• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권12호
• /
• pp.5780-5802
• /
• 2017

Cloud computing system consists of distributed resources in a dynamic and decentralized environment. Therefore, using cloud computing resources efficiently and getting the maximum profits are still challenging problems to the cloud service providers and cloud service users. It is important to provide the efficient scheduling. To schedule cloud resources, numerous heuristic algorithms such as Particle Swarm Optimization (PSO), Genetic Algorithm (GA), Ant Colony Optimization (ACO), Cuckoo Search (CS) algorithms have been adopted. The paper proposes a Modified Particle Swarm Optimization (MPSO) algorithm to solve the above mentioned issues. We first formulate an optimization problem and propose a Modified PSO optimization technique. The performance of MPSO was evaluated against PSO, and GA. Our experimental results show that the proposed MPSO minimizes the task execution time, and maximizes the resource utilization rate.

• Structural Engineering and Mechanics
• /
• 제66권2호
• /
• pp.173-183
• /
• 2018

This paper proposes a developed optimization model for steel frames with semi-rigid beam-to-column connections and fixed bases using teaching-learning-based optimization (TLBO) and genetic algorithm (GA) techniques. This method uses rotational deformations of frame members ends as an optimization variable to simultaneously obtain the optimum cross-sections and the most suitable beam-to-column connection type. The total cost of members plus connections cost of the frame are minimized. Frye and Morris (1975) polynomial model is used for modeling nonlinearity of semi-rigid connections, and the $P-{\Delta}$ effect and geometric nonlinearity are considered through a stepped analysis process. The stress and displacement constraints of AISC-LRFD (2016) specifications, along with size fitting constraints, are considered in the design procedure. The developed model is applied to three benchmark steel frames, and the results are compared with previous literature results. The comparisons show that developed model using both LTBO and GA achieves better results than previous approaches in the literature.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제11권3호
• /
• pp.135-145
• /
• 2011

Accurate process characterization and optimization are the first step for a successful advanced process control (APC), and they should be followed by continuous monitoring and control in order to run manufacturing processes most efficiently. In this paper, process characterization and recipe optimization methods with multiple outputs are presented in high density plasma-chemical vapor deposition (HDP-CVD) silicon dioxide deposition process. Five controllable process variables of Top $SiH_4$, Bottom $SiH_4$, $O_2$, Top RF Power, and Bottom RF Power, and two responses of interest, such as deposition rate and uniformity, are simultaneously considered employing both statistical response surface methodology (RSM) and neural networks (NNs) based genetic algorithm (GA). Statistically, two phases of experimental design was performed, and the established statistical models were optimized using performance index (PI). Artificial intelligently, NN process model with two outputs were established, and recipe synthesis was performed employing GA. Statistical RSM offers minimum numbers of experiment to build regression models and response surface models, but the analysis of the data need to satisfy underlying assumption and statistical data analysis capability. NN based-GA does not require any underlying assumption for data modeling; however, the selection of the input data for the model establishment is important for accurate model construction. Both statistical and artificial intelligent methods suggest competitive characterization and optimization results in HDP-CVD $SiO_2$ deposition process, and the NN based-GA method showed 26% uniformity improvement with 36% less $SiH_4$ gas usage yielding 20.8 ${\AA}/sec$ deposition rate.

• Journal of Electrical Engineering and Technology
• /
• 제5권4호
• /
• pp.653-665
• /
• 2010

In this study, we introduce a neurofuzzy approach to the design of fuzzy controllers. The development process exploits key technologies of Computational Intelligence (CI), namely, genetic algorithms (GA) and neurofuzzy networks. The crux of the design methodology deals with the selection and determination of optimal values of the scaling factors of fuzzy controllers, which are essential to the entire optimization process. First, the tuning of the scaling factors of the fuzzy controller is carried out. Next, we form a nonlinear mapping for the scaling factors, which are realized by GA-based neurofuzzy networks by using a fuzzy set or fuzzy relation. The proposed approach is applied to control nonlinear systems like the inverted pendulum. Results of comprehensive numerical studies are presented through a detailed comparative analysis.

• Journal of Electrical Engineering and Technology
• /
• 제10권3호
• /
• pp.1007-1014
• /
• 2015

An optimally designed six-phase induction motor (6PIM) is compared with an initial design induction motor having the same ratings. The Genetic Algorithm (GA) method is used for optimization and multi objective function is considered. Comparison of the optimum design with the initial design reveals that better performance can be obtained by a simple optimization method. Also in this paper each design of 6PIM, is simulated by MAXWELL_2D. The obtained simulation results are compared in order to find the most suitable solution for the specified application, considering the influence of each design upon the motor performance. Construction a 6PIM based on the information obtained from GA method has been done. Quality parameters of the designed motors, such as: efficiency, power losses and power factor measured and optimal design has been evaluated. Laboratory tests have proven the correctness of optimal design.

• 전기학회논문지
• /
• 제67권6호
• /
• pp.767-772
• /
• 2018

Recently, some meta-heuristic algorithms, such as GA(Genetic Algorithm) and GP(Genetic Programming), have been used to optimize CNN(Convolutional Neural Network). The CNN, which is one of the deep learning models, has seen much success in a variety of computer vision tasks. However, designing CNN architectures still requires expert knowledge and a lot of trial and error. In this paper, the recent attempts to automatically construct CNN architectures are investigated and analyzed. First, two GA based methods are summarized. One is the optimization of CNN structures with the number and size of filters, connection between consecutive layers, and activation functions of each layer. The other is an new encoding method to represent complex convolutional layers in a fixed-length binary string, Second, CGP(Cartesian Genetic Programming) based method is surveyed for CNN structure optimization with highly functional modules, such as convolutional blocks and tensor concatenation, as the node functions in CGP. The comparison for three approaches is analysed and the outlook for the potential next steps is suggested.

• International Journal of Control, Automation, and Systems
• /
• 제1권1호
• /
• pp.101-110
• /
• 2003

This paper introduces an identification method for nonlinear models in the form of rule-based Fuzzy-Neural Networks (FNN). In this study, the development of the rule-based fuzzy neural networks focuses on the technologies of Computational Intelligence (CI), namely fuzzy sets, neural networks, and genetic algorithms. The FNN modeling and identification environment realizes parameter identification through synergistic usage of clustering techniques, genetic optimization and a complex search method. We use a HCM (Hard C-Means) clustering algorithm to determine initial apexes of the membership functions of the information granules used in this fuzzy model. The parameters such as apexes of membership functions, learning rates, and momentum coefficients are then adjusted using the identification algorithm of a GA hybrid scheme. The proposed GA hybrid scheme effectively combines the GA with the improved com-plex method to guarantee both global optimization and local convergence. An aggregate objective function (performance index) with a weighting factor is introduced to achieve a sound balance between approximation and generalization of the model. According to the selection and adjustment of the weighting factor of this objective function, we reveal how to design a model having sound approximation and generalization abilities. The proposed model is experimented with using several time series data (gas furnace, sewage treatment process, and NOx emission process data from gas turbine power plants).

• 대한기계학회논문집A
• /
• 제26권12호
• /
• pp.2556-2564
• /
• 2002

The design of airfoil had practiced by repeat tests in its first stage, though an airfoil has as been designed based on simulations according to techniques of computational fluid dynamics. Here, using of traditional optimization is unsuitable because a state of flux is hypersensitive to the shape of airfoil. Therefore the paper optimized the shape of airfoil in transonic region using a genetic algorithm (GA). Response surfaces are based on back propagation neural network (BPN) and regression model. Training data of BPN and regression model were obtained by computational fluid dynamic analysis using CFD-ACE, and each analysis has been designed by design of experiments.

• Smart Structures and Systems
• /
• 제14권1호
• /
• pp.55-70
• /
• 2014

The paper presents a multi-objective optimization strategy for a multi-type sensor placement for Structural Health Monitoring (SHM) of long span bridges. The problem is formulated for simultaneous placement of strain sensors and accelerometers (heterogeneous network) based on application demands for SHM system. Modal Identification (MI) and Accurate Mode Shape Expansion (AMSE) were chosen as the application demands for SHM. The optimization problem is solved through the use of integer Genetic Algorithm (GA) to maximize a common metric to ensure adequate MI and AMSE. The performance of the joint optimization problem solved by GA is compared with other established methods for homogenous sensor placement. The results indicate that the use of a multi-type sensor system can improve the quality of SHM. It has also been demonstrated that use of GA improves the overall quality of the sensor placement compared to other methods for optimization of sensor placement.

• Journal of Power Electronics
• /
• 제15권4호
• /
• pp.1119-1130
• /
• 2015

This study investigates the multi-objective fuzzy optimization of crowbar resistance for the doubly fed induction generator (DFIG) low-voltage ride-through (LVRT). By integrating the crowbar resistance of the crowbar circuit as a decision variable, a multi-objective model for crowbar resistance value optimization has been established to minimize rotor overcurrent and to simultaneously reduce the DFIG reactive power absorbed from the grid during the process of LVRT. A multi-objective genetic algorithm (MOGA) is applied to solve this optimization problem. In the proposed GA, the value of the crowbar resistance is represented by floating-point numbers in the GA population. The MOGA emphasizes the non-dominated solutions and simultaneously maintains diversity in the non-dominated solutions. A fuzzy-set-theory-based is employed to obtain the best solution. The proposed approach has been evaluated on a 3 MW DFIG LVRT. Simulation results show the effectiveness of the proposed approach for solving the crowbar resistance multi-objective optimization problem in the DFIG LVRT.