Abstract
Accurate electricity consumption forecasting can be treated as a reliable guidance for power production. However, traditional electricity forecasting models suffer from simultaneously capturing the periodicity and the volatility of sequential electricity consumption data, while the periodicity and the volatility are important for electricity forecasting. In order to effectively model this sequential data and predict electricity consumption accurately, we propose a multi-scale prediction (Long Short Term Memory, LSTM) algorithm based on Time-Frequency Variational Autoencoder (TFVAE-LSTM). The proposed algorithm treats the sequential data as a superposition of data in different frequencies, it defines an encoder in frequency domain to extract frequency features to model the periodicity and volatility, and defines a decoder in time domain to capture the sequential features of data. Based on the extracted Time-Frequency features in a TFVAE, a multi-scale LSTM model is defined to further extract sequential features from different scales to predict electricity consumption. Experiments show the effectiveness of the proposed TFVAE-LSTM for electricity consumption forecasting tasks.
Highlights
For sequential electricity consumption data, some of its attributes follow obvious multimodal Gaussian distribution, and extracting its statistical features is effective for the electricity consumption forecasting task
This paper proposes a multi-scale prediction (LSTM) algorithm based on Time-Frequency Variational Autoencoder (TFVAE-Long Short Term Memory (LSTM))
A multi-scale prediction (LSTM) algorithm based on Time-Frequency Variational Autoencoder (TFVAE-LSTM) is proposed
Summary
For sequential electricity consumption data, some of its attributes follow obvious multimodal Gaussian distribution, and extracting its statistical features is effective for the electricity consumption forecasting task. Sequential electricity consumption data has more complicated attributes while meeting the above characteristics To solve this question, this paper proposes a multi-scale prediction (LSTM) algorithm based on Time-Frequency Variational Autoencoder (TFVAE-LSTM). In order to simultaneously model the inherent temporality of the electricity consumption data as effective Time-Frequency features, this paper uses a decoder defined in time domain in the proposed TFVAE to generate sequential electricity consumption data. Time-Frequency features obeying Gaussian distribution are extracted Based on these features, this paper defines a multi-scale LSTM to future extract temporal features from different time scales and combines the multiscale information to predict electricity consumption.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: 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.
