract

The integration of virtual power plants (VPP) has become more popular. Thus, research on VPP for different issues is highly desirable. This article addresses power quality issues. The presented investigation is based on multipoint, synchronic measurements obtained from five points that are related [...] Read more.

The integration of virtual power plants (VPP) has become more popular. Thus, research on VPP for different issues is highly desirable. This article addresses power quality issues. The presented investigation is based on multipoint, synchronic measurements obtained from five points that are related to the VPP. This article provides a proposition and discussion of using one global index in place of the classical power quality (PQ) parameters. Furthermore, in the article, one new global power quality index was proposed. Then the PQ measurements, as well as global indexes, were used to prepare input databases for cluster analysis. The mentioned cluster analysis aimed to detect the short-term working conditions of VPP that were specific from the point of view of power quality. To realize this the hierarchical clustering using the Ward algorithm was realized. The article also presents the application of the cubic clustering criterion to support cluster analysis. Then the assessment of the obtained condition was realized using the global index to assure the general information of the cause of its occurrence. Furthermore, the article noticed that the application of the global index, assured reduction of database size to around 74%, without losing the features of the data. Full article

(This article belongs to the Special Issue Machine Learning and Data Mining Applications in Power Systems)

► Show Figures

Figure 1

26 pages, 9338 KiB

Open AccessArticle

The Impact of Supply Voltage Waveform Distortion on Non-Intentional Emission in the Frequency Range 2–150 kHz: An Experimental Study with Power-Line Communication and Selected End-User Equipment

by Marek Wasowski, Tomasz Sikorski, Grzegorz Wisniewski, Pawel Kostyla, Jaroslaw Szymanda, Marcin Habrych, Lukasz Gornicki, Jaroslaw Sokol and Mariusz Jurczyk

Energies 2021, 14(3), 777; https://doi.org/10.3390/en14030777 - 2 Feb 2021

Cited by 11 | Viewed by 3640

Abstract

Knowledge of the conducted emissions in the frequency range 2–150 kHz contains some gaps related to the impact of the harmonics in the supply voltage on the nature of these emissions. It can be noticed that the conducted emissions from non-sinusoidal power supplies [...] Read more.

Knowledge of the conducted emissions in the frequency range 2–150 kHz contains some gaps related to the impact of the harmonics in the supply voltage on the nature of these emissions. It can be noticed that the conducted emissions from non-sinusoidal power supplies have not been studied sufficiently, and that the impact of this distortion may be greater than the generally known results of emission tests carried out under standardized test conditions. This paper is aimed at investigating experimental cases of the influence of supply voltage waveform distortion on non-intentional emission in the range 2–150 kHz and the efficiency of power line communication based on selected PRIME (PoweRline Intelligent Metering Evolution) power line communication (PLC) technology. A series of experimental laboratory studies were investigated, representing the operation of the investigated PLC system with different types of end-user equipment (LED—Light Emitting Diode, CFL—Compact Fluorescent Lamp, induction motor with frequency converter) working under a distorted supply voltage condition obtained by the programmable power supply for different scenarios of the admissible harmonics contribution in the range 0–2 kHz. The scenarios included limits defined in standards EN 50160 and IEC 61000-4-13. The researchers used spectral analysis with a notation to emission limits, compatibility levels, and mains signalling, as well as statistics of the PLC communication. The obtained results provide important conclusions, which may be applied both in the development of the design of the appliances in question and the higher frequency emission testing methods. Full article

(This article belongs to the Special Issue Machine Learning and Data Mining Applications in Power Systems)

► Show Figures

Figure 1

22 pages, 5200 KiB

Open AccessArticle

A Case Study on Battery Energy Storage System in a Virtual Power Plant: Defining Charging and Discharging Characteristics

by Dominika Kaczorowska, Jacek Rezmer, Michal Jasinski, Tomasz Sikorski, Vishnu Suresh, Zbigniew Leonowicz, Pawel Kostyla, Jaroslaw Szymanda and Przemyslaw Janik

Energies 2020, 13(24), 6670; https://doi.org/10.3390/en13246670 - 17 Dec 2020

Cited by 16 | Viewed by 3606

Abstract

A virtual power plant (VPP) can be defined as the integration of decentralized units into one centralized control system. A VPP consists of generation sources and energy storage units. In this article, based on real measurements, the charging and discharging characteristics of the [...] Read more.

A virtual power plant (VPP) can be defined as the integration of decentralized units into one centralized control system. A VPP consists of generation sources and energy storage units. In this article, based on real measurements, the charging and discharging characteristics of the battery energy storage system (BESS) were determined, which represents a key element of the experimental virtual power plant operating in the power system in Poland. The characteristics were determined using synchronous measurements of the power of charge and discharge of the storage and the state of charge (SoC). The analyzed private network also includes a hydroelectric power plant (HPP) and loads. The article also examines the impact of charging and discharging characteristics of the BESS on its operation, analyzing the behavior of the storage unit for the given operation plans. The last element of the analysis is to control the power flow in the private network. The operation of the VPP for the given scenario of power flow control was examined. The aim of the scenario is to adjust the load of the private network to the level set by the function. The tests of power flow are carried out on the day on which the maximum power demand occurred. The analysis was performed for four cases: a constant value limitation when the HPP is in operation and when it is not, and two limits set by function during normal operation of the HPP. Thus, the article deals not only with the issue of determining the actual characteristics of charging and discharging the storage unit, but also their impact on the operation of the entire VPP. Full article

(This article belongs to the Special Issue Machine Learning and Data Mining Applications in Power Systems)

► Show Figures

Figure 1

20 pages, 11232 KiB

Open AccessArticle

A Case Study on Power Quality in a Virtual Power Plant: Long Term Assessment and Global Index Application

by Michal Jasiński, Tomasz Sikorski, Dominika Kaczorowska, Jacek Rezmer, Vishnu Suresh, Zbigniew Leonowicz, Paweł Kostyla, Jarosław Szymańda and Przemysław Janik

Energies 2020, 13(24), 6578; https://doi.org/10.3390/en13246578 - 14 Dec 2020

Cited by 14 | Viewed by 2841

Abstract

The concept of virtual power plants (VPP) was introduced over 20 years ago but is still actively researched. The majority of research now focuses on analyzing case studies of such installations. In this article, the investigation is based on a VPP in Poland, [...] Read more.

The concept of virtual power plants (VPP) was introduced over 20 years ago but is still actively researched. The majority of research now focuses on analyzing case studies of such installations. In this article, the investigation is based on a VPP in Poland, which contains hydropower plants (HPP) and energy storage systems (ESS). For specific analysis, the power quality (PQ) issues were selected. The used data contain 26 weeks of multipoint, synchronic measurements of power quality levels in four related points. The investigation is concerned with the application of a global index to a single-point assessment as well as an area-related assessment approach. Moreover, the problem of flagged data is discussed. Finally, the assessment of VPP’s impact on PQ level is conducted. Full article

(This article belongs to the Special Issue Machine Learning and Data Mining Applications in Power Systems)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Machine Learning and Data Mining Applications in Power Systems

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (16 papers)

Editorial

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI