A scoping review of deep neural networks for electric load forecasting
Abstract The increasing dependency on electricity and demand for renewable energy sources means that distributed system operators face new challenges in their grid. Accurate forecasts of electric load can solve these challenges. In recent years deep neural networks have become increasingly popular i...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
SpringerOpen
2021-09-01
|
Series: | Energy Informatics |
Subjects: | |
Online Access: | https://doi.org/10.1186/s42162-021-00148-6 |
id |
doaj-7fcf19eb450249cbbb046e6b61eee86a |
---|---|
record_format |
Article |
spelling |
doaj-7fcf19eb450249cbbb046e6b61eee86a2021-09-26T11:16:03ZengSpringerOpenEnergy Informatics2520-89422021-09-014S211310.1186/s42162-021-00148-6A scoping review of deep neural networks for electric load forecastingNicolai Bo Vanting0Zheng Ma1Bo Nørregaard Jørgensen2Department of Mathematics and Computer Science, University of Southern DenmarkCenter for Health Informatics, the Maersk Mc-Kinney Moller Institute, University of Southern DenmarkCenter for Energy Informatics, the Maersk Mc-Kinney Moller Institute, University of Southern DenmarkAbstract The increasing dependency on electricity and demand for renewable energy sources means that distributed system operators face new challenges in their grid. Accurate forecasts of electric load can solve these challenges. In recent years deep neural networks have become increasingly popular in research, and researchers have carried out many experiments to create the most accurate deep learning models. Players in the energy sector can exploit the increasing amount of energy-related data collected from smart meters to improve the grid’s operating quality. This review investigates state-of-the-art methodologies relating to energy load forecasting using deep neural networks. A thorough literature search is conducted, which outlines and analyses essential aspects regarding deep learning load forecasts in the energy domain. The literature suggests two main perspectives: demand-side management and grid control on the supply side. Each perspective has multiple applications with its challenges to achieve accurate forecasts; households, buildings, and grids. This paper recommends using a hybrid deep learning multivariate model consisting of a convolutional and recurrent neural network based on the scoping review. The suggested input variables should be historical consumption, weather, and day features. Combining the convolutional and recurrent networks ensures that the model learns as many repeating patterns and features in the data as possible.https://doi.org/10.1186/s42162-021-00148-6Load forecastingDeep learningArtificial neural networkScoping reviewEnergy sector |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Nicolai Bo Vanting Zheng Ma Bo Nørregaard Jørgensen |
spellingShingle |
Nicolai Bo Vanting Zheng Ma Bo Nørregaard Jørgensen A scoping review of deep neural networks for electric load forecasting Energy Informatics Load forecasting Deep learning Artificial neural network Scoping review Energy sector |
author_facet |
Nicolai Bo Vanting Zheng Ma Bo Nørregaard Jørgensen |
author_sort |
Nicolai Bo Vanting |
title |
A scoping review of deep neural networks for electric load forecasting |
title_short |
A scoping review of deep neural networks for electric load forecasting |
title_full |
A scoping review of deep neural networks for electric load forecasting |
title_fullStr |
A scoping review of deep neural networks for electric load forecasting |
title_full_unstemmed |
A scoping review of deep neural networks for electric load forecasting |
title_sort |
scoping review of deep neural networks for electric load forecasting |
publisher |
SpringerOpen |
series |
Energy Informatics |
issn |
2520-8942 |
publishDate |
2021-09-01 |
description |
Abstract The increasing dependency on electricity and demand for renewable energy sources means that distributed system operators face new challenges in their grid. Accurate forecasts of electric load can solve these challenges. In recent years deep neural networks have become increasingly popular in research, and researchers have carried out many experiments to create the most accurate deep learning models. Players in the energy sector can exploit the increasing amount of energy-related data collected from smart meters to improve the grid’s operating quality. This review investigates state-of-the-art methodologies relating to energy load forecasting using deep neural networks. A thorough literature search is conducted, which outlines and analyses essential aspects regarding deep learning load forecasts in the energy domain. The literature suggests two main perspectives: demand-side management and grid control on the supply side. Each perspective has multiple applications with its challenges to achieve accurate forecasts; households, buildings, and grids. This paper recommends using a hybrid deep learning multivariate model consisting of a convolutional and recurrent neural network based on the scoping review. The suggested input variables should be historical consumption, weather, and day features. Combining the convolutional and recurrent networks ensures that the model learns as many repeating patterns and features in the data as possible. |
topic |
Load forecasting Deep learning Artificial neural network Scoping review Energy sector |
url |
https://doi.org/10.1186/s42162-021-00148-6 |
work_keys_str_mv |
AT nicolaibovanting ascopingreviewofdeepneuralnetworksforelectricloadforecasting AT zhengma ascopingreviewofdeepneuralnetworksforelectricloadforecasting AT bonørregaardjørgensen ascopingreviewofdeepneuralnetworksforelectricloadforecasting AT nicolaibovanting scopingreviewofdeepneuralnetworksforelectricloadforecasting AT zhengma scopingreviewofdeepneuralnetworksforelectricloadforecasting AT bonørregaardjørgensen scopingreviewofdeepneuralnetworksforelectricloadforecasting |
_version_ |
1716868099579314176 |