An adaptive genetic algorithm with diversity-guided mutation and its global convergence property

An adaptive genetic algorithm with diversity-guided mutation, which combines adaptive probabilities of crossover and mutation was proposed. By means of homogeneous finite Markov chains, it is proved that adaptive genetic algorithm with diversity-guided mutation and genetic algorithm with diversity-guided mutation converge to the global optimum if they maintain the best solutions, and the convergence of adaptive genetic algorithms with adaptive probabilities of crossover and mutation was studied. The performances of the above algorithms in optimizing several unimodal and multimodal functions were compared. The results show that for multimodal functions the average convergence generation of the adaptive genetic algorithm with diversity-guided mutation is about 900 less than that of (adaptive) genetic algorithm with adaptive probabilities and genetic algorithm with diversity-guided mutation, and the adaptive genetic algorithm with diversity-guided mutation does not lead to premature convergence. It is also shown that the better balance between overcoming premature convergence and quickening convergence speed can be gotten.

Adaptive immune-genetic algorithm for global optimization to multivariable function

An adaptive immune-genetic algorithm （AIGA） is proposed to avoid premature convergence and guarantee the diversity of the population. Rapid immune response （secondary response）, adaptive mutation and density operators in the AIGA are emphatically designed to improve the searching ability, greatly increase the converging speed, and decrease locating the local maxima due to the premature convergence. The simulation results obtained from the global optimization to four multivariable and multi-extreme functions show that AIGA converges rapidly, guarantees the diversity, stability and good searching ability.

Two-Phase Genetic Algorithm Applied in the Optimization of Multi-Modal Function

This paper presents a two-phase genetic algorithm (TPGA) based on the multi- parent genetic algorithm (MPGA). Through analysis we find MPGA will lead the population' s evol vement to diversity or convergence according to the population size and the crossover size, so we make it run in different forms during the global and local optimization phases and then forms TPGA. The experiment results show that TPGA is very efficient for the optimization of low-dimension multi-modal functions, usually we can obtain all the global optimal solutions.

GLOBAL OPTIMIZATION OF PUMP CONFIGURATION PROBLEM USING EXTENDED CROWDING GENETIC ALGORITHM

An extended crowding genetic algorithm (ECGA) is introduced for solvingoptimal pump configuration problem, which was presented by T. Westerlund in 1994. This problem hasbeen found to be non-convex, and the objective function contained several local optima and globaloptimality could not be ensured by all the traditional MINLP optimization method. The concepts ofspecies conserving and composite encoding are introduced to crowding genetic algorithm (CGA) formaintain the diversity of population more effectively and coping with the continuous and/or discretevariables in MINLP problem. The solution of three-levels pump configuration got from DICOPT++software (OA algorithm) is also given. By comparing with the solutions obtained from DICOPT++, ECPmethod, and MIN-MIN method, the ECGA algorithm proved to be very effective in finding the globaloptimal solution of multi-levels pump configuration via using the problem-specific information.

Investigation into the Computational Costs of Using Genetic Algorithm and Simulated Annealing for the Optimization of Explicit Friction Factor Models

Research reports show that the accuracies of many explicit friction factor models, having different levels of accuracies and complexities, have been improved using genetic algorithm (GA), a global optimization approach. However, the computational cost associated with the use of GA has yet to be discussed. In this study, the parameters of sixteen explicit models for the estimation of friction factor in the turbulent flow regime were optimized using two popular global search methods namely genetic algorithm (GA) and simulated annealing (SA). Based on 1000 interval values of Reynolds number (Re) in the range of and 100 interval values of relative roughness () in the range of , corresponding friction factor (f) data were obtained by solving Colebrook-White equation using Microsoft Excel spreadsheet. These data were then used to modify the parameters of the selected explicit models. Although both GA and SA led to either moderate or significant improvements in the accuracies of the existing friction factor models, SA outperforms the GA. Moreover, the SA requires far less computational time than the GA to complete the corresponding optimization process. It can therefore be concluded that SA is a better global optimizer than GA in the process of finding an improved explicit friction factor model as an alternative to the implicit Colebrook-White equation in the turbulent flow regime.

A REAL-VALUED GENETIC ALGORITHM FOR OPTIMIZATION PROBLEM WITH CONTINUOUS VARIABLES

A real valued genetic algorithm(RVGA) for the optimization problem with continuous variables is proposed. It is composed of a simple and general purpose dynamic scaled fitness and selection operator, crossover operator, mutation operators and adaptive probabilities for these operators. The algorithm is tested by two generally used functions and is used in training a neural network for image recognition. Experimental results show that the algorithm is an efficient global optimization algorithm.

A Method for Rapidly Determining the Optimal Distribution Locations of GNSS Stations for Orbit and ERP Measurement Based on Map Grid Zooming and Genetic Algorithm

Designing the optimal distribution of Global Navigation Satellite System(GNSS)ground stations is crucial for determining the satellite orbit,satellite clock and Earth Rotation Parameters(ERP)at a desired precision using a limited number of stations.In this work,a new criterion for the optimal GNSS station distribution for orbit and ERP determination is proposed,named the minimum Orbit and ERP Dilution of Precision Factor(OEDOP)criterion.To quickly identify the specific station locations for the optimal station distribution on a map,a method for the rapid determination of the selected station locations is developed,which is based on the map grid zooming and heuristic technique.Using the minimum OEDOP criterion and the proposed method for the rapid determination of optimal station locations,an optimal or near-optimal station distribution scheme for 17 newly built BeiDou Navigation Satellite System(BDS)global tracking stations is suggested.To verify the proposed criterion and method,real GNSS data are processed.The results show that the minimum OEDOP criterion is valid,as the smaller the value of OEDOP,the better the precision of the satellite orbit and ERP determination.Relative to the exhaustive method,the proposed method significantly improves the computational efficiency of the optimal station location determination.In the case of 3 newly built stations,the computational efficiency of the proposed method is 35 times greater than that of the exhaustive method.As the number of stations increases,the improvement in the computational efficiency becomes increasingly obvious.

OPTIMIZATION BASED ON LMPROVED REAL—CODED GENETIC ALGORITHM

An improved real-coded genetic algorithm is pro-posed for global optimization of functionsl.The new algo-rithm is based om the judgement of the searching perfor-mance of basic real-coded genetic algorithm.The opera-tions of basic real-coded genetic algorithm are briefly dis-cussed and selected.A kind of chaos sequence is described in detail and added in the new algorithm ad a disturbance factor.The strategy of field partition is also used to im-prove the strcture of the new algorithm.Numerical ex-periment shows that the mew genetic algorithm can find the global optimum of complex funtions with satistaiting precision.

Particle Swarm Optimization with Directed Mutation

In the standard particle swarm optimization(SPSO),the big problem is that it suffers from premature convergence,that is,in complex optimization problems,it may easily get trapped in local optima.In order to mitigate premature convergence problem,this paper presents a new algorithm,which is called particle swarm optimization(PSO) with directed mutation,or DMPSO.The main idea of this algorithm is to "let the best particle(the smallest fitness of the particle swarm) become more excellent and the worst particle(the largest fitness of the particle swarm) try to be excellent".The new algorithm is tested on a set of eight benchmark functions,and compared with those of other four PSO variants.The experimental results illustrate the effectiveness and efficiency of the DMPSO.The comparisons show that DMPSO significantly improves the performance of PSO and searching accuracy.

A New Genetic Algorithm Based Upon Globally Optimal Choosing and Its Practices

A new genetic algorithm (GA) is developed. It features three new operations: restoration, reconstruction and recording the better, so as to produce a limited monotonic sequence of fitness value, to realize a globally optimal choosing, and to converge to a globally optimal solution through a perfectly stochastic process. Practical examples are given to illustrate the superiority of this new GA.

Capability Analysis of Chaotic Mutation and Its Self-Adaption

Through studying several kinds of chaotic mappings' distributions of orbital points, we analyze the capabilityof the chaotic mutations based on these mappings. Nunerical experiments support our conclusions very well. Thecapability analysis also led to a self-adaptive mechanism of chaotic mutation. The introducing of the self-adaptivechaotic mutation can improve the performance of genetic algorithm very prominently.

Application of Genetic Algorithm in Estimation of Gyro Drift Error Model

Extended Kalman Filter(EKF)algorithm is widely used in parameter estimation for nonlinear systems.The estimation precision is sensitively dependent on EKF’s initial state covariance matrix and state noise matrix.The grid optimization method is always used to find proper initial matrix for off-line estimation.However,the grid method has the draw back being time consuming hence,coarse grid followed by a fine grid method is adopted.To further improve efficiency without the loss of estimation accuracy,we propose a genetic algorithm for the coarse grid optimization in this paper.It is recognized that the crossover rate and mutation rate are the main influencing factors for the performance of the genetic algorithm,so sensitivity experiments for these two factors are carried out and a set of genetic algorithm parameters with good adaptability were selected by testing with several gyros’experimental data.Experimental results show that the proposed algorithm has higher efficiency and better estimation accuracy than the traversing grid algorithm.

Capability Analysis of Chaotic Mutation and Its Self－Adaption

Through studying several kinds of chaotic mappings' distributions of orbital points, we analyze the capability of the chaotic mutations based on these mappings. Numerical experiments support our conclusions very well. The capability analysis also led to a self-adaptive mechanism of chaotic mutation. The introducing of the self-adaptive chaotic mutation can improve the performance of genetic algorithm very prominently.

Three-Objective Programming with Continuous Variable Genetic Algorithm

The subject area of multiobjective optimization deals with the investigation of optimization problems that possess more than one objective function. Usually, there does not exist a single solution that optimizes all functions simultaneously;quite the contrary, we have solution set that is called nondominated set and elements of this set are usually infinite. It is from this set decision made by taking elements of nondominated set as alternatives, which is given by analysts. Since it is important for the decision maker to obtain as much information as possible about this set, our research objective is to determine a well-defined and meaningful approximation of the solution set for linear and nonlinear three objective optimization problems. In this paper a continuous variable genetic algorithm is used to find approximate near optimal solution set. Objective functions are considered as fitness function without modification. Initial solution was generated within box constraint and solutions will be kept in feasible region during mutation and recombination.

Orthogonal genetic algorithm for solving quadratic bilevel programming problems

A quadratic bilevel programming problem is transformed into a single level complementarity slackness problem by applying Karush-Kuhn-Tucker（KKT） conditions.To cope with the complementarity constraints,a binary encoding scheme is adopted for KKT multipliers,and then the complementarity slackness problem is simplified to successive quadratic programming problems,which can be solved by many algorithms available.Based on 0-1 binary encoding,an orthogonal genetic algorithm,in which the orthogonal experimental design with both two-level orthogonal array and factor analysis is used as crossover operator,is proposed.Numerical experiments on 10 benchmark examples show that the orthogonal genetic algorithm can find global optimal solutions of quadratic bilevel programming problems with high accuracy in a small number of iterations.

Real-coded genetic algorithm for optimal vibration controlof flexible structure

Presents the study on the optimum location of actuators/sensors for active vibration control in aerospace flexible structures with the performance function first built by maximization of dissipation energy due to control action and a real coded genetic algorithm then proposed to produce a global optimum solution, and proves the feasibility and advantages of this algorithm with the example of a standard test function and a two collocated actuators/sensors cantilever, and comparing the results with those given in the literatures.

A Genetic Algorithm with Weighted Average Normally-Distributed Arithmetic Crossover and Twinkling

Genetic algorithms have been extensively used as a global optimization tool. These algorithms, however, suffer from their generally slow convergence rates. This paper proposes two approaches to address this limitation. First, a new crossover technique, the weighted average normally-distributed arithmetic crossover (NADX), is introduced to enhance the rate of convergence. Second, twinkling is incorporated within the crossover phase of the genetic algorithms. Twinkling is a controlled random deviation that allows only a subset of the design variables to undergo the decisions of an optimization algorithm while maintaining the remaining variable values. Two twinkling genetic algorithms are proposed. The proposed algorithmsare compared to simple genetic algorithms by using various mathematical and engineering design test problems. The results show that twinkling genetic algorithms have the ability to consistently reach known global minima, rather than nearby sub-optimal points, and are able to do this with competitive rates of convergence.

An Improved Immune Genetic Algorithm for Solving the Optimization Problems of Computer Communication Networks

Obtaining the average delay and selecting a route in a communication networkare multi-constrained nonlinear optimization problems . In this paper, based on the immune geneticalgorithm, a new fuzzy self-adaptive mutation operator and a new upside-down code operator areproposed. This improved IGA is further successfully applied to solve optimal problems of computercommunication nets.

An Improved Tunicate Swarm Algorithm with Best-random Mutation Strategy for Global Optimization Problems

The Tunicate Swarm Algorithm(TSA)inspires by simulating the lives of Tunicates at sea and how food is obtained.This algorithm is easily entrapped to local optimization despite the simplicity and optimal,leading to early convergence compared to some metaheuristic algorithms.This paper sought to improve this algorithm's performance using mutating operators such as the lévy mutation operator,the Cauchy mutation operator,and the Gaussian mutation operator for global optimization problems.Thus,we introduced a version of this algorithm called the QLGCTSA algorithm.Each of these operators has a different performance,increasing the QLGCTSA algorithm performance at a specific optimization operation stage.This algorithm has been run on benchmark functions,including three different compositions,unimodal(UM),and multimodal(MM)groups and its performance evaluate six large-scale engineering problems.Experimental results show that the QLGCTSA algorithm had outperformed other competing optimization algorithms.

A NEW OPTIMIZATION ALGORITHM BASED ON THE PRINCIPLE OF EVOLUTION

A new genetic algorithm is proposed for the optimization problem of real-valued variable functions. A new robust and adaptive fitness scaling is presented by introducing the median of the population in exponential transformation. For float-point represented chromosomes, crossover and mutation operators are given. Convergence of the algorithm is proved. The performance is tested by two generally used functions. Hybrid algorithm which takes the BP algorithm as a mutation operator is used to train a neural network for image recognition. Experimental results show that the proposed algorithm is an efficient global optimization algorithm.