Analytical Probabilistic Power Flow Approximation Using Invertible Neural Networks
This addresses operational uncertainty in distribution systems with renewable energy, offering a more efficient and accurate alternative to Monte Carlo simulations, though it is incremental in applying invertible neural networks to this domain.
The paper tackles the computational intensity and accuracy trade-offs in probabilistic power flow analysis for distribution systems by proposing a framework using invertible neural networks to approximate voltage distributions analytically, achieving state-of-the-art performance as both a power flow solver and estimator.
Probabilistic power flow (PPF) is essential for quantifying operational uncertainty in modern distribution systems with high penetration of renewable generation and flexible loads. Conventional PPF methods primarily rely on Monte Carlo (MC) based power flow (PF) simulations or simplified analytical approximations. While MC approaches are computationally intensive and demand substantial data storage, analytical approximations often compromise accuracy. In this paper, we propose a novel analytical PPF framework that eliminates the dependence on MC-based PF simulations and, in principle, enables an approximation of the analytical form of arbitrary voltage distributions. The core idea is to learn an explicit and invertible mapping between stochastic power injections and system voltages using invertible neural networks (INNs). By leveraging the Change of Variable Theorem, the proposed framework facilitates direct approximation of the analytical form of voltage probability distributions without repeated PF computations. Extensive numerical studies demonstrate that the proposed framework achieves state-of-the-art performance both as a high-accuracy PF solver and as an efficient analytical PPF estimator.