The computational grid provides a promising platform for the deployment of various high-performance computing applications. A grid system consists of heterogeneous resource domains, while the computational tasks of fi...The computational grid provides a promising platform for the deployment of various high-performance computing applications. A grid system consists of heterogeneous resource domains, while the computational tasks of finite element analysis may differ in demand of computing power. The cost-effective utilization of resources in the grid can be obtained through scheduling tasks to optimal resource domains. Firstly, a cost-effective scheduling strategy is presented for finite element applications. Secondly, aiming at the conjugate gradient solver stemming from finite element analysis, a performance evaluation formula is presented for determining optimal resouree domains, which is derived from phase parallel model and takes the heterogeneous characteristic of resource domains into account. Finally, experimental results show that the presented formula delivers a good estimation of the actual execution time, and indicate that the presented formula can be used to determine optimal resource domains in the grid environment.展开更多
In this paper, an objective-based gradient multi-objective optimization （MOO） technique, the Objective-Based Gradient Algorithm （OBGA）, is proposed with the goal of defining the Pareto domain more precisely and ef...In this paper, an objective-based gradient multi-objective optimization （MOO） technique, the Objective-Based Gradient Algorithm （OBGA）, is proposed with the goal of defining the Pareto domain more precisely and efficiently than current MOO techniques. The performance of the OBGA in locating the Pareto domain was evaluated in terms of precision, computation time and number of objective function calls, and compared to two current MOO algorithms： Dual Population Evolutionary Algorithm （DPEA） and Non-Dominated Sorting Genetic Algorithm I1 （NSGA-II）, using four test problems. For all test problems, the OBGA systematically produced a more precise Pareto domain than DPEA and NSGA-II. With the adequate selection of the OBGA parameters, computation time required for the OBGA can be lower than that required for DPEA and NSGA-II. Results clearly show that the OBGA is a very effective and efficient algorithm for locating the Pareto domain.展开更多
Pigeon-inspired optimization(PIO) is a new swarm intelligence optimization algorithm, which is inspired by the behavior of homing pigeons. A variant of pigeon-inspired optimization named multi-objective pigeon-inspire...Pigeon-inspired optimization(PIO) is a new swarm intelligence optimization algorithm, which is inspired by the behavior of homing pigeons. A variant of pigeon-inspired optimization named multi-objective pigeon-inspired optimization(MPIO) is proposed in this paper. It is also adopted to solve the multi-objective optimization problems in designing the parameters of brushless direct current motors, which has two objective variables, five design variables, and five constraint variables. Furthermore, comparative experimental results with the modified non-dominated sorting genetic algorithm are given to show the feasibility, validity and superiority of our proposed MIPO algorithm.展开更多
Based on the supercritical ＂wingl＂ which was released in the DPW-III conference, multi-objective optimization has been done to increase the lift-drag ratio at cruise condition and improve transonic buffet boundary a...Based on the supercritical ＂wingl＂ which was released in the DPW-III conference, multi-objective optimization has been done to increase the lift-drag ratio at cruise condition and improve transonic buffet boundary and drag-rise performance. Hicks-Henne shape functions are used to represent the bump shape. In the design optimization to increase lift-drag ratio, the objectives involve the cruise point and three other off-design points nearby. In the other optimization process to improve buffet and drag-rise performance, three buffet onset points near the cruise point and one drag-rise point are selected as the design points. Non-dominating sort genetic algorithm II （NSGA-II） is used in both processes. Additionally, individual analysis for every selected point on the Pareto frontier is conducted in order to avoid local convergence and achieve global optimum. Re- sults of optimization for aerodynamic efficiency show a decrease of 11 counts in drag at the cruise point. Drag at nearby off-design points are also reduced to some extent. Similar approaches are made to improve buffet and drag-rise characteristics, resulting in significant improvements in both ways.展开更多
文摘The computational grid provides a promising platform for the deployment of various high-performance computing applications. A grid system consists of heterogeneous resource domains, while the computational tasks of finite element analysis may differ in demand of computing power. The cost-effective utilization of resources in the grid can be obtained through scheduling tasks to optimal resource domains. Firstly, a cost-effective scheduling strategy is presented for finite element applications. Secondly, aiming at the conjugate gradient solver stemming from finite element analysis, a performance evaluation formula is presented for determining optimal resouree domains, which is derived from phase parallel model and takes the heterogeneous characteristic of resource domains into account. Finally, experimental results show that the presented formula delivers a good estimation of the actual execution time, and indicate that the presented formula can be used to determine optimal resource domains in the grid environment.
文摘In this paper, an objective-based gradient multi-objective optimization （MOO） technique, the Objective-Based Gradient Algorithm （OBGA）, is proposed with the goal of defining the Pareto domain more precisely and efficiently than current MOO techniques. The performance of the OBGA in locating the Pareto domain was evaluated in terms of precision, computation time and number of objective function calls, and compared to two current MOO algorithms： Dual Population Evolutionary Algorithm （DPEA） and Non-Dominated Sorting Genetic Algorithm I1 （NSGA-II）, using four test problems. For all test problems, the OBGA systematically produced a more precise Pareto domain than DPEA and NSGA-II. With the adequate selection of the OBGA parameters, computation time required for the OBGA can be lower than that required for DPEA and NSGA-II. Results clearly show that the OBGA is a very effective and efficient algorithm for locating the Pareto domain.
基金partially supported by the National Natural Science Foundation of China(Grant Nos.61425008,61333004 and 61273054)National Key Basic Research Program of China("973"Project)(Grant Nos.2014CB046401 and 2013CB035503)Top-Notch Young Talents Program of China,Aeronautical Foundation of China(Grant No.20135851042)
文摘Pigeon-inspired optimization(PIO) is a new swarm intelligence optimization algorithm, which is inspired by the behavior of homing pigeons. A variant of pigeon-inspired optimization named multi-objective pigeon-inspired optimization(MPIO) is proposed in this paper. It is also adopted to solve the multi-objective optimization problems in designing the parameters of brushless direct current motors, which has two objective variables, five design variables, and five constraint variables. Furthermore, comparative experimental results with the modified non-dominated sorting genetic algorithm are given to show the feasibility, validity and superiority of our proposed MIPO algorithm.
文摘Based on the supercritical ＂wingl＂ which was released in the DPW-III conference, multi-objective optimization has been done to increase the lift-drag ratio at cruise condition and improve transonic buffet boundary and drag-rise performance. Hicks-Henne shape functions are used to represent the bump shape. In the design optimization to increase lift-drag ratio, the objectives involve the cruise point and three other off-design points nearby. In the other optimization process to improve buffet and drag-rise performance, three buffet onset points near the cruise point and one drag-rise point are selected as the design points. Non-dominating sort genetic algorithm II （NSGA-II） is used in both processes. Additionally, individual analysis for every selected point on the Pareto frontier is conducted in order to avoid local convergence and achieve global optimum. Re- sults of optimization for aerodynamic efficiency show a decrease of 11 counts in drag at the cruise point. Drag at nearby off-design points are also reduced to some extent. Similar approaches are made to improve buffet and drag-rise characteristics, resulting in significant improvements in both ways.
