Determining optimum control of double skin envelope for indoor thermal environment based on artificial neural network

This study aims to develop an artificial neural network (ANN)-based temperature control method to keep energy efficient indoor thermal environment in buildings with double skin envelope systems. Control logic that effectively controls the opening conditions of air inlets and outlets of the double skin envelope as well as the operation of the cooling system was developed employing the ANN model. To determine the optimal structure and learning methods for the ANN model, a parametrical optimization process was conducted in terms of the number of hidden layers, the number of neurons in the hidden layers, learning rate, and moment; this process was followed by performance tests of various optimized models. Analysis of the performance tests proved predictability and adaptability of the developed ANN model for diverse background conditions in terms of stable root mean square (RMS) and mean square error (MSE) values. The developed ANN model showed strong potential as a temperature control method for indoor thermal environment of buildings with double skin envelope systems.