estimation of distribution algorithm (EDA) is a kind of typical model-based evolutionary algorithm (EA). Although possessing competitive advantages in theoretical analysis, current EDAs may encounter premature converg...
详细信息
ISBN:
(纸本)9781509006229
estimation of distribution algorithm (EDA) is a kind of typical model-based evolutionary algorithm (EA). Although possessing competitive advantages in theoretical analysis, current EDAs may encounter premature convergence due to the rapid shrinkage of the search range and the relatively low sampling efficiency. Focusing on continuous EDAs with Gaussian models, this paper proposes a novel probability density estimator which can adaptively enlarge the variances and thus endow EDA with flexible search behavior. For the estimated probability density, a reflecting sampling strategy which can further improve the search efficiency is put forward. With these two algorithmic strategies, a new EDA variant named EDA(ve-rs) is developed. Experimental results on a set of benchmark problems demonstrate that EDA(ve-rs) outperforms conventional EDAs and can produce superior solutions in comparison with some state-oft-he-art EAs.
estimation-of-distributionalgorithms (EDAs) have been applied with quite some success when solving real-valued optimization problems, especially in the case of Black Box Optimization (BBO). Generally, the performance...
详细信息
ISBN:
(纸本)9781450349208
estimation-of-distributionalgorithms (EDAs) have been applied with quite some success when solving real-valued optimization problems, especially in the case of Black Box Optimization (BBO). Generally, the performance of an EDA depends on the match between its driving probability distribution and the landscape of the problem being solved. Because most well-known EDAs, including CMA-ES, NES, and AMaLGaM, use a uni-modal search distribution, they have a high risk of getting trapped in local optima when a problem is multi-modal with a (moderate) number of relatively comparable modes. This risk could potentially be mitigated using niching methods that define multiple regions of interest where separate search distributions govern sub-populations. However, a key question is how to determine a suitable number of niches, especially in BBO. In this paper, we present a novel, adaptive niching approach that determines the niches through hierarchical clustering based on the correlation between the probability densities and fitness values of solutions. We test the performance of a combination of this niching approach with AMaLGaM on both new and well-known niching benchmark problems and find that the new approach properly identifies multiple landscape modes, leading to much better performance on multi-modal problems than with a non-niched, uni-modal EDA.y
This paper presents a set of evolutionary mechanisms embedded on an estimation of distribution algorithm (MITEDA-AC) that performs the synthesis of an analog low pass filter. Analog circuits are modeled with linked li...
详细信息
ISBN:
(纸本)9783319624280;9783319624273
This paper presents a set of evolutionary mechanisms embedded on an estimation of distribution algorithm (MITEDA-AC) that performs the synthesis of an analog low pass filter. Analog circuits are modeled with linked lists in order to represent and evolve both, topology and sizing. The developed representation mechanism ensures that generated circuits be feasible, and in order to reduce the gap between real circuits and those evolvable, the concept of preferred values was included on representation and generation mechanisms. The algorithm interacts with SPICE to performance evaluation of each individual in the population. MITEDA-AC was inspired by the COMIT because like this, it uses bivariate probability distributions to generate the optimal dependency tree, but without local optimizers. Features integrated in the learning mechanism of this evolvable algorithm, were the number of capacitors, resistors and inductors included in each circuit of the population. This paper describes the algorithm and discusses its results.
The estimation of distribution algorithm(EDA) is a new evolutionary algorithm developed as an alternative to the traditional genetic algorithm (GA). The EDA guides the search by avoiding the crossover and mutation ope...
详细信息
The estimation of distribution algorithm(EDA) is a new evolutionary algorithm developed as an alternative to the traditional genetic algorithm (GA). The EDA guides the search by avoiding the crossover and mutation operators of the GA in favor of building and sampling probabilistic distributions of promising candidate solutions. By increasing the probability of generating solutions with better fitness values, the EDA locates the region of the global optimum or its accurate approximation. In this study, EDA was used to calibrate the parameters of the soil and water assessment tool hydrologic model for the Xunhe River Basin in China. The EDA was compared with three other algorithms: (1) the Multistart Local Metric Stochastic Radial Basis Function algorithm (a surrogate optimization method), (2) the Shuffled Complex Evolution algorithm, and (3) the GA. Four metrics are presented to assess the performance of the algorithms: (1) efficiency in terms of the average best objective function value in a limited number of function evaluations, (2) variability in terms of standard deviation and the box plot, (3) reliability in terms of the empirical cumulative distribution function, and (4) accuracy in terms of the Nash-Sutcliffe efficiency coefficient and overall volume error. Results indicated that the EDA is more efficient and could provide more accurate solutions with a relatively high probability, at least for this case study. (C) 2016 American Society of Civil Engineers.
In order to improve the efficiency of operating rooms,reduce the costs for hospitals and improve the level of service qualities, a scheduling method was developed based on an estimation of distribution algorithm（ EDA...
详细信息
In order to improve the efficiency of operating rooms,reduce the costs for hospitals and improve the level of service qualities, a scheduling method was developed based on an estimation of distribution algorithm（ EDA）. First, a scheduling problem domain is described. Based on assignment constraints and resource capacity constraints, the mathematical programming models are set up with an objective function to minimize the system makespan. On the basis of the descriptions mentioned above, a solution policy of generating feasible scheduling solutions is established. Combined with the specific constraints of operating theatres, the EDA-based algorithm is put forward to solve scheduling problems. Finally, simulation experiments are designed to evaluate the scheduling method. The orthogonal table is chosen to determine the parameters in the proposed method. Then the genetic algorithm and the particle swarm optimization algorithm are chosen for comparison with the EDA-based algorithm, and the results indicate that the proposed method can decrease the makespan of the surgical system regardless of the size of operations. Moreover, the computation time of the EDA-based algorithm is only approximately 5 s when solving the large scale problems, which means that the proposed algorithm is suitable for carrying out an on-line scheduling optimization of the patients.
In manual order-picking systems such as picker-toparts, order pickers walk through a warehouse in order to pick up articles required by customers. Order batching consists of combining these customer orders into pickin...
详细信息
In manual order-picking systems such as picker-toparts, order pickers walk through a warehouse in order to pick up articles required by customers. Order batching consists of combining these customer orders into picking orders. In online batching, customer orders arrive throughout the scheduling. This paper considers an online order-batching problem in which the turnover time of all customer orders has to be minimized, i.e., the time period between the arrival time of the customer order and its completion time. A continuous estimation of distribution algorithm-based approach is proposed and developed to solve the problem and implement the solution. Using this approach, the warehouse performance can be noticeably improved with a substantial reduction in the average turnover time of a set of customer orders.
作者：
Wang, K.Choi, S. H.Lu, H.Wuhan Univ
Econ & Management Sch Dept Management Sci & Engn Wuhan 430072 Peoples R China Univ Hong Kong
Dept Ind & Mfg Syst Engn Hong Kong Hong Kong Peoples R China Wuhan Univ Technol
Sch Logist Engn Dept Logist Management Wuhan 430070 Peoples R China
The permutation flowshop scheduling problem (PFSP) is NP-complete and tends to be more complicated when considering stochastic uncertainties in the real-world manufacturing environments. In this paper, a two-stage sim...
详细信息
The permutation flowshop scheduling problem (PFSP) is NP-complete and tends to be more complicated when considering stochastic uncertainties in the real-world manufacturing environments. In this paper, a two-stage simulation-based hybrid estimation of distribution algorithm (TSSB-HEDA) is presented to schedule the permutation flowshop under stochastic processing times. To deal with processing time uncertainty, TSSB-HEDA evaluates candidate solutions using a novel two-stage simulation model (TSSM). This model first adopts the regression-based meta-modelling technique to determine a number of promising candidate solutions with less computation cost, and then uses a more accurate but time-consuming simulator to evaluate the performance of these selected ones. In addition, to avoid getting trapped into premature convergence, TSSB-HEDA employs both the probabilistic model of EDA and genetic operators of genetic algorithm (GA) to generate the offspring individuals. Enlightened by the weight training process of neural networks, a self-adaptive learning mechanism (SALM) is employed to dynamically adjust the ratio of offspring individuals generated by the probabilistic model. Computational experiments on Taillard's benchmarks show that TSSB-HEDA is competitive in terms of both solution quality and computational performance. (C) 2015 Elsevier Ltd. All rights reserved.
A multi-carpooling model is proposed for the multi-vehicle carpooling problem in distributed parallel computing environment. A two-stage stochastic optimization of the estimation of distribution algorithm solves the o...
详细信息
ISBN:
(纸本)9781509016990
A multi-carpooling model is proposed for the multi-vehicle carpooling problem in distributed parallel computing environment. A two-stage stochastic optimization of the estimation of distribution algorithm solves the optimum of the multi-carpooling problem with a carpooling probabilistic matrix. A ridable matrix initiates the carpooling probabilistic matrix, and the carpooling probabilistic matrix continues updating during the optimization. The carpooling model mines efficient and compromised ridesharing routes for shared riders by the optimization iterations. Experimental results indicate that the carpooling model has the characteristics of effective and efficient traffic including shorter waiting time, more passenger load, and less average riding distance.
As the last process of the semiconductor fabrication, the final testing is crucial to guarantee the quality of the integrated circuit products. The semiconductor final testing scheduling problem (SFTSP) is of great si...
详细信息
As the last process of the semiconductor fabrication, the final testing is crucial to guarantee the quality of the integrated circuit products. The semiconductor final testing scheduling problem (SFTSP) is of great significance to the efficiency of the semiconductor companies. To find satisfactory solutions within reasonable computational time, the intelligent manufacturing scheduling based on the meta-heuristic methods has become a common approach. In this paper, a hybrid estimation of distribution algorithm (HEDA) is proposed to solve the SFTSP. First, novel encoding and decoding methods are proposed to map from the solution space to the schedule space effectively. Second, a probability model that describes the distribution of the solution space is built to generate the new individuals of the population. Third, a mechanism is used to update the parameters of the probability model with the superior solutions at every generation. Furthermore, to enhance the exploitation ability of the algorithm, a local search procedure is hybridized to find neighbor solutions of the promising individuals obtained by sampling the probability model. In addition, the influence of parameters is investigated based on Taguchi method of design-of-experiment, and a set of suitable parameters is suggested. Finally, numerical simulation based on some benchmark instances is carried out. The comparisons between the HEDA and some existing algorithms demonstrate the effectiveness of the proposed HEDA in solving the SFTSP.
The flexible jobshop scheduling problem permits the operation of each job to be processed by more than one machine. The configuration mentioned generally seeks to minimize the completion time of all jobs known in the ...
详细信息
The flexible jobshop scheduling problem permits the operation of each job to be processed by more than one machine. The configuration mentioned generally seeks to minimize the completion time of all jobs known in the literature as 'makespan'. We propose an estimation of distribution algorithm for Sequencing, AEDS for simplicity and functionality. The AEDS attempts to find a relationship or interaction between the input variables, jobs, operations and shifts to optimize the output variable of real manufacturing processes, the makespan. In this sense the AEDS algorithm is used to guide the search and to solve the problem. In the algorithm, three graphical models were used to find better solutions. To set off-duty hours for operators before starting their activities in each shift as an input parameter and its development through the AEDS algorithm is a novelty of this research on the current research work. The comparison between AEDS and a genetic algorithm shows the effectiveness of AEDS solving the problem statement. Using the AEDS proposed, the performance Of real manufacturing processes can be improved significantly when different machines are assigned to different schedules.
暂无评论