Prediction of electricity generation from a combined cycle power plant based on a stacking ensemble and its hyperparameter optimization with a grid-search method

被引：67

作者：

Qu, Zhijian ^{[1
]}

Xu, Juan ^{[1
]}

Wang, Zixiao ^{[1
]}

Chi, Rui ^{[1
]}

Liu, Hanxin ^{[1
]}

机构：

[1] East China Jiaotong Univ, Sch Elect Engn, Nanchang 330013, Jiangxi, Peoples R China

来源：

ENERGY | 2021年 / 227卷

基金：

中国国家自然科学基金;

关键词：

Prediction; Combined cycle power plant; Stacking; Hyperparameter optimization; NEURAL-NETWORK; LONG-TERM; FUZZY; MODEL; CONSUMPTION; REGRESSION; SYSTEM; OUTPUT; GAS;

D O I：

10.1016/j.energy.2021.120309

中图分类号：

O414.1 [热力学];

学科分类号：

摘要：

Electric power makes a significant contribution to society. Predicting power generation is becoming increasingly important for electric power planning and energy utilization. A reliable forecasting model is necessary for accurate planning of electricity generation. The main goal of this study is to develop effective and realistic solutions for the full-load power generation prediction of combined cycle power plants. According to 9568 items of data pertaining to a combined cycle power plant in six years of its full-load operation, a prediction method based on stacking ensemble hyperparameter optimization is established. The results demonstrate that this method provides high prediction accuracy for the power plant under multiple complex environmental variables. Besides, the predictions generated using this method are compared with those of traditional machine learning methods, random forest, and other ensemble methods, as well as those cited in the literature using the same dataset. The predictions show that the proposed method offers more accurate predictions of the power generation from a combined cycle plant, which opens up a new idea for power planning and energy utilization. (c) 2021 Elsevier Ltd. All rights reserved.

引用

页数：15

共 46 条

[1] Novel suboptimal approaches for hyperparameter tuning of deep neural network [under the shelf of optical communication] [J].

Amirabadi, M. A. ;

Kahaei, M. H. ;

Nezamalhosseini, S. A. .

PHYSICAL COMMUNICATION, 2020, 41

[2] Ensemble learning approach based on stacking for unmanned surface vehicle's dynamics [J].

Cheng, Chen ;

Xu, Peng-Fei ;

Cheng, Hongxia ;

Ding, Yanxu ;

Zheng, Jinhai ;

Ge, Tong ;

Sun, Dianhong ;

Xu, Jin .

OCEAN ENGINEERING, 2020, 207

[3] Multi-year long-term load forecast for area distribution feeders based on selective sequence learning [J].

Dong, Ming ;

Shi, Jian ;

Shi, QingXin .

ENERGY, 2020, 206

[4] Empirical Mode Decomposition based Multi-objective Deep Belief Network for short-term power load forecasting [J].

Fan, Chaodong ;

Ding, Changkun ;

Zheng, Jinhua ;

Xiao, Leyi ;

Ai, Zhaoyang .

NEUROCOMPUTING, 2020, 388 :110-123

[5] Short term load forecasting based on phase space reconstruction algorithm and bi-square kernel regression model [J].

Fan, Guo-Feng ;

Peng, Li-Ling ;

Hong, Wei-Chiang .

APPLIED ENERGY, 2018, 224 :13-33

[6] Development and multi-utility of an ANN model for an industrial gas turbine [J].

Fast, M. ;

Assadi, M. ;

De, S. .

APPLIED ENERGY, 2009, 86 (01) :9-17

[7] Data-Driven Planning for Renewable Distributed Generation Integration [J].

Fathabad, Abolhassan Mohammadi ;

Cheng, Jianqiang ;

Pan, Kai ;

Qiu, Feng .

IEEE TRANSACTIONS ON POWER SYSTEMS, 2020, 35 (06) :4357-4368

[8] Performance evaluation of hybrid adaptive neuro-fuzzy inference system models for predicting monthly global solar radiation [J].

Halabi, Laith M. ;

Mekhilef, Saad ;

Hossain, Monowar .

APPLIED ENERGY, 2018, 213 :247-261

[9] Comparative studies among machine learning models for performance estimation and health monitoring of thermal power plants [J].

Hundi, Prabhas ;

Shahsavari, Rouzbeh .

APPLIED ENERGY, 2020, 265

[10]

Kaya H, 2011, COMBINED CYCLE POWER

← 1 2 3 4 5 →