Residential Load Forecasting based on Deep Neural Network
4th International Conference on Innovative Trends in Information Technology, ICITIIT 2023
; 2023.
Article
Dans Anglais
| Scopus | ID: covidwho-2304298
ABSTRACT
This paper presents residential load forecasting using multivariate multi-step Deep Neural Networks (DNN) such as LSTM, CNN, Stacked LSTM, and Hybrid CNN-LSTM. A preliminary Exploratory Data Analysis (EDA) is conducted, and the decision variables are identified. An elbowing method is used to determine the number of clusters. Data is categorized based on weekdays, weekends, vacations, and Covid-Lockdown. Dimensionality-reduction using principal component analysis (PCA) is conducted. Seasonality-based clustering is found to improve the DNN model prediction accuracy further. A comparative analysis employs error metrics such as RMSE, MSE, MAPE, and MAE. The multivariate LSTM model with feedback is found to be the best fit model with the better performance indices. © 2023 IEEE.
CNN-LSTM; Convolution Neural Networks (CNN); Deep Neural Networks (DNN); Hybrid Model; Long-Short Term Memory (LSTM); Short Term Load Forecasting (STLF); Brain; Deep neural networks; Electric power plant loads; Forecasting; Housing; Principal component analysis; Convolution neural network; Convolution neural network-long-short term memory; Deep neural network; Long-short term memory; Residential load forecasting; Short term load forecasting; Long short-term memory
Texte intégral:
Disponible
Collection:
Bases de données des oragnisations internationales
Base de données:
Scopus
langue:
Anglais
Revue:
4th International Conference on Innovative Trends in Information Technology, ICITIIT 2023
Année:
2023
Type de document:
Article
Documents relatifs à ce sujet
MEDLINE
...
LILACS
LIS