Back to Search
Dossier
一种基于凸约束学习的电力系统储能调度方法
InventionUnknown
7Claims · 3 independent
§ Ⅰ
Dossier Overview
Inventor
桑林卫; 刘静怡; 吴在军; 胡秦然
Filing Date
Aug 3, 2026
Publication Date
Oct 20, 2026
IPC Classification
H02J 3/466 (2026.01)H02J 3/48 (2026.01)H02J 3/32 (2026.01)H02J 3/11 (2026.01)H02J 3/06 (2026.01)H02J 3/175 (2026.01)G06F 30/27 (2020.01)G06Q 50/06 (2024.01)G06F 18/213 (2023.01)G06F 18/214 (2023.01)G06N 3/0464 (2023.01)G06N 3/048 (2023.01)G06N 3/084 (2023.01)H02J 101/20 (2026.01)H02J 101/40 (2026.01)H02J 103/30 (2026.01)H02J 103/35 (2026.01)H02J 105/52 (2026.01)G06F 111/04 (2020.01)G06F 119/04 (2020.01)G06F 119/08 (2020.01)G06F 119/14 (2020.01)
本发明公开了一种基于凸约束学习的电力系统储能调度方法，首先构建面向电力系统运行的、可显式反映灵活性资源物理约束的老化衰减模型，实现调度模型对设备真实状态的感知；其次，通过将变量网络与参数网络联合构建成满足凸性的神经结构，学习得到一类具备可解释性与凸性保证的代理约束模型，实现高精度过程逼近；最后，在保障可行性的前提下，将学习到的凸代理模型转化为线性或凸规划形式的可嵌入式约束，构建既能准确刻画灵活性资源复杂运行特性，又能满足凸优化可解性、可行性与高效求解要求的混合调度模型。
Sign in to read the full text
Claim 1 is shown. Create a free account to read all 7 claims, the full description, all drawings, translations and legal status.
- All claims
- Technical field
- Background
- Summary
- Drawing descriptions
- Detailed description
External Resources