Abstract
A highly efficient deep learning method for short-term power load forecasting has been developed recently. It is a challenge to improve forecasting accuracy, as power consumption data at the individual household level is erratic for variable weather conditions and random human behaviour. In this paper, a robust short-term power load forecasting method is developed based on a Bidirectional long short-term memory (Bi-LSTM) and long short-term memory (LSTM) neural network with stationary wavelet transform (SWT). The actual power load data is classified according to seasonal power usage behaviour. For each load classification, short-term power load forecasting is performed using the developed method. A set of lagged power load data vectors is generated from the historical power load data, and SWT decomposes the vectors into sub-components. A Bi-LSTM neural network layer extracts features from the sub-components, and an LSTM layer is used to forecast the power load from each extracted feature. A dropout layer with fixed probability is added after the Bi-LSTM and LSTM layers to bolster the forecasting accuracy. In order to evaluate the accuracy of the proposed model, it is compared against other developed short-term load forecasting models which are subjected to two seasonal load classifications.
Highlights
Load forecasting with high accuracy is very important for practical power system and smart grids analysis
The paper is arranged as follows: in Section II the data description and observation are analyzed, in Section III a curve fitting method for STLF is described; in Section IV the methodology included with five main parts stationary wavelet transform (SWT), BiLSTM, long short-term memory (LSTM), Dropout layer, ISWT of the proposed shortterm power load forecasting model are explained; in Section V the accuracy of the proposed load forecasting model is evaluated by case study using experimental data; and in Section VI conclusions are drawn
A robust short-term power load forecasting has been developed by using wavelet transform and deep learning method in this paper
Summary
Load forecasting with high accuracy is very important for practical power system and smart grids analysis. T the individual household level, a hybrid deep learning methodology combined with LSTM neural network and with SWT is proposed [5], in which SWT decompose the input data into signal components and each signal component is fed to LSTM separately for forecasting This developed model accuracy is verified by using remote sensor data of five different family houses in London, United Kingdom. In order to overcome the difficulty of data fitting in input and improve the accuracy of forecasting, [26] developed Solar photovoltaic (PV) power forecasting hybrid method based on DWT-CNN-LSTM models; independently established for four weather types : sunny, cloudy, rainy, and heavy rainy days. The paper is arranged as follows: in Section II the data description and observation are analyzed, in Section III a curve fitting method for STLF is described; in Section IV the methodology included with five main parts SWT, BiLSTM, LSTM, Dropout layer, ISWT of the proposed shortterm power load forecasting model are explained; in Section V the accuracy of the proposed load forecasting model is evaluated by case study using experimental data; and in Section VI conclusions are drawn
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: European Journal of Electrical Engineering and Computer Science
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
