Multi-Scale Graph Attention Network Based on Encoding Decomposition for Electricity Consumption Prediction

Accurate electricity consumption forecasting is essential for power scheduling. In short-term forecasting, electricity consumption data exhibit periodic patterns, as well as fluctuations associated with production events. Traditional forecasting methods typically focus on sequential features of the...

Full description

Saved in:
Bibliographic Details
Main Authors: Sheng Huang, Huakun Que, Lukun Zeng, Jingxu Yang, Kaihong Zheng
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/17/23/5813
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846124328793407488
author Sheng Huang
Huakun Que
Lukun Zeng
Jingxu Yang
Kaihong Zheng
author_facet Sheng Huang
Huakun Que
Lukun Zeng
Jingxu Yang
Kaihong Zheng
author_sort Sheng Huang
collection DOAJ
description Accurate electricity consumption forecasting is essential for power scheduling. In short-term forecasting, electricity consumption data exhibit periodic patterns, as well as fluctuations associated with production events. Traditional forecasting methods typically focus on sequential features of the data, which may lead to an over-smoothing issue for the fluctuations. In practice, the fluctuations of electricity consumption associated with these events tend to follow recognizable patterns. By emphasizing the impact of these experiential electricity consumption fluctuations on the current prediction process, we can capture the volatility variations to alleviate the over-smoothing problem. To this end, we propose an encoding decomposition-based multi-scale graph neural network (CMNN). The CMNN starts by decomposing the electricity data into various components. For the high-order components that exhibit approximate periodic behavior, the CMNN designs a Multi-scale Bi-directional Long Short-Term Memory (MBLSTM) network for fitting and prediction. For the low-order components that exhibit fluctuations, the CMNN transforms these components from one-dimensional time series into a two-dimensional low-order component graph to model the volatility of the low-order components, and proposes a Gaussian Graph Auto-Encoder to forecast the low-order components. Finally, the CMNN combines the predicted components to produce the final electricity consumption prediction. Experiments demonstrate that the CMNN enhances the accuracy of electricity consumption predictions.
format Article
id doaj-art-f4b8b2e11bcc4f8da67ad613bb27367b
institution Kabale University
issn 1996-1073
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj-art-f4b8b2e11bcc4f8da67ad613bb27367b2024-12-13T16:24:59ZengMDPI AGEnergies1996-10732024-11-011723581310.3390/en17235813Multi-Scale Graph Attention Network Based on Encoding Decomposition for Electricity Consumption PredictionSheng Huang0Huakun Que1Lukun Zeng2Jingxu Yang3Kaihong Zheng4Metrology Center of Guangdong Power Grid Corporation, Guangzhou 510080, ChinaMetrology Center of Guangdong Power Grid Corporation, Guangzhou 510080, ChinaDigital Grid Group Co., Ltd., China Southern Power Grid, Guangzhou 510663, ChinaDigital Grid Group Co., Ltd., China Southern Power Grid, Guangzhou 510663, ChinaDigital Grid Group Co., Ltd., China Southern Power Grid, Guangzhou 510663, ChinaAccurate electricity consumption forecasting is essential for power scheduling. In short-term forecasting, electricity consumption data exhibit periodic patterns, as well as fluctuations associated with production events. Traditional forecasting methods typically focus on sequential features of the data, which may lead to an over-smoothing issue for the fluctuations. In practice, the fluctuations of electricity consumption associated with these events tend to follow recognizable patterns. By emphasizing the impact of these experiential electricity consumption fluctuations on the current prediction process, we can capture the volatility variations to alleviate the over-smoothing problem. To this end, we propose an encoding decomposition-based multi-scale graph neural network (CMNN). The CMNN starts by decomposing the electricity data into various components. For the high-order components that exhibit approximate periodic behavior, the CMNN designs a Multi-scale Bi-directional Long Short-Term Memory (MBLSTM) network for fitting and prediction. For the low-order components that exhibit fluctuations, the CMNN transforms these components from one-dimensional time series into a two-dimensional low-order component graph to model the volatility of the low-order components, and proposes a Gaussian Graph Auto-Encoder to forecast the low-order components. Finally, the CMNN combines the predicted components to produce the final electricity consumption prediction. Experiments demonstrate that the CMNN enhances the accuracy of electricity consumption predictions.https://www.mdpi.com/1996-1073/17/23/5813graph attention networkmulti-scale graph neural networklow-order component graphelectricity consumption prediction
spellingShingle Sheng Huang
Huakun Que
Lukun Zeng
Jingxu Yang
Kaihong Zheng
Multi-Scale Graph Attention Network Based on Encoding Decomposition for Electricity Consumption Prediction
Energies
graph attention network
multi-scale graph neural network
low-order component graph
electricity consumption prediction
title Multi-Scale Graph Attention Network Based on Encoding Decomposition for Electricity Consumption Prediction
title_full Multi-Scale Graph Attention Network Based on Encoding Decomposition for Electricity Consumption Prediction
title_fullStr Multi-Scale Graph Attention Network Based on Encoding Decomposition for Electricity Consumption Prediction
title_full_unstemmed Multi-Scale Graph Attention Network Based on Encoding Decomposition for Electricity Consumption Prediction
title_short Multi-Scale Graph Attention Network Based on Encoding Decomposition for Electricity Consumption Prediction
title_sort multi scale graph attention network based on encoding decomposition for electricity consumption prediction
topic graph attention network
multi-scale graph neural network
low-order component graph
electricity consumption prediction
url https://www.mdpi.com/1996-1073/17/23/5813
work_keys_str_mv AT shenghuang multiscalegraphattentionnetworkbasedonencodingdecompositionforelectricityconsumptionprediction
AT huakunque multiscalegraphattentionnetworkbasedonencodingdecompositionforelectricityconsumptionprediction
AT lukunzeng multiscalegraphattentionnetworkbasedonencodingdecompositionforelectricityconsumptionprediction
AT jingxuyang multiscalegraphattentionnetworkbasedonencodingdecompositionforelectricityconsumptionprediction
AT kaihongzheng multiscalegraphattentionnetworkbasedonencodingdecompositionforelectricityconsumptionprediction