Energy Forecasting: A Comprehensive Review of Techniques and Technologies
Distribution System Operators (DSOs) and Aggregators benefit from novel energy forecasting (EF) approaches. Improved forecasting accuracy may make it easier to deal with energy imbalances between generation and consumption. It also helps operations such as Demand Response Management (DRM) in Smart G...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/17/7/1662 |
| _version_ | 1797212623489466368 |
|---|---|
| author | Aristeidis Mystakidis Paraskevas Koukaras Nikolaos Tsalikidis Dimosthenis Ioannidis Christos Tjortjis |
| author_facet | Aristeidis Mystakidis Paraskevas Koukaras Nikolaos Tsalikidis Dimosthenis Ioannidis Christos Tjortjis |
| author_sort | Aristeidis Mystakidis |
| collection | DOAJ |
| description | Distribution System Operators (DSOs) and Aggregators benefit from novel energy forecasting (EF) approaches. Improved forecasting accuracy may make it easier to deal with energy imbalances between generation and consumption. It also helps operations such as Demand Response Management (DRM) in Smart Grid (SG) architectures. For utilities, companies, and consumers to manage energy resources effectively and make educated decisions about energy generation and consumption, EF is essential. For many applications, such as Energy Load Forecasting (ELF), Energy Generation Forecasting (EGF), and grid stability, accurate EF is crucial. The state of the art in EF is examined in this literature review, emphasising cutting-edge forecasting techniques and technologies and their significance for the energy industry. It gives an overview of statistical, Machine Learning (ML)-based, and Deep Learning (DL)-based methods and their ensembles that form the basis of EF. Various time-series forecasting techniques are explored, including sequence-to-sequence, recursive, and direct forecasting. Furthermore, evaluation criteria are reported, namely, relative and absolute metrics such as Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), Coefficient of Determination (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula>), and Coefficient of Variation of the Root Mean Square Error (CVRMSE), as well as the Execution Time (ET), which are used to gauge prediction accuracy. Finally, an overall step-by-step standard methodology often utilised in EF problems is presented. |
| first_indexed | 2024-04-24T10:45:20Z |
| format | Article |
| id | doaj.art-3d934c72ab4244349dc72321f5d03cae |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-04-24T10:45:20Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-3d934c72ab4244349dc72321f5d03cae2024-04-12T13:18:00ZengMDPI AGEnergies1996-10732024-03-01177166210.3390/en17071662Energy Forecasting: A Comprehensive Review of Techniques and TechnologiesAristeidis Mystakidis0Paraskevas Koukaras1Nikolaos Tsalikidis2Dimosthenis Ioannidis3Christos Tjortjis4School of Science and Technology, International Hellenic University, 14th km Thessaloniki-Moudania, 57001 Thessaloniki, GreeceSchool of Science and Technology, International Hellenic University, 14th km Thessaloniki-Moudania, 57001 Thessaloniki, GreeceInformation Technologies Institute, Centre for Research & Technology, 57001 Thessaloniki, GreeceInformation Technologies Institute, Centre for Research & Technology, 57001 Thessaloniki, GreeceSchool of Science and Technology, International Hellenic University, 14th km Thessaloniki-Moudania, 57001 Thessaloniki, GreeceDistribution System Operators (DSOs) and Aggregators benefit from novel energy forecasting (EF) approaches. Improved forecasting accuracy may make it easier to deal with energy imbalances between generation and consumption. It also helps operations such as Demand Response Management (DRM) in Smart Grid (SG) architectures. For utilities, companies, and consumers to manage energy resources effectively and make educated decisions about energy generation and consumption, EF is essential. For many applications, such as Energy Load Forecasting (ELF), Energy Generation Forecasting (EGF), and grid stability, accurate EF is crucial. The state of the art in EF is examined in this literature review, emphasising cutting-edge forecasting techniques and technologies and their significance for the energy industry. It gives an overview of statistical, Machine Learning (ML)-based, and Deep Learning (DL)-based methods and their ensembles that form the basis of EF. Various time-series forecasting techniques are explored, including sequence-to-sequence, recursive, and direct forecasting. Furthermore, evaluation criteria are reported, namely, relative and absolute metrics such as Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), Coefficient of Determination (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula>), and Coefficient of Variation of the Root Mean Square Error (CVRMSE), as well as the Execution Time (ET), which are used to gauge prediction accuracy. Finally, an overall step-by-step standard methodology often utilised in EF problems is presented.https://www.mdpi.com/1996-1073/17/7/1662forecastingtime-series analysisenergy loadmachine learningartificial neural networksstatistical methods |
| spellingShingle | Aristeidis Mystakidis Paraskevas Koukaras Nikolaos Tsalikidis Dimosthenis Ioannidis Christos Tjortjis Energy Forecasting: A Comprehensive Review of Techniques and Technologies Energies forecasting time-series analysis energy load machine learning artificial neural networks statistical methods |
| title | Energy Forecasting: A Comprehensive Review of Techniques and Technologies |
| title_full | Energy Forecasting: A Comprehensive Review of Techniques and Technologies |
| title_fullStr | Energy Forecasting: A Comprehensive Review of Techniques and Technologies |
| title_full_unstemmed | Energy Forecasting: A Comprehensive Review of Techniques and Technologies |
| title_short | Energy Forecasting: A Comprehensive Review of Techniques and Technologies |
| title_sort | energy forecasting a comprehensive review of techniques and technologies |
| topic | forecasting time-series analysis energy load machine learning artificial neural networks statistical methods |
| url | https://www.mdpi.com/1996-1073/17/7/1662 |
| work_keys_str_mv | AT aristeidismystakidis energyforecastingacomprehensivereviewoftechniquesandtechnologies AT paraskevaskoukaras energyforecastingacomprehensivereviewoftechniquesandtechnologies AT nikolaostsalikidis energyforecastingacomprehensivereviewoftechniquesandtechnologies AT dimosthenisioannidis energyforecastingacomprehensivereviewoftechniquesandtechnologies AT christostjortjis energyforecastingacomprehensivereviewoftechniquesandtechnologies |