Jiriwibhakorn, Somchat

Preferred name

Alternative Name

Jiriwibhakorn, S.

Jiriwibhakorn, Somchart

Main Affiliation

School of Engineering

somchat.ji@kmitl.ac.th

Now showing 1 - 10 of 23

Some of the metrics are blocked by your
consent settings
Network observability determination using artificial neural networks
(2005-12-01)
Tanprasert, Pornthep
;
Jiriwibhakorn, Somchat
This paper purposes a method for the determination of network observability of the Provincial Electricity Authority (PEA)'s power system in Thailand using the artificial neural networks (ANNs). The network observability problem related to the power system configuration or network topology, called the topological observability, is studied to solve the topological observability problem. The artificial neural networks (ANNs) based on back propagation learning are used as a tool to solve this problem.
Some of the metrics are blocked by your
consent settings
PEA distribution reliability (SAIFI, SAIDI) determination using artificial neural networks
(2005-12-01)
Kaewmanee, Keattisak
;
Jiriwibhakorn, Somchat
This paper purposes the methodology of SAIFI and SAIDI determination of Provincial Electricity Authority (PEA) distribution network in Thailand using Artificial Neural Networks (ANNs). Data used in this study was obtained from the Reliability Program[1]. The data of feeders 2 and 7 of Pattananikom substation was used as the examples in this research from January to July 2004. The three inputs of ANNs for reliability indices (SAIFI, SAIDI) consist of the number of customers behind the protective equipment, interruption frequency of protective equipment per month and total time interruption per month. Referring to the results obtained after inputting ANNs and SAIFI to be trained in neural networks, the mean absolute percentage error (mape) of feeders 2 and 7 are 0.0042%, 0.0168% respectively, while inputting SAIDI into the network, the mean absolute percentage error (mape) of feeders 2 and 7 are 0.6377%, 3.2942% respectively.
Some of the metrics are blocked by your
consent settings
Optimal power flow problem solved by using Distributed Sobol particle swarm optimization
(2010-07-30)
Wannakarn, P.
;
Khamsawang, S.
;
Pothiya, S.
;
Jiriwibhakorn, S.
The Distributed Sobol particle swarm optimization (DSPSO) algorithm was studies for solving optimal power flow problem (OPF), in this paper. In the proposed method, swarm size of the particles is separated in multi-groups and searching procedure is divided according with the swarm group. Reducing search space and high cost elimination are concluded in the DSPSO. The DSPSO was tested for solving two sizes of the OPF problem, six bus test system and IEEE-30 bus test system respectively. The numerical results obtain from the DSPSO were compare with many optimization methods, namely bee colony algorithm (BA), differential evolution algorithm (DE), genetic algorithm (GA), particle swarm optimization (PSO) and tabu search algorithm (TSA). The results show that the proposed method had faster convergence and better solution than the rest methods.
Some of the metrics are blocked by your
consent settings
Effective horizon detection on complex seas using back propagation neural network
(2019-07-01)
Kumeechai, Pisanu
;
Jiriwibhakorn, Somchat
Object detection is one of the main features of surface vehicles that do not require a driver (USV). Research on the detection of the horizon is one of the basic factors in conducting obstructions. Precisely detection helps to improve the efficiency and accuracy of object detection. Because it will eliminate most irrelevant areas. In this paper, there are four different algorithms that apply to three image sequences that have been taken in the open sea. This paper focuses on the accuracy rate and efficiency of horizon detection. By testing four different algorithms, including Hough transform, least squares, RANSAC and neural networks to separate the horizon from the image. Experimental results show that artificial neural network methods use more time but accuracy better than others.
Some of the metrics are blocked by your
consent settings
Real-time critical clearing time estimation by considering contingency conditions
(2018-07-02)
Phootrakornchai, Witsawa
;
Jiriwibhakorn, Somchat
This paper presents an approach called adaptive neuro-fuzzy inference system for the transient stability assessment by considering contingency conditions of networks. The contingency condition herein means a case of transmission outage and network configuration change. In addition, in this study all significant dynamic parameters of a power system (e.g. machine models, excitation systems, turbine governors, and load characteristic etc.) are considered for the estimation. We use the critical clearing time for the transient stability index. The 9-bus IEEE is applied for the power dynamic simulation. Finally, this study shows that the adaptive neuro-fuzzy inference system can be applied with the real-time critical clearing time estimation subject to contingency conditions and some parameters affecting the system's dynamic behavior are taken into account.
Some of the metrics are blocked by your
consent settings
Assessment of wind power generation
(2018-08-13)
Wannakam, Khanittha
;
Jiriwibhakorn, Somchat
Wind power generation is an unstable source of renewable energy. Electricity depends on the weather at the installation location of the wind turbine. This paper presents the prediction of wind power by using the Weibull distribution and Adaptive Neuro-Fuzzy Inference System. The lowest error rates from the Adaptive Neuro-Fuzzy Inference System were 2.1912% and 4.5678%. This is the error value of the training data and the test data respectively.
Some of the metrics are blocked by your
consent settings
Critical generator and maximum power limit determination using neural networks
(2002-12-01)
Jiriwibhakorn, Somchat
The critical clearing time (CCT) often determines the maximum power output of a critical generator (CG) in a multi-machine network if transient stability is to be maintained under fault conditions. Using a time domain simulation method the CG can be identified and its maximum power limit (MPL) established. This paper proposes a novel method of using a neural network to predict the MPL of the CG. Both weighted and weightless neural networks are used and compared using Sobol sequences (Sob) to select the training patterns. The methods are tested on a 4 machine, 11 bus and a 10 machine, 39 bus New England system under variation of loading, fault location and network structures. It is shown that the permissible MPL of the CG can be established to within 5% of those obtained by time simulation.
Some of the metrics are blocked by your
consent settings
Application of nearest neighbor algorithm for critical clearing time (CCT) approximation
(2002-12-01)
Jiriwibhakorn, Somchat
;
Pothisarn, Chaichan
The nearest neighbor algorithm (NNA) has been applied for calculating the critical clearing time (CCT) of a 4-machine 11 bus system under variations in load, fault location and network structure. The CCT is one significant factor for the operator to set the protective relays and circuit breakers to maintain the transient stability of the power systems during the large disturbances, e.g. three-phase-to-ground faults. In this paper, Sobol sequences (Sob) [1] was applied to the selection of the training patterns of the CCT. The results when compared with time domain simulation methods show less mean absolute errors than using a pseudo random choice of inputs. The nearest neighbor algorithm has been successfully applied for approximating the CCT of the system under those variations.
Some of the metrics are blocked by your
consent settings
Reliability indices estimation in PEA distribution system using ANNs
(2017-05-10)
Jiriwibhakorn, Somchat
;
Kaewmanee, Keattisak
The purpose of this paper is to present the methodology of SAIFI, SAIDI and CAIDI estimation of Provincial Electricity Authority (PEA) distribution network in Thailand using Artificial Neural Networks (ANNs). The data used in this study was obtained from the Reliability Program of PEA. The feeder data from Singburi substation was used as the samples of ANNs in this research from January 2010 to October 2012. The three inputs of ANNs for reliability indices (SAIFI, SAIDI and CAIDI) consist of the number of customers behind the protective equipment, the interruption frequency of protective equipment per month and the total time interruption per month. ANNs gave the outputs (SAIFI, SAIDI and CAIDI) faster with accurate results.
Some of the metrics are blocked by your
consent settings
Critical Clearing Time Determination of EGAT System Using Artificial Neural Networks
(2003-12-01)
Pothisarn, Chaichan
;
Jiriwibhakorn, Somchat
Currently, with the continuous interconnection and size increasing, the power systems become larger and more complex. Therefore, the study of transient stability for protection system design and planning is more difficult and takes more time due to system size and complexity. This paper proposes an application of Artificial Neural Networks (ANNs) in transient stability study, with fast access to the answer of the power system stability. ANNs was used to determine the critical clearing time (CCT) of the Electricity Generating Authority of Thailand (EGAT) system. The results show that designed ANNs can estimate the CCT correctly.

Jiriwibhakorn, Somchat

Filters

Settings

Sort By

Results per page