Submit to Energies Review for Energies Propose a Special Issue

Journal Browser

► Journal Browser

Machine Learning Prediction Models in Energy Systems

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of Energies (ISSN 1996-1073). This special issue belongs to the section "F: Electrical Engineering".

Deadline for manuscript submissions: closed (15 December 2021) | Viewed by 37105

Share This Special Issue

Special Issue Editors

Prof. Dr. Annamária R. Várkonyi-Kóczy

E-Mail Website
Guest Editor

1. Institute of Automation, Óbuda University, Budapest 1034, Hungary
2. Department of Mathematics and Informatics, J. Selye University, 945 01 Komarno, Slovakia
Interests: machine learning; soft computing techniques; big data analysis; IoT; predictive analytics; hybrid techniques in intelligent measurement; signal and image processing; modeling and diagnostics; fault diagnostics; optimization

Dr. Amir Mosavi

E-Mail Website
Guest Editor

1. School of the Built Environment, Oxford Brookes University, Oxford OX3 0BP, UK
2. Kalman Kando Faculty of Electrical Engineering, Obuda University, 1034 Budapest, Hungary
Interests: machine learning; deep learning; ensemble and hybrid models; applied mathematics; soft computing; deep reinforcement learning; machine learning for big data; mathematical IT; hydropower modeling; prediction models; time series prediction; climate models; machine learning for remote sensing; hazard models; extreme events; atmospheric models; forecasting models; predictive analytics; Internet of Things
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

This Special Issue is devoted to the latest advancements in prediction models used in energy systems. We invite scientists from around the world to contribute to developing a comprehensive collection of papers on the progressive and high-impact realm of prediction models and diagnostics methods for energy applications. Novel algorithms, new applications, comparative analysis of models, case studies, and state-of-the-art review papers are particularly welcomed.

Very recently, prediction models have been fundamentally revolutionized thanks to affordable computational power, big data technologies, efficient data handling, pre-processing methods, and most importantly, intelligent learning algorithms. Novel machine learning methods, hybrids, ensembles, and deep learning methods integrated with intelligent optimization, various soft computing techniques, and/or advanced statistical methods are rapidly emerging to deliver models with higher accuracy. Today, prediction models are becoming essential in modelling, handling, and diagnosing energy systems with a growing widespread popularity. From energy generation, conversion, distribution, consumption, power, price, loss, load, and demand forecasting to control, diagnosis, failure identification, performance, and maintenance, novel prediction models have shown great progress with promising results.

Prediction models greatly contribute to empowering energy solutions in a broad range of applications. Sustainable and clean energy, smart grids and networks, NetZero, energy selection, energy-saving, emissions estimation/monitoring, fault detection, batteries, buildings, fuels, wind power, smart energy systems, lighting, solar photovoltaic power, heating systems, fuel cells, energy prices, biofuels, power prediction, safety, security, energy theft, performance, production, energy management, Internet of Things (IoT), smart cities, facility maintenance (including mobility and transportation), renewable energies, and nuclear and other energy wastes management are among the challenging applications of prediction models, and are relevant to this Special Issue. As a response to the recent advancements in this domain, the objective of this collection is to present notable methods and applications of prediction models.

Prof. Dr. Annamária R. Várkonyi-Kóczy
Dr. Amir Mosavi
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. Energies 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 2600 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

energy systems
prediction models
machine learning
deep learning
deep reinforcement learning
hybrid and ensemble models
soft computing
big data
Internet of Things (IoT)
demand prediction
consumption prediction
load prediction
renewable energy production
artificial intelligence
explainable artificial intelligence (XAI)
smart grids
cost prediction
systems maintenance
short-term and long-term prediction models
energy performance
solar energy prediction
wind energy prediction
building energy
sustainable energy
anomaly detection
energy saving
energy price prediction
energy conversion and management
energy conversion efficiency
energy and climate change
smart urban energy systems
nature-inspired optimization algorithms

Published Papers (10 papers)

Download All Papers

Research

Jump to: Review

16 pages, 2375 KiB

Open AccessArticle

Hierarchical Diagnostics and Risk Assessment for Energy Supply in Military Vehicles

by Péter Földesi, László T. Kóczy, Ferenc Szauter, Dániel Csikor and Szabolcs Kocsis Szürke

Energies 2022, 15(13), 4791; https://doi.org/10.3390/en15134791 - 29 Jun 2022

Cited by 3 | Viewed by 1611

Abstract

Hybrid vehicles are gaining increasing global prominence, especially in the military, where unexpected breakdowns or even power deficits are not only associated with greater expense but can also cost the lives of military personnel. In some cases, it is extremely important that all battery cells and modules deliver the specified amount of capacity. Therefore, it is recommended to introduce a new measurement line of rapid diagnostics before deployment, in addition to the usual procedures. Using the results of rapid testing, we recommend the introduction of a hierarchical three-step diagnostics and assessment procedure. In this procedure, the key factor is the building up of a hierarchical tree-structured fuzzy signature that expresses the partial interdependence or redundancy of the uncertain descriptors obtained from the rapid tests. The fuzzy signature structure has two main important components: the tree structure itself, and the aggregations assigned to the internal nodes. The fuzzy signatures that are thus determined synthesize the results from the regular maintenance data, as well as the effects of the previous operating conditions and the actual state of the battery under examination; a signature that is established this way can be evaluated by “executing the instructions” coded into the aggregations. Based on the single fuzzy membership degree calculated for the root of the signature, an overall decision can be made concerning the general condition of the batteries. Full article

(This article belongs to the Special Issue Machine Learning Prediction Models in Energy Systems)

► Show Figures

Figure 1

24 pages, 2690 KiB

Open AccessArticle

Workforce Planning Framework for a Mobile Call Center Considering a Special Event

by Thanyawan Chanpanit and Apinanthana Udomsakdigool

Energies 2022, 15(4), 1551; https://doi.org/10.3390/en15041551 - 19 Feb 2022

Viewed by 1779

Abstract

Workforce planning is essential in today’s business management. If an organization can find and keep enough staff who have the right values, then they can provide high-quality service. This paper presents a workforce planning framework for selecting the best forecasting model in order to provide minimum wage and computer electricity costs for a mobile call center during the Songkran festival event, and to optimize workforce planning. The framework is constructed with four main steps: a study of a separate period; the separation of models with different data types; the simulation of models under different service levels to determine the number of customers waiting in a call center; and the evaluation of the models. The results from the proposed framework presented the best forecasting method and the optimal workforce plan. It is clear that this approach can assist in systematically selecting the best forecasting model. In addition, a workforce planner can use this framework to support workforce planning and cost evaluation in other event periods. Full article

(This article belongs to the Special Issue Machine Learning Prediction Models in Energy Systems)

► Show Figures

Figure 1

37 pages, 10947 KiB

Open AccessArticle

Design of Ensemble Forecasting Models for Home Energy Management Systems

by Karol Bot, Samira Santos, Inoussa Laouali, Antonio Ruano and Maria da Graça Ruano

Energies 2021, 14(22), 7664; https://doi.org/10.3390/en14227664 - 16 Nov 2021

Cited by 18 | Viewed by 2848

Abstract

The increasing levels of energy consumption worldwide is raising issues with respect to surpassing supply limits, causing severe effects on the environment, and the exhaustion of energy resources. Buildings are one of the most relevant sectors in terms of energy consumption; as such, efficient Home or Building Management Systems are an important topic of research. This study discusses the use of ensemble techniques in order to improve the performance of artificial neural networks models used for energy forecasting in residential houses. The case study is a residential house, located in Portugal, that is equipped with PV generation and battery storage and controlled by a Home Energy Management System (HEMS). It has been shown that the ensemble forecasting results are superior to single selected models, which were already excellent. A simple procedure was proposed for selecting the models to be used in the ensemble, together with a heuristic to determine the number of models. Full article

(This article belongs to the Special Issue Machine Learning Prediction Models in Energy Systems)

► Show Figures

Figure 1

17 pages, 2500 KiB

Open AccessArticle

Deep Learning-Based Approaches to Optimize the Electricity Contract Capacity Problem for Commercial Customers

by Rafik Nafkha, Tomasz Ząbkowski and Krzysztof Gajowniczek

Energies 2021, 14(8), 2181; https://doi.org/10.3390/en14082181 - 14 Apr 2021

Cited by 3 | Viewed by 1552

Abstract

The electricity tariffs available to customers in Poland depend on the connection voltage level and contracted capacity, which reflect the customer demand profile. Therefore, before connecting to the power grid, each consumer declares the demand for maximum power. This amount, referred to as the contracted capacity, is used by the electricity provider to assign the proper connection type to the power grid, including the size of the security breaker. Maximum power is also the basis for calculating fixed charges for electricity consumption, which is controlled and metered through peak meters. If the peak demand exceeds the contracted capacity, a penalty charge is applied to the exceeded amount, which is up to ten times the basic rate. In this article, we present several solutions for entrepreneurs based on the implementation of two-stage and deep learning approaches to predict maximal load values and the moments of exceeding the contracted capacity in the short term, i.e., up to one month ahead. The forecast is further used to optimize the capacity volume to be contracted in the following month to minimize network charge for exceeding the contracted level. As confirmed experimentally with two datasets, the application of a multiple output forecast artificial neural network model and a genetic algorithm (two-stage approach) for load optimization delivers significant benefits to customers. As an alternative, the same benefit is delivered with a deep learning architecture (hybrid approach) to predict the maximal capacity demands and, simultaneously, to determine the optimal capacity contract. Full article

(This article belongs to the Special Issue Machine Learning Prediction Models in Energy Systems)

► Show Figures

Figure 1

16 pages, 5255 KiB

Open AccessArticle

Machine Learning-Based Predictive Modelling of Biodiesel Production—A Comparative Perspective

by Krishna Kumar Gupta, Kanak Kalita, Ranjan Kumar Ghadai, Manickam Ramachandran and Xiao-Zhi Gao

Energies 2021, 14(4), 1122; https://doi.org/10.3390/en14041122 - 20 Feb 2021

Cited by 43 | Viewed by 2558

Abstract

Owing to the ever-growing impetus towards the development of eco-friendly and low carbon footprint energy solutions, biodiesel production and usage have been the subject of tremendous research efforts. The biodiesel production process is driven by several process parameters, which must be maintained at optimum levels to ensure high productivity. Since biodiesel productivity and quality are also dependent on the various raw materials involved in transesterification, physical experiments are necessary to make any estimation regarding them. However, a brute force approach of carrying out physical experiments until the optimal process parameters have been achieved will not succeed, due to a large number of process parameters and the underlying non-linear relation between the process parameters and responses. In this regard, a machine learning-based prediction approach is used in this paper to quantify the response features of the biodiesel production process as a function of the process parameters. Three powerful machine learning algorithms—linear regression, random forest regression and AdaBoost regression are comprehensively studied in this work. Furthermore, two separate examples—one involving biodiesel yield, the other regarding biodiesel free fatty acid conversion percentage—are illustrated. It is seen that both random forest regression and AdaBoost regression can achieve high accuracy in predictive modelling of biodiesel yield and free fatty acid conversion percentage. However, AdaBoost may be a more suitable approach for biodiesel production modelling, as it achieves the best accuracy amongst the tested algorithms. Moreover, AdaBoost can be more quickly deployed, as it was seen to be insensitive to number of regressors used. Full article

(This article belongs to the Special Issue Machine Learning Prediction Models in Energy Systems)

► Show Figures

Figure 1

15 pages, 765 KiB

Open AccessArticle

Application of Support Vector Machine Modeling for the Rapid Seismic Hazard Safety Evaluation of Existing Buildings

by Ehsan Harirchian, Tom Lahmer, Vandana Kumari and Kirti Jadhav

Energies 2020, 13(13), 3340; https://doi.org/10.3390/en13133340 - 30 Jun 2020

Cited by 25 | Viewed by 4129

Abstract

The economic losses from earthquakes tend to hit the national economy considerably; therefore, models that are capable of estimating the vulnerability and losses of future earthquakes are highly consequential for emergency planners with the purpose of risk mitigation. This demands a mass prioritization filtering of structures to identify vulnerable buildings for retrofitting purposes. The application of advanced structural analysis on each building to study the earthquake response is impractical due to complex calculations, long computational time, and exorbitant cost. This exhibits the need for a fast, reliable, and rapid method, commonly known as Rapid Visual Screening (RVS). The method serves as a preliminary screening platform, using an optimum number of seismic parameters of the structure and predefined output damage states. In this study, the efficacy of the Machine Learning (ML) application in damage prediction through a Support Vector Machine (SVM) model as the damage classification technique has been investigated. The developed model was trained and examined based on damage data from the 1999 Düzce Earthquake in Turkey, where the building’s data consists of 22 performance modifiers that have been implemented with supervised machine learning. Full article

(This article belongs to the Special Issue Machine Learning Prediction Models in Energy Systems)

► Show Figures

Graphical abstract

19 pages, 4509 KiB

Open AccessArticle

Modeling Nearly Zero Energy Buildings for Sustainable Development in Rural Areas

by Reza Khakian, Mehrdad Karimimoshaver, Farshid Aram, Soghra Zoroufchi Benis, Amir Mosavi and Annamaria R. Varkonyi-Koczy

Energies 2020, 13(10), 2593; https://doi.org/10.3390/en13102593 - 20 May 2020

Cited by 21 | Viewed by 3685

Abstract

The energy performance of buildings and energy-saving measures have been widely investigated in recent years. However, little attention has been paid to buildings located in rural areas. The aim of this study is to assess the energy performance of two-story residential buildings located in the mountainous village of Palangan in Iran and to evaluate the impact of multiple parameters, namely building orientation, window-to-wall ratio (WWR), glazing type, shading devices, and insulation, on its energy performance. To attain a nearly zero energy building design in rural areas, the building is equipped with photovoltaic modules. The proposed building design is then economically evaluated to ensure its viability. The findings indicate that an energy saving of 29% can be achieved compared to conventional buildings, and over 22 MWh of electricity can be produced on an annual basis. The payback period is assessed at 21.7 years. However, energy subsidies are projected to be eliminated in the near future, which in turn may reduce the payback period. Full article

(This article belongs to the Special Issue Machine Learning Prediction Models in Energy Systems)

► Show Figures

Figure 1

16 pages, 1315 KiB

Open AccessArticle

Earthquake Hazard Safety Assessment of Existing Buildings Using Optimized Multi-Layer Perceptron Neural Network

by Ehsan Harirchian, Tom Lahmer and Shahla Rasulzade

Energies 2020, 13(8), 2060; https://doi.org/10.3390/en13082060 - 20 Apr 2020

Cited by 33 | Viewed by 4039

Abstract

The latest earthquakes have proven that several existing buildings, particularly in developing countries, are not secured from damages of earthquake. A variety of statistical and machine-learning approaches have been proposed to identify vulnerable buildings for the prioritization of retrofitting. The present work aims to investigate earthquake susceptibility through the combination of six building performance variables that can be used to obtain an optimal prediction of the damage state of reinforced concrete buildings using artificial neural network (ANN). In this regard, a multi-layer perceptron network is trained and optimized using a database of 484 damaged buildings from the Düzce earthquake in Turkey. The results demonstrate the feasibility and effectiveness of the selected ANN approach to classify concrete structural damage that can be used as a preliminary assessment technique to identify vulnerable buildings in disaster risk-management programs. Full article

(This article belongs to the Special Issue Machine Learning Prediction Models in Energy Systems)

► Show Figures

Graphical abstract

22 pages, 3360 KiB

Open AccessArticle

Intelligent Road Inspection with Advanced Machine Learning; Hybrid Prediction Models for Smart Mobility and Transportation Maintenance Systems

by Nader Karballaeezadeh, Farah Zaremotekhases, Shahaboddin Shamshirband, Amir Mosavi, Narjes Nabipour, Peter Csiba and Annamária R. Várkonyi-Kóczy

Energies 2020, 13(7), 1718; https://doi.org/10.3390/en13071718 - 04 Apr 2020

Cited by 38 | Viewed by 5628

Abstract

Prediction models in mobility and transportation maintenance systems have been dramatically improved by using machine learning methods. This paper proposes novel machine learning models for an intelligent road inspection. The traditional road inspection systems based on the pavement condition index (PCI) are often associated with the critical safety, energy and cost issues. Alternatively, the proposed models utilize surface deflection data from falling weight deflectometer (FWD) tests to predict the PCI. Machine learning methods are the single multi-layer perceptron (MLP) and radial basis function (RBF) neural networks as well as their hybrids, i.e., Levenberg–Marquardt (MLP-LM), scaled conjugate gradient (MLP-SCG), imperialist competitive (RBF-ICA), and genetic algorithms (RBF-GA). Furthermore, the committee machine intelligent systems (CMIS) method was adopted to combine the results and improve the accuracy of the modeling. The results of the analysis have been verified through using four criteria of average percent relative error (APRE), average absolute percent relative error (AAPRE), root mean square error (RMSE) and standard error (SE). The CMIS model outperforms other models with the promising results of APRE = 2.3303, AAPRE = 11.6768, RMSE = 12.0056 and SD = 0.0210. Full article

(This article belongs to the Special Issue Machine Learning Prediction Models in Energy Systems)

► Show Figures

Figure 1

Review

Jump to: Research

26 pages, 1667 KiB

Open AccessEditor’s ChoiceReview

A Review of Deep Learning Techniques for Forecasting Energy Use in Buildings

by Jason Runge and Radu Zmeureanu

Energies 2021, 14(3), 608; https://doi.org/10.3390/en14030608 - 25 Jan 2021

Cited by 51 | Viewed by 6694

Abstract

Buildings account for a significant portion of our overall energy usage and associated greenhouse gas emissions. With the increasing concerns regarding climate change, there are growing needs for energy reduction and increasing our energy efficiency. Forecasting energy use plays a fundamental role in building energy planning, management and optimization. The most common approaches for building energy forecasting include physics and data-driven models. Among the data-driven models, deep learning techniques have begun to emerge in recent years due to their: improved abilities in handling large amounts of data, feature extraction characteristics, and improved abilities in modelling nonlinear phenomena. This paper provides an extensive review of deep learning-based techniques applied to forecasting the energy use in buildings to explore its effectiveness and application potential. First, we present a summary of published literature reviews followed by an overview of deep learning-based definitions and techniques. Next, we present a breakdown of current trends identified in published research along with a discussion of how deep learning-based models have been applied for feature extraction and forecasting. Finally, the review concludes with current challenges faced and some potential future research directions. Full article

(This article belongs to the Special Issue Machine Learning Prediction Models in Energy Systems)

► Show Figures