ORIGINAL RESEARCH
Elman-Based Forecaster Integrated by Adaboost Algorithm in 15 min and 24 h ahead Power Output Prediction Using PM 2.5 Values, PV Module Temperature, Hours of Sunshine, and Meteorological Data
Jianguo Zhou 1  
,  
Wei Li 1  
,  
Xuechao Yu 1  
,  
Xiaolei Xu 1  
,  
Xiaolei Yuan 2  
,  
 
 
More details
Hide details
1
Department of Economics and Management, North China Electric Power University, Baoding, China
2
Dezhou Power Supply Company, Dezhou City, Shandong Province, China
3
Spic Ningjin Thermoelectricity Co., Ning Jin County, China
CORRESPONDING AUTHOR
Wei Li   

Department of Economics and Management, North China Electric Power University, 689 Huadian Road, Baoding, 071003 Baoding, China
Online publish date: 2018-12-12
Publish date: 2019-02-18
Submission date: 2018-01-04
Final revision date: 2018-03-22
Acceptance date: 2018-03-26
 
Pol. J. Environ. Stud. 2019;28(3):1999–2008
KEYWORDS
TOPICS
ABSTRACT
Nowadays, with the depletion of fossil energy and deterioration of environmental quality, solar energy is perceived to be a renewable and clean energy. While developing rapidly all over the world, solar energy is also faced with many challenges resulting from its inherent properties. In order to reduce the impact on the grid and facilitate scheduling, it is a growing problem to build a feasible model to forecast PV power with high precision. Therefore, this paper proposes an Elman-based forecaster integrated by Adaboost algorithm, namely Adaboost + Elman. Before forecasting, input variables containing PM 2.5 values, temperature of the PV module, sunshine hours, and meteorological data are made using correlation, clustering, and discriminate analysis to avoid information redundancy and improve the generalization ability of the model. To verify the developed model’s application to shortterm PV forecasting in two different time scales, data of Huangsi in 2016 are used for model construction and verification. An additional 7 models are introduced to make comparison. Experimental results prove that the proposed model is effective and practicable for two different scales of short-term PV power prediction.
eISSN:2083-5906
ISSN:1230-1485