Hierarchical graph neural network improves power flow predictions under grid outages
Hierarchical Graph Neural Network for Probabilistic Power Flow with Grid Topology Contingencies
Graphics
Summary
Accurately predicting how power flows through an electrical grid is complicated, especially when parts of the grid fail unexpectedly. This paper describes a new computer model that breaks down the grid into smaller units to better understand changes when outages happen. The model uses a combination of simple electrical calculations and a special neural network to predict voltage and phase angle changes more accurately than existing methods, even when the grid layout changes. The authors tested their method on large realistic power grids and found it is both more precise and efficient than other approaches.
What this means in practice
- •For power grid operators: Improve accuracy and speed of power flow predictions during line outages to better manage grid stability and response.
- •For electrical system planners: Simulate grid behavior under various outage scenarios without costly repeated nonlinear solves, enabling faster contingency analysis.
Authors
Jinbao Wang, Jun Liu, Shiliang Zhang, Xuehui Ma, Lin Yan, Haolin Liu, Sabita Maharjan
Abstract
Data-driven surrogates reduce the nonlinear solves required for probabilistic power flow (PPF), but models tied to a fixed bus--branch graph often generalize poorly when outages change electrical coupling. This paper proposes a topology-decomposition-driven hierarchical bidirectional graph neural network (TDD--HBGNN) for PPF under unseen topologies. For each realized topology, the network is decomposed into fundamental topological units (FTUs), dynamically homogeneous voltage clusters (DHVCs), and a core backbone sub-grid (CBSG), with equivalent-admittance representations preserving electrical ports between units. A sensitivity-based linear prior captures the first-order voltage-magnitude and phase-angle response, while the HBGNN learns topology-dependent nonlinear residuals. Impedance- and uncertainty-aware bottom-up aggregation condenses local perturbations, while mode-modulated top-down broadcasting restores system context at buses. We evaluate our approach on the IEEE 118-bus and Polish 2746-bus systems under unseen N--1 and N--2 contingencies against six baseline methods. Compared with these methods, TDD--HBGNN achieves 2.47--4.20-fold lower all-bus phase-angle errors and lower phase-angle errors in every held-out event. Its voltage-magnitude advantage is concentrated near the outaged branches, where paired error ratios reach 1.75--2.58 on the IEEE system and 1.87--1.97 in Polish N--2 events. All system--contingency--baseline comparisons favor TDD--HBGNN in joint voltage--angle error. Moreover, shared hierarchical operators keep the model size at 0.658 million parameters across both grids and yield 0.161--1.793~ms forward latency per probabilistic case. These results demonstrate system-wide angular accuracy, outage-local voltage accuracy, and parameter-efficient scaling across unseen topologies.