Power Flow Analysis Using Deep Neural Networks in Three-Phase Unbalanced Smart Distribution Grids
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...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10444519/ |
| _version_ | 1797289793208451072 |
|---|---|
| author | Deepak Tiwari Mehdi Jabbari Zideh Veeru Talreja Vishal Verma Sarika Khushalani Solanki Jignesh Solanki |
| author_facet | Deepak Tiwari Mehdi Jabbari Zideh Veeru Talreja Vishal Verma Sarika Khushalani Solanki Jignesh Solanki |
| author_sort | Deepak Tiwari |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-07T19:11:08Z |
| format | Article |
| id | doaj.art-3d36e2636e4a437a8fdc00f9b9221bee |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-07T19:11:08Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-3d36e2636e4a437a8fdc00f9b9221bee2024-03-01T00:01:03ZengIEEEIEEE Access2169-35362024-01-0112299592997010.1109/ACCESS.2024.336906810444519Power Flow Analysis Using Deep Neural Networks in Three-Phase Unbalanced Smart Distribution GridsDeepak Tiwari0https://orcid.org/0000-0001-7275-3528Mehdi Jabbari Zideh1https://orcid.org/0000-0001-7297-4021Veeru Talreja2https://orcid.org/0000-0003-3009-9120Vishal Verma3Sarika Khushalani Solanki4https://orcid.org/0000-0002-7584-9661Jignesh Solanki5https://orcid.org/0000-0002-4317-1892Commonwealth Edison (ComEd), Chicago, IL, USALane Department of Computer Science and Electrical Engineering, West Virginia University, Morgantown, WV, USAProduct Development, VelocityEHS, Chicago, IL, USAElectric Power Research Institute (EPRI), Knoxville, TN, USALane Department of Computer Science and Electrical Engineering, West Virginia University, Morgantown, WV, USALane Department of Computer Science and Electrical Engineering, West Virginia University, Morgantown, WV, USAMost 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.https://ieeexplore.ieee.org/document/10444519/Power flow analysisdeep neural networksradial basis function networksmulti-layer perceptronconvolutional neural networksunbalanced power distribution grids |
| spellingShingle | Deepak Tiwari Mehdi Jabbari Zideh Veeru Talreja Vishal Verma Sarika Khushalani Solanki Jignesh Solanki Power Flow Analysis Using Deep Neural Networks in Three-Phase Unbalanced Smart Distribution Grids IEEE Access Power flow analysis deep neural networks radial basis function networks multi-layer perceptron convolutional neural networks unbalanced power distribution grids |
| title | Power Flow Analysis Using Deep Neural Networks in Three-Phase Unbalanced Smart Distribution Grids |
| title_full | Power Flow Analysis Using Deep Neural Networks in Three-Phase Unbalanced Smart Distribution Grids |
| title_fullStr | Power Flow Analysis Using Deep Neural Networks in Three-Phase Unbalanced Smart Distribution Grids |
| title_full_unstemmed | Power Flow Analysis Using Deep Neural Networks in Three-Phase Unbalanced Smart Distribution Grids |
| title_short | Power Flow Analysis Using Deep Neural Networks in Three-Phase Unbalanced Smart Distribution Grids |
| title_sort | power flow analysis using deep neural networks in three phase unbalanced smart distribution grids |
| topic | Power flow analysis deep neural networks radial basis function networks multi-layer perceptron convolutional neural networks unbalanced power distribution grids |
| url | https://ieeexplore.ieee.org/document/10444519/ |
| work_keys_str_mv | AT deepaktiwari powerflowanalysisusingdeepneuralnetworksinthreephaseunbalancedsmartdistributiongrids AT mehdijabbarizideh powerflowanalysisusingdeepneuralnetworksinthreephaseunbalancedsmartdistributiongrids AT veerutalreja powerflowanalysisusingdeepneuralnetworksinthreephaseunbalancedsmartdistributiongrids AT vishalverma powerflowanalysisusingdeepneuralnetworksinthreephaseunbalancedsmartdistributiongrids AT sarikakhushalanisolanki powerflowanalysisusingdeepneuralnetworksinthreephaseunbalancedsmartdistributiongrids AT jigneshsolanki powerflowanalysisusingdeepneuralnetworksinthreephaseunbalancedsmartdistributiongrids |