Graph-X: 価格予測とリスク考慮型仮想発電所の市場参加のためのグラフ構造深層学習
Graph-X: Graph-Structured Deep Learning for Price Forecasting and Risk-Aware Virtual Power Plant Market Participation (原題)
Usama Aslam, Vikram Kumar, Muhammad Ahsan Niazi, S. Hassan
🤖 gxceed AI 要約
日本語
本論文は、仮想発電所（VPP）の市場参加における価格変動と運用不確実性に対処するため、グラフ構造深層学習と確率最適化を統合したフレームワークGraph-Xを提案する。入札を価格・数量グラフとして表現し、スパースグラフ畳み込みや時間畳み込みを用いて市場清算行動をモデル化する。予測はスペクトルリスク尺度に基づく確率的入札モデルに統合され、ISOニューイングランドの実データでMAE 1.81 $/MWh、R2 0.944を達成し、利益を18.1%向上させた。
English
This paper proposes Graph-X, a unified graph-structured deep learning and stochastic optimization framework for day-ahead electricity price forecasting and risk-aware VPP bidding. It models market-clearing behavior by converting bids into price-quantity graphs, integrating sparse graph convolutions and temporal learning. Validated on ISO New England data, it achieves MAE 1.81 $/MWh and R2 0.944, improving VPP profitability by 18.1%.
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
日本では再エネ導入拡大に伴いVPPの重要性が高まっており、本手法は需給調整市場や容量市場での入札戦略に応用可能。SSBJ開示や再エネ調達の効率化にも寄与する可能性がある。
In the global GX context
Globally, VPPs are key to integrating renewables and enhancing grid flexibility. This work advances AI-driven market participation, aligning with energy transition goals and providing a framework for risk-aware bidding in liberalized markets.
👥 読者別の含意
🔬研究者:Provides a novel graph-based deep learning approach for price forecasting and risk-aware bidding, with strong empirical results.
🏢実務担当者:Offers a practical tool for VPP operators to optimize bidding strategies and improve profitability.
🏛政策担当者:Demonstrates how AI can enhance market efficiency and renewable integration, informing market design.
📄 Abstract（原文）
The increasing integration of distributed energy resources, renewable generation, and flexible loads has made Virtual Power Plant (VPP) market participation highly exposed to price volatility and operational uncertainty. This paper proposes Graph-X, a unified graph-structured deep learning and stochastic optimization framework for day-ahead electricity price forecasting and risk-aware VPP bidding. Unlike conventional temporal forecasting models, Graph-X captures structural market-clearing behavior by converting raw bids into continuous differentiable curves represented on a discrete price–quantity graph. The proposed architecture combines sparse graph convolutions, recurrent temporal learning, dilated temporal convolutions, and cyclical calendar encodings to model spatial, temporal, and operational market dependencies. Forecasts are further integrated with a stochastic bidding model governed by a coherent spectral risk measure to align prediction accuracy with financial performance. The framework is validated using historical hourly data from the ISO New England day-ahead electricity market. Results show that Graph-X achieves an MAE of 1.81 $/MWh and an R2 score of 0.944, outperforming GNN, LSTM, Transformer, and ARIMA baselines. In VPP bidding, Graph-X delivers an average daily profit of 52.3 k$, improving profitability by 18.1% (equivalent to $2.92 annually) over the GNN baseline, with an average inference time of 12.5 ms per forecast.
🔗 Provenance — このレコードを発見したソース
- semanticscholar https://doi.org/10.3390/math14162974first seen 2026-08-20 05:28:37 · last seen 2026-09-21 05:22:35
🔔 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。