• Energy Research
• 2025-2025close
• IT close
• EU close
• Energy and Buildings close

Advanced energy benchmarking in residential buildings, using data-driven modeling, provides a fast, accurate, and systematic approach to assessing energy performance and comparing it with reference standards or targets. This process is essential for identifying opportunities to improve energy efficiency and for shaping effective energy retrofit strategies. However, building professionals often face barriers to adopting these tools, mainly due to the complexity and limited interpretability of data-driven models, which can negatively affect decision-making. In order to contribute in addressing these issues, this study combines data-driven modeling with Explainable Artificial Intelligence (XAI) techniques to advance energy benchmarking analysis in residential buildings and enhance their usability by also non-expert users. The proposed process focuses on estimating primary energy demand for space heating and domestic hot water in residential building units, extracting knowledge from about 49,000 Energy Performance Certificates (EPCs) issued in the Piedmont Region, Italy. The effectiveness of five machine learning algorithms is assessed to select the most suitable estimation model. Then to ensure the trustworthiness of the selected model, a XAI layer is implemented to identify and remove input variable domain regions that demonstrated to be critical for the robustness of the inference mechanism learnt in the training phase. Moreover, the study assesses the model capability to evaluate building energy performance, examining both the current state and potential scenarios for energy retrofitting. A second XAI layer is then introduced to provide local explanations for model estimations of both pre- and post-retrofit conditions of a building. The final aim is to enable an external benchmarking analysis, by extracting from the analysed EPCs reference groups of similar buildings, that facilitate a performance comparison for the investigated retrofit scenarios. This energy benchmarking process promotes transparent and informed decision-making, aiming to instill confidence in final users when leveraging data-driven models for energy planning in the building sector.

This paper addresses the critical need for more efficient and adaptive building control systems to maximise occupant comfort while reducing energy consumption. Our objective is to explore the practical application of model-free Deep Reinforcement Learning (DRL) in real-world building environments by developing a system that learns and adapts to changing conditions, beginning its operation by imitating an existing Rule-Based Control (RBC) system. This approach ensures initial reliability and performance while setting the stage for advanced learning capabilities. The methodology involves two distinct phases. Initially, the DRL controller mimics the behaviour of the RBC system, using imitation learning with behavioural cloning as a safe and efficient strategy to achieve baseline operational efficiency. Subsequently, the controller is implemented within a real building in an online learning setting. In this phase, the controller utilises real-time data to continuously refine its control policy, responding adaptively to occupant behaviours and external environmental conditions. To validate our approach, we conducted a comprehensive analysis, comparing the performance of our DRL controller against the baseline RBC controller, another RBC, and a PI (Proportional-Integral) controller implemented in a digital twin model of the real office environment. Energy consumption and temperature violations related to a temperature acceptability range are considered as metrics, providing a robust framework for assessing the effectiveness of our system. The results indicate that our DRL controller, supported by imitation learning, outperforms the two RBCs by reducing energy consumption by 40 % while reducing the cumulative sum of temperature violations by 43 % and 13 % with respect to the two RBCs. Although the PI controller ensures better performance in terms of temperature violations compared to DRL, it requires 45 % more energy than the proposed DRL controller due to its inherent inability to deal with multi-objective control problems. In conclusion, this paper demonstrates the feasibility and advantages of implementing advanced DRL techniques in real-world building control scenarios. Integrating imitation learning with a DRL controller offers a novel and effective way to enhance the scalability of DRL systems, expanding their application in buildings and driving significant improvements in energy efficiency. Energy and Buildings, 335 ISSN:0378-7788 ISSN:1872-6178

The construction sector and the existing building stock are responsible for high environmental impacts. Effective measures for urban sustainable regeneration and reducing the impact of urban areas must address the use of circular solutions to increase the rate of materials reused and reusable and minimise raw materials usage and waste production. Also, nearly zero energy buildings (NZEBs) using only renewable energy sources (RES) without fossil fuels are essential to achieve the decarbonisation target proposed by the European Union by 2050. The comparison of three intervention scenarios, reconstruction (R), deep renovation (DR) and conservation (C), in three different periods (10, 30, and 60 years) using the Life Cycle Assessment method allows for the estimation of their environmental impact in terms of Global Warming Potential and Primary Energy. The experimental application to an existing urban block in the first urban periphery of Bologna (Italy) provides interesting results. In this case, DR is not the most cost-effective in the long term, but the R is the most successful. Further simulations on other existing urban blocks are necessary to extend the results and obtain valuable data to integrate into georeferenced maps used as decision-support tools by local actors to boost the climate neutrality transition.

The characteristics of building envelopes impose significant impacts on indoor thermal comfort, especially for buildings that possess higher portions of glazing. As a result, the overall Indoor Environmental Quality (IEQ) is also largely controlled by the glazing scenario. Recent studies present three strategies to mitigate this aspect, by either i) improving the U-value with additional glass layers (insulation-based), ii) utilizing shading devices, or iii) changing the transparency or reflectance of glass (radiation control). In this study, Water-filled Glass (WFG) is presented as a potential fourth strategy. WFG is an innovative technology that utilizes a water layer within an insulated glass unit, to help improve the energy performance of the glazing. Current research primarily focuses on the energy consumption of WFG technology, and its potential to reduce both operational and embodied carbon. However, the potential impact on the thermal comfort of buildings, due to the thermal mass, absorption and radiant heating–cooling properties of its water layer have not yet been analysed in detail. To build on this, this paper provides comparisons of various standard and advanced glazing technologies clustered in the above strategies, to assess the impact of glazing choice on indoor thermal comfort. This is conducted for both an office and a sunroom scenario using the Analytical Comfort Zone PMV (SolarCal) Method. Seven conventional glass technologies across nine locations were measured, to represent all major inhabited climate regions (Köppen-Geiger A-D). Results show that WFG-like technologies can provide the highest amount of thermal comfort in up to eight out of nine climates; depending on the structure and in free-floating conditions, up to 26 % thermally comfortable periods can be achieved over an entire year. When this is compared to the base case, an additional 19 % comfortable periods are created. For hotter and more tropical climates (Af, BSk, Bwh), solar-gain focused techniques often function best, such as electrochromic and double glazing with permanent shading. This study also highlights the importance of thermal mass in glass structures, as well as the advantage of dynamic fluid mass over a static one. The results show that by utilizing WFG, up to 64–145 kWh of energy can also potentially be absorbed annually. In addition to this, this glazing technology offers warmer discomfort periods for many climates during colder seasons. Whilst this initially may seem undesirable, it offers an opportunity for the adoption of passive strategies, as well as heat redistribution to neighbouring thermal spaces, to potentially reduce overall energy usage at the building level.

Building energy consumption constitutes a significant share of global energy demand. This study examines how a prefabricated building, often subject to challenges in maintaining comfort, can meet the nearly zero-energy building (nZEB) standards in Italy. This study fills the gap in the literature on prefabricated buildings that meet nZEB standards, proposing an innovative approach that integrates vacuum insulated panels (VIP) and photovoltaic systems with storage to optimize energy efficiency and thermal comfort. The paper examines an existing prefabricated building and assesses the most effective solutions to implement, along with their respective impacts on comfort and energy consumption. The model of the building is developed in EnergyPlus and verified with experimental data. The results indicate significant energy savings, demonstrating the feasibility of prefabricated buildings in achieving nZEB goals. In particular, if the building is equipped with solar shading, controlled mechanical ventilation, free cooling, and vacuum insulated panels, the thermal savings is 60 %. If the maximum photovoltaic power possible is installed on the roof the energy demand coverage is 63 %, which increases to 95 % with a storage system with a nominal capacity of 10 kWh. This paper aims to provide insights for designers, researchers and policymakers by exposing the potential for prefabricated solutions to meet stringent energy standards and promote sustainability in the construction industry.