Parallel architecture design of genetic algorithms on HPC platform

Summary form only given. This article gives a brief overview of theoretical advances, computing trends, applications and future perspectives in parallel genetic algorithms. It explains basic terms and behavior of (parallel) genetic algorithms. Genetic algorithms are easily parallelized algorithms, therefore two kinds of possible parallelism, data parallelism and control parallelism, are mentioned and described towards them. Parallelism of genetic algorithms brings many advantages and gains. Classifications of these algorithms are often based on the type of computing model, a walk strategy and the used computing machinery. Afterwards significant milestones in the theory with latest advances are briefly mentioned. Then current trends in parallel computing with stress computer architectures of parallel systems, interconnection topologies, operating systems, parallel (genetic) libraries and programming paradigms are reviewed shortly. The sufficient space is devoted to the latest applications of parallel genetic algorithms. After the discussion section, perspectives of the algorithms are predicted till the year 2005. The information in the article is segregated into two periods before and after the year 2000 in all chapters. The second period is more interesting and of higher importance, because it highlights recent research efforts and gives some hints about possible future trends. That is why we devote much space to the second period. As there is no such an overview of the recent period of parallel genetic algorithms, our investigation could be appealing and useful in many aspects.

One of the important problems of sustainable logistics is routing vehicles in a sustainable manner, the green vehicle routing problem, or vehicle routing problems which aim to reduce CO2 emissions. In the literature research, it was seen that these problems were solved with heuristic, metaheuristic, or hyper-heuristic methods and hybrid approaches since they are in the NP-hard class. This work presents a parallel multi-process genetic algorithm that incorporates problem-specific genetic operators to minimize CO2 emissions in the capacity-constrained vehicle routing problem. Unlike previous research, the algorithm combines parallel computing with tailored genetic operators in order to enhance the diversity of solutions and speed up convergence. Genetic algorithm models were developed to minimize total distance, CO2 emissions, and both objectives simultaneously. Two genetic algorithm models were developed to minimize total distance and CO2 emissions. Experimental results using the reference CVRP examples such as A-n32-k5 and B-n44-k7 show that the proposed approach reduces CO2 emissions by 1.2% more than hybrid artificial bee colony optimization, 1.3% more than ant colony optimization, and 4% more than the traditional genetic algorithm. Experimental results using benchmark CVRP instances demonstrate that the proposed approach outperforms hybrid artificial bee colony optimization, ant colony optimization, and traditional genetic algorithms for most of the test cases. This is done by exploiting multi-core processors, and the parallel architecture has improved computational efficiency; the modules compare and update solutions against the global optimum. Results obtained show that prioritizing CO2 emissions as the only objective yields better results compared to multi-objective models. This study makes two significant contributions to the literature: (1) it introduces a novel parallel genetic algorithm framework optimized for CO2 emission reduction, and (2) it provides empirical evidence underscoring the advantages of emission-focused optimization in CVRP.

This paper addresses scheduling problems in hybrid flow shop-like systems with a migration parallel genetic algorithm (PGA_MIG). This parallel genetic algorithm model allows genetic diversity by the application of selection and reproduction mechanisms nearer to nature. The space structure of the population is modified by dividing it into disjoined subpopulations. From time to time, individuals are exchanged between the different subpopulations (migration). Influence of parameters and dedicated strategies are studied. These parameters are the number of independent subpopulations, the interconnection topology between subpopulations, the choice/replacement strategy of the migrant individuals, and the migration frequency. A comparison between the sequential and parallel version of genetic algorithm (GA) is provided. This comparison relates to the quality of the solution and the execution time of the two versions. The efficiency of the parallel model highly depends on the parameters and especially on the migration frequency. In the same way this parallel model gives a significant improvement of computational time if it is implemented on a parallel architecture which offers an acceptable number of processors (as many processors as subpopulations).

A scalable parallel genetic algorithm for the Generalized Assignment Problem

Genetic algorithms(GA), which are based on the idea of natural selection and survival of the fittest, have proven successful in solving complex problems that are not easily solved through conventional methods. Parallel genetic algorithm(PGA) is an extension of the classical GA. The important aspect in PGA is migration and GA operation. This paper presents PGAs that use fuzzy algorithm and natural select concept to migration of subpopulations. Fuzzy algorithm is used to change GA operators. Experimental results show that the proposed methods exhibit good performance compared to the classical method.

Intelligent optimization algorithm (IOA) has been widely studied and applied to solve various optimization problems. When scholars improve IOA with mathematical methods, they also want to seek an effective method to implement algorithms with higher real time, especially for a complex problem. Parallel design is an effective method to improve the real time of IOA. Currently, the parallel programming based on open multi-processing (OpenMP) and compute unified device architecture (CUDA) are two popular methods. To find and develop a new IOA parallel method, in this paper, a parallel design and implementation method based on field programmable gate array (FPGA) is explored. In order to validate the proposed method, parallel genetic algorithm (GA) and parallel particle swarm optimization (PSO) algorithm are realized by the proposed method. Furthermore, the performance and advantage of the proposed FPGA-based parallel IOA method are tested by comparing with OpenMP-based parallel programming and CUDA-based parallel programming, the final results show that the proposed method with highest real-time performance in IOA parallel implementation. A case study by using FPGA-based parallel simulate annealing (SA) to address job shop scheduling problem (JSSP) to illustrate the proposed method has high potential in industrial applications.

Genetic algorithms offer very good performances for solving large optimization problems, especially in the domain of error-correcting codes. However, they have a major drawback related to the time complexity and memory occupation when running on a uniprocessor computer. This paper proposes a parallel decoder for linear block codes, using parallel genetic algorithms (PGA). The good performance and time complexity are confirmed by theoretical study and by simulations on BCH(63,30,14) codes over both AWGN and flat Rayleigh fading channels. The simulation results show that the coding gain between parallel and single genetic algorithm is about 0.7 dB at BER = 10﹣5 with only 4 processors.

The class of MIMD parallel computers includes multiprocessor architectures, such as UMA, COMA, and NUMA, as well as multicomputer architectures, such as MPP and COW. Despite huge technological differences, machines with different architectures may be used to run certain similar applications. An interesting category of applications that may be successfully executed on a variety of parallel architectures is that of genetic algorithms (GAs) that provide more and more attractive solution of many complex engineering problems for which classical optimization methods cannot be used. GAs prove to be parallelizable in a natural way. Parallel genetic algorithms (PGAs) highlight good balance between calculations and communications that allows obtaining good results on different classes of parallel architectures. The paper describes the results obtained in a comparative study of PGAs, implemented on a cluster of SunBlade 100 workstations (COW) and on a Sun Enterprise E10000 (UMA) computer. The study demonstrates suitability of these different architectures for the development and execution of this class of applications. Also, some relevant facts concerning the performance of PGAs are presented.

Floorplanning is an important problem in very large-scale integrated-circuit (VLSI) design automation as it determines the performance, size, yield and reliability of VLSI chips. From the computational point of view, floorplan area minimization is an NP-hard problem. This paper presents a parallel genetic algorithm (GA) for floorplan area optimization. The parallel GA is based an island model with an asynchronous migration mechanism, and is implemented using Web services and multithreading technologies. The parallel GA is compared with a sequential GA that the parallel GA is based on. Experimental results show that the parallel GA can produce better results than the sequential GA when they use the same amount of computing resources. In addition, since the number of islands and migration interval are two important parameters that directly affect the performance of island-based parallel GAs, the impact of the two parameters on the performance of the parallel GA are empirically studied in this paper.

Modern group communication based applications require multiple parameters to be considered for routing in a Cellular network. Traditional algorithms fail in the situations where these parameters frequently change due to the dynamism prevailing in the network. A new technique for topology discovery in these types of networks using ant colony optimization (ACO) has been proposed based on the restricted flooding principle. To provide a better quality of service in routing with multiple constraints, a genetic algorithm based routing has been proposed to find optimal routes within a shorter span of time than the traditional deterministic routing algorithms. Moreover, with the exponential growth in the number of mobile users, to enable a large number of users to participate in a group communication, a parallel genetic algorithm (GA) is proposed in this paper. Our simulation results show that the topology discovery using ant colony optimization is faster. The Call service rate using parallel genetic algorithm is more than that of sequential genetic algorithm and the Call blocking rate of parallel genetic algorithm is less than that of sequential genetic algorithm, for large number of routers in the network.

A genetic similarity algorithm for searching the Gene Ontology terms and annotating anonymous protein sequences

this paper is based on the analyses of current logistics vehicles dispatching system at home and abroad as well as a contrast between its implementation techniques. It uses genetic algorithm to solve vehicles dispatching problems in logistics. Genetic algorithm has always had its advantage in overall searching and is therefore adopted in this case. But in order to overcome the precocity of basic genetic algorithm and at the same time improve the quality of the optimum solution and cut searching time, the paper adopts the Parallel Genetic Algorithm (PGA). Based on the above theoretical research, together with an object-oriented system analysis and design method, this study designed and developed an intelligent dispatching system based on PGA and carried out a series of experimental tests. The test results show this PGA dispatching system can effectively fulfill the dispatching tasks and meet the demand of logistics dispatching center. This dispatching system is highly effective in elevating the competitiveness of small and medium-sized logistics companies.

In the past few years, CUDA and OpenCL are developed in full use of the GPU, which is a significant topic in high performance computing. In this paper, we have proposed an implementation of the genetic algorithm for the traveling salesman problem on the parallel OpenCL architecture. Population initialization, fitness evaluation, selection, crossover and mutation operators are implemented on the GPU by using individual to thread mapping. Moreover we have evaluated our algorithm using a set of benchmark instances from the TSPLIB library. The comparison results shows that GPU computations provide better performance than traditional CPU implementation.

We investigated the usefulness of a parallel genetic algorithm for phylogenetic inference under the maximum-likelihood (ML) optimality criterion. Parallelization was accomplished by assigning each "individual" in the genetic algorithm "population" to a separate processor so that the number of processors used was equal to the size of the evolving population (plus one additional processor for the control of operations). The genetic algorithm incorporated branch-length and topological mutation, recombination, selection on the ML score, and (in some cases) migration and recombination among subpopulations. We tested this parallel genetic algorithm with large (228 taxa) data sets of both empirically observed DNA sequence data (for angiosperms) as well as simulated DNA sequence data. For both observed and simulated data, search-time improvement was nearly linear with respect to the number of processors, so the parallelization strategy appears to be highly effective at improving computation time for large phylogenetic problems using the genetic algorithm. We also explored various ways of optimizing and tuning the parameters of the genetic algorithm. Under the conditions of our analyses, we did not find the best-known solution using the genetic algorithm approach before terminating each run. We discuss some possible limitations of the current implementation of this genetic algorithm as well as of avenues for its future improvement.

Genetic algorithms are adaptive search algorithms that have been shown to be robust optimization algorithms for multimodal real-valued functions and a variety of combinatorial optimization problems. In contrast to more standard search algorithms, genetic algorithms base their progress on the performance of a population of candidate solutions, rather than on a single candidate solution. The authors will concentrate on the application of genetic algorithms to the traveling salesman problem. For this problem, there exist several such algorithms, ranging from pure genetic algorithms to genetic algorithms that incorporate heuristic information. These algorithms will be reviewed and their performance contrasted. A serious drawback of genetic algorithms is their inefficiency when implemented on a sequential machine. However, due to their inherent parallel properties, they can be successfully implemented on parallel machines, resulting in considerable speedup. Parallel genetic algorithms will be reviewed and their uses in the traveling salesman problem will be indicated.