Genetic programming for photovoltaic plant output forecasting

被引：29

作者：

Russo, M. ^{[1
]}

Leotta, G. ^{[2
]}

Pugliatti, P. M. ^{[2
]}

Gigliucci, G. ^{[3
]}

机构：

[1] Univ Catania, Dept Phys & Astron, I-95125 Catania, Italy

[2] Enel Ingn & Ric SpA, I-95121 Catania, Italy

[3] Enel Ingn & Ric SpA, I-56122 Pisa, Italy

来源：

SOLAR ENERGY | 2014年 / 105卷

关键词：

Artificial intelligence; Genetic programming; Artificial neural network; Distributed computing system; Hybrid models; SOLAR-RADIATION; POWER OUTPUT; PREDICTION; SIMULATION; MODEL;

D O I：

10.1016/j.solener.2014.02.021

中图分类号：

TE [石油、天然气工业]; TK [能源与动力工程];

学科分类号：

0807 ; 0820 ;

摘要：

In this paper we have identified several mathematical models for predicting the solar power output of a 1.05 kWp Monocrystalline Silicon high-efficiency photovoltaic string located at the ENEL Catania site, Italy. The data we used corresponds to 15 min of averaged power generated over a whole year (2010). A tool named the Brain Project was used. It follows a distributed genetic programming approach. Seventy-four inputs were investigated for our purposes, but no cloud information was considered. The accuracy of all the models was evaluated and compared to other approaches. Among these, the simpler models, that foresee only two inputs perform similarly to our more complex models and to several others in literature. (C) 2014 Elsevier Ltd. All rights reserved.

引用

页码：264 / 273

页数：10

共 22 条

[1] Improving the assessment of ICESat water altimetry accuracy accounting for autocorrelation [J].