Feature Paper Collection: Energy and Buildings

Building energy consumption takes up over 30% of global final energy use and 26% of global energy-related emissions. In addition, building operations represent nearly 55% of global electricity consumption. The management of peak demand plays a crucial role in optimizing building electricity usage, consequently leading to a reduction in carbon footprint. Accurately forecasting peak demand in commercial buildings provides benefits to both the suppliers and consumers by enhancing efficiency in electricity production and minimizing energy waste. Precise predictions of energy peaks enable the implementation of proactive peak-shaving strategies, the effective scheduling of battery response, and an enhancement of smart grid management. The current research on peak demand for commercial buildings has shown a gap in addressing timestamps for peak consumption incidents. To bridge the gap, an Energy Peaks and Timestamping Prediction (EPTP) framework is proposed to not only identify the energy peaks, but to also accurately predict the timestamps associated with their occurrences. In this EPTP framework, energy consumption prediction is performed with a long short-term memory network followed by the timestamp prediction using a multilayer perceptron network. The proposed framework was validated through experiments utilizing real-world commercial supermarket data. This evaluation was performed in comparison to the commonly used block maxima approach for indexing. The 2-h hit rate saw an improvement from 21% when employing the block maxima approach to 52.6% with the proposed EPTP framework for the hourly resolution. Similarly, the hit rate increased from 65.3% to 86% for the 15-min resolution. In addition, the average minute deviation decreased from 120 min with the block maxima approach to 62 min with the proposed EPTP framework with high-resolution data. The framework demonstrates satisfactory results when applied to high-resolution data obtained from real-world commercial supermarket energy consumption. Full article

Different standard methods for the assessment of the thermal performance of the building envelope are used: analogy with coeval building, theoretical method, heat flow meter measurement, simple hot box, infrared thermography, and thermometric method. Review papers on these methods, applied in situ and in laboratory, have been published, focusing on theory, equipment, metrological performance, test conditions and data acquisition, data analysis, benefits, and limitations. However, steps forward have been done and not been deepened in previous works: in fact, the representative points method and the weighted area method have been proposed, too, whilst artificial intelligence and data-driven methods have begun to prove the reliability also in the U-value prevision using available datasets. Considering this context, this work aims at updating the literature background considering exclusively in situ methods. The work starts from bibliometric and scientometric analysis not previously conducted: this helped to group the methods and to sketch the innovations and the future perspectives. Indeed, from the bibliometric and scientometric literature analysis what emerged was (i) the richness of the background on this topic, especially in the recent years, (ii) two macro-groups (methods with and without measurements), and (iii) the importance of paper keywords (otherwise, interesting papers are eluded by the output of simple database queries). The method study that followed aims at providing (i) a broader view of the thermal transmittance (U-value) assessment procedures, including the utmost recent applications, proposal, and outlooks in this field, (ii) the understanding on the fundamental theories of the techniques, (iii) practical advice for building-envelope assessment, focusing on the advantages and limitations useful for professionals and researchers involved in the energy audit, conservation, or refurbishment of building stock, (iv) the identification of the interconnection between the techniques that often rely on one another, and (v) final remarks and future perspective of the procedures, which embrace the use of artificial intelligence (AI). From the topic analysis, as a result, it emerged that this is an open field for future research, especially with the implementation of AI, which requires good datasets and trials on the models’ architectures, in terms of input layer, number of hidden layer and neurons, and percentage of data to be employed for model training and testing. Full article