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.

This work used the established mathematic models of an intermediate-temperature solid oxide fuel cell (IT-SOFC) and gas turbine (GT) hybrid system fueled with wood chip gas to investigate the load performance and safe characteristic under off-design conditions. Three different operating modes (mode A: regulating the fuel proportionally, and the air is passively regulated. Mode B: regulating the fuel only. Mode C: simultaneously regulating the fuel and air) were chosen, and the component safety factors (such as fuel cell maximum temperature, compressor surge margin, carbon deposition in reformer) were considered. Results show that when the operation modes A and C are executed, the hybrid system output power can be safely changed from 41% to 104%, and 45% to 103%, respectively. When mode B is executed, the load adjustment range of hybrid system is from 20% to 134%, which is wider than that of two above operation modes. However, the safety characteristic in this case is very complicated. The system will suffer from two potential malfunctions caused by too lower temperature entering turbine and CH4/CO cracking in reforming reactor when it operates in low load conditions. When the system operates in the high load conditions exceeding 130% of relative power, the potential thermal cracking of fuel cell will be occurred.

In this study, the implementation of a solid oxide fuel cell–gas turbine hybrid engine for primary propulsion and electric power generation in aircraft is investigated. The following three parameters, which are crucial in attaining optimal performance at any point in the flight profile, were identified: the oxygen-to-carbon ratio of the catalytic partial oxidation reformer, the fuel utilization factor of the fuel cell, and the airflow split ratio at the outlet of the high-pressure compressor. The study assesses the impact of varying these parameters within specified ranges on the performance of the hybrid system. At the design point, the system yielded a total power output of 1.96 MW, with 102.5 kW of electric power coming from the fuel cell and 7.9 kN (1.86 MW) of thrust power coming from the gas turbine. The results indicate that varying the oxygen-to-carbon ratio affected the fuel cell’s fuel utilization and resulted in a slight decrease in gas turbine thrust. The fuel utilization factor primarily affected the power output of the fuel cell stack, with a minor impact on thrust. Notably, varying the airflow split ratio showed the most significant influence on the overall system performance. This analysis provides insights into the system’s sensitivities and contributes to the development of more sustainable aircraft energy systems.