← 論文一覧に戻る

ハイパーパラメータ最適化と物理制約付き後処理を用いた建物熱負荷予測の深層学習フレームワーク

A deep-learning framework for predicting building heat load with hyperparameter optimisation and physics-constrained post-processing (原題)

Ma, Minghui, Valdiserri, Paolo, Ballerini, Vincenzo, Li, Ruixin, di Schio, Eugenia Rossi

📚 査読済 / ジャーナル2026#省エネOrigin: EU経営インパクト: コスト削減対象セクター: real_estate
DOI: 10.1016/j.enbuild.2026.117783
原典: https://hdl.handle.net/11585/1068610

🤖 gxceed AI 要約

日本語

本研究は、ボローニャの単一アパートを対象に、過去24時間のデータから翌1時間の熱負荷を予測する深層学習フレームワークを提案。OptunaでLSTM、TCN、MLP、XGBoost、LRのハイパーパラメータを最適化し、LSTMが最高性能を示した。物理制約付き後処理により誤差をさらに低減し、低計算コストで実用的な省エネ運用に貢献する。

English

This study proposes a deep learning framework to predict building heat load for a single apartment in Bologna using previous 24h data. Optuna optimizes hyperparameters for LSTM, TCN, MLP, XGBoost, and LR; LSTM performs best. Physics-constrained post-processing reduces MAE by 28.2%, offering a scalable solution for intelligent building energy management and low-carbon operation.

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ZEBや省エネ基準強化、カーボンニュートラル目標に資する。AIによる熱負荷予測は、ビル管理の効率化とエネルギー消費削減に直結し、SSBJ開示におけるエネルギー使用量削減の裏付けとしても有用。

In the global GX context

This work aligns with global energy transition goals and supports intelligent building management. It demonstrates a practical AI-driven approach to reduce building energy consumption, relevant for TCFD/ISSB climate disclosure where energy efficiency metrics are key.

👥 読者別の含意

🔬研究者:Provides a comparative analysis of deep learning models with hyperparameter optimization and physics-constrained post-processing for heat load prediction.

🏢実務担当者:Offers a scalable, low-cost framework for intelligent heating control and demand-side management in buildings.

🏛政策担当者:Highlights the potential of AI in building energy efficiency, supporting policy for smart building and carbon reduction.

📄 Abstract（原文）

Driven by global energy transition and carbon neutrality goals, accurate building heat load prediction is of great significance for intelligent heating control, demand-side energy management, and fault detection. This study focuses on a single-apartment located in Bologna and predicts the heat load for the next hour based on the previous 24 h of data. A dataset of 18 typical operating scenarios was constructed, encompassing variations in outdoor meteorological conditions, occupancy, thermostat settings, and equipment heat gains. Subsequently, the Optuna framework was employed to systematically optimize the hyperparameters of five models—LSTM, TCN, MLP, XGBoost, and LR—and their prediction performance was comparatively analyzed. Results show that that the deep learning models LSTM and TCN perform best, with LSTM slightly outperforming (LSTM: MAE = 0.082 kW, RMSE = 0.118 kW, R2 = 0.863; TCN: MAE = 0.0864 kW, RMSE = 0.1196 kW, R2 = 0.8606). Whereas the LR model exhibits the poorest performance, achieving only 0.1202 kW, 0.1504 kW, and 0.7793 on the respective metrics. After applying a post-processing (PC) correction mechanism, the MAE and RMSE of LSTM decreased to 0.058 kW and 0.100 kW, corresponding to reductions of 28.2% and 15.3%, respectively. This framework effectively integrates data-driven methods with physical constraints while maintaining low computational cost, providing a scalable and practical solution for intelligent building energy management and low-carbon operation.

🔗 Provenance — このレコードを発見したソース

🔔 こうした論文の新着を逃したくない方は キーワードアラート に登録（無料・3キーワードまで）。

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。