Figure 1
The flow starts with load consumption and weather data, then moves to the sigmoid regression model for error measurements, M A P E and R 2. The genetic algorithm begins with initialization, then prepares a population with A, B, C, D, and E parameters, then evaluates sigmoid regression. After that, the process checks whether the criteria are satisfied using the number of iterations or error. If the answer is no, the flow continues to selection, then crossover, then mutation, and then returns to evaluate sigmoid regression again. If the answer is yes, the flow continues to show all iterations, errors, and parameters, and then ends.Proposed hybrid sigmoid regression genetic algorithm model