Hybrid Artificial Neural Network by Using Differential Search Algorithm for Solving Power Flow Problem
Power flow (PF) is in one of the most studied non-linear problems related to power systems which heavily affects security issues such as generation cost, voltage stability and active power loss. In this paper, a simple and new approach based on artificial neural network (ANN) and differential sear...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Stefan cel Mare University of Suceava
2019-11-01
|
Series: | Advances in Electrical and Computer Engineering |
Subjects: | |
Online Access: | http://dx.doi.org/10.4316/AECE.2019.04007 |
id |
doaj-2ffda249045644acb9f4b68f971f718e |
---|---|
record_format |
Article |
spelling |
doaj-2ffda249045644acb9f4b68f971f718e2020-11-25T02:08:03ZengStefan cel Mare University of SuceavaAdvances in Electrical and Computer Engineering1582-74451844-76002019-11-01194576410.4316/AECE.2019.04007Hybrid Artificial Neural Network by Using Differential Search Algorithm for Solving Power Flow ProblemABACI, K.YAMACLI, V.Power flow (PF) is in one of the most studied non-linear problems related to power systems which heavily affects security issues such as generation cost, voltage stability and active power loss. In this paper, a simple and new approach based on artificial neural network (ANN) and differential search (DSA) algorithm has been proposed and applied for one of the most complex problems in power systems, Power Flow (PF) problem. By using the proposed DSA implemented ANN method, IEEE 9-bus, IEEE 30-bus and IEEE 118-bus test system parameters are obtained without running iterative convergence methods such as Gauss-Siedel or Newton-Raphson. By comparing with several most used non-linear iterative methods, the results obtained using the classical training method and proposed DSA implemented hybrid training methods are presented and discussed. Obtained results in this work show that the ANN based power flow method can be implemented to solve non-linear static and dynamical problems concerning power systems successfully.http://dx.doi.org/10.4316/AECE.2019.04007heuristic algorithmsiterative methodsneural networksoptimizationpower system analysis computing |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
ABACI, K. YAMACLI, V. |
spellingShingle |
ABACI, K. YAMACLI, V. Hybrid Artificial Neural Network by Using Differential Search Algorithm for Solving Power Flow Problem Advances in Electrical and Computer Engineering heuristic algorithms iterative methods neural networks optimization power system analysis computing |
author_facet |
ABACI, K. YAMACLI, V. |
author_sort |
ABACI, K. |
title |
Hybrid Artificial Neural Network by Using Differential Search Algorithm for Solving Power Flow Problem |
title_short |
Hybrid Artificial Neural Network by Using Differential Search Algorithm for Solving Power Flow Problem |
title_full |
Hybrid Artificial Neural Network by Using Differential Search Algorithm for Solving Power Flow Problem |
title_fullStr |
Hybrid Artificial Neural Network by Using Differential Search Algorithm for Solving Power Flow Problem |
title_full_unstemmed |
Hybrid Artificial Neural Network by Using Differential Search Algorithm for Solving Power Flow Problem |
title_sort |
hybrid artificial neural network by using differential search algorithm for solving power flow problem |
publisher |
Stefan cel Mare University of Suceava |
series |
Advances in Electrical and Computer Engineering |
issn |
1582-7445 1844-7600 |
publishDate |
2019-11-01 |
description |
Power flow (PF) is in one of the most studied non-linear problems related to power systems which heavily
affects security issues such as generation cost, voltage stability and active power loss. In this paper,
a simple and new approach based on artificial neural network (ANN) and differential search (DSA) algorithm
has been proposed and applied for one of the most complex problems in power systems, Power Flow (PF) problem.
By using the proposed DSA implemented ANN method, IEEE 9-bus, IEEE 30-bus and IEEE 118-bus test system parameters
are obtained without running iterative convergence methods such as Gauss-Siedel or Newton-Raphson. By comparing
with several most used non-linear iterative methods, the results obtained using the classical training method
and proposed DSA implemented hybrid training methods are presented and discussed. Obtained results in this work
show that the ANN based power flow method can be implemented to solve non-linear static and dynamical problems
concerning power systems successfully. |
topic |
heuristic algorithms iterative methods neural networks optimization power system analysis computing |
url |
http://dx.doi.org/10.4316/AECE.2019.04007 |
work_keys_str_mv |
AT abacik hybridartificialneuralnetworkbyusingdifferentialsearchalgorithmforsolvingpowerflowproblem AT yamacliv hybridartificialneuralnetworkbyusingdifferentialsearchalgorithmforsolvingpowerflowproblem |
_version_ |
1724927866982891520 |