Search Results (119)

Water, the lifeblood of our planet, sustains ecosystems, economies, and communities. However, climate change and increasing hydrological variability have exacerbated global water scarcity, threatening livelihoods and economic stability. According to the United Nations, over 2 billion people currently live in water-stressed regions, a figure expected to rise significantly by 2030. To address this urgent challenge, this study proposes an AI-driven anomaly detection framework for smart water metering networks (SWMNs) using machine learning (ML) techniques and data resampling methods to enhance water conservation efforts. This research utilizes 6 years of monthly water consumption data from 1375 households from Location A, Windhoek, Namibia, and applies support vector machine (SVM), decision tree (DT), random forest (RF), and k-nearest neighbors (kNN) models within ensemble learning strategies. A significant challenge in real-world datasets is class imbalance, which can reduce model reliability in detecting abnormal patterns. To address this, we employed data resampling techniques including random undersampling (RUS), SMOTE, and SMOTEENN. Among these, SMOTEENN achieved the best overall performance for individual models, with the RF classifier reaching an accuracy of 99.5% and an AUC score of 0.998. Ensemble learning approaches also yielded strong results, with the stacking ensemble achieving 99.6% accuracy, followed by soft voting at 99.2% and hard voting at 98.1%. These results highlight the effectiveness of ensemble methods and advanced sampling techniques in improving anomaly detection under class-imbalanced conditions. To the best of our knowledge, this is the first study to explore and evaluate the combined use of ensemble learning and resampling techniques for ML-based anomaly detection in SWMNs. By integrating artificial intelligence into water systems, this work lays the foundation for scalable, secure, and efficient smart water management solutions, contributing to global efforts in sustainable water governance. Full article

Understanding the characteristics of residential hot-water consumption can be useful for developing effective water-conservation strategies in response to increasing pressure on natural resources. This study systematically investigates residential hot-water consumption through direct monitoring of over 40 domestic fixtures (belonging to six different end-use categories) in five Italian households, recorded over a period ranging from approximately two weeks to nearly four months, and using smart meters with 5 min resolution. A multi-step analysis is applied—at both household and end-use levels, explicitly differentiating tap uses by purpose and location—to (i) quantify daily per capita hot-water consumption, (ii) calculate hot-water ratios, and (iii) assess daily profiles. The results show an average total water consumption of 106.7 L/person/day, with at least 26.1% attributed to hot water. In addition, daily profiles reveal distinct patterns across end uses: hot- and cold-water consumption at kitchen sinks are not aligned over time (with cold water peaking before meals and hot water used predominantly afterward), while bathroom taps show more synchronized use and a marked evening peak in hot-water consumption. Study findings—along with the related open-access dataset—provide a valuable benchmark based on field measurements to support in the process of water demand modeling and the development of targeted demand-management strategies. Full article

Water, an essential asset for life and growth, is under growing pressure due to climate change, overpopulation, pollution, and industrialization. At the same time, water distribution within cities relies on piping networks that are over 30 years old and thereby prone to leaks, cracking, and losses. Taking this into account, non-revenue water (i.e., water that is distributed to homes and facilities but not returning revenues) is estimated at almost 50%. To this end, intelligent water management via computational advanced tools is required in order to optimize water usage, to mitigate losses, and, more importantly, to ensure sustainability. To address this issue, a case study was developed in this paper, following a step-by-step methodology for the city of Heraklion, Greece, in order to introduce an intelligent water management system that integrates advanced technologies into the aging water distribution infrastructure. The first step involved the digitalization of the network’s spatial data using geographic information systems (GIS), aiming at enhancing the accuracy and accessibility of water asset mapping. This methodology allowed for the creation of a framework that formed a “digital twin”, facilitating real-time analysis and effective water management. Digital twins were developed upon real-time data, validated models, or a combination of the above in order to accurately capture, simulate, and predict the operation of the real system/process, such as water distribution networks. The next step involved the incorporation of a hydraulic simulation and modeling tool that was able to analyze and calculate accurate water flow parameters (e.g., velocity, flowrate), pressure distributions, and potential inefficiencies within the network (e.g., loss of mass balance in/out of the district metered areas). This combination provided a comprehensive overview of the water system’s functionality, fostering decision-making and operational adjustments. Lastly, automatic meter reading (AMR) devices could then provide real-time data on water consumption and pressure throughout the network. These smart water meters enabled continuous monitoring and recording of anomaly detections and allowed for enhanced control over water distribution. All of the above were implemented and depicted in a web-based environment that allows users to detect water meters, check water consumption within specific time-periods, and perform real-time simulations of the implemented water network. Full article

Smart cities integrate advanced technologies, data-driven decision-making, and interconnected infrastructure to enhance urban living and resource efficiency. Among these, Smart Water Management (SWM) is crucial for optimizing water distribution and reducing Non-Revenue Water (NRW) losses, a persistent challenge for utilities worldwide. Water leaks contribute significantly to NRW, necessitating real-time leak detection and management systems to minimize detection time and human effort. Achieving this requires seamless integration of SWM technologies, including advanced metering infrastructure, the Internet of Things (IoT), and Artificial Intelligence (AI). While previous studies have explored various leak detection techniques, many lack a focused analysis of real-time data integration and automated alerts in SWM systems. This Systematic Literature Review (SLR) addresses this gap by examining advancements in automatic data collection, leak detection models, and real-time alert mechanisms. The findings highlight the growing potential of data-driven approaches to enhance leak detection accuracy and efficiency, particularly those leveraging flow and pressure data. Despite advancements, model accuracy, scalability, and real-world applicability remain. This review provides critical insights for future research, guiding the development of automated, AI-driven leak management systems to improve water distribution, minimize losses, and enhance sustainability in smart cities. Full article

Detailed hydraulic modeling of a water distribution network (WDN) in an urban area is implemented therein, based on data from geoinformatic tools (GIS), to investigate and analyze the network’s hydraulic response to different scenarios of operation. A detailed mapping of the water meters of the consumers in the urban district is therefore conducted in the frame of a District Metered Area (DMA) zoning. Different consumptions according to water meters and patterns of daily water demand, resulting from both theoretical and measured data from a limited number of smart meters, are used in the hydraulic simulations. The analysis conducted assists common engineering practice to identify critical locations for constructing new hydraulic infrastructure, resulting in the restructuring and reorganization of the DMA, assisting to face existing and common problems of WDNs within the general framework of DMA design and efficient water management. A case study on the WDN of Efkarpia, located in the city of Thessaloniki, Greece, satisfying the principal design criteria of DMAs, is presented in this work, under both normal and emergency conditions. Hydraulic analysis is performed based on different scenarios, mainly consisting of different consumptions according to water meters and different demand patterns, all resulting in high pressures in the southern part of the DMA. Hydraulic simulations are then performed considering two basic operating scenarios, namely the operation of the old DMA of Efkarpia and a new DMA, which is reduced in size. The two scenarios are compared in terms of estimated pressures in the studied area, as well as in terms of energy consumption in the upstream pumping station. The comparisons reveal that the new DMA outperforms the old one, with a large increase in the pressure at nodes where low pressures were assessed in the old DMA, a reduction in daily pressure variation up to 45%, and quite significant energy savings assessed around 21.6%. Full article

Real-time monitoring, data-driven decisions, and energy consumption optimization have reached a new level with IoT advancement. However, a significant challenge faced by intelligent nodes and IoT applications resides in their energy requirements in the long term, especially in the case of gas or water smart meters. This article proposes an algorithm for smart meters’ energy consumption optimization based on IoT, LoRaWAN, and NB-IoT using microcontroller-based development boards, PZEM004T energy meters, Dragino LoRaWAN shield, or BG96 NB-IoT modules. The algorithm adjusts the transmission time based on the change in data in real-time. According to the experimental results, the energy consumption and the number of packets transmitted significantly decreased using LoRaWAN or NB-IoT, saving up to 76.11% and 86.81% of the transmitted packets, respectively. Additionally, the outcome highlights a notable percentage reduction in the energy consumption spike frequency, with NB-IoT achieving an 87.3% reduction and LoRaWAN slightly higher at 88.5%. This study shows that adaptive algorithms are very effective in extending the lifetime of IoT nodes, thereby providing a solid baseline for scalable, lightweight, energy-monitoring IoT applications. The results could help shape the development of smart energy metering systems and sustainable IoT. Full article

This paper examines Connected Smart Green Buildings (CSGBs) in Burnaby, BC, Canada, with a focus on townhouses with one to four bedrooms. The proposed model integrates sustainable materials and smart components such as recycled insulation, Photovoltaic (PV) solar panels, smart meters, and high-efficiency systems. These elements improve energy efficiency and promote sustainability. Operating in island mode, CSGBs can function independently of the grid, providing resilience during power outages and reducing reliance on external energy sources. Real data on electricity, gas, and water consumption are used to optimize load management under isolated conditions. Electric Vehicles (EVs) are also considered in the system. They serve as energy storage devices and, through Vehicle-to-Grid (V2G) technology, can supply power when needed. A hybrid Machine Learning (ML) model combining Long Short-Term Memory (LSTM) and a Convolutional Neural Network (CNN) is proposed to improve the performance. The metrics considered include accuracy, efficiency, emissions, and cost. The performance was compared with several well-known models including Linear Regression (LR), CNN, LSTM, Random Forest (RF), Gradient Boosting (GB), and hybrid LSTM–CNN, and the results show that the proposed model provides the best results. For a four-bedroom Connected Smart Green Townhouse (CSGT), the Mean Absolute Percentage Error (MAPE) is 4.43%, the Root Mean Square Error (RMSE) is 3.49 kWh, the Mean Absolute Error (MAE) is 3.06 kWh, and $R^2$ is 0.81. These results indicate that the proposed model provides robust load optimization, particularly in island mode, and highlight the potential of CSGBs for sustainable urban living. Full article

This paper examines Connected Smart Green Townhouses (CSGTs) as a modern residential building model in Burnaby, British Columbia (BC). This model incorporates a wide range of sustainable materials and smart components such as recycled insulation, Photovoltaic (PV) solar panels, smart meters, and high-efficiency systems. The CSGTs operate in grid-connected mode to balance on-site renewables with grid resources to improve efficiency, cost-effectiveness, and sustainability. Real datasets are used to optimize resource consumption, including electricity, gas, and water. Renewable Energy Sources (RESs), such as PV systems, are integrated with smart grid technology. This creates an effective framework for managing energy consumption. The accuracy, efficiency, emissions, and cost are metrics used to evaluate CSGT performance. CSGTs with one to four bedrooms are investigated considering water systems and party walls. A deep Machine Learning (ML) model combining Long Short-Term Memory (LSTM) and a Convolutional Neural Network (CNN) is proposed to improve the performance. In particular, the Mean Absolute Percentage Error (MAPE) is below 5%, the Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) are within acceptable levels, and $R^2$ is consistently above 0.85. The proposed model outperforms other models such as Linear Regression (LR), CNN, LSTM, Random Forest (RF), and Gradient Boosting (GB) for all bedroom configurations. Full article

Assessing leakage risks in water distribution networks (WDNs) and implementing preventive monitoring for high-risk pipelines has become a widely accepted approach for leakage control. However, existing methods face significant data barriers between Geographic Information System (GIS) and leakage prediction systems. These barriers hinder traditional pipeline risk assessment methods, particularly when addressing challenges such as data imbalance, poor model interpretability, and lack of intuitive prediction results. To overcome these limitations, this study proposes a leakage assessment framework for water distribution networks based on multiple attention mechanisms and a generative model-based data balancing method. Extensive comparative experiments were conducted using water distribution network data from B2 and B3 District Metered Areas in Zhengzhou. The results show that the proposed model, optimized with a balanced data method, achieved a 40.76% improvement in the recall rate for leakage segment assessments, outperforming the second-best model using the same strategy by 1.7%. Furthermore, the strategy effectively enhanced the performance of all models, further proving that incorporating more valid data contributes to improved assessment results. This study comprehensively demonstrates the application of data-driven models in the field of “smart water management”, providing practical guidance and reference cases for advancing the development of intelligent water infrastructure. Full article

Smart meters monitor hourly water consumption patterns while reducing the cost and inconvenience of traditional meters. This study comprehensively analyzes 1871 households that previously used traditional meters from the distribution point to the distribution area. All the households were equipped with smart meters and the data collected were used for analysis. On the basis of the total estimated water consumption, 227 households were classified as single households. These households were further classified into single-worker and -nonworker households. This study analyzed smart meter data to evaluate the timings and amounts of water consumption peaks. The results indicate that worker households peaked at 8:00, with 29 L/h of consumption on weekdays, and peaked again on evenings at 20:00–21:00, averaging 32 L/h. For nonworker households, the peak occurred at 9:00, with 20 L/h, with no major changes in the afternoon, and a second peak occurred at 19:00–20:00 in evening, with an average of 19 L/h. Moreover, worker households peaked at 8:00 and 20:00 on weekdays, and at 9:00 and 19:00 on weekends. It was revealed that worker households consume 10% more on weekends than on weekdays, and 262% more from 13:00 to 16:00. These findings may assist in water supply planning by supporting distribution schedules on the basis of peak household consumption, leading to more helpful resource management. Full article

This study aims to create a reliable water-demand forecasting system using Long Short-Term Memory networks. The model integrates hourly water demands from 10 District Metered Areas of a Water Distribution Network in northeast Italy and weather data, handling missing values with LSTM-based data imputation. It considers temporal aspects like time, weekdays, holidays, and weekend patterns, employing sine and cosine transformations to capture daily cycles. To ensure the model’s robustness, the testing was conducted during the last week of the dataset, specifically week 81, with iterative adjustments to the LSTM’s hyperparameters to optimize prediction accuracy. These tuning efforts focused on learning rate, number of layers, and batch size, tailored to maximize the system’s performance. This method is essential for smart decision-making in water utility management and demonstrates significant potential for improving operational efficiencies. Full article

This paper presents the application of the Comparison of Flow Pattern Distribution (CFPD) method for detecting water leakage and understanding consumption behaviors at both microscale and macroscale. Implemented at Lille University’s Scientific Campus, this research utilizes Automated Meter Reading (AMR) to collect real-time water supply and consumption data. The research successfully identified several significant leak events by analyzing this data with the CFPD method on weekly and daily scales. The analysis of the data resulted in identifying the seasonal and operational consumption patterns across different periods of the year. The findings highlight the effectiveness of the CFPD method in achieving water conservation and operational efficiency, consequently contributing to the UN Sustainable Development Goal (SDG) 6 concerning clean water and sanitation. Full article

This paper presents a comparison between traditional District Metered Areas (DMAs) and an innovative concept called District Information Areas (DIAs) in managing water distribution systems (WDSs). Both aim to improve efficiency and resilience, but differ in approach. DMAs use physical segmentation with measurement devices mainly for leak detection, while DIAs employ smart sensors and data analytics for decentralised management. DIAs operate semi-autonomously, making local decisions based on data analysis and coordinating with neighbouring areas. While traditional methods still play a role in maintenance, DIAs aim to enhance sensor coverage and support future digital twin development. The advantages of DIAs include reduced latency, increased flexibility, improved efficiency, and enhanced resilience during disruptions. Full article

Modelling consumer demand under intermittent water supply (IWS) is an unresolved challenge. To understand withdrawal behaviours in more detail, fifty-six smart meters were installed in households across an IWS network in Lahan, Nepal. The most frequent withdrawal type was small withdrawals (median two litres), while large tank-filling-type behaviours contributed significantly to a household’s overall water consumption. Behaviour was highly heterogeneous; households with large storage tanks tended to practice tank-filling behaviour significantly more than those without. Consequently, a one-size-fits-all approach to consumer demand modelling may not always be appropriate and could lead to unrealistic predictions of supply inequality. Full article

Buildings play a significant role in the rise of energy consumption and carbon emissions. Building operations are responsible for 28% of the world’s carbon emissions. It is crucial, therefore, to evaluate the environmental impact of various buildings’ operational phase in order to implement sustainable strategies for the mitigation of their energy usage and associated carbon footprint. While numerous studies have been conducted to determine the carbon footprint of conventional building operation phases, there are still a lack of actual data on the operational carbon (OC) emissions of mass timber buildings. There is also a lack of research pertaining to the operational carbon of buildings within larger campuses and their inherent energy usage. This study, therefore, aims to quantify empirical data on the carbon footprint of a mass timber building, using, as a case study, the recent Adohi Hall building, situated at the University of Arkansas, Fayetteville. The study also aims to examine and identify the best energy use scenarios for the campus building under consideration. The research team obtained data on Adohi Hall’s energy consumption, fuel input usage, and other utilities (such as water, electricity, chilled water, and natural gas) accounting for the operation of the building from 2021 to 2023, a span of three years. The University of Arkansas Facilities Management (FAMA) provided the data. The study relies on the life cycle assessment (LCA) as its primary approach, with SimaPro 9, Ecoinvent v3.7 database, DataSmart, version 2023.1 and the U.S. Life Cycle Inventory (USLCI) database utilized to model the energy and water consumption of Adohi Hall during the operational phase (B6 & B7). The results indicate 4496 kg CO₂ eq emissions associated with the operation per square meter of Adohi Hall over its 50-year lifespan. The study also examines various scenarios of fuel sources leading to carbon emissions and provides insights into reduction strategies during the operational phase of buildings. Among them, the electricity based on a cleaner fuel source diversification, according to realistic expectations and technological advancements projections, results in a 17% reduction in Adohi Hall’s OC. Due to the usage of the combined heat and power (CHP) plant on the campus of the University of Arkansas as a complementary source of electricity and heating for Adohi Hall, the resulting carbon emission is approximately 21% (20.73%) less when compared to similar buildings in the same city but outside the campus. The study, therefore, reveals that CHP plant development is a highly effective strategy for building OC reduction. Full article