Multi-Objective

In this work, we suggest that the poorer results obtained with Particle Swarm Optimization (PSO) in some previous studies should be attributed to the cross-validation scheme commonly employed to improve generalization of PSO-trained Neural Network River Forecasting (NNRF) models. Cross-validation entails splitting the training dataset into two, and accepting particle position updates only if fitness improvements are concurrently measured on both subsets. The NNRF calibration process thus becomes a multi-objective (MO) optimization problem which is still addressed as a single-objective one. In our opinion, PSO cross-validated training should be carried out under a MO optimization framework instead. Therefore, in this work we introduce a novel MO variant of the swarm optimization algorithm to train NNRF models for the prediction of future streamflow discharges in the Shenandoah River watershed, Virginia (US). The case study comprises over 9,000 observations of both streamflow and rainfall observations, spanning a period of almost 25 years. The newly introduced Multi-objective Fully Informed Particle Swarm (MOFIPS) optimization algorithm is found to provide better performing models with respect to those developed using the standard PSO, as well as advanced gradient-based optimization techniques. These findings encourage the use of a MO approach to NNRF cross-validated training with swarm optimization.

Keywords:
FIPS, multi-objective, particle swarm optimization, PSO, neural network river forecasting, NNRF

FMS's seems to be a very promising technology as they provide flexibility, which is essential for many manufacturing companies. This paper speaks about multi-objective optimization related to FMS scheduling which act as a constraint in configuring the loop layout in optimum manner by various evolutionary algorithms i.e. Meta-heuristics like GA, SA etc. The first objective is concern with flexible batch scheduling problem (FBSP). The next objective is focus on determination of optimum machine sequence with minimum total transportation cost. In this paper, the various loop layout problems are tested using C++ codes for enactment of objective function with respect to computational time and number of problem instances involved in GA and SA. The results of the different optimization algorithms (Genetic Algorithm and simulated annealing method) are compared with existing results and conclusions are depicted.

A robust multi-objective wing design optimization procedure using CFD is presented in this work. Instead of directly applying CFD to wing design optimization, a Kriging aerodynamic model that approximates CFD result is proposed to save computational cost. By introducing 6 sigma robust approach as a sub-objective function, multi-objective wing design problems can be solved with aerodynamic robustness. Non-Uniform Rational B-Spline curves (NURBS) are introduced to depict the wing geometry in design optimization process. The most important parameters of the wing geometry can then be screened by design of experiment and treated as design variables due to the local variation property of NURBS. Under this formulation, a multi-objective genetic algorithm based on non-dominated sorting is employed to handle multiple flight conditions in wing design. The optimum wing geometry is selected according to trade-off among design objects on the non-dominated front. To validate the proposed approach, two robust design optimization cases are studied for ONERA-M6-Wing. It turns out that the drag coefficient is insensitive to Mach number between Ma0.8-Ma0.9 after robust optimization. The result also verifies the effectiveness of our method in boosting performance and robustness of multiple flight conditions: the lift curve slope (Ma0.3) of optimum wing and the 6 sigma objective function of transonic drag (Ma0.8-Ma0.9) increase by 11.9% and 25.4%, respectively. Observations in the optimization cases are concluded as follows: 1) For wing aerodynamic design problems, the multi-objective robust optimization can both improve the performance at different flight conditions and provide robustness. 2) The Kriging aerodynamic model derived from CFD result can satisfy the precision requirement of wing design. 3) Even though the optimization result is subject to the weights of the 6 sigma function in sub-object, the influence is not comparable to the trade-off among design objects. 4) The optimum solution obtained by proposed approach is superior to gradient based optimization method, while the computational cost is acceptable.

Keywords: robustness; NURBS; non-dominated; Kriging model; multi-objective

Background and objectives: The multi-objective water resource reservoir systems are generally composed of conflict purposes. In this study, keeping the minimum water level at above elevations increases hydropower generation through the water effective head. However, this operating policy results in decreasing the potential of storage variation and active storage capacity, which may be caused some deficits for meeting downstream demands. Accordingly, one of the major aims in this research is to maximize the hydropower generation in complicated multiple and multi-objective reservoir systems in which the desired reliability is kept to meet downstream demands. To reach this aim, the optimal minimum water level is calculated. In this area of research, it can be pointed to the hybrid optimization model; classical mathematical models and evolutionary algorithms (1), hybrid evolutionary algorithms (4) and the multi-objective optimization model (14).
Materials and Methods: In this research, a simulation-optimization model is developed for the Karun basin included the 6 dams system of the current condition. In this hybrid model, maximizing of the total produced energy is defined as objective function constrained to water balance and reliability. This model is capable to investigate the water resource system in details with allocating priority to different demands. In this way, the hydropower generation is maximized using the genetic algorithm and via evolutionary process, in which desired reliability for meeting demands is kept using penalty in the objective function.
Results: The results indicate that the system reliability for meeting demands is kept in the level of 75% in which the annual average of hydropower energy produced by the system is 18193 GWH. The most portions is related to Karun 1 reservoir with 3483GWH and the less one is related to Karun 4 with 2007 GWH per year. Additionally, agriculture networks of Dez river and Gargar network on Gargar river, that is one of the Karun branches, are the boundary area of the optimization for satisfying minimum acceptable reliability. In other words, these networks have been identified as critical networks for meeting demands.
Conclusion: In the common states, evolutionary algorithms are unable to consider the constraint and should be found a remedy to impose constraints. However, this research showed that using penalty in objective function accordance with the violation values of target reliability makes desired performance in the complicated system. Moreover, applying of the simulation-optimization model helps significantly to input more details of the water resource systems in the simulation model. This is more efficient than applying the single optimization model made simplifying of the problems.
Key words: Hydropower, Genetic algorithm, Multi-objective, Optimization Reservoirs.