Special Issue "Applications of Machine Learning for Renewable Energy based Modern Power Systems"

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Energy Science and Technology".

Deadline for manuscript submissions: closed (31 March 2022) | Viewed by 11847

Special Issue Editors

Prof. Dr. Giuseppe Marco Tina
E-Mail Website
Guest Editor
Dipartimento di Ingegneria Elettrica Elettronica e Informatica, Università degli Studi di Catania, st. A.Doria, n. 6, 95125 Catania, Italy
Interests: MATLAB simulation; renewable energy technologies; electrical power engineering; power electronics
Special Issues, Collections and Topics in MDPI journals
Dr. Massimiliano De Benedetti
E-Mail
Guest Editor
Dipartimento di Elettronica, Informazione e Bioingegneria (DEIB) Politecnico di Milano.Via Ponzio 34/5, 20133 Milano, Italia
Interests: reinforcement learning; multi agent systems; autonomous agents; stochastic optimization; distributed systems; virtual power plant; DERs aggregation

Special Issue Information

Dear Colleagues,

Nowadays, along with the increased importance of distributed non-programmable renewable electricity generation and the increasing spread of distributed storage systems, intelligent apparatus are needed for the technical and economical management of power systems.

Smart grid is an approach in which user safety should be ensured while monitoring, updating, and continuously and reliably distributing electricity grid by adding smart meters and monitoring systems to the power grid, in order to ensure electronic communication between suppliers and consumers.

The smart grid structure will offer opportunities to progress in the operation of the distribution network, which is not limited to energy supply and ancillary services (e.g., reserves and demand balance) but has also to ensure quality criteria of energy and energy measurement.

The field of Machine Learning has developed from the quest for artificial intelligence. It gives computers the ability to learn statistical patterns from data without being explicitly programmed. These patterns can then be applied to new data in order to make predictions. Machine Learning also allows to automatically adapt to changes in the data without amending the underlying model. Every day, we deal dozens of times with Machine Learning applications, such as when doing a Google search, using spam filters or face detection tools, speaking to voice recognition software, or sitting in a self-driving car.

In recent years, machine learning methods have evolved in the smart grid community. This change towards analyzing data rather than modeling specific problems has led to adaptable, more generic methods that require less expert knowledge and are easier to deploy in a number of cases.

The growing number of Distributed Energy Resources (DERs) connected to the DSO grid (or, more in general, within a smart grid) require a scalable approach to control, optimize, and monitor each end point. A centralized approach that introduces a single point of failure cannot be used in this scenario where a smart grid must be reliable without affecting the overall system stability. Furthermore, the computational power related to a centralized control and optimization algorithm grows exponentially with the number of DERs that must be integrated and optimally managed within a smart grid.

To tackle the scalability and the reliability requirements, machine learning techniques are usually coupled with a multi-agent system approach and a decentralized/distributed control architecture.

Multi-agent systems can solve problems that are difficult or impossible for an individual agent or a  monolithic system to solve and can be applied to artificial intelligence: they simplify problem-solving by dividing the necessary knowledge into subunits—to which an independent intelligent agent is associated—and by coordinating the agents' activity (distributed artificial intelligence).

This Special Issue will bring together researchers from academia and industry to share and publish novel ideas, explore inherent challenges in developing future power systems, investigate novel designs, explore enabling technologies, and share relevant experiences in machine learning methods in smart grids and their applications.

Topics for this Special Issue include, but are not limited to:

  • Enabling technologies for mini- e microgrids
  • Distributed generating resources in smart grids
  • Concentrated and distributed storage systems in smart grids
  • Smart metering, demand–response, and dynamic pricing
  • Intelligent monitoring systems.
  • Control and operation for smart grids
  • Smart grid impact on isolation and service restoration
  • Smart grid enhancement of energy management systems
  • Vehicle-to-grid (V2G).
  • Data Management and Grid Analytics
  • Energy management systems for microgrids
  • DERs coordination and aggregation
  • DERs distributed optimization
  • DERs modelling through machine learning
  • DERs and multi-agent system
  • DERs and decentralized/distributed systems
  • Microgrid modelling through machine learning
  • Grid services and DERs optimization
  • Multi-agent systems
  • Distributed artificial intelligence

Prof. Giuseppe Marco Tina
Dr. Massimiliano De Benedetti
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2300 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Artificial neural network (ANNs)
  • Deep Neural Network 
  • Power system 
  • Solar energy 
  • Microgrids 
  • Wind energy 
  • Electricity demand 
  • Electricity markets 
  • Balancing
  • Forecast 
  • Diagnostic
  • Performance estimation 
  • Energy management
  • DERs 
  • Forecast 
  • Modelling
  • Grid Services 
  • Distributed Systems Optimization

Published Papers (5 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Review

Article
Power Efficiency Improvement of a Boost Converter Using a Coupled Inductor with a Fuzzy Logic Controller: Application to a Photovoltaic System
Appl. Sci. 2021, 11(3), 980; https://doi.org/10.3390/app11030980 - 22 Jan 2021
Cited by 7 | Viewed by 1348
Abstract
DC/DC converters are widely used in photovoltaic (PV) systems to track the maximum power points (MPP) of a photovoltaic generator (PVG). The variation of solar radiation (G) and PV cells temperature (T) affect the power efficiency of these DC/DC converters because they change [...] Read more.
DC/DC converters are widely used in photovoltaic (PV) systems to track the maximum power points (MPP) of a photovoltaic generator (PVG). The variation of solar radiation (G) and PV cells temperature (T) affect the power efficiency of these DC/DC converters because they change the MPP, thus a sizing adaptation of the component values in these DC/DC converters is needed. Power loss in the inductor due to core saturation can severely degrade power efficiency. This paper proposes a new method that allows to adapt the inductor values according to the variable output power of the PV array in order to minimize losses and improve the converter power efficiency. The main idea is to replace the DC/DC inductor with a coupled inductor where the DC/DC inductor value is adjusted through an additional winding in the magnetic core that modulates the magnetic field inside it. Low current intensities from the PVG supply this winding through a circuit controlled by a fuzzy logic controller in order to regulate the second winding current intensity. Experimental results show a significant improvement of the power efficiency of the proposed solution as compared to a conventional converter. Full article
Show Figures

Figure 1

Article
An Improved Power System Transient Stability Prediction Model Based on mRMR Feature Selection and WTA Ensemble Learning
Appl. Sci. 2020, 10(7), 2255; https://doi.org/10.3390/app10072255 - 26 Mar 2020
Cited by 13 | Viewed by 1809
Abstract
Fast online transient stability assessment (TSA) is very important to maintain the stable operation of power systems. However, the existing transient stability assessment methods suffer the drawbacks of unsatisfactory prediction accuracy, difficult applicability, or a heavy computational burden. In light of this, an [...] Read more.
Fast online transient stability assessment (TSA) is very important to maintain the stable operation of power systems. However, the existing transient stability assessment methods suffer the drawbacks of unsatisfactory prediction accuracy, difficult applicability, or a heavy computational burden. In light of this, an improved high accuracy power system transient stability prediction model is proposed, based on min-redundancy and max-relevance (mRMR) feature selection and winner take all (WTA) ensemble learning. Firstly, the contributions of four different series of raw sampled data from all of the three-time stages, namely the pre-fault, during-fault and post-fault, to transient stability are compared. The new feature of generator electromagnetic power is introduced and compared with three conventional types of input features, through a support vector machine (SVM) classifier. Furthermore, the two types of most contributive input features are obtained by the mRMR feature selection method. Finally, the prediction results of the electromagnetic power of generators and the voltage amplitude of buses are combined using the WTA ensemble learning method, and an improved transient stability prediction model with higher accuracy for unstable samples is obtained, whose overall prediction accuracy would not decrease either. The real-time data collected by wide area monitoring systems (WAMS) can be fed into this model for fast online transient stability prediction; the results can also provide a basis for the future emergency control decision-making of power systems. Full article
Show Figures

Figure 1

Article
Pattern Discovery in White Etching Crack Experimental Data Using Machine Learning Techniques
Appl. Sci. 2019, 9(24), 5502; https://doi.org/10.3390/app9245502 - 14 Dec 2019
Cited by 4 | Viewed by 2322
Abstract
White etching crack (WEC) failure is a failure mode that affects bearings in many applications, including wind turbine gearboxes, where it results in high, unplanned maintenance costs. WEC failure is unpredictable as of now, and its root causes are not yet fully understood. [...] Read more.
White etching crack (WEC) failure is a failure mode that affects bearings in many applications, including wind turbine gearboxes, where it results in high, unplanned maintenance costs. WEC failure is unpredictable as of now, and its root causes are not yet fully understood. While WECs were produced under controlled conditions in several investigations in the past, converging the findings from the different combinations of factors that led to WECs in different experiments remains a challenge. This challenge is tackled in this paper using machine learning (ML) models that are capable of capturing patterns in high-dimensional data belonging to several experiments in order to identify influential variables to the risk of WECs. Three different ML models were designed and applied to a dataset containing roughly 700 high- and low-risk oil compositions to identify the constituting chemical compounds that make a given oil composition high-risk with respect to WECs. This includes the first application of a purpose-built neural network-based feature selection method. Out of 21 compounds, eight were identified as influential by models based on random forest and artificial neural networks. Association rules were also mined from the data to investigate the relationship between compound combinations and WEC risk, leading to results supporting those of previous analyses. In addition, the identified compound with the highest influence was proved in a separate investigation involving physical tests to be of high WEC risk. The presented methods can be applied to other experimental data where a high number of measured variables potentially influence a certain outcome and where there is a need to identify variables with the highest influence. Full article
Show Figures

Figure 1

Article
Improving the Reliability of Photovoltaic and Wind Power Storage Systems Using Least Squares Support Vector Machine Optimized by Improved Chicken Swarm Algorithm
Appl. Sci. 2019, 9(18), 3788; https://doi.org/10.3390/app9183788 - 10 Sep 2019
Cited by 11 | Viewed by 1597
Abstract
In photovoltaic and wind power storage systems, the reliability of the battery directly affects the overall reliability of the energy storage system. Failed batteries can seriously affect the stable operation of energy storage systems. This paper aims to improve the reliability of the [...] Read more.
In photovoltaic and wind power storage systems, the reliability of the battery directly affects the overall reliability of the energy storage system. Failed batteries can seriously affect the stable operation of energy storage systems. This paper aims to improve the reliability of the storage systems by accurately predicting battery life and identifying failing batteries in time. The current prediction models mainly use artificial neural networks, Gaussian process regression and hybrid models. Although these models can achieve high prediction accuracy, the computational cost is high due to model complexity. Least squares support vector machine (LSSVM) is a computationally efficient alternative. Hence, this study combines the improved chicken swarm optimization algorithm (ICSO) and LSSVM into a hybrid ICSO-LSSVM model for the reliability of photovoltaic and wind power storage systems. The following are the contributions of this work. First, the optimal penalty parameter and kernel width are determined. Second, the chicken swarm optimization algorithm (CSO) is improved by introducing chaotic search behavior in the hen and an adaptive learning factor in the chicks. The performance of the ICSO algorithm is shown to be better than CSO using standard test problems. Third, the prediction accuracy of the three models is compared. For NMC1 battery, the predicted relative error of ICSO-LSSVM is 0.94%; for NMC2 battery, the relative error of ICSO-LSSVM is 1%. These findings show that the proposed model is suitable for predicting the failure of batteries in energy storage systems, which can improve preventive and predictive maintenance of such systems. Full article
Show Figures

Figure 1

Review

Jump to: Research

Review
A State-of-Art-Review on Machine-Learning Based Methods for PV
Appl. Sci. 2021, 11(16), 7550; https://doi.org/10.3390/app11167550 - 17 Aug 2021
Cited by 21 | Viewed by 3398
Abstract
In the current era, Artificial Intelligence (AI) is becoming increasingly pervasive with applications in several applicative fields effectively changing our daily life. In this scenario, machine learning (ML), a subset of AI techniques, provides machines with the ability to programmatically learn from data [...] Read more.
In the current era, Artificial Intelligence (AI) is becoming increasingly pervasive with applications in several applicative fields effectively changing our daily life. In this scenario, machine learning (ML), a subset of AI techniques, provides machines with the ability to programmatically learn from data to model a system while adapting to new situations as they learn more by data they are ingesting (on-line training). During the last several years, many papers have been published concerning ML applications in the field of solar systems. This paper presents the state of the art ML models applied in solar energy’s forecasting field i.e., for solar irradiance and power production forecasting (both point and interval or probabilistic forecasting), electricity price forecasting and energy demand forecasting. Other applications of ML into the photovoltaic (PV) field taken into account are the modelling of PV modules, PV design parameter extraction, tracking the maximum power point (MPP), PV systems efficiency optimization, PV/Thermal (PV/T) and Concentrating PV (CPV) system design parameters’ optimization and efficiency improvement, anomaly detection and energy management of PV’s storage systems. While many review papers already exist in this regard, they are usually focused only on one specific topic, while in this paper are gathered all the most relevant applications of ML for solar systems in many different fields. The paper gives an overview of the most recent and promising applications of machine learning used in the field of photovoltaic systems. Full article
Show Figures

Figure 1

Back to TopTop