Modeling the AC power flow equations with optimally compact neural networks: Application to unit commitment

Kody, Alyssa; Chevalier, Samuel; Chatzivasileiadis, Spyros; Molzahn, Daniel K.

doi:10.1016/j.epsr.2022.108282

Cited by 24 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model applied data-filtering techniques to distinguish high-quality data for training and improving the model's accuracy. The researchers in [43] developed an optimally compact NN model by transforming the nonlinearities of PF equations into piecewise linear approximations using mixed integer linear programs (MILPs). The proposed strategy allows for maintaining a high number of binary variables that are used for unit commitment.…”

Section: Related Workmentioning

confidence: 99%

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

Tiwari,

Zideh,

Talreja

et al. 2024

IEEE Access

View full text Add to dashboard Cite

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 strength of the proposed DNN models over the traditional iterative-based PF solvers is that these models can capture the nonlinear relationships in PF calculations to accurately predict the 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 which demonstrate that all three DNN models provide highly accurate results in predicting PF solutions.INDEX TERMS Power flow analysis, deep neural networks, radial basis function networks, multi-layer perceptron, convolutional neural networks, unbalanced power distribution grids.The associate editor coordinating the review of this manuscript and approving it for publication was Ehab Elsayed Elattar .

show abstract

Section: Related Workmentioning

confidence: 99%

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

Tiwari,

Zideh,

Talreja

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Neural networks to aid optimization. Using the mixed-integer neural network (NN) reformulation [32,35,14], NNs can be used for approximating complex input-output dependencies within optimization, e.g., in power systems problems [20,10,16,18]. The reformulation represents the activation of each ReLU function using linear and binary constraints parameterized by NN weights and biases, which can be computationally challenging at scale [14].…”

Section: Related Workmentioning

confidence: 99%

Emission-Aware Optimization of Gas Networks: Input-Convex Neural Network Approach

Dvorkin¹,

Chevalier²,

Chatzivasileiadis³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Gas network planning optimization under emission constraints prioritizes gas supply with the least CO 2 intensity. As this problem includes complex physical laws of gas flow, standard optimization solvers cannot guarantee convergence to a feasible solution. To address this issue, we develop an input-convex neural network (ICNN) aided optimization routine which incorporates a set of trained ICNNs approximating the gas flow equations with high precision. Numerical tests on the Belgium gas network demonstrate that the ICNN-aided optimization dominates non-convex and relaxation-based solvers, with larger optimality gains pertaining to stricter emission targets. Moreover, whenever the non-convex solver fails, the ICNN-aided optimization provides a feasible solution to network planning.Preprint. Under review.

show abstract

“…In response to these challenges, several authors propose the application of neural networks and machine learning in OPF. Various articles explore the intersection of OPF and neural networks [16], [18], [19], leveraging these technologies to enhance the speed and efficiency of studies. Recent trends indicate a growing preference for machine learning in solving AC optimal power flow due to the significant runtime speedup compared to traditional optimization techniques.…”

Section: Introductionmentioning

confidence: 99%

Optimal Power Flow with Physics-informed Typed Graph Neural Networks

Lopez-Garcia,

Domínguez-Navarro

2024

IEEE Trans. Power Syst.

View full text Add to dashboard Cite

This work describes a new way to solve the optimal power flow problem applying typed graph neural networks. Typed graph neural networks allow the representation of different elements of transmission systems with different types of nodes, thus adding accuracy and interpretability to the solutions obtained, in comparison to results obtained with conventional feed-forward neural network models. The proposed graph neural network architecture is trained without the need of training data, through a physics informed loss function which incorporates not only the optimization objective, but also operational constraints of the physical system. Results are comparable with those obtained with the interior point method, and it is shown that the calculation time is greatly reduced.

show abstract

Modeling the AC power flow equations with optimally compact neural networks: Application to unit commitment

Cited by 24 publications

References 22 publications

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

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

Emission-Aware Optimization of Gas Networks: Input-Convex Neural Network Approach

Optimal Power Flow with Physics-informed Typed Graph Neural Networks

Contact Info

Product

Resources

About