Machine Learning Accelerated Real-Time Model Predictive Control for Power Systems
Machine Learning Accelerated Real-Time Model Predictive Control for Power Systems
复制标题
DOI：
10.1109/jas.2023.123135
复制
发表时间：
2023-04
期刊：
影响因子：
--
通讯作者：
Ramij Raja Hossain;Ratnesh Kumar
中科院分区：
文献类型：
--
作者：
Ramij Raja Hossain;Ratnesh Kumar
针对电力系统紧急稳压中模型预测控制(MPC)的实时实现问题，提出了一种基于机器学习的加速策略。尽管在各种应用中取得了成功，但由于大型复杂系统需要在线控制计算时间，预测控制在电力系统中的实时实现并不成功，而在电力系统中，计算时间在很大程度上超过了实际使用的可用决策时间。本文通过开发一种基于预测控制的新型框架来解决这一长期存在的问题，该框架i)在离线设置下计算额定负荷的最优策略，并通过利用最新测量数据在每个控制时刻进行连续的在线控制校正来使其适应实时场景；ii)采用基于机器学习的方法来预测电压轨迹及其对控制输入的灵敏度，从而将整体控制计算速度提高数倍。此外，还提出了一种在静止无功补偿器(SVC)、切负荷(LS)和有载调压开关(LTC)之间实现控制协调的方案，该方案结合了LTC的实际延迟动作。针对IEEE9节点和39节点系统，在额定负荷变化为±20%的情况下验证了所提方案的性能。结果表明，该方法将在线计算速度提高了20倍，使其降到了一个实际可行的值(几分之一秒)，首次实现了电力系统控制中预测控制的实时性和可行性。
This paper presents a machine-learning-based speed-up strategy for real-time implementation of model-predictive-control (MPC) in emergency voltage stabilization of power systems. Despite success in various applications, real-time implementation of MPC in power systems has not been successful due to the online control computation time required for large-sized complex systems, and in power systems, the computation time exceeds the available decision time used in practice by a large extent. This long-standing problem is addressed here by developing a novel MPC-based framework that i) computes an optimal strategy for nominal loads in an offline setting and adapts it for real-time scenarios by successive online control corrections at each control instant utilizing the latest measurements, and ii) employs a machine-learning based approach for the prediction of voltage trajectory and its sensitivity to control inputs, thereby accelerating the overall control computation by multiple times. Additionally, a realistic control coordination scheme among static var compensators (SVC), load-shedding (LS), and load tap-changers (LTC) is presented that incorporates the practical delayed actions of the LTCs. The performance of the proposed scheme is validated for IEEE 9-bus and 39-bus systems, with ±20% variations in nominal loading conditions together with contingencies. We show that our proposed methodology speeds up the online computation by 20-fold, bringing it down to a practically feasible value (fraction of a second), making the MPC real-time and feasible for power system control for the first time.