Consumption of water varies throughout the day due to the daily routines of the consumer. This pattern of daily water consumption is called the water demand profile. The initiatives to create these profiles are to improve hydraulic performance and to build energy conservation strategies for designed networks in Dubai. Therefore, the aim of the work presented here was to develop and analyze a domestic consumption profile for selected developments with socio-demographic factors including weekday/weekend variation, population, income, fasting during the month of Ramadan, and the outbreak of COVID-19. Data from more than 7000 smart meters were collected while water meters of more than 350 residential flats were examined manually. Water demand profiles generated from the data showed weekdays have more predictable peaks (morning 6–8 am and evening 5–7 pm) than weekends. During Ramadan, peak hours shifted to 7–10 am followed by 3–4 pm during workdays while peaks for low-income areas were higher due to a stricter working routine. The COVID-19 crisis has led to significant rise in observed consumption, with over a 30% increase during the month of Ramadan. The observed results, if compared with further end-use studies on more factors affecting demand profiles, can help in generating both cost and energy efficient networks.

The activated sludge process (ASP) is the most widely used biological wastewater treatment system. Advances in research have led to the adoption of Artificial Intelligence (AI), in particular, Nature-Inspired Algorithm (NIA) techniques such as Genetic Algorithms (GAs) and Particle Swarm Optimization (PSO) to optimize treatment systems. This has aided in reducing the complexity and computational time of ASP modelling. This paper covers the latest NIAs used in ASP and discusses the advantages and limitations of each algorithm compared to more traditional algorithms that have been utilized over the last few decades. Algorithms were assessed based on whether they looked at real/ideal treatment plant (WWTP) data (and efficiency) and whether they outperformed the traditional algorithms in optimizing the ASP. While conventional algorithms such as Genetic Algorithms (GAs), Particle Swarm Optimization (PSO), and Ant Colony Optimization (ACO) were found to be successfully employed in optimization techniques, newer algorithms such as Whale Optimization Algorithm (WOA), Bat Algorithm (BA), and Intensive Weed Optimization Algorithm (IWO) achieved similar results in the optimization of the ASP, while also having certain unique advantages.

The development of technology has made it easier for engineers to design and test models that allow simulation of real-time water distribution networks with greater accuracy. However, with so many nodes and links in a network, building a model still requires some simplification. One such simplification is the ‘conservative approach’, which applies the principle of ‘lumped demand’, taking the demand only from nodes at the ends of pipes. Herein, the full effect of lumped demand on key water parameters is analysed, on a large-scale network based on as-built networks of Al Furjan and Dubai Silicon Oasis, Dubai, UAE for different conditions. Epanet and WDNetXL software are used for the analysis, and results show the impact of different levels of skeletonisation on the head and velocity values for the two models. The analysis indicates that the head changes are high for a branched network under the extreme condition of firefighting. It includes the effect of skeletonising local tanks, with changes being higher when all tanks are empty. These findings provide a critical evaluation of the performance of this method for the Middle East region and it is concluded that the considerable velocity changes observed in the models could lead to overdesign.

The activated sludge process is pivotal in wastewater treatment, with ongoing research into its process control methods. Modeling treatment plants aids in analyzing relationships among variables, supporting fault detection and operational decision-making. However, datasets from real-world treatment plants often contain outliers and missing values due to sensor faults, maintenance activities, and operational disruptions, making outlier handling and data imputation essential for reliable modeling. Existing studies on data imputation for activated sludge systems are often based on synthetic or short datasets, limited method comparisons, or inconsistent evaluation metrics, which reduces their applicability to full-scale operational settings. This study addresses these limitations by presenting a comprehensive, head-to-head comparison of Kohonen Self-Organising Maps (KSOM) with widely used multiple imputation and tree-based methods, namely Amelia II, MICE, missForest, and missRanger. The methods are applied to a real-world multivariate dataset comprising 19 process variables collected over 8.5 years from a full-scale activated sludge treatment plant, containing 39% overall missing data with highly uneven missingness across variables. A validation framework based on held-out observation data is used, and performance is assessed using complementary metrics, including the coefficient of determination (R²), average absolute error (AAE), relative average absolute error (RAAE), mean squared error (MSE), and root mean squared error (RMSE). Results show that KSOM consistently outperforms the competing methods across most variables and evaluation metrics. KSOM achieves near-perfect R² values (≈1) for many process variables, with lower absolute and relative errors, even for variables with very high (>70%) and irregular missingness. These findings highlight KSOM’s robustness in capturing multivariate relationships and cluster structure in complex, operational WWTP data.