Machine-learning methods for integrated renewable power generation: A comparative study of artificial neural networks, support vector regression, and Gaussian Process Regression

File Description SizeFormat 
Manuscript.pdfFile embargoed until 10 April 202010.25 MBAdobe PDF    Request a copy
Title: Machine-learning methods for integrated renewable power generation: A comparative study of artificial neural networks, support vector regression, and Gaussian Process Regression
Authors: Sharifzadeh, M
Sikinioti-Lock, A
Shah, N
Item Type: Journal Article
Abstract: Renewable energy from wind and solar resources can contribute significantly to the decarbonisation of the conventionally fossil-driven electricity grid. However, their seamless integration with the grid poses significant challenges due to their intermittent generation patterns, which is intensified by the existing uncertainties and fluctuations from the demand side. A resolution is increasing energy storage and standby power generation which results in economic losses. Alternatively, enhancing the predictability of wind and solar energy as well as demand enables replacing such expensive hardware with advanced control and optimization systems. The present research contribution establishes consistent sets of data and develops data-driven models through machine-learning techniques. The aim is to quantify the uncertainties in the electricity grid and examine the predictability of their behaviour. The predictive methods that were selected included conventional artificial neural networks (ANN), support vector regression (SVR) and Gaussian process regression (GPR). For each method, a sensitivity analysis was conducted with the aim of tuning its parameters as optimally as possible. The next step was to train and validate each method with various datasets (wind, solar, demand). Finally, a predictability analysis was performed in order to ascertain how the models would respond when the prediction time horizon increases. All models were found capable of predicting wind and solar power, but only the neural networks were successful for the electricity demand. Considering the dynamics of the electricity grid, it was observed that the prediction process for renewable wind and solar power generation, and electricity demand was fast and accurate enough to effectively replace the alternative electricity storage and standby capacity.
Issue Date: 1-Jul-2019
Date of Acceptance: 19-Mar-2019
URI: http://hdl.handle.net/10044/1/69909
DOI: https://dx.doi.org/10.1016/j.rser.2019.03.040
ISSN: 1364-0321
Publisher: Elsevier
Start Page: 513
End Page: 538
Journal / Book Title: Renewable and Sustainable Energy Reviews
Volume: 108
Copyright Statement: © 2019 Elsevier Ltd. All rights reserved. This manuscript is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International Licence http://creativecommons.org/licenses/by-nc-nd/4.0/
Sponsor/Funder: Engineering & Physical Science Research Council (E
Funder's Grant Number: EP/P024807/1
Keywords: Science & Technology
Technology
Green & Sustainable Science & Technology
Energy & Fuels
Science & Technology - Other Topics
Machine-learning
Big data
Renewable wind and solar power
Electricity demand
Artificial neural networks (ANN)
Support vector regression (SVR)
Gaussian process regression (GPR)
TERM WIND-SPEED
VARIATIONAL MODE DECOMPOSITION
WAVELET PACKET DECOMPOSITION
ELECTRICITY PRICE
SOLAR-RADIATION
HYBRID MODEL
TIME-SERIES
SMART GRIDS
FORECASTING TECHNIQUES
LSTM NETWORK
09 Engineering
Energy
Publication Status: Published
Embargo Date: 2020-04-10
Online Publication Date: 2019-04-10
Appears in Collections:Centre for Environmental Policy
Chemical Engineering
Faculty of Natural Sciences



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commonsx