QPSO-optimized VMD-SE-transformer-BiLSTM for short-term air conditioning load forecasting in industrial buildings
QPSO最適化VMD-SE-Transformer-BiLSTMを用いた産業用建物の短期空調負荷予測 (AI 翻訳)
Yingfeng Wei, Hui Chen, Ye Tian, Chi-Kai Wang, Yulei Hu, Zhiheng Xie, Yu Du, JianPing Yang, Jiaqi Qian, Huimin Liu, Jiewen Deng, Lu Dong
🤖 gxceed AI 要約
日本語
本研究では、産業用建物の空調負荷予測のため、VMD-SEでノイズ低減後、TransformerとBiLSTMを組み合わせたハイブリッドモデルを提案。QPSOで最適化し、中国湖北省の実データで検証した結果、R2=0.981と高い予測精度を達成。インテリジェントなHVAC制御やデマンドレスポンスによる低炭素エネルギー管理に貢献する。
English
This study proposes a hybrid forecasting framework integrating VMD-SE, Transformer, and BiLSTM, optimized by QPSO, for short-term air conditioning load in industrial buildings. Validated on real datasets from Hubei, China, the model achieves high accuracy (R2=0.981), supporting intelligent HVAC scheduling, demand response, and low-carbon energy management.
Unofficial AI-generated summary based on the public title and abstract. Not an official translation.
📝 gxceed 編集解説 — Why this matters
日本のGX文脈において
日本の産業界では、空調負荷予測の高度化によるエネルギーマネジメントがGX実現に重要。本モデルは中国データで検証されているが、手法自体は日本の工場にも適用可能で、SSBJや有報のGHG排出量削減目標達成に資する実務知見を提供する。
In the global GX context
While tested on Chinese data, the proposed model offers a practical approach for industrial load forecasting that can be adapted globally to enhance energy efficiency and support carbon reduction targets, aligning with ISSB and TCFD frameworks for climate-related disclosures.
👥 読者別の含意
🔬研究者:Provides a novel hybrid forecasting approach that combines VMD, SE, Transformer, and BiLSTM, optimized with QPSO, demonstrating high accuracy for industrial load forecasting.
🏢実務担当者:The model can be used for intelligent HVAC scheduling and demand response in industrial buildings to reduce energy consumption and carbon emissions.
📄 Abstract（原文）
The air-conditioning loads of industrial buildings exhibit considerable nonlinearity, nonstationarity, and multi-scale variability due to the interaction between production processes and external weather conditions. This study proposes a three-stage hybrid forecasting framework that integrates Variational Mode Decomposition and Sample Entropy (VMD–SE) with a transformer–Bidirectional Long Short-Term Memory (BiLSTM) network architecture, optimized using Quantum Particle Swarm Optimization (QPSO). The VMD–SE module reconstructs the load signal by entropy-based component screening, significantly reducing high-frequency noise while maintaining essential dynamic features. The dual-path transformer–BiLSTM network concurrently captures long-term global dependencies and short-term local changes, facilitating an extensive temporal representation. By automatically adjusting its core parameters, QPSO achieves more efficient convergence, increased stability, and enhanced global search. Two real-world datasets obtained from industrial facilities in Hubei, China, reflecting distinct seasons and load levels, were utilized for validation using ablation and comparative experiments. The proposed model outperformed benchmark models such as SVR, GRU, and CNN–informer, achieving a coefficient of determination (R2) of 0.981 23 and a root mean square error of 0.181 32. The findings indicate that the proposed model is effective and versatile across various situations, offering both theoretical understanding and practical guidance for intelligent HVAC scheduling, dynamic demand response, and low-carbon energy management in industrial facilities. Our results show that the model is robust and flexible, providing a practical and theoretically grounded approach for intelligent HVAC scheduling, demand response, and industrial carbon reduction.
🔗 Provenance — このレコードを発見したソース
- semanticscholar https://doi.org/10.1063/5.0319827first seen 2026-05-06 00:07:34
gxceed は公開メタデータに基づく研究支援データセットです。要約・翻訳・解説は AI 支援で生成されています。 最終的な解釈・検証は利用者が原典資料に基づいて行うことを前提とします。