A Multi-Scale Electricity Consumption Prediction Algorithm Based on Time-Frequency Variational Autoencoder
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 t...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9398679/ |
| _version_ | 1818443935388794880 |
|---|---|
| author | Kaihong Zheng Peng Li Shangli Zhou Wenhan Zhang Sheng Li Lukun Zeng Yingnan Zhang |
| author_facet | Kaihong Zheng Peng Li Shangli Zhou Wenhan Zhang Sheng Li Lukun Zeng Yingnan Zhang |
| author_sort | Kaihong Zheng |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-14T19:07:56Z |
| format | Article |
| id | doaj.art-7f7a7cfadb634292a4e6ed47aa556453 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T19:07:56Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-7f7a7cfadb634292a4e6ed47aa5564532022-12-21T22:50:48ZengIEEEIEEE Access2169-35362021-01-019909379094610.1109/ACCESS.2021.30714529398679A Multi-Scale Electricity Consumption Prediction Algorithm Based on Time-Frequency Variational AutoencoderKaihong Zheng0https://orcid.org/0000-0001-6291-0198Peng Li1Shangli Zhou2Wenhan Zhang3Sheng Li4Lukun Zeng5Yingnan Zhang6China Southern Power Grid, Digital Grid Research Institute, Guangzhou, ChinaChina Southern Power Grid, Digital Grid Research Institute, Guangzhou, ChinaChina Southern Power Grid, Digital Grid Research Institute, Guangzhou, ChinaChina Southern Power Grid, Digital Grid Research Institute, Guangzhou, ChinaChina Southern Power Grid, Digital Grid Research Institute, Guangzhou, ChinaChina Southern Power Grid, Digital Grid Research Institute, Guangzhou, ChinaChina Southern Power Grid, Digital Grid Research Institute, Guangzhou, ChinaAccurate 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.https://ieeexplore.ieee.org/document/9398679/Time-frequency variational autoencoderelectricity consumption forecastingneural network |
| spellingShingle | Kaihong Zheng Peng Li Shangli Zhou Wenhan Zhang Sheng Li Lukun Zeng Yingnan Zhang A Multi-Scale Electricity Consumption Prediction Algorithm Based on Time-Frequency Variational Autoencoder IEEE Access Time-frequency variational autoencoder electricity consumption forecasting neural network |
| title | A Multi-Scale Electricity Consumption Prediction Algorithm Based on Time-Frequency Variational Autoencoder |
| title_full | A Multi-Scale Electricity Consumption Prediction Algorithm Based on Time-Frequency Variational Autoencoder |
| title_fullStr | A Multi-Scale Electricity Consumption Prediction Algorithm Based on Time-Frequency Variational Autoencoder |
| title_full_unstemmed | A Multi-Scale Electricity Consumption Prediction Algorithm Based on Time-Frequency Variational Autoencoder |
| title_short | A Multi-Scale Electricity Consumption Prediction Algorithm Based on Time-Frequency Variational Autoencoder |
| title_sort | multi scale electricity consumption prediction algorithm based on time frequency variational autoencoder |
| topic | Time-frequency variational autoencoder electricity consumption forecasting neural network |
| url | https://ieeexplore.ieee.org/document/9398679/ |
| work_keys_str_mv | AT kaihongzheng amultiscaleelectricityconsumptionpredictionalgorithmbasedontimefrequencyvariationalautoencoder AT pengli amultiscaleelectricityconsumptionpredictionalgorithmbasedontimefrequencyvariationalautoencoder AT shanglizhou amultiscaleelectricityconsumptionpredictionalgorithmbasedontimefrequencyvariationalautoencoder AT wenhanzhang amultiscaleelectricityconsumptionpredictionalgorithmbasedontimefrequencyvariationalautoencoder AT shengli amultiscaleelectricityconsumptionpredictionalgorithmbasedontimefrequencyvariationalautoencoder AT lukunzeng amultiscaleelectricityconsumptionpredictionalgorithmbasedontimefrequencyvariationalautoencoder AT yingnanzhang amultiscaleelectricityconsumptionpredictionalgorithmbasedontimefrequencyvariationalautoencoder AT kaihongzheng multiscaleelectricityconsumptionpredictionalgorithmbasedontimefrequencyvariationalautoencoder AT pengli multiscaleelectricityconsumptionpredictionalgorithmbasedontimefrequencyvariationalautoencoder AT shanglizhou multiscaleelectricityconsumptionpredictionalgorithmbasedontimefrequencyvariationalautoencoder AT wenhanzhang multiscaleelectricityconsumptionpredictionalgorithmbasedontimefrequencyvariationalautoencoder AT shengli multiscaleelectricityconsumptionpredictionalgorithmbasedontimefrequencyvariationalautoencoder AT lukunzeng multiscaleelectricityconsumptionpredictionalgorithmbasedontimefrequencyvariationalautoencoder AT yingnanzhang multiscaleelectricityconsumptionpredictionalgorithmbasedontimefrequencyvariationalautoencoder |