DEVELOPING WIND POWER FORECASTING MODEL USING  DEEP LEARNING APPROACH-A CASE OF ADAMA WIND  FARM

SEBLEWONGALE, MEZGEBU AYENE

dc.contributor.author	SEBLEWONGALE, MEZGEBU AYENE
dc.date.accessioned	2023-06-19T12:00:32Z
dc.date.available	2023-06-19T12:00:32Z
dc.date.issued	2023-02
dc.identifier.uri	http://ir.bdu.edu.et/handle/123456789/15404
dc.description.abstract	Wind is a renewable energy source that is used to generate electricity. Wind power is one of the suitable solutions for global warming since it is free from pollution, doesn’t cause greenhouse effects, and it is a natural source of energy. However, Wind power generation highly depends on weather conditions. It is very difficult to easily predict the amount of power generated from wind at a particular instant in time. Wind power forecasting depicts how much wind power is to be expected at a particular instant of time in the days and years to come. There is no accurate and reliable forecasting model for the Adama wind farm that enables the forecasting of the power generated from the farm. Therefore, the main objective of this thesis is to develop a wind power forecasting model for the Adama wind farm by using deep learning techniques. Forecasting of wind power generation capacity involves appropriate modeling techniques that use past wind power generation data. We have experimented using Long Short -Term Memory (LSTM), Bidirectional Long Short-Term Memory (Bi-LSTM) and Gated Recurrent Unit (GRU) from the deep learning models. To achieve the highest forecasting accuracy, we have collected a total of four years of data starting from 2016-2019 with 163,802 rows with five-minute intervals. For hyperparameter optimization we have applied grid search and random search technique. The Mean Absolute Errors (MAE) for the experiment of the LSTM, Bi-LSTM, and GRU are found as 0.645, 0.644, and 0.645, respectively. Similarly, the Mean Absolute Percentage Error (MAPE) from experimental work of LSTM, Bi-LSTM, and GRU are found as 0.398, 0.388, and 0.406 respectively. The result reveals that the model used is good enough for the forecasting of wind power. Bi-LSTM outperforms other two techniques. Such wind power forecasting helps energy planners and regional power providers to calculate power production and energy generated from other sources. Keywords: Deep Learning, MAE, MAPE, wind power, wind power forecasting	en_US
dc.language.iso	en_US	en_US
dc.subject	Computing	en_US
dc.title	DEVELOPING WIND POWER FORECASTING MODEL USING DEEP LEARNING APPROACH-A CASE OF ADAMA WIND FARM	en_US
dc.type	Thesis	en_US