Daily natural gas load prediction method based on APSO optimization and Attention-BiLSTM
As the economy continues to develop and technology advances, there is an increasing societal need for an environmentally friendly ecosystem. Consequently, natural gas, known for its minimal greenhouse gas emissions, has been widely adopted as a clean energy alternative. The accurate prediction of sh...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
PeerJ Inc.
2024-02-01
|
Series: | PeerJ Computer Science |
Subjects: | |
Online Access: | https://peerj.com/articles/cs-1890.pdf |
_version_ | 1797284191523569664 |
---|---|
author | Xinjing Qi Huan Wang Yubo Ji Yuan Li Xuguang Luo Rongshan Nie Xiaoyu Liang |
author_facet | Xinjing Qi Huan Wang Yubo Ji Yuan Li Xuguang Luo Rongshan Nie Xiaoyu Liang |
author_sort | Xinjing Qi |
collection | DOAJ |
description | As the economy continues to develop and technology advances, there is an increasing societal need for an environmentally friendly ecosystem. Consequently, natural gas, known for its minimal greenhouse gas emissions, has been widely adopted as a clean energy alternative. The accurate prediction of short-term natural gas demand poses a significant challenge within this context, as precise forecasts have important implications for gas dispatch and pipeline safety. The incorporation of intelligent algorithms into prediction methodologies has resulted in notable progress in recent times. Nevertheless, certain limitations persist. However, there exist certain limitations, including the tendency to easily fall into local optimization and inadequate search capability. To address the challenge of accurately predicting daily natural gas loads, we propose a novel methodology that integrates the adaptive particle swarm optimization algorithm, attention mechanism, and bidirectional long short-term memory (BiLSTM) neural networks. The initial step involves utilizing the BiLSTM network to conduct bidirectional data learning. Following this, the attention mechanism is employed to calculate the weights of the hidden layer in the BiLSTM, with a specific focus on weight distribution. Lastly, the adaptive particle swarm optimization algorithm is utilized to comprehensively optimize and design the network structure, initial learning rate, and learning rounds of the BiLSTM network model, thereby enhancing the accuracy of the model. The findings revealed that the combined model achieved a mean absolute percentage error (MAPE) of 0.90% and a coefficient of determination (R2) of 0.99. These results surpassed those of the other comparative models, demonstrating superior prediction accuracy, as well as exhibiting favorable generalization and prediction stability. |
first_indexed | 2024-03-07T17:44:27Z |
format | Article |
id | doaj.art-00951a991d2941a0ac663f109b20361e |
institution | Directory Open Access Journal |
issn | 2376-5992 |
language | English |
last_indexed | 2024-03-07T17:44:27Z |
publishDate | 2024-02-01 |
publisher | PeerJ Inc. |
record_format | Article |
series | PeerJ Computer Science |
spelling | doaj.art-00951a991d2941a0ac663f109b20361e2024-03-02T15:05:31ZengPeerJ Inc.PeerJ Computer Science2376-59922024-02-0110e189010.7717/peerj-cs.1890Daily natural gas load prediction method based on APSO optimization and Attention-BiLSTMXinjing Qi0Huan Wang1Yubo Ji2Yuan Li3Xuguang Luo4Rongshan Nie5Xiaoyu Liang6College of Metrology and Measurement Engineering, China Jiliang University, Hangzhou, Zhejiang, ChinaNingbo China Resources Xingguang Gas Co Ltd, Ningbo, Zhejiang, ChinaNingbo China Resources Xingguang Gas Co Ltd, Ningbo, Zhejiang, ChinaWuhan Gas & Heat and Design Institute Co Ltd, Wuhan, Hubei, ChinaWuhan Gas & Heat and Design Institute Co Ltd, Wuhan, Hubei, ChinaCollege of Quality and Safety Engineering, China Jiliang University, Hangzhou, Zhejiang, ChinaCollege of Metrology and Measurement Engineering, China Jiliang University, Hangzhou, Zhejiang, ChinaAs the economy continues to develop and technology advances, there is an increasing societal need for an environmentally friendly ecosystem. Consequently, natural gas, known for its minimal greenhouse gas emissions, has been widely adopted as a clean energy alternative. The accurate prediction of short-term natural gas demand poses a significant challenge within this context, as precise forecasts have important implications for gas dispatch and pipeline safety. The incorporation of intelligent algorithms into prediction methodologies has resulted in notable progress in recent times. Nevertheless, certain limitations persist. However, there exist certain limitations, including the tendency to easily fall into local optimization and inadequate search capability. To address the challenge of accurately predicting daily natural gas loads, we propose a novel methodology that integrates the adaptive particle swarm optimization algorithm, attention mechanism, and bidirectional long short-term memory (BiLSTM) neural networks. The initial step involves utilizing the BiLSTM network to conduct bidirectional data learning. Following this, the attention mechanism is employed to calculate the weights of the hidden layer in the BiLSTM, with a specific focus on weight distribution. Lastly, the adaptive particle swarm optimization algorithm is utilized to comprehensively optimize and design the network structure, initial learning rate, and learning rounds of the BiLSTM network model, thereby enhancing the accuracy of the model. The findings revealed that the combined model achieved a mean absolute percentage error (MAPE) of 0.90% and a coefficient of determination (R2) of 0.99. These results surpassed those of the other comparative models, demonstrating superior prediction accuracy, as well as exhibiting favorable generalization and prediction stability.https://peerj.com/articles/cs-1890.pdfNatural gas daily loadBidirectional long short-term memory network (BiLSTM)Attention mechanismAdaptive particle swarm optimization (APSO) |
spellingShingle | Xinjing Qi Huan Wang Yubo Ji Yuan Li Xuguang Luo Rongshan Nie Xiaoyu Liang Daily natural gas load prediction method based on APSO optimization and Attention-BiLSTM PeerJ Computer Science Natural gas daily load Bidirectional long short-term memory network (BiLSTM) Attention mechanism Adaptive particle swarm optimization (APSO) |
title | Daily natural gas load prediction method based on APSO optimization and Attention-BiLSTM |
title_full | Daily natural gas load prediction method based on APSO optimization and Attention-BiLSTM |
title_fullStr | Daily natural gas load prediction method based on APSO optimization and Attention-BiLSTM |
title_full_unstemmed | Daily natural gas load prediction method based on APSO optimization and Attention-BiLSTM |
title_short | Daily natural gas load prediction method based on APSO optimization and Attention-BiLSTM |
title_sort | daily natural gas load prediction method based on apso optimization and attention bilstm |
topic | Natural gas daily load Bidirectional long short-term memory network (BiLSTM) Attention mechanism Adaptive particle swarm optimization (APSO) |
url | https://peerj.com/articles/cs-1890.pdf |
work_keys_str_mv | AT xinjingqi dailynaturalgasloadpredictionmethodbasedonapsooptimizationandattentionbilstm AT huanwang dailynaturalgasloadpredictionmethodbasedonapsooptimizationandattentionbilstm AT yuboji dailynaturalgasloadpredictionmethodbasedonapsooptimizationandattentionbilstm AT yuanli dailynaturalgasloadpredictionmethodbasedonapsooptimizationandattentionbilstm AT xuguangluo dailynaturalgasloadpredictionmethodbasedonapsooptimizationandattentionbilstm AT rongshannie dailynaturalgasloadpredictionmethodbasedonapsooptimizationandattentionbilstm AT xiaoyuliang dailynaturalgasloadpredictionmethodbasedonapsooptimizationandattentionbilstm |