Machine Learning-Aided Security Constrained Optimal Power Flow

Rahman, Jubeyer; Feng, Cong; Zhang, Jie

doi:10.1109/pesgm41954.2020.9281941

Cited by 17 publications

(7 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first metric η 1 is the DNN validation loss, which is defined in (7). The second metric η 2 is the accuracy of the state parameters, defined in (13), where 2|G|− 1 is the dimension of DNN output, ŷ(m) k,d is the predicted state parameter and y Gi ), and introduced in (3). The third metric η 3 is defined in (14), where ĉost…”

Section: A Algorithms and Metricsmentioning

confidence: 99%

“…For instance, [12] proposes a stacked extreme learning machine to speedup the parameter tuning process and reduce the learning complexity. Reference [13] builds a random forest model to calculate a near-optimal OPF solution and to perform post-contingency analysis. Further, [14] compares the performance of OPF solvers developed according to different ML methods (random forest, multitarget decision tree, and extreme learning machine).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Chen

Lakshminarayana

Maple

et al. 2022

IEEE Open J. Power Energy

View full text Add to dashboard Cite

Recently there has been a surge of interest in adopting deep neural networks (DNNs) for solving the optimal power flow (OPF) problem in power systems. Computing optimal generation dispatch decisions using a trained DNN takes significantly less time when compared to conventional optimization solvers. However, a major drawback of existing work is that the machine learning models are trained for a specific system topology. Hence, the DNN predictions are only useful as long as the system topology remains unchanged. Changes to the system topology (initiated by the system operator) would require retraining the DNN, which incurs significant training overhead and requires an extensive amount of training data (corresponding to the new system topology). To overcome this drawback, we propose a DNN-based OPF predictor that is trained using a meta-learning (MTL) approach. The key idea behind this approach is to find a common initialization vector that enables fast training for any system topology. The developed OPF-predictor is validated through simulations using benchmark IEEE bus systems. The results show that the MTL approach 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.

show abstract

Section: A Algorithms and Metricsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

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

Chen

Lakshminarayana

Maple

et al. 2022

IEEE Open J. Power Energy

View full text Add to dashboard Cite

show abstract

“…First, it is checked to see whether it violates the minimum and maximum generating limits. If the generation points are violated, the points are set within the generation limits by using (16) ,min i g P are the real powergeneration dispatch, and the minimum and maximum levels of the generation power of the ith generator.…”

Section: The Post-processing Phasementioning

confidence: 99%

“…The results showed that, compared with a stateof-the-art solver, DeepOPF provided viable solutions with less than 0.2% optimality loss, while reducing the computation time by up to two orders of magnitude. In [16], a multi-inputmulti-output (MIMO) random forest model was applied to obtain network voltages and bus angles. Subsequently, network equations were used to calculate the current injection, as well as the real and reactive power injections at various buses.…”

Section: Introductionmentioning

confidence: 99%

A Deep Neural Network-Based Optimal Power Flow Approach for Identifying Network Congestion and Renewable Energy Generation Curtailment

Zafar

Chung

2022

IEEE Access

View full text Add to dashboard Cite

Herein, we propose a novel method for identifying power congestion and renewable-energy source (RES) power curtailment in power grids by using deep neural network (DNN)-based optimal power flow (OPF) analysis. Synthetic data for load demand and RES power generation are used to obtain the OPF solutions by using an OPF solver. RES locations are selected based on an analysis of the congestion cases, and the DNN is trained by using the load demand and RES power as inputs and the OPF solution as the output. Thereafter, post-processing is performed on the DNN-OPF output by using network information. The final results show the accuracies of identified values on RES curtailment, line loading, generation dispatch schedule, and total generation operating cost. The IEEE 39-bus system was adopted as a case study to validate the proposed model. The results demonstrate that the proposed scheme is much faster and more suitable for transmission systems than conventional OPF methods. Furthermore, the normalized root-mean-squared error was less than 1%, and the computational time was more than 30 times faster than conventional OPF analysis.INDEX TERMS Deep neural network, Network congestion, Optimal power flow, Power curtailment, Renewable energy sources.

show abstract

“…With voltages predicted by the welltrained DNNs, all remaining variables (i.e., power generations) can be obtained via simple matrix operation. Reference [10] also learns the mapping between loads and voltages using random forest, but it does not consider feasibility and needs a strong assumption to enforce power balance constraints. The main contributions of this study are summarized as below:…”

Section: Introductionmentioning

confidence: 99%

DeepOPF-V: Solving AC-OPF Problems Efficiently

Huang

Pan

Chen

et al. 2022

IEEE Trans. Power Syst.

View full text Add to dashboard Cite

AC optimal power flow (AC-OPF) problems need to be solved more frequently in the future to maintain stable and economic operation. To tackle this challenge, a deep neural network-based voltage-constrained approach (DeepOPF-V) is proposed to find feasible solutions with high computational efficiency. It predicts voltages of all buses and then uses them to obtain all remaining variables. A fast post-processing method is developed to enforce generation constraints. The effectiveness of DeepOPF-V is validated by case studies of several IEEE test systems. Compared with existing approaches, DeepOPF-V achieves a state-of-art computation speedup up to three orders of magnitude and has better performance in preserving the feasibility of the solution.

show abstract

Machine Learning-Aided Security Constrained Optimal Power Flow

Cited by 17 publications

References 9 publications

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

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

A Deep Neural Network-Based Optimal Power Flow Approach for Identifying Network Congestion and Renewable Energy Generation Curtailment

DeepOPF-V: Solving AC-OPF Problems Efficiently

Contact Info

Product

Resources

About