Calibration of building model based on indoor temperature for overheating assessment using genetic algorithm: Methodology, evaluation criteria, and case study
“…Table 10 shows that the weight gain model exhibits a higher prediction performance for this error rate. Both models satisfied the acceptable standards and yielded similar prediction performance to recent studies on calibrating the indoor temperature prediction performance of building energy system models ( Donovan et al, 2019 , Baba et al, 2022 ). Fig.…”
“…Table 10 shows that the weight gain model exhibits a higher prediction performance for this error rate. Both models satisfied the acceptable standards and yielded similar prediction performance to recent studies on calibrating the indoor temperature prediction performance of building energy system models ( Donovan et al, 2019 , Baba et al, 2022 ). Fig.…”
“…When calibrating models for assessing the thermal and energy performance of buildings, the most common parameters dealt with are those related to the outdoor climate [39,40], with the location of the building, including the degree of sunlight and potential shading [40], building characteristics such as thermal insulation and air tightness [39,41] and its ventilation, air conditioning and heating systems [40,42,43] as well as the conditions of use of the buildings and the equipment and systems installed in it [42,44]. By means of trial and error, the model was calibrated by modifying the air exchange through ventilation according to the measurements of its inlet velocity through the diffusers in the rooms of the two buildings.…”
Section: Model Calibrationmentioning
confidence: 99%
“…Consequently, some studies indicate that the combination of high levels of thermal insulation and airtightness in energy-efficient, passive, or nearzero-energy buildings may lead to an increased risk of overheating compared to older buildings [52,[62][63][64]. Other studies show that although there is no direct correlation between a building's level of energy efficiency and its susceptibility to overheating, the effectiveness of passive overheating control systems in more energy-efficient buildings is strongly linked to the behavior of the building occupants [2,40,65], which often differ significantly from those expected [66,67]. However, there is growing evidence that in temperate climates, where both average summer temperatures and the frequency and intensity of heat waves are increasing, designing new buildings and retrofitting existing ones to be more energy efficient during the heating season is not enough [67,68].…”
Section: Energy Policy For the Design Of Buildingmentioning
Studies of the effects of removing underfloor insulation and increasing the thermal capacity of building walls are currently found almost exclusively in existing vernacular architecture and rammed-earth buildings, mostly in countries with warm climates. This paper proposes the combined use of these two measures to reduce the risk of overheating in a detached single-family house in a temperate climate during the summer. Experimental studies conducted during the largest heat wave on record in the summer of 2019 showed that peak daytime temperatures decreased by 5.2 °C to 7.1 °C, and peak nighttime temperatures decreased by 4.7 °C to 6.8 °C. Simulation studies taking into account occupant heat showed that the proposed passive methods could, under the IPCC 8.5 scenario, eliminate the need for mechanical cooling in a detached single-family house in the temperate climate of Central and Eastern Europe by 2100. The actual heating energy consumption for the building with an uninsulated floor and increased wall heat capacity was 5.5 kWh/m2 higher than for the reference building, indicating that it can be a near-zero energy building. The proposed concept is in line with the new approach to the energy design of buildings, which should not be limited to reducing thermal energy demand, but should also respond to the needs arising from global warming.
“…The stochastic computing model's significant potential is to examine the idea of attempting to solve models by combining the artificial neural network's high generalization potential with the combined abilities of local and global search strategies. Multi-objective problems [ 15 ], hybrid cable networks [ 16 ], and building model calibration [ 17 ] are just a few examples of recent research that has extensively used soft computing approaches.…”
Numerical treatment of the COVID-19 transposition and severity in Romania and Pakistan has been presented in this study, i.e., ANN-GA-SQP through artificial neural network genetic algorithms (ANN-GA) and sequential quadratic programming (SQP), a design of an integrated computational intelligent paradigm, COVID-19 is widely considered to be the greatest health threat humanity has ever faced. In terms of both health and economics, COVID-19 is a huge disaster. Many academics have looked at the COVID-19 model in their research papers, although they use different traditional techniques to represent it. The use of hybrid suggested solutions to solve this issue in the present article is significant, demonstrating the study's novelty. The SIR model of COVID-19 consists of a susceptible, infectious, and recovered class of population. The activation function for the construction of functions based on fitness in mean squared error sense is developed using nonlinear equations of the COVID-19 SIR model for the best performance of ANN-GA-SQP with the combined potential of GA and SQP of a network. While detailed refining is done with efficient local search with SQP, GAs operates as a global search. In addition, a neuron analysis will be presented to verify the effectiveness and complexity of the proposed method. Adam’s numerical methodology is applied to compare the sustainability and efficacy of the presented paradigm. Analytical evaluations of mean, median, and semi-interquartile range values, as well as Theil’s inequality coefficients, root mean squared error, and mean of absolute deviation) values have been observed. The convergence and correctness of the ANN-GA-SQP approach are further validated by statistical analyses.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
