Optimal Deep Learning LSTM Model for Electric Load Forecasting using Feature Selection and Genetic Algorithm: Comparison with Machine Learning Approaches †

By Salah Bouktif, Ali Fiaz, Ali Ouni, Mohamed Adel Serhani. Energies, 2018

845 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition, Electrical and Electronic Engineering, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/33d26e0b78b2a5d4dfb84fdad1604468a3476933

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Electrical and Electronic Engineering

In Management Science and Operations Research

Citations in the corpus

Hybrid CNN-LSTM Model for Short-Term Individual Household Load Forecasting (2020, neutral): “Moreover, the forecasting frameworks based on ANN models can be over-ﬁtted, and their convergence rate is slow [15].”
A Short-Term Load Forecasting Method Using Integrated CNN and LSTM Network (2021, background): “In recent times, deep learning approaches have drawn a special attention because of having a greater number of hidden layers, which enables these models to deal with the complicated non-linear patterns [23], [24].”
Artificial intelligence for waste management in smart cities: a review (2023, background): “According to a literature study, extended short-term memory deep neural networks can handle numerous variables, which makes them helpful for resolving issues with time series forecasting (Bouktif et al. 2018).”
Predicting residential energy consumption using CNN-LSTM neural networks (2019, background): “The last output of the LSTM layer is passed to a fully connected layer, which easily generates a predicted time series of energy consumption [26].”
Deep Learning for Time Series Forecasting: The Electric Load Case (2019, methodology): “In [23] a LSTM-based network is trained using a multivariate input which includes temperature, holiday/working day information, date and time information.”
A Deep Neural Network Model for Short-Term Load Forecast Based on Long Short-Term Memory Network and Convolutional Neural Network (2018, background): “Compared to shallow learning, deep learning usually involves a larger number of hidden layers, which makes the model able to learn more complex non-linear patterns [21].”