Anabela Simões

An Immune System-Based Genetic Algorithm to Deal with Dynamic Environments: Diversity and Memory

The standard Genetic Algorithm has several limitations when dealing with dynamic environments. The most harmful limitation as to do with the tendency for the large majority of the members of a population to convergence prematurely to a particular region of the search space, making thus difficult for the GA to find other solutions when changes in the environment occur. Several approaches have been tested to overcome this limitation by introducing diversity in the population or through the incorporation of memory in order to help the algorithm when situations of the past can be observed in future situations. In this paper, we propose a GA inspired in the immune system ideas in order to deal with dynamic environments. This algorithm combines the two aspects mentioned above: diversity and memory and we will show that our algorithm is also more adaptable and accurate than the other algorithms proposed in the literature.

Evolutionary Algorithms for Dynamic Environments: Prediction Using Linear Regression and Markov Chains

In this work we investigate the use of prediction mechanisms in Evolutionary Algorithms for dynamic environments. These mechanisms, linear regression and Markov chains, are used to estimate the generation when a change in the environment will occur, and also to predict to which state (or states) the environment may change, respectively. Different types of environmental changes were studied. A memory-based evolutionary algorithm empowered by these two techniques was successfully applied to several instances of the dynamic bit matching problem.

An Evolutionary Approach to the Zero/One Knapsack Problem: Testing Ideas from Biology

The transposition mechanism, widely studied in previous publications, showed that when used instead of the standard crossover operators, allows the genetic algorithm to achieve better solutions. Nevertheless, all the studies made concerning this mechanism always focused the domain of function optimization. In this paper, we present an empirical study that compares the performances of the transposition-based GA and the classical GA solving the 0/1 knapsack problem. The obtained results show that, just like in the domain of function optimization, transposition is always superior to crossover.

Improving prediction in evolutionary algorithms for dynamic environments

The addition of prediction mechanisms in Evolutionary Algorithms (EAs) applied to dynamic environments is essential in order to anticipate the changes in the landscape and maximize its adaptability. In previous work, a combination of a linear regression predictor and a Markov chain model was used to enable the EA to estimate when next change will occur and to predict the direction of the change. Knowing when and how the change will occur, the anticipation of the change was made introducing useful information before it happens. In this paper we introduce mechanisms to dynamically adjust the linear predictor in order to achieve higher adaptability and robustness. We also extend previous studies introducing nonlinear change periods in order to evaluate the predictors accuracy.

Prediction in evolutionary algorithms for dynamic environments using markov chains and nonlinear regression

The inclusion of prediction mechanisms in Evolutionary Algorithms (EAs) used to solve dynamic environments allows forecasting the future and this way we can prepare the algorithm to the changes. Prediction is a difficult task, but if some recurrence is present in the environment, it is possible to apply statistical methods which use information from the past to estimate the future. In this work we enhance a previously proposed computational architecture, incorporating a new predictor based on nonlinear regression. The system uses a memory-based EA to evolve the best solution and a predictor module based on Markov chains to estimate which possible environments will appear in the next change. Another prediction module is responsible to estimate when next change will happen. In this work important enhancements are introduced in this module, replacing the linear predictor by a nonlinear one. The performance of the EA is compared using no prediction, using predictions supplied by linear regression and by nonlinear regression. The results show that this new module is very robust allowing to accurately predicting when next change will occur in different types of change periods.

Prediction in evolutionary algorithms for dynamic environments

Evolutionary algorithms have been widely used to solve dynamic optimization problems. Memory-based evolutionary algorithms are often used when the dynamics of the environment follow some repeated behavior. Over the last few years, the use of prediction mechanisms combined with memory has been explored. These prediction techniques are used to avoid the decrease of the algorithm’s performance when a change occurs. This paper investigates the use of prediction methods in memory-based evolutionary algorithms for two distinct situations: to predict when the next change will happen and how the environment will change. For the first predictor two techniques are explored, one based on linear regression and another supported by nonlinear regression. For the second, a technique based on Markov chains is explored. Several experiments were carried out using different types of dynamics in two benchmark problems. Experimental results show that the incorporation of the proposed prediction techniques efficiently improves the performance of evolutionary algorithms in dynamic optimization problems.

CHC-based algorithms for the dynamic traveling salesman problem

The CHC algorithm uses an elitist selection method which, combined with an incest prevention mechanism and a method to diverge the population whenever it converges, allows the maintenance of the population diversity. This algorithm was successfully used in the past for static optimization problems. In this paper we propose three new and improved CHC-based algorithms designed to deal with dynamic environments. The performance of the investigated CHC algorithms is tested in different instances of the dynamic Traveling Salesman Problem. The experimental results show the efficiency, robustness and adaptability of the improved CHC variants solving different dynamic traveling salesman problems.

Improving the Genetic Algorithm’s Performance when Using Transformation

Transformation is a biologically inspired genetic operator that, when incorporated in the standard Genetic Algorithm can promote diversity in the population. Previous work using this genetic operator in the domain of function c Jtimization and combinatorial optimization showed that t.he premature convergence of the population is avoide<... Furthermore, the solutions obtained were, in general, superior to the solutions achieved by the GA with standard I-point, 2-point and uniform crossover. In this paper we present an extensive empirical study carried to determine the best parameter setting to use with transformation in order to enhance the GAs performance. These parameters include the gene segment length, the replacement rate (percentage of individuals of the previous population used to update the gene segment pool), and the mutation and transformation rates.

Memory-based CHC algorithms for the dynamic traveling salesman problem

The CHC algorithm uses an elitist selection method that, combined with an incest prevention mechanism and a method to diverge the population whenever it converges, allows the maintenance of the population diversity. This algorithm was successfully used in the past for static optimization problems. The use of memory in Evolutionary Algorithms has been proved to be advantageous when dealing with dynamic optimization problems. In this paper we investigate the use of three different explicit memory strategies included in the CHC algorithm. These strategies - direct, immigrant and associative - combined with the CHC algorithm are used to solve different instances of the dynamic Traveling Salesman Problem in cyclic, noisy and random environments. The experimental results, statistically validated, show that the memory schemes significantly improve the performance of the original CHC algorithm for all types of studied environments. Moreover, when compared with the equivalent memory-based standard EAs with the same memory schemes, the memory-based CHC algorithms obtain superior results when the environmental changes are slower.

A Comparative Study Using Genetic Algorithms to Deal with Dynamic Environments

One of the approaches used in Evolutionary Algorithms (EAs) for problems in which the environment changes from time to time is to use techniques that preserve the diversity in population. We have tested and compared several algorithms that try to keep the population as diverse as possible. One of those approaches applies a new biologically inspired genetic operator called transformation, previously used with success in static optimization problems. We tested two EAs using transformation and two other classical approaches: random immigrants and hypermutation. The comparative study was made using the dynamic 0/1 Knapsack optimization problem. Depending on the characteristics of the dynamic changes, the best results were obtained with transformation or with hypermutation.