Artificial neural networks for energy analysis of office buildings with daylighting

An artificial neural network (ANN) model was developed for office buildings with daylighting for subtropical climates. A total of nine variables were used as the input parameters – four variables were related to the external weather conditions (daily average dry-bulb temperature, daily average wet-bulb temperature, daily global solar radiation and daily average clearness index), four for the building envelope designs (solar aperture, daylight aperture, overhang and side-fins projections), and the last variable was day type (i.e. weekdays, Saturdays and Sundays). There were four nodes at the output layer with the estimated daily electricity use for cooling, heating, electric lighting and total building as the output. Building energy simulation using EnergyPlus was conducted to generate daily building energy use database for the training and testing of ANNs. The Nash–Sutcliffe efficiency coefficient for the ANN modelled cooling, heating, electric lighting and total building electricity use was 0.994, 0.940, 0.993, and 0.996, respectively, indicating excellent predictive power. Error analysis showed that lighting electricity use had the smallest errors, from 0.2% under-estimation to 3.6% over-estimation, with the coefficient of variation of the root mean square error ranging from 3% to 5.6%.     

Future projection of the energy dependency of Turkey using artificial neural network

Energy dependency (ED) implies the extent to which an economy relies upon imports in order to meet its energy needs. The ED is calculated as net imports divided by the sum of gross inland energy consumption plus bunkers. This study aims at obtaining numerical equations to estimate of Turkey's energy dependency based on basic energy indicators and sectoral energy consumption by using artificial neural network (ANN) technique. It seeks to contribute to the strategies necessary to preserve the supply–demand balance of Turkey. For this purpose, two different models were used to train the ANN approach. In Model 1, main energy indicators such as total production of primary energy per capita, total gross electricity generation per capita and final energy consumption per capita were used in the input layer of the ANN while sectoral energy consumption per capita was used in Model 2.The ED was in the output layer for both models. Different models were employed to estimate the ED with a high confidence for future projections. The R² values of ED were found to be 0.999 for both models. In accordance with the analysis results, ED is expected to increase from 72% to 82% within 14 years of period. Consequently, the utilization of renewable energy sources and nuclear energy is strictly recommended to ensure the ED stability in Turkey.     

Artificial neural network for forecasting residential electrical energy

An artificial neural network (ANN) model for forecasting the residential electrical energy (REE) in the Eastern Province of Saudi Arabia is presented. A comparison of the neural model with the polynomial fit is made for validation purposes. The results show that the forecasting of the REE predicted by the ANN is closer to the real data than that predicted by the polynomial fit model. Copyright © 1999 John Wiley & Sons, Ltd.     

Artificial neural network estimation of global solar radiation using air temperature and relative humidity

Measured air temperature and relative humidity values between 1998 and 2002 for Abha city in Saudi Arabia were used for the estimation of global solar radiation (GSR) in future time domain using artificial neural network method. The estimations of GSR were made using three combinations of data sets namely: (i) day of the year and daily maximum air temperature as inputs and GSR as output, (ii) day of the year and daily mean air temperature as inputs and GSR as output and (iii) time day of the year, daily mean air temperature and relative humidity as inputs and GSR as output. The measured data between 1998 and 2001 were used for training the neural networks while the remaining 240 days’ data from 2002 as testing data. The testing data were not used in training the neural networks. Obtained results show that neural networks are well capable of estimating GSR from temperature and relative humidity. This can be used for estimating GSR for locations where only temperature and humidity data are available.     

Artificial neural network analysis of liquid desiccant dehumidification system

The dehumidification process involves simultaneous heat and mass transfer and reliable transfer coefficients are required in order to analyze the system. This has been proved to be difficult and many assumptions are made to simplify the analysis. The present research proposes the use of ANN based model in order to simulate the relationship between inlet and outlet parameters of the dehumidifier. For the analysis, randomly packed dehumidifier with lithium chloride as the liquid desiccant is chosen. A multilayer ANN is used to investigate the performance of dehumidifier. For training ANN models, data is obtained from analytical equations. Eight parameters are used as inputs to the ANN, namely: air and desiccant flow rates, air and desiccant inlet temperatures, air inlet humidity, desiccant inlet concentration, dimensionless temperature ratio, and inlet temperature of the cooling water. The outputs of the ANN are the water condensation rate and the outlet desiccant concentration as well as its temperature. ANN predictions for these parameters are validated well with experimental values available in the literature with R² value in the range of 0.9251-0.9660. This study shows that liquid desiccant dehumidification system can be alternatively modeled using ANN with a reasonable degree of accuracy.     

Transport energy demand modeling of South Korea using artificial neural network

Artificial neural network models were developed to forecast South Korea's transport energy demand. Various independent variables, such as GDP, population, oil price, number of vehicle registrations, and passenger transport amount, were considered and several good models (Model 1 with GDP, population, and passenger transport amount; Model 2 with GDP, number of vehicle registrations, and passenger transport amount; and Model 3 with oil price, number of vehicle registrations, and passenger transport amount) were selected by comparing with multiple linear regression models. Although certain regression models obtained better R-squared values than neural network models, this does not guarantee the fact that the former is better than the latter because root mean squared errors of the former were much inferior to those of the latter. Also, certain regression model had structural weakness based on P-value. Instead, neural network models produced more robust results. Forecasted results using the neural network models show that South Korea will consume around 37 MTOE of transport energy in 2025.     

Development of surrogate models using artificial neural network for building shell energy labelling

Surrogate models are an important part of building energy labelling programs, but these models still present low accuracy, particularly in cooling-dominated climates. The objective of this study was to evaluate the feasibility of using an artificial neural network (ANN) to improve the accuracy of surrogate models for labelling purposes. An ANN was applied to model the building stock of a city in Brazil, based on the results of extensive simulations using the high-resolution building energy simulation program EnergyPlus. Sensitivity and uncertainty analyses were carried out to evaluate the behaviour of the ANN model, and the variations in the best and worst performance for several typologies were analysed in relation to variations in the input parameters and building characteristics. The results obtained indicate that an ANN can represent the interaction between input and output data for a vast and diverse building stock. Sensitivity analysis showed that no single input parameter can be identified as the main factor responsible for the building energy performance. The uncertainty associated with several parameters plays a major role in assessing building energy performance, together with the facade area and the shell-to-floor ratio. The results of this study may have a profound impact as ANNs could be applied in the future to define regulations in many countries, with positive effects on optimizing the energy consumption.     

Mechanically aspirated radiation shields: A CFD and neural network design analysis

Accurate air temperature measurements made by surface meteorological stations are demanded by climate research programs for various uses. Heating of the temperature sensor due to coupling with the environment can lead to significant errors. Therefore, accurate in situ temperature measurements require shielding the sensor from exposure to direct and reflected solar radiation, while also allowing the sensor to be brought into contact with atmospheric air at the ambient temperature. The difficulty in designing a radiation shield for such a temperature sensor lies in satisfying these two conditions simultaneously. In this paper, we perform a computational fluid dynamics analysis of mechanically aspirated radiation shields (MARS) to study the effect of geometry, wind speed, and interplay of multiple heat transfer processes. Finally, an artificial neural network model is developed to learn the relationship between the temperature error and specified input variables. The model is then used to perform a sensitivity analysis and design optimization.     

Artificial Neural Networks based thermodynamic and economic analysis of a hydrogen production system assisted by geothermal energy on Field Programmable Gate Array

In this study, the thermodynamic and economic analysis of a geothermal energy assisted hydrogen production system was performed using real-time Artificial Neural Networks on Field Programmable Gate Array. During the modeling of the system in the computer environment, a liquid geothermal resource with a temperature of 200 °C and a flow rate of 100 kg/s was used for electricity generation, and this electricity was used as a work input in the electrolysis unit to split off water into the hydrogen and oxygen. In the designed system, the net work produced from the geothermal power cycle, the overall exergy efficiency of the system, the unit cost of the produced hydrogen and the simple payback period of the system were calculated as 7978 kW, 38.37%, 1.088 $/kg H₂ and 4.074 years, respectively. In the second stage of the study, Feed-Forward Artificial Neural Networks model with a single hidden layer was used for modeling the system. The activation functions of the hidden layer and output layer were Tangent Sigmoid and Linear functions, respectively. The system was implemented on Field Programmable Gate Array using the Matlab-based model of the system as a reference. The maximum operating frequency and chip statistics of the designed unit of Field Programmable Gate Array based geothermal energy assisted hydrogen production system were presented. The result can be used to gain better knowledge and optimize hydrogen production systems.     

Modelling of solar energy potential in Nigeria using an artificial neural network model

In this study, an artificial neural network (ANN) based model for prediction of solar energy potential in Nigeria (lat. 4–14°N, log. 2–15°E) was developed. Standard multilayered, feed-forward, back-propagation neural networks with different architecture were designed using neural toolbox for MATLAB. Geographical and meteorological data of 195 cities in Nigeria for period of 10 years (1983–1993) from the NASA geo-satellite database were used for the training and testing the network. Meteorological and geographical data (latitude, longitude, altitude, month, mean sunshine duration, mean temperature, and relative humidity) were used as inputs to the network, while the solar radiation intensity was used as the output of the network. The results show that the correlation coefficients between the ANN predictions and actual mean monthly global solar radiation intensities for training and testing datasets were higher than 90%, thus suggesting a high reliability of the model for evaluation of solar radiation in locations where solar radiation data are not available. The predicted solar radiation values from the model were given in form of monthly maps. The monthly mean solar radiation potential in northern and southern regions ranged from 7.01–5.62 to 5.43–3.54 kW h/m² day, respectively. A graphical user interface (GUI) was developed for the application of the model. The model can be used easily for estimation of solar radiation for preliminary design of solar applications.     

Artificial neural networks used for the prediction of the cetane number of biodiesel

Cetane number (CN) is one of the most significant properties to specify the ignition quality of any fuel for internal combustion engines. The CN of biodiesel varies widely in the range of 48–67 depending upon various parameters including the oil processing technology and climatic conditions where the feedstock (vegetable oil) is collected. Determination of the CN of a fuel by an experimental procedure is a tedious job for the upcoming biodiesel production industry. The fatty acid composition of base oil predominantly affects the CN of the biodiesel produced from it. This paper discusses the currently available CN estimation techniques and the necessity of accurate prediction of CN of biodiesel. Artificial Neural Network (ANN) models are developed to predict the CN of any biodiesel. The present paper deals with the application of multi-layer feed forward, radial base, generalized regression and recurrent network models for the prediction of CN. The fatty acid compositions of biodiesel and the experimental CNs are used to train the networks. The parameters that affect the development of the model are also discussed. ANN predicted CNs are found to be in agreement with the experimental CNs. Hence, the ANN models developed can be used reliably for the prediction of CN of biodiesel.     

Energy demand estimation of South Korea using artificial neural network

Because South Korea's industries depend heavily on imported energy sources (fifth largest importer of oil and second largest importer of liquefied natural gas in the world), the accurate estimating of its energy demand is critical in energy policy-making. This research proposes an artificial neural network model (a structure with feed-forward multilayer perceptron, error back-propagation algorithm, momentum process, and scaled data) to efficiently estimate the energy demand for South Korea. The model has four independent variables, such as gross domestic product (GDP), population, import, and export amounts. The data are obtained from diverse local and international sources. The proposed model better estimated energy demand than a linear regression model (a structure with multiple linear variables and least square method) or an exponential model (a structure with mixed integer variables, branch and bound method, and Broyden–Fletcher–Goldfarb–Shanno (BFGS) method) in terms of root mean squared error (RMSE). The model also forecasted better than the other two models in terms of RMSE without any over-fitting problem. Further testing with four scenarios based upon reliable source data showed unanticipated results. Instead of growing permanently, the energy demands peaked at certain points, and then decreased gradually. This trend is quite different from the results by regression or exponential model.     

Analysis of residential energy use

The structure, inputs, validation and operation of a residential energy use model are examined with the intention of providing an analytical tool for evaluation of energy conservation option for effects on energy use and related costs.     

Artificial neural networks applications in building energy predictions and a case study for tropical climates

This study presents artificial neural network (ANN) methods in building energy use predictions. Applications of the ANN methods in energy audits and energy savings predictions due to building retrofits are emphasized. A generalized ANN model that can be applied to any building type with minor modifications would be a very useful tool for building engineers. ANN methods offer faster learning time, simplicity in analysis and adaptability to seasonal climate variations and changes in the building's energy use when compared to other statistical and simulation models. The model herein is presented for predicting chiller plant energy use in tropical climates with small seasonal and daily variations. It was successfully created based on both climatic and chiller data. The average absolute training error for the model was 9.7% while the testing error was 10.0%. This indicates that the model can successfully predict the particular chiller energy consumption in a tropical climate. Copyright © 2005 John Wiley & Sons, Ltd.     

Artificial neural network prediction indicators of density functional theory metal hydride models

The metal hydride is a capable candidate for mobile storage for hydrogen-powered vehicles. An artificial neural network (ANN) has proved useful for many applications, and capable of much more in discovery of new materials. Because of its ability to generalize from examples presented to it, an ANN is a powerful tool for discovering new metal hydride combinations. An ANN can deduce quantitative structure property relationships for metal hydrides. The ANN found correlations between fundamental electronic and energy values modeled ab initio and several experimental parameters. Some of the properties successfully predicted with good correlation are: entropy, enthalpy, temperature at 1 atm of pressure, pressure at 25 °C, and the percent weight of hydrogen stored. The marriage of ANN to computational modeling produces good predictions for many important properties of metal hydrides.     

Estimation of the energy of a PV generator using artificial neural network

The integration of grid-connected photovoltaic (GCPVS) systems into urban buildings is very popular in industrialized countries. Many countries enhance the international collaboration efforts which accelerate the development and deployment of photovoltaic solar energy as a significant and sustainable renewable energy option. A previous method, based on artificial neural networks (ANNs), has been developed to electrical characterisation of PV modules. This method was able to generate V–I curves of si-crystalline PV modules for any irradiance and module cell temperature. The results showed that the proposed ANN introduced a good accurate prediction for si-crystalline PV modules performance when compared with the measured values. Now, this method, based on ANNs, is going to be applied to obtain a suitable value of the power provided by a photovoltaic installation. Specifically this method is going to be applied to obtain the power provided by a particular installation, the “Univer generator”, since modules used in these works were the same as the ones used in this photovoltaic generator.     

Optimization of an artificial neural network dedicated to the multivariate forecasting of daily global radiation

This paper presents an application of Artificial Neural Networks (ANNs) to predict daily solar radiation. We look at the Multi-Layer Perceptron (MLP) network which is the most used of ANNs architectures. In previous studies, we have developed an ad-hoc time series preprocessing and optimized a MLP with endogenous inputs in order to forecast the solar radiation on a horizontal surface. We propose in this paper to study the contribution of exogenous meteorological data (multivariate method) as time series to our optimized MLP and compare with different forecasting methods: a naïve forecaster (persistence), ARIMA reference predictor, an ANN with preprocessing using only endogenous inputs (univariate method) and an ANN with preprocessing using endogenous and exogenous inputs. The use of exogenous data generates an nRMSE decrease between 0.5% and 1% for two stations during 2006 and 2007 (Corsica Island, France). The prediction results are also relevant for the concrete case of a tilted PV wall (1.175 kWp). The addition of endogenous and exogenous data allows a 1% decrease of the nRMSE over a 6 months-cloudy period for the power production. While the use of exogenous data shows an interest in winter, endogenous data as inputs on a preprocessed ANN seem sufficient in summer.     

Determination and modelling of energy consumption in wheat production using neural networks: “A case study in Canterbury province, New Zealand”

This study was conducted on irrigated and dryland wheat fields in Canterbury in the 2007-2008 harvest year based on an extensive process of data collection involving a questionnaire and interviews. Total energy consumption in wheat production was estimated at 22,566 MJ/ha. On average, fertilizer and electricity were used more than other energy sources, at around 10,654 (47%) and 4870 (22%) MJ/ha, respectively. The energy consumption for wheat production in irrigated and dryland farming systems was estimated at 25,600 and 17,458 MJ/ha, respectively.In this study, several direct and indirect factors have been identified to create an artificial neural networks (ANN) model to predict energy use in wheat production. The final model can predict energy consumption based on farm conditions (size of crop area), farmers’ social considerations (level of education), and energy inputs (N and P use and irrigation frequency), and it predicts energy use in Canterbury arable farms with an error margin of ±12% (±2900 MJ/ha). Furthermore, comparison between the ANN model and a Multiple Linear Regression (MLR) model showed that the ANN model can predict energy consumption relatively better than the MLR multiple model on the selected training set and validation set.     

Artificial neural network models for predicting soil thermal resistivity

Thermal properties of soils are of great importance in view of the modern trends of utilizing the subsurface for transmission of either heated fluids or high power currents. For these situations, it is essential to estimate the resistance offered by the soil mass in dissipating the heat generated through it. Several investigators have tried to develop mathematical and theoretical models to estimate soil thermal resistivity. However, it is evident that these models are not efficient enough to predict accurate thermal resistivity of soils. This is mainly due to the fact that thermal resistivity of soils is a complex phenomenon that depends upon various parameters viz., type of the soil, particle size distribution and its compaction characteristics (i.e., dry density and moisture content). To overcome this, Artificial Neural Network (ANN) models, which are based on experimentally obtained thermal resistivity values for clay, silt, silty-sand, fine- and coarse-sands, have been developed. Incidentally, these soils are the most commonly encountered soils in nature and exhibit entirely different characteristics. The thermal resistivity of these soils, corresponding to their different compaction states, was obtained with the help of a laboratory thermal probe and compared vis-à-vis those obtained from the ANN model. The thermal resistivity of these soils obtained from ANN models and experimental investigations are found to match extremely well. The performance indices such as coefficient of determination, root mean square error, mean absolute error, and variance account for were used to control the performance of the prediction capacity of the models developed in this study. In addition to this, thermal resistivity of these soils obtained from ANN models were compared with those computed from the empirical relationships reported in the literature and were found to be superior. The study demonstrates the utility and efficiency of the ANN model for estimating thermal resistivity of soils.     

Electric load forecasting by using dynamic neural network

Electrical energy is fundamental for the wellbeing and for the economic development of any country. However, all countries must ensure access to essential resources and ensure the continuity of its supply. Due to the non-storable nature of electrical energy, the amount of consumed active power should always be equal the produced active power just to avoid power system frequency deviation problem. In order to keep the relationship production–consumption relation in compliance with different standards and to secure profitable operations of power system, electric load consumption must be predicted and controlled instantaneously. Several statistical and classical techniques are proposed in the literature but unfortunately all these methods are not accurate in a satisfactory manner. In this paper, a dynamic neural network is used for the prediction of daily power consumption. The suitability and the performance of the proposed approach is illustrated and verified with simulations on load data collected from French Transmission System Operator (RTE) website. The obtained results show that the accuracy and the efficiency are improved comparatively to conventional methods widely used in this field of research.