Hydropower operation of multi-reservoir systems is very difficult to solve mostly due to their nonlinear, nonconvex and large-scale nature. While conventional methods are long known to be incapable of solving these types of problems, evolutionary algorithms are shown to successfully handle the complexity of these problems at the expense of very large computational cost, particularly when population-based methods are used. A novel hybrid cellular automata-simulated annealing (CA-SA) method is proposed in this study which avoids the shortcomings of the existing conventional and evolutionary methods for the optimal hydropower operation of multi-reservoir systems. The start and the end instances of time at each operation period is considered as the CA cells with the reservoir storages at these instances are taken as the cell state which leads to a cell neighborhood defined by the two adjacent periods. The local updating rule of the proposed CA is derived by projecting the objective function and the constraints of the original problem on the cell neighborhoods represented by an optimization sub-problem with the number of decision variables equal to the number of reservoirs in the system. These sub-problems are subsequently solved by a modified simulated annealing approach to finding the updated values of the cell states. Once all the cells are covered, the cell states are updated and the process is iterated until the convergence is achieved. The proposed method is first used for hydropower operation of two well-known benchmark problems, namely the well-known four- and ten-reservoir problems. The results are compared with the existing results obtained from cellular automata. Genetic algorithm and particle swarm optimization indicating that the proposed method is much more efficient than existing algorithms. The proposed method is then applied for long-term hydropower operation of a real-world three-reservoir system in the USA, and the results are presented and compared with the existing results.

An adaptive hybrid genetic algorithm (GA) and cellular automata (CA) method is proposed for solving implicit stochastic optimization of reservoir operation problems. The method is based on a decomposition approach in which the reliability constraints are handled with GA, whereas the resulting deterministic problem is solved with a CA model. Two versions, binary and integer GA, were employed for handling the reliability constraints of the problem. In the first one, GA was used to determine the success/failure pattern of the operation, whereas in the latter, only failure periods were determined with GA. The proposed method was used for monthly water supply and hydropower operation of an existing reservoir and the results are presented and compared with those of a GA model. To demonstrate the efficiency and scale independency of the model, short-term, medium-term, and long-term operations are considered assuming different target reliabilities. Comparison of the results with those of a GA model shows the superiority of the proposed method.

As is much of the world, California increasingly is challenged by water scarcity. A recent multiyear drought depleted surface reservoir and groundwater storage in many places of the state. The Sustainable Groundwater Management Act (SGMA), passed in 2014, promises sustainable groundwater management in California and suggests managed aquifer recharge (MAR) as one of the key practices to eliminate groundwater overdraft by groundwater sustainability agencies. Questions remain, however, about the amount of water available for MAR. Conjunctive management provides the opportunity to modify reservoir operations and enhance recharge long before any drought occurs. However, the amount by which reoperation of surface reservoirs can increase the available water for MAR has not been thoroughly investigated. Folsom reservoir is operated to meet a variety of objectives, including flood control, water supply, hydropower, and environmental flow. The inclusion of water discharge for groundwater recharge adds another objective for the operation of the reservoir and complicates the decision-making. Various management strategies were developed and applied to evaluate performance of the system during a historical period, and a new objective was added to maximize the available water for recharge from Folsom reservoir. Although the reoperation strategy offers additional storage in the system and increases the expected value of recharge from 280 to 430 million cubic meter (mcm) per year, trade-offs between different objectives showed that new operating rules perform quite satisfactorily, with nonsignificant deficits and violations of old objectives.

The uncertainty of water resources availability is a growing problem in California as agricultural industrialization, population growth, and climate change affect water resources. The intense manipulation of the hydrological regime has led to the depletion of the water resources in the state and the subsequent use of various adaptive management strategies to cope with environmental conditions and social concerns. The historical imbalance between water pumping and replenishment in Pajaro Valley has led to overdrafted aquifers, seawater intrusion, and salinization. The objective of this study is to estimate the sustainable carrying capacity of agricultural land in Pajaro Valley while preventing groundwater overdraft. A groundwater box model was built and calibrated using historical data to represent current and future hydrology and water management strategies. An optimization model maximized the economic profit using the agricultural acreage as the decision variable with a set of constraints aimed at determining the sustainable carrying capacity of the groundwater basin. Model constraints include total land and water availability, crop acreage, agricultural water use, and historical demand. In the Pajaro Valley, agricultural operations must use less water more efficiently, which means changes in crop types, size of activities, and fallowing land in parts of the basin. Results of the optimal scenario over 25 years show a 15% reduction of total agricultural acreage, 8.5% reduction in food production, average profit loss of 4%, and a 79% reduction in aquifer depletion. This study provides an overall vision of what can be accomplished with coordinated land use planning using strategies that harmonize individual decisions and shared natural resources.

This study presents an innovative data-driven approach to optimally design water distribution networks (WDNs). The methodology comprises five key stages: Generation of 600 synthetic WDNs with diverse properties, optimized to determine optimal component diameters; Extraction of 80 topological and hydraulic features from the optimized WDNs using graph theory; preprocessing and preparing the extracted features using established data science methods; Application of six feature selection methods (Variance Threshold, k-best, chi-squared, Light Gradient-Boosting Machine, Permutation, and Extreme Gradient Boosting) to identify the most relevant features for describing optimal diameters; and Integration of the selected features with four machine learning models (Random Forest, Support Vector Machine, Bootstrap Aggregating, and Light Gradient-Boosting Machine), resulting in 24 ensemble models. The Extreme Gradient Boosting-Light Gradient-Boosting Machine (Xg-LGB) model emerged as the optimal choice, achieving R², MAE, and RMSE values of 0.98, 0.017, and 0.02, respectively. When applied to a benchmark WDN, this model accurately predicted optimal diameters, with R², MAE, and RMSE values of 0.94, 0.054, and 0.06, respectively. These results highlight the developed model’s potential for the accurate and efficient optimal design of WDNs.