Building Behavior Simulation by Means of Artificial Neural Network in Summer Conditions

Abstract

Many studies in Italy showed that buildings are responsible for about 40% of total energy consumption, due to worsening performance of building envelope; in fact, a great number of Italian buildings were built before the 1970s and 80s. In particular, the energy consumptions for cooling are considerably increased with respect to the ones for heating. In order to reduce the cooling energy demand, ensuring indoor thermal comfort, a careful study on building envelope performance is necessary. Different dynamic software could be used in order to evaluate and to improve the building envelope during the cooling period, but much time and an accurate validation of the model are required. However, when a wide experimental data is available, the Artificial Neural Network (ANN) can be an alternative, simple and fast tool to use. In the present study, the indoor thermal conditions in many dwellings built in Umbria Region were investigated in order to evaluate the envelope performance. They were recently built and have very low energy consumptions. Based on the experimental data, a feed forward network was trained, in order to evaluate the different envelopes performance. As input parameters the outdoor climatic conditions and the thermal characteristics of building envelopes were set, while, as a target parameter, the indoor air temperature was provided. A good training of network was obtained with a high regression value (0.9625) and a very small error (0.007 °C) on air temperature. The network was also used to simulate the envelope behavior with new innovative glazing systems, in order to evaluate and to improve the energy performance.

Mean Age of Air in Natural Ventilated Buildings: Experimental Evaluation and CO2 Prediction by Artificial Neural Networks

“…Neural networks are mathematical models able to simulate the learning process of the biological neural system and can be trained based on experimental data, so they are not programmed [42]. For the implementation of a network able to predict the CO 2 concentration within the room, a similar methodology developed in previous works [37][38][39] was adopted. A multi-layer perceptron (MLP) network with only one hidden layer was trained by using Leverberg-Marquardt backpropagation algorithm and by providing several inputs and one target for the training process: the CO 2 concentration was chosen as the target parameter and the following parameters were supplied as inputs: Table 3.…”

“…Artificial neural networks (ANN), are the most used in prediction problems, i.e., when an output is calculated starting from known parameters [33][34][35][36]. The authors have also studied the ANN in different kinds of applications, such as energy demand [37], thermal comfort [38], and indoor air temperature [39] prediction; in each one, the strengths and weakness of ANN were highlighted. According to these works, artificial neural networks could be a very useful tool for CO 2 concentration prediction within the room, starting from a few input parameters.…”

“…In these studies, the same pattern of ANN was used, i.e., one input, one hidden, and one output layer. Only in [36,39], two hidden layers were needed for obtaining a good reliability of the ANN.…”

“…An ANN was then implemented by using a methodology purposely developed for the intended objectives. Specifically, data of only 19 experimental campaigns were provided for the trained process, while the last 14 surveys were used for testing the generalization of the network, i.e., for checking the reliability of ANN with data different from those used for the training process [33][34][35][36][37][38][39]. The paper is structured as follows: Section 2 presents the case studies, the employed measurement methodology, the instruments characteristic, and the developed methodology for ANN implementation.…”

Research and Application Based on Adaptive Boosting Strategy and Modified CGFPA Algorithm: A Case Study for Wind Speed Forecasting

“…In recent years, ANNs have been successfully utilized in a variety of applications as one of the most current artificial intelligence techniques [47,48]. In numerous neural network architectures, the most prevalent training method is the feed-forward neural network with back propagation (BP) training algorithm [27].…”