This article examines the effect of different configuration issues of the Multiobjective evolutionary algorithms on the efficient frontier formulation for the constrained portfolio optimization problem. We present the...
详细信息
This article examines the effect of different configuration issues of the Multiobjective evolutionary algorithms on the efficient frontier formulation for the constrained portfolio optimization problem. We present the most popular techniques for dealing with the complexities of the constrained portfolio optimization problem and experimentally analyse their strengths and weaknesses. In particular, we examine the efficient incorporation of complex real world constraints into the Multiobjective evolutionary algorithms and their corresponding effect on the efficient frontier formulation for the portfolio optimization problem. Moreover, we examine various constraint-handling approaches for the constrained portfolio optimization problem such as penalty functions and reparation operators and we draw conclusions about the efficacy of the examined approaches. We also examine the effect on the efficient frontier formulation by the application of different genetic operators and the relevant results are analysed. Finally, we address issues related with the various performance metrics that are applied for the evaluation of the derived solutions.
In this study, a single autonomous underwater vehicle (AUV) aims to rendezvous with a submerged leader recovery vehicle through a cluttered and variable operating field. The rendezvous problem is transformed into a No...
详细信息
In this study, a single autonomous underwater vehicle (AUV) aims to rendezvous with a submerged leader recovery vehicle through a cluttered and variable operating field. The rendezvous problem is transformed into a Nonlinear Optimal Control Problem (NOCP) and then numerical solutions are provided. A penalty function method is utilized to combine the boundary conditions, vehicular and environmental constraints with the performance index that is final rendezvous time. Four evolutionary based path planning methods namely Particle Swarm Optimization (PSO), Biogeography-Based Optimization (BBO), Differential Evolution (DE), and Firefly Algorithm (FA) are employed to establish a reactive planner module and provide a numerical solution for the proposed NOCP. The objective is to synthesize and analyze the performance and capability of the mentioned methods for guiding an AUV from an initial loitering point toward the rendezvous through a comprehensive simulation study. The proposed planner module entails a heuristic for refining the path considering situational awareness of environment, encompassing static and dynamic obstacles within a spatiotemporal current fields. The planner thus needs to accommodate the unforeseen changes in the operating field such as emergence of unpredicted obstacles or variability of current field and turbulent regions. The simulation results demonstrate the inherent robustness and efficiency of the proposed planner for enhancing a vehicle's autonomy so as to enable it to reach the desired rendezvous. The advantages and shortcoming of all utilized methods are also presented based on the obtained results. (C) 2017 Elsevier B.V. All rights reserved.
Selection functions enable evolutionary algorithms (EAs) to apply selection pressure to a population of individuals, by regulating the probability that an individual's genes survive, typically based on fitness. Va...
详细信息
Selection functions enable evolutionary algorithms (EAs) to apply selection pressure to a population of individuals, by regulating the probability that an individual's genes survive, typically based on fitness. Various conventional fitness based selection functions exist, each providing a unique method of selecting individuals based on their fitness, fitness ranking within the population, and/or various other factors. However, the full space of selection algorithms is only limited by max algorithm size, and each possible selection algorithm is optimal for some EA configuration applied to a particular problem class. Therefore, improved performance is likely to be obtained by tuning an EA's selection algorithm to the problem at hand, rather than employing a conventional selection function. This thesis details an investigation of the extent to which performance can be improved by tuning the selection algorithm. We do this by employing a Hyper-heuristic to explore the space of algorithms which determine the methods used to select individuals from the population. We show, with both a conventional EA and a Covariance Matrix Adaptation evolutionary Strategy, the increase in performance obtained with a tuned selection algorithm, versus conventional selection functions. Specifically, we measure performance on instances from several benchmark problem classes, including separate testing instances to show generalization of the improved performance. This thesis consists of work that was presented at the Genetic and evolutionary Computation Conference (GECCO) in 2018, as well as work that will be submitted to GECCO in 2019.
During millions of years, nature has developed patterns and processes with interesting characteristics. They have been used as inspiration for a significant number of innovative models that can be extended to solve co...
详细信息
During millions of years, nature has developed patterns and processes with interesting characteristics. They have been used as inspiration for a significant number of innovative models that can be extended to solve complex engineering and mathematical problems. One of the most famous patterns present in nature is the Golden Section (GS). It defines an especial proportion that allows the adequate formation, selection, partition, and replication in several natural phenomena. On the other hand, evolutionary algorithms (EAs) are stochastic optimization methods based on the model of natural evolution. One important process in these schemes is the operation of selection which exerts a strong influence on the performance of their search strategy. Different selection methods have been reported in the literature. However, all of them present an unsatisfactory performance as a consequence of the deficient relations between elitism and diversity of their selection procedures. In this paper, a new selection method for evolutionary computation algorithms is introduced. In the proposed approach, the population is segmented into several groups. Each group involves a certain number of individuals and a probability to be selected, which are determined according to the GS proportion. Therefore, the individuals are divided into categories where each group contains individual with similar quality regarding their fitness values. Since the possibility to choose an element inside the group is the same, the probability of selecting an individual depends exclusively on the group from which it belongs. Under these conditions, the proposed approach defines a better balance between elitism and diversity of the selection strategy. Numerical simulations show that the proposed method achieves the best performance over other selection algorithms, in terms of its solution quality and convergence speed. (C) 2018 Elsevier Ltd. All rights reserved.
In this paper, two universal reinforcement learning methods are considered to solve the problem of maximum power point tracking for photovoltaics. Both methods exhibit fast achievement of the MPP under varying environ...
详细信息
In this paper, two universal reinforcement learning methods are considered to solve the problem of maximum power point tracking for photovoltaics. Both methods exhibit fast achievement of the MPP under varying environmental conditions and are applicable in different PV systems. The only required knowledge of the PV system are the open-circuit voltage, the short-circuit current and the maximum power, all under STC, which are always provided by the manufacturer. Both methods are compared to a Fuzzy Logic Controller and the universality of the proposed methods is highlighted. After the implementation and the validation of proper performance of both methods, two evolutionary optimization algorithms (Big Bang-Big Crunch and Genetic Algorithm) are applied. The results demonstrate that both methods achieve higher energy production and in both methods the time for tracking the MPP is reduced, after the application of both evolutionary algorithms.
Structural damage identification based on finite element (FE) model updating has been a research direction of increasing interest over the last decade in the mechanical, civil, aerospace, etc., engineering fields. Var...
详细信息
Structural damage identification based on finite element (FE) model updating has been a research direction of increasing interest over the last decade in the mechanical, civil, aerospace, etc., engineering fields. Various studies have addressed direct, sensitivity-based, probabilistic, statistical, and iterative methods for updating FE models for structural damage identification. In contrast, evolutionary algorithms (EAs) are a type of modern method for FE model updating. Structural damage identification using FE model updating by evolutionary algorithms is an active research focus in progress but lacking a comprehensive survey. In this situation, this study aims to present a review of critical aspects of structural damage identification using evolutionary algorithm-based FE model updating. First, a theoretical background including the structural damage detection problem and the various types of FE model updating approaches is illustrated. Second, the various residuals between dynamic characteristics from FE model and the corresponding physical model, used for constructing the objective function for tracking damage, are summarized. Third, concerns regarding the selection of parameters for FE model updating are investigated. Fourth, the use of evolutionary algorithms to update FE models for damage detection is examined. Fifth, a case study comparing the applications of two single-objective EAs and one multi-objective EA for FE model updating-based damage detection is presented. Finally, possible research directions for utilizing evolutionary algorithm-based FE model updating to solve damage detection problems are recommended. This study should help researchers find crucial points for further exploring theories, methods, and technologies of evolutionary algorithm-based FE model updating for structural damage detection.
This paper investigates an optimized design of newly developed nonlinear controller called finite-time convergent controller to a third-order boiler-turbine dynamics. The third-order boiler-turbine dynamics only inclu...
详细信息
This paper investigates an optimized design of newly developed nonlinear controller called finite-time convergent controller to a third-order boiler-turbine dynamics. The third-order boiler-turbine dynamics only includes highly nonlinear and critical parameters of thermal plant like drum pressure, electric power and drum level;the design of controller is always a complicated task. The present work explores the possibility of application of newly developed finite-time convergent controller to a third-order boiler-turbine dynamics. The novelty of the newly developed finite-time convergent controller is complete utilization of system nonlinearities instead of cancelling or linearizing them. Also, the finite-time convergent controller ensures robustness and fast convergence. To achieve optimal performance, the tuning parameters involved in finite-time convergent controller have been optimized using evolutionary algorithm techniques. To validate the control performance of an optimized nonlinear controller design, simulations have been conducted using various evolutionary algorithm techniques and the results are reported as various case studies. To compare the performance of proposed optimized finite-time convergent controller, the fuzzy logic controller has also been designed using ANFIS for boiler-turbine system and the results are reported.
The runtime of an evolutionary algorithm can be reduced by increasing the number of parallel evaluations. However, increasing the number of parallel evaluations can also result in wasted computational effort since the...
详细信息
The runtime of an evolutionary algorithm can be reduced by increasing the number of parallel evaluations. However, increasing the number of parallel evaluations can also result in wasted computational effort since there is a greater probability of creating solutions that do not contribute to convergence towards the global optimum. A trade-off, therefore, arises between the runtime and computational effort for different levels of parallelization of an evolutionary algorithm. When the computational effort is translated into cost, the trade-off can be restated as runtime versus cost. This trade-off is particularly relevant for cloud computing environments where the computing resources can be exactly matched to the level of parallelization of the algorithm, and the cost is proportional to the runtime and how many instances that are used. This paper empirically investigates this trade-off for two different evolutionary algorithms, NSGA-II and differential evolution (DE) when applied to a multi-objective discrete-event simulation (DES) problem. Both generational and steady-state asynchronous versions of both algorithms are included. The approach is to perform parameter tuning on a simplified version of the DES model. A subset of the best configurations from each tuning experiment is then evaluated on a cloud computing platform. The results indicate that, for the included DES problem, the steady-state asynchronous version of each algorithm provides a better runtime versus cost trade-off than the generational versions and that DE outperforms NSGA-II.
The profitability of the livestock industry largely depends on cost-effective feed ration formulation as feed accounts for between 60 and 80% of production costs. Therefore, feed formulation is a recurring problem for...
详细信息
The profitability of the livestock industry largely depends on cost-effective feed ration formulation as feed accounts for between 60 and 80% of production costs. Therefore, feed formulation is a recurring problem for breeders. In addition, the presence of linear and non-linear constraints, and multiple possible combinations that are subject to upsurge makes the formulation of feed a Non-deterministic Polynomial-time hard (NP-hard) problem. Generally, feed formulation is done by specifying the nutritional requirements as rigid constraints and an algorithm attempts to find a feasible cost-effective formulation. However, relaxing the constraints can sometimes provide a huge reduction in the cost of feed while not seriously affecting the economic performance of the livestock. This entails the development of a feed formulation software that has an inbuilt mechanism to enable relaxation to the constraints based on the users' necessities. Accordingly, the problem formulation and the optimization algorithm should facilitate this. We modified the conventional problem formulation with a tolerance parameter (as a percentage of the actual value) to accommodate the relaxation of constraints. We solved this problem with differential evolution, a variant of evolutionary algorithms, which are good for handling NP-hard problems. In addition, the relaxation of the constraints was done in an interactive way using the proposed method without penalties. In other words, the proposed method is flexible and possesses the ability to search for a feasible and least-cost solution if available or otherwise, the best solution and finds the suitable feed components to be used in ration formulation at an optimal cost depending on the nutrient requirements and growth stage of the animal.
The deployment of an unmanned aerial network (UAV-network) for the optimal coverage of ground nodes is an NP-hard problem. This work focuses on the application of a multi-layout multi-subpopulation genetic algorithm (...
详细信息
The deployment of an unmanned aerial network (UAV-network) for the optimal coverage of ground nodes is an NP-hard problem. This work focuses on the application of a multi-layout multi-subpopulation genetic algorithm (MLMPGA) to solve multi-objective coverage problems of UAV-networks. The multi objective deployment is based on a weighted fitness function that takes into account coverage, fault tolerance, and redundancy as relevant factors to optimally place the UAVs. The proposed approach takes advantage of different subpopulations evolving with different layouts. This feature is aimed at reflecting the evolutionary concept of different species adapting to the search space conditions of the multi-objective coverage problem better than single-population genetic algorithms. The proposed multi-subpopulation genetic algorithm is evaluated and compared against single-population genetic algorithm configurations and other well-known meta-heuristic optimization algorithms, such as particle swarm optimization and hill climbing algorithm, under different numbers of ground nodes. The proposed MLMPGA achieves significantly better performance results than the other meta-heuristic algorithms, such as classical genetic algorithms, hill climbing algorithm, and particle swarm optimization, in the vast majority of our simulation scenarios. (C) 2017 Published by Elsevier B.V.
暂无评论