Multi-objective workflow scheduling in cloud computing: trade-off between makespan and cost

Cluster Computing - Recently, modern businesses have started to transform into cloud computing platforms to deploy their workflow applications. However, scheduling workflow under resource...     

Failure-aware workflow scheduling in cluster environments

The goal of workflow application scheduling is to achieve minimal makespan for each workflow. Scheduling workflow applications in high performance cluster environments is an NP-Complete problem, and becomes more complicated when potential resource failures are considered. While more research on failure prediction has been witnessed in recent years to improve system availability and reliability, very few of them attack the problem in the context of workflow application scheduling. In this paper, we study how a workflow scheduler benefits from failure prediction and propose FLAW, a failure-aware workflow scheduling algorithm. We propose two important definitions on accuracy, Application Oblivious Accuracy (AOA) and Application Aware Accuracy (AAA), from the perspectives of system and scheduling respectively, as we observe that the prediction accuracy defined conventionally imposes different performance implications on different applications and fails to measure how that improves scheduling effectiveness. The comprehensive evaluation results using real failure traces show that FLAW performs well with practically achievable prediction accuracy by reducing the average makespan, the loss time and the number of job rescheduling.     

Reliable budget aware workflow scheduling strategy on multi-cloud environment

Cluster Computing - The resource provisioning and workflow execution in a multi-cloud environment using a pay-as-you-use framework have recently gained the attention of the cloud computing research...     

Energy and resource efficient workflow scheduling in a virtualized cloud environment

High energy consumption (EC) is one of the leading and interesting issue in the cloud environment. The optimization of EC is generally related to scheduling problem. Optimum scheduling strategy is used to select the resources or tasks in such a way that system performance is not violated while minimizing EC and maximizing resource utilization (RU). This paper presents a task scheduling model for scheduling the tasks on virtual machines (VMs). The objective of the proposed model is to minimize EC, maximize RU, and minimize workflow makespan while preserving the task’s deadline and dependency constraints. An energy and resource efficient workflow scheduling algorithm (ERES) is proposed to schedule the workflow tasks to the VMs and dynamically deploy/un-deploy the VMs based on the workflow task’s requirements. An energy model is presented to compute the EC of the servers. Double threshold policy is used to perceive the server’ status i.e. overloaded/underloaded or normal. To balance the workload on the overloaded/underloaded servers, live VM migration strategy is used. To check the effectiveness of the proposed algorithm, exhaustive simulation experiments are conducted. The proposed algorithm is compared with power efficient scheduling and VM consolidation (PESVMC) algorithm on the accounts of RU, energy efficiency and task makespan. Further, the results are also verified in the real cloud environment. The results demonstrate the effectiveness of the proposed ERES algorithm.

     

Ant colony based constrained workflow scheduling for heterogeneous computing systems

The problem of constrained workflow scheduling on heterogeneous computing systems has been of major interest in the recent years. The user requirements are described by defining constraints on the workflow makespan and/or its execution cost. The uncertainty in the activity execution path and the dynamicity in the resource workload may cause some run-time changes of the makespan or cost. To prohibit run-time constraint violation, the system needs robust schedules. In this paper, probability of violation (POV) of constraints is proposed as a criterion for the schedule robustness. An ant colony system is then used to minimize an aggregation of violation of constraints and the POV. Simulation results on real world workflows show the effectiveness of the proposed method in finding feasible schedules. The results also indicate that the proposed method decreases the POV, as well as the expected penalty at run-time.     

A hybrid multi-objective metaheuristic optimization algorithm for scientific workflow scheduling

Cluster Computing - Workflow is composed of some interdependent tasks and workflow scheduling in the cloud environment that refers to sorting the workflow tasks on virtual machines on the cloud...     

HSGA: a hybrid heuristic algorithm for workflow scheduling in cloud systems

In heterogeneous distributed computing systems like cloud computing, the problem of mapping tasks to resources is a major issue which can have much impact on system performance. For some reasons such as heterogeneous and dynamic features and the dependencies among requests, task scheduling is known to be a NP-complete problem. In this paper, we proposed a hybrid heuristic method (HSGA) to find a suitable scheduling for workflow graph, based on genetic algorithm in order to obtain the response quickly moreover optimizes makespan, load balancing on resources and speedup ratio. At first, the HSGA algorithm makes tasks prioritization in complex graph considering their impact on others, based on graph topology. This technique is efficient to reduction of completion time of application. Then, it merges Best-Fit and Round Robin methods to make an optimal initial population to obtain a good solution quickly, and apply some suitable operations such as mutation to control and lead the algorithm to optimized solution. This algorithm evaluates the solutions by considering efficient parameters in cloud environment. Finally, the proposed algorithm presents the better results with increasing number of tasks in application graph in contrast with other studied algorithms.     

Trust-driven and QoS demand clustering analysis based cloud workflow scheduling strategies

Due to the restrictions that most traditional scheduling strategies only cared about users’ quality of service (QoS) time or cost requirements, lacked the effective analysis of users’ real service demand and could not guarantee scheduling security, this paper added trust into workflow’s QoS target and proposed a novel customizable cloud workflow scheduling model. In order to better analyze different user’s service requirements and provide customizable services, the new model divided workflow scheduling into two stages: the macro multi-workflow scheduling as the unit of cloud user and the micro single workflow scheduling. It introduced trust mechanism into multi-workflow scheduling level. And in single workflow scheduling level, it classified workflows into time-sensitive, cost-sensitive and balance three types according to different workflow’s QoS demand parameters using fuzzy clustering method. Based on it, it customized different service strategies for different type. The simulation experiments show that the new schema has some advantages in shortening workflow’s final completion time, achieving relatively high execution success rate and user satisfaction compared to other kindred solutions.     

Elastic resource provisioning for scientific workflow scheduling in cloud under budget and deadline constraints

With the popularization and development of cloud computing, lots of scientific computing applications are conducted in cloud environments. However, current application scenario of scientific computing is also becoming increasingly dynamic and complicated, such as unpredictable submission times of jobs, different priorities of jobs, deadlines and budget constraints of executing jobs. Thus, how to perform scientific computing efficiently in cloud has become an urgent problem. To address this problem, we design an elastic resource provisioning and task scheduling mechanism to perform scientific workflow jobs in cloud. The goal of this mechanism is to complete as many high-priority workflow jobs as possible under budget and deadline constraints. This mechanism consists of four steps: job preprocessing, job admission control, elastic resource provisioning and task scheduling. We perform the evaluation with four kinds of real scientific workflow jobs under different budget constraints. We also consider the uncertainties of task runtime estimations, provisioning delays, and failures in evaluation. The results show that in most cases our mechanism achieves a better performance than other mechanisms. In addition, the uncertainties of task runtime estimations, VM provisioning delays, and task failures do not have major impact on the mechanism’s performance.     

An effective meta-heuristic based multi-objective hybrid optimization method for workflow scheduling in cloud computing environment

Cluster Computing - Cloud computing is an emerging distributed computing model that offers computational capability over internet. Cloud provides a huge level collection of powerful and scalable...     

A divide and conquer approach to deadline constrained cost-optimization workflow scheduling for the cloud

The modeling of complex computational applications as giant computational workflows has been a critically effective means of better understanding the intricacies of applications and of determining the best approach to their realization. It is a challenging assignment to schedule such workflows in the cloud while also considering users’ different quality of service requirements. The present paper introduces a new direction based on a divide-and-conquer approach to scheduling these workflows. The proposed Divide-and-conquer Workflow Scheduling algorithm (DQWS) is designed with the objective of minimizing the cost of workflow execution while respecting its deadline. The critical path concept is the inspiration behind the divide-and-conquer process. DQWS finds the critical path, schedules it, removes the critical path from the workflow, and effectively divides the leftover into some mini workflows. The process continues until only chain structured workflows, called linear graphs, remain. Scheduling linear graphs is performed in the final phase of the algorithm. Experiments show that DQWS outperforms its competitors, both in terms of meeting deadlines and minimizing the monetary costs of executing scheduled workflows.

     

DCHG-TS: a deadline-constrained and cost-effective hybrid genetic algorithm for scientific workflow scheduling in cloud computing

Cluster Computing - Cloud infrastructures are suitable environments for processing large scientific workflows. Nowadays, new challenges are emerging in the field of optimizing workflows such that...     

On the use of meta-heuristics to increase the efficiency of online grid workflow scheduling algorithms

The competitiveness of online algorithms is measured based on the correctness of the results produced and processing time efficiency. Traditionally evolutionary algorithms are not favored in online paradigms because of the large number of iterations involved in the algorithm which translates directly into processing time overhead. In this paper we describe MARS (Management Architecture for Resource Services) online scheduling algorithm which uses Simulated Annealing and concepts from Tabu Search to drastically decrease the processing time of the algorithm. The paper outlines the concepts behind MARS, the components involved and scheduling methodology used. In addition we also identify the time consuming bottlenecks in the performance of the system and how evolutionary algorithms help us soar past them.

Regulation of Homotypic Cell-Cell Adhesion by Branched N-Glycosylation of N-cadherin Extracellular EC2 and EC3 Domains

The effects of altering N-cadherin N-glycosylation on several cadherin-mediated cellular behaviors were investigated using small interfering RNA and site-directed mutagenesis. In HT1080 fibrosarcoma cells, small interfering RNA-directed knockdown of N-acetylglucosaminyltransferase V (GnT-V), a glycosyltransferase up-regulated by oncogene signaling, caused decreased expression of N-linked β(1,6)-branched glycans expressed on N-cadherin, resulting in enhanced N-cadherin-mediated cell-cell adhesion, but had no effect on N-cadherin expression on the cell surface. This effect on adhesion was accompanied by decreased cell migration and invasion, opposite of the effects observed when GnT-V was overexpressed in these cells (Guo, H. B., Lee, I., Kamar, M., and Pierce, M. (2003) J. Biol. Chem. 278, 52412–52424). A detailed study using site-directed mutagenesis demonstrated that three of the eight putative N-glycosylation sites in the N-cadherin sequence showed N-glycan expression. Moreover, all three of these sites, located in the extracellular domains EC2 and EC3, were shown by leucoagglutinating phytohemagglutinin binding to express at least some β(1,6)-branched glycans, products of GnT-V activity. Deletion of these sites had no effect on cadherin levels on the cell surface but led to increased stabilization of cell-cell contacts, cell-cell adhesion- mediated intracellular signaling, and reduced cell migration. We show for the first time that these deletions had little effect on formation of the N-cadherin-catenin complex but instead resulted in increased N-cadherin cis-dimerization. Branched N-glycan expression at three sites in the EC2 and -3 domains regulates N-cadherin-mediated cell-cell contact formation, outside-in signaling, and cell migration and is probably a significant contributor to the increase in the migratory/invasive phenotype of cancer cells that results when GnT-V activity is up-regulated by oncogene signaling.     

Scientific workflow management in proteomics

Data processing in proteomics can be a challenging endeavor, requiring extensive knowledge of many different software packages, all with different algorithms, data format requirements, and user interfaces. In this article we describe the integration of a number of existing programs and tools in Taverna Workbench, a scientific workflow manager currently being developed in the bioinformatics community. We demonstrate how a workflow manager provides a single, visually clear and intuitive interface to complex data analysis tasks in proteomics, from raw mass spectrometry data to protein identifications and beyond.     

Estimation of symbiotic N2 fixation in an Amazon floodplain forest

Sustainable management for existing Amazonian forests requires an extensive knowledge about the limits of ecosystem nutrient cycles. Therefore, symbiotic nitrogen (N₂) fixation of legumes was investigated in a periodically flooded forest of the central Amazon floodplain (Várzea) over two hydrological cycles (20 months) using the ¹⁵N natural abundance method. No seasonal variation in ¹⁵N abundance (δ ¹⁵N values) in trees which would suggest differences in N₂ fixation rates between the terrestrial and the aquatic phase was found. Estimations of the percentage of N derived from atmosphere (%Ndfa) for the nodulated legumes with Neptunia oleracea on the one side and Teramnus volubilis on the other resulted in mean %Ndfa values between 9 and 66%, respectively. More than half of the nodulated legume species had %Ndfa values above 45%. These relatively high N gains are important for the nodulated legumes during the whole hydrological cycle. With a %Ndfa of 4–5% for the entire Várzea forest, N₂ fixation is important for the ecosystem and therefore, has to be taken into consideration for new sustainable land-use strategies in this area.     

Metalloendopeptidases EC 3.4.24.15 and EC 3.4.24.16: potential roles in vascular physiology

The zinc metalloendopeptidases EC 3.4.24.15 (EP24.15) and EC 3.4.24.16 (EP 24.16) are closely relatedubiquitous enzymes, which have well-defined in vitroactivities in generation and degradation of a range ofspecific peptide targets. Despite this, little is knownregarding their roles in whole animal physiology. One of thepeptides degraded by these enzymes in vitro isbradykinin, a mediator with potent effects on the vasculatureat both systemic and local levels. This review summarises thework that has examined the role of EP 24.15/24.16 inregulation of the vascular effects of bradykinin invivo. This work was made possible by the development of aspecific stable inhibitor of these enzymes, JA-2. Use of thisinhibitor has shown that EP 24.15/24.16 are capable ofregulating responses induced by exogenous bradykinin. Thiseffect was observed at a systemic level with an increase inthe hypotensive effect of intravenous bradykinin. Further workis required to determine whether these enzymes also regulatebradykinin produced endogenously.     

Fire in the Brazilian Amazon

Regenerating forests have become a common land-cover type throughout the Brazilian Amazon. However, the potential for these systems to accumulate and store C and nutrients, and the fluxes resulting from them when they are cut, burned, and converted back to croplands and pastures have not been well quantified. In this study, we quantified pre- and post-fire pools of biomass, C, and nutrients, as well as the emissions of those elements, at a series of second- and third-growth forests located in the states of Pará and Rondônia, Brazil. Total aboveground biomass (TAGB) of second- and third-growth forests averaged 134 and 91 Mg ha^–1, respectively. Rates of aboveground biomass accumulation were rapid in these systems, but were not significantly different between second- and third-growth forests, ranging from 9 to 16 Mg ha^–1 year^–1. Residual pools of biomass originating from primary forest vegetation accounted for large portions of TAGB in both forest types and were primarily responsible for TAGB differences between the two forest types. In second-growth forests this pool (82 Mg ha^–1) represented 58% of TAGB, and in third-growth forests (40 Mg ha^–1) it represented 40% of TAGB. Amounts of TAGB consumed by burning of second- and third-growth forests averaged 70 and 53 Mg ha^–1, respectively. Aboveground pre-fire pools in second- and third-growth forests averaged 67 and 45 Mg C ha^–1, 821 and 707 kg N ha^–1, 441 and 341 kg P ha^–1, and 46 and 27 kg Ca ha^–1, respectively. While pre-fire pools of C, N, S and K were not significantly different between second- and third-growth forests, pools of both P and Ca were significantly higher in second-growth forests. This suggests that increasing land use has a negative impact on these elemental pools. Site losses of elements resulting from slashing and burning these sites were highly variable: losses of C ranged from 20 to 47 Mg ha^–1; N losses ranged from 306 to 709 kg ha^–1; Ca losses ranged from 10 to 145 kg ha^–1; and P losses ranged from 2 to 20 kg ha^–1. Elemental losses were controlled to a large extent by the relative distribution of elemental mass within biomass components of varying susceptibilities to combustion and the temperatures of volatilization of each element. Due to a relatively low temperature of volatilization and its concentration in highly combustible biomass pools, site losses of N averaged 70% of total pre-fire pools. In contrast, site losses of P and Ca resulting from burning were 33 and 20% of total pre-fire pools, respectively, as much of the mass of those elements was deposited on site as ash. Pre- and post-fire biomass and elemental pools of second- and third-growth forests, as well as the emissions from those systems, were intermediate between those of primary forests and pastures in the Brazilian Amazon. Overall, regenerating forests have the capacity to act as either large terrestrial sinks or sources of C and nutrients, depending on the course of land-use patterns within the Brazilian Amazon. Combining remote sensing techniques with field measures of aboveground C accumulation in regenerating forests and C fluxes from those forests when they are cut and burned, we estimate that during 1990–1991 roughly 104 Tg of C was accumulated by regenerating forests across the Brazilian Amazon. Further, we estimate that approximately 103 Tg of C was lost via the cutting and burning of regenerating forests across the Brazilian Amazon during this same period. Since average C accumulations (5.5 Mg ha^–1 year^–1) in regenerating forests were 19% of the C lost when such forests are cut and burned (29.3 Mg ha^–1), our results suggest that when less than 19% of the total area accounted for by secondary forests is cut and burned in a given year, those forests will be net accumulators of C during that year. Conversely, when more than 19% of regenerating forests are burned, those forests will be a net source of C to the atmosphere.     

Mixing patterns in Amazon lakes

The diel mixing patterns of two small floodplain lakes, Lago Jacaretinga in the Amazon drainage, and Lago Cristalino in the Rio Negro system, were investigated during both the high-water and low-water states of the Amazon River hydrograph. Measurements included temperature, oxygen, ammonia, phosphate, and chlorophyll. In both lakes thermal stratification developed during the day and was eroded at night. During the low-water period when the lakes were shallow, nocturnal circulation extended to the lake bottom, whereas when the lakes were deeper (greater than about 5 m), circulation did not reach the bottom and an anoxic hypolimnion developed. During the low-water period, percent of oxygen concentrations were relatively high but always less than saturation. Low oxygen concentrations were observed during the high-water period. At all times nocturnal mixing supplied a significant amount of oxygen to the lake ecosystems. Nighttime upward mixing of recycled nitrogen and phosphorus also appeared to be important nutrient sources for algal productivity.