Estimation of renewable energy and built environment-related variables using neural networks – A review

Rodrigues, Eugénio; Gomes, Álvaro; Gaspar, Adélio Rodrigues; Antunes, Carlos Henggeler

doi:10.1016/j.rser.2018.05.060

Cited by 50 publications

(25 citation statements)

References 216 publications

(180 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These are only some of the application of the neural networks to engineering field, which are limited to the energy prediction tasks. Nevertheless, many other applications can be found in literature, especially when the scale field of analysis concerns not only the buildings [24], but also the built environment and the cities [34].…”

Section: 2mentioning

confidence: 99%

Application of artificial neural network and geographic information system to evaluate retrofit potential in public school buildings

Cecconi

Moretti

Tagliabue

2019

Renewable and Sustainable Energy Reviews

View full text Add to dashboard Cite

School buildings in Italy are outdated, in critical maintenance conditions and they often perform below acceptable service levels and quality standards. Nevertheless, data supporting renovation policies are missing or very expensive to be obtained. The paper presents a methods for evaluating building's energy savings potential, using the Building Energy Certification (Certificazione Energetica degli Edifici-CENED) open database. The aim of the research concerns the development of a data-driven set of methods, based on the use of open data, machine learning (ML) and Geographic Information Systems (GIS) to support regional energy retrofit policies on school buildings. The main advantage concerns the possibility to predict the post-retrofit energy savings, avoiding the expensive on-site Condition Assessment (CA) phase. Data have been first clustered to identify the most common thermo-physical properties of the envelope, then three retrofit scenarios have been defined to allow the retrofit of homogeneous types of buildings. The energy saving potentials have been evaluated through the implementation of eight Artificial Neural Networks. Ultimately, data have been geolocated and further processed to support the definition of the energy retrofit policies for the most critical regional areas. The Lombardy region has been chosen as case study to test the robustness of the proposed methods. The results of the case study proved that school buildings energy retrofit policies can be defined and compared using available open data, ML and GIS. The future developments of the research concern the further integration of GIS for retrofit cost assessment and scenario analysis.

show abstract

Section: 2mentioning

confidence: 99%

Application of artificial neural network and geographic information system to evaluate retrofit potential in public school buildings

Cecconi

Moretti

Tagliabue

2019

Renewable and Sustainable Energy Reviews

View full text Add to dashboard Cite

show abstract

“…They achieve high accuracy, are computationally efficient, and require no knowledge of the physical relationships between inputs and outputs. ANNs are a powerful tool for making predictions based on a large number of interrelated experimental data [5,6,21,27,[40][41][42][43][54][55][56].…”

Section: Introductionmentioning

confidence: 99%

The Use of Artificial Neural Networks for Forecasting of Air Temperature inside a Heated Foil Tunnel

Francik

Kurpaska

2020

Sensors

View full text Add to dashboard Cite

It is important to correctly predict the microclimate of a greenhouse for control and crop management purposes. Accurately forecasting temperatures in greenhouses has been a focus of research because internal temperature is one of the most important factors influencing crop growth. Artificial Neural Networks (ANNs) are a powerful tool for making forecasts. The purpose of our research was elaboration of a model that would allow to forecast changes in temperatures inside the heated foil tunnel using ANNs. Experimental research has been carried out in a heated foil tunnel situated on the property of the Agricultural University of Krakow. Obtained results have served as data for ANNs. Conducted research confirmed the usefulness of ANNs as tools for making internal temperature forecasts. From all tested networks, the best is the three-layer Perceptron type network with 10 neurons in the hidden layer. This network has 40 inputs and one output (the forecasted internal temperature). As the networks input previous historical internal temperature, external temperature, sun radiation intensity, wind speed and the hour of making a forecast were used. These ANNs had the lowest Root Mean Square Error (RMSE) value for the testing data set (RMSE value = 3.7 °C).

show abstract

“…Artificial neural network (ANN), a technique for artificial intelligence and machine learning, is often applied as a tool to deal with nonlinear problems and offer predictions in civil engineering [1][2][3][4], material science [5,6], etc. The extension of its applications into the iron and steel industry is also reported [7][8][9][10][11].…”

Section: Introductionmentioning

confidence: 99%

Influence of Variation/Response Space Complexity and Variable Completeness on BP-ANN Model Establishment: Case Study of Steel Ladle Lining

et al. 2019

View full text Add to dashboard Cite

Artificial neural network (ANN) is widely applied as a predictive tool to solve complex problems. The performance of an ANN model is significantly affected by the applied architectural parameters such as the node number in a hidden layer, which is largely determined by the complexity of cases, the quality of the dataset, and the sufficiency of variables. In the present study, the impact of variation/response space complexity and variable completeness on backpropagation (BP) ANN model establishment was investigated, with a steel ladle lining from secondary steel metallurgy as the case study. The variation dataset for analysis comprised 160 lining configurations of ten variables. Thermal and thermomechanical responses were obtained via finite element (FE) modeling with elastic material behavior. Guidelines were proposed to define node numbers in the hidden layer for each response as a function of the node number in the input layer weighted with the percent value of the significant variables contributing above 90% to the response, as well as the node number in the output layer. The minimum numbers of input variables required to achieve acceptable prediction performance were three, five, and six for the maximum compressive stress, the end temperature, and the maximum tensile stress. empirical equations into other fields are far less satisfying. Equations (1) and (2) show more robust applications, yet they yield a rather larger number for trials.

show abstract

Estimation of renewable energy and built environment-related variables using neural networks – A review

Cited by 50 publications

References 216 publications

Application of artificial neural network and geographic information system to evaluate retrofit potential in public school buildings

Application of artificial neural network and geographic information system to evaluate retrofit potential in public school buildings

The Use of Artificial Neural Networks for Forecasting of Air Temperature inside a Heated Foil Tunnel

Influence of Variation/Response Space Complexity and Variable Completeness on BP-ANN Model Establishment: Case Study of Steel Ladle Lining

Contact Info

Product

Resources

About