An On‐Line Approach for Classifying and Extracting Application Behavior on Linux

21st International Conference on Advanced Networking and Applications (AINA '07)

et al. 2007

Self Cite

Motivated by the first process allocation limitations of the original Route load balancing algorithm, this paper presents RouteGA (Route with Genetic Algorithm support) which considers historical information about parallel application executions in order to optimize the first scheduling. This information is extracted by using monitors and summarized in a knowledge base used to quantify process occupation at the launch moment. Such occupation is used to parameterize a genetic algorithm responsible for optimizing the process allocation on heterogeneous computing environments such as Grids. Results confirm RouteGA overperforms the original Route, which had previously overperformed others from literature.

Section: Introductionmentioning

confidence: 99%

RouteGA: A Grid Load Balancing Algorithm with Genetic Support

Mello

Filho

21st International Conference on Advanced Networking and Applications (AINA '07)

et al. 2007

Self Cite

“…The labeling algorithm is built in accordance with the idea that the ART-2A network weights resemble the input patterns that have been learned by a certain neuron of the F<i layer Senger et al, 2004. The ART-2A network weights are also called prototypes because they define the direction for the data grouping.…”

Section: Training Algorithmmentioning

confidence: 99%

Automatic Text Classification Using an Artificial Neural Network

Mello

High Performance Computational Science and Engineering

Yang

2005

Self Cite

The increasing volume of available documents in the World Wide Web has turned the document indexing and searching more and more complex. This issue has motivated the development of several researches in the text classification area. However, the techniques resulting from these researches require human intervention to choose the more adequate parameters to carry on the classification. Motivated by such limitation, this article presents a new model for the text automatic classification 1. This model uses a self-organizing artificial neural network architecture, which does not require previous knowledge on the domains to be classified. The document features, in a word radical frequency format, are submitted to such architecture, what generates clusters with similar sets of documents. The model deals with stages of feature extraction, classification, labeling and indexing of documents for searching purposes. The classification stage, receives the radical frequency vectors, submit them to the ART-2A neural network that classifies them and stores the patterns in clusters, based on their similarity

“…Among such sources, the execution traces and monitoring have proved their great potential to acquire application knowledge [6].…”

Section: Introductionmentioning

confidence: 99%

“…Some techniques have been proposed to characterize and predict parallel application behavior using such knowledge sources [6]. By using those techniques scheduling software can significantly improve allocation decisions, matching the best resources to serve each task.…”

Section: Introductionmentioning

confidence: 99%

“…This work presents the adaptation and use of the simulated annealing (SA) meta-heuristic to the scheduling of parallel applications on heterogeneous environments. It considers the parallel application knowledge, obtained from extraction models [6], to orient the decisions to be taken. Results confirm that the proposed meta-heuristic improves the scheduling mainly on large and heterogeneous environments such as grids.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

On Simulated Annealing for the Scheduling of Parallel Applications

Mello¹,

2008 20th International Symposium on Computer Architecture and High Performance Computing

2008

Self Cite

A grid scheduling algorithm inspired on the simulated annealing meta-heuristic (SA) is presented. Guided by predictions about parallel applications resource usage, the algorithm uses SA to find a near-optimal solution which minimizes the overall execution time for scheduling problems on heterogeneous grids. The scheduling algorithm is validated by simulations, using a model which considers the mainly details about the distributed computers and the jobs, and is compared with other scheduling algorithms. The results allows identify the best SA parameters values, that are the learning rate and the iteration size, for each grid size. We found good results when simulating the scheduling algorithm for grid sizes near by 512 computers. We also observed that the SA computing cost do not jeopardize the scheduling results, which are better when compared with the performance of other scheduling disciplines.