Data-Driven Optimal Power Flow: A Physics-Informed Machine Learning Approach

  title={Data-Driven Optimal Power Flow: A Physics-Informed Machine Learning Approach},
  author={Xingyu Lei and Zhifang Yang and Juan Yu and Junbo Zhao and Qian Gao and Hongxin Yu},
  journal={IEEE Transactions on Power Systems},
This paper proposes a data-driven approach for optimal power flow (OPF) based on the stacked extreme learning machine (SELM) framework. SELM has a fast training speed and does not require the time-consuming parameter tuning process compared with the deep learning algorithms. However, the direct application of SELM for OPF is not tractable due to the complicated relationship between the system operating status and the OPF solutions. To this end, a data-driven OPF regression framework is… 

Review of Learning-Assisted Power System Optimization

A series of typical references are selected and categorized into four kinds: the boundary parameter improvement, the optimization option selection, the surrogate model and the hybrid model, providing a novel perspective to understand the latest research progress and achievements.

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.

Fast Inverter Control by Learning the OPF Mapping using Sensitivity-Informed Gaussian Processes

Fast inverter control is a desideratum towards the smoother integration of renewables. Adjusting inverter injection setpoints for distributed energy resources can be an effective grid control

Explicit Data-Driven Small-Signal Stability Constrained Optimal Power Flow

This paper proposes a data-driven small-signal stability constrained optimal power flow (SSSC-OPF) method with high computational efficiency and economic benefits, and uses the support vector machine with a kernel function to derive the explicit data- driven surrogate constraint for small- signal stability.

Deep Active Learning for Solvability Prediction in Power Systems

A deep active learning framework for power system solvability prediction is proposed, where the acquisition functions, which correspond to different sampling strategies, are defined in terms of the on-the-fly posterior probability from the classifier.

A Data-Driven Genetic Algorithm for Power Flow Optimization in the Power System With Phase Shifting Transformer

Phase-shifting transformer (PST) is one of the flexible AC transmission technologies to solve the problem of uneven power transmission. Considering that PST can also be used as a regulation means for

Sampling Strategies for Static Powergrid Models

The Correlation Sampling algorithm is proposed and it is shown that this approach is able to cover a larger area of the sampling space compared to different random sampling algorithms from the literature and a copula-based approach, while at the same time inter-dependencies of the inputs are taken into account, which, from the other algorithms, only the copula -based approach does.

Deep Reinforcement Learning for Optimal Power Flow with Renewables Using Graph Information

A deep reinforcement learning (DRL)-based strategy leveraging spatial-temporal graphical correlations and features of power systems, to dynamically search for the optimal power (OPF) of power Systems with a high uptake of RERs, and demonstrates that the algorithm outperforms other benchmark algorithms.

Data-Driven Electricity Price Risk Assessment for Spot Market

Electricity price risk assessment (EPRA) is essential for spot market analysis and operation. The statistical moments (i.e., the mean and standard deviation) of the price need to be assessed to



Fast Calculation of Probabilistic Power Flow: A Model-Based Deep Learning Approach

A model-based deep learning approach to overcome the computational challenge of Probabilistic power flow by using a deep neural network to approximate the power flow calculation and is trained according to the physical power flow equations.

Short-Term Wind Speed Forecasting via Stacked Extreme Learning Machine With Generalized Correntropy

An enhanced SELM is developed via replacing the Euclidean norm of the mean square error (MSE) criterion in ELM with the generalized correntropy criterion to further improve the forecasting performance.

Data-Driven Probabilistic Optimal Power Flow With Nonparametric Bayesian Modeling and Inference

Numerical results show the feasibility and superiority of the proposed DPMM-based POPF algorithm for better informed decision-making in power systems with high level of uncertainties.

Data-Driven Power Flow Linearization: A Regression Approach

The results show that the proposed approach can realize a higher calculation accuracy than model-based approaches can, and the obtained regression parameter matrices of data-driven models reflect power system physics by demonstrating similar patterns with some power system matrices.

Extreme learning machine: Theory and applications

MPLP-Based Fast Power System Reliability Evaluation Using Transmission Line Status Dictionary

A fast reliability evaluation method that accelerates the calculation of the OPF using multi-parametric linear programming (MPLP) and improves the evaluation efficiency by 23–30 times compared with the normal DC-OPF-based model.

Stacked Extreme Learning Machines

A stacked ELMs (S-ELMs) that is specially designed for solving large and complex data problems and can achieve much better testing accuracy than SVM and slightly better accuracy than deep belief network (DBN) with much faster training speed is proposed.

Cumulant-based probabilistic optimal power flow (P-OPF) with Gaussian and gamma distributions

This paper introduces the cumulant method for the probabilistic optimal power flow (P-OPF) problem. By noting that the inverse of the Hessian used in the logarithmic barrier interior point can be

Data-Based Distributionally Robust Stochastic Optimal Power Flow—Part I: Methodologies

A data-based method to solve a multi-stage stochastic optimal power flow (OPF) problem based on limited information about forecast error distributions and utilizes the Wasserstein metric to quantify differences between the empirical data- based distribution and the real unknown data-generating distribution.