According to the United Nation’s World Water Development Report, by 2050 more than 50% of the world’s population will be under high water scarcity. To avoid water stress, water resources are needed to be managed more securely. Smart water technology (SWT) has evolved for proper management and saving of water resources. Smart water system (SWS) uses sensor, information, and communication technology (ICT) to provide real-time monitoring of data such as pressure, water ow, water quality, moisture, etc. with the capability to detect any abnormalities such as non-revenue water (NRW) losses, water contamination in the water distribution system (WDS). It makes water and energy utilization more efficient in the water treatment plant and agriculture. In addition, the standardization of data format i.e., use of Water Mark UP language 2.0 has made data exchange easier for between different water authorities. This review research exhibits the current state-of-the-art of the on-going SWT along with present challenges and future scope on the mentioned technologies. A conclusion is drawn that smart technologies can lead to better water resource management, which can lead to the reduction of water scarcity worldwide. High implementation cost may act as a barrier to the implementation of SWT in developing countries, whereas data security and its reliability along with system ability to give accurate results are some of the key challenges in its field implementation.

An accurate prediction of future water consumption is necessary to create a satisfactory design for a water distribution system. In this study, two new hybrid approaches are proposed for accurately predicting future hourly and monthly water demands. The first approach is based on the hybridization of ensemble empirical mode decomposition (EEMD) and difference pattern sequence forecasting (DPSF), and the second is based on the hybridization of EEMD with DPSF and autoregressive integrated moving average (ARIMA). Historical hourly water consumption datasets of southeastern Spain and monthly datasets of Nagpur, India are used for assessing the performance of the proposed approaches. The performance of the EEMD-DPSF approach is checked using the root mean square error (RMSE), mean absolute error (MAE), and mean percentage absolute error (MAPE). Further, the results are compared with those obtained using PSF, ARIMA, DPSF, their hybrid models, and various other ANN models. The proposed EEMD-DPSF method is found to perform significantly better than the other state-of-the-art methods in terms of prediction accuracy without compromising time and memory complexities. The comparison between the two proposed models demonstrates that the EEMD-DPSF approach provides better results, whereas the EEMD-DPSF-ARIMA approach requires shorter computational time.

Localizing leakages in large water distribution systems is an important and ever-present problem. Due to the complexity originating from water pipeline networks, too few sensors, and noisy measurements, this is a highly challenging problem to solve. In this work, we present a methodology based on generative deep learning and Bayesian inference for leak localization with uncertainty quantification. A generative model, utilizing deep neural networks, serves as a probabilistic surrogate model that replaces the full equations, while at the same time also incorporating the uncertainty inherent in such models. By embedding this surrogate model into a Bayesian inference scheme, leaks are located by combining sensor observations with a model output approximating the true posterior distribution for possible leak locations. We show that our methodology enables producing fast, accurate, and trustworthy results. It showed a convincing performance on three problems with increasing complexity. For a simple test case, the Hanoi network, the average topological distance (ATD) between the predicted and true leak location ranged from 0.3 to 3 with a varying number of sensors and level of measurement noise. For two more complex test cases, the ATD ranged from 0.75 to 4 and from 1.5 to 10, respectively. Furthermore, accuracies upwards of 83%, 72%, and 42% were achieved for the three test cases, respectively. The computation times ranged from 0.1 to 13 s, depending on the size of the neural network employed. This work serves as an example of a digital twin for a sophisticated application of advanced mathematical and deep learning techniques in the area of leak detection.

The performance of a water distribution system of providing a required flow rate at all the nodes with required pressure heads throughout its design life is affected by uncertainties associated with different parameters such as future water demands, pipe roughness coefficient values, required pressure heads at nodes, etc. The objective of this paper is to present a comprehensive review on the nature of uncertainties (random or fuzzy), various models and methods used for their quantification, and different ways of handling them in the design of water distribution networks. While probabilistic based approaches are used for handling uncertainty of random type, the possibilistic based approach considers uncertainty of fuzzy nature. Some key issues and serious limitations of the existing approaches for modeling uncertain parameters related to water distribution networks are identified. The uncertainty in water demands is due to both their random nature and lack of information about their values. Therefore, a combination of both types of approaches, called the fuzzy random approach, is found to be more effective. The fuzzy random approach can provide optimal design solutions that are not only cost-effective but also has higher reliability to cope with severe future uncertainties.

Satyam Tiwari1, Aniket Sharma2, Prerna Pandey3, Shilpa Dongre4 and Rajesh Gupta5 1 PG Student, Email: satyam700@outlook.com (Corresponding Author) 2 Research Scholar, Email: sharmaaniket0392@gmail.com 3 Research Scholar, Email: prerna.pandey1203@gmail.com 4 Assistant Professor, Email: shilpa_dg@rediffmail.com 5 Professor, Email: drrajeshgupta123@hotmail.com Dept. of Civil Engineering, Visvesvaraya National Institute of Technology Nagpur-440010, Maharashtra, India. ABSTRACT The battle of intermittent water supply posed a tough challenge by jointly considering a problem related to analysis, design and operation of water distribution networks (WDNs). A methodology is needed which could summon all the inefficiencies of the existing network on a single platform to achieve the different stated objectives (Indicators) under some technical and financial constraints. The main targets are: (1) reduction in losses by repairing leaks, and/or replacing pipes, (2) to increase consumer satisfaction by meeting the demands at required pressure. A multi-stage methodology is proposed to suggest a solution to the given problem. Initially, demand nodes are clustered to form District Metering Area (DMA) by considering the locations of existing valves using the methodology of Sharma et al. (2022, Accepted for publication). The methodology of Sharma et al. (2022) consists of identification of clusters and their boundaries by considering the location of existing valves. The boundaries optimization is solved using Genetic Algorithm (GA) with customer satisfaction as a constraint to identify permanent boundaries. Out of the several ways of improving the network performance in desired 5-year periods with limited budget in each year, the leak detection and repair, pipe replacement with same or higher size, and valve installation to reduce excess pressure are proposed to be targeted primarily. A fast greedy algorithm, similar to that used by Gupta and Bhave (1996) for design of WDN and Agrawal et al. (2007) for strengthening and expansion of WDN, is proposed to be used. The iterative methodology will start with existing network. Benefits in terms of improvements in both head and outflows at demand nodes due to change in any option will be calculated along with increase in cost for that option. All the options will be considered one by one. Out of several options at any stage few best will be selected. The iterative process of selection for any year will be repeated till the available fund for that year are exhausted. Final solution for the first year will become, initial solution for the next year. Solution for all the five years will be obtained. Finally, the performance of network would be assessed using suggested parameters and the results will be reported. Gupta R. and Bhave P.R. (1996). "Reliability-based design of water distribution systems", Journal of Environmental Engineering, American Society of Civil EngineersAgrawal M. L., Gupta R., and Bhave P. R. (2007). "Reliability-based strengthening and expansion of water distribution networks", Journal of Water Resources Planning & Management ASCESharma, A. N., Dongre, S. R., Gupta, R., Pandey, P., and Bokde, N. D. (2022, Accepted for publication). “Partitioning of Water Distribution Network into District Metered Areas using Existing Valves”, Computer modelling in Engineering and Sciences