Short-Term Forecasting of Electric Loads Using Nonlinear Autoregressive Artificial Neural Networks with Exogenous Vector Inputs
Short-term load forecasting is crucial for the operations planning of an electrical grid. Forecasting the next 24 h of electrical load in a grid allows operators to plan and optimize their resources. The purpose of this study is to develop a more accurate short-term load forecasting method utilizing...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2017-01-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1996-1073/10/1/40 |
| _version_ | 1811187870718754816 |
|---|---|
| author | Jaime Buitrago Shihab Asfour |
| author_facet | Jaime Buitrago Shihab Asfour |
| author_sort | Jaime Buitrago |
| collection | DOAJ |
| description | Short-term load forecasting is crucial for the operations planning of an electrical grid. Forecasting the next 24 h of electrical load in a grid allows operators to plan and optimize their resources. The purpose of this study is to develop a more accurate short-term load forecasting method utilizing non-linear autoregressive artificial neural networks (ANN) with exogenous multi-variable input (NARX). The proposed implementation of the network is new: the neural network is trained in open-loop using actual load and weather data, and then, the network is placed in closed-loop to generate a forecast using the predicted load as the feedback input. Unlike the existing short-term load forecasting methods using ANNs, the proposed method uses its own output as the input in order to improve the accuracy, thus effectively implementing a feedback loop for the load, making it less dependent on external data. Using the proposed framework, mean absolute percent errors in the forecast in the order of 1% have been achieved, which is a 30% improvement on the average error using feedforward ANNs, ARMAX and state space methods, which can result in large savings by avoiding commissioning of unnecessary power plants. The New England electrical load data are used to train and validate the forecast prediction. |
| first_indexed | 2024-04-11T14:09:54Z |
| format | Article |
| id | doaj.art-12a4ce10145c4718a629652b12a1fb84 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-04-11T14:09:54Z |
| publishDate | 2017-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-12a4ce10145c4718a629652b12a1fb842022-12-22T04:19:44ZengMDPI AGEnergies1996-10732017-01-011014010.3390/en10010040en10010040Short-Term Forecasting of Electric Loads Using Nonlinear Autoregressive Artificial Neural Networks with Exogenous Vector InputsJaime Buitrago0Shihab Asfour1University of Miami, Department of Industrial Engineering, 1251 Memorial Drive, 268 McArthur Engineering Building, Coral Gables, FL 33146, USAUniversity of Miami, Department of Industrial Engineering, 1251 Memorial Drive, 268 McArthur Engineering Building, Coral Gables, FL 33146, USAShort-term load forecasting is crucial for the operations planning of an electrical grid. Forecasting the next 24 h of electrical load in a grid allows operators to plan and optimize their resources. The purpose of this study is to develop a more accurate short-term load forecasting method utilizing non-linear autoregressive artificial neural networks (ANN) with exogenous multi-variable input (NARX). The proposed implementation of the network is new: the neural network is trained in open-loop using actual load and weather data, and then, the network is placed in closed-loop to generate a forecast using the predicted load as the feedback input. Unlike the existing short-term load forecasting methods using ANNs, the proposed method uses its own output as the input in order to improve the accuracy, thus effectively implementing a feedback loop for the load, making it less dependent on external data. Using the proposed framework, mean absolute percent errors in the forecast in the order of 1% have been achieved, which is a 30% improvement on the average error using feedforward ANNs, ARMAX and state space methods, which can result in large savings by avoiding commissioning of unnecessary power plants. The New England electrical load data are used to train and validate the forecast prediction.http://www.mdpi.com/1996-1073/10/1/40short-term load forecastingnonlinear autoregressive exogenous inputartificial neural networksclosed-loop forecasting |
| spellingShingle | Jaime Buitrago Shihab Asfour Short-Term Forecasting of Electric Loads Using Nonlinear Autoregressive Artificial Neural Networks with Exogenous Vector Inputs Energies short-term load forecasting nonlinear autoregressive exogenous input artificial neural networks closed-loop forecasting |
| title | Short-Term Forecasting of Electric Loads Using Nonlinear Autoregressive Artificial Neural Networks with Exogenous Vector Inputs |
| title_full | Short-Term Forecasting of Electric Loads Using Nonlinear Autoregressive Artificial Neural Networks with Exogenous Vector Inputs |
| title_fullStr | Short-Term Forecasting of Electric Loads Using Nonlinear Autoregressive Artificial Neural Networks with Exogenous Vector Inputs |
| title_full_unstemmed | Short-Term Forecasting of Electric Loads Using Nonlinear Autoregressive Artificial Neural Networks with Exogenous Vector Inputs |
| title_short | Short-Term Forecasting of Electric Loads Using Nonlinear Autoregressive Artificial Neural Networks with Exogenous Vector Inputs |
| title_sort | short term forecasting of electric loads using nonlinear autoregressive artificial neural networks with exogenous vector inputs |
| topic | short-term load forecasting nonlinear autoregressive exogenous input artificial neural networks closed-loop forecasting |
| url | http://www.mdpi.com/1996-1073/10/1/40 |
| work_keys_str_mv | AT jaimebuitrago shorttermforecastingofelectricloadsusingnonlinearautoregressiveartificialneuralnetworkswithexogenousvectorinputs AT shihabasfour shorttermforecastingofelectricloadsusingnonlinearautoregressiveartificialneuralnetworkswithexogenousvectorinputs |