Forecasting wavelet denoised global horizontal irradiance using attention-based long short term memory network: A case study of South Africa
| dc.contributor.advisor | Sigauke, Caston | |
| dc.contributor.advisor | Bere, Aphonce | |
| dc.contributor.advisor | Thanyani, Maduvhahafani | |
| dc.contributor.author | Nelwamondo, Ndamulelo Innocent | |
| dc.date | 2022 | |
| dc.date.accessioned | 2022-08-10T07:40:54Z | |
| dc.date.available | 2022-08-10T07:40:54Z | |
| dc.date.issued | 2022-07-15 | |
| dc.description | MSc (e-Science) | en_ZA |
| dc.description | Department of Mathematical and Computational Sciences | |
| dc.description.abstract | Microgrids are becoming a crucial component of the electricity grid in dependability, economics, and environmental sustainability. Microgrids rely heavily on renewable energy sources. From an engineering standpoint, anticipating short-term solar generation is a critical challenge in microgrid planning and design. Anticipating solar power is heavily reliant on forecasting sun radiation. Short-term solar radiation forecasting may also be used to estimate the energy potentials of photovoltaic (PV) panels impacted by degradation rates. A comparison of multiple models, namely the Autoregressive Integrated Moving Average (ARIMA), Long Short Term Memory (LSTM), Attention-based LSTM and a hybrid Attention-based LSTM-ARIMA for forecasting 5-day ahead 1-minute solar radiation is performed in this study. The best model for forecasting Global Solar Radiation(GHI) from Richtersveld station is ARIMA with MAE = 0.782 and RMSE = 1.271, followed by hybrid model with MAE = 4.120 and RMSE = 4.987. For Stellenbosch University station, attention LSTM was the best with MAE = 1.512 and RMSE = 1.640, followed by hybrid with MAE = 2.011 and RMSE = 2.511. The hybrid attention-based LSTM-ARIMA model on the USAid Venda station was the best fitting model with RMSE = 7.383 and MAE = 14.1293, followed by LSTM with MAE = 7.817 and RMSE = 8.444. Comparing the results on nonwavelet denoised and wavelet denoised, models performed better on wavelet denoised data. ARIMA model was the best with MAE = 0.194 and RMSE = 0.542, followed by hybrid with MAE = 2.176 and RMSE = 2.308. | en_ZA |
| dc.description.sponsorship | NRF | en_ZA |
| dc.format.extent | 1 online resource (ix, 38 leaves) : color illustrations | |
| dc.identifier.apacitation | Nelwamondo, N. I. (2022). <i>Forecasting wavelet denoised global horizontal irradiance using attention-based long short term memory network: A case study of South Africa</i>. (). . Retrieved from http://hdl.handle.net/11602/2237 | en_ZA |
| dc.identifier.chicagocitation | Nelwamondo, Ndamulelo Innocent. <i>"Forecasting wavelet denoised global horizontal irradiance using attention-based long short term memory network: A case study of South Africa."</i> ., , 2022. http://hdl.handle.net/11602/2237 | en_ZA |
| dc.identifier.citation | Nelwamondo, N. I. (2022) Forecasting wavelet denoised global horizontal irradiance using attention-based long short term memory network: A case study of South Africa. University of Venda. South Africa.<http://hdl.handle.net/11602/2237>. | |
| dc.identifier.ris | TY - Dissertation AU - Nelwamondo, Ndamulelo Innocent AB - Microgrids are becoming a crucial component of the electricity grid in dependability, economics, and environmental sustainability. Microgrids rely heavily on renewable energy sources. From an engineering standpoint, anticipating short-term solar generation is a critical challenge in microgrid planning and design. Anticipating solar power is heavily reliant on forecasting sun radiation. Short-term solar radiation forecasting may also be used to estimate the energy potentials of photovoltaic (PV) panels impacted by degradation rates. A comparison of multiple models, namely the Autoregressive Integrated Moving Average (ARIMA), Long Short Term Memory (LSTM), Attention-based LSTM and a hybrid Attention-based LSTM-ARIMA for forecasting 5-day ahead 1-minute solar radiation is performed in this study. The best model for forecasting Global Solar Radiation(GHI) from Richtersveld station is ARIMA with MAE = 0.782 and RMSE = 1.271, followed by hybrid model with MAE = 4.120 and RMSE = 4.987. For Stellenbosch University station, attention LSTM was the best with MAE = 1.512 and RMSE = 1.640, followed by hybrid with MAE = 2.011 and RMSE = 2.511. The hybrid attention-based LSTM-ARIMA model on the USAid Venda station was the best fitting model with RMSE = 7.383 and MAE = 14.1293, followed by LSTM with MAE = 7.817 and RMSE = 8.444. Comparing the results on nonwavelet denoised and wavelet denoised, models performed better on wavelet denoised data. ARIMA model was the best with MAE = 0.194 and RMSE = 0.542, followed by hybrid with MAE = 2.176 and RMSE = 2.308. DA - 2022-07-15 DB - ResearchSpace DP - Univen KW - Deep learning KW - Global Horizontal Irradiance KW - Hybrid ARIMA-LSTM model KW - Solar energy KW - Wavelet denoising LK - https://univendspace.univen.ac.za PY - 2022 T1 - Forecasting wavelet denoised global horizontal irradiance using attention-based long short term memory network: A case study of South Africa TI - Forecasting wavelet denoised global horizontal irradiance using attention-based long short term memory network: A case study of South Africa UR - http://hdl.handle.net/11602/2237 ER - | en_ZA |
| dc.identifier.uri | http://hdl.handle.net/11602/2237 | |
| dc.identifier.vancouvercitation | Nelwamondo NI. Forecasting wavelet denoised global horizontal irradiance using attention-based long short term memory network: A case study of South Africa. []. , 2022 [cited yyyy month dd]. Available from: http://hdl.handle.net/11602/2237 | en_ZA |
| dc.language.iso | en | en_ZA |
| dc.rights | University of Venda | |
| dc.subject | Deep learning | en_ZA |
| dc.subject | UCTD | en_ZA |
| dc.subject | Hybrid ARIMA-LSTM model | en_ZA |
| dc.subject | Solar energy | en_ZA |
| dc.subject | Wavelet denoising | en_ZA |
| dc.title | Forecasting wavelet denoised global horizontal irradiance using attention-based long short term memory network: A case study of South Africa | en_ZA |
| dc.type | Dissertation | en_ZA |