m.j. zeynali

Numerous studies in optimization of water supply networks have been allocated to cost reduction of these infrastructures. In general optimization methods, minimizing the costs is the unique purpose, but applying this view point for the case of water supply systems may lead to reduction of the utility and efficiency of the system. Therefore, some multi-objective optimization models have been used to decrease the large amount of costs in these systems and to increase their operation efficiency. The present study has attempted to illustrate a case study for a town of Kerman in order to decrease the costs of rebuilding pipe network using the Imperialistic Competition Optimization Algorithm. So, the network simulation was performed with Water GEMS software. Firstly, the water supply network of the study area was simulated in the Water GEMS model. Next, the properties of water supply network were inserted. Then, using the standard pressure and speed constraints, the optimal options of the algorithm were obtained. By re-running the results of this optimized model in the Water GEMS model and the limits’ checkup, the total costs were estimated and compared. Analysis of the optimal model results showed that in comparison with the state prior to the network optimization, the Imperialistic Competition Algorithm has significantly reduced the cost function of the network.

One of the most common methods for estimating suspended sediment of rivers is sediment rating curve. For better estimation of the amount of suspended sediment based on the sediment curve rating equation, it is possible to optimize its coefficients. One of the methods used for optimizing the coefficients of the sediment curve rating equation is taking advantage of meta-heuristic algorithms. The main objective of this research is the use of grasshopper optimisation algorithm to optimize the relationship between discharge and sediment discharge and comparison the results of this model with genetic algorithms and particle swarm. With respect to the objective function, which minimizes the difference between the measured values of the sediment and the calculated values of that, the optimal values of these coefficients are determined. The results of this research indicated since the objective function, grasshopper optimisation algorithm compared with Genetic algorithm and particle swarm optimization has a good performance. So that grasshopper optimisation algorithm with 7694507 values has the best performance in this problem and then PSO and GA algorithms with 7702357 and 7703750 have a good performance and finally this value in sediment rating curve is equal to 9163544.

Prediction of climate change using the recorded data from reference periods requires precise methods that are able to accurately detect fluctuations and predict changes for future periods. In this study, six multivariate regression models, ANN, SVR, ANFIS, SVM and GP, were investigated and compared for down scaling the daily mean temperature of the Urmia synoptic station, using 26 prediction parameters taken from the fifth IPCC report. The average daily temperature values measured from 12/03/1961 to 20/12/2005 were used for the analysis. 16 of the 26 parameters having a high correlation with the average daily temperature values were selected for all methods using the Pearson correlation test. To investigate the modeling errors, the coefficient of determination, Root Mean Square Error, and effectiveness criteria were used. The results of the evaluation of the accuracy and modeling error showed that among the smart models, GP, ANN, ANFIS and SVM, the Genetic Programming model has the least amount of errors, and in the regression model (multivariate regression and support vector regression) support vector regression has the lowest error rate and the highest accuracy of simulated daily temperature values of the Urmia station. In general, the results of the simulation of the mean daily temperature indicate that regression has better accuracy than smart methods. Since in this study, we only used the data from the Urmia synoptic station, so the results are only valid for this station, and it is not safe to generalize the results for all stations.

One of the most important problems in water resources management is the optimal operation of dam reservoirs. Various methods have been applied to deal with optimization problems. Noting the inability of the conventional optimization methods to solve complex optimization problems, the Meta-Heuristic algorithms have been noticed more than ever. In this study, particle swarm, genetic and continuous ant colony system algorithms were used to optimize the operation of the Doroodzan reservoir. Furthermore, the effect of chain constraints inclusion on the framework of these algorithms were analyzed. The results indicated that regarding the chain constraints, all programs resulted in feasible solutions, where without chain constraints, in some cases the algorithm was unable to find a feasible solution. Therefore, applying these constraints in the framework of the algorithms improved their performances further. In finding the optimized solution, the Genetic algorithm had a better performance than the two other algorithms. Reliability criterion was used to evaluate the algorithms performances. Based on this criterion, as one of the most important criteria in determining system performance, the Genetic algorithm with the Reliability value of 0.964 had the most suitable performance.