Power Flow Analysis Using Deep Neural Networks in Three-Phase Unbalanced Smart Distribution Grids

TL;DR

This work tackles efficient PF computation in unbalanced three-phase distribution grids with DER/EV penetration by framing PF as a multi-output regression problem learned by three DNNs: RBFnet, MLP, and CNN. Data for training and testing are generated with OpenDSS via a MATLAB interface, with inputs $X_i=[|V_i|, \theta_{V_i}, Z, P, Q]$ and outputs $X_o=[|V_i|, |I_i|, \theta_{V_i}, \theta_{I_i}, P_{l_{ij}}]$, all normalized prior to learning. Across IEEE 4-node, IEEE 123-bus, and AEP feeder test cases, the CNN generally achieves the lowest prediction error, with RBFN and MLP also delivering very low MAE/MSE; topology changes and DER/EV variability increase errors but remain within acceptable ranges. The results demonstrate that data-driven PF predictors can deliver accurate, scalable, and fast PF solutions suitable for real-time operation and planning, reducing reliance on traditional iterative methods while handling unbalanced operations and resource variability.

Abstract

Most power systems' approaches are currently tending towards stochastic and probabilistic methods due to the high variability of renewable sources and the stochastic nature of loads. Conventional power flow (PF) approaches such as forward-backward sweep (FBS) and Newton-Raphson require a high number of iterations to solve non-linear PF equations making them computationally very intensive. PF is the most important study performed by utility, required in all stages of the power system, especially in operations and planning. This paper discusses the applications of deep learning (DL) to predict PF solutions for three-phase unbalanced power distribution grids. Three deep neural networks (DNNs); Radial Basis Function Network (RBFnet), Multi-Layer Perceptron (MLP), and Convolutional Neural Network (CNN), are proposed in this paper to predict PF solutions. The PF problem is formulated as a multi-output regression model where two or more output values are predicted based on the inputs. The training and testing data are generated through the OpenDSS-MATLAB COM interface. These methods are completely data-driven where the training relies on reducing the mismatch at each node without the need for the knowledge of the system. The novelty of the proposed methodology is that the models can accurately predict the PF solutions for the unbalanced distribution grids with mutual coupling and are robust to different R/X ratios, topology changes as well as generation and load variability introduced by the integration of distributed energy resources (DERs) and electric vehicles (EVs). To test the efficacy of the DNN models, they are applied to IEEE 4-node and 123-node test cases, and the American Electric Power (AEP) feeder model. The PF results for RBFnet, MLP, and CNN models are discussed in this paper demonstrating that all three DNN models provide highly accurate results in predicting PF solutions.

Figures (6)

• Figure 1: Outline of Proposed Methodology
• Figure 2: Loadshape for load at bus 4.
• Figure 3: AEP feeder
• Figure 5: Simulation results of the DNN model for the AEP feeder for output voltage and current phasors.
• Figure 6: IEEE 123-Bus feeder with renewable energy sources