Nalazite se na CroRIS probnoj okolini. Ovdje evidentirani podaci neće biti pohranjeni u Informacijskom sustavu znanosti RH. Ako je ovo greška, CroRIS produkcijskoj okolini moguće je pristupi putem poveznice www.croris.hr
izvor podataka: crosbi !

Generative adversarial networks and convolutional neural networks based weather classification model for day ahead short-term photovoltaic power forecasting (CROSBI ID 260215)

Prilog u časopisu | izvorni znanstveni rad | međunarodna recenzija

Wang, Fei ; Zhang, Zhanyao ; Liu, Chun ; Yu, Yili ; Pang, Songling ; Duić, Neven ; Shafie- khah, Miadreza ; P.S. Catalao, Joao Generative adversarial networks and convolutional neural networks based weather classification model for day ahead short-term photovoltaic power forecasting // Energy conversion and management, 181 (2019), 443-462. doi: 10.1016/j.enconman.2018.11.074

Podaci o odgovornosti

Wang, Fei ; Zhang, Zhanyao ; Liu, Chun ; Yu, Yili ; Pang, Songling ; Duić, Neven ; Shafie- khah, Miadreza ; P.S. Catalao, Joao

engleski

Generative adversarial networks and convolutional neural networks based weather classification model for day ahead short-term photovoltaic power forecasting

Accurate solar photovoltaic power forecasting can help mitigate the potential risk caused by the uncertainty ofphotovoltaic out power in systems with high penetration levels of solar photovoltaic generation. Weatherclassification based photovoltaic power forecasting modeling is an effective method to enhance its forecastingprecision because photovoltaic output power strongly depends on the specific weather statuses in a given timeperiod. However, the most intractable problems in weather classification models are the insufficiency of trainingdataset (especially for the extreme weather types) and the selection of applied classifiers. Given the aboveconsiderations, a generative adversarial networks and convolutional neural networks-based weather classifica-tion model is proposed in this paper. First, 33 meteorological weather types are reclassified into 10 weathertypes by putting several single weather types together to constitute a new weather type. Then a data- drivengenerative model named generative adversarial networks is employed to augment the training dataset for eachweather types. Finally, the convolutional neural networks-based weather classification model was trained by theaugmented dataset that consists of both original and generated solar irradiance data. In the case study, weevaluated the quality of generative adversarial networks-generated data, compared the performance of con-volutional neural networks classification models with traditional machine learning classification models such assupport vector machine, multilayer perceptron, and k-nearest neighbors algorithm, investigated the precisionimprovement of different classification models achieved by generative adversarial networks, and applied theweather classification models in solar irradiance forecasting. The simulation results illustrate that generativeadversarial networks can generate new samples with high quality that capture the intrinsic features of theoriginal data, but not to simply memorize the training data. Furthermore, convolutional neural networks clas- sification models show better classification performance than traditional machine learning models. And theperformance of all these classification models is indeed improved to the different extent via the generativeadversarial networks-based data augment. In addition, weather classification model plays a significant role indetermining the most suitable and precise day-ahead photovoltaic power forecasting model with high efficiency

Photovoltaic power forecasting ; Weather classification ; Generative adversarial networks ; Convolutional neural networks

nije evidentirano

nije evidentirano

nije evidentirano

nije evidentirano

nije evidentirano

nije evidentirano

Podaci o izdanju

181

2019.

443-462

objavljeno

0196-8904

1879-2227

10.1016/j.enconman.2018.11.074

Povezanost rada

Strojarstvo

Poveznice
Indeksiranost