This study reviews a selection of approaches that have used Artificial Neural Networks (ANN), Particle Swarm Optimization (PSO), and Multi Linear Regression (MLR) to forecast electricity demand for Gokceada Island. Artificial Neural Networks, Particle Swarm Optimization, and Linear Regression methods are frequently used in the literature. Imports, exports, car numbers, and tourist-passenger numbers are used as based on input values from 2014 to 2020 for Gokceada Island, and the electricity energy demands up to 2040 are estimated as an output value. The results obtained were analyzed using statistical error metrics such as R², MSE, RMSE, and MAE. The confidence interval analysis of the methods was performed. The correlation matrix is used to show the relationship between the actual value and method outputs and the relationship between independent and dependent variables. It was observed that ANN yields the highest confidence interval of 95% among the method utilized, and the statistical error metrics have the highest correlation for ANN methods between electricity demand output and actual data.

Medium Neural Networks (MNN), Whale Optimization Algorithm (WAO), and Support Vector Machine (SVM) methods are frequently used in the literature for estimating electricity demand. The objective of this study was to make an estimation of the electricity demand for Turkey’s mainland with the use of mixed methods of MNN, WAO, and SVM. Imports, exports, gross domestic product (GDP), and population data are used based on input data from 1980 to 2019 for mainland Turkey, and the electricity demands up to 2040 are forecasted as an output value. The performance of methods was analyzed using statistical error metrics Root Mean Square Error (RMSE), Mean Absolute Error (MAE), R-squared, and Mean Square Error (MSE). The correlation matrix was utilized to demonstrate the relationship between the actual data and calculated values and the relationship between dependent and independent variables. The p-value and confidence interval analysis of statistical methods was performed to determine which method was more effective. It was observed that the minimum RMSE, MSE, and MAE statistical errors are 5.325 × 10⁻¹⁴, 28.35 × 10⁻²⁸, and 2.5 × 10⁻¹⁴, respectively. The MNN methods showed the strongest correlation between electricity demand forecasting and real data among all the applications tested.

With the increasing integration of renewable energy sources into distribution and transmission networks, the efficiency of cascade H-bridge multilevel inverters (MLIs) in power control applications has become increasingly significant for sustainable electricity generation. Traditionally, obtaining optimal switching angles of MLIs to minimize total harmonic distortion (THD) requires solving the selective harmonic elimination equations. To this end, this research aims to use two recently developed intelligent optimization algorithms, dandelion optimizer and gold rush optimizer, to solve this problem. To evaluate the effectiveness of the proposed algorithms, an eleven-level cascaded H-bridge MLI (CHB-MLI) was considered in the study. Simulation results for different modulation indices were obtained, and the accuracy and solution quality were compared with genetic algorithm and particle swarm optimization algorithms. MATLAB/Simulink-based models were used to verify numerical computations, ensuring the reliability of the findings. This research contributes to the field by providing insights into obtaining optimal switching angles and minimizing THD in MLIs by applying intelligent optimization algorithms.

Accurate instantaneous electricity peak load prediction is crucial for efficient capacity planning and cost-effective electricity network establishment. This paper aims to enhance the accuracy of instantaneous peak load forecasting by employing models incorporating various optimization and machine learning (ML) methods. This study examines the impact of independent inputs on peak load estimation through various combinations and subsets using multilinear regression (MLR) equations. This research utilizes input data from 1980 to 2020, including import and export data, population, and gross domestic product (GDP), to forecast the instantaneous electricity peak load as the output value. The effectiveness of these techniques is evaluated based on error metrics, including mean absolute error (MAE), mean square error (MSE), mean absolute percentage error (MAPE), root mean square error (RMSE), and R². The comparison extends to popular optimization methods, such as particle swarm optimization (PSO), and the newest method in the field, including dandelion optimizer (DO) and gold rush optimizer (GRO). This comparison is made against conventional machine learning methods, such as support vector regression (SVR) and artificial neural network (ANN), in terms of their prediction accuracy. The findings indicate that the ANN and GRO approaches produce the least statistical errors. Furthermore, the correlation matrix indicates a robust positive linear correlation between GDP and instantaneous peak load. The proposed model demonstrates strong predictive capabilities for estimating peak load, with ANN and GRO performing exceptionally well compared to other methods.

Determining the ignition and damping voltage values of dielectric barrier discharge (DBD) at various frequencies and in different gas ambients is important regarding lighting techniques and various industrial applications. DBDs can be operated with sinusoidal or square-wave currents between line frequency and microwave frequencies or with special pulsed waveforms. For large-scale industrial applications, power supplies operating between 500 Hz and 500 kHz are preferred. In this study, an experimental application was carried out to determine the current and voltage parameters in the damping and ignition of DBD at various frequencies and in different gas ambients. Within the scope of the study, the supply voltage was gradually applied at certain frequencies to the cylindrical plane electrode system placed in a specially designed closed and vacuumable reactor, these experiments were also repeated in various gas environments, and the voltage–current (V–I) measurements of the system were made. According to the results, it was observed that the frequency and gas type had a significant effect on the discharge damping and ignition voltages and that increasing the frequency significantly facilitated the ignition of the DBD. Similarly, the conductivity of the ambient gas significantly reduced the ignition voltage level of the DBD.

The accurate forecasting of energy losses in the interconnected grids of Türkiye assumes crucial importance in facilitating strategic planning, optimizing resource allocation, and fostering infrastructure development within the energy sector. A limited number of studies in the existing literature address the estimation of network losses, with investigations into such losses have predominantly relied on conventional machine learning (ML) methodologies. This study proposes an arithmetic optimization algorithm (AOA) approach to the total network losses (TNL) estimation of Türkiye. Firstly, the models are generated with AOA, IAOA, and LevyAOA methods, and then long-term TNL projections were conducted for three scenarios between 2021 and 2050. TNL is modelled as a linear regression model, and for this model, import, export, population, and gross domestic product (GDP) indicators are used as input parameters, and the TNL indicator is used as the output parameter. In the experiments, the historical data records of Türkiye from 1979 to 2020 are used to create the estimation model. Then, long-term TNL estimations with different scenarios are realized for Türkiye up to 2050. The TNL are expressed in gigawatt-hours (GWh) on an annual basis. According to the experimental results and comparisons, the IAOA method has shown quality and robust performance for estimating the TNL compared to other methods. Compared to the standard AOA, the proposed IAOA reduced the total error by 42.57% and the total relative error by 55.49% on the 1979–2020 dataset.