Considering renewable energy sources in electricity load forecasting

Eser, Omer Talha (2024) Considering renewable energy sources in electricity load forecasting. Masters thesis, Dublin, National College of Ireland.

Preview

PDF (Master of Science) Download (2MB) | Preview

Abstract

Uses of renewable energy sources have been increased and integrated into power grid which means is managing these sources in the grid is becoming vital in terms of grid reliability and stability. Hence, forecasting of the most promising sources, wind and solar, is becoming more important for efficient and effective power grid operation. On the other hand, designing stable and reliable smart grid requires an accurate forecasting of electricity load, which uses historical load/demand data and its related factors to forecast. In this case, we aimed to develop accurate forecasting models by comparing their results to find out the best model for this task. Therefore, we utilized different machine learning models in both traditional and advanced deep learning models to make comparisons. More weather parameters were used in understanding correlations between them. The proposed models were used to forecast 2-hour and 1-week ahead electrical load of NEMA zone in New England. The proposed LSTM model exhibits remarkable performance to all other models by obtaining with lowest values of 0.047, 0.062, 0.003, with metrics of MAE, RMSE, MSE, respectively. R2 value of 0.902, which was close to 1, as well. For wind power forecasting side, RMSE, MSE, MAE, and R2 of proposed XGBoost are, 0.208, 0.043, 0.162, and 0.078, respectively. In solar power forecast, proposed XGBoost is evaluated with four metrics e.g. MAE, MSE, R2, RMSE, and 0.088, 0.024, 0.714, 0.155, respectively.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Jameel Syed, Muslim UNSPECIFIED
Subjects:	G Geography. Anthropology. Recreation > GE Environmental Sciences Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Electricity Supply G Geography. Anthropology. Recreation > GE Environmental Sciences > Environment
Divisions:	School of Computing > Master of Science in Artificial Intelligence
Depositing User:	Ciara O'Brien
Date Deposited:	18 Jun 2025 11:39
Last Modified:	18 Jun 2025 11:39
URI:	https://norma.ncirl.ie/id/eprint/7910

Actions (login required)

View Item