ANFIS-based prediction of power generation for combined cycle power plant

TL;DR

This paper demonstrates that ANFIS can accurately and efficiently predict power generation in a combined cycle power plant using environmental inputs, outperforming existing tools in speed and precision.

Contribution

The paper introduces a novel application of ANFIS for power prediction in combined cycle plants, with a hybrid training algorithm and high accuracy results.

Findings

ANFIS accurately predicts power output using environmental data.

The proposed method is faster than existing MATLAB toolbox implementations.

High prediction accuracy demonstrated with real plant data.

Abstract

This paper presents the application of an adaptive neuro-fuzzy inference system (ANFIS) to predict the generated electrical power in a combined cycle power plant. The ANFIS architecture is implemented in MATLAB through a code that utilizes a hybrid algorithm that combines gradient descent and the least square estimator to train the network. The Model is verified by applying it to approximate a nonlinear equation with three variables, the time series Mackey-Glass equation and the ANFIS toolbox in MATLAB. Once its validity is confirmed, ANFIS is implemented to forecast the generated electrical power by the power plant. The ANFIS has three inputs: temperature, pressure, and relative humidity. Each input is fuzzified by three Gaussian membership functions. The first-order Sugeno type defuzzification approach is utilized to evaluate a crisp output. Proposed ANFIS is cable of successfully predicting power generation with extremely high accuracy and being much faster than Toolbox, which makes it a promising tool for energy generation applications.