Learning Optimization Proxies for Large-Scale Security-Constrained Economic Dispatch
Learning Optimization Proxies for Large-Scale Security-Constrained Economic Dispatch
复制标题
DOI：
10.1016/j.epsr.2022.108566
复制
发表时间：
2021-12
期刊：
影响因子：
--
通讯作者：
Wenbo Chen;Seonho Park;Mathieu Tanneau;P. V. Hentenryck
中科院分区：
文献类型：
--
作者：
Wenbo Chen;Seonho Park;Mathieu Tanneau;P. V. Hentenryck
安全约束经济调度（SCED）是输电系统运营商（TSO）清理实时能源市场、同时确保电网可靠运行的基本优化模型。在运营不确定性日益增加的背景下，由于可再生能源发电机和分布式能源的渗透率不断提高，运营商必须持续实时监控风险，即他们必须快速评估系统在负载和可再生能源发电的各种变化下的行为。不幸的是，考虑到实时操作的严格限制，系统地解决每个此类场景的优化问题是不切实际的。为了克服这一限制，本文提出学习 SCED 的优化代理，即可以在毫秒内预测 SCED 最佳解决方案的机器学习（ML）模型。在对 MISO 市场出清优化进行原理性分析的推动下，本文提出了一种新颖的即时 ML 管道，该管道解决了学习 SCED 解决方案的主要挑战，即负载、可再生能源输出和生产成本的变化，以及承诺决策的组合结构。还提出了一种新颖的组合分类加回归架构，以进一步捕获 SCED 解决方案的行为。在法国传输系统上进行了数值实验，并证明了该方法能够在与实时操作兼容的时间范围内产生准确的优化代理，从而产生低于 1% 的相对误差。
The Security-Constrained Economic Dispatch (SCED) is a fundamental optimization model for Transmission System Operators (TSO) to clear real-time energy markets while ensuring reliable operations of power grids. In a context of growing operational uncertainty, due to increased penetration of renewable generators and distributed energy resources, operators must continuously monitor risk in real-time, i.e., they must quickly assess the system’s behavior under various changes in load and renewable production. Unfortunately, systematically solving an optimization problem for each such scenario is not practical given the tight constraints of real-time operations. To overcome this limitation, this paper proposes to learn an optimization proxy for SCED, i.e., a Machine Learning (ML) model that can predict an optimal solution for SCED in milliseconds. Motivated by a principled analysis of the market-clearing optimizations of MISO, the paper proposes a novel just-in-time ML pipeline that addresses the main challenges of learning SCED solutions, i.e., the variability in load, renewable output and production costs, as well as the combinatorial structure of commitment decisions. A novel combined classification-plus-regression architecture is also proposed, to further capture the behavior of SCED solutions. Numerical experiments are reported on the French transmission system, and demonstrate the approach’s ability to produce, within a time frame that is compatible with real-time operations, accurate optimization proxies that produce relative errors below 1%.