000			03066nam a22003017a 4500
003			KOHA
005			20230424101501.0
008			221011d2022 cy ||||| m||| 00| 0 eng d
040			_aCY-NiCIU _beng _cCY-NiCIU _erda
041			_aeng
090			_aYL 2636 _bZ43 2022
100	1		_aZidan, Tareq Abdalkarim
245	1	0	_aESTIMATION OF SOLAR RADIATION WITH ADVANCED MACHINE LEARNING ENSEMBLE TECHNIQUES / _cTAREQ ABDALKARIM ZIDAN; SUPERVISOR: ASSOC. PROF. DR. HÜSEYİN ÖZTOPRAK
264			_c2022
300			_a51 sheets; _c31 cm. _eIncludes CD
336			_2rdacontent _atext _btxt
337			_2rdamedia _aunmediated _bn
338			_2rdacarrier _avolume _bnc
502			_aThesis (MSc) - Cyprus International University. Institute of Graduate Studies and Research Electrical and Electronics Engineering Department
504			_aIncludes bibliography (sheets 46-51)
520			_aABSTRACT Over decades, the applications of solar energy as in power supply, water supply, agriculture, and transportation have been increasing exponentially. However, reliable and efficient planning, design, operation, and monitoring of solar energy systems, requires accurate information on the available solar radiation. However, measurement of solar radiation especially in the developing nations is quite challenging, due to the cost of purchasing the measuring instruments, coupled with their calibration and maintenance. Meanwhile, information on the solar radiation in those regions is estimated using data-driven computational techniques. Several models have been proposed for solar radiation estimation, ranging from empirical, intelligent (machine learning). However, these models often produce unsatisfactory results. In this regard, the objective of this thesis is to investigate the application of advanced ensemble machine learning models for the estimation of solar radiation in four major cities of Libya, namely; Benghazi, Misurata, Sebha and Tripoli. Two ensemble techniques are employed; the averaging ensemble (AE) and neuro-fuzzy ensemble. The ensemble models are developed by combining three single machine learning models namely; Artificial Neural Network (ANN), Support Vector Machine (SVM) and Adaptive Neuro Fuzzy Inference System (ANFIS). The models are developed using meteorological data consisting of relative humidity (RH), Wind Speed (WS), Maximum Temperature, Minimum Temperature, Mean Temperature and Rainfall as predictors. The simulation results indicated that the NFE provide the highest accuracy in all the study areas. The developed models can reliable be used as alternative tool for estimation of solar radiation in the study areas. Keywords: Ensemble Machine Learning, Estimation, Machine Learning, Modelling, Solar Radiation.
650		0	_aMachine learning _vDissertations, Academic
650		0	_aEnsemble learning (Machine learning) _vDissertations, Academic
650		0	_aSolar radiation _vDissertations, Academic
700	1		_aÖztoprak, Hüseyin _esupervisor
942			_2ddc _cTS
999			_c285391 _d285391