抄録
Against the backdrop of ongoing urbanization and increasingly severe climate change, urban water resource management faces multiple challenges, including supply–demand imbalances and rising system complexity. Traditional scheduling systems, constrained by delayed response and limited intelligent optimization capacity, can no longer meet the comprehensive requirements of modern cities for safety, real-time performance, and efficiency in water supply systems. This paper systematically reviews the theoretical foundations, key methodologies, and practical advances of intelligent scheduling systems for urban water resources that integrate big data and artificial intelligence (AI). First, it analyzes the basic models of urban water resource scheduling and the limitations of traditional approaches, highlighting their inadequacy in adapting to nonlinear and time-varying complex environments. Second, it explores the role of big data technologies in water use behavior modeling, demand forecasting, and decision support, with a focus on the key applications of AI algorithms such as machine learning and deep learning in scheduling optimization, system perception, and intelligent control. Subsequently, the paper concentrates on intelligent optimization strategies for urban water supply networks, proposing innovative technological pathways including multi-source data fusion, coordinated control, and resilient scheduling to enhance system stability and robustness. Finally, it summarizes the current challenges of data acquisition, model generalization, and system integration. It looks ahead to the future directions of intelligent scheduling systems in achieving efficient and sustainable management of urban water resources. This paper aims to provide theoretical support and technical references for the construction of a new generation of intelligent water resource scheduling systems.
