Building energy systems (BESs) are essential for modern infrastructure but face significant challenges in equipment diagnosis, energy consumption prediction, and operational control. The complexity of BESs, coupled with the increasing integration of renewable energy sources, presents difficulties in fault detection, accurate energy forecasting, and dynamic system optimisation. Traditional control strategies struggle with low efficiency, slow response times, and limited adaptability, making it difficult to ensure reliable operation and optimal energy management. To address these issues, researchers have increasingly turned to machine learning (ML) techniques, which offer promising solutions for improving fault diagnosis, energy scheduling, and real-time control in BESs. This review provides a comprehensive analysis of ML techniques applied to fault diagnosis, energy consumption prediction, energy scheduling, and operational control. According to the results of analysis and literature review, supervised learning methods, such as support vector machines and random forest, demonstrate high classification accuracy for fault detection but require extensive labelled datasets. Unsupervised learning approaches, including principal component analysis and clustering algorithms, offer robust fault identification capabilities without labelled data but may struggle with complex nonlinear patterns. Deep learning techniques, particularly convolutional neural networks and long short-term memory models, exhibit superior accuracy in energy consumption forecasting and real-time system optimisation. Reinforcement learning further enhances energy management by dynamically adjusting system parameters to maximise efficiency and cost savings. Despite these advancements, challenges remain in terms of data availability, computational costs, and model interpretability. Future research should focus on improving hybrid ML models, integrating explainable AI techniques, and enhancing real-time adaptability to evolving energy demands. This review also highlights the transformative potential of ML in BESs and outlines future directions for sustainable and intelligent building energy management.

Building sustainable green cities for the future can be difficult or highly challenging as such cities need to reduce their environmental footprint through eco-friendly materials, resource and energy conservation, as well as renewable energy generation. A recent paper by the first author has proposed sustainable concrete with 80% ground granulated blast furnace slag (GGBFS) to build Masdar City in the UAE with a $153\mathrm{kg}/{\mathrm{m}}^3$ carbon footprint. This paper proposes three new types of sustainable concretes in an attempt to further reduce the carbon footprint. In Type I, a total of 4 concrete mixes were made with a high volume GGBFS with 60, 70, 80, and 90% replacement of ordinary portland cement (OPC), 100% recycled water (RW), and 100% recycled aggregate (RA). The same replacement ratios were used in Type II but with only 100% RA. In Type III, a total of four concrete mixes made with a high volume fly ash (FA) cement with 40, 50, 60, and 70% replacement of OPC. The paper provides information on the mix design, full justification of ${\mathrm{CO}}_2$ footprint, and the cost for each concrete mix. The hardened and plastic properties and durability test parameters for each mix are presented. The results showed that the fly ash and slag significantly reduced the carbon footprint and meet the requirements of future sustainable cities. An economical mix with 90% GGBFS and 10% OPC was nominated for use in the future construction of sustainable cities with 125 $\mathrm{kg}/{\mathrm{m}}^3$ emissions.

Concrete is a heterogeneous material that consists of cement, aggregates, and water as basic constituents. Several cementitious materials and additives are added with different volumetric ratios to improve the strength and durability requirements of concrete. Consequently, performance of concrete when exposed to elevated temperature is greatly affected by the concrete type. Moreover, post-fire properties of concrete are influenced by the constituents of each concrete type. Heating rate, days of curing, type of curing, cooling method, and constituents of the mix are some of the factors that impact the post-fire behavior of concrete structures. In this paper, an extensive review was conducted and focused on the effect of concrete constituents on the overall behavior of concrete when exposed to elevated temperature. It was evident that utilizing fibers can improve the tensile capacity of concrete after exposure to higher temperatures. However, there is an increased risk of spalling due to the induced internal stresses. In addition, supplementary cementitious materials such as metakaolin and silica fume enhanced concrete strength, the latter proving to be the most effective. In terms of the heating process, it was clear that several constituents, such as silica fume or fly ash, that decrease absorption affect overall workability, increase the compressive strength of concrete, and can yield an increase in the strength of concrete at 200 °C. Most of the concrete types show a moderate and steady decrease in the strength up until 400 °C. However, the decrease is more rapid until the concrete reaches 800 °C or 1000 °C at which it spalls or cannot take any applied load. This review highlighted the need for more research and codes’ provisions to account for different types of concrete constituents and advanced construction materials technology.