Forecasting and analysis of solar power output from integrated solar energy and IoT system
Solar-powered irrigation systems has attracted enormous attention considering because it is a green energy source and cost-effective green energy and power supply source for plantations and farms, especially those located in rural areas. Solar power generation systems may experience either insuffici...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English English |
| Published: |
Institute of Electrical and Electronics Engineers Inc.
2021
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/42365/1/Forecasting%20and%20analysis%20of%20solar%20power%20output%20from%20integrated.pdf http://umpir.ump.edu.my/id/eprint/42365/2/Forecasting%20and%20analysis%20of%20solar%20power%20output%20from%20integrated%20solar%20energy%20and%20IoT%20system_ABS.pdf http://umpir.ump.edu.my/id/eprint/42365/ https://doi.org/10.1109/ICICoS53627.2021.9651831 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Solar-powered irrigation systems has attracted enormous attention considering because it is a green energy source and cost-effective green energy and power supply source for plantations and farms, especially those located in rural areas. Solar power generation systems may experience either insufficient voltage or overvoltage of solar power generation usually occurs especially for the based on the specific country that has specific climate of the installation spot. East coast states of Malaysia face northeast monsoon every year and during this season, the outputs from solar power generation systems will fluctuate greatly that the solar power distribution throughout the year was never reported elsewhere. Thus, in this study, auto-tracking solar panel was installed in a mini farm equipped with Internet-of- Thing (IoT) system for 24/7 data monitoring. From the results, the highest amount of energy generated was found from between 12 pm until 2 pm with approximately 45.9% efficiency. Then, ARIMA (11, 2, 4) model was applied using Python tool to forecast the energy generation data obtained. This forecast found the Mean Absolute Percentage Error (MAPE) of around 32.0%, which of Mean Absolute Percentage Error (MAPE) implies that the prediction was is about 68.0% validity with Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MASE) figures of recorded with 1.70 and 0.32, respectively. Forecasting the output is important to ensure the availability of existing and back-up of electricity supply, besides to avoid over and underutilization of electricity. |
|---|