Volume 7, Issue 1 (6-2017)                   JEM 2017, 7(1): 2-13 | Back to browse issues page

XML Persian Abstract Print

Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Economic Estimation of Reserve Requirements of Wind Farms with using Neural Networks to Predict Wind Speed. JEM 2017; 7 (1) :2-13
URL: http://energy.kashanu.ac.ir/article-1-574-en.html
Abstract:   (25796 Views)

Nowadays, increasing the renewable energy applications in power system, especially wind power, has caused higher imbalance probability between generation and demand. Therefore, an accurate estimation of wind farm reserve requirements and the reserve cost reduction in power systems with high wind power penetration is very important. In this paper, the reserve requirements of a wind farm are estimated by using a probabilistic approach. Reserve requirements of wind farm are divided into two categories provided by fast-responsive and slow-responsive resources. Indeed the purpose of this division is decreasing the cost of reserve provision by reducing the use of fast-responsive resources that is more expensive in comparison with slow-responsive resources. Wind speed prediction has been done by the ANN (Artificial Neural Network) and ARIMA (Autoregressive Integrated Moving Average), with using real measured data on a wind farm in the state of Pennsylvania. In this study, the Reserve requirements of wind farms and the cost of provision of reserve requirements will be reduced by using artificial neural networks that is a method based on artificial intelligence and is more accurate than statistical and traditional method ARIMA.

Full-Text [PDF 1740 kb]   (1393 Downloads)    
Type of Study: Research | Subject: Electrical Engineering
Received: 2015/12/10 | Revised: 2018/01/9 | Accepted: 2017/02/4 | Published: 2017/03/6

Add your comments about this article : Your username or Email:

Rights and permissions
  This work is licensed under a This work is licensed under a Creative Common International License..

© 2023 CC BY-NC 4.0 | Energy Engineering & Management

Designed & Developed by : Yektaweb