Power flow model based on artificial neural networks

Müller, Heloisa H.; Rider, Marcos J.; Castro, Carlos A.; Paucar, V. Leonardo

doi:10.1109/ptc.2005.4524546

Cited by 7 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These methods use machine learning as a tool. For example, probabilistic and data-driven methods utilize the detection and identification of physical topology [19], [20], [21], [22], [23], [24], [25]. In addition to using topological information, one can embed physics in the mapping rule learning with various machine learning tools [15], [26], [27], [28], [29], [30].…”

Section: Introductionmentioning

confidence: 99%

Alternative Auto-Encoder for State Estimation in Distribution Systems With Unobservability

Sundaray

Weng

2023

IEEE Trans. Smart Grid

View full text Add to dashboard Cite

and the M.S. degree in electrical engineering from the University of Wisconsin-Madison, USA, in 2019. He is currently pursuing the Ph.D. degree in electrical engineering with Arizona State University, Tempe, AZ, USA, where he is also serving as a Research Associate. In recognition of his extraordinary achievements, he received University Graduate Fellowship in 2020. His research interest focuses on the areas of interdisciplinary study of energy systems, and machine learning. The objective is to perform investigation of smart grids and determine relationship between the systems and the physics involved.

show abstract

Section: Introductionmentioning

confidence: 99%

Alternative Auto-Encoder for State Estimation in Distribution Systems With Unobservability

Sundaray

Weng

2023

IEEE Trans. Smart Grid

View full text Add to dashboard Cite

show abstract

“…A further way of solving the PF problem is via machine learning (ML). Multiple ML implementations of transmission systems exist in the literature, such as a radial basis NN [18], a counter‐propagation artificial neural network (ANN CPNN) [19], a feedforward neural network (FFNN) with backpropagation network (BPN) algorithms [20], a graph neural network [21], a deep learning BPN [22] and a multilayer perceptron trained with the second order Levenberg‐Marquardt method [23]. An example of the application of ML to a DS is the work in [24].…”

Section: Introductionmentioning

confidence: 99%

State solutions for distribution systems and switching event using a neural network

Yaniv

Lin

Raz

et al. 2021

IET Generation Trans & Dist

View full text Add to dashboard Cite

Power flow calculations are an essential stage in many planning and control applications for distribution systems.To use these in control applications, however, the calculation time needs to be improved, and this can be done by the use of a trained ANN. This paper presents the considerations for constructing ANNs for DSs, and describes a method for training the system in order to support switching events representing a change in topology. The solutions for three DSs, balanced as well as unbalanced, are presented and the various considerations affecting the most appropriate ANN construction are discussed. The results are compared to the solution from the classical complex Newton-Raphson and the fixed-point iterative methods. The solutions have very high precision and good results are found for switched laterals. The computational performance is also compared and an improvement of two orders of magnitude is observed.

show abstract

“…In power flow analysis, calculations are made by characteristic values of various components such as busbars, generators, power lines and transformers on power system. [2,3]…”

mentioning

confidence: 99%

Power Flow Analysis by Artificial Neural Network

Efe¹,

Cebecı

2013

IJEPE

View full text Add to dashboard Cite

Computer based methods used to analysis the power systems are developed instead of the steady state of mathematical methods. By the development of computer technology, solution of the network problems gets easier. Increment of the necessity to electrical energy by the development of technology, whereas the increment rate of raw energy sources doesn't enough, it have made it mandatory to use the energy sources efficiently. Interconnected networks formed by the connection between not only the domestic sources and customers, but also between the different countries for the optimization and for the efficient use of the sources. Electrical engineers faced by the planning and optimization problems of developing interconnected networks. By this way, the requirement of the use of intelligent systems and computer analysis of power systems has become inevitable. In this study, power flow analysis the of a power system that consist five busbars performed by designed neural network. Results are compared by the results that gained by the analysis with classic Gauss-Seidel method of the same system, then the success of the neural network is investigated.

show abstract

Power flow model based on artificial neural networks

Cited by 7 publications

References 9 publications

Alternative Auto-Encoder for State Estimation in Distribution Systems With Unobservability

Alternative Auto-Encoder for State Estimation in Distribution Systems With Unobservability

State solutions for distribution systems and switching event using a neural network

Power Flow Analysis by Artificial Neural Network

Contact Info

Product

Resources

About