Coupling an artificial neuron network daylighting model and building energy simulation for vacuum photovoltaic glazing

Qiu, Changyu; Yi, Yun Kyu; Wang, Meng; Yang, Hongxing

doi:10.1016/j.apenergy.2020.114624

Cited by 24 publications

(3 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, typical BIPV windows are not suitable for the cold region due to the inferior thermal insulation [5]. To improve the thermal performance of the BIPV glazing, a novel CdTebased vacuum PV glazing (VPV) is developed with a highly integrate three-layer structure [6]. The previous studies [7,8] indicated that the vacuum PV glazing not only has an excellent thermal performance but also can provide better visual comfort than common windows.…”

Section: Introductionmentioning

confidence: 99%

Numerical evaluation and sensitivity analysis on dynamic heat transfer of a novel CdTe-base vacuum PV glazing

Changyu¹,

Qiu²,

Yang³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Building-integrated photovoltaic (BIPV) technology plays an important role on the path to carbon neutral society. The CdTe-based vacuum PV glazing is proposed to improve the thermal performance of the PV glazing. Therefore, the goals of renewable energy production and energy-efficient building can be achieved at the same time. To fully understand the dynamic heat transfer process and thermal behaviour, this study conducted a comprehensive numerical evaluation based on a mathematic heat transfer model for the CdTe-based vacuum PV glazing. It was found the average dynamic solar heat gain coefficient (SHGC) of the CdTe-based vacuum PV glazing is 0.147 and will increase with the increment of incident solar radiation. The dynamic overall heat transfer coefficient (U-value) varies from 0.451 to 0.467 W/m 2 K under summer conditions which are higher than which under winter conditions. The solar radiation dominates the total heat transfer compared with the temperature difference in the daytime. The solar radiation and ambient temperature have a negative effect on the PV efficiency and a distinctly positive effect on the outside surface temperature. However, the inside surface temperature is much more stable. A sensitivity analysis was also conducted to investigate the thermal response of the vacuum PV glazing with different design parameters and various environmental conditions. The emissivity of low-e coating is the most effective design parameter. The results indicate that the vacuum PV glazing can perform an excellent thermal insulation performance and contribute to the optimization of the design parameters in future studies.

show abstract

Section: Introductionmentioning

confidence: 99%

Numerical evaluation and sensitivity analysis on dynamic heat transfer of a novel CdTe-base vacuum PV glazing

Changyu¹,

Qiu²,

Yang³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…This has enabled complex thermo-energetic simulations to be carried out more efficiently allowing, as a result, the development of simplified tools based on these simulations [10][11][12][13][14]. In general, tools based on pre-simulated cases are divided into applications with graphic interfaces [10,11] and metamodels based on statistical [13][14][15][16] or computational techniques, such as the artificial intelligence [17][18][19].…”

Section: Introductionmentioning

confidence: 99%

Metamodeling of the Energy Consumption of Buildings with Daylight Harvesting – Application of Artificial Neural Networks Sensitive to Orientation

Fonseca

Sc²,

Pereira

2021

Journal of Daylighting

View full text Add to dashboard Cite

Daylight harvesting is a well-known strategy to address building energy efficiency. However, few simplified tools can evaluate its dual impact on lighting and air conditioning energy consumption. Artificial neural networks (ANNs) have been used as metamodels to predict energy consumption with high precision, few input parameters and instant response. However, this approach still lacks the potential to estimate consumption when there is daylight harvesting, at the ambient level, where the effect of orientation can be noted. This study investigates this potential, in order to evaluate the applicability of ANNs as a tool to aid the architectonic design. The ANNs were approached as metamodels trained based on EnergyPlus thermo-energetic simulations. The network configuration focused on determining its simplest feasible form. The input parameters adopted as the main variables of the building envelope were as follows: orientation, window-to-wall ratio and visible transmission. The effects of the encoding of orientation as a network input parameter, the number of examples of each variable for network training and changing the parameters used for the training were evaluated. The networks predicted the individualized consumption according to the end use with errors below 5%, indicating their potential to be applied as a simplified tool to support the design process, considering the elementary variables of the building envelope. The discussion of results focused on guidelines and challenges to achieve this purpose when contemplating the broadening of the metamodel scope.

show abstract

“…Solar radiation plays an essential role in building environments and energy use. In recent years, numerous studies have been conducted on the use of solar radiation in buildings for electricity generation [1][2][3][4][5], hot water supply [6][7][8],…”

mentioning

confidence: 99%

Modeling solar radiation on a human body indoors by a novel mathematical model

Arens

et al. 2021

Building and Environment

View full text Add to dashboard Cite

Solar radiation affects occupant comfort and building energy consumption in ways that have received relatively little attention in environmental design and energy simulation. Direct, diffuse, and reflected irradiation on the body have warming effects that can be equated to increases in the mean radiant temperature (MRT) of the occupant's surroundings. A simplified occupant-centered model (SolarCal Model, i.e., SC Model) has recently been adopted in ASHRAE Standard 55, followed by a comprehensive simulation procedure combining detailed room-and manikin geometries using the Daylight Coefficient Model (DC Model). This paper presents an intermediate-level mathematical model (the HNU Solar Model) capable of rapid annual calculations of the MRT increases. Both the room and occupant geometries are simplified but consistent with those of the SC Model. Novel strategies of the calculation include a sky-annulus fraction, virtual body shadow, and equivalent window. Modeled results are compared with those simulated by the DC Model using Radiance software, which is assumed to be accurate. The differences in the Delta MRT by diffuse, direct, and reflected solar radiation are usually less than 1, 2, and 0.5°C between the DC and HNU Solar Models, respectively. For a given occupant position indoors, the HNU Solar Model only needs five seconds to obtain the annual Delta MRT, while the DC Model needs about seven minutes. The HNU Solar Model provides a simple and practical way to evaluate indoor environments at the room scale, to design fenestration, and to predict set-point changes in annual energy simulation of HVAC systems.

show abstract

Coupling an artificial neuron network daylighting model and building energy simulation for vacuum photovoltaic glazing

Cited by 24 publications

References 36 publications

Numerical evaluation and sensitivity analysis on dynamic heat transfer of a novel CdTe-base vacuum PV glazing

Numerical evaluation and sensitivity analysis on dynamic heat transfer of a novel CdTe-base vacuum PV glazing

Metamodeling of the Energy Consumption of Buildings with Daylight Harvesting – Application of Artificial Neural Networks Sensitive to Orientation

Modeling solar radiation on a human body indoors by a novel mathematical model

Contact Info

Product

Resources

About