Search

Rising energy consumption in buildings has prompted architectural engineers and policymakers to ask "what-if" questions in the pursuit of energy efficiency. Current simulation and machine learning methods rely primarily on correlations and associations necessitating causal inference techniques. In this research, a causal inferential approach combining double machine learning and domain knowledge using directed acyclic graphs is employed. The utility of this approach is demonstrated on the 2015 United States Residential energy consumption survey to evaluate the impact of energy policies and occupant behavior on cooling energy consumption. The results show that energy policies such as energy audits, proper insulation, access to interval data and Energy Star qualified windows significantly reduce energy use intensity (EUI). Additionally, air conditioning usage by occupants causally affects EUI. For instance, proper insulation reduces EUI by 5.603 kWh/m2 while changing static thermostat settings to automatic adjustments at certain times reduces EUI by 3.542 kWh/m2. This study suggests potential energy-saving policies for balanced building energy efficiency and functionality. [Display omitted] • An ML-based causal inference analysis is proposed to explain cooling energy use. • The effects of energy policy and occupant behavior on energy use are quantified. • Significant policy improvements to enhance cooling energy use are proposed. • Occupant behaviors beneficial to cooling energy use are highlighted. [ABSTRACT FROM AUTHOR]

The effects of heat waves (HW) are more pronounced in urban areas than in rural areas due to the additive effect of the urban heat island (UHI) phenomenon. However, the synergies between UHI and HW are still an open scientific question and have only been quantified for a few metropolitan cities. In the current study, we explore the synergies between UHI and HW in Seoul city. We consider summertime data from two non-consecutive years (i.e., 2012 and 2016) and ten automatic weather stations. Our results show that UHI is more intense during HW periods than non-heat wave (NHW) periods (i.e., normal summer background conditions), with a maximum UHI difference of 3.30°C and 4.50°C, between HW and NHW periods, in 2012 and 2016 respectively. Our results also show substantial variations in the synergies between UHI and HW due to land use characteristics and synoptic weather conditions; the synergies were relatively more intense in densely built areas and under low wind speed conditions. Our results contribute to our understanding of thermal risks posed by HW in urban areas and, subsequently, the health risks on urban populations. Moreover, they are of significant importance to emergency relief providers as a resource allocation guideline, for instance, regarding which areas and time of the day to prioritize during HW periods in Seoul. [ABSTRACT FROM AUTHOR]

The urban heat island (UHI) phenomenon is a serious concern for urban planners and policymakers, requiring effective and efficient mitigation policies. To develop such policies, accurate and pre-emptive estimations of current and future UHI manifestations are vital elements that help determine efficient policies and mitigation techniques. There are two fundamental approaches for modelling overheating in an urban environment: white-box and black-box based methods. The first one is characterized by the easily interpretable working process, while the unclear working procedure defines the second one. The present study comprehensively reviews the commonly used white-box and black-box based approaches applied for UHI predictions, analyses the existing literature adopting these tools for UHI prediction, and discusses the effectiveness of fusing both methods at the design and operation stages of the urban area for effective prediction and mitigation of UHI effect. The literature analysis showed that the transparent working process and high prediction accuracy of the physical-based white-box models make them a popular and reliable tool for UHI evaluation. Nevertheless, some white-box based simulation tools are too complex and require a high level of expertise to operate, leading to potential inaccuracies in the obtained outcomes. Black-box models, in turn, despite their opaque working process, are more straightforward in use and require less computation time. The fusion of these two methods is a novel approach that may benefit both UHI prediction and mitigation at the design and operation stages, respectively. • Current use of white-box and black-box modelling of UHI is discussed. • Future research directions and areas of effective discourse are identified. • Fusion of white-box and black-box approaches for city design stages are discussed. • Coupling White-box modelling and machine-learning for city operations are proposed. [ABSTRACT FROM AUTHOR]

• Interactions between UHI and air pollutant concentrations are explored. • UHI is positively correlated with common primary air pollutants. • UHI is negatively correlated with ground-level O 3 concentrations. • Seasonal effects are stronger in autumn and winter season than in spring. • The relationship between UHI and air pollutant concentrations is weakest in summer. Urban environments face two challenging problems that are parallel in nature but yet with compelling potential synergistic interactions; urban heat island (UHI) and air pollution. We explore these interactions using in-situ temperature and air pollution data collected from 13 monitoring stations for nine years. Through regression analysis and analysis of variance (ANOVA) tests, we found that carbon monoxide (CO), nitrogen dioxide (NO 2), sulfur dioxide (SO 2), and particulate matter (PM) show positive correlations with UHI intensity (UHII). At the same time, Ozone (O 3) was negatively correlated with UHII. Moreover, there was a substantial seasonal effect on the strength of the correlations between UHI and air pollution, with some air pollutants showing strong associations with UHI during certain seasons (i.e., winter and autumn). The strongest interactions were observed for NO 2 (R² = 0.176) and PM10 (R² = 0.596) during the wintertime and for SO 2 (R² = 0.849), CO (R² = 0.346), PM2.5 (R² = 0.695) and O 3 (R² = 0.512) during autumn. Understanding such interactions is essential for urban climate studies and our study provides a basis for scientific discussions on integrative mitigation strategies for both UHI and air pollution in Seoul city. [ABSTRACT FROM AUTHOR]

The urban heat island is a vastly documented climatological phenomenon, but when it comes to coastal cities, close to desert areas, its analysis becomes extremely challenging, given the high temporal variability and spatial heterogeneity. The strong dependency on the synoptic weather conditions, rather than on city-specific, constant features, hinders the identification of recurrent patterns, leading conventional predicting algorithms to fail. In this paper, an advanced artificial intelligence technique based on long short-term memory (LSTM) model is applied to gain insight and predict the highly fluctuating heat island intensity (UHII) in the city of Sydney, Australia, governed by the dualistic system of cool sea breeze from the ocean and hot western winds from the vast desert biome inlands. Hourly measurements of temperature, collected for a period of 18 years (1999–2017) from 8 different sites in a 50 km radius from the coastline, were used to train (80%) and test (20%) the model. Other inputs included date, time, and previously computed UHII, feedbacked to the model with an optimized time step of six hours. A second set of models integrated wind speed at the reference station to account for the sea breeze effect. The R2 ranged between 0.770 and 0.932 for the training dataset and between 0.841 and 0.924 for the testing dataset, with the best performance attained right in correspondence of the city hot spots. Unexpectedly, very little benefit (0.06–0.43%) was achieved by including the sea breeze among the input variables. Overall, this study is insightful of a rather rare climatological case at the watershed between maritime and desertic typicality. We proved that accurate UHII predictions can be achieved by learning from long-term air temperature records, provided that an appropriate predicting architecture is utilized. Unlabelled Image • Predicting the urban heat island in coastal cities close to deserts is challenging. • The city of Sydney is selected as representative and uniquely complex case study. • A long short-term memory forecast model is developed based on 18-year data. • R2 between 0.841 and 0.924 is achieved, with the best performance at the city hot spots. • Negligible benefit is attained by including sea breeze among the inputs. [ABSTRACT FROM AUTHOR]

Buildings consume about 40 % of globally-produced energy. A notable amount of this energy is used to provide sufficient comfort levels to the building occupants. Moreover, given recent increases in global temperatures as a result of climate change and the associated decrease in comfort levels, providing adequate comfort levels in indoor spaces has become increasingly important. However, striking a balance between reducing building energy use and providing adequate comfort levels is a significant challenge. Conventional control methods for indoor spaces, such as on/off, proportional-integral (PI), and proportional-integral-derivative (PID) controllers, display significant instabilities and frequently overshoot thermostats, resulting in unnecessary energy use. Additionally, conventional building control methods rarely include comfort regulatory schemes. Consequently, recent research efforts have focused on the use of advanced artificial intelligence (AI) methods to optimize building energy usage while maintaining occupant thermal comfort. We present a review of the current AI-based methodologies being used to enhance thermal comfort in indoor spaces. we focus on thermal comfort predictive models using diverse machine learning (ML) algorithms and their deployment in building control systems for energy saving purposes. We then discuss gaps in the existing literature and highlight potential future research directions. [ABSTRACT FROM AUTHOR]

Clothing insulation is a key variable in the prediction of occupant thermal comfort. Consequently, the aim of the current study was to develop predictive models that forecast clothing insulation levels of building occupants. Using field measurements, we investigated the influence of outdoor environment factors and mode of transport on clothing insulation levels of university students. Our results showed that both the mode of transport and weather variables influenced the clothing insulation levels of the students. We then developed a deep neural network model that forecasts mean daily clothing insulation levels using outdoor air temperature at 6 am, dew point temperature at 6 am, gender, season and mode of transport in the based on the collected data from 1316 questionnaire surveys. In addition, we revealed that outdoor environment factors had stronger associations with clothing insulation levels than indoor environment elements. The developed deep neural network model indicated a high R² value of 0.90. In comparison to the deep neural network model, a developed linear model using the same data indicated a lower R² value of 0.698, which implies that the proposed deep neural network model provides an efficient method to forecast clothing insulation levels. [ABSTRACT FROM AUTHOR]

Summary: The use of photovoltaic (PV) systems has drawn attention as a solution to reduce the dependence on fossil fuel for building energy needs. Moreover, incorporating energy storage systems (ESSs) in PV systems can optimise electric energy costs by increasing dependency on PV‐generated energy during electric peak load times. However, current ESSs have limited capacities making it difficult to fully maximise PV‐generated energy. We propose a novel integrated energy‐efficient system for PV, ESS and electric heat pump (EHP) that maximises the usage of PV energy, optimises ESS usage and reduces EHP energy consumption costs. The components of the proposed integrated system are linked with a deep learning (DL)‐based algorithm that forecasts PV energy generation and energy demand of the EHP. The proposed system schedules the charging/discharging time of ESSs depending on peak load times, the forecasted EHP electric demand, and PV‐generated energy. The data used were collected for 10 months from a retail shop equipped with an EHP and ESS. We found that the developed DL‐based forecasting models for PV and EHP are accurate and reliable (ie, R2 above 0.95). Also, the results show that the proposed integrated energy‐efficient PV‐ESS‐EHP system saves 12% of the total annual electric costs, which corresponds to 1 285 291 Won. The proposed system ensures an efficient method to maximise PV‐generated energy resulting in reduced dependency on fossil fuels for building energy needs. [ABSTRACT FROM AUTHOR]