Solar Power Generation Analysis and Forecasting Real-World Data Using LSTM and Autoregressive CNN

2020-09-22
tosun, nail
sert, egemen
Ayaz, Enes
YILMAZ, ekin
GÖL, MURAT
Generated power of a solar panel is volatile and susceptible to environmental conditions. In this study, we have analyzed variables affecting the generated power of a 17.5 kW real-world solar power plant with respect to five independent variables over the generated power: irradiance, time of measurement, panel's temperature, ambient temperature and cloudiness of the weather at the time of measurement. After our analysis, we have trained three different models to predict intra-day solar power forecasts of the plant. Our models are able to predict future power output of the solar power plant with less than 10% RMSE without requiring additional sensor data, e.g. a camera to observe clouds. Based on our forecasting accuracy, our study promises: fast, scaleable and effective solutions to solar power plant maintainers and may facilitate grid safety on a large scale.

Suggestions

Assessment of solar data estimation models for four cities in Iran
Jahani, Elham; Sadati, S. M. Sajed; Yousefzadeh, Moslem (2015-04-29)
The estimated solar resources are important for designing renewable energy systems since measured data are not always available. The estimation models have been introduced in several studies. These models are mainly dependent on local meteorological data and need to be assessed for different locations and times. The current study compares the results of Angstrom's model and a neural network (NN) model developed for this study with measured data for four cities in Iran. The time resolution for the estimated ...
Smart grid applications and technologies in distribution systems
Pehlivanoğlu Gürbüz, Kübra; Sevaioğlu, Osman; Department of Electrical and Electronics Engineering (2019)
Smart grid control purposes to rise the percentage of energy production through alternative energy sources like renewable resources and to make consumers to be comprehended in grid actively, is realising importance day by day. Further to that it can help us employment opportunities and improving growth in addition to keep the power on at minimum cost to prosumers, while the participation is elucidated and enabled new products, service and markets, accommodating all generation and storage options and provide...
Solar steam generation by heat localization
GHASEMİ, Hadi; Nİ, George; MARCONNET, Amy Marie; LOOMİS, James; Yerci, Selçuk; MİLJKOVİC, Nenad; CHEN, Gang (2014-07-01)
Currently, steam generation using solar energy is based on heating bulk liquid to high temperatures. This approach requires either costly high optical concentrations leading to heat loss by the hot bulk liquid and heated surfaces or vacuum. New solar receiver concepts such as porous volumetric receivers or nanofluids have been proposed to decrease these losses. Here we report development of an approach and corresponding material structure for solar steam generation while maintaining low optical concentratio...
Solar Power Prediction with an Hour-based Ensemble Machine Learning Method
Ertekin Bolelli, Şeyda (2020-03-01)
In recent years, the share of solar power in total energy production has gained a rapid increase. Therefore, prediction of solar power production has become increasingly important for energy regulations. In this study we proposed an ensemble method which gives competitive prediction performance for solar power production. This method firstly decomposes the nonlinear power production data into components with a multi-scale decomposition technique such as Empirical Mode Decomposition (EMD). These components a...
Solar energy harvesting with ultra-broadband metamaterial absorber
BAĞMANCI, MEHMET; KARAASLAN, MUHARREM; ÜNAL, EMİN; AKGÖL, OĞUZHAN; BAKIR, MEHMET; Sabah, Cumali (World Scientific Pub Co Pte Lt, 2019-03-30)
In this study, a novel metamaterial absorber (MA) is designed and numerically demonstrated for solar energy harvesting. The structure is composed of three layers with different thicknesses. The interactions of three layers bring about the plasmonic resonances. Although the main operation frequency of the structure is chosen between 430 and 770 THz, which is the visible light regime, the proposed structure is also investigated in the ultra-violet (UV) region. One can see from the results that the proposed st...
Citation Formats
n. tosun, e. sert, E. Ayaz, e. YILMAZ, and M. GÖL, “Solar Power Generation Analysis and Forecasting Real-World Data Using LSTM and Autoregressive CNN,” 2020, Accessed: 00, 2021. [Online]. Available: https://hdl.handle.net/11511/70226.