期刊
2023 IEEE BELGRADE POWERTECH
卷 -, 期 -, 页码 -出版社
IEEE
DOI: 10.1109/POWERTECH55446.2023.10202943
关键词
AC-OPF; Active power curtailment; Distribution systems; Machine learning; Voltage control; Volt-Var control
The concept of smart sustainable buildings is crucial for developing smart cities. This paper proposes a data-driven local control scheme for controllable devices in these buildings, using machine learning algorithms and historical data. The scheme improves the safety of distribution networks with a higher penetration rate of controllable devices.
The concept of smart sustainable buildings (SSBs) is an important part of the smart city. It includes a variety of controllable devices that provide flexibility to the grid and support its sustainable development. The best way to control these buildings is an undertreated question, with some going for centralized model-based approaches and others opting for local control schemes derived from data. In this paper, through AC-Optimal Power Flow (OPF) modeling of the distribution network, the optimal solution of each controllable equipment is obtained based on historical data. Next, we use machine learning algorithms to design data-driven local control schemes for each controllable device, which can approximate the optimal solution of AC-OPF. Then, the control scheme is applied to specific cases to verify its feasibility and viability as compared to the traditional OPF control scheme, which is popular within the research community. This scheme can promote the safe operation of distribution networks with higher penetration rate (30% to 50%) of controllable devices.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据