Grid search of multilayer perceptron based on the walk-forward validation methodology

Multilayer perceptron neural network is one of the widely used method for load forecasting. There are hyperparameters which can be to determine structure and train multilayer model. This paper aims propose a framework grid search model based on walk-forward validation methodology. The training process will specify optimal models satisfy requirement minimum accuracy scores root mean square error, absolute percentage error error. testing evaluate along with other ones. results indicated that have near values. US airline passenger Ho Chi Minh city demand data were verify reliability framework.