Solar irradiance forecasting for Malaysia using multiple regression and artificial neural network
The installed capacity of solar photovoltaic (PV) globally continues to rise. In Malaysia, the monthly average daily solar radiation is 4,000-5,000 Wh/m², with the average daily sunshine duration ranging from 4 to 8 h. However, the output of solar energy is related to solar irradiance, which lacks s...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | en |
| Published: |
Science and Technology Research Institute for Defence
2022
|
| Online Access: | http://eprints.utem.edu.my/id/eprint/26679/2/2022%20VOL%2015.PDF http://eprints.utem.edu.my/id/eprint/26679/ https://www.stride.gov.my/v3/images/buletin-teknikal/2022_vol_15_num_1.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The installed capacity of solar photovoltaic (PV) globally continues to rise. In Malaysia, the monthly average daily solar radiation is 4,000-5,000 Wh/m², with the average daily sunshine duration ranging from 4 to 8 h. However, the output of solar energy is related to solar irradiance, which lacks stability due to weather variation. Therefore, solar irradiance forecasting has become an important resource for network grid operators to control the output of solar PV energy. Weather forecasting data, such as temperature, dew point, humidity, pressure and wind speed, are widely available from local meteorological organisations. However, solar irradiance forecasting data is often unavailable. In this paper, multiple regression (MR) and artificial neural network (ANN) models are used to forecast solar irradiance using weather forecasting data. The correlation of each weather parameter with solar irradiance is investigated. It is evident that the ANN model is able to improve the accuracy in terms of root mean square error (RMSE) by 18.42% of its as compared to the MR model |
|---|