Adaptive Informed Deep Neural Networks for Power Flow Analysis

TL;DR

This paper presents PINN4PF, a physics-informed neural network architecture that significantly improves power flow analysis accuracy and scalability in large-scale power systems by integrating system topology and nonlinear dynamics.

Contribution

The paper introduces a novel physics-informed deep neural network with a double-head architecture and topology-aware loss function for enhanced power flow analysis.

Findings

PINN4PF outperforms baselines by up to two orders of magnitude.

The architecture demonstrates high scalability to large power systems.

It effectively captures nonlinear power system dynamics.

Abstract

This study introduces PINN4PF, an end-to-end deep learning architecture for power flow (PF) analysis that effectively captures the nonlinear dynamics of large-scale modern power systems. The proposed neural network (NN) architecture consists of two important advancements in the training pipeline: (A) a double-head feed-forward NN that aligns with PF analysis, including an activation function that adjusts to the net active and reactive power injections patterns, and (B) a physics-based loss function that partially incorporates power system topology information through a novel hidden function. The effectiveness of the proposed architecture is illustrated through 4-bus, 15-bus, 290-bus, and 2224-bus test systems and is evaluated against two baselines: a linear regression model (LR) and a black-box NN (MLP). The comparison is based on (i) generalization ability, (ii) robustness, (iii) impact of training dataset size on generalization ability, (iv) accuracy in approximating derived PF quantities (specifically line current, line active power, and line reactive power), and (v) scalability. Results demonstrate that PINN4PF outperforms both baselines across all test systems by up to two orders of magnitude not only in terms of direct criteria, e.g., generalization ability, but also in terms of approximating derived physical quantities.