DeepOPF: Deep Neural Network for DC Optimal Power Flow

@article{Pan2019DeepOPFDN,
  title={DeepOPF: Deep Neural Network for DC Optimal Power Flow},
  author={Xiang Pan and Tianyu Zhao and Minghua Chen},
  journal={2019 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)},
  year={2019},
  pages={1-6}
}
  • Xiang PanTianyu ZhaoMinghua Chen
  • Published 11 May 2019
  • Computer Science
  • 2019 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)
We develop DeepOPF as a Deep Neural Network (DNN) based approach for solving direct current optimal power flow (DC-OPF) problems. DeepOPF is inspired by the observation that solving DC-OPF for a given power network is equivalent to characterizing a high-dimensional mapping between the load inputs and the dispatch and transmission decisions. We construct and train a DNN model to learn such mapping, then we apply it to obtain optimized operating decisions upon arbitrary load inputs. We adopt… 

Figures and Tables from this paper

DeepOPF: A Deep Neural Network Approach for Security-Constrained DC Optimal Power Flow

DeepOPF is inspired by the observation that solving SC-DCOPF problems for a given power network is equivalent to depicting a high-dimensional mapping from the load inputs to the generation and phase angle outputs and develops a post-processing procedure based on $\ell _1$-projection to ensure the feasibility of the obtained solution.

DeepOPF: deep neural networks for optimal power flow

DeepOPF leverages a DNN model to depict the high-dimensional load-to-solution mapping and can directly solve the OPF problem upon given load, excelling in fast computation process and desirable scalability.

DeepOPF+: A Deep Neural Network Approach for DC Optimal Power Flow for Ensuring Feasibility

The proposed DeepOPF+ approach improves over existing DNN-based schemes in that it ensures feasibility and achieves a consistent speed up performance in both light-load and heavy-load regimes and theoretically characterize the calibration magnitude necessary for ensuring universal feasibility.

DeepOPF: A Feasibility-Optimized Deep Neural Network Approach for AC Optimal Power Flow Problems

An efficient Deep Neural Network approach, DeepOPF, is developed to ensure the feasibility of the generated solution of the AC-OPF problem, by employing a penalty approach in training the DNN.

Learning to Optimize Power Distribution Grids using Sensitivity-Informed Deep Neural Networks

Numerical tests showcase that sensitivity-informed deep learning can enhance prediction accuracy in terms of mean square error (MSE) by 2-3 orders of magnitude at minimal computational overhead.

Learning to Solve the AC-OPF Using Sensitivity-Informed Deep Neural Networks

Numerical tests on three benchmark power systems corroborate the advanced generalization and constraint satisfaction capabilities for the OPF solutions predicted by an SI-DNN over a conventionally trained DNN, especially in low-data setups.

Model Information-Aided Deep Learning for Corrective AC Power flow

A novel model information-aided deep learning approach to approximate the corrective AC optimal power flow solution with proper model information with better performances in both training time and accuracy is presented.

A Meta-Learning Approach to the Optimal Power Flow Problem Under Topology Reconfigurations

This work proposes a DNN-based OPF predictor that is trained using a meta-learning (MTL) approach that achieves significant training speed-ups and requires only a few gradient steps with a few data samples to achieve high OPF prediction accuracy and outperforms other pretraining techniques.

Projection-aware Deep Neural Network for DC Optimal Power Flow Without Constraint Violations

  • Minsoo KimHongseok Kim
  • Computer Science, Engineering
    2022 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)
  • 2022
This is the first paper that guarantees no constraint violations of DC optimal power flow using deep neural network, and the proposed PA-DNN takes active power demand as an input and has a projection layer at the final layer.

DeepOPF-V: Solving AC-OPF Problems Efficiently

A deep neural network-based voltage-constrained approach to solve AC optimal power flow problems with a state-of-art computation speedup up to three orders of magnitude and has better performance in preserving the feasibility of the solution.
...

References

SHOWING 1-10 OF 44 REFERENCES

Efficient Representation and Approximation of Model Predictive Control Laws via Deep Learning

We show that artificial neural networks with rectifier units as activation functions can exactly represent the piecewise affine function that results from the formulation of model predictive control

Statistical Learning for DC Optimal Power Flow

An ensemble control policy is proposed that combines several basis policies to improve performance and is based on the observation that the OPF solution corresponding to a certain uncertainty realization is a basic feasible solution, which provides an affine control policy.

On Computational Issues of Market-Based Optimal Power Flow

The deregulated electricity market calls for robust optimal power flow (OPF) tools that can provide a) deterministic convergence; b) accurate computation of nodal prices; c) support of both smooth

Optimal power flow: a bibliographic survey II

Over the past half-century, Optimal Power Flow (OPF) has become one of the most important and widely studied nonlinear optimization problems. In general, OPF seeks to optimize the operation of

Optimal power flow: a bibliographic survey I

Over the past half-century, Optimal Power Flow (OPF) has become one of the most important and widely studied nonlinear optimization problems. In general, OPF seeks to optimize the operation of

Learning for Convex Optimization

This work considers the problem of using the information available through this solution process to directly learn the optimal solution as a function of the input parameters, thus reducing the need of solving computationally expensive large-scale parametric programs in real time.

A generalized quadratic-based model for optimal power flow

  • J. Momoh
  • Engineering
    Conference Proceedings., IEEE International Conference on Systems, Man and Cybernetics
  • 1989
A quadratic-based model of a power system is used to formulate a generalized optimum power system flow problem and the generalized algorithm using sensitivity of objective functions with optimal adjustments in the constraints yields a global optimal solution.

A Knowledge-Based Framework for Power Flow and Optimal Power Flow Analyses

A knowledge-based paradigm for PF and OPF analyses is used to extract complex features, hidden relationships, and useful hypotheses potentially describing regularities in the problem solutions from operation data-sets to reduce the complexity of power flow and optimal power flow problems.