Toward Net-Zero Energy Buildings: A Systematic Review of AI-Driven Renewable Energy Integration and Optimization
ネットゼロエネルギー建築に向けて：AI駆動の再生可能エネルギー統合と最適化に関する系統的レビュー (AI 翻訳)
Mahmood Mazin Ali Mahmood, Keng Wai Chan
🤖 gxceed AI 要約
日本語
本系統的レビューは、2012年から2025年までの41の研究を分析し、機械学習、IoT、BIMを統合した再エネ技術の有効性を評価。太陽光発電による電気代35～64%削減、ML予測モデルでR2=0.989の精度を報告。実時間センサー統合や多気候データセットの不足などの研究ギャップを指摘し、ネットゼロエネルギー建築への道筋を示す。
English
This systematic review of 41 studies (2012-2025) evaluates AI-driven renewable energy integration in buildings, covering PV, ML prediction, HVAC optimization, and occupancy management. Quantitative findings show 35-64% electricity cost reduction with solar PV and ML prediction accuracy up to R2=0.989. It identifies gaps in real-time sensor integration and multi-climate datasets, offering actionable guidance for net-zero energy buildings.
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
日本ではZEB（ネット・ゼロ・エネルギー・ビル）の普及が進んでおり、本レビューのAI・IoT統合知見は、建築物省エネ基準やスマートグリッド連携に資する。特にPVコスト削減効果は、日本企業の省エネ投資判断に有用なエビデンスを提供する。
In the global GX context
Globally, buildings are a major emission source, and this review provides a structured synthesis of AI and renewable technologies for net-zero targets. The findings support corporate Scope 2 reduction strategies and align with ISSB/TCFD frameworks by enabling more accurate energy forecasting and cost-efficient decarbonization.
👥 読者別の含意
🔬研究者:Identifies research gaps in real-time sensor integration and multi-climate datasets, providing a foundation for further ML and BIM-based building energy studies.
🏢実務担当者:Offers quantitative evidence (35-64% cost reduction, R2=0.989) to justify investment in AI-driven PV and HVAC optimization for building portfolios.
🏛政策担当者:Highlights the need for policies promoting multi-climate pilot projects and real-time data infrastructure to scale net-zero building technologies.
📄 Abstract（原文）
Buildings account for 40% of global energy consumption and one-third of greenhouse gas emissions. Renewable energy systems (RESs), such as solar photovoltaic (PV) and geothermal heat pumps, are critical technological solutions for decarbonization. Despite the growing literature, existing reviews lack a comprehensive synthesis integrating machine learning (ML), Internet of Things (IoT), and Building Information Modeling (BIM). Following the PRISMA protocol, this paper presents a systematic review of 41 studies published between 2012 and 2025. The review evaluates four primary domains: RES performance, building energy prediction, HVAC optimization, and occupancy-aware management. Quantitative findings reveal that solar PV-integrated buildings achieve electricity cost reductions of 35–64%, while ML-enhanced energy prediction models attain accuracies up to R2 = 0.989. Critical research gaps are identified, including the scarcity of real-time sensor integration and geographically inclusive multi-climate datasets. Ultimately, this review contributes a structured synthesis of effective technologies, a comparative analysis of methodological approaches (ML, simulation, hybrid), and actionable future directions. It provides practical guidance for researchers and policymakers toward achieving net-zero energy buildings. This study serves as a definitive reference for the development of sustainable, low-energy built environments.
🔗 Provenance — このレコードを発見したソース
- crossref https://doi.org/10.3390/buildings16132475first seen 2026-06-24 05:43:41
🔔 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。