检索结果-内蒙古大学图书馆

multi-objective proportional-integral-derivative optimization algorithm for parameters optimization of double-fed induction generator-based wind turbines

引用

APPLIED SOFT COMPUTING 2021年 110卷 107673-107673页

作者： Yin, Linfei Gao, Qi Guangxi Univ Coll Elect Engn Nanning 530004 Guangxi Peoples R China Guangxi Univ Inst Artificial Intelligence Nanning 530004 Guangxi Peoples R China

The meta-heuristic algorithm inspired by natural may reduce the optimization performance due to excessive imitation. This paper proposes a novel multi-objective proportional-integral-derivative optimization algorithm inspired by mathematical thought to provide a better non-dominated solution for multi-objective problems. The idea of the proportional-integral-derivative control algorithm is introduced to cooperate with multi-objective optimization problems for the first time. The proposed algorithm is employed to store and maintain non-dominated solutions. Two groups of controllers of the proposed algorithm are designed for the multi-objective optimization problems, i.e., exploitative controllers aim to obtain the local optimal solution;explorative controllers aim to obtain the global optimal solution. To verify the effectiveness of the multi-objective proportional-integral-derivative optimization algorithm, eight comparison algorithms are compared with eight benchmark functions;five comparison algorithms are compared under the multi-objective parameters optimization problem of double-fed induction generator-based wind turbines. The results of benchmark functions show that the multi-objective proportional-integral-derivative optimization algorithm has superior convergence performances and outperforms other comparison algorithms. The proposed algorithm has excellent optimization performance to obtain the minimum deviation of rotor speed and reactive power for the wind power system controller. (C) 2021 Elsevier B.V. All rights reserved.

关键词： multi-objective optimization problems multi-objective proportional-integral-derivative optimization algorithm Meta-heuristic algorithm Double-fed induction generator

来源：评论

学校读者我要写书评

暂无评论

A Convolutional Neural Network-Based Surrogate Model for multi-objective optimization Evolutionary Algorithm Based on Decomposition

引用

SWARM AND EVOLUTIONARY COMPUTATION 2022年 72卷

作者： Zhang, Tao Li, Fuzhang Zhao, Xin Qi, Wang Liu, Tianwei Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China Tianjin Univ Sch Tianjin Int Engn Inst Tianjin 300072 Peoples R China

Evolutionary algorithms (EAs) show good performance in solving multi-objective optimization problems (MOPs). An EA needs to perform a substantial number of fitness evaluations. For the MOP with high complexity, the fit-ness evaluation functions are computationally expensive, making the evolutionary algorithms time-consuming. Surrogate-assisted evolutionary algorithms (SAEAs) that apply surrogate models instead of fitness exact evalua-tion functions have successfully reduced the computational complexity of fitness evaluations. However, because training a surrogate model requires a certain amount of calculation, a large amount of calculation is required by the SAEA to train multiple surrogate models. Furthermore, most existing surrogate models may not achieve desired evaluation accuracy when processing medium-dimensional and high-dimensional MOPs. This paper pro -poses a novel surrogate model. The surrogate model can be applied in multi-objective optimization evolutionary algorithm based on decomposition (MOEA/D), which is a classic decomposition-based multi-objective optimiza-tion algorithm. The surrogate model is designed based on the convolutional neural network structure, and it is called the multi-objective parallel fitness evaluation network (MPFEN). An MPFEN model contains multiple sub-networks which can be applied as the surrogate models. By training the MPFEN model, we can obtain all sur-rogate models required by a MOEA/D simultaneously without training each required surrogate model separately. Therefore, the amount of calculation of training surrogate models in a MOEA/D is reduced. The evaluation accu-racy of the MPFEN model is tested by experiments. The experimental results show that the evaluation accuracy of MPFEN model is higher than that of other classical surrogate models in most cases. By applying the MPFEN model, the solution quality of SAEA is also improved.

关键词： multi-objective optimization problems Surrogate-assisted evolutionary algorithms multi-objective parallel fitness evaluation network Convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Handling shape optimization of superconducting cavities with DNMOGA

引用

COMPUTER PHYSICS COMMUNICATIONS 2024年 299卷

作者： Wang, Peilin Ye, Kuangkuang Hao, Xuerui Wang, Jike Wuhan Univ Inst Adv Studies Wuhan 430072 Peoples R China

Radiofrequency (RF) cavities hold immense importance in various accelerator applications, but their optimization poses significant challenges due to complex situations involved. In this study, a recently proposed multiobjective optimization algorithm is utilized to optimize the 325 MHz double spoke cavity, which is characterized by 38 geometric parameters and is one of the most complex cavities commonly used in accelerators. The algorithm utilized combines neural network dynamically to speed up convergence of MOGAs, and it is called DNMOGA. Remarkably, when comparing to two manually optimized cavities (MOCs) respectively, DNMOGA consistently produces some cavities that outperform the MOC in all indicators concerned. This result announces the robust generalization capability exhibited by DNMOGA, and further shows the possibility of designing cavities employing the state-of-art optimization algorithms instead of manual optimization processes completely.

关键词： multi-objective optimization problems Superconducting double spoke cavity multiobjectives genetic algorithms Neural network DNMOGA

来源：评论

学校读者我要写书评

暂无评论

The adaptable Pareto set problem for facility location: A video game approach

引用

EXPERT SYSTEMS WITH APPLICATIONS 2021年 186卷 115682-115682页

作者： Vargas-Santiago, Mariano Monroy, Raul Zhang, Chi Ramirez-Marquez, Jose E. Leon-Velasco, Diana A. Sch Sci & Engn Tecnol Monterrey Carretera Lago Guadalupe Km 35 Estado De Mexico 52926 Mexico Beijing Univ Technol Sch Econ & Engn Beijing 100124 Peoples R China Stevens Inst Technol Sch Syst Enterprises Enterprise Sci & Engn Div Hoboken NJ 07030 USA Univ Autonoma Metropolitana Dept Math Cuajimalpa Mexico

Facility Location is a multi-objective optimization problem, where, given a set of demand centers, D, one is to determine how many facilities to open, in such a way that we satisfy the overall demand, while minimizing the sum of two types of costs: one associated to opening a facility, and the other to the distance from each demand center to the nearest facility that has been opened. There exist various techniques to solve it, including methods that are complete, and others that find a good solution, though not necessarily the optimal one. Current techniques, however, do not contemplate that there already is an initial configuration of the problem or that changes have occurred in the environment and so the existing solution must be adjusted to meet new requirements: they reformulate the optimization problem each time, starting from scratch. To fill in this gap, we introduce the adaptable Pareto set of the Facility Location Problem. In particular, we introduce a method that may apply either of two heuristics, namely: the incremental and the decremental heuristics, which deal with the case where it is necessary to increase (respectively, decrease) the number of facilities opened. To complete these heuristics, we provide a video game for crowdsourcing solutions to the adaptable Pareto set for the facility location problem;we have considered both cases, one where some facilities need to be added, and the other, where some facilities need to be removed. We have tested our two methods using the Swain dataset. Our experimental results show that our heuristics are competitive, when compared against both the optimal solution found through a complete method, and that approximated via a genetic algorithm. Further, our results show that video game players may obtain better solutions than those found heuristically, and that these solutions sometimes are similar to those found using a brute force algorithm.

关键词： Facility location problem multi-objective optimization problems Pareto set Heuristics Serious video games Crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

A multi objective-BSC model for new product development project portfolio selection

引用

EXPERT SYSTEMS WITH APPLICATIONS 2020年 162卷 113757-113757页

作者： Abbasi, Darya Ashrafi, Maryam Ghodsypour, Seyed Hassan Amirkabir Univ Technol Dept Ind Engn & Management Syst Tehran Iran

The most significant factor for the survival of an enterprise under a high level of competition is new product development (NPD). As a result, selecting a potential NPD project portfolio to gain competitive advantage has become a major concern to enterprises. However, selection of an NPD project portfolio is intricate due to multiple selection criteria and factors. This study focuses on optimizing an NPD project portfolio selection problem. To this end, Balance Score Card (BSC) is employed as a comprehensive framework to define NPD project selection criteria. Afterward, a multi-objective mathematical model is formulated that attempts to maximize total outcome, to minimize total risk, and to maximize strategic advantages. Our proposed model also takes into account suppliers, consumer demands, and project interdependencies. Because of the NP-hardness of the proposed model, two multi-objective metaheuristic algorithms, multi-objective particle swarm optimization (MOPSO), and non dominated sorting genetic algorithm (NSGA-II) are applied to solve the proposed model. It should be noted that the performance of algorithms is evaluated using the epsilon-constraint method and enhanced using response surface methodology (RSM). Finally, several numerical examples of different sizes are generated to compare the performance of metaheuristic solution methods based on four comparing metrics. Computational results show that NSGA-II outperforms MOPSO in terms of all the evaluation metrics. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： New product development Project portfolio selection multi-objective optimization problems Non dominated sorting genetic algorithm multi-objective particle swarm optimization epsilon-Constraint method

来源：评论

学校读者我要写书评

暂无评论

A Post-Pareto Approach for multi-objective Decision Making Using a Non-Uniform Weight Generator Method

引用

Procedia Computer Science 2012年 12卷 116-121页

作者： Victor M. Carrillo Heidi Taboada Computational Science Program. The University of Texas at El Paso 500 West University El Paso TX 79968-0521 United States of America Department of Industrial Manufacturing and Systems Engineering. The University of Texas at El Paso 500 West University El Paso TX 79968-0521 United States of America

There exist two general approaches to solve multiple objective problems. The first approach involves the aggregation of all the objective functions into a single composite objective function. Mathematical methods such as the weighted sum method, goal programming, or utility functions are methods that pertain to this general approach. The output of this method is a single solution. On the other hand, we have the multiple objective evolutionary algorithms that offer the decision maker a set of trade off solutions usually called non dominated solutions or, Pareto-optimal solutions. This set is usually very large and the decision maker faces the problem of reducing the size of this set to have a manageable number of solutions to analyze. This paper presents a post- Pareto approach to prune the non-dominated set of solutions obtained by multiple objective evolutionary algorithms. The proposed approach uses a non-uniform weight generator method to reduce the size of the Pareto-optimal set. A pair of examples is presented to show the performance of the method.

关键词： post-Pareto optimality decision making multi-objective optimization problems

来源：评论

学校读者我要写书评

暂无评论

A NOVEL multi-objective ESTIMATION OF DISTRIBUTION ALGORITHM BASED ON SENSITIVITY OF objective FUNCTION

引用

INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL 2013年第6期9卷 2543-2566页

作者： Seo, Hyunshik Lee, Chaewoo Ajou Univ Dept Elect & Comp Engn San 5 Suwon 443749 South Korea

Most multi-objective optimization problems (MOPs) have a set of optimal trade-off solutions known as the Pareto-optimal solutions since the objectives in MOPs are usually in conflict with one another. Recently proposed estimation of distribution algorithms (EDAs) build a probability distribution model based on the probabilistic information about decision variables of solutions, and then produce new solutions from the model. In the algorithms, the modeling technique enables the initial large search space to be reduced to small promising solution space during the search. However, the existing EDAs might be inefficient at generating the promising solutions since they depend on the information extracted from the decision variables of current solutions expected to approach the optimal solutions. For effective modeling of the promising solutions, we firstly introduce new information about the relationship between decision variables and objective functions;this information is called sensitivity of objective function. Secondly, we propose a multi-objective estimation of distribution algorithm based on the sensitivity of objective function (MOEDA-S). In the MOEDA-S, the sensitivity-based distribution modeling adapts to the current search strategy such that the convergence-focused search at the beginning part of the search is changed to a diversity-focused search at the latter part of the search. MOEDA-S is compared with two other leading multi-objective evolutionary algorithms on a set of test instances. The simulation results show that MOEDA-S outperforms the two compared algorithms in terms of both convergence and diversity performances of the solutions.

关键词： multi-objective optimization problems multi-objective evolutionary algorithms Estimation of distribution algorithms Variables sensitivity-based modeling

来源：评论

学校读者我要写书评

暂无评论

An IGD+ Performance Indicator Based Particle Swarm Optimizer For multi-objective optimization

An IGD+ Performance Indicator Based Particle Swarm Optimizer...

引用

第33届中国控制与决策会议

作者： Fei Li Shijian Dong Yuanqu Liu Zhengkun Shang School of Electrical and Information Engineering Anhui Unviersity of Technology AnHui Province Key Laboratory of Special Heavy Load Robot Anhui Unviersity of Technology Ma'anshan University School of Information and Control Engineering China University of Mining and Technology Department of Automation North China Electric Power University

Particle swarm optimizer（PSO） is suitable for solving multi-objective optimization problems（MOPs）.However,there are two main issues for any multi-objective particle swarm optimizers（MOPSOs）.The first issue is how to balance the convergence and *** second issue is how to enhance the exploitation and exploration during the evolutionary *** order to address these issues,an modified inverted generational distance（IGD） performance indicator based PSO（IGD-MOPSO） is *** external archive updating strategies based on the IGD indicator and the objective space decomposition method are proposed to select the evenly distributed non-dominated *** leader updated strategy of each particle is based on the IGD indicator value which is associated to the corresponding reference *** genetic operator is embedded into the evolutionary procedure to reset the position in order to help the particle jump out of the local *** have conducted the simulation on some related benchmark test *** experimental results have indicated that the proposed algorithm is competitive with some related algorithms.

关键词： IGD+ indicator Particle swarm optimization The external archive updated strategy objective space decomposition multi-objective optimization problems

来源：评论

学校读者我要写书评

暂无评论

Fast method of constructing the non-dominated set: Arena's principle

引用

Gaojishu Tongxin/Chinese High Technology Letters 2005年第4期15卷 11-14页

作者： Kuang, Da Zheng, Jinhua Institute of Information Engineering Xiangtan University Xiangtan 411105 China

multi-objective Evolutionary Algorithm (MOEA) is used to solve multi-objective optimization problems (MOOPs). In order to improve the efficiency of MOEA, a fast method of constructing non-dominated set called Arena' s Principle is suggested. The time complexity of the Arena's Principle is better than that of Deb's and Jensen's on constructing non-dominated set. In the experiments, Arena's Principle is compared with Deb' and Jensen's approach. It is shown that the experimental results satisfy the theoretical analysis.

关键词： multi-objective evolutionary algorithm multi-objective optimization problems Non-dominated set Pareto-optimal front

来源：评论

学校读者我要写书评

暂无评论

multi-objective Approach for Plug-in Vehicle Aggregators Optimal Operation in a Smart Grid

Multi-Objective Approach for Plug-in Vehicle Aggregators Opt...

引用

International Symposium on Power Electronics, Electrical Drives, Automation and Motion

作者： G. Carpinelli F. Mottola D. Proto Università degli Studi di Napoli 'Federico II' Via Claudio 21 Napoli (Italy)

ISBN: (纸本)9781467312998

This paper deals with Smart Grids including renewable generation plants and plug-in vehicle fleets managed by aggregators and connected to the grid through power electronic devices. A new multi-objective optimization model is proposed in order to obtain the optimal operation of the Smart Grids. The proposed model originates from the need of accomplishing numerous and sometime conflicting objectives in the Smart Grid operation and allows to perform several services, aimed at contemporaneously meeting needs internal to the SG and external to it. Among the possible optimization methods to solve the multi-objective model, two different approaches were used in this paper based on objective sum criterion and weighted sum criterion, respectively. The objective sum criterion does not require any articulation of preferences and seems particularly suitable when low CPU time is required. The weighted sum criterion could lead to better quality of decisions since it evaluates the relative importance of each objective. Numerical simulations applying the analyzed methods for the optimal operation of a low voltage test Smart Grid were performed and discussed.

关键词： Electric vehicles vehicles aggregators multi-objective optimization problems smart grids ancillary services

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：