物理嵌入式图形卷积神经网络用于电流计算,考虑不确定注入和拓
概括
一个新的模型驱动的图形卷积神经网络 (MD-GCN) 为电力系统提供了高效和强大的功率流计算. 这种方法可以提高精度,尽管电源注入不确定,网络拓也在变化.
科学领域:
- 电气工程 电气工程
- 计算科学 计算科学
- 人工智能的人工智能
背景情况:
- 概率性电力系统分析需要高效的电力流量计算来量化不确定性影响.
- 现有的数据驱动方法缺乏对不确定的注入和拓变化的稳定性.
- 重复的功率流量计算的计算负担阻碍了实时操作分析.
研究的目的:
- 提出一种新的模型驱动的图形卷积神经网络 (MD-GCN),用于增强的功率流计算.
- 为了提高电力系统运行的计算效率和稳定性.
- 解决传统和数据驱动的功率流分析方法的局限性.
主要方法:
- 开发了一个模型驱动的图形卷积神经网络 (MD-GCN),通过嵌入线性化功率流模型到层wise传播.
- 实现了一个新的输入特征构建方法,具有多个社区聚合和全球聚合层.
- 集成的物理连接关系和系统范围的影响,用于全面的特征表示.
主要成果:
- MD-GCN表现出高计算效率和对拓变化的优越稳定性.
- 提出的方法显著优于IEEE标准系统 (30,57,118和1354-bus) 的现有方法.
- 通过邻里聚合和全球聚合提高了特征提取的准确性.
结论:
- MD-GCN提供了一个有效的解决方案,用于在不确定性下准确和高效的功率流量计算.
- 通过结合物理功率流原理,增强了模型的解释性.
- 该方法是可扩展和强大的,用于分析大规模的电力系统.
相关概念视频
The Power Flow Problem and Solution
263
Power flow problem analysis is fundamental for determining real and reactive power flows in network components, such as transmission lines, transformers, and loads. The power system's single-line diagram provides data on the bus, transmission line, and transformer. Each bus k in the system is characterized by four key variables: voltage magnitude Vk, phase angle δk, real power Pk, and reactive power Qk. Two of these four variables are inputs, while the...
263
Fast Decoupled and DC Powerflow
239
The fast decoupled power flow method addresses contingencies in power system operations, such as generator outages or transmission line failures. This method provides quick power flow solutions, essential for real-time system adjustments. Fast decoupled power flow algorithms simplify the Jacobian matrix by neglecting certain elements, leading to two sets of decoupled equations:
239
Maximum Power Flow and Line Loadability
138
The maximum power flow for lossy transmission lines is derived using ABCD parameters in phasor form. These parameters create a matrix relationship between the sending-end and receiving-end voltages and currents, allowing the determination of the receiving-end current. This relationship facilitates calculating the complex power delivered to the receiving end, from which real and reactive power components are derived.
138
Calculation of Electric Flux
1.8K
Consider the electric field of an oppositely charged, parallel-plate system and an imaginary box between those plates. Let the bottom face of the box be ABCD, and the top face be FGHK. The electric field between the plates is uniform and points from the positive plate toward the negative plate. The calculation of this field's flux through the box's various faces shows that the net flux through the box is zero. Why does the flux cancel out here?
1.8K
Control of Power Flow
292
There are several methods to control power flow in power systems:
292
Calculations of Electric Potential I
2.0K
Consider a ring of radius R with a uniform charge density λ. What will the electric potential be at point M, which is located on the axis of the ring at a distance x from the center of the ring?
The ring is divided into infinitesimal small arcs such that point M is equidistant from all the arcs. Here, the cylindrical coordinate system is used to calculate the electric potential at point M. A general element of the arc between angles θ and θ + dθ is of the...
The ring is divided into infinitesimal small arcs such that point M is equidistant from all the arcs. Here, the cylindrical coordinate system is used to calculate the electric potential at point M. A general element of the arc between angles θ and θ + dθ is of the...
2.0K


