An artificial intelligence-based model for optimal conjunctive operation of surface and groundwater resources.

A hybrid simulation-optimization model is proposed for the optimal conjunctive operation of surface and groundwater resources. This second-level model is created by finding and combining the best aspects of two resilient metaheuristics, the moth swarm algorithm and the symbiotic organization search algorithm, and then connecting the resulting algorithm to an artificial neural network simulator. For assessment of the developed model efficiency, its results are compared with two first-level simulation-optimization models. The comparisons reveal that the operation policies obtained by the developed second-level model can reliably supply more than 99% of the total demands in the study regions, indicating its superior efficiency compared to the two other first-level models. In addition, the highest sustainability index in the study regions belongs to the proposed model. Comparing the results of this research with those of other recent studies confirm the supremacy of the developed second-level model over several previously developed models.

Optimization of hydropower energy generation by 14 robust evolutionary algorithms.

The use of evolutionary algorithms (EAs) for solving complex engineering problems has been very promising, so the application of EAs for optimal operation of hydropower reservoirs can be of great help. Accordingly, this study investigates the capability of 14 recently-introduced robust EAs in optimization of energy generation from Karun-4 hydropower reservoir. The best algorithm is the one that produces the largest objective function (energy generation) and has the minimum standard deviation (SD), the minimum coefficient of variations (CV), and the shortest time of CPU usage. It was found that the best solution was achieved by the moth swarm algorithm (MSA), with the optimized energy generation of 19,311,535 MW which was 65.088% more than the actual energy generation (11,697,757). The values of objective function, SD and CV for MSA were 0.147, 0.0029 and 0.0192, respectively. The next ranks were devoted to search group algorithm (SGA), water cycle algorithm (WCA), symbiotic organism search algorithm (SOS), and coyote optimization algorithm (COA), respectively, which have increased the energy generation by more than 65%. Some of the utilized EAs, including grasshopper optimization algorithm (GOA), dragonfly algorithm (DA), antlion optimization algorithm (ALO), and whale optimization algorithm (WOA), failed to produce reasonable results. The overall results indicate the promising capability of some EAs for optimal operation of hydropower reservoirs.

A new optimization algorithm to solve multi-objective problems.

Simultaneous optimization of several competing objectives requires increasing the capability of optimization algorithms. This paper proposes the multi-objective moth swarm algorithm, for the first time, to solve various multi-objective problems. In the proposed algorithm, a new definition for pathfinder moths and moonlight was proposed to enhance the synchronization capability as well as to maintain a good spread of non-dominated solutions. In addition, the crowding-distance mechanism was employed to select the most efficient solutions within the population. This mechanism indicates the distribution of non-dominated solutions around a particular non-dominated solution. Accordingly, a set of non-dominated solutions obtained by the proposed multi-objective algorithm is kept in an archive to be used later for improving its exploratory capability. The capability of the proposed MOMSA was investigated by a set of multi-objective benchmark problems having 7 to 30 dimensions. The results were compared with three well-known meta-heuristics of multi-objective evolutionary algorithm based on decomposition (MOEA/D), Pareto envelope-based selection algorithm II (PESA-II), and multi-objective ant lion optimizer (MOALO). Four metrics of generational distance (GD), spacing (S), spread (Δ), and maximum spread (MS) were employed for comparison purposes. The qualitative and quantitative results indicated the superior performance and the higher capability of the proposed MOMSA algorithm over the other algorithms. The MOMSA algorithm with the average values of CPU time = 2771 s, GD = 0.138, S = 0.063, Δ = 1.053, and MS = 0.878 proved to be a robust and reliable model for multi-objective optimization.

Comparative analysis of some evolutionary-based models in optimization of dam reservoirs operation.

Deriving optimal operation policies for multi-reservoir systems is a complex engineering problem. It is necessary to employ a reliable technique to efficiently solving such complex problems. In this study, five recently-introduced robust evolutionary algorithms (EAs) of Harris hawks optimization algorithm (HHO), seagull optimization algorithm (SOA), sooty tern optimization algorithm (STOA), tunicate swarm algorithm (TSA) and moth swarm algorithm (MSA) were employed, for the first time, to optimal operation of Halilrood multi-reservoir system. This system includes three dams with parallel and series arrangements simultaneously. The results of mentioned algorithms were compared with two well-known methods of genetic algorithm (GA) and particle swarm optimization (PSO) algorithm. The objective function of the optimization model was defined as the minimization of total deficit over 223 months of reservoirs operation. Four performance criteria of reliability, resilience, vulnerability and sustainability were used to compare the algorithms' efficiency in optimization of this multi-reservoir operation. It was observed that the MSA algorithm with the best value of objective function (6.96), the shortest CPU run-time (6738 s) and the fastest convergence rate (< 2000 iterations) was the superior algorithm, and the HHO algorithm placed in the next rank. The GA, and the PSO were placed in the middle ranks and the SOA, and the STOA placed in the lowest ranks. Furthermore, the comparison of utilized algorithms in terms of sustainability index indicated the higher performance of the MSA in generating the best operation scenarios for the Halilrood multi-reservoir system. The application of robust EAs, notably the MSA algorithm, to improve the operation policies of multi-reservoir systems is strongly recommended to water resources managers and decision-makers.

Optimization of water distribution of network systems using the Harris Hawks optimization algorithm (Case study: Homashahr city).

In this article applies the Harris Hawks Optimization Algorithm for optimization of the water distribution network of the Homashahr located in Iran for a period of one month (from 30 September 2018 to 30 October 2019). The utilized time-series data included water demand, reservoir storage. In this article, a model based on the Harris Hawks Optimization Algorithm (HHO) was developed for the optimization of the water distribution network. The analysis showed that the best solutions achieved by the Harris Hawks Optimization Algorithm (HHO) were 35,508 $. The results revealed that the HHO algorithm was well in the optimal design of water supply networks problem. At the end, about 12% of the optimization was done by this algorithm.•In this article applied the Harris Hawks Optimization Algorithm for optimization of the water distribution network of the Homashahr located in Iran.•The method presented in this article can be useful for managers of water and wastewater companies, water resource facilities and water distribution system managing director for optimal network design to reduce costs.•The present algorithm performs better than the other algorithms in the discussion of the optimization of water distribution networks.

Data on optimization of the non-linear Muskingum flood routing in Kardeh River using Goa algorithm.

This article describes the time series data for optimizing the Non-linear Muskingum flood routing of the Kardeh River, located in Northeastern of Iran for a period of 2 days (from 27 April 1992 to 28 April 1992). The utilized time-series data included river inflow, Storage volume and river outflow. In this data article, a model based on the Grasshopper Optimization Algorithm (GOA) was developed for the optimization of the Non-linear Muskingum flood routing model. The GOA algorithm was compared with other metaheuristic algorithms such as the Genetic Algorithm (GA) and Harmony search (HS). The analysis showed that the best solutions achieved by the GOA, Genetic Algorithm (GA), and Harmony search (HS) were 3.53, 5.29, and 5.69, respectively. The analysis of these datasets revealed that the GOA algorithm was superior to GA and HS algorithms for the optimal flood routing river problem.

Improved Moth-Swarm Algorithm to predict transient storage model parameters in natural streams.

Transient storage model (TSM) is the most popular model for simulating solutes transport in natural streams. Accurate estimate of TSM parameters is essential in many hydraulic and environmental problems. In this study, an improved version of high-level Moth-Swarm Algorithm (IMSA) was used to predict the TSM parameters. First, the performance of the improved model was successfully assessed through several benchmark functions. Next, a series of 58 measured hydraulic and geometric datasets was used to validate the model. The data were divided into two series randomly, 38 datasets were selected for derivation and the remaining 20 datasets were used to verification. Then the results of IMSA were compared with other algorithms proposed by previous researchers. Two statistical indices of root mean square error (RMSE) and coefficient of correlation (CC) were employed to evaluate the performance of the model. The results showed that despite the high complexity and uncertainty associated with the dispersion processes, the IMSA algorithm could accurately predict the TSM parameters.

Data on optimization of the Karun-4 hydropower reservoir operation using evolutionary algorithms.

This article describes the time series data for optimizing the hydropower operation of the Karun-4 reservoir located in Iran for a period of 106 months (from October 2010 to July 2019). The utilized time-series data included reservoir inflow, reservoir storage, evaporation from the reservoir, precipitation on the reservoir, and release of water through the power plant. In this data article, a model based on Moth Swarm Algorithm (MSA) was developed for the optimization of water resources. The analysis showed that the best solutions achieved by the MSA, Genetic Algorithm (GA), and Particle Swarm Optimization (PSO) were 0.147, 0.3026, and 0.1584, respectively. The analysis of these datasets revealed that the MSA algorithm was superior to GA and PSO algorithms in the optimal operation of the hydropower reservoir problem.