Energy Consumption Forecasting for Smart Meters Using Extreme Learning Machine Ensemble
The employment of smart meters for energy consumption monitoring is essential for planning and management of power generation systems. In this context, forecasting energy consumption is a valuable asset for decision making, since it can improve the predictability of forthcoming demand to energy prov...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/23/8096 |
| _version_ | 1797507140972183552 |
|---|---|
| author | Paulo S. G. de Mattos Neto João F. L. de Oliveira Priscilla Bassetto Hugo Valadares Siqueira Luciano Barbosa Emilly Pereira Alves Manoel H. N. Marinho Guilherme Ferretti Rissi Fu Li |
| author_facet | Paulo S. G. de Mattos Neto João F. L. de Oliveira Priscilla Bassetto Hugo Valadares Siqueira Luciano Barbosa Emilly Pereira Alves Manoel H. N. Marinho Guilherme Ferretti Rissi Fu Li |
| author_sort | Paulo S. G. de Mattos Neto |
| collection | DOAJ |
| description | The employment of smart meters for energy consumption monitoring is essential for planning and management of power generation systems. In this context, forecasting energy consumption is a valuable asset for decision making, since it can improve the predictability of forthcoming demand to energy providers. In this work, we propose a data-driven ensemble that combines five single well-known models in the forecasting literature: a statistical linear autoregressive model and four artificial neural networks: (radial basis function, multilayer perceptron, extreme learning machines, and echo state networks). The proposed ensemble employs extreme learning machines as the combination model due to its simplicity, learning speed, and greater ability of generalization in comparison to other artificial neural networks. The experiments were conducted on real consumption data collected from a smart meter in a one-step-ahead forecasting scenario. The results using five different performance metrics demonstrate that our solution outperforms other statistical, machine learning, and ensembles models proposed in the literature. |
| first_indexed | 2024-03-10T04:44:23Z |
| format | Article |
| id | doaj.art-6380a8b316654711ab327ab144422e3a |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T04:44:23Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-6380a8b316654711ab327ab144422e3a2023-11-23T03:03:55ZengMDPI AGSensors1424-82202021-12-012123809610.3390/s21238096Energy Consumption Forecasting for Smart Meters Using Extreme Learning Machine EnsemblePaulo S. G. de Mattos Neto0João F. L. de Oliveira1Priscilla Bassetto2Hugo Valadares Siqueira3Luciano Barbosa4Emilly Pereira Alves5Manoel H. N. Marinho6Guilherme Ferretti Rissi7Fu Li8Centro de Informática, Universidade Federal de Pernambuco, Recife 50740-560, BrazilEscola Politécnica de Pernambuco, Universidade de Pernambuco, Recife 50720-001, BrazilGraduate Program in Industrial Engineering, Federal University of Technology—Paraná, Ponta Grossa 84017-220, BrazilGraduate Program in Industrial Engineering, Federal University of Technology—Paraná, Ponta Grossa 84017-220, BrazilCentro de Informática, Universidade Federal de Pernambuco, Recife 50740-560, BrazilEscola Politécnica de Pernambuco, Universidade de Pernambuco, Recife 50720-001, BrazilEscola Politécnica de Pernambuco, Universidade de Pernambuco, Recife 50720-001, BrazilCPFL Energia, Campinas, São Paulo 13087-397, BrazilCPFL Energia, Campinas, São Paulo 13087-397, BrazilThe employment of smart meters for energy consumption monitoring is essential for planning and management of power generation systems. In this context, forecasting energy consumption is a valuable asset for decision making, since it can improve the predictability of forthcoming demand to energy providers. In this work, we propose a data-driven ensemble that combines five single well-known models in the forecasting literature: a statistical linear autoregressive model and four artificial neural networks: (radial basis function, multilayer perceptron, extreme learning machines, and echo state networks). The proposed ensemble employs extreme learning machines as the combination model due to its simplicity, learning speed, and greater ability of generalization in comparison to other artificial neural networks. The experiments were conducted on real consumption data collected from a smart meter in a one-step-ahead forecasting scenario. The results using five different performance metrics demonstrate that our solution outperforms other statistical, machine learning, and ensembles models proposed in the literature.https://www.mdpi.com/1424-8220/21/23/8096energy consumptionsmart meteringforecastingBox and Jenkins modelsneural networksensembles |
| spellingShingle | Paulo S. G. de Mattos Neto João F. L. de Oliveira Priscilla Bassetto Hugo Valadares Siqueira Luciano Barbosa Emilly Pereira Alves Manoel H. N. Marinho Guilherme Ferretti Rissi Fu Li Energy Consumption Forecasting for Smart Meters Using Extreme Learning Machine Ensemble Sensors energy consumption smart metering forecasting Box and Jenkins models neural networks ensembles |
| title | Energy Consumption Forecasting for Smart Meters Using Extreme Learning Machine Ensemble |
| title_full | Energy Consumption Forecasting for Smart Meters Using Extreme Learning Machine Ensemble |
| title_fullStr | Energy Consumption Forecasting for Smart Meters Using Extreme Learning Machine Ensemble |
| title_full_unstemmed | Energy Consumption Forecasting for Smart Meters Using Extreme Learning Machine Ensemble |
| title_short | Energy Consumption Forecasting for Smart Meters Using Extreme Learning Machine Ensemble |
| title_sort | energy consumption forecasting for smart meters using extreme learning machine ensemble |
| topic | energy consumption smart metering forecasting Box and Jenkins models neural networks ensembles |
| url | https://www.mdpi.com/1424-8220/21/23/8096 |
| work_keys_str_mv | AT paulosgdemattosneto energyconsumptionforecastingforsmartmetersusingextremelearningmachineensemble AT joaofldeoliveira energyconsumptionforecastingforsmartmetersusingextremelearningmachineensemble AT priscillabassetto energyconsumptionforecastingforsmartmetersusingextremelearningmachineensemble AT hugovaladaressiqueira energyconsumptionforecastingforsmartmetersusingextremelearningmachineensemble AT lucianobarbosa energyconsumptionforecastingforsmartmetersusingextremelearningmachineensemble AT emillypereiraalves energyconsumptionforecastingforsmartmetersusingextremelearningmachineensemble AT manoelhnmarinho energyconsumptionforecastingforsmartmetersusingextremelearningmachineensemble AT guilhermeferrettirissi energyconsumptionforecastingforsmartmetersusingextremelearningmachineensemble AT fuli energyconsumptionforecastingforsmartmetersusingextremelearningmachineensemble |