Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.5
3.2
Journals
Energies
Special Issues
Energy Consumption Forecasting Using Machine Learning
energies-logo
Submit to Energies Review for Energies Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Energy Consumption Forecasting Using Machine Learning

A special issue of Energies (ISSN 1996-1073). This special issue belongs to the section "K: State-of-the-Art Energy Related Technologies".

Deadline for manuscript submissions: closed (30 June 2022) | Viewed by 9573

Special Issue Editor

Dr. Sasan Barak

E-Mail Website
Guest Editor
Southampton Business School, University of Southampton, Southampton SO16 7PP, UK
Interests: machine learning; artificial intelligence; energy forecasting; deep learning
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Energy is vital to the development of any country. In recent decades, as living standards have risen, the global energy demand has increased exponentially, and the problem of energy shortages has become increasingly apparent. Therefore, an excellent energy supply management solution is essential. Energy supply management is based on region-specific forecasts of demand. Inaccurate forecasts of this demand not only lead to a significant amount of wasted energy but also higher operating costs for production.

Recent empirical studies have shown that using machine learning approaches combined with statistical learning methods can provide better performance than traditional statistical methods (Barak and Sadegh, 2016). For example, the hybrid of the recurrent neural network and exponential smoothing models by Smyl (2020) won first prize in the M4 time series forecasting competition (Makridakis, Spiliotis, and Assimakopoulos, 2018). Memarzadeh and Keynia (2021) combined wavelet transform with CNN and LSTM, respectively, and the results outperformed the single network model. Kim and Cho (2019) combined both CNN and LSTM neural networks in order to take advantage of their respective strengths.

Therefore, in this Special Issue, we would like to analyse the potential of using machine learning, especially deep learning models, and their improvement using statistical learning methods for energy forecasting.

The main challenge in energy forecasting is related to electricity data forecasting, but it can also concern green energy sources.

Dr. Sasan Barak
Guest Editor

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 forecasting
  • deep learning
  • machine learning
  • statistical learning
  • hybrid model

Published Papers (3 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

21 pages, 6843 KiB  
Article
An Hour-Ahead PV Power Forecasting Method Based on an RNN-LSTM Model for Three Different PV Plants
by Muhammad Naveed Akhter, Saad Mekhilef, Hazlie Mokhlis, Ziyad M. Almohaimeed, Munir Azam Muhammad, Anis Salwa Mohd Khairuddin, Rizwan Akram and Muhammad Majid Hussain
Energies 2022, 15(6), 2243; https://0-doi-org.brum.beds.ac.uk/10.3390/en15062243 - 18 Mar 2022
Cited by 42 | Viewed by 3299
Abstract
Incorporating solar energy into a grid necessitates an accurate power production forecast for photovoltaic (PV) facilities. In this research, output PV power was predicted at an hour ahead on yearly basis for three different PV plants based on polycrystalline (p-si), monocrystalline (m-si), and [...] Read more.
Incorporating solar energy into a grid necessitates an accurate power production forecast for photovoltaic (PV) facilities. In this research, output PV power was predicted at an hour ahead on yearly basis for three different PV plants based on polycrystalline (p-si), monocrystalline (m-si), and thin-film (a-si) technologies over a four-year period. Wind speed, module temperature, ambiance, and solar irradiation were among the input characteristics taken into account. Each PV plant power output was the output parameter. A deep learning method (RNN-LSTM) was developed and evaluated against existing techniques to forecast the PV output power of the selected PV plant. The proposed technique was compared with regression (GPR, GPR (PCA)), hybrid ANFIS (grid partitioning, subtractive clustering and FCM) and machine learning (ANN, SVR, SVR (PCA)) methods. Furthermore, different LSTM structures were also investigated, with recurrent neural networks (RNN) based on 2019 data to determine the best structure. The following parameters of prediction accuracy measure were considered: RMSE, MSE, MAE, correlation (r) and determination (R2) coefficients. In comparison to all other approaches, RNN-LSTM had higher prediction accuracy on the basis of minimum (RMSE and MSE) and maximum (r and R2). The p-si, m-si and a-si PV plants showed the lowest RMSE values of 26.85 W/m2, 19.78 W/m2 and 39.2 W/m2 respectively. Moreover, the proposed method was found to be robust and flexible in forecasting the output power of the three considered different photovoltaic plants. Full article
(This article belongs to the Special Issue Energy Consumption Forecasting Using Machine Learning)
►▼ Show Figures

Figure 1

19 pages, 5126 KiB  
Article
Prediction of Electric Buses Energy Consumption from Trip Parameters Using Deep Learning
by Teresa Pamuła and Danuta Pamuła
Energies 2022, 15(5), 1747; https://0-doi-org.brum.beds.ac.uk/10.3390/en15051747 - 26 Feb 2022
Cited by 13 | Viewed by 2252
Abstract
The energy demand of electric buses (EBs) is a very important parameter that should be considered by transport companies when introducing electric buses into the urban bus fleet. This article proposes a novel deep-learning-based model for predicting energy consumption of an electric bus [...] Read more.
The energy demand of electric buses (EBs) is a very important parameter that should be considered by transport companies when introducing electric buses into the urban bus fleet. This article proposes a novel deep-learning-based model for predicting energy consumption of an electric bus traveling in an urban area. The model addresses two important issues: accuracy and cost of prediction. The aim of the research was to develop the deep-learning-based prediction model, which requires only the data readily available to bus fleet operators, such as location of the bus stops (coordinates, altitude), route traveled, schedule, travel time between stops, and to find the most suitable type and configuration of neural network to evaluate the model. The developed prediction model was assessed with different types of deep neural networks using real data collected for several bus lines in a medium-sized city in Poland. Conducted research has shown that the deep learning network with autoencoders (DLNA) neural network allows for the most accurate energy consumption estimation of 93%. The proposed model can be used by public transport companies to plan driving schedules and energy management when introducing electric buses. Full article
(This article belongs to the Special Issue Energy Consumption Forecasting Using Machine Learning)
►▼ Show Figures

Figure 1

25 pages, 8667 KiB  
Article
Forecasting Solar Home System Customers’ Electricity Usage with a 3D Convolutional Neural Network to Improve Energy Access
by Vivien Kizilcec, Catalina Spataru, Aldo Lipani and Priti Parikh
Energies 2022, 15(3), 857; https://0-doi-org.brum.beds.ac.uk/10.3390/en15030857 - 25 Jan 2022
Cited by 4 | Viewed by 2559
Abstract
Off-grid technologies, such as solar home systems (SHS), offer the opportunity to alleviate global energy poverty, providing a cost-effective alternative to an electricity grid connection. However, there is a paucity of high-quality SHS electricity usage data and thus a limited understanding of consumers’ [...] Read more.
Off-grid technologies, such as solar home systems (SHS), offer the opportunity to alleviate global energy poverty, providing a cost-effective alternative to an electricity grid connection. However, there is a paucity of high-quality SHS electricity usage data and thus a limited understanding of consumers’ past and future usage patterns. This study addresses this gap by providing a rare large-scale analysis of real-time energy consumption data for SHS customers (n = 63,299) in Rwanda. Our results show that 70% of SHS users’ electricity usage decreased a year after their SHS was installed. This paper is novel in its application of a three-dimensional convolutional neural network (CNN) architecture for electricity load forecasting using time series data. It also marks the first time a CNN was used to predict SHS customers’ electricity consumption. The model forecasts individual households’ usage 24 h and seven days ahead, as well as an average week across the next three months. The last scenario derived the best performance with a mean squared error of 0.369. SHS companies could use these predictions to offer a tailored service to customers, including providing feedback information on their likely future usage and expenditure. The CNN could also aid load balancing for SHS based microgrids. Full article
(This article belongs to the Special Issue Energy Consumption Forecasting Using Machine Learning)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-3
Back to TopTop