In water distribution systems, pumps are used for supplying water from low points to elevated tanks that supply the network’s demands. The pumps are operated in different ways that could be distinguished by the complexity of the required control system. Such control systems range from pressure and time-based controls, through simple fixed ON-OFF trigger levels (e.g., a bang-bang controller) to complex online pump optimization schemes based on water demand predictions [e.g., the model predictive controller (MPC)]. In this study, we propose an off-line optimization method that utilizes dynamic trigger levels for pump operations. More specifically, these trigger dynamics are optimized according to electricity tariff structure, pump operation conditions, and long demand series in order to allow a more robust operation. We also provide a multiobjective analysis for the optimization problem and analyze the impact of different objectives on the obtained solution. In addition, the methodology is also demonstrated on real-world data.

This paper presents a modeling framework for real-time decision support for irrigation scheduling using probabilistic seasonal weather forecasts which are incorporated into a simulation-optimization framework. The simulation of the field processes is performed by the Soil Water Atmosphere Plant (SWAP) model, whereas the optimization is performed by three different stochastic programming methods: implicit approach, explicit single-stage approach and explicit two-stage approach. To evaluate the benefit of the probabilistic forecasts, the irrigation schedules from the different stochastic methods are compared with the best benchmark of perfect forecasts as well as with the real field and the Agriculture Extension Service of Israel schedules. The analysis is performed on a real case study of irrigated chickpeas field in Kibbutz Hazorea, Northern Israel. The results show that incorporating stochastic weather forecasts could lead to substantial improvements compared with current irrigation practices.

Modern water distribution systems (WDSs) offer automated controls and operations to improve their efficiency and reliability. Nonetheless, such automation can be vulnerable to cyber-attacks. Therefore, various approaches have been suggested to detect cyber-attacks in WDSs. However, most of these approaches rely on labeled attack records which are rarely available in real-world applications. Thus, for a detection model to be practical, it should be able to detect and localize events without referring to a predetermined list of labeled attacks. This study proposes a semi-supervised approach that relies solely on attack-free datasets to address this challenge. The approach utilizes a reduction in dimensionality by using maximum canonical correlation analysis (MCCA) followed by support vector data description (SVDD). The developed algorithm was tested on two case studies and various datasets, demonstrating consistently high performance in detecting and localizing cyber-attacks.