Forecasting Electricity Demand by Neural Networks and Definition of Inputs by Multi-Criteria Analysis
The planning of efficient policies based on forecasting electricity demand is essential to guarantee the continuity of energy supply for consumers. Some techniques for forecasting electricity demand have used specific procedures to define input variables, which can be particular to each case study....
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/16/4/1712 |
| _version_ | 1811153841443307520 |
|---|---|
| author | Carolina Deina João Lucas Ferreira dos Santos Lucas Henrique Biuk Mauro Lizot Attilio Converti Hugo Valadares Siqueira Flavio Trojan |
| author_facet | Carolina Deina João Lucas Ferreira dos Santos Lucas Henrique Biuk Mauro Lizot Attilio Converti Hugo Valadares Siqueira Flavio Trojan |
| author_sort | Carolina Deina |
| collection | DOAJ |
| description | The planning of efficient policies based on forecasting electricity demand is essential to guarantee the continuity of energy supply for consumers. Some techniques for forecasting electricity demand have used specific procedures to define input variables, which can be particular to each case study. However, the definition of independent and casual variables is still an issue to be explored. There is a lack of models that could help the selection of independent variables, based on correlate criteria and level of importance integrated with artificial networks, which could directly impact the forecasting quality. This work presents a model that integrates a multi-criteria approach which provides the selection of relevant independent variables and artificial neural networks to forecast the electricity demand in countries. It provides to consider the particularities of each application. To demonstrate the applicability of the model a time series of electricity consumption from a southern region of Brazil was used. The dependent inputs used by the neural networks were selected using a traditional method called Wrapper. As a result of this application, with the multi-criteria ELECTRE I method was possible to recognize temperature and average evaporation as explanatory variables. When the variables selected by the multi-criteria approach were included in the predictive models, were observed more consistent results together with artificial neural networks, better than the traditional linear models. The Radial Basis Function Networks and Extreme Learning Machines stood out as potential techniques to be used integrated with a multi-criteria method to better perform the forecasting. |
| first_indexed | 2024-03-11T08:53:31Z |
| format | Article |
| id | doaj.art-18391b69519249f4beaa9bdfc5ce49eb |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-11T08:53:31Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-18391b69519249f4beaa9bdfc5ce49eb2023-11-16T20:16:44ZengMDPI AGEnergies1996-10732023-02-01164171210.3390/en16041712Forecasting Electricity Demand by Neural Networks and Definition of Inputs by Multi-Criteria AnalysisCarolina Deina0João Lucas Ferreira dos Santos1Lucas Henrique Biuk2Mauro Lizot3Attilio Converti4Hugo Valadares Siqueira5Flavio Trojan6Graduate Program in Industrial Engineering (PPGEP), Federal University of Rio Grande do Sul (UFRGS), Av. Paulo Gama, 110, Porto Alegre 90040-060, BrazilGraduate Program in Industrial Engineering (PPGEP), Federal University of Technology-Parana (UTFPR), Rua Doutor Washington Subtil Chueire, 330, Ponta Grossa 84017-220, BrazilGraduate Program in Electrical Engineering (PPGEE), Federal University of Technology-Parana (UTFPR), Rua Doutor Washington Subtil Chueire, 330, Ponta Grossa 84017-220, BrazilDepartment of General and Applied Administration (DAGA), Federal University of Parana (UFPR), Avenue Prefeito Lothário Meissner, 632, Jardim Botânico 80210-170, BrazilDepartment of Civil, Chemical and Environmental Engineering, University of Genoa, Pole of Chemical Engineering, Via Opera Pia 15, 15145 Genoa, ItalyGraduate Program in Industrial Engineering (PPGEP), Federal University of Technology-Parana (UTFPR), Rua Doutor Washington Subtil Chueire, 330, Ponta Grossa 84017-220, BrazilGraduate Program in Industrial Engineering (PPGEP), Federal University of Technology-Parana (UTFPR), Rua Doutor Washington Subtil Chueire, 330, Ponta Grossa 84017-220, BrazilThe planning of efficient policies based on forecasting electricity demand is essential to guarantee the continuity of energy supply for consumers. Some techniques for forecasting electricity demand have used specific procedures to define input variables, which can be particular to each case study. However, the definition of independent and casual variables is still an issue to be explored. There is a lack of models that could help the selection of independent variables, based on correlate criteria and level of importance integrated with artificial networks, which could directly impact the forecasting quality. This work presents a model that integrates a multi-criteria approach which provides the selection of relevant independent variables and artificial neural networks to forecast the electricity demand in countries. It provides to consider the particularities of each application. To demonstrate the applicability of the model a time series of electricity consumption from a southern region of Brazil was used. The dependent inputs used by the neural networks were selected using a traditional method called Wrapper. As a result of this application, with the multi-criteria ELECTRE I method was possible to recognize temperature and average evaporation as explanatory variables. When the variables selected by the multi-criteria approach were included in the predictive models, were observed more consistent results together with artificial neural networks, better than the traditional linear models. The Radial Basis Function Networks and Extreme Learning Machines stood out as potential techniques to be used integrated with a multi-criteria method to better perform the forecasting.https://www.mdpi.com/1996-1073/16/4/1712electricity demandmulti-criteria forecasting modeldependent variableartificial neural networksforecasting models |
| spellingShingle | Carolina Deina João Lucas Ferreira dos Santos Lucas Henrique Biuk Mauro Lizot Attilio Converti Hugo Valadares Siqueira Flavio Trojan Forecasting Electricity Demand by Neural Networks and Definition of Inputs by Multi-Criteria Analysis Energies electricity demand multi-criteria forecasting model dependent variable artificial neural networks forecasting models |
| title | Forecasting Electricity Demand by Neural Networks and Definition of Inputs by Multi-Criteria Analysis |
| title_full | Forecasting Electricity Demand by Neural Networks and Definition of Inputs by Multi-Criteria Analysis |
| title_fullStr | Forecasting Electricity Demand by Neural Networks and Definition of Inputs by Multi-Criteria Analysis |
| title_full_unstemmed | Forecasting Electricity Demand by Neural Networks and Definition of Inputs by Multi-Criteria Analysis |
| title_short | Forecasting Electricity Demand by Neural Networks and Definition of Inputs by Multi-Criteria Analysis |
| title_sort | forecasting electricity demand by neural networks and definition of inputs by multi criteria analysis |
| topic | electricity demand multi-criteria forecasting model dependent variable artificial neural networks forecasting models |
| url | https://www.mdpi.com/1996-1073/16/4/1712 |
| work_keys_str_mv | AT carolinadeina forecastingelectricitydemandbyneuralnetworksanddefinitionofinputsbymulticriteriaanalysis AT joaolucasferreiradossantos forecastingelectricitydemandbyneuralnetworksanddefinitionofinputsbymulticriteriaanalysis AT lucashenriquebiuk forecastingelectricitydemandbyneuralnetworksanddefinitionofinputsbymulticriteriaanalysis AT maurolizot forecastingelectricitydemandbyneuralnetworksanddefinitionofinputsbymulticriteriaanalysis AT attilioconverti forecastingelectricitydemandbyneuralnetworksanddefinitionofinputsbymulticriteriaanalysis AT hugovaladaressiqueira forecastingelectricitydemandbyneuralnetworksanddefinitionofinputsbymulticriteriaanalysis AT flaviotrojan forecastingelectricitydemandbyneuralnetworksanddefinitionofinputsbymulticriteriaanalysis |