.png){kind=icon}
.png){kind=icon}
Return
Power system state estimation based on graph contrastive learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2025.126571.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The efficient and stable operation of power systems relies on accurate state estimation. Traditional state estimation methods usually involve solving a minimization problem iteratively using Gauss-Newton methods, however, these methods still have some limitations, such as numerical instability and issues like the convergence time depending on the initial point. To solve the above problems, this paper proposes, for the first time, a data-driven state estimation model based on graph contrastive learning (GCLSE for short). Specifically, the model introduces the Bootstrapped Representation Learning on Graphs (BGRL) framework, effectively addressing the issue of large estimation errors in the presence of noise. We also propose a graph augmentation method using edge feature masking to preserve the topology of the power system. To comprehensively capture the features of nodes and edges in the power grid, the model introduces a novel hybrid encoder, which combines an Edge-Conditioned Convolutional Neural Network (ECC) with self-attention mechanisms and residual blocks, and a Graph Convolutional Network (GCN) incorporating dynamic propagation strategies and gating mechanisms. The model proposes a dual optimization strategy combining contrastive loss and node state prediction loss, which optimizes model parameters while also improving state estimation accuracy. Experiments were conducted on the IEEE 39-bus system and the ACTIVSg2000 system using the base case and N-1 contingency topologies. Results show that the GCLSE model achieves lower estimation errors for voltage magnitude and voltage angle differences compared to existing benchmark models. The GCLSE model can also be used to provide abetter initial guess for the WLS method, which results in faster convergence as well as shorter computation time. Estimation error of the proposed methods meets the practical engineering requirements for state estimation and complies with the GBT standard's 2.5% error threshold.
Keywords:
Graph contrastive learning
State estimation
Graph Convolutional Network
Edge-conditioned convolutional neural networks
Graph augmentation
Journal
IF:
7.5
Papers:
2.9W
Citations:
10.2W