GAP/D: VLSI Hardware for Parallel and Adaptive Distributed Genetic Algorithms

In this paper, we evaluate the performance of a distributed genetic algorithm (DGA) with cellular structures on function optimization problems. The DGA in this paper is a genetic algorithm with several subpopulations. Each subpopulation in the DGA has a cellular structure as in cellular genetic algorithms and has interaction area with other subpopulations. We examine several parameter specifications in the DGA on well-known function optimization problems.

A major problem in the use of genetic algorithms is premature convergence. One approach for dealing with this problem is the distributed genetic algorithm model. Its basic idea is to keep, in parallel, several subpopulations that are processed by genetic algorithms, with each one being independent of the others. Making distinctions between the subpopulations by applying genetic algorithms with different configurations, we obtain the so-railed heterogeneous distributed genetic algorithms. These algorithms represent a promising way for introducing a correct exploration/exploitation balance in order to avoid premature convergence and reach approximate final solutions. This paper presents the gradual distributed real-coded genetic algorithms, a type of heterogeneous distributed real-coded genetic algorithms that apply a different crossover operator to each sub-population. Experimental results show that the proposals consistently outperform sequential real-coded genetic algorithms.

In this paper, we consider a two-level 0-1 programming problem in which there is not coordination between the decision maker (DM) at the upper level and the decision maker at the lower level. We propose a revised computational method that solves problems related to computational methods for obtaining the Stackelberg solution. Specifically, in order to improve the computational accuracy of approximate Stakelberg solutions and shorten the computational time of a computational method implementing a genetic algorithm (GA) proposed by the authors, a distributed genetic algorithm is introduced with respect to the upper level GA, which handles decision variables for the upper level DM. Parallelization of the lower level GA is also performed along with parallelization of the upper level GA. The proposed algorithm is also improved in order to eliminate unnecessary computation during operation of the lower level GA, which handles decision variables for the lower level DM. In order to verify the effectiveness of the proposed method, we propose comparisons with existing methods by performing numerical experiments to verify both the accuracy of the solution and the time required for the computation.

Genetic algorithms have become an effective method to search the optimal solution. However, traditional genetic algorithms have some disadvantages in solving practical problems. This paper proposes a distributed genetic algorithm framework based on the resource-based RESTFUL service, we can regard every sub-population as a resource in this framework, and these sub-populations will evolve independently, meanwhile the main service will exchange information among sub-populations. Using HTTP verbs and resource identifier URI to call services to improve the efficiency and accuracy of genetic algorithms, finally the paper discusses the implementation of the algorithm in the Rails framework.

We present a new distributed genetic algorithm that can be used to extract useful information from distributed, large data over the network. The main idea of the proposed algorithms is to determine how many and which individuals move between subpopulations at each site adaptively. In addition, we present a method to help individuals from other subpopulations not be weeded out but adapt to the new subpopulation. We used six data sets from UCI Machine Learning Repository to compare the performance of our approach with that of the single, centralized genetic algorithm. As a result, the proposed algorithm produced better performance than the single genetic algorithm in terms of the classification accuracy with the feature subsets.

As more research centers embark on sequencing new genomes, the problem of DNA fragment assembly for shotgun sequencing is growing in importance and complexity. Accurate and fast assembly is a crucial part of any sequencing project and since the DNA fragment assembly problem is NP-hard, exact solutions are very difficult to obtain. Various heuristics, including genetic algorithms, were designed for solving the fragment assembly problem. While the sequential genetic algorithm has given good results, it is unable to sequence very large DNA molecules. In this work, we present two parallel methods, a distributed genetic algorithm and a parallel simulated annealing, to solve problem instances that are 77K base pairs long accurately

Existing music recommendation systems don't suit user subjectivity and are not naturally intuitive. We previously proposed a music recommendation system to address these problems. Our music recommendation system uses Kansei agents and a Kansei retrieval system. The Kansei agents employ a Kansei model and are characterized by a three-layered neural network. Music fluctuation properties are defined as inputs to the neural networks of the Kansei agents. Our previously proposed system returns recommendations based on user subjectivity. However, this system incurs significant user evaluation load. In this study, we introduce a distributed genetic algorithm (DGA) as an optimization method to address this problem. We compare the proposed DGA method to our previous method by simulation. The simulation results indicate that the proposed DGA method significantly outperforms previous method.

Achieving good performance with a parallel genetic algorithm requires properly configuring control parameters such as mutation rate, crossover rate, and population size. We consider the problem of setting control parameter values in a standard, island-model distributed genetic algorithm. As an alternative to tuning parameters by hand or using a self-adaptive approach, we propose a very simple strategy which statically assigns random control parameter values to each processor. Experiments on benchmark problems show that this simple approach can yield results which are competitive with homogeneous distributed genetic algorithm using parameters tuned specifically for each of the benchmarks.

Integrating Internet technologies with traditional healthcare systems has enabled the emergence of cloud healthcare systems. These systems aim to optimize the balance between online diagnosis and offline treatment to effectively reduce patients’ waiting times and improve the utilization of idle medical resources. In this paper, a distributed genetic algorithm (DGA) is proposed as a means to optimize the balance of patient assignment (PA) in cloud healthcare systems. The proposed DGA utilizes individuals as solutions for the PA optimization problem and generates better solutions through the execution of crossover, mutation, and selection operators. Besides, the distributed framework in the DGA is proposed to improve its population diversity and scalability. Experimental results demonstrate the effectiveness of the proposed DGA in optimizing the PA problem within the cloud healthcare systems.

Recently, Genetic Algorithm has been studied as an effective approach for large scale optimization problems. However, we have issues of early convergence and settings of many parameters in the GA approach. In order to deal with such issues, parameter free genetic algorithm(PfGA) and distributed genetic algorithm(DGA) were proposed. In this paper, we propose a distributed parameter free genetic algorithm(DPfGA) that keeps parameter free characteristic and improves efficiency of optimization. Besides the distributed construction of GA, we propose the method varying the number of offspring adaptively in accordance with the current performance of optimization. We show effectiveness of the algorithm through application of the algorithm to TSP(Travelling Salesman Problem).

Discovery of Classification Rules Using Distributed Genetic Algorithm

The paper presents a distributed genetic algorithm implementation for obtaining good quality consistent results for different ordering problems. Most importantly, the solution found by the proposed Distributed GA is not only of high quality but also robust and does not require fine tuning of the probabilities of crossover and mutation. In addition, implementation of the Distributed GA is simple and does not require the use of any specialized, expensive hardware. Fault tolerance has also been provided by dynamic reconfiguration of the distributed system in the event of a process or machine failure. The effectiveness of using a simple crossover scheme with Distributed GA is demonstrated by solving three variations of the Traveling Salesman Problem (TSP).

A parameter generation method based on model checking is proposed to tackle the parameter selection of hierarchical scheduling systems in Integrated Modular Avionics (IMA) by combining the classical symbolic model checking and the Statistical Model Checking (SMC). It builds a generic timed automata network to describe the temporal behavior of hierarchical systems. A distributed genetic algorithm is adopted to search the optimum partition parameters with respect to processor utilization while guaranteeing the schedulability of the system, which is formulated as safety properties of symbolic model checking and hypothesis testing of SMC. Comparing with the widely-used response time analysis, the formal model of this method is more expressive to cover complex features. The application of SMC alleviates the "state space explosion" of classical model checking. Finally, the parameter generation experiments show that the present method is able to find the global optimum solutions in the parameter space.

Reactive scheduling is one of the solutions for scheduling in dynamically changing manufacturing system. However, most of study for reactive scheduling use centralized scheduler. It is necessary to discuss about decentralized scheduler to catch up with nowadays huge and complex manufacturing systems. Also, it needs to be allowed that most of real manufacturing system scheduling problems are multi objective. The proposed approach gives more accurate and wider ranged solution for scheduling used distributed genetic algorithm. The effectiveness of the proposed method is confirmed by preliminary computer simulation results.

Combinatorial optimization problems are commonly tackled through the use of metaheuristics aimed to improve the way the search space is explored (diversification) and how promising areas are exploited (intensification), in order to obtain good-quality solutions. We present a distributed genetic algorithm to solve the Prize Collecting Steiner Tree Problem, a classical combinatorial optimization problem. The proposed algorithm improves the quality of the solutions by asynchronously combining distributed populations that evolve in parallel, starting from initial heterogeneous configurations. To show the effectiveness of this approach an empirical study that considers both execution time and solution quality is presented. Results show that better solutions are reached when initial populations combine configurations with high and low fitness.