Methods of improving seismic event locations were investigated as part of a research study aimed at reducing ground control safety hazards. Seismic event waveforms collected with a 23-station three-dimensional sensor ...Methods of improving seismic event locations were investigated as part of a research study aimed at reducing ground control safety hazards. Seismic event waveforms collected with a 23-station three-dimensional sensor array during longwall coal mining provide the data set used in the analyses. A spatially variable seismic velocity model is constructed using seismic event sources in a passive tomographic method. The resulting three-dimensional velocity model is used to relocate seismic event positions. An evolutionary optimization algorithm is implemented and used in both the velocity model development and in seeking improved event location solutions. Results obtained using the different velocity models are compared. The combination of the tomographic velocity model development and evolutionary search algorithm provides improvement to the event locations.展开更多
Feature selection is one of the important topics in text classification. However, most of existing feature selection methods are serial and inefficient to be applied to massive text data sets. In this case, a feature ...Feature selection is one of the important topics in text classification. However, most of existing feature selection methods are serial and inefficient to be applied to massive text data sets. In this case, a feature selection method based on parallel collaborative evolutionary genetic algorithm is presented. The presented method uses genetic algorithm to select feature subsets and takes advantage of parallel collaborative evolution to enhance time efficiency, so it can quickly acquire the feature subsets which are more representative. The experimental results show that, for accuracy ratio and recall ratio, the presented method is better than information gain, x2 statistics, and mutual information methods; the consumed time of the presented method with only one CPU is inferior to that of these three methods, but the presented method is supe rior after using the parallel strategy.展开更多
A hybrid identification model based on multilayer artificial neural networks(ANNs) and particle swarm optimization(PSO) algorithm is developed to improve the simultaneous identification efficiency of thermal conductiv...A hybrid identification model based on multilayer artificial neural networks(ANNs) and particle swarm optimization(PSO) algorithm is developed to improve the simultaneous identification efficiency of thermal conductivity and effective absorption coefficient of semitransparent materials.For the direct model,the spherical harmonic method and the finite volume method are used to solve the coupled conduction-radiation heat transfer problem in an absorbing,emitting,and non-scattering 2D axisymmetric gray medium in the background of laser flash method.For the identification part,firstly,the temperature field and the incident radiation field in different positions are chosen as observables.Then,a traditional identification model based on PSO algorithm is established.Finally,multilayer ANNs are built to fit and replace the direct model in the traditional identification model to speed up the identification process.The results show that compared with the traditional identification model,the time cost of the hybrid identification model is reduced by about 1 000 times.Besides,the hybrid identification model remains a high level of accuracy even with measurement errors.展开更多
To solve aircraft arrival sequencing and scheduling problems,and improve the typical predatory search algorithm（PSA）,an innovative PSA is developed.The new PSA uses variable constraints of local search and global se...To solve aircraft arrival sequencing and scheduling problems,and improve the typical predatory search algorithm（PSA）,an innovative PSA is developed.The new PSA uses variable constraints of local search and global search to avoid falling into local optimal solutions and the degeneration of solutions.To test the performance of new PSA,a case study with ten arriving flights and two runways is performed.Test results show that the new PSA performs much better than typical PSA and genetic algorithm（GA）in the aspects of the rate of gaining optimal solutions and the computational time.展开更多
A methodology for the selection of the optimal land uses of the reclamation of mined areas is proposed. It takes into consideration several multi-nature criteria and constraints, including spatial constrains related t...A methodology for the selection of the optimal land uses of the reclamation of mined areas is proposed. It takes into consideration several multi-nature criteria and constraints, including spatial constrains related to the permissible land uses in certain parts of the mined area. The methodology combines desirability functions and evolution searching algorithms for selection of the optimal reclamation scheme. Its application for the reclamation planning of the Amynteon lignite surface mine in Greece indicated that it handles effectively spatial and non-spatial constraints and incorporates easily the decision-makers preferences regarding the reclamation strategy in the optimization procedure.展开更多
This study presents a numerical method for optimizing hull form in calm water with respect to total drag which contains a viscous drag and a wave drag. The ITTC 1957 model-ship correlation line was used to predict fri...This study presents a numerical method for optimizing hull form in calm water with respect to total drag which contains a viscous drag and a wave drag. The ITTC 1957 model-ship correlation line was used to predict frictional drag and the corrected linearized thin-ship theory was employed to estimate the wave drag The evolution strategy （ES） which is a member of the evolutionary algorithms （EAs） family obtains an optimum hull form by considering some design constraints. Standard Wigley hull is considered as an initial hull in optimization procedures for two test cases and new hull forms were achieved at Froude numbers 0.24, 0.316 and 0.408. In one case the ES technique was ran for the initial hull form, where the main dimensions were fixed and the only variables were the hull offsets. In the other case in addition to hull offsets, the raain dimensions were considered as variables that are optimized simultaneously. The numerical results of optimization procedure demonstrate that the optimized hull forms yield a reduction in total drag.展开更多
Production optimization has gained increasing attention from the smart oilfield community because it can increase economic benefits and oil recovery substantially.While existing methods could produce high-optimality r...Production optimization has gained increasing attention from the smart oilfield community because it can increase economic benefits and oil recovery substantially.While existing methods could produce high-optimality results,they cannot be applied to real-time optimization for large-scale reservoirs due to high computational demands.In addition,most methods generally assume that the reservoir model is deterministic and ignore the uncertainty of the subsurface environment,making the obtained scheme unreliable for practical deployment.In this work,an efficient and robust method,namely evolutionaryassisted reinforcement learning(EARL),is proposed to achieve real-time production optimization under uncertainty.Specifically,the production optimization problem is modeled as a Markov decision process in which a reinforcement learning agent interacts with the reservoir simulator to train a control policy that maximizes the specified goals.To deal with the problems of brittle convergence properties and lack of efficient exploration strategies of reinforcement learning approaches,a population-based evolutionary algorithm is introduced to assist the training of agents,which provides diverse exploration experiences and promotes stability and robustness due to its inherent redundancy.Compared with prior methods that only optimize a solution for a particular scenario,the proposed approach trains a policy that can adapt to uncertain environments and make real-time decisions to cope with unknown changes.The trained policy,represented by a deep convolutional neural network,can adaptively adjust the well controls based on different reservoir states.Simulation results on two reservoir models show that the proposed approach not only outperforms the RL and EA methods in terms of optimization efficiency but also has strong robustness and real-time decision capacity.展开更多
Compton camera-based prompt gamma(PG) imaging has been proposed for range verification during proton therapy. However, a deviation between the PG and dose distributions, as well as the difference between the reconstru...Compton camera-based prompt gamma(PG) imaging has been proposed for range verification during proton therapy. However, a deviation between the PG and dose distributions, as well as the difference between the reconstructed PG and exact values, limit the effectiveness of the approach in accurate range monitoring during clinical applications. The aim of the study was to realize a PG-based dose reconstruction with a Compton camera, thereby further improving the prediction accuracy of in vivo range verification and providing a novel method for beam monitoring during proton therapy. In this paper, we present an approach based on a subset-driven origin ensemble with resolution recovery and a double evolutionary algorithm to reconstruct the dose depth profile(DDP) from the gamma events obtained by a cadmium-zinc-telluride Compton camera with limited position and energy resolution. Simulations of proton pencil beams with clinical particle rate irradiating phantoms made of different materials and the CT-based thoracic phantom were used to evaluate the feasibility of the proposed method. The results show that for the monoenergetic proton pencil beam irradiating homogeneous-material box phantom,the accuracy of the reconstructed DDP was within 0.3 mm for range prediction and within 5.2% for dose prediction. In particular, for 1.6-Gy irradiation in the therapy simulation of thoracic tumors, the range deviation of the reconstructed spreadout Bragg peak was within 0.8 mm, and the relative dose deviation in the peak area was less than 7% compared to the exact values. The results demonstrate the potential and feasibility of the proposed method in future Compton-based accurate dose reconstruction and range verification during proton therapy.展开更多
Multi-objective evolutionary algorithms(MOEAs) are typically used to optimize two or three objectives in the accelerator field and perform well. However, the performance of these algorithms may severely deteriorate wh...Multi-objective evolutionary algorithms(MOEAs) are typically used to optimize two or three objectives in the accelerator field and perform well. However, the performance of these algorithms may severely deteriorate when the optimization objectives for an accelerator are equal to or greater than four. Recently, many-objective evolutionary algorithms(MaOEAs)that can solve problems with four or more optimization objectives have received extensive attention. In this study, two diffraction-limited storage ring(DLSR) lattices of the Extremely Brilliant Source(ESRF-EBS) type with different energies were designed and optimized using three MaOEAs and a widely used MOEA. The initial population was found to have a significant impact on the performance of the algorithms and was carefully studied. The performances of the four algorithms were compared, and the results demonstrated that the grid-based evolutionary algorithm(GrEA) had the best performance.Ma OEAs were applied in many-objective optimization of DLSR lattices for the first time, and lattices with natural emittances of 116 and 23 pm·rad were obtained at energies of 2 and 6 GeV, respectively, both with reasonable dynamic aperture and local momentum aperture(LMA). This work provides a valuable reference for future many-objective optimization of DLSRs.展开更多
Evolutionary algorithm is applied for distillation separation sequence optimization synthesis problems with combination explosion. The binary tree data structure is used to describe the distillation separation sequenc...Evolutionary algorithm is applied for distillation separation sequence optimization synthesis problems with combination explosion. The binary tree data structure is used to describe the distillation separation sequence, and it is directly applied as the coding method. Genetic operators, which ensure to prohibit illegal filial generations completely, are designed by using the method of graph theory. The crossover operator based on a single parent or two parents is designed successfully. The example shows that the average ratio of search space from evolutionary algorithm with two-parent genetic operation is lower, whereas the rate of successful minimizations from evolutionary algorithm with single parent genetic operation is higher.展开更多
A software defined networking(SDN) system has a logically centralized control plane that maintains a global network view and enables network-wide management, optimization, and innovation. Network-wide management and o...A software defined networking(SDN) system has a logically centralized control plane that maintains a global network view and enables network-wide management, optimization, and innovation. Network-wide management and optimization problems are typicallyvery complex with a huge solution space, large number of variables, and multiple objectives. Heuristic algorithms can solve theseproblems in an acceptable time but are usually limited to some particular problem circumstances. On the other hand, evolutionaryalgorithms(EAs), which are general stochastic algorithms inspired by the natural biological evolution and/or social behavior of species, can theoretically be used to solve any complex optimization problems including those found in SDNs. This paper reviewsfour types of EAs that are widely applied in current SDNs: Genetic Algorithms(GAs), Particle Swarm Optimization(PSO), Ant Colony Optimization(ACO), and Simulated Annealing(SA) by discussing their techniques, summarizing their representative applications, and highlighting their issues and future works. To the best of our knowledge, our work is the first that compares the tech-niques and categorizes the applications of these four EAs in SDNs.展开更多
This paper discusses the convergence rates about a class of evolutionary algorithms in general search spaces by means of the ergodic theory in Markov chain and some techniques in Banach algebra. Under certain conditio...This paper discusses the convergence rates about a class of evolutionary algorithms in general search spaces by means of the ergodic theory in Markov chain and some techniques in Banach algebra. Under certain conditions that transition probability functions of Markov chains corresponding to evolutionary algorithms satisfy, the authors obtain the convergence rates of the exponential order. Furthermore, they also analyze the characteristics of the conditions which can be met by genetic operators and selection strategies.展开更多
There has been a growing interest in mathematical models to character the evolutionary algorithms. The best-known one of such models is the axiomatic model called the abstract evolutionary algorithm （AEA）, which uni...There has been a growing interest in mathematical models to character the evolutionary algorithms. The best-known one of such models is the axiomatic model called the abstract evolutionary algorithm （AEA）, which unifies most of the currently known evolutionary algorithms and describes the evolution as an abstract stochastic process composed of two fundamental abstract operators： abstract selection and evolution operators. In this paper, we first introduce the definitions of the generalized abstract selection and evolution operators. Then we discuss the characterization of some parameters related to generalized abstract selection and evolution operators. Based on these operators, we finally give the strong convergence of the generalized abstract evolutionary algorithm. The present work provides a big step toward the establishment of a unified theory of evolutionary computation.展开更多
For many real-world multiobjective optimization problems,the evaluations of the objective functions are computationally expensive.Such problems are usually called expensive multiobjective optimization problems(EMOPs)....For many real-world multiobjective optimization problems,the evaluations of the objective functions are computationally expensive.Such problems are usually called expensive multiobjective optimization problems(EMOPs).One type of feasible approaches for EMOPs is to introduce the computationally efficient surrogates for reducing the number of function evaluations.Inspired from ensemble learning,this paper proposes a multiobjective evolutionary algorithm with an ensemble classifier(MOEA-EC)for EMOPs.More specifically,multiple decision tree models are used as an ensemble classifier for the pre-selection,which is be more helpful for further reducing the function evaluations of the solutions than using single inaccurate model.The extensive experimental studies have been conducted to verify the efficiency of MOEA-EC by comparing it with several advanced multiobjective expensive optimization algorithms.The experimental results show that MOEA-EC outperforms the compared algorithms.展开更多
There has been a growing interest in mathematical models to character the evolutionary algorithms. The best-known one of such models is the axiomatic model colled the abstract evolutionary algorithm. In this paper, we...There has been a growing interest in mathematical models to character the evolutionary algorithms. The best-known one of such models is the axiomatic model colled the abstract evolutionary algorithm. In this paper, we first introduce the definitions of the abhstract selection and evolution operators, and that of the abstract evolutionary algorithm, which describes the evolution as an abstract stochastic process composed of these two fundamental abstract operators. In particular, a kind of abstract evolutionary algorithms based on a special selection mechansim is discussed. According to the sorting for the state space, the properties of the single step transition matrix for the algorithm are anaylzed. In the end, we prove that the limit probability distribution of the Markov chains exists. The present work provides a big step toward the establishment of a unified theory of evolutionary computation.展开更多
Aimed at the real-time forward kinematics solving problem of Stewart parallel manipulator in the control course, a mixed algorithm combining immune evolutionary algorithm and numerical iterative scheme is proposed. Fi...Aimed at the real-time forward kinematics solving problem of Stewart parallel manipulator in the control course, a mixed algorithm combining immune evolutionary algorithm and numerical iterative scheme is proposed. Firstly taking advantage of simpleness of inverse kinematics, the forward kinematics is transformed to an optimal problem. Immune evolutionary algorithm is employed to find approximate solution of this optimal problem in manipulator＇s workspace. Then using above solution as iterative initialization, a speedy numerical iterative scheme is proposed to get more precise solution. In the manipulator running course, the iteration initialization can be selected as the last period position and orientation. Because the initialization is closed to correct solution, solving precision is high and speed is rapid enough to satisfy real-time requirement. This mixed forward kinematics algorithm is applied to real Stewart parallel manipulator in the real-time control course. The examination result shows that the algorithm is very efficient and practical.展开更多
传统的Pareto支配关系在高维目标空间存在固有缺陷,而一些改进的支配方法在平衡高维目标解群的收敛性与多样性上尚有提升空间.基于此,提出一种参考向量关联区域(小生境)自动缩减的支配关系A2R(dominance relation based on the Automati...传统的Pareto支配关系在高维目标空间存在固有缺陷,而一些改进的支配方法在平衡高维目标解群的收敛性与多样性上尚有提升空间.基于此,提出一种参考向量关联区域(小生境)自动缩减的支配关系A2R(dominance relation based on the Automatically reduced region Associated with the Reference vector).该支配方法在进化全过程中逐代缩减小生境规模,从而实现收敛性与多样性自动平衡,而且不引入额外参数.另外,提出利用基于L_(p)-范式(p=1/M,M为目标数)的拥挤距离度量高维目标解群的多样性.将上述两种策略嵌入到经典的NSGA-II(Nondominated Sorting Genetic Algorithm II)框架,设计一种基于A2R支配关系的高维多目标进化算法MaOEA/A2R(Many-Objective Evolutionary Algorithm base on A2R).该算法与其他5种代表性的高维多目标进化算法一同在5-、10-、15-和20-目标的DTLZ(benchmark MOP proposed by Deb,Thiele,Lau-manns,and Zitzler)和WFG(benchmark MOP pro-posed by Walking Fish Group)基准测试问题上进行IGD(Inverted Generational Distance)和HV(Hyper Volume)性能测试.结果表明,MaOEA/A2R算法总体上具有较好的收敛性和多样性.由此表明,MaOEA/A2R是一种颇具前景的高维多目标进化算法.展开更多
文摘Methods of improving seismic event locations were investigated as part of a research study aimed at reducing ground control safety hazards. Seismic event waveforms collected with a 23-station three-dimensional sensor array during longwall coal mining provide the data set used in the analyses. A spatially variable seismic velocity model is constructed using seismic event sources in a passive tomographic method. The resulting three-dimensional velocity model is used to relocate seismic event positions. An evolutionary optimization algorithm is implemented and used in both the velocity model development and in seeking improved event location solutions. Results obtained using the different velocity models are compared. The combination of the tomographic velocity model development and evolutionary search algorithm provides improvement to the event locations.
基金supported by the Science and Technology Plan Projects of Sichuan Province of China under Grant No.2008GZ0003the Key Technologies R & D Program of Sichuan Province of China under Grant No.2008SZ0100
文摘Feature selection is one of the important topics in text classification. However, most of existing feature selection methods are serial and inefficient to be applied to massive text data sets. In this case, a feature selection method based on parallel collaborative evolutionary genetic algorithm is presented. The presented method uses genetic algorithm to select feature subsets and takes advantage of parallel collaborative evolution to enhance time efficiency, so it can quickly acquire the feature subsets which are more representative. The experimental results show that, for accuracy ratio and recall ratio, the presented method is better than information gain, x2 statistics, and mutual information methods; the consumed time of the presented method with only one CPU is inferior to that of these three methods, but the presented method is supe rior after using the parallel strategy.
基金supported by the Fundamental Research Funds for the Central Universities (No.3122020072)the Multi-investment Project of Tianjin Applied Basic Research(No.23JCQNJC00250)。
文摘A hybrid identification model based on multilayer artificial neural networks(ANNs) and particle swarm optimization(PSO) algorithm is developed to improve the simultaneous identification efficiency of thermal conductivity and effective absorption coefficient of semitransparent materials.For the direct model,the spherical harmonic method and the finite volume method are used to solve the coupled conduction-radiation heat transfer problem in an absorbing,emitting,and non-scattering 2D axisymmetric gray medium in the background of laser flash method.For the identification part,firstly,the temperature field and the incident radiation field in different positions are chosen as observables.Then,a traditional identification model based on PSO algorithm is established.Finally,multilayer ANNs are built to fit and replace the direct model in the traditional identification model to speed up the identification process.The results show that compared with the traditional identification model,the time cost of the hybrid identification model is reduced by about 1 000 times.Besides,the hybrid identification model remains a high level of accuracy even with measurement errors.
文摘To solve aircraft arrival sequencing and scheduling problems,and improve the typical predatory search algorithm（PSA）,an innovative PSA is developed.The new PSA uses variable constraints of local search and global search to avoid falling into local optimal solutions and the degeneration of solutions.To test the performance of new PSA,a case study with ten arriving flights and two runways is performed.Test results show that the new PSA performs much better than typical PSA and genetic algorithm（GA）in the aspects of the rate of gaining optimal solutions and the computational time.
文摘A methodology for the selection of the optimal land uses of the reclamation of mined areas is proposed. It takes into consideration several multi-nature criteria and constraints, including spatial constrains related to the permissible land uses in certain parts of the mined area. The methodology combines desirability functions and evolution searching algorithms for selection of the optimal reclamation scheme. Its application for the reclamation planning of the Amynteon lignite surface mine in Greece indicated that it handles effectively spatial and non-spatial constraints and incorporates easily the decision-makers preferences regarding the reclamation strategy in the optimization procedure.
基金marine research institute (MRC) of AUT for some financial support of this project
文摘This study presents a numerical method for optimizing hull form in calm water with respect to total drag which contains a viscous drag and a wave drag. The ITTC 1957 model-ship correlation line was used to predict frictional drag and the corrected linearized thin-ship theory was employed to estimate the wave drag The evolution strategy （ES） which is a member of the evolutionary algorithms （EAs） family obtains an optimum hull form by considering some design constraints. Standard Wigley hull is considered as an initial hull in optimization procedures for two test cases and new hull forms were achieved at Froude numbers 0.24, 0.316 and 0.408. In one case the ES technique was ran for the initial hull form, where the main dimensions were fixed and the only variables were the hull offsets. In the other case in addition to hull offsets, the raain dimensions were considered as variables that are optimized simultaneously. The numerical results of optimization procedure demonstrate that the optimized hull forms yield a reduction in total drag.
基金This work is supported by the National Natural Science Foundation of China under Grant 52274057,52074340 and 51874335the Major Scientific and Technological Projects of CNPC under Grant ZD2019-183-008the Science and Technology Support Plan for Youth Innovation of University in Shandong Province under Grant 2019KJH002,111 Project under Grant B08028.
文摘Production optimization has gained increasing attention from the smart oilfield community because it can increase economic benefits and oil recovery substantially.While existing methods could produce high-optimality results,they cannot be applied to real-time optimization for large-scale reservoirs due to high computational demands.In addition,most methods generally assume that the reservoir model is deterministic and ignore the uncertainty of the subsurface environment,making the obtained scheme unreliable for practical deployment.In this work,an efficient and robust method,namely evolutionaryassisted reinforcement learning(EARL),is proposed to achieve real-time production optimization under uncertainty.Specifically,the production optimization problem is modeled as a Markov decision process in which a reinforcement learning agent interacts with the reservoir simulator to train a control policy that maximizes the specified goals.To deal with the problems of brittle convergence properties and lack of efficient exploration strategies of reinforcement learning approaches,a population-based evolutionary algorithm is introduced to assist the training of agents,which provides diverse exploration experiences and promotes stability and robustness due to its inherent redundancy.Compared with prior methods that only optimize a solution for a particular scenario,the proposed approach trains a policy that can adapt to uncertain environments and make real-time decisions to cope with unknown changes.The trained policy,represented by a deep convolutional neural network,can adaptively adjust the well controls based on different reservoir states.Simulation results on two reservoir models show that the proposed approach not only outperforms the RL and EA methods in terms of optimization efficiency but also has strong robustness and real-time decision capacity.
基金supported by Natural Science Foundation of Beijing Municipality (Beijing Natural Science Foundation)(No.7191005)。
文摘Compton camera-based prompt gamma(PG) imaging has been proposed for range verification during proton therapy. However, a deviation between the PG and dose distributions, as well as the difference between the reconstructed PG and exact values, limit the effectiveness of the approach in accurate range monitoring during clinical applications. The aim of the study was to realize a PG-based dose reconstruction with a Compton camera, thereby further improving the prediction accuracy of in vivo range verification and providing a novel method for beam monitoring during proton therapy. In this paper, we present an approach based on a subset-driven origin ensemble with resolution recovery and a double evolutionary algorithm to reconstruct the dose depth profile(DDP) from the gamma events obtained by a cadmium-zinc-telluride Compton camera with limited position and energy resolution. Simulations of proton pencil beams with clinical particle rate irradiating phantoms made of different materials and the CT-based thoracic phantom were used to evaluate the feasibility of the proposed method. The results show that for the monoenergetic proton pencil beam irradiating homogeneous-material box phantom,the accuracy of the reconstructed DDP was within 0.3 mm for range prediction and within 5.2% for dose prediction. In particular, for 1.6-Gy irradiation in the therapy simulation of thoracic tumors, the range deviation of the reconstructed spreadout Bragg peak was within 0.8 mm, and the relative dose deviation in the peak area was less than 7% compared to the exact values. The results demonstrate the potential and feasibility of the proposed method in future Compton-based accurate dose reconstruction and range verification during proton therapy.
文摘Multi-objective evolutionary algorithms(MOEAs) are typically used to optimize two or three objectives in the accelerator field and perform well. However, the performance of these algorithms may severely deteriorate when the optimization objectives for an accelerator are equal to or greater than four. Recently, many-objective evolutionary algorithms(MaOEAs)that can solve problems with four or more optimization objectives have received extensive attention. In this study, two diffraction-limited storage ring(DLSR) lattices of the Extremely Brilliant Source(ESRF-EBS) type with different energies were designed and optimized using three MaOEAs and a widely used MOEA. The initial population was found to have a significant impact on the performance of the algorithms and was carefully studied. The performances of the four algorithms were compared, and the results demonstrated that the grid-based evolutionary algorithm(GrEA) had the best performance.Ma OEAs were applied in many-objective optimization of DLSR lattices for the first time, and lattices with natural emittances of 116 and 23 pm·rad were obtained at energies of 2 and 6 GeV, respectively, both with reasonable dynamic aperture and local momentum aperture(LMA). This work provides a valuable reference for future many-objective optimization of DLSRs.
文摘Evolutionary algorithm is applied for distillation separation sequence optimization synthesis problems with combination explosion. The binary tree data structure is used to describe the distillation separation sequence, and it is directly applied as the coding method. Genetic operators, which ensure to prohibit illegal filial generations completely, are designed by using the method of graph theory. The crossover operator based on a single parent or two parents is designed successfully. The example shows that the average ratio of search space from evolutionary algorithm with two-parent genetic operation is lower, whereas the rate of successful minimizations from evolutionary algorithm with single parent genetic operation is higher.
文摘A software defined networking(SDN) system has a logically centralized control plane that maintains a global network view and enables network-wide management, optimization, and innovation. Network-wide management and optimization problems are typicallyvery complex with a huge solution space, large number of variables, and multiple objectives. Heuristic algorithms can solve theseproblems in an acceptable time but are usually limited to some particular problem circumstances. On the other hand, evolutionaryalgorithms(EAs), which are general stochastic algorithms inspired by the natural biological evolution and/or social behavior of species, can theoretically be used to solve any complex optimization problems including those found in SDNs. This paper reviewsfour types of EAs that are widely applied in current SDNs: Genetic Algorithms(GAs), Particle Swarm Optimization(PSO), Ant Colony Optimization(ACO), and Simulated Annealing(SA) by discussing their techniques, summarizing their representative applications, and highlighting their issues and future works. To the best of our knowledge, our work is the first that compares the tech-niques and categorizes the applications of these four EAs in SDNs.
基金This work is supported by the National Natural Science Foundation of ChinaVisiting Scholar Foundation of Key Lab, in Univers
文摘This paper discusses the convergence rates about a class of evolutionary algorithms in general search spaces by means of the ergodic theory in Markov chain and some techniques in Banach algebra. Under certain conditions that transition probability functions of Markov chains corresponding to evolutionary algorithms satisfy, the authors obtain the convergence rates of the exponential order. Furthermore, they also analyze the characteristics of the conditions which can be met by genetic operators and selection strategies.
基金Supported by the National Science Foundation of China(60133010)Supported by the Science Foundation of Henan Province(2000110019)
文摘There has been a growing interest in mathematical models to character the evolutionary algorithms. The best-known one of such models is the axiomatic model called the abstract evolutionary algorithm （AEA）, which unifies most of the currently known evolutionary algorithms and describes the evolution as an abstract stochastic process composed of two fundamental abstract operators： abstract selection and evolution operators. In this paper, we first introduce the definitions of the generalized abstract selection and evolution operators. Then we discuss the characterization of some parameters related to generalized abstract selection and evolution operators. Based on these operators, we finally give the strong convergence of the generalized abstract evolutionary algorithm. The present work provides a big step toward the establishment of a unified theory of evolutionary computation.
文摘For many real-world multiobjective optimization problems,the evaluations of the objective functions are computationally expensive.Such problems are usually called expensive multiobjective optimization problems(EMOPs).One type of feasible approaches for EMOPs is to introduce the computationally efficient surrogates for reducing the number of function evaluations.Inspired from ensemble learning,this paper proposes a multiobjective evolutionary algorithm with an ensemble classifier(MOEA-EC)for EMOPs.More specifically,multiple decision tree models are used as an ensemble classifier for the pre-selection,which is be more helpful for further reducing the function evaluations of the solutions than using single inaccurate model.The extensive experimental studies have been conducted to verify the efficiency of MOEA-EC by comparing it with several advanced multiobjective expensive optimization algorithms.The experimental results show that MOEA-EC outperforms the compared algorithms.
基金Supported by the National Science Foundation of China(60133010)Supported by the Science Foundation of Henan Province(2000110019)
文摘There has been a growing interest in mathematical models to character the evolutionary algorithms. The best-known one of such models is the axiomatic model colled the abstract evolutionary algorithm. In this paper, we first introduce the definitions of the abhstract selection and evolution operators, and that of the abstract evolutionary algorithm, which describes the evolution as an abstract stochastic process composed of these two fundamental abstract operators. In particular, a kind of abstract evolutionary algorithms based on a special selection mechansim is discussed. According to the sorting for the state space, the properties of the single step transition matrix for the algorithm are anaylzed. In the end, we prove that the limit probability distribution of the Markov chains exists. The present work provides a big step toward the establishment of a unified theory of evolutionary computation.
文摘Aimed at the real-time forward kinematics solving problem of Stewart parallel manipulator in the control course, a mixed algorithm combining immune evolutionary algorithm and numerical iterative scheme is proposed. Firstly taking advantage of simpleness of inverse kinematics, the forward kinematics is transformed to an optimal problem. Immune evolutionary algorithm is employed to find approximate solution of this optimal problem in manipulator＇s workspace. Then using above solution as iterative initialization, a speedy numerical iterative scheme is proposed to get more precise solution. In the manipulator running course, the iteration initialization can be selected as the last period position and orientation. Because the initialization is closed to correct solution, solving precision is high and speed is rapid enough to satisfy real-time requirement. This mixed forward kinematics algorithm is applied to real Stewart parallel manipulator in the real-time control course. The examination result shows that the algorithm is very efficient and practical.
文摘传统的Pareto支配关系在高维目标空间存在固有缺陷,而一些改进的支配方法在平衡高维目标解群的收敛性与多样性上尚有提升空间.基于此,提出一种参考向量关联区域(小生境)自动缩减的支配关系A2R(dominance relation based on the Automatically reduced region Associated with the Reference vector).该支配方法在进化全过程中逐代缩减小生境规模,从而实现收敛性与多样性自动平衡,而且不引入额外参数.另外,提出利用基于L_(p)-范式(p=1/M,M为目标数)的拥挤距离度量高维目标解群的多样性.将上述两种策略嵌入到经典的NSGA-II(Nondominated Sorting Genetic Algorithm II)框架,设计一种基于A2R支配关系的高维多目标进化算法MaOEA/A2R(Many-Objective Evolutionary Algorithm base on A2R).该算法与其他5种代表性的高维多目标进化算法一同在5-、10-、15-和20-目标的DTLZ(benchmark MOP proposed by Deb,Thiele,Lau-manns,and Zitzler)和WFG(benchmark MOP pro-posed by Walking Fish Group)基准测试问题上进行IGD(Inverted Generational Distance)和HV(Hyper Volume)性能测试.结果表明,MaOEA/A2R算法总体上具有较好的收敛性和多样性.由此表明,MaOEA/A2R是一种颇具前景的高维多目标进化算法.
