gxceed
← 論文一覧に戻る

Graph Spatiotemporal World-Model-Driven Rolling MPC for Low-Carbon Economic Dispatch of Industrial-Park Integrated Electricity–Heat–Hydrogen Energy Systems

グラフ時空間ワールドモデル駆動型ローリングMPCによる産業団地統合電力・熱・水素エネルギーシステムの低炭素経済ディスパッチ (AI 翻訳)

Junling Liu, W. Xiaojun, Leilei Wang, Yu Song

Electronics📚 査読済 / ジャーナル2026-05-22#エネルギー転換Origin: CN
DOI: 10.3390/electronics15112231
原典: https://doi.org/10.3390/electronics15112231

🤖 gxceed AI 要約

日本語

本論文は、産業団地の統合電力・熱・水素エネルギーシステム（IEHES）の低炭素経済ディスパッチ問題に対して、グラフ時空間ワールドモデル駆動型のローリングMPCフレームワーク（GraphWorldModel_MPC）を提案する。提案手法は、グラフベースの表現でシステムの結合関係を捉え、物理整合性を考慮した状態遷移学習を実現。ケーススタディでは、月間総運用コストを6.07%削減し、等価炭素排出量を6.89%低減しながら、制約違反ゼロを達成した。

English

This paper proposes a graph spatiotemporal world-model-driven rolling MPC framework (GraphWorldModel_MPC) for low-carbon economic dispatch of industrial-park integrated electricity-heat-hydrogen energy systems. The method captures coupling relationships via a graph representation and learns multi-step state transitions with physics-consistency constraints. Case studies show a 6.07% reduction in monthly operating cost and 6.89% reduction in equivalent carbon emissions compared to conventional EMPC, with zero dispatch violations.

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、産業団地のエネルギー管理と脱炭素化が重要課題となっている。本手法は水素を含むマルチエネルギーシステムの最適運用を実現し、SSBJや有価証券報告書における非財務情報開示のエネルギー効率改善指標として活用可能な実証データを提供する。

In the global GX context

Globally, this paper contributes to the optimization of integrated energy systems with hydrogen, addressing both economic and carbon reduction targets. It demonstrates a data-driven MPC approach that could inform similar efforts in industrial parks worldwide, aligning with ISSB and CSRD requirements for climate resilience and low-carbon operations.

👥 読者別の含意

🔬研究者:A novel graph-based world model for multi-energy dispatch that balances economy and low-carbon operation; relevant for MPC and energy system optimization research.

🏢実務担当者:Can be applied to industrial park energy management systems to achieve cost savings and carbon reductions with guaranteed constraint satisfaction.

🏛政策担当者:Demonstrates feasibility of low-carbon dispatch with zero violations, supporting industrial decarbonization policy and technology deployment.

📄 Abstract（原文）

Industrial-park integrated electricity–heat–hydrogen energy systems (IEHESs) face a challenging rolling dispatch problem because strong multi-energy coupling, intertemporal storage dynamics, and forecast uncertainty make it difficult to achieve economy, low-carbon operation, and hard-constraint feasibility simultaneously. To address this issue, this paper proposes a graph spatiotemporal world-model-driven rolling model predictive control (MPC) framework, termed GraphWorldModel_MPC, for low-carbon economic dispatch of industrial-park IEHESs. First, a unified graph-based representation is constructed to characterize the topology-aware coupling relationships among the electricity, heat, and hydrogen subsystems. Second, a graph spatiotemporal world model is developed to learn multi-step state transitions, while constraint-aligned physics-consistency terms are incorporated to align the predicted trajectories with multi-energy balance, storage-boundary evolution, and ramping semantics. In addition, the learned dynamics are embedded into a hard-constrained economic MPC framework, and a quantile-based safety-tightening mechanism is adopted to mitigate residual prediction uncertainty and enhance closed-loop feasibility. Case studies on an industrial-park IEHES show that the proposed method achieves an average 24-step normalized root mean square error (NRMSE) of 4.28% and reduces the monthly total operating cost by 6.07%, 3.83%, and 10.79% compared with conventional economic MPC (EMPC), distributionally robust adaptive MPC (DRAMPC), and GRU-MPC, respectively. It also reduces equivalent carbon emissions by 6.89%, 4.52%, and 9.50% relative to these benchmarks, while maintaining zero dispatch violations in the tested monthly horizon.

🔗 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。