Hierarchical Method Based on Artificial Neural Networks for Power Output Prediction of a Combined Cycle Power Plant

Hierarchical Method Based on Artificial Neural Networks for Power Output Prediction of a Combined Cycle Power Plant

Rafik Fainti (Applied Intelligent Systems Laboratory, School of Nuclear Engineering, Purdue University, West Lafayette, IN, USA), Antonia Nasiakou (Applied Intelligent Systems Laboratory, School of Nuclear Engineering, Purdue University, West Lafayette, IN, USA), Miltiadis Alamaniotis (Nuclear Engineering Program, University of Utah, Salt Lake City, UT, USA & Applied Intelligent Systems Laboratory, School of Nuclear Engineering, Purdue University, West Lafayette, IN, USA) and Lefteri H. Tsoukalas (Applied Intelligent Systems Laboratory, School of Nuclear Engineering, Purdue University, West Lafayette, IN, USA)
DOI: 10.4018/IJMSTR.2016100102
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

The increasing demand for electricity the last decades leads towards the more frequent use of Combined Cycle Power Plants (CCPPs) because of the quite efficient way these units are capable to produce electricity. Hence, the prediction of the output of these units is of significant interest and constitutes the cornerstone towards the attainment of economic power production and a reliable power generation system as a whole. To that end, the aim of this paper is the development of a hierarchical predictive method based on Artificial Neural Networks (ANNs) in order to efficiently predict the power plant's output. The under consideration features are the hourly average ambient variables of Temperature (T), Ambient Pressure (AP), Relative Humidity (RH) and Exhaust Vacuum (V) for predicting the hourly power output of a CCPP. A parellel, but equally important, aim of this study is to assess the effectiveness of ANNs in this type of applications.
Article Preview

2. Literature Review

A plethora of Artificial Intelligence (AI) techniques has been proposed in the literature towards the development of anticipatory methods in order to confront the challenges related to new generation power systems. A medium term load forecasting method is developed in (Alamaniotis et al., 2016). More precisely, two different models based on kernel machines, namely Gaussian process and relevance vector regression combined with Gaussian kernels, were developed and compared against the ARMA (2,2) model with very promising results. Neural networks have been used in a previous work (Fainti et al., 2016), in order to define prediction intervals regarding the ampacity level of each phase of a distribution system. Support Vector Machines (SVMs) and fuzzy inference techniques are combined to produce an anticipatory system regarding the states of a complex power system in (Alamaniotis & Agarwal, 2014).

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 5: 4 Issues (2017): 2 Released, 2 Forthcoming
Volume 4: 4 Issues (2016)
Volume 3: 4 Issues (2015)
Volume 2: 4 Issues (2014)
Volume 1: 4 Issues (2013)
View Complete Journal Contents Listing