Research

22 pages, 1731 KiB

Open AccessArticle

Power Forecasting of a Photovoltaic Plant Located in ENEA Casaccia Research Center

by Martina Radicioni, Valentina Lucaferri, Francesco De Lia, Antonino Laudani, Roberto Lo Presti, Gabriele Maria Lozito, Francesco Riganti Fulginei, Riccardo Schioppo and Mario Tucci

Energies 2021, 14(3), 707; https://doi.org/10.3390/en14030707 - 30 Jan 2021

Cited by 11 | Viewed by 1873

Abstract

This work proposes an Artificial Neural Network (ANN) able to provide an accurate forecasting of power produced by photovoltaic (PV) plants. The ANN is customized on the basis of the particular season of the year. An accurate analysis of input variables, i.e., solar [...] Read more.

This work proposes an Artificial Neural Network (ANN) able to provide an accurate forecasting of power produced by photovoltaic (PV) plants. The ANN is customized on the basis of the particular season of the year. An accurate analysis of input variables, i.e., solar irradiance, temperature and air humidity, carried out by means of Pearson Correlation, has allowed to select, day by day, the most suitable set of inputs and ANN architecture also to reduce the necessity of large computational resource. Thus, features are added to the ANN as needed, avoiding waste of computational resources. The method has been validated through data collected from a PV plant installed in ENEA (National agency for new technologies, energy and sustainable economic development) Research Center, located in Casaccia, Rome (Italy). The developed strategy is able to furnish accurate predictions even in the case of strong irregularities of solar irradiance, providing accurate results in rapidly changing scenarios. Full article

(This article belongs to the Special Issue Soft Computing Techniques in Energy System)

► Show Figures

Figure 1

33 pages, 1708 KiB

Open AccessArticle

Building Suitable Datasets for Soft Computing and Machine Learning Techniques from Meteorological Data Integration: A Case Study for Predicting Significant Wave Height and Energy Flux

by Antonio Manuel Gómez-Orellana, Juan Carlos Fernández, Manuel Dorado-Moreno, Pedro Antonio Gutiérrez and César Hervás-Martínez

Energies 2021, 14(2), 468; https://doi.org/10.3390/en14020468 - 17 Jan 2021

Cited by 10 | Viewed by 2121

Abstract

Meteorological data are extensively used to perform environmental learning. Soft Computing (SC) and Machine Learning (ML) techniques represent a valuable support in many research areas, but require datasets containing information related to the topic under study. Such datasets are not always available in [...] Read more.

Meteorological data are extensively used to perform environmental learning. Soft Computing (SC) and Machine Learning (ML) techniques represent a valuable support in many research areas, but require datasets containing information related to the topic under study. Such datasets are not always available in an appropriate format and its preparation and pre-processing implies a lot of time and effort by researchers. This paper presents a novel software tool with a user-friendly GUI to create datasets by means of management and data integration of meteorological observations from two data sources: the National Data Buoy Center and the National Centers for Environmental Prediction and for Atmospheric Research Reanalysis Project. Such datasets can be created using buoys and reanalysis data through customisable procedures, in terms of temporal resolution, predictive and objective variables, and can be used by SC and ML methodologies for prediction tasks (classification or regression). The objective is providing the research community with an automated and versatile system for the casuistry that entails well-formed and quality data integration, potentially leading to better prediction models. The software tool can be used as a supporting tool for coastal and ocean engineering applications, sustainable energy production, or environmental modelling; as well as for decision-making in the design and building of coastal protection structures, marine transport, ocean energy converters, and well-planned running of offshore and coastal engineering activities. Finally, to illustrate the applicability of the proposed tool, a case study to classify waves depending on their significant height and to predict energy flux in the Gulf of Alaska is presented. Full article

(This article belongs to the Special Issue Soft Computing Techniques in Energy System)

► Show Figures

Figure 1

21 pages, 5372 KiB

Open AccessEditor’s ChoiceArticle

Wind Turbine Data Analysis and LSTM-Based Prediction in SCADA System

by Imre Delgado and Muhammad Fahim

Energies 2021, 14(1), 125; https://doi.org/10.3390/en14010125 - 29 Dec 2020

Cited by 51 | Viewed by 5617

Abstract

The number of wind farms is increasing every year because many countries are turning their attention to renewable energy sources. Wind turbines are considered one of the best alternatives to produce clean energy. Most of the wind farms installed supervisory control and data [...] Read more.

The number of wind farms is increasing every year because many countries are turning their attention to renewable energy sources. Wind turbines are considered one of the best alternatives to produce clean energy. Most of the wind farms installed supervisory control and data acquisition (SCADA) system in their turbines to monitor wind turbines and logged the information as time-series data. It demands a powerful information extraction process for analysis and prediction. In this research, we present a data analysis framework to visualize the collected data from the SCADA system and recurrent neural network-based variant long short-term memory (LSTM) based prediction. The data analysis is presented in cartesian, polar, and cylindrical coordinates to understand the wind and energy generation relationship. The four features: wind speed, direction, generated active power, and theoretical power are predicted and compared with state-of-the-art methods. The obtained results confirm the applicability of our model in real-life scenarios that can assist the management team to manage the generated energy of wind turbines. Full article

(This article belongs to the Special Issue Soft Computing Techniques in Energy System)

► Show Figures

Figure 1

30 pages, 16384 KiB

Open AccessArticle

Predicting the Amount of Electric Power Transaction Using Deep Learning Methods

by Gwiman Bak and Youngchul Bae

Energies 2020, 13(24), 6649; https://doi.org/10.3390/en13246649 - 16 Dec 2020

Cited by 6 | Viewed by 1980

Abstract

The most important thing to operate a power system is that the power supply should be close to the power demand. In order to predict the amount of electric power transaction (EPT), it is important to choose and decide the variable and its [...] Read more.

The most important thing to operate a power system is that the power supply should be close to the power demand. In order to predict the amount of electric power transaction (EPT), it is important to choose and decide the variable and its starting date. In this paper, variables that could be acquired one the starting day of prediction were chosen. This paper designated date, temperature and special day as variables to predict the amount of EPT of the Korea Electric Power company. This paper also used temperature data from a year ago to predict the next year. To do this, we proposed single deep learning algorithms and hybrid deep learning algorithms. The former included multi-layer perceptron (MLP), convolution neural network (CNN), long short-term memory (LSTM), gated recurrent unit (GRU), support vector machine regression (SVR), and adaptive network-based fuzzy inference system (ANFIS). The latter included LSTM + CNN and CNN + LSTM. We then confirmed the improvement of accuracy for prediction using pre-processed variables compared to original variables We also assigned two years of test data during 2017–2018 as variable data to measure high prediction accuracy. We then selected a high-accuracy algorithm after measuring root mean square error (RMSE) and mean absolute percent error (MAPE). Finally, we predicted the amount of EPT in 2018 and then measured the error for each proposed algorithm. With these acquired error data, we obtained a model for predicting the amount of EPT with a high accuracy. Full article

(This article belongs to the Special Issue Soft Computing Techniques in Energy System)

► Show Figures

Figure 1

40 pages, 1829 KiB

Open AccessArticle

Identification of Relevant Criteria Set in the MCDA Process—Wind Farm Location Case Study

by Bartłomiej Kizielewicz, Jarosław Wątróbski and Wojciech Sałabun

Energies 2020, 13(24), 6548; https://doi.org/10.3390/en13246548 - 11 Dec 2020

Cited by 60 | Viewed by 3123

Abstract

The paper undertakes the problem of proper structuring of multi-criteria decision support models. To achieve that, a methodological framework is proposed. The authors’ framework is the basis for the relevance analysis of individual criteria in any considered decision model. The formal foundations of [...] Read more.

The paper undertakes the problem of proper structuring of multi-criteria decision support models. To achieve that, a methodological framework is proposed. The authors’ framework is the basis for the relevance analysis of individual criteria in any considered decision model. The formal foundations of the authors’ approach provide a reference set of Multi-Criteria Decision Analysis (MCDA) methods (TOPSIS, VIKOR, COMET) along with their similarity coefficients (Spearman correlation coefficients and WS coefficient). In the empirical research, a practical MCDA-based wind farm location problem was studied. Reference rankings of the decision variants were obtained, followed by a set of rankings in which particular criteria were excluded. This was the basis for testing the similarity of the obtained solutions sets, as well as for recommendations in terms of both indicating the high significance and the possible elimination of individual criteria in the original model. When carrying out the analyzes, both the positions in the final rankings, as well as the corresponding values of utility functions of the decision variants were studied. As a result of the detailed analysis of the obtained results, recommendations were presented in the field of reference criteria set for the considered decision problem, thus demonstrating the practical usefulness of the authors’ proposed approach. It should be pointed out that the presented study of criteria relevance is an important factor for objectification of the multi-criteria decision support processes. Full article

(This article belongs to the Special Issue Soft Computing Techniques in Energy System)

► Show Figures

Graphical abstract

21 pages, 1321 KiB

Open AccessArticle

Multitask Support Vector Regression for Solar and Wind Energy Prediction

by Carlos Ruiz, Carlos M. Alaíz and José R. Dorronsoro

Energies 2020, 13(23), 6308; https://doi.org/10.3390/en13236308 - 30 Nov 2020

Cited by 5 | Viewed by 1631

Abstract

Given the impact of renewable sources in the overall energy production, accurate predictions are becoming essential, with machine learning becoming a very important tool in this context. In many situations, the prediction problem can be divided into several tasks, more or less related [...] Read more.

Given the impact of renewable sources in the overall energy production, accurate predictions are becoming essential, with machine learning becoming a very important tool in this context. In many situations, the prediction problem can be divided into several tasks, more or less related between them but each with its own particularities. Multitask learning (MTL) aims to exploit this structure, training several models at the same time to improve on the results achievable either by a common model or by task-specific models. In this paper, we show how an MTL approach based on support vector regression can be applied to the prediction of photovoltaic and wind energy, problems where tasks can be defined according to different criteria. As shown experimentally with three different datasets, the MTL approach clearly outperforms the results of the common and specific models for photovoltaic energy, and are at the very least quite competitive for wind energy. Full article

(This article belongs to the Special Issue Soft Computing Techniques in Energy System)

► Show Figures

Figure 1

16 pages, 1053 KiB

Open AccessArticle

Machine Learning-Based Approach to Predict Energy Consumption of Renewable and Nonrenewable Power Sources

by Prince Waqas Khan, Yung-Cheol Byun, Sang-Joon Lee, Dong-Ho Kang, Jin-Young Kang and Hae-Su Park

Energies 2020, 13(18), 4870; https://doi.org/10.3390/en13184870 - 17 Sep 2020

Cited by 56 | Viewed by 6579

Abstract

In today’s world, renewable energy sources are increasingly integrated with nonrenewable energy sources into electric grids and pose new challenges because of their intermittent and variable nature. Energy prediction using soft-computing techniques plays a vital role in addressing these challenges. As electricity consumption [...] Read more.

In today’s world, renewable energy sources are increasingly integrated with nonrenewable energy sources into electric grids and pose new challenges because of their intermittent and variable nature. Energy prediction using soft-computing techniques plays a vital role in addressing these challenges. As electricity consumption is closely linked to other energy sources such as natural gas and oil, forecasting electricity consumption is essential for making national energy policies. In this paper, we utilize various data mining techniques, including preprocessing historical load data and the load time series’s characteristics. We analyzed the power consumption trends from renewable energy sources and nonrenewable energy sources and combined them. A novel machine learning-based hybrid approach, combining multilayer perceptron (MLP), support vector regression (SVR), and CatBoost, is proposed in this paper for power forecasting. A thorough comparison is made, taking into account the results obtained using other prediction methods. Full article

(This article belongs to the Special Issue Soft Computing Techniques in Energy System)

► Show Figures

Graphical abstract

26 pages, 3453 KiB

Open AccessArticle

Minimizing the Standard Deviation of the Thermal Load in the Spent Nuclear Fuel Cask Loading Problem

by Joaquín Bautista-Valhondo, Lluís Batet and Manuel Mateo

Energies 2020, 13(18), 4869; https://doi.org/10.3390/en13184869 - 17 Sep 2020

Cited by 3 | Viewed by 2045

Abstract

The paper assumes that, at the end of the operational period of a Spanish nuclear power plant, an Independent Spent Fuel Storage Installation will be used for long-term storage. Spent fuel assemblies are selected and transferred to casks for dry storage, with a [...] Read more.

The paper assumes that, at the end of the operational period of a Spanish nuclear power plant, an Independent Spent Fuel Storage Installation will be used for long-term storage. Spent fuel assemblies are selected and transferred to casks for dry storage, with a series of imposed restrictions (e.g., limiting the thermal load). In this context, we present a variant of the problem of spent nuclear fuel cask loading in one stage (i.e., the fuel is completely transferred from the spent fuel pool to the casks at once), offering a multi-start metaheuristic of three phases. (1) A mixed integer linear programming (MILP-1) model is used to minimize the cost of the casks required. (2) A deterministic algorithm (A1) assigns the spent fuel assemblies to a specific region of a specific cask based on an MILP-1 solution. (3) Starting from the A1 solutions, a local search algorithm (A2) minimizes the standard deviation of the thermal load among casks. Instances with 1200 fuel assemblies (and six intervals for the decay heat) are optimally solved by MILP-1 plus A1 in less than one second. Additionally, A2 gets a Pearson’s coefficient of variation lower than 0.75% in less than 260s CPU (1000 iterations). Full article

(This article belongs to the Special Issue Soft Computing Techniques in Energy System)

► Show Figures

Graphical abstract

25 pages, 5703 KiB

Open AccessArticle

Computational Intelligent Approaches for Non-Technical Losses Management of Electricity

by Rubén González Rodríguez, Jamer Jiménez Mares and Christian G. Quintero M.

Energies 2020, 13(9), 2393; https://doi.org/10.3390/en13092393 - 11 May 2020

Cited by 8 | Viewed by 2144

Abstract

This paper presents an intelligent system for the detection of non-technical losses of electrical energy associated with the fraudulent behaviors of system users. This proposal has three stages: a non-supervised clustering of consumption profiles based on a hybrid algorithm between self-organizing maps (SOM) [...] Read more.

This paper presents an intelligent system for the detection of non-technical losses of electrical energy associated with the fraudulent behaviors of system users. This proposal has three stages: a non-supervised clustering of consumption profiles based on a hybrid algorithm between self-organizing maps (SOM) and genetic algorithms (GA). A second stage for demand forecasting is based on ARIMA (autoregressive integrated moving average) models corrected intelligently through neural networks (ANN). The final stage is a classifier based on random forests for fraudulent user detection. The proposed intelligent approach was trained and tested with real data from the Colombian Caribbean region, where the utility reports energy losses of around 18% of the total energy purchased by the company during the five last years. The results show an average overall performance of 82.9% in the detection process of fraudulent users, significantly increasing the effectiveness compared to the approaches (68%) previously applied by the utility in the region. Full article

(This article belongs to the Special Issue Soft Computing Techniques in Energy System)

► Show Figures

Graphical abstract

Journal Menu

Journal Browser

Soft Computing Techniques in Energy System

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (9 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI