Yuri Frota

Optimizing virtual machine allocation for parallel scientific workflows in federated clouds

Cloud computing has established itself as an interesting computational model that provides a wide range of resources such as storage, databases and computing power for several types of users. Recently, the concept of cloud computing was extended with the concept of federated clouds where several resources from different cloud providers are inter-connected to perform a common action (e.g. execute a scientific workflow). Users can benefit from both single-provider and federated cloud environment to execute their scientific workflows since they can get the necessary amount of resources on demand. In several of these workflows, there is a demand for high performance and parallelism techniques since many activities are data and computing intensive and can execute for hours, days or even weeks. There are some Scientific Workflow Management Systems (SWfMS) that already provide parallelism capabilities for scientific workflows in single-provider cloud. Most of them rely on creating a virtual cluster to execute the workflow in parallel. However, they also rely on the user to estimate the amount of virtual machines to be allocated to create this virtual cluster. Most SWfMS use this initial virtual cluster configuration made by the user for the entire workflow execution. Dimensioning the virtual cluster to execute the workflow in parallel is then a top priority task since if the virtual cluster is under or over dimensioned it can impact on the workflow performance or increase (unnecessarily) financial costs. This dimensioning is far from trivial in a single-provider cloud and specially in federated clouds due to the huge number of virtual machine types to choose in each location and provider. In this article, we propose an approach named GraspCC-fed to produce the optimal (or near-optimal) estimation of the amount of virtual machines to allocate for each workflow. GraspCC-fed extends a previously proposed heuristic based on GRASP for executing standalone applications to consider scientific workflows executed in both single-provider and federated clouds. For the experiments, GraspCC-fed was coupled to an adapted version of SciCumulus workflow engine for federated clouds. This way, we believe that GraspCC-fed can be an important decision support tool for users and it can help determining an optimal configuration for the virtual cluster for parallel cloud-based scientific workflows. We introduce an estimation of the amount of VMs to allocate in scientific workflows.The GraspCC-fed heuristic based on GRASP is proposed.GraspCC-fed considers scientific workflows in single-provider and federated clouds.An evaluation of GraspCC-fed is provided using SciPhylomics and adapted SciCumulus.GraspCC-fed is suitable to determine an optimal configuration for virtual clusters.

The maximum balanced subgraph of a signed graph: Applications and solution approaches

The Maximum Balanced Subgraph Problem (MBSP) is the problem of finding a subgraph of a signed graph that is balanced and maximizes the cardinality of its vertex set. This paper is the first one to discuss applications of the MBSP arising in three different research areas: the detection of embedded structures, portfolio analysis in risk management and community structure. The efficient solution of the MBSP is also in the focus of this paper. We discuss pre-processing routines and heuristic solution approaches to the problem. a GRASP metaheuristic is developed and improved versions of a greedy heuristic are discussed. Extensive computational experiments are carried out on a set of instances from the applications previously mentioned as well as on a set of random instances.

A branch-and-cut algorithm for the equitable coloring problem using a formulation by representatives

An equitable k-coloring of a graph is defined by a partition of its vertices into k disjoint stable subsets, such that the difference between the cardinalities of any two subsets is at most one. The equitable coloring problem consists of finding the minimum value of k such that a given graph can be equitably k-colored. We present two new integer programming formulations based on representatives for the equitable coloring problem. We propose a primal constructive heuristic, branching strategies, and the first branch-and-cut algorithm in the literature of the equitable coloring problem. The computational experiments were carried out on randomly generated graphs, DIMACS graphs, and other graphs from the literature.

A branch-and-price approach for the partition coloring problem

This work proposes a new integer programming model for the partition coloring problem and a branch-and-price algorithm to solve it. Experiments are reported for random graphs and instances originating from routing and wavelength assignment problems arising in telecommunication network design. We show that our method largely outperforms previously existing approaches.

Optimization of a Cloud Resource Management Problem from a Consumer Perspective

Cloud Computing is a distributed computing paradigm in which computing resources are available to users via Internet. Although there are many works on resource management in related literature, few of them tackle the problem from the perspective of commercial cloud consumers. In this paper, the proposed resource management problem selects cloud resources aiming to reduce the payment cost and the execution time of user applications. In order to solve this problem, an integer programming formulation and a heuristic based on Greedy Randomized Adaptive Search Procedure (GRASP) are also introduced. The model and the algorithm were tested over a set of instances constructed from requirements of real applications combined with sets of resources offered by commercial clouds. The obtained results indicate that the presented methods can be an important decision support tool for cloud consumers.

New branch-and-bound algorithms for k-cardinality tree problems

Abstract Given an undirected graph, the k -cardinality tree problem (KCTP) is the problem of finding a subtree with exactly k edges whose sum of weights is minimum. In this paper we present a lower bound for KCTP based on the work by Kataoka et al. [Kataoka, S., N. Araki and T. Yamada, Upper and lower bounding procedures for the minimum rooted k -subtree problem, European Journal of Operational Research, 122 (2000), 561–569]. This new bound is the basis for the development of a branch-and-bound algorithm for the problem. Experiments carried out on instances from KCTLib revealed that the new exact algorithm largely outperforms the previous approach.

An ILS algorithm to evaluate structural balance in signed social networks

Evaluating balance in a social network has been a challenge for social network researchers. The degree of balance in a social group can be used as a tool to study whether and how this group evolves to a possible balanced state. In particular, the solution of the Correlation Clustering (CC) problem can be used as a criterion to measure the amount of balance in signed social networks, where positive (friendly) and negative (antagonistic) interactions take place. In this work, we provide an efficient solution of the CC problem by the use of the ILS metaheuristic. The proposed algorithm outperforms other solution strategies from literature in execution time, with the same solution quality.

Evaluating Grasp-based cloud dimensioning for comparative genomics: A practical approach

Cloud computing establishes a new computing model where a wide range of computing resources are provided to several types of users. Especially for bioinformatics experiments modeled as scientific workflows, clouds provide several types of resources as virtual machines (VM), storage, databases and computing power that can be combined for empowering the scientific workflow execution. These workflows usually require high performance environments and parallelism techniques since their activities are data and computing intensive and can execute for a long time. There are then some Scientific Workflow Management Systems (SWfMS) that already manage the parallel execution of scientific workflows in clouds. Most of them instantiate a virtual cluster for the execution. However, they rely on the user to estimate the amount of VMs to be instantiated to create this virtual cluster. Estimating the amount of VMs to instantiate is then a crucial task to avoid negative impacts on the workflow performance with under or over estimations. This dimensioning also is not a trivial task in clouds due to the large number of VM types to choose in a cloud provider. Previously proposed approach named GraspCC already provides a near optimal estimation of the amount of VM for general applications, not scientific workflows. In this paper, we coupled the GraspCC to SciCumulus (Cloud-based Parallel Engine for Scientific Workflows) engine to estimate the necessary amount of VMs for bioinformatics workflows. We have evaluated GraspCC by comparing the estimative with real executions of a set of large-scale comparative genomics workflows. It showed the suitability of GraspCC to estimate the amount of VMs in real bioinformatics cloud workflows.

A Branch-and-Cut Algorithm for Equitable Coloring based on a Formulation by Representatives

Let G = (V,E) be an undirected graph, where V is the set of vertices and E is that of edges. An equitable k-coloring of G is a partition of V into k disjoint stable subsets such that the difference on the cardinalities of any two subsets is at most one. Each subset is associated with a color and called a color set. The Equitable Coloring Problem (ECP) consists of finding the minimum value of k such that there is an equitable k-coloring of G. This number is said to be the equitable chromatic number of G and it is denoted by χ=(G). The equitable coloring problem was first introduced in [7], motivated by an application to municipal garbage collection [9]. It was proved to be NPhard in [5]. A branch-and-cut algorithm based on an integer programming

Upper and lower bounding procedures for the minimum caterpillar spanning problem

Abstract A spanning caterpillar in a graph is a tree composed by a path such that all vertices not in the path are leaves. In the Minimum Spanning Caterpillar Problem (MSCP) each edge has two costs: a path cost when it belongs to the path and a connection cost when it is incident to a leaf. The goal is to find a spanning caterpillar minimizing the sum of all path and connection costs. In this paper we formulate the as a minimum Steiner arborescence problem. This reduction is the basis for the development of an efficient branch-and-cut algorithm for the MSCP. We als developed a GRASP heuristic to generate primal bounds. Experiments carried out on instances adapted from TSPLIB 2.1 revealed that the exact algorithm is capable to solve to optimality instances with up to 300 vertices in reasonable time. They also showed that our heuristic yields very high quality solutions.