2025-10-06 京都大学
京都大学情報学研究科の大塚敏之教授らは、日立製作所と共同で、地域ごとの価値観（CO₂削減・コスト・利便性など）をリアルタイムに反映して仮想発電所（VPP）を制御できる新技術を開発した。モデル予測制御（MPC）と選好学習（Preference Learning）を組み合わせ、価値観の変動に応じて分散エネルギー資源を最適運用。シミュレーションでは、CO₂排出量を最大20％削減、コストを16％低減できた。地域ニーズに応じた柔軟な電力制御を可能にし、脱炭素社会実現に貢献する。
コミュニティの価値観をリアルタイムに反映する仮想発電所のイメージ図
＜関連情報＞
- https://www.kyoto-u.ac.jp/ja/research-news/2025-10-06
- https://www.kyoto-u.ac.jp/sites/default/files/2025-10/web_2510_Ohtsuka-e04ba3df2675fe52b0ed2d60d339b863.pdf
コミュニティの選好を反映した仮想発電所のモデル予測配分制御 Model Predictive Allocation Control for Virtual Power Plants Reflecting Community Preferences
Shinji Ishihara and Toshiyuki Ohtsuka
2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC) Date Added to IEEE Xplore: 28 January 2026
DOI:https://doi.org/10.1109/SMC58881.2025.11342607
Abstract
Virtual Power Plants (VPPs) have been increasingly being used to achieve carbon neutrality in energy systems and to improve resilience. This study handled a control scheme for small-scale community-operated VPPs, which has attracted much attention in recent years. In such community-operated VPPs, operations are not limited to maximizing economic value, but are also focused on community preferences. In this study we proposed Model Predictive Allocation Control (MPAC), which enables VPPs to operate in a way that appropriately reflects community preferences. The MPAC formulates the energy resource allocation control by Model Predictive Control (MPC) and modifies the VPP operation by tuning the weight parameters of the MPC. Furthermore, the weight parameters can be tuned by a preference learning-based optimization algorithm to easily reflect the community’s decisions. We also compensate for the operational stability of the VPPs by using frequency stabilizing control in combination. The effectiveness of the proposed method was verified by experiments using numerical simulations.
