scholarly journals Estimation of Room-Level Cooling Energy in Hot/Arid Climate by Machine Learning-Based Approaches

2021 ◽  
Author(s):  
Bingyan Jia ◽  
Danlin Hou ◽  
Liangzhu (Leon) Wang ◽  
Ibrahim Galal Hassan
Keyword(s):  
Machine Learning ◽  
Power Density ◽  
Mean Squared Error ◽  
Building Energy ◽  
Energy Performance ◽  
Mean Bias Error ◽  
Support Vector ◽  
Bias Error ◽  
Model Parameters ◽  
Meta Model

Abstract Building energy models (BEM) are developed for understanding a building’s energy performance. A meta-model of the whole building energy analysis is often used for the BEM calibration and energy prediction. The literature review shows that studies with a focus on the development of room-level meta-models are missing. This study aims to address this research gap through a case study of a residential building with 138 apartments in Doha, Qatar. Five parameters, including cooling setpoint, number of occupants, lighting power density, equipment power density, and interior solar reflectance, are selected as input parameters to create ninety-six different scenarios. Three machine-learning models are used as meta-models to generalize the relationship between cooling energy and the model parameters, including Multiple Linear Regression, Support Vector Regression, and Artificial Neural Networks. The three meta-models’ prediction accuracies are evaluated by the Normalized Mean Bias Error (NMBE), Coefficient of Variation of the Root Mean Squared Error CV (RMSE), and R square (R2). The results show that the ANN model performs best. A new generic BEM is then established to validate the meta-model. The results indicate that the proposed meta-model is accurate and efficient in predicting the cooling energy in summer and transitional months for a building with a similar floor configuration.

scholarly journals Comparison between Energy Simulation and Monitoring Data in an Office Building

Energies ◽  
2021 ◽  
Vol 15 (1) ◽  
pp. 239
Author(s):  
Koldobika Martin-Escudero ◽  
Garazi Atxalandabaso ◽  
Aitor Erkoreka ◽  
Amaia Uriarte ◽  
Matteo Porta
Keyword(s):  
Building Energy ◽  
Energy Performance ◽  
Building Envelope ◽  
Energy Simulation ◽  
Office Building ◽  
Mean Bias Error ◽  
Bias Error ◽  
Data Sets ◽  
Hourly Basis ◽  
Good Agreement

One of the most important steps in the retrofitting process of a building is to understand its pre-retrofitting stage energy performance. The best choice for carrying this out is by means of a calibrated building energy simulation (BES) model. Then, the testing of different retrofitting solutions in the validated model allows for quantifying the improvements that may be obtained, in order to choose the most suitable solution. In this work, based on the available detailed building drawings, constructive details, building operational data and the data sets obtained on a minute basis (for a whole year) from a dedicated energy monitoring system, the calibration of an in-use office building energy model has been carried out. It has been possible to construct a detailed white box model based on Design Builder software. Then, comparing the model output for indoor air temperature, lighting consumption and heating consumption against the monitored data, some of the building envelope parameters and inner building inertia of the model were fine tuned to obtain fits fulfilling the ASHRAE criteria. Problems found during this fitting process and how they are solved are explained in detail. The model calibration is firstly performed on an hourly basis for a typical winter and summer week; then, the whole year results of the simulation are compared against the monitored data. The results show a good agreement for indoor temperature, lighting and heating consumption compared with the ASHRAE criteria for the mean bias error (MBE).

scholarly journals Evaluation of Urban-Scale Building Energy-Use Models and Tools—Application for the City of Fribourg, Switzerland

2021 ◽  
Vol 13 (4) ◽  
pp. 1595
Author(s):  
Valeria Todeschi ◽  
Roberto Boghetti ◽  
Jérôme H. Kämpf ◽  
Guglielmina Mutani
Keyword(s):  
Machine Learning ◽  
Energy Use ◽  
Residential Buildings ◽  
Building Energy ◽  
Energy Performance ◽  
Space Heating ◽  
Engineering Model ◽  
Building Energy Use ◽  
The Impact ◽  
The City

Building energy-use models and tools can simulate and represent the distribution of energy consumption of buildings located in an urban area. The aim of these models is to simulate the energy performance of buildings at multiple temporal and spatial scales, taking into account both the building shape and the surrounding urban context. This paper investigates existing models by simulating the hourly space heating consumption of residential buildings in an urban environment. Existing bottom-up urban-energy models were applied to the city of Fribourg in order to evaluate the accuracy and flexibility of energy simulations. Two common energy-use models—a machine learning model and a GIS-based engineering model—were compared and evaluated against anonymized monitoring data. The study shows that the simulations were quite precise with an annual mean absolute percentage error of 12.8 and 19.3% for the machine learning and the GIS-based engineering model, respectively, on residential buildings built in different periods of construction. Moreover, a sensitivity analysis using the Morris method was carried out on the GIS-based engineering model in order to assess the impact of input variables on space heating consumption and to identify possible optimization opportunities of the existing model.

Energy models for cost-optimal analysis: Development and calibration of residential reference building models for Northern Cyprus

2021 ◽  
pp. 1420326X2110130
Author(s):  
Manta Marcelinus Dakyen ◽  
Mustafa Dagbasi ◽  
Murat Özdenefe
Keyword(s):  
Energy Efficiency ◽  
Energy Consumption ◽  
Mean Squared Error ◽  
Residential Buildings ◽  
Mean Bias Error ◽  
Bias Error ◽  
Sampled Data ◽  
Low Carbon ◽  
Building Stock ◽  
Northern Cyprus

Ambitious energy efficiency goals constitute an important roadmap towards attaining a low-carbon society. Thus, various building-related stakeholders have introduced regulations targeting the energy efficiency of buildings. However, some countries still lack such policies. This paper is an effort to help bridge this gap for Northern Cyprus, a country devoid of building energy regulations that still experiences electrical energy production and distribution challenges, principally by establishing reference residential buildings which can be the cornerstone for prospective building regulations. Statistical analysis of available building stock data was performed to determine existing residential reference buildings. Five residential reference buildings with distinct configurations that constituted over 75% floor area share of the sampled data emerged, with floor areas varying from 191 to 1006 m2. EnergyPlus models were developed and calibrated for five residential reference buildings against yearly measured electricity consumption. Values of Mean Bias Error (MBE) and Cumulative Variation of Root Mean Squared Error CV(RMSE) between the models’ energy consumption and real energy consumption on monthly based analysis varied within the following ranges: (MBE)monthly from –0.12% to 2.01% and CV(RMSE)monthly from 1.35% to 2.96%. Thermal energy required to maintain the models' setpoint temperatures for cooling and heating varied from 6,134 to 11,451 kWh/year.

scholarly journals Dynamic Detection of Delayed Cerebral Ischemia Using Machine Learning

2020 ◽  
Author(s):  
Murad Megjhani ◽  
Kalijah Terilli ◽  
Ayham Alkhachroum ◽  
David J. Roh ◽  
Sachin Agarwal ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cerebral Ischemia ◽  
Characteristic Curve ◽  
Delayed Cerebral Ischemia ◽  
Risk Scores ◽  
Support Vector ◽  
Model Parameters ◽  
Learning Approaches ◽  
Physiologic Data ◽  
Over Time

AbstractObjectiveTo develop a machine learning based tool, using routine vital signs, to assess delayed cerebral ischemia (DCI) risk over time.MethodsIn this retrospective analysis, physiologic data for 540 consecutive acute subarachnoid hemorrhage patients were collected and annotated as part of a prospective observational cohort study between May 2006 and December 2014. Patients were excluded if (i) no physiologic data was available, (ii) they expired prior to the DCI onset window (< post bleed day 3) or (iii) early angiographic vasospasm was detected on admitting angiogram. DCI was prospectively labeled by consensus of treating physicians. Occurrence of DCI was classified using various machine learning approaches including logistic regression, random forest, support vector machine (linear and kernel), and an ensemble classifier, trained on vitals and subject characteristic features. Hourly risk scores were generated as the posterior probability at time t. We performed five-fold nested cross validation to tune the model parameters and to report the accuracy. All classifiers were evaluated for good discrimination using the area under the receiver operating characteristic curve (AU-ROC) and confusion matrices.ResultsOf 310 patients included in our final analysis, 101 (32.6%) patients developed DCI. We achieved maximal classification of 0.81 [0.75-0.82] AU-ROC. We also predicted 74.7 % of all DCI events 12 hours before typical clinical detection with a ratio of 3 true alerts for every 2 false alerts.ConclusionA data-driven machine learning based detection tool offered hourly assessments of DCI risk and incorporated new physiologic information over time.

scholarly journals Using digital image processing to characterize the Campbell–Stokes sunshine recorder and to derive high-temporal resolution direct solar irradiance

2015 ◽  
Vol 8 (1) ◽  
pp. 183-194 ◽  
Author(s):  
A. Sanchez-Romero ◽  
J. A. González ◽  
J. Calbó ◽  
A. Sanchez-Lorenzo
Keyword(s):  
Image Processing ◽  
Temporal Resolution ◽  
Solar Irradiance ◽  
Atmospheric Aerosol ◽  
Mean Squared Error ◽  
Sunshine Duration ◽  
Strong Relationship ◽  
Mean Bias Error ◽  
Bias Error ◽  
High Temporal Resolution

Abstract. The Campbell–Stokes sunshine recorder (CSSR) has been one of the most commonly used instruments for measuring sunshine duration (SD) through the burn length of a given CSSR card. Many authors have used SD to obtain information about cloudiness and solar radiation (by using Ångström–Prescott type formulas), but the burn width has not been used systematically. In principle, the burn width increases for increasing direct beam irradiance. The aim of this research is to show the relationship between burn width and direct solar irradiance (DSI) and to prove whether this relationship depends on the type of CSSR and burning card. A method of analysis based on image processing of digital scanned images of burned cards is used. With this method, the temporal evolution of the burn width with 1 min resolution can be obtained. From this, SD is easily calculated and compared with the traditional (i.e., visual) determination. The method tends to slightly overestimate SD, but the thresholds that are used in the image processing could be adjusted to obtain an improved estimation. Regarding the burn width, experimental results show that there is a high correlation between two different models of CSSRs, as well as a strong relationship between burn widths and DSI at a high-temporal resolution. Thus, for example, hourly DSI may be estimated from the burn width with higher accuracy than based on burn length (for one of the CSSR, relative root mean squared error is 24 and 30%, respectively; mean bias error is −0.6 and −30.0 W m−2, respectively). The method offers a practical way to exploit long-term sets of CSSR cards to create long time series of DSI. Since DSI is affected by atmospheric aerosol content, CSSR records may also become a proxy measurement for turbidity and atmospheric aerosol loading.

scholarly journals Cloud Detection with Historical Geostationary Satellite Sensors for Climate Applications

2019 ◽  
Vol 11 (9) ◽  
pp. 1052 ◽  
Author(s):  
Reto Stöckli ◽  
Jędrzej S. Bojanowski ◽  
Viju O. John ◽  
Anke Duguay-Tetzlaff ◽  
Quentin Bourgeois ◽  
...  
Keyword(s):  
Mean Squared Error ◽  
Sensor Data ◽  
Mean Bias Error ◽  
Retrieval Algorithm ◽  
Bias Error ◽  
Cloud Detection ◽  
Climate Data ◽  
Detection Algorithms ◽  
Fractional Cover ◽  
Spatio Temporal

Can we build stable Climate Data Records (CDRs) spanning several satellite generations? This study outlines how the ClOud Fractional Cover dataset from METeosat First and Second Generation (COMET) of the EUMETSAT Satellite Application Facility on Climate Monitoring (CM SAF) was created for the 25-year period 1991–2015. Modern multi-spectral cloud detection algorithms cannot be used for historical Geostationary (GEO) sensors due to their limited spectral resolution. We document the innovation needed to create a retrieval algorithm from scratch to provide the required accuracy and stability over several decades. It builds on inter-calibrated radiances now available for historical GEO sensors. It uses spatio-temporal information and a robust clear-sky retrieval. The real strength of GEO observations—the diurnal cycle of reflectance and brightness temperature—is fully exploited instead of just accounting for single “imagery”. The commonly-used naive Bayesian classifier is extended with covariance information of cloud state and variability. The resulting cloud fractional cover CDR has a bias of 1% Mean Bias Error (MBE), a precision of 7% bias-corrected Root-Mean-Squared-Error (bcRMSE) for monthly means, and a decadal stability of 1%. Our experience can serve as motivation for CDR developers to explore novel concepts to exploit historical sensor data.

scholarly journals Spatiotemporal Approaches for Quality Control and Error Correction of Atmospheric Data through Machine Learning

2020 ◽  
Vol 2020 ◽  
pp. 1-12 ◽  
Author(s):  
Hye-Jin Kim ◽  
Sung Min Park ◽  
Byung Jin Choi ◽  
Seung-Hyun Moon ◽  
Yong-Hyuk Kim
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Quality Control ◽  
Mean Squared Error ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Weather Element ◽  
Applied Machine Learning ◽  
Squared Error ◽  
Atmospheric Data

We propose three quality control (QC) techniques using machine learning that depend on the type of input data used for training. These include QC based on time series of a single weather element, QC based on time series in conjunction with other weather elements, and QC using spatiotemporal characteristics. We performed machine learning-based QC on each weather element of atmospheric data, such as temperature, acquired from seven types of IoT sensors and applied machine learning algorithms, such as support vector regression, on data with errors to make meaningful estimates from them. By using the root mean squared error (RMSE), we evaluated the performance of the proposed techniques. As a result, the QC done in conjunction with other weather elements had 0.14% lower RMSE on average than QC conducted with only a single weather element. In the case of QC with spatiotemporal characteristic considerations, the QC done via training with AWS data showed performance with 17% lower RMSE than QC done with only raw data.

scholarly journals Evaluating essential features of proppant transport at engineering scales combining field measurements with machine learning algorithms

2021 ◽  
Author(s):  
Xiaoyu Wang ◽  
Lei Hou ◽  
Xueyu Geng ◽  
Peibin Gong ◽  
Honglei Liu
Keyword(s):  
Machine Learning ◽  
Mean Squared Error ◽  
Learning Algorithms ◽  
Field Measurements ◽  
Stratified Flow ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Proppant Transport ◽  
Control Variate ◽  
Injection Process

The characterization of the proppant transport at a field-engineering scale is still challenging due to the lack of direct subsurface measurements. Features that control the proppant transport may link the experimental and numerical observations to the practical operations at a field scale. To improve the numerical and laboratory simulations, we propose a machine-learning-based workflow to evaluate the essential features of proppant transport and their corresponding calculations. The proppant flow in fractures is estimated by applying the Gated recurrent unit (GRU) and Support-vector machine (SVM) algorithms to the measurements obtained from shale gas fracturing operations. Over 430,000 groups of fracturing data are collected and pre-processed by the proppant transport models to calculate key features, including settlement, stratified flow and inception of settled particles. The features are then fed into machine learning algorithms for pressure prediction. The root mean squared error (RMSE) is used as the criterion for ranking selected features via the control variate method. Our result shows that the stratified-flow feature (fracture-level) possesses better interpretations for the proppant transport, in which the Bi-power model helps to produce the best predictions. The settlement and inception features (particle-level) perform better in cases that the pressure fluctuates significantly, indicating that more complex fractures may have been generated. Moreover, our analyses on the remaining errors in the pressure-ascending cases suggest that (1) an introduction of the alternate-injection process, and (2) the improved calculation of proppant transport in complex fracture networks and highly-filled fractures will be beneficial to both experimental observations and field applications.

Sign in / Sign up

Export Citation Format

Share Document