I was born Trang City,Thailand,in 1973. I received the B.Sc.and M.Sc degrees in Electrical Engineering from Rajamangala university of technology in 1999 and Prince Songkhla of University 2002 respectively.
I joins technology department at Rajamangala University of Technology Srivijaya, Trang Campus,where currently I was an Assistant Professor.
Currently,I am woking toward the Ph.D.degree at the University of the Ryukyus,Okinawa,Japan Since 2008. (http://pesc.eee.u-ryukyu.ac.jp/staff.html)
My research interests include neural networks,optimization techniques,power systems,forecasting,scheduling, Market operations,deregulate,electricity,renewable energy,power economics and application of artificial intelligence techniques in power system. (http://doc.clib.psu.ac.th/public7/thesis7/full/218347/218347.htm)
List of Publication Papers 1. Tomonobu Senjyu, Hirofumi Toyama, Phatchakorn Areekul, Shantanu Chakraborty, Atsushi Yona, Naomitsu Urasaki, Toshihisa Funabashi. "Next-Day Peak Electricity Price Forecasting Using NN Based on Rough Sets Theory". IEEJ Transactions on Electrical and Electronic Engineering. Volume 4, Issue 5, September 2009, pp. 618-624. (http://www3.interscience.wiley.com/journal/122580340/abstract?CRETRY=1&SRETRY=0)
2. Phatchakorn Areekul, Tomonobu Senjyu, Naomitsu Urasaki and Atsushi Yona. "Next Day Price Forecasting in Deregulated Market by Combination of Artificial Neural Network and ARIMA Time Series Models". IEEJ Transactions on Power and Energy, Vol. 129 (2009) No. 10, pp.1267-1274. (http://www.jstage.jst.go.jp/article/ieejpes/129/10/129_1267/_article)
This paper presents a the application of neural network for short term electric power load forecasting. Short term load forecasting plays an important role in operation planning, control and interchange transaction scheduling for great saving in electric utility organizations. In this paper has concept in short term load forecasting of electrical distribution by using neural network involved is designed using back propagation learning technique which can forecast of peak and valley loads, hourly load and next day energy. Inputs data for neural network training is contain past daily loads and past temperature of 6 main provinces in Thailandand will separate for learning in daytype contains Workday,Monday,Saturday or holiday of government and Sunday include 8 past days for training which the neural has 55 input neurals is best suitable pattern. For hidden layer has 10 hidden neurals gave least error in forecasting and results show accuracy forecasting. The testing results showthatthispaperhas mean absolute percentage error less than 2.0 % which lower than results of EGAT (Electricity Generating Authority of Thailand) about 27-36 %
Keywords
Short-term load forecasting, electricity, Artificial Neural Networks (ANN), temperature
English
hi5 Coins
ขอมีความสุขและขอให้
สมหวังในทุกสิ่งดังที่ใจปราถนา
ได้เดินทางเยอะๆ
มีความสุขมากๆ
สุขภาพแข็งแรง
ประสบความสำเร็จในชีวิตดังที่ได้ตั้งใจไว้
วิชิต ลักษณะวิลาศ