Edwin Rodriguez-Ubinas | Universidad Politécnica de Madrid (original) (raw)

Papers by Edwin Rodriguez-Ubinas

2021 2nd International Conference on Electronics, Communications and Information Technology (CECIT), Dec 1, 2021

This paper uses machine learning techniques to model monthly electricity consumption data of Duba... more This paper uses machine learning techniques to model monthly electricity consumption data of Dubai, the United Arab Emirates, at a consumer level to predict month-ahead prediction. Mainly, statistical-based multivariate approaches are used in conjunction with weather data for modeling electricity consumption. However, in this study, data of occupant's profile is analyzed along with regular consumption data for modeling and capturing the trend of electricity consumption. First, the two data sets are joined to extract the consumer's profile-driven electricity consumption dataset. And then, a ranking-based feature selection using a correlation approach is used, and further, the outlier removal process is performed to obtain the filtered data. Among various machine learning approaches, the Random Forest approach is found to have a better model with the least RMSE and MAPE across a 5-fold cross-validation approach.

Energy and Buildings, Jul 1, 2023

Energy Reports, Sep 1, 2023

Sustainability

The construction industry is one of the largest consumers of natural resources, and the building ... more The construction industry is one of the largest consumers of natural resources, and the building sector accounts for around 40% of energy consumption and CO2 emissions. To contribute to the need for more sustainable solutions, this research analyzed and highlighted the benefits of off-site construction, utilizing eleven zero-energy prefabricated houses from the Solar Decathlon Middle East competition as case studies. The study used construction data documented by the competition organizers, such as drawings, manuals, photos, and in-person observations during the assembly process. The comparative analysis focused on the construction categories, types of solutions, structural materials, façade types, and building materials. The case studies featured both heavy and lightweight construction and three types of off-site construction: panelized, volumetric, and hybrid. The hybrid construction was the most utilized since it combines the advantages of less intensive on-site work of the volum...

Energies

The building sector consumes as much as 80% of generated electricity in the UAE; during the COVID... more The building sector consumes as much as 80% of generated electricity in the UAE; during the COVID-19 pandemic, the energy consumption of two sub-sectors, i.e., commercial (50%) and residential (30%), was significantly impacted. The residential sector was impacted the most due to an increase in the average occupancy during the lockdown period. This increment continued even after the lockdown due to the fear of infection. The COVID-19 pandemic and its lockdown measures can be considered experimental setups, allowing for a better understanding of how users shift their consumption under new conditions. The emergency health measures and new social dynamics shaped the residential sector’s energy behavior and its increase in electricity consumption. This article presents and analyzes the identified issues concerning residential electricity consumers and how their behaviors change based on the electricity consumption data during the COVID-19 period. The Dubai Electricity and Water Authority...

International Journal of Energy Production and Management

2021 2nd International Conference on Electronics, Communications and Information Technology (CECIT)

This paper uses machine learning techniques to model monthly electricity consumption data of Duba... more This paper uses machine learning techniques to model monthly electricity consumption data of Dubai, the United Arab Emirates, at a consumer level to predict month-ahead prediction. Mainly, statistical-based multivariate approaches are used in conjunction with weather data for modeling electricity consumption. However, in this study, data of occupant's profile is analyzed along with regular consumption data for modeling and capturing the trend of electricity consumption. First, the two data sets are joined to extract the consumer's profile-driven electricity consumption dataset. And then, a ranking-based feature selection using a correlation approach is used, and further, the outlier removal process is performed to obtain the filtered data. Among various machine learning approaches, the Random Forest approach is found to have a better model with the least RMSE and MAPE across a 5-fold cross-validation approach.

WIT Transactions on Ecology and the Environment

The high energy consumption of buildings in desert environments, caused mainly by high cooling ne... more The high energy consumption of buildings in desert environments, caused mainly by high cooling needs, calls for mitigation. In Dubai, it is estimated that buildings account for 70% of the total energy demand, and this share is expected to grow due to the urbanization rate. One strategy to reduce building consumption is implementing zero energy buildings. These are energy-efficient buildings capable of generating their own energy consumption. Passive design options are key for managing building energy demand. This work analyses the passive design options used in zero energy houses in Dubai for the Solar Decathlon Middle East 2021, where the participating teams designed, constructed, and testoperated fully solar-powered houses. First, we describe the strategies that include compactness of the building shape, orientation, and the envelope's thermal performance, and compare them with the best practices for the region. We find that the high-performing opaque surfaces exceed Dubai's Green Building Rating system, the transparent surfaces are mostly placed in the north unshaded, the east and west facades have little to no openings, while the south ones are mostly horizontally shaded, and there is a low window to wall ratio. Lastly, we consider the effect of these strategies against the monitored building performance during the competition: the light level (lux), the electricity consumed for heating, cooling, ventilation, and lighting (kWh), the indoor temperature (°C), controlling for solar radiation (W/m 2) and outdoor temperature. The findings highlight solutions that best respond to Dubai's environment and help to improve the energy performance of the buildings in desert climates.

WIT Transactions on Ecology and the Environment

WIT Transactions on The Built Environment

This paper presents a test and validation research on the energy performance of photovoltaic solu... more This paper presents a test and validation research on the energy performance of photovoltaic solutions integrated as opaque, ventilated façades in the harsh desert climate of Dubai, UAE. We have assessed the performance of copper indium gallium selenide (CIGS) and monocrystalline silicon (c-Si) modules in the three most suitable orientations for Dubai's buildings (south, east, and west), over one full year. Additionally, we investigated the effect of modules' temperature on the energy yield. The normalized energy yield of c-Si modules was continuously higher than the CIGS modules, across all orientations, with an average annual difference of 13.6%. Throughout the whole period, the south-oriented modules produced more energy than those in the east and west. During the period from October to February, they produced up to 48.5% more than the other orientations. The east and west façades, on the other hand, produced up to 40.9% more energy than the south in the period from April to August. Furthermore, although the annual irradiance on the west was only 1.7% lower than the east, the annual production of the west modules was more than 12% less. These modules start to receive direct solar irradiation in the afternoon when ambient temperatures reach their highest values, and after they accumulated heat during the morning.

Given the extreme hot and humid ambient conditions of UAE, it comes no surprise that the demand f... more Given the extreme hot and humid ambient conditions of UAE, it comes no surprise that the demand for air conditioning would increase rapidly. In the UAE, roughly 90% of the electricity is consumed by the building sector. In that sector, air conditioners (A/Cs) consume about 80% of the total annual house electricity. The fact that performance of A/Cs decreases as the ambient temperature increases. Additional challenge to optimize energy consumption is that in hot and humid regions A/C units are simultaneously required to control the temperature and humidity. Thus, oversized A/C units are usually used which increases the energy consumption and affect indoor thermal comfort. This study aimed to analyze the implementation of the ASHRAE standard in a residence in Dubai. Transient System Simulation (TRNSYS) program is selected to study a detailed analysis of a residential building implementing ASHRAE building standards. The goal is to reach to an indoor temperature of 22.5°C and a 50% relative humidity according to ASHRAE standards. The values obtained from running the simulation over all the zones can now be used in order to size the A/C system. The maximum required load for all zones is 59.6 kW, however after applying the optimization method it was reduced by 4,5% to reach 56.9kW.

International journal of energy production and management, Aug 25, 2022

Energy Reports, Dec 1, 2023

Energy Conversion and Management

Lecture Notes in Computer Science, 2022

WIT Transactions on Ecology and the Environment

Zero-energy buildings are one of the most effective decarbonization strategies for cities. They a... more Zero-energy buildings are one of the most effective decarbonization strategies for cities. They are highly efficient buildings that can generate enough energy to meet their demand using renewables. Photovoltaics (PV) is a cost-effective way of generating renewable energy in buildings. Additionally, PV modules can be more than generation systems and be an essential part of the buildings, contributing to their appearance, thermal performance, and daylight harvesting. New policies and regulations around the world encourage the use of PV and bring more flexibility for their integration in buildings. Therefore, it is fundamental for regulators, researchers, and building professionals, to have a comprehensive PV in buildings categorization. As a response, the objective of this work was to develop a classification for building attached photovoltaics (BAPV) and building integrated photovoltaics (BIPV). The classifications resulted from an extensive literature review that helped to identify relevant aspects, criteria, and gaps in previous categorizations. It considers the application type, location, opacity, accessibility from the inside, and heat dissipation (a missing parameter in prior works). After summarizing the existing categories, describing the findings, and explaining the proposed classifications, the authors illustrated them using zero-energy houses.

Energy Conversion and Management

IOP Conference Series: Earth and Environmental Science

The ability of bifacial photovoltaic (PV) modules to generate additional energy from the rear sid... more The ability of bifacial photovoltaic (PV) modules to generate additional energy from the rear side makes the selection of a tilt angle more challenging than its counterpart monofacial PV. Multiple factors such as site conditions (albedo, average sun-hour ambient temperature, elevation from sea level, diffuse fraction, global horizontal irradiance, and latitude) and PV module specifications (such as bifaciality, power temperature coefficient, and efficiency) can influence the optimum tilt that ensures maximum annual yield of the bifacial PV modules. System Advisor Model (SAM) is used to generate a training dataset of optimal tilt that covers a global range of site conditions and module specifications. Furthermore, we used a Ranker-based feature selection approach to evaluate features and generate a rank-list based on their R-squared score to the dependent variable. From all the available features, the absolute latitude value, sun hour ambient temperature, global horizontal irradiance...

2021 2nd International Conference on Electronics, Communications and Information Technology (CECIT), Dec 1, 2021

This paper uses machine learning techniques to model monthly electricity consumption data of Duba... more This paper uses machine learning techniques to model monthly electricity consumption data of Dubai, the United Arab Emirates, at a consumer level to predict month-ahead prediction. Mainly, statistical-based multivariate approaches are used in conjunction with weather data for modeling electricity consumption. However, in this study, data of occupant's profile is analyzed along with regular consumption data for modeling and capturing the trend of electricity consumption. First, the two data sets are joined to extract the consumer's profile-driven electricity consumption dataset. And then, a ranking-based feature selection using a correlation approach is used, and further, the outlier removal process is performed to obtain the filtered data. Among various machine learning approaches, the Random Forest approach is found to have a better model with the least RMSE and MAPE across a 5-fold cross-validation approach.

Energy and Buildings, Jul 1, 2023

Energy Reports, Sep 1, 2023

Sustainability

The construction industry is one of the largest consumers of natural resources, and the building ... more The construction industry is one of the largest consumers of natural resources, and the building sector accounts for around 40% of energy consumption and CO2 emissions. To contribute to the need for more sustainable solutions, this research analyzed and highlighted the benefits of off-site construction, utilizing eleven zero-energy prefabricated houses from the Solar Decathlon Middle East competition as case studies. The study used construction data documented by the competition organizers, such as drawings, manuals, photos, and in-person observations during the assembly process. The comparative analysis focused on the construction categories, types of solutions, structural materials, façade types, and building materials. The case studies featured both heavy and lightweight construction and three types of off-site construction: panelized, volumetric, and hybrid. The hybrid construction was the most utilized since it combines the advantages of less intensive on-site work of the volum...

Energies

The building sector consumes as much as 80% of generated electricity in the UAE; during the COVID... more The building sector consumes as much as 80% of generated electricity in the UAE; during the COVID-19 pandemic, the energy consumption of two sub-sectors, i.e., commercial (50%) and residential (30%), was significantly impacted. The residential sector was impacted the most due to an increase in the average occupancy during the lockdown period. This increment continued even after the lockdown due to the fear of infection. The COVID-19 pandemic and its lockdown measures can be considered experimental setups, allowing for a better understanding of how users shift their consumption under new conditions. The emergency health measures and new social dynamics shaped the residential sector’s energy behavior and its increase in electricity consumption. This article presents and analyzes the identified issues concerning residential electricity consumers and how their behaviors change based on the electricity consumption data during the COVID-19 period. The Dubai Electricity and Water Authority...

International Journal of Energy Production and Management

2021 2nd International Conference on Electronics, Communications and Information Technology (CECIT)

This paper uses machine learning techniques to model monthly electricity consumption data of Duba... more This paper uses machine learning techniques to model monthly electricity consumption data of Dubai, the United Arab Emirates, at a consumer level to predict month-ahead prediction. Mainly, statistical-based multivariate approaches are used in conjunction with weather data for modeling electricity consumption. However, in this study, data of occupant's profile is analyzed along with regular consumption data for modeling and capturing the trend of electricity consumption. First, the two data sets are joined to extract the consumer's profile-driven electricity consumption dataset. And then, a ranking-based feature selection using a correlation approach is used, and further, the outlier removal process is performed to obtain the filtered data. Among various machine learning approaches, the Random Forest approach is found to have a better model with the least RMSE and MAPE across a 5-fold cross-validation approach.

WIT Transactions on Ecology and the Environment

The high energy consumption of buildings in desert environments, caused mainly by high cooling ne... more The high energy consumption of buildings in desert environments, caused mainly by high cooling needs, calls for mitigation. In Dubai, it is estimated that buildings account for 70% of the total energy demand, and this share is expected to grow due to the urbanization rate. One strategy to reduce building consumption is implementing zero energy buildings. These are energy-efficient buildings capable of generating their own energy consumption. Passive design options are key for managing building energy demand. This work analyses the passive design options used in zero energy houses in Dubai for the Solar Decathlon Middle East 2021, where the participating teams designed, constructed, and testoperated fully solar-powered houses. First, we describe the strategies that include compactness of the building shape, orientation, and the envelope's thermal performance, and compare them with the best practices for the region. We find that the high-performing opaque surfaces exceed Dubai's Green Building Rating system, the transparent surfaces are mostly placed in the north unshaded, the east and west facades have little to no openings, while the south ones are mostly horizontally shaded, and there is a low window to wall ratio. Lastly, we consider the effect of these strategies against the monitored building performance during the competition: the light level (lux), the electricity consumed for heating, cooling, ventilation, and lighting (kWh), the indoor temperature (°C), controlling for solar radiation (W/m 2) and outdoor temperature. The findings highlight solutions that best respond to Dubai's environment and help to improve the energy performance of the buildings in desert climates.

WIT Transactions on Ecology and the Environment

WIT Transactions on The Built Environment

This paper presents a test and validation research on the energy performance of photovoltaic solu... more This paper presents a test and validation research on the energy performance of photovoltaic solutions integrated as opaque, ventilated façades in the harsh desert climate of Dubai, UAE. We have assessed the performance of copper indium gallium selenide (CIGS) and monocrystalline silicon (c-Si) modules in the three most suitable orientations for Dubai's buildings (south, east, and west), over one full year. Additionally, we investigated the effect of modules' temperature on the energy yield. The normalized energy yield of c-Si modules was continuously higher than the CIGS modules, across all orientations, with an average annual difference of 13.6%. Throughout the whole period, the south-oriented modules produced more energy than those in the east and west. During the period from October to February, they produced up to 48.5% more than the other orientations. The east and west façades, on the other hand, produced up to 40.9% more energy than the south in the period from April to August. Furthermore, although the annual irradiance on the west was only 1.7% lower than the east, the annual production of the west modules was more than 12% less. These modules start to receive direct solar irradiation in the afternoon when ambient temperatures reach their highest values, and after they accumulated heat during the morning.

Given the extreme hot and humid ambient conditions of UAE, it comes no surprise that the demand f... more Given the extreme hot and humid ambient conditions of UAE, it comes no surprise that the demand for air conditioning would increase rapidly. In the UAE, roughly 90% of the electricity is consumed by the building sector. In that sector, air conditioners (A/Cs) consume about 80% of the total annual house electricity. The fact that performance of A/Cs decreases as the ambient temperature increases. Additional challenge to optimize energy consumption is that in hot and humid regions A/C units are simultaneously required to control the temperature and humidity. Thus, oversized A/C units are usually used which increases the energy consumption and affect indoor thermal comfort. This study aimed to analyze the implementation of the ASHRAE standard in a residence in Dubai. Transient System Simulation (TRNSYS) program is selected to study a detailed analysis of a residential building implementing ASHRAE building standards. The goal is to reach to an indoor temperature of 22.5°C and a 50% relative humidity according to ASHRAE standards. The values obtained from running the simulation over all the zones can now be used in order to size the A/C system. The maximum required load for all zones is 59.6 kW, however after applying the optimization method it was reduced by 4,5% to reach 56.9kW.

International journal of energy production and management, Aug 25, 2022

Energy Reports, Dec 1, 2023

Energy Conversion and Management

Lecture Notes in Computer Science, 2022

WIT Transactions on Ecology and the Environment

Zero-energy buildings are one of the most effective decarbonization strategies for cities. They a... more Zero-energy buildings are one of the most effective decarbonization strategies for cities. They are highly efficient buildings that can generate enough energy to meet their demand using renewables. Photovoltaics (PV) is a cost-effective way of generating renewable energy in buildings. Additionally, PV modules can be more than generation systems and be an essential part of the buildings, contributing to their appearance, thermal performance, and daylight harvesting. New policies and regulations around the world encourage the use of PV and bring more flexibility for their integration in buildings. Therefore, it is fundamental for regulators, researchers, and building professionals, to have a comprehensive PV in buildings categorization. As a response, the objective of this work was to develop a classification for building attached photovoltaics (BAPV) and building integrated photovoltaics (BIPV). The classifications resulted from an extensive literature review that helped to identify relevant aspects, criteria, and gaps in previous categorizations. It considers the application type, location, opacity, accessibility from the inside, and heat dissipation (a missing parameter in prior works). After summarizing the existing categories, describing the findings, and explaining the proposed classifications, the authors illustrated them using zero-energy houses.

Energy Conversion and Management

IOP Conference Series: Earth and Environmental Science

The ability of bifacial photovoltaic (PV) modules to generate additional energy from the rear sid... more The ability of bifacial photovoltaic (PV) modules to generate additional energy from the rear side makes the selection of a tilt angle more challenging than its counterpart monofacial PV. Multiple factors such as site conditions (albedo, average sun-hour ambient temperature, elevation from sea level, diffuse fraction, global horizontal irradiance, and latitude) and PV module specifications (such as bifaciality, power temperature coefficient, and efficiency) can influence the optimum tilt that ensures maximum annual yield of the bifacial PV modules. System Advisor Model (SAM) is used to generate a training dataset of optimal tilt that covers a global range of site conditions and module specifications. Furthermore, we used a Ranker-based feature selection approach to evaluate features and generate a rank-list based on their R-squared score to the dependent variable. From all the available features, the absolute latitude value, sun hour ambient temperature, global horizontal irradiance...