scholarly journals Design of Short-Term Forecasting Model of Distributed Generation Power for Solar Power Generation

2015 ◽  
Vol 8 (S1) ◽  
pp. 261 ◽  
Author(s):  
Yoon-Su Jeong ◽  
Seung-Hee Lee ◽  
Kun-Hee Han ◽  
Duchwan Ryu ◽  
Yoonsung Jung
Keyword(s):  
Power Generation ◽  
Distributed Generation ◽  
Solar Power ◽  
Forecasting Model ◽  
Short Term ◽  
Solar Power Generation ◽  
Short Term Forecasting ◽  
Generation Power

scholarly journals The “Weather Intelligence for Renewable Energies” Benchmarking Exercise on Short-Term Forecasting of Wind and Solar Power Generation

Energies ◽  
2015 ◽  
Vol 8 (9) ◽  
pp. 9594-9619 ◽  
Author(s):  
Simone Sperati ◽  
Stefano Alessandrini ◽  
Pierre Pinson ◽  
George Kariniotakis
Keyword(s):  
Power Generation ◽  
Solar Power ◽  
Renewable Energies ◽  
Short Term ◽  
Solar Power Generation ◽  
Short Term Forecasting

scholarly journals Weather data errors analysis in solar power stations generation forecasting

2018 ◽  
Vol 51 ◽  
pp. 02002 ◽  
Author(s):  
Stanislav Eroshenko ◽  
Alexandra Khalyasmaa
Keyword(s):  
Detailed Analysis ◽  
Solar Power ◽  
Weather Data ◽  
Forecasting Model ◽  
Short Term ◽  
Data Errors ◽  
Power Stations ◽  
Software Product ◽  
Short Term Forecasting ◽  
Errors Analysis

The paper presents a short-term forecasting model for solar power stations (SPS) generation developed by the authors. This model is based on weather data and built into the existing software product as a separate short-term forecasting module for the SPS generation. The main problems associated with forecasting the SPS generation on cloudy days were revealed in the framework of authors' research, which is due not to the error of the developed model but to the use of the same learning sample for both solar and cloudy days. This paper contains analysis of the main problems related to the learning sampling, samples pattern, quality and representativeness for forecasting the SPS generation on cloudy days. Besides, the paper includes a calculation example performed for the existing SPS and a detailed analysis of the forecast generation on cloudy days based on the actual weather provider data.

scholarly journals Weather data errors analysis in solar power stations generation forecasting

2018 ◽  
Vol 51 ◽  
pp. 02002 ◽  
Author(s):  
Stanislav Eroshenko ◽  
Alexandra Khalyasmaa
Keyword(s):  
Detailed Analysis ◽  
Solar Power ◽  
Weather Data ◽  
Forecasting Model ◽  
Short Term ◽  
Data Errors ◽  
Power Stations ◽  
Software Product ◽  
Short Term Forecasting ◽  
Errors Analysis

The paper presents a short-term forecasting model for solar power stations (SPS) generation developed by the authors. This model is based on weather data and built into the existing software product as a separate short-term forecasting module for the SPS generation. The main problems associated with forecasting the SPS generation on cloudy days were revealed in the framework of authors' research, which is due not to the error of the developed model but to the use of the same learning sample for both solar and cloudy days. This paper contains analysis of the main problems related to the learning sampling, samples pattern, quality and representativeness for forecasting the SPS generation on cloudy days. Besides, the paper includes a calculation example performed for the existing SPS and a detailed analysis of the forecast generation on cloudy days based on the actual weather provider data.

scholarly journals Neural Network Ensemble-Based Solar Power Generation Short-Term Forecasting

2010 ◽  
Vol 14 (1) ◽  
pp. 69-75 ◽  
Author(s):  
Aymen Chaouachi ◽  
◽  
Rashad M. Kamel ◽  
Ken Nagasaka
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Power Generation ◽  
Solar Power ◽  
Photovoltaic System ◽  
Neural Network Ensemble ◽  
Error Performance ◽  
Solar Power Generation ◽  
The Neural Network ◽  
Short Term Forecasting

This paper presents the applicability of artificial neural networks for 24 hour ahead solar power generation forecasting of a 20 kW photovoltaic system, the developed forecasting is suitable for a reliable Microgrid energy management. In total four neural networks were proposed, namely: multi-layred perceptron, radial basis function, recurrent and a neural network ensemble consisting in ensemble of bagged networks. Forecasting reliability of the proposed neural networks was carried out in terms forecasting error performance basing on statistical and graphical methods. The experimental results showed that all the proposed networks achieved an acceptable forecasting accuracy. In term of comparison the neural network ensemble gives the highest precision forecasting comparing to the conventional networks. In fact, each network of the ensemble over-fits to some extent and leads to a diversity which enhances the noise tolerance and the forecasting generalization performance comparing to the conventional networks.

A novel competitive swarm optimized RBF neural network model for short-term solar power generation forecasting

2020 ◽  
Vol 397 ◽  
pp. 415-421 ◽  
Author(s):  
Zhile Yang ◽  
Monjur Mourshed ◽  
Kailong Liu ◽  
Xinzhi Xu ◽  
Shengzhong Feng
Keyword(s):  
Neural Network ◽  
Power Generation ◽  
Network Model ◽  
Neural Network Model ◽  
Solar Power ◽  
Rbf Neural Network ◽  
Short Term ◽  
Solar Power Generation

Comparison of Three Short Term Photovoltaic System Power Generation Forecasting Methods

2013 ◽  
Vol 479-480 ◽  
pp. 585-589 ◽  
Author(s):  
Wen Yeau Chang
Keyword(s):  
Neural Network ◽  
Power Generation ◽  
Solar Power ◽  
Short Term ◽  
Pv System ◽  
Percent Error ◽  
Solar Power Generation ◽  
Forecasting Methods ◽  
Network Method ◽  
Absolute Percent Error

An accurate forecasting method for solar power generation of the photovoltaic (PV) system is urgent needed under the relevant issues associated with the high penetration of solar power in the electricity system. This paper presents a comparison of three forecasting approaches on short term solar power generation of PV system. Three forecasting methods, namely, persistence method, back propagation neural network method, and radial basis function (RBF) neural network method, are investigated. To demonstrate the performance of three methods, the methods are tested on the practical information of solar power generation of a PV system. The performance is evaluated based on two indexes, namely, maximum absolute percent error and mean absolute percent error.

Sign in / Sign up

Export Citation Format

Share Document