Data-driven Approach to Estimate Urban Heat Island Impacts on Building Energy Consumption

Energy, Год журнала: 2025, Номер 316, С. 134508 - 134508

Опубликована: Янв. 11, 2025

Язык: Английский

---

Ranking building design and operation parameters for residential heating demand forecasting with machine learning

Journal of Building Engineering, Год журнала: 2024, Номер 86, С. 108817 - 108817

Опубликована: Фев. 19, 2024

The European Union's Energy Performance in Buildings Directive has made significant strides enhancing building energy efficiency since its inception 2002. However, approximately 75% of EU buildings still fall short energy-efficient standards. Furthermore, there is a growing momentum to extend the concept nearly zero-energy entire districts, thereby fostering Net-Zero Districts. This underscores necessity for large-scale urban modelling identify and improve underperforming transition planning. Given increasing interest black box models performance, this study aims common input variables demand literature, analyse their influence, develop heating prediction model using different algorithms: Random Forest, XGBoost, Extra Trees. Four large datasets generated from white-box simulation three Spanish cities were used training testing models. features consistently stand out as most important prediction: shape factor, infiltration rate, south equivalent surface, internal gains, regardless algorithm or climatic zone. multi-location XGBoost with an optimizer emerged best-performing model, average Mean Absolute Percentage Error value hovering around 40%. Analysis employing SHapley Additive exPlanation (SHAP) values showcases model's ability factors that drive higher demand, alongside strong predictive performance. suggests potential integration into programmes key be addressed during renovation. Additionally, results show XGBoost-based software's identifying renovation targets.

Язык: Английский

---

Optimization of Ex/Energy Efficiencies in an Integrated Compressed Air Energy Storage System (CAES) using Machine Learning Algorithms: A Multi-Objective Approach based on Analysis of Variance

Energy, Год журнала: 2025, Номер unknown, С. 135675 - 135675

Опубликована: Март 1, 2025

Язык: Английский

---

Fuzzy logic-supported building design for low-energy consumption in urban environments

Case Studies in Thermal Engineering, Год журнала: 2024, Номер unknown, С. 105384 - 105384

Опубликована: Окт. 1, 2024

Язык: Английский

---

Systematic review of the efficacy of data-driven urban building energy models during extreme heat in cities: Current trends and future outlook

Building Simulation, Год журнала: 2024, Номер 17(5), С. 695 - 722

Опубликована: Март 11, 2024

Язык: Английский

---

Integration of LSTM networks with gradient boosting machines (GBM) for assessing heating and cooling load requirements in building energy efficiency

Energy Exploration & Exploitation, Год журнала: 2024, Номер 42(6), С. 2191 - 2217

Опубликована: Авг. 2, 2024

Due to rising demand for energy-efficient buildings, advanced predictive models are needed evaluate heating and cooling load requirements. This research presents a unified strategy that blends LSTM networks GBM improve building energy estimates’ precision reliability. Data on usage, weather conditions, occupancy trends, features is collected prepared start the process. model attributes created using sequential relationships initial projections networks. Combining with takes advantage of each model's strengths: LSTM's data processing GBM's complex nonlinear connection capture. Performance measures like RMSE MAE used hybrid validity. Compared individual models, integrated LSTM-GBM method improves prediction accuracy. higher capacity allows real-time management systems, improving operations reducing use. Implementing this in Building Management Systems (BMS) shows its practicality achieving sustainable efficiency.

Язык: Английский

---

Urban Building Energy Modeling to Support Climate-Sensitive Planning in the Suburban Areas of Santiago de Chile

Buildings, Год журнала: 2024, Номер 14(1), С. 185 - 185

Опубликована: Янв. 11, 2024

Greenhouse gas emissions depend on natural and anthropic phenomena; however, to reduce emissions, we can only intervene in terms of causes. Human activity is very different various countries cities. This mainly due differences the type urban environment, climatic conditions, socioeconomic context, government stability, other aspects. Urban building energy modeling (UBEM), with a GIS-based approach, allows evaluation all specific characteristics buildings, population, context that describe use its spatial distribution within city. In this paper, UBEM developed using consumption eight typical buildings (archetypes) climate zone Santiago de Chile. The archetype-based then applied commune Renca, critical suburb Santiago, QGIS analyze demand for space heating potential saving after four retrofitting interventions. Knowing costs interventions price, simple payback time was evaluated reduction GHG emissions. Starting from actual stock, results show most effective intervention Renca thermal insulation walls roofs; dwellings, particular could be more convenient if associated installation solar technologies. methodology replicated data used by planners public administrations available many Chilean cities countries.

Язык: Английский

---

Advancing Urban Building Energy Modeling: Building Energy Simulations for Three Commercial Building Stocks through Archetype Development

Buildings, Год журнала: 2024, Номер 14(5), С. 1241 - 1241

Опубликована: Апрель 27, 2024

Urban building energy models (UBEMs), developed to understand the performance of stocks a region, can aid in key decisions related policy and climate change solutions. However, creating city-scale UBEM is challenging due requirements diverse geometric non-geometric datasets. Thus, we aimed further elucidate process with disparate scarce data based on bottom-up, physics-based approach. We focused three typically overlooked but functionally important commercial stocks, which are sales shopping, healthcare facilities, food services, region Pittsburgh, Pennsylvania. harvested relevant local information employed photogrammetry image processing. created archetypes for types, designed 3D buildings SketchUp, performed an analysis using EnergyPlus. The average annual simulated use intensities (EUIs) were 528 kWh/m2, 822 2894 kWh/m2 respectively. In addition variations found pattern among considerable observed within same stock. About 9% 11% errors shopping facilities when validating results actual data. suggested conservation measures could reduce EUI by 10–26% depending type. assist finding energy-efficient retrofit solutions respect carbon reduction goal at city scale. limitations highlighted may be considered higher accuracy, has high potential integrate urban models, circular economy, life cycle assessment sustainable planning.

Язык: Английский

---

Multi-aspect analysis of measures to reduce the building's energy demand.

Journal of Building Engineering, Год журнала: 2024, Номер 91, С. 109758 - 109758

Опубликована: Май 25, 2024

Issues related to reducing the energy demand of residential buildings are still relevant in light transition and ongoing climate change. A single-family house from early 1990s with a heated area approximately 177 m2, located north-eastern part Poland, was used as case study. The article contains results nine years measurements that included consumption for heating domestic hot water preparation. It estimated annual final 128.2 kWh/m2 [462 MJ/m2]. After insulating building envelope replacing windows triple-glazed ones, this value reduced 68.2 [246 measurement were build statistical model, based on multiple regression, calculate similar one analysed any given location. presents second, more advanced, simulations model made DesignBuilder environment, which enabled additional analysis operation ventilation system. scope study also multi-variant economic renovation, Life Cycle Cost (LCC), Net Present Value (NPV) Internal Rate Return (IRR) values determined.

Язык: Английский

---

Urban residential building stock synthetic datasets for building energy performance analysis

Data in Brief, Год журнала: 2024, Номер 53, С. 110241 - 110241

Опубликована: Фев. 28, 2024

The urban building stock dataset consists of synthetic input and output data for the energy simulation one million buildings. four different residential types, namely: terraced, detached, semi-detached, bungalow. Constructing this buildings requires conversion, categorization, extraction, analytical processes. (in .csv) format comprises 19 parameters, including advanced features such as HVAC system fabric (walls, roofs, floors, door, windows) U-values, renewable parameters. primary parameter in is Energy Use Intensity (EUI kWh/(m2*year)), along with Performance Certificate (EPC) labels categorized on an A to G rating scale. Additionally, contains end-use demand parameters heating lighting, which are crucial jEPlus, a parametric tool, coupled EnergyPlus DesignBuilder templates facilitate physics-based simulations generating dataset. can be valuable resource researchers, practitioners, policymakers seeking enhance sustainability efficiency environments. Furthermore, holds immense potential future research field analysis modeling.

Язык: Английский

---