Advanced Methods of Power Load Forecasting

• Format: eBook
• Language: English
• Published: Basel MDPI - Multidisciplinary Digital Publishing Institute 2022
• Subjects: Artificial Neural Network; attention; bidirectional long short-term memory; CNN; deep learning; deep neural network; demand; DIMS; encoder decoder; forecast; galvanizing; Holt–Winters model; irregular; load; long-term forecasting; LSTM; machine learning; Mathematics and Science; multi-layer stacked; multiple seasonality; neural network; online training; parameters tuning; peak load; Physics; power system; Prophet model; recurrent neural network; Reference, Information and Interdisciplinary subjects; Research and information: general; short-term electrical load forecasting; short-term load forecast; short-term load forecasting; statistical analysis; time series
• ISBN: 3036542175; 9783036542188; 3036542183; 9783036542171
• DOI: 10.3390/books978-3-0365-4217-1

This reprint introduces advanced prediction models focused on power load forecasting. Models based on artificial intelligence and more traditional approaches are shown, demonstrating the real possibilities of use to improve prediction in this field. Models of LSTM neural networks, LSTM networks with a SESDA architecture, in even LSTM-CNN are used. On the other hand, multiple seasonal Holt-Winters models with discrete seasonality and the application of the Prophet method to demand forecasting are presented. These models are applied in different circumstances and show highly positive results. This reprint is intended for both researchers related to energy management and those related to forecasting, especially power load.