Solar energy has a key role in producing clean and emissions-free power compare to conventional methods. However, sustainable development also requires a reliable and predictable energy source. It also needs methods to measure and predict predictable supply. The main aim of the study is to improve reliable and precise solar radiation prediction models on monthly mean daily basis using various machine learning techniques. Simple Membership Function and Fuzzy Rule Generating Technique (SMGRT), which does not require error and trial for model adjustment, is the first-choice model in this study. Experience and observations about the model will greatly reduce the volume of processing for the fuzzy SMGRT model. On the other hand, Deep Learning (DL) and Adaptive Neuro-Fuzzy Inference System (ANFIS) have become increasingly popular in understanding nonlinear data structures and solving complex problems. Therefore, DL and ANFIS were also applied to estimate solar radiation. The data set used in the study were created using sunshine duration (s), extra-terrestrial solar radiation (H₀ ), relative humidity (RH), cloudiness (C), air temperature (T) and soil temperature (ST) parameters. Estimation performance of models was evaluated by using several statistical indicators which are Mean Bias Error (MBE), Mean Square Error (MSE), Root Mean Square Error (RMSE), and Correlation Coefficient (R²). When the performances of the models were compared, it was seen that all three models obtained remarkable results. In addition, it was shown that the models performed well based on the metrics in the testing phase. The SMGRT model has slightly better performance than DL and ANFIS for different input combinations. SMGRT Model 1 (with inputs H₀, s, and T) shows the best statistical performance (MBE = 0.156, MSE = 1.878, RMSE = 1.371, and R² = 0.960) not only in SMGRT models but also in others.

In this study, the possibility of using Stepwise multilinear regression and deep learning models to estimate the behaviour of the organic Rankine cycle (ORC) has been investigated. It was found that a number of parameters affects the performance of the turbine and hence the amount of power obtained by the ORC. Therefore, limited and simulative parameters might not be sufficient to obtain the best prediction expression. In the present study, the data obtained from a 10 kW ORC system was used as the basis for deep learning models. To this end, the variable selection, which represents the inputs to the neural network, is included in the first steps of a stepwise multilinear regression (SMLR). The aim of the deep learning (DL) models is to use the capabilities of dense layers, and then to strengthen SMLR contributions. The main aim here was to estimate the power generation of the expander, which has an important role in deciding the ORC’s performance. The present study is intended to act as a crucial resource for defining an active estimation procedure for the ORC system through the use of DL. Therefore, an interoperability framework is proposed to estimate ORC power production using SMLR and DL as a new approach in this study. The interoperability approach for the proposed models (SMLR and DL) was found to be successful.

The understanding of the behavior of a wind turbine is difficult due to changes in weather conditions. To obtain the response of a wind turbine influenced by changes in both wind speed and its direction, using the meteorological station data is often preferred to using the real turbine data. Furthermore, simulated data can be easily extrapolated to varied turbine hub heights. In order to estimate the most effective power output in this study, a wind turbine simulation was developed. The simulation depends on the real meteorological data. For the purpose, three modeling techniques, namely Multi-Nonlinear Regression (MNLR), Adaptive Neuro-Fuzzy Inference System (ANFIS), and support vector machines (SVM) were used. In SVM learning process, polynomial and radial basis kernel functions were used. Models were compared to wind turbine measurement values in the same region for similar data. MNLR was used to determine quantify the strength of the relationship between parameters and to eliminate the ineffective parameters. Efficient parameters preferred for training and testing phases of the SVM and ANFIS. The Subtractive Clustering and Grid Partitioning methods were used to identify the inference parameters of ANFIS. According to performance evaluations, MNLR-ANFIS modeling based on Subtractive Clustering gave better results than Grid Partitioning. The results showed that proposed collaborative model could be applied to wind power estimation problems.

Enerjinin son derece önemli olduğu günümüzde ülkelerin mevcut olanaklarını kullanarak üretebilecekleri enerjinin her türü özellikle enerji kaynağında dışa bağımlı olan ülkeler açısından büyük önem taşımaktadır. Bu açıdan yenilenebilir enerji kaynaklarını kullanmak kadar önemli olan bir diğer yöntem de atıl durumdaki enerjiden yararlanmaktır. Doğal gaz basınç düşürme istasyonlarında üretilebilecek enerji bu duruma örnek olarak verilebilir. Mevcut doğal gaz basınç düşürme ve ölçüm istasyonları, doğal gazın basıncını genleşme vanası kullanarak düşürmektedir. Bu çalışmada doğal gazın basınç düşürme işlemi için genleşme vanası yerine genleşme türbini kullanarak üretilebilecek güç üretim potansiyeli incelenmiştir. Bunun için bir A tipi doğal gaz basınç düşürme ve ölçüm istasyonu (A-Type Gas Pressure Regulation & Metering Station – RMS-A) adı verilen tipi bir basınç düşürme ve ölçüm istasyonundan alınan bir yıllık veriler kullanılarak güç üretim potansiyeli incelenmiştir. Doğal gazın istasyon girişindeki basınç ve sıcaklık değerleri ile istasyona giriş debisi çalışmanın temel girdi parametreleri olarak kullanılmıştır. Bu parametreler bir bilgisayar yazılımında simüle edilerek elde edilebilecek güç miktarı hesaplanmıştır.. Sonuç olarak basınç düşürme ve ölçüm istasyonlarında doğal gazın basıncı düşürülürken aynı zamanda önemli seviyede güç üretimi sağlanabileceği değerlendirilmiştir.