Optimal Deep Learning LSTM Model for Electric Load Forecasting using Feature Selection and Genetic Algorithm: Comparison with Machine Learning Approaches †
Background: With the development of smart grids, accurate electric load forecasting has become increasingly important as it can help power companies in better load scheduling and reduce excessive electricity production. However, developing and selecting accurate time series models is a challenging t...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2018-06-01
|
Series: | Energies |
Subjects: | |
Online Access: | http://www.mdpi.com/1996-1073/11/7/1636 |
_version_ | 1811302135491461120 |
---|---|
author | Salah Bouktif Ali Fiaz Ali Ouni Mohamed Adel Serhani |
author_facet | Salah Bouktif Ali Fiaz Ali Ouni Mohamed Adel Serhani |
author_sort | Salah Bouktif |
collection | DOAJ |
description | Background: With the development of smart grids, accurate electric load forecasting has become increasingly important as it can help power companies in better load scheduling and reduce excessive electricity production. However, developing and selecting accurate time series models is a challenging task as this requires training several different models for selecting the best amongst them along with substantial feature engineering to derive informative features and finding optimal time lags, a commonly used input features for time series models. Methods: Our approach uses machine learning and a long short-term memory (LSTM)-based neural network with various configurations to construct forecasting models for short to medium term aggregate load forecasting. The research solves above mentioned problems by training several linear and non-linear machine learning algorithms and picking the best as baseline, choosing best features using wrapper and embedded feature selection methods and finally using genetic algorithm (GA) to find optimal time lags and number of layers for LSTM model predictive performance optimization. Results: Using France metropolitan’s electricity consumption data as a case study, obtained results show that LSTM based model has shown high accuracy then machine learning model that is optimized with hyperparameter tuning. Using the best features, optimal lags, layers and training various LSTM configurations further improved forecasting accuracy. Conclusions: A LSTM model using only optimally selected time lagged features captured all the characteristics of complex time series and showed decreased Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) for medium to long range forecasting for a wider metropolitan area. |
first_indexed | 2024-04-13T07:22:40Z |
format | Article |
id | doaj.art-ad514c7fb4344cfc9bf90f8ddf302d07 |
institution | Directory Open Access Journal |
issn | 1996-1073 |
language | English |
last_indexed | 2024-04-13T07:22:40Z |
publishDate | 2018-06-01 |
publisher | MDPI AG |
record_format | Article |
series | Energies |
spelling | doaj.art-ad514c7fb4344cfc9bf90f8ddf302d072022-12-22T02:56:35ZengMDPI AGEnergies1996-10732018-06-01117163610.3390/en11071636en11071636Optimal Deep Learning LSTM Model for Electric Load Forecasting using Feature Selection and Genetic Algorithm: Comparison with Machine Learning Approaches †Salah Bouktif0Ali Fiaz1Ali Ouni2Mohamed Adel Serhani3Department of Computer Science and Software Engineering, College of Information Technology, UAE University, Al Ain 15551, UAEDepartment of Computer Science and Software Engineering, College of Information Technology, UAE University, Al Ain 15551, UAEDepartment of Software Engineering and IT, Ecole de Technologie Superieure, Montréal, QC H3C 1K3, CanadaDepartment of Computer Science and Software Engineering, College of Information Technology, UAE University, Al Ain 15551, UAEBackground: With the development of smart grids, accurate electric load forecasting has become increasingly important as it can help power companies in better load scheduling and reduce excessive electricity production. However, developing and selecting accurate time series models is a challenging task as this requires training several different models for selecting the best amongst them along with substantial feature engineering to derive informative features and finding optimal time lags, a commonly used input features for time series models. Methods: Our approach uses machine learning and a long short-term memory (LSTM)-based neural network with various configurations to construct forecasting models for short to medium term aggregate load forecasting. The research solves above mentioned problems by training several linear and non-linear machine learning algorithms and picking the best as baseline, choosing best features using wrapper and embedded feature selection methods and finally using genetic algorithm (GA) to find optimal time lags and number of layers for LSTM model predictive performance optimization. Results: Using France metropolitan’s electricity consumption data as a case study, obtained results show that LSTM based model has shown high accuracy then machine learning model that is optimized with hyperparameter tuning. Using the best features, optimal lags, layers and training various LSTM configurations further improved forecasting accuracy. Conclusions: A LSTM model using only optimally selected time lagged features captured all the characteristics of complex time series and showed decreased Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) for medium to long range forecasting for a wider metropolitan area.http://www.mdpi.com/1996-1073/11/7/1636deep neural networkslong short term memory networksshort- and medium-term load forecastingmachine learningfeature selectiongenetic algorithm |
spellingShingle | Salah Bouktif Ali Fiaz Ali Ouni Mohamed Adel Serhani Optimal Deep Learning LSTM Model for Electric Load Forecasting using Feature Selection and Genetic Algorithm: Comparison with Machine Learning Approaches † Energies deep neural networks long short term memory networks short- and medium-term load forecasting machine learning feature selection genetic algorithm |
title | Optimal Deep Learning LSTM Model for Electric Load Forecasting using Feature Selection and Genetic Algorithm: Comparison with Machine Learning Approaches † |
title_full | Optimal Deep Learning LSTM Model for Electric Load Forecasting using Feature Selection and Genetic Algorithm: Comparison with Machine Learning Approaches † |
title_fullStr | Optimal Deep Learning LSTM Model for Electric Load Forecasting using Feature Selection and Genetic Algorithm: Comparison with Machine Learning Approaches † |
title_full_unstemmed | Optimal Deep Learning LSTM Model for Electric Load Forecasting using Feature Selection and Genetic Algorithm: Comparison with Machine Learning Approaches † |
title_short | Optimal Deep Learning LSTM Model for Electric Load Forecasting using Feature Selection and Genetic Algorithm: Comparison with Machine Learning Approaches † |
title_sort | optimal deep learning lstm model for electric load forecasting using feature selection and genetic algorithm comparison with machine learning approaches † |
topic | deep neural networks long short term memory networks short- and medium-term load forecasting machine learning feature selection genetic algorithm |
url | http://www.mdpi.com/1996-1073/11/7/1636 |
work_keys_str_mv | AT salahbouktif optimaldeeplearninglstmmodelforelectricloadforecastingusingfeatureselectionandgeneticalgorithmcomparisonwithmachinelearningapproaches AT alifiaz optimaldeeplearninglstmmodelforelectricloadforecastingusingfeatureselectionandgeneticalgorithmcomparisonwithmachinelearningapproaches AT aliouni optimaldeeplearninglstmmodelforelectricloadforecastingusingfeatureselectionandgeneticalgorithmcomparisonwithmachinelearningapproaches AT mohamedadelserhani optimaldeeplearninglstmmodelforelectricloadforecastingusingfeatureselectionandgeneticalgorithmcomparisonwithmachinelearningapproaches |