Impedance-Aware Graph Convolutional Networks for Voltage Estimation in Active Distribution Networks
- The University of North Carolina at Charlotte
- University of North Carolina, Charlotte
- ORNL
Voltage estimation plays a key role in ensuring the effective control and reliability of distribution networks. However, traditional machine learning methods often fail to capture the details of the distribution network’s topology. To overcome this challenge, graph convolutional networks (GCN) have emerged as an alternative. Graph convolutional networks inherently capture the topology of the grid, utilizing correlations to achieve precise voltage estimation. Other machine learning models and conventional GCNs fail to account for the distribution line characteristics found in the real world, limiting their effectiveness. This paper proposes an advanced variant of GCN called the Impedance-Aware Graph Convolutional Network (IA-GCN). The IA-GCN layer incorporates the magnitude of the impedance into the graph convolution mechanism, allowing it to capture topological nuances and provide valuable insights into node interrelationships by considering impedance as an intrinsic dimension. The performance of the IA-GCN layer is then compared with that of GCN and GraphSAGE layers through a surrogate model for voltage estimation. The performance analysis demonstrates that IA-GCN outperforms GCN by reducing the MAE by 87.55% and improving the R-squared value by 98%.
- Research Organization:
- Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
- Sponsoring Organization:
- USDOE; USDOE Office of Electricity Delivery and Energy Reliability (OE)
- DOE Contract Number:
- AC05-00OR22725
- OSTI ID:
- 2477541
- Country of Publication:
- United States
- Language:
- English
Similar Records
Graph Convolutional Network-Based Topology Embedded Deep Reinforcement Learning for Voltage Stability Control
Probabilistic Physics-Informed Graph Convolutional Network for Active Distribution System Voltage Prediction