Parallel Hybrid Genetic Algorithms on Consumer-Level Graphics Hardware

This paper presents a parallel hybrid genetic algorithm (GA) for solving the sum-of-pairs multiple protein sequence alignment. A new chromosome representation and its corresponding genetic operators are proposed. A multi-population GENITOR-type GA is combined with local search heuristics. It is then extended to run in parallel on a multiprocessor system for speeding up. Experimental results of benchmarks from the BAliBASE show that the proposed method is superior to MSA, OMA, and SAGA methods with regard to quality of solution and running time. It can be used for finding multiple sequence alignment as well as testing cost functions.

An important and challenging data mining application in marketing is to learn models for predicting potential customers who contribute large profit to a company under resource constraints. In this paper, we first formulate this learning problem as a constrained optimization problem and then converse it to an unconstrained Multi-objective Optimization Problem (MOP). A parallel Multi-Objective Evolutionary Algorithm (MOEA) on consumer-level graphics hardware is used to handle the MOP. We perform experiments on a real-life direct marketing problem to compare the proposed method with the parallel Hybrid Genetic Algorithm, the DMAX approach, and a sequential MOEA. It is observed that the proposed method is much more effective and efficient than the other approaches.

The traditional single intelligent algorithm has slow convergence speed in the frequency assignment, and the effect cannot meet the increasing frequency equipment in the naval battlefield. Based on the single intelligent frequency assignment algorithm and the frequency conflict analysis model between systems, this paper proposes three heuristic frequency assignment algorithms based on hybrid genetic algorithms, namely, Genetic Algorithm and Tabu Search (GATS), Hybrid Genetic Simulated Annealing Algorithm (HGSAA) and Genetic Algorithm-ant Colony Algorithm (GAA). The simulation results show that the hybrid algorithm can quickly converge to a better allocation result than the single intelligent algorithm in the frequency assignment problem, and the optimal value is better than the single intelligent algorithm. Among them, the convergence speed and optimal value of the GAA are the best of the three algorithms. Therefore, this algorithm can be applied to frequency assignment with more frequency-using equipment within a fixed range.

This paper proposed and implemented an genetic and weed invasion hybrid algorithm in Sparse Array Synthesis. The classical weed invasion algorithm has high requirements on the convergence parameters in the process of generating weeds from seeds. Inappropriate parameters can easily lead to local convergence of evolution. The mutation and crossover operations similar to the genetic algorithm were introduced into the classical weed invasion algorithm. The method improves convergence speed, avoids local convergence, and enhances the stability of the algorithm. The algorithm is used in practical application in the synthesis of linear sparsely distributed array pattern, and the predetermined index is obtained through calculation. At the same time, compared with the genetic algorithm and the classical weed invasion algorithm, the results show that the hybrid algorithm has certain advantages.

A hybrid genetic local search algorithm for the permutation flowshop scheduling problem

Evolutionary programming is a good global optimization method. By introduction, the improved adaptive mutation operation and improved selection operation based on thickness adjustment of artificial immune system into traditional evolutionary programming, a fast immunized evolutionary programming is proposed in this paper. At last, this algorithm is verified by simulation experiment of typical optimization function. The results of experiment show that, the proposed fast immunized evolutionary programming can improve not only the convergent speed of original algorithm but also the computation effect of original algorithm, and is a very good optimization method.

Evolutionary programming is a good global optimization method. By introducing the improved adaptive mutation operation and improved selection operation based on thickness adjustment of artificial immune system into traditional evolutionary programming, a fast immunized evolutionary programming is proposed in this paper. At last, this algorithm is verified by simulation experiment of typical optimization function. The results of the experiment show that, the proposed fast immunized evolutionary programming can improve not only the convergent speed of original algorithm but also the computation effect of original algorithm, and is a very good optimization method.

Optimization of multi-pass milling using parallel genetic algorithm and parallel genetic simulated annealing

Sorting by reversals unsigned permutations is a problem exhaustively studied in the fields of combinatorics of permutations and bioinformatics with crucial applications in the analysis of evolutionary distance between organisms. This problem was shown to be NP-hard, which gave rise to the development of a series of approximation and heuristic algorithms. Among these approaches, evolutionary algorithms were also proposed, from which to the best of our knowledge a parallel version of the first proposed genetic algorithm computes the highest quality results. These solutions were not optimized for the case when the population reaches a degenerate state, that is when individuals of the population remain very similar, and the procedure still continues consuming computational resources, but without improving the individuals. In this paper, a memetic algorithm is proposed for sorting unsigned permutations by reversals, using the local search as a way to improve the fitness function image of the individuals. Also, the entropy of the population is controlled, such that, when a degenerate state is reached the population is restarted. Several experiments were performed using permutations generated from biological data as well as hundreds of randomly generated permutations of different size, from which some ones were chosen and used as benchmark permutations. Experiments have shown that the proposed memetic algorithm uses more adequately the computational resources and gives competitive results in comparison with the parallel genetic algorithm and outperforms the results of the standard genetic algorithm.

Genetic Algorithm (GA) is a population-based stochastic optimizer that mimics natural selection to solve complex, non-differentiable, and multimodal problems. This paper first reviews the biological foundations and canonical operators- selection, crossover and mutation--before surveying major variants such as Hybrid GA, Parallel GA and the Predator--Prey Dynamic GA that inject local search, island parallelism or ecological balance to mitigate premature convergence. This paper then benchmarks these algorithms on continuous function optimisation and combinatorial tasks, using the sphere function and the travelling-salesman problem as illustrative cases. Results show that Hybrid GA with simulated-annealing local search achieves the best accuracy--speed trade-off, while PDGA offers the most stable evolution curve in high-dimensional multimodal landscapes. Finally, this paper identifies remaining challenges--expensive fitness evaluation, parameter sensitivity and interpretability--and outline future directions including surrogate-assisted evolution, GPU/quantum acceleration and lifelong on-device adaptation. The study confirms that GA, when properly hybridised and parallelised, remains a competitive backbone for next-generation AI systems.

Previous studies have shown that embedding local search in classical evolutionary programming (EP) could lead to improved performance on function optimization problems. The utility of local search is investigated with fast evolutionary programming (FEP) and comparisons are offered between performance improvements obtained when using local search with Gaussian and Cauchy mutations. Experiments were conducted on a suite of four well known function optimization problems using two local search methods (conjugate gradient and F.J. Solis and R.J.-B. Wets, (1981)) with varying amounts of local search being incorporated into the evolutionary algorithm. Empirical results indicate that FEP with the conjugate gradient method outperforms other hybrid methods on three of the four functions when evolution was conducted for a fixed number of generations. Trials using local search produced solutions that were statistically as good as or better than trials without local search. However, the cost of using local search justified the enhancement in solution quality only when using Gaussian mutations but not when using Cauchy mutations.


 One of the most significant aspects of the working world is the concept of a picket schedule. It is difficult for the scheduler to make an archive since there are frequently many issues with the picket schedule. These issues include schedule clashes, requests for leave, and trading schedules. Evolutionary algorithms have been successful in solving a wide variety of scheduling issues. Evolutionary algorithms are very susceptible to data convergence. But no one has discussed where to start from, where the data converges from making schedules using evolutionary algorithms. The best algorithms among evolutionary algorithms for scheduling are genetic algorithms and memetics algorithms. When it comes to the two algorithms, using genetic algorithms or memetics algorithms may not always offer the optimum outcomes in every situation. Therefore, it is necessary to compare the genetic algorithm and the algorithm's memetic algorithm to determine which one is suitable for the nurse picket schedule. From the results of this study, the memetic algorithm is better than the genetic algorithm in making picket schedules. The memetic algorithm with a population of 10000 and a generation of 5000 does not produce convergent data. While for the genetic algorithm, when the population is 5000 and the generation is 50, the data convergence starts. For accuracy, the memetic algorithm violates only 24 of the 124 existing constraints (80,645%). The genetic algorithm violates 27 of the 124 constraints (78,225%). The average runtime used to generate optimal data using the memetic algorithm takes 20.935592 seconds. For the genetic algorithm, it takes longer, as much as 53.951508 seconds.

The VLSI Physical design floorplanning is the process where circuit description is converted into geometric description. This NP-Optimization problem with non-slicing blocks is very hard to solve. Memetic algorithms are used to solve NP-Optimization problems. Memetic algorithms are a family of meta-heuristic search algorithms in which a rule-based representation of Local Search (LS) is co-adapted alongside the candidate solutions within a hybrid evolutionary system. However, they may execute for a long time for difficult problems, because of several fitness evaluations. A promising approach to overcome this limitation is to parallelize these algorithms. In this paper, we propose to implement a parallel Memetic Algorithm (MA) on Graphical Processing Units. The General Purpose Graphical Processing Unit (GPGPU) is the complete parallel hardware which is best used for the Parallel Computing. The Parallel Memetic Algorithm we followed for an application perspective is a modified or hybrid genetic algorithm with extensive attributes to local search. The Parallel Memetic Algorithm operator gives a perfect exploration in the available search area and it is typical for addressing a modular assignment problem. It reduces the time efficiently for execution which is a boon for VLSI industry where we don’t have to spend more weeks for Physical design to be completed. We perform experiments to compare our parallel MA with an ordinary MA and demonstrate that the former is much more effective than the latter. Both fitness evaluation and genetic operations are spread over the GPU cores, allowing for the efficient processing of very large datasets. The parallel nature of Memetic algorithm can be best harnessed with help of GPGPU and significant changes in execution time and optimization are shown for VLSI Floorplanning problem.

A genetic algorithm (StGA) technique is presented to deal with global optimization of continuous problems. In this algorithm, a novel scheme called stochastic coding is employed, so that the search space is explored in terms of regions towards the near-global solution. The effectiveness and efficiency of the algorithm are demonstrated through performing optimization on several test functions and the results are compared with the well established fast evolutionary programming (FEP) technique in terms of the global optimization accuracy and the computational efficiency. Comparisons show that StGA can improve the accuracy of the optimization results on these functions by up to several orders as compared with FEP, whereas computational effort required by StGA is on average about ten times less than FEP.

This paper presents the first implementation of a generic memetic algorithm on one of the two GPU (Graphic Processing Unit) chips of a GTX295 gaming card. Observed speedups range between ×70 and ×120, mainly depending on the population size. An automatic parallelization of a memetic algorithm is provided through an upgrade of the EASEA language, so that the EC community can benefit from the extraordinary power of these cards without needing to program them.