PREDICTION OF PV POWER GENERATION USING ANFIS CONSIDERING UNCERTAINTIES
The environment and end-user (s) are affected by the use of fossil fuels in power generation. This being a challenge in the power generation and distribution sectors, the majority of end users are moving to using renewable energy sources like solar power plants in generating power. However, because...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
University of Kragujevac
2025-06-01
|
| Series: | Proceedings on Engineering Sciences |
| Subjects: | |
| Online Access: | https://pesjournal.net/journal/v7-n2/26.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The environment and end-user (s) are affected by the use of fossil fuels in power generation. This being a challenge in the power generation and distribution sectors, the majority of end users are moving to using renewable energy sources like solar power plants in generating power. However, because photovoltaic(PV) systems are intermittent, it’s do not warrant maximum power generation under uncertainties. Therefore, uncertainties need to be assessed before PV systems are installed. Solar Irradiation [DNI (W/m2)], Diffuse Horizontal Irradiance [DHI (W/m2)], Global Horizontal irradiance [GHI (W/m2)], Wind Speed(m/s), and shading(trees) were considered as uncertainties in this paper. The objective of this work is to predict PV power generation using ANFIS considering uncertainties. Obtaining location weather data, 150kW PV system modeling, and the modeling of a shading(tree) effect were done using System Advisor Model (SAM) software. Furthermore, ANFIS was used to train location weather data obtained and the prediction of PV power generation in MATLAB software. Different times of the year were analyzed. The results show that ANFIS due to its adaptive nature is the most appropriate and suitable technique for predicting the performance of solar PV systems under different climate conditions. Under the no shading and shading scenarios, an annual AC energy harvested in a year was around 56,020kWh, and 51,000kWh, energy yield in a year was 962kWh/kW, and 930kWh/kW with a DC capacity factor of 11% and 9.5% respectively. To enhance PV power prediction under uncertainty conditions, future works should incorporate some optimization technique(s) into the ANFIS prediction approach. |
|---|---|
| ISSN: | 2620-2832 2683-4111 |