Electrical Power Prediction through a Combination of Multilayer Perceptron with Water Cycle Ant Lion and Satin Bowerbird Searching Optimizers

Predicting the electrical power (PE) output is a significant step toward sustainable development of combined cycle plants. Due to effect several parameters on simulation PE, utilizing robust method high importance. Hence, in this study, potent metaheuristic strategy, namely, water algorithm (WCA), employed solve issue. First, nonlinear neural network framework formed link PE with influential parameters. Then, optimized by WCA algorithm. A publicly available dataset used feed hybrid model. Since population-based technique, its sensitivity population size assessed trial-and-error effort attain most suitable configuration. The results training phase showed that proposed can find an optimal solution for capturing relationship between and factors less than 1% error. Likewise, examining test revealed model forecast accuracy. Moreover, comparison two powerful benchmark techniques, ant lion optimization satin bowerbird optimizer, pointed as more accurate technique design intended system. Lastly, potential predictive formulas, based efficient WCAs, are extracted presented.