Advertisement

Prediction of Electrical Energy Output for Combined Cycle Power Plant with Different Regression Models

  • Zhihui Chen
  • Fumin ZouEmail author
  • Lyuchao Liao
  • Siqi Gao
  • Meirun Zhang
  • Jie Chun
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 891)

Abstract

Prediction of electrical output is beneficial to energy saving and financial interests. The electrical energy output of Combined Cycle Power Plant (CCPP) is predicted with four different models in this paper. The analysis reveals that some attributes in CCPP have a high linear relation with the energy output but the other has multi-collinearity. Therefore, the output is decided by attributes in a specific combination which means the output can be precisely predicted by a suitable models. We input four attributes to train models with 5 × 2 cross-validation for tuning hyper-parameters, and four machine learning methods are compared with Multi-linear Regression, Support Vector Regression, Backward propagation neural network and CART based algorithm XGBoost. The result shows that XGBoost has the best fitting in output with the lowest variance and bias, which is based on boosting algorithm and ensemble learning with a root mean square error of 2.752, mean absolute error 1.938 and a \( \text{R}^{2} \) of 0.9748.

Keywords

Combined cycle power plant (CCPP) Electrical output prediction Machine learning XGBoost 

Notes

Acknowledgments

Our deepest gratitude goes to financial support from CERNET innovation Project (NGII20170625) for energy project research, and supporter of dataset for modeling Pinar Tüfekci (email: ptufekci ‘@’ nku.edu.tr), ÇorluFaculty of Engineering, Namik Kemal University is also acknowledged for supporting data. Greatly appreciate your reviewing which contribute to a better paper.

References

  1. 1.
    Kesgin, U., Heperkan, H.: Simulation of thermodynamic systems using soft computing techniques. Int. J. Energy Res. 29(7), 581–611 (2005)CrossRefGoogle Scholar
  2. 2.
    Tüfekci, P.: Prediction of full load electrical power output of a base load operated combined cycle power plant using machine learning methods. Int. J. Electr. Power Energy Syst. 60, 126–140 (2014)CrossRefGoogle Scholar
  3. 3.
    Islikaye, A.A., Cetin, A.: Performance of ML methods in estimating net energy produced in a combined cycle power plant. In: 2018 6th International Istanbul Smart Grids and Cities Congress and Fair (ICSG), Istanbul, Turkey, pp. 217–220. IEEE (2018)Google Scholar
  4. 4.
    Zhandos, A., Guo, J.: An approach based on decision tree for analysis of behavior with combined cycle power plant. In: 2017 International Conference on Progress in Informatics and Computing (PIC), Nanjing, pp. 415–419. IEEE (2017)Google Scholar
  5. 5.
  6. 6.
    Izzah, A., Sari, Y.A., Widyastuti, R., Cinderatama, T.A.: Mobile app for stock prediction using improved multiple linear regression. In: 2017 International Conference on Sustainable Information Engineering and Technology (SIET), Malang, pp. 150–154. IEEE (2017)Google Scholar
  7. 7.
    Shengwei, W., Yanni, L., Jiayu, Z., Jiajia, L.: Agricultural price fluctuation model based on SVR. In: 2017 9th International Conference on Modelling, Identification and Control (ICMIC), Kunming, pp. 545–550. IEEE (2017)Google Scholar
  8. 8.
    Zhang, X., Fang, C., Wang, Z., Ma, H.: Prediction of urban built-up area based on RBF Neural network—comparative analysis with BP neural network and linear regression. Res. Environ. Yangtze Basin 22(6), 691–697 (2013)Google Scholar
  9. 9.
    Friedman, J.H.: Greedy function approximation: a gradient boosting machine. Ann. Stat. 1189–1232 (2001)Google Scholar
  10. 10.
    Chen, T., Guestrin, C.: Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785–794. ACM (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Zhihui Chen
    • 1
    • 2
  • Fumin Zou
    • 2
    Email author
  • Lyuchao Liao
    • 1
    • 2
  • Siqi Gao
    • 1
    • 2
  • Meirun Zhang
    • 1
    • 2
  • Jie Chun
    • 1
    • 2
  1. 1.Beidou Navigation and Smart Traffic Innovation Center of Fujian ProvinceFujian University of TechnologyFuzhouChina
  2. 2.Fujian Key Laboratory for Automotive Electronics and Electric DriveFujian University of TechnologyFuzhouChina

Personalised recommendations