Effective ways to optimise real-time pump scheduling to maximise energy efficiency are being sought to meet the challenges in the energy market. However, the considerable number of evaluations of popular optimisation methods based on metaheuristics cause significant delays for real-time pump scheduling, and the simplification of traditional deterministic methods may introduce bias towards the optimal solutions. To address these limitations, an exploration-enhanced deep reinforcement learning (DRL) framework is proposed to address real-time pump scheduling problems in water distribution systems. The experimental results indicate that E-PPO can learn suboptimal scheduling policies for various demand distributions and can control the application time to 0.42 s by transferring the online computation-intensive optimisation task offline. Furthermore, a form of penalty of the tank level was found that can reduce energy costs by up to 11.14% without sacrificing the water level in the long term. Following the DRL framework, the proposed method makes it possible to schedule pumps in a more agile way as a timely response to changing water demand while still controlling the energy cost and level of tanks.

Accurate forecasting of hourly water demand is essential for effective and sustainable operation, and the cost-effective management of water distribution networks. Unlike monthly or yearly water demand, hourly water demand has more fluctuations and is easily affected by short-term abnormal events. An effective preprocessing method is needed to capture the hourly water demand patterns and eliminate the interference of abnormal data. In this study, an innovative preprocessing framework, including a novel local outlier detection and correction method Isolation Forest (IF), an adaptive signal decomposition technique Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), and basic forecasting models have been developed. In order to compare a promising deep learning method Gated Recurrent Unit (GRU) as a basic forecasting model with the conventional forecasting models, Support Vector Regression (SVR) and Artificial Neural Network (ANN) have been used. The results show that the proposed hybrid method can utilize the complementary advantages of the preprocessing methods to improve the accuracy of the forecasting models. The root-mean-square error of the SVR, ANN, and GRU models has been reduced by 57.5%, 27.8%, and 30.0%, respectively. Further, the GRU-based models developed in this study are superior to the other models, and the IF-CEEMDAN-GRU model has the highest accuracy. Hence, it is promising that this preprocessing framework can improve the performance of the water demand forecasting models.

Leakage in water distribution systems (WDS) is a major problem that results in substantial resource wastage. Pressure management, which is based on optimized control strategies using pressure-reducing valve installation, is considered one of the most effective methods for controlling network leakage and can be broadly classified into varied types, depending on the different control strategies. When facing diverse operational conditions in actual engineering, selecting the most suitable optimization strategy for the specific water supply network can greatly control leakage and efficiently utilize water resources. This article employs a greedy algorithm to iteratively determine the control sequence for pressure-reducing valves (PRVs), with the objective of minimizing surplus pressure. Subsequently, it proposed five evaluation indicators, namely, daily flow, daily leakage, pressure imbalance indicator, median daily pressure at nodes, and water age, which are used to evaluate and compare pressure management strategies in two sample networks. Finally, a suitable control strategy was successfully developed and implemented for an actual WDS of Y city in southern China, resulting in significant achievements. In conclusion, this paper embodies our attempt and contemplation in formulating pressure management strategies under diverse operating conditions in WDS, with the objective of providing guidance for practical engineering applications.

With energy and water resources shortages, the energy and water resources managements of water distribution networks (WDNs) have become increasingly important. However, achieving real-time scheduling of pump and valve in dynamic environments remains challenging. Thus, this study proposes a multi-agent reinforcement learning scheduling framework to address the uncertainty of water demand in WDNs. First, we constructed a WDN environment and modelled the scheduling problem as a Markov decision process. Second, a multi-agent deep deterministic policy gradient (MADDPG) method was used to determine the strategy of the fully cooperative multi-agent task. Moreover, the impacts of energy and water loss costs on the scheduling strategy were explored. Finally, the results were compared with those of a genetic algorithm (GA), particle swarm optimisation (PSO), and differential evolution (DE) to verify the performance and robustness of the proposed model. The results show that water loss dominates the scheduling process, and the scheduling solutions for minimising water loss and energy costs are mainly affected by the demand pattern of consumers rather than the energy tariff. The proposed MADDPG model outperforms the GA, PSO, and DE models, achieving a significantly faster solution, which is advantageous for practical applications.

Urban water distribution systems face growing challenges from energy inefficiencies caused by hydraulic anomalies, such as pipe aging, bursts, demand variability, and suboptimal pump and valve operations. This review systematically evaluates current technologies for energy-efficient management of WDNs under such conditions, structured around both basic and applied technologies. Basic technologies include real-time monitoring, data acquisition, and hydraulic modeling with CFD simulation. Applied technologies focus on demand forecasting, pressure management for energy optimization, and leakage anomaly detection. Case studies demonstrate the practical value of these approaches. Despite recent advances, challenges persist in data interoperability, real-time optimization complexity, scalability, and forecasting uncertainty. Future research should emphasize adaptive AI algorithms, integration of digital twin platforms with control systems, hybrid optimization frameworks, and renewable energy recovery technologies. This review provides a comprehensive foundation for the development of intelligent, energy-efficient, and resilient urban water distribution systems through integrated, data-driven management strategies.

Fire following earthquake (FFE) is a common secondary disaster that can inflict great damage to humans. A large number of seismic resilience evaluation methods have been proposed, but few of them consider the influence of FFE. In this study, a multi-scenario simulation based model was developed to evaluate the post-disaster performance of water distribution networks (WDNs) in supplying both firefighting flow and original demand under the effect of seismic damage and FFEs. Hypothetical earthquakes were generated and the spatial–temporal distribution of FFEs was simulated by the Poisson distribution model and the Weibull distribution model. The post-disaster performance was evaluated by two types of seismic reliability metrics. The developed model was applied to a WDN currently operating in China with eight pre-determined earthquake scenarios. The results showed that the firefighting flow was concentrated in the first few hours after the earthquake. Thus, the serviceability of both original demand and firefighting flow was influenced significantly within the first few hours, while little impact was observed after the concentrated firefighting flow was delivered. The proposed model quantified the WDN’s performance under specific seismic damage and potential FFEs, and can be used for the planning, design, and maintenance of WDNs.