A method for detailed, short-term energy yield forecasting of photovoltaic installations

被引：43

作者：

Anagnostos, D. ^{[1
,3
]}

Schmidt, T. ^{[4
]}

Cavadias, S. ^{[1
]}

Soudris, D. ^{[1
]}

Poortmans, J. ^{[2
,3
]}

Catthoor, F. ^{[2
,3
]}

机构：

[1] Natl Tech Univ Athens, Heroon Polytech 9,Zographou Campus, Athens 15780, Greece

[2] IMEC, Kapeldreef 75, B-3001 Heverlee, Belgium

[3] Katholieke Univ Leuven, Kasteelpk Arenberg 10, B-3001 Heverlee, Belgium

[4] DLR Inst Networked Energy Syst, Energy Syst Anal, Carl von Ossietzky Str 15, D-26129 Oldenburg, Germany

来源：

RENEWABLE ENERGY | 2019年 / 130卷

关键词：

Energy yield forecasting; Sky-imager; Neural networks; SOLAR IRRADIANCE; CLASSIFICATION; NETWORK; MODELS;

D O I：

10.1016/j.renene.2018.06.058

中图分类号：

X [环境科学、安全科学];

学科分类号：

08 ; 0830 ;

摘要：

The global shift towards renewable energy production combined with the expected penetration of electric cars, increasing energy usage of cloud computing centers and the transformation of the electricity grid itself towards the "Smart Grid" requires novel solutions on all levels of energy production and management. Forecasting of energy production especially will become a major component for design and operation in all temporal and spatial scales, creating opportunities for optimized control of energy storage, local energy exchange etc. To this end, a method for the creation of detailed and accurate energy yield forecasts for PV installations is presented. Based on sky-imager information and using tailored neural networks, highly detailed energy yield forecasts are produced for a monitored test installation, for horizons up to 15 min and with a resolution of 1 s. Thermal effects are included in the calculations and error propagation is minimized by reducing the modeling steps. The described method manages to outperform state of the art models by up to 39% in forecast skill, while at the same time retaining temporal resolutions that enable control schemes and energy exchange in a local scale. (C) 2018 Elsevier Ltd. Alt rights reserved.

引用

页码：122 / 129

页数：8

共 25 条

[1]

Aksanli B., 2011, Proceedings of the 4th Workshop on Power-Aware Computing and Systems, p5:1, DOI [DOI 10.1109/MC.2012.249, 10.1109/mc.2012.249]

[2] Systematic cross-validation of photovoltaic energy yield models for dynamic environmental conditions [J].

Anagnostos, D. ;

Goverde, H. ;

Catthoor, F. ;

Soudris, D. ;

Poortmans, J. .

SOLAR ENERGY, 2017, 155 :698-705

[3]

[Anonymous], 2017, RENEWABLES 2017 ANAL

[4] Trends in Data Centre Energy Consumption under the European Code of Conduct for Data Centre Energy Efficiency [J].

Avgerinou, Maria ;

Bertoldi, Paolo ;

Castellazzi, Luca .

ENERGIES, 2017, 10 (10)

[5] Very short-term photovoltaic power forecasting with cloud modeling: A review [J].

Barbieri, Florian ;

Rajakaruna, Sumedha ;

Ghosh, Arindam .

RENEWABLE & SUSTAINABLE ENERGY REVIEWS, 2017, 75 :242-263

[6] Online 24-h solar power forecasting based on weather type classification using artificial neural network [J].

Chen, Changsong ;

Duan, Shanxu ;

Cai, Tao ;

Liu, Bangyin .

SOLAR ENERGY, 2011, 85 (11) :2856-2870

[7] Short-term probabilistic forecasts for Direct Normal Irradiance [J].

Chu, Yinghao ;

Coimbra, Carlos F. M. .

RENEWABLE ENERGY, 2017, 101 :526-536

[8] Short-term peer-to-peer solar forecasting in a network of photovoltaic systems [J].

Elsinga, Boudewijn ;

van Sark, Wilfried G. J. H. M. .

APPLIED ENERGY, 2017, 206 :1464-1483

[9] Matching renewable energy supply and demand in green datacenters [J].

Goiri, Inigo ;

Haque, Md E. ;

Le, Kien ;

Beauchea, Ryan ;

Nguyen, Thu D. ;

Guitart, Jordi ;

Torres, Jordi ;

Bianchin, Ricardo .

AD HOC NETWORKS, 2015, 25 :520-534

[10] Smart Distribution Grid: Optimal Day-Ahead Scheduling With Reconfigurable Topology [J].

Golshannavaz, Sajjad ;

Afsharnia, Saeed ;

Aminifar, Farrokh .

IEEE TRANSACTIONS ON SMART GRID, 2014, 5 (05) :2402-2411

← 1 2 3 →