A Lightweight Distributed Framework for Computational Offloading in Mobile Cloud Computing

The latest developments in mobile computing technology have enabled intensive applications on the modern Smartphones. However, such applications are still constrained by limitations in processing potentials, storage capacity and battery lifetime of the Smart Mobile Devices (SMDs). Therefore, Mobile Cloud Computing (MCC) leverages the application processing services of computational clouds for mitigating resources limitations in SMDs. Currently, a number of computational offloading frameworks are proposed for MCC wherein the intensive components of the application are outsourced to computational clouds. Nevertheless, such frameworks focus on runtime partitioning of the application for computational offloading, which is time consuming and resources intensive. The resource constraint nature of SMDs require lightweight procedures for leveraging computational clouds. Therefore, this paper presents a lightweight framework which focuses on minimizing additional resources utilization in computational offloading for MCC. The framework employs features of centralized monitoring, high availability and on demand access services of computational clouds for computational offloading. As a result, the turnaround time and execution cost of the application are reduced. The framework is evaluated by testing prototype application in the real MCC environment. The lightweight nature of the proposed framework is validated by employing computational offloading for the proposed framework and the latest existing frameworks. Analysis shows that by employing the proposed framework for computational offloading, the size of data transmission is reduced by 91%, energy consumption cost is minimized by 81% and turnaround time of the application is decreased by 83.5% as compared to the existing offloading frameworks. Hence, the proposed framework minimizes additional resources utilization and therefore offers lightweight solution for computational offloading in MCC.     

Performance Evaluation of Resource Management in Cloud Computing Environments

Cloud computing is a computational model in which resource providers can offer on-demand services to clients in a transparent way. However, to be able to guarantee quality of service without limiting the number of accepted requests, providers must be able to dynamically manage the available resources so that they can be optimized. This dynamic resource management is not a trivial task, since it involves meeting several challenges related to workload modeling, virtualization, performance modeling, deployment and monitoring of applications on virtualized resources. This paper carries out a performance evaluation of a module for resource management in a cloud environment that includes handling available resources during execution time and ensuring the quality of service defined in the service level agreement. An analysis was conducted of different resource configurations to define which dimension of resource scaling has a real influence on client requests. The results were used to model and implement a simulated cloud system, in which the allocated resource can be changed on-the-fly, with a corresponding change in price. In this way, the proposed module seeks to satisfy both the client by ensuring quality of service, and the provider by ensuring the best use of resources at a fair price.     

JobCenter: an open source, cross-platform, and distributed job queue management system optimized for scalability and versatility

ABSTRACT: BACKGROUND: Laboratories engaged in computational biology or bioinformatics frequently need to run lengthy, multistep, and user-driven computational jobs. Each job can tie up a computer for a few minutes to several days, and many laboratories lack the expertise or resources to build and maintain a dedicated computer cluster. RESULTS: JobCenter is a client-server application and framework for job management and distributed job execution. The client and server components are both written in Java and are cross-platform and relatively easy to install. All communication with the server is client-driven, which allows worker nodes to run anywhere (even behind external firewalls) and provides inherent load balancing. Adding a worker node to the worker pool is as simple as dropping the JobCenter client files onto any computer and performing basic configuration, providing tremendous ease-of-use, flexibility, and limitless horizontal scalability. Each worker installation may be independently configured, including the types of jobs it is able to run. Executed jobs may be written in any language and may include multiple execution steps. CONCLUSIONS: JobCenter is a versatile and scalable distributed job management system that allows laboratories to very efficiently distribute all computational work among all available resources. JobCenter is freely available at http://code.google.com/p/jobcenter/.     

Design and analysis of a distributed grid resource discovery protocol

Computational grids have been emerging as a new paradigm for solving large complex problems over the recent years. The problem space and data set are divided into smaller pieces that are processed in parallel over the grid network and reassembled upon completion. Typically, resources are logged into a resource broker that is somewhat aware of all of the participants available on the grid. The resource broker scheme can be a bottleneck because of the amount of computational power and network bandwidth needed to maintain a fresh view of the grid. In this paper, we propose to place the load of managing the network resource discovery on to the network itself: inside of the routers. In the proposed protocol, the routers contain tables for resources similar to routing tables. These resource tables map IP addresses to the available computing resource values, which are provided through a scoring mechanism. Each resource provider is scored based on the attributes they provide such as the number of processors, processor frequency, amount of memory, hard drive space, and the network bandwidth. The resources are discovered on the grid by the protocol’s discovery packets, which are encapsulated within the TCP/IP packets. The discovery packet visits the routers and look up in the resource tables until a satisfactory resource is found. The protocol is validated by simulations with five different deployment environments.     

Predictable quality of service atop degradable distributed systems

High performance and distributed computing systems such as peta-scale, grid and cloud infrastructure are increasingly used for running scientific models and business services. These systems experience large availability variations through hardware and software failures. Resource providers need to account for these variations while providing the required QoS at appropriate costs in dynamic resource and application environments. Although the performance and reliability of these systems have been studied separately, there has been little analysis of the lost Quality of Service (QoS) experienced with varying availability levels. In this paper, we present a resource performability model to estimate lost performance and corresponding cost considerations with varying availability levels. We use the resulting model in a multi-phase planning approach for scheduling a set of deadline-sensitive meteorological workflows atop grid and cloud resources to trade-off performance, reliability and cost. We use simulation results driven by failure data collected over the lifetime of high performance systems to demonstrate how the proposed scheme better accounts for resource availability.     

Micro-Level Adaptation,Macro-Level Selection,and the Dynamics of Market Partitioning

This paper provides a micro-foundation for dual market structure formation through partitioning processes in marketplaces by developing a computational model of interacting economic agents. We propose an agent-based modeling approach, where firms are adaptive and profit-seeking agents entering into and exiting from the market according to their (lack of) profitability. Our firms are characterized by large and small sunk costs, respectively. They locate their offerings along a unimodal demand distribution over a one-dimensional product variety, with the distribution peak constituting the center and the tails standing for the peripheries. We found that large firms may first advance toward the most abundant demand spot, the market center, and release peripheral positions as predicted by extant dual market explanations. However, we also observed that large firms may then move back toward the market fringes to reduce competitive niche overlap in the center, triggering nonlinear resource occupation behavior. Novel results indicate that resource release dynamics depend on firm-level adaptive capabilities, and that a minimum scale of production for low sunk cost firms is key to the formation of the dual structure.     

Efficient Nash Equilibrium Resource Allocation Based on Game Theory Mechanism in Cloud Computing by Using Auction

One of the most complex issues in the cloud computing environment is the problem of resource allocation so that, on one hand, the cloud provider expects the most profitability and, on the other hand, users also expect to have the best resources at their disposal considering the budget constraints and time. In most previous work conducted, heuristic and evolutionary approaches have been used to solve this problem. Nevertheless, since the nature of this environment is based on economic methods, using such methods can decrease response time and reducing the complexity of the problem. In this paper, an auction-based method is proposed which determines the auction winner by applying game theory mechanism and holding a repetitive game with incomplete information in a non-cooperative environment. In this method, users calculate suitable price bid with their objective function during several round and repetitions and send it to the auctioneer; and the auctioneer chooses the winning player based the suggested utility function. In the proposed method, the end point of the game is the Nash equilibrium point where players are no longer inclined to alter their bid for that resource and the final bid also satisfies the auctioneer’s utility function. To prove the response space convexity, the Lagrange method is used and the proposed model is simulated in the cloudsim and the results are compared with previous work. At the end, it is concluded that this method converges to a response in a shorter time, provides the lowest service level agreement violations and the most utility to the provider.     

Micro-economics based resource allocation in Grid-Federation environment

A Grid-Federation environment is composed of a collection of autonomous and selfish distributed cluster resource managers. These selfish managers participate in Grid-Federation to share their resources. Market models could be used to motivate the self-interested participants to share their resources. In this paper, firstly, a market for resource exchange in grid federation environment is established. Then, in order that the market reaches a Walrasian equilibrium, a computationally tractable mechanism is proposed. A Walrasian equilibrium problem consists of finding a set of prices and allocations of resources in such a way that the cluster resource managers could maximize their utilities and the market clears. Market clears when the resource supply equals to the demand. We show that in a Walrasian equilibrium, the Grid Federation market reaches an efficient resource allocation.     

MRPack: Multi-Algorithm Execution Using Compute-Intensive Approach in MapReduce

Large quantities of data have been generated from multiple sources at exponential rates in the last few years. These data are generated at high velocity as real time and streaming data in variety of formats. These characteristics give rise to challenges in its modeling, computation, and processing. Hadoop MapReduce (MR) is a well known data-intensive distributed processing framework using the distributed file system (DFS) for Big Data. Current implementations of MR only support execution of a single algorithm in the entire Hadoop cluster. In this paper, we propose MapReducePack (MRPack), a variation of MR that supports execution of a set of related algorithms in a single MR job. We exploit the computational capability of a cluster by increasing the compute-intensiveness of MapReduce while maintaining its data-intensive approach. It uses the available computing resources by dynamically managing the task assignment and intermediate data. Intermediate data from multiple algorithms are managed using multi-key and skew mitigation strategies. The performance study of the proposed system shows that it is time, I/O, and memory efficient compared to the default MapReduce. The proposed approach reduces the execution time by 200% with an approximate 50% decrease in I/O cost. Complexity and qualitative results analysis shows significant performance improvement.     

Migration cost and profit oriented cloud federation formation: hedonic coalition game based approach

Cloud federation has paved the way for cloud service providers (CSP) to collaborate with other CSPs to serve users’ resource requests, which are prohibitively high for any single CSP during peak time. Moreover, to entice different CSPs to participate in federation, it is necessary to maximize the profit of all CSPs involved in the federation. Further, federation enables overloaded CSPs to distribute their load among other underloaded member CSPs of federation by migrating the virtual machines (VM). Migration of VM among member CSPs of federation, also enables to increase the reliability and availability of cloud services on occurrence of faults in the datacenters of CSPs. Thus it becomes important for CSPs to form a federation with other CSPs, in such a way that the migration cost of VMs between CSPs of the same federation is minimized and simultaneously profit of CSPs in federation is maximized. In this paper, we model the problem of forming federation among CSPs as a hedonic coalition game, with a utility function depending on profit and migration cost, with the objective of maximizing the former and minimizing the latter. We propose an algorithm to solve this hedonic game and compare its performance with other existing game-theory based cloud federation formation mechanisms.     

Exploiting performance characterization of BLAST in the grid

Sequence analysis has become essential to the study of genomes and biological research in general. Basic Local Alignment Search Tool (BLAST) leads the way as the most accepted method for performing necessary query searches and analysis of discovered genes. Combating growing data sizes, with the goal of speeding up job runtimes, scientist are resorting to grid computing technologies. However, grid environments are characterized by dynamic, heterogeneous, and transient state of available resources causing major hindrance to users when trying to realize user-desired levels of service. This paper analyzes performance characteristics of NCBI BLAST on several resources and captures influence of resource characteristics and job parameters on BLAST job runtime across those resources. Obtained results are summarized as a set of principles characterizing performance of NCBI BLAST across homogeneous and heterogeneous environments. These principles are then applied and verified through creation of a grid-enabled BLAST wrapper application called Dynamic BLAST. Results show runtime savings up to 50% and resource utilization improvement of approximately 40%.     

Decreasing functional responses as a result of adaptive consumer behavior

Summary Several different mechanisms that may produce decreasing functional responses are investigated using models that assume that an optimally foraging consumer is exploiting one or two resources. Decreasing functional responses are associated with situations in which there are costs to resource consumption. If the process of resource acquisition has costs, decreasing functional responses may occur when there is a single homogeneous resource. If the cost is solely a function of the amount of resource ingested, decreasing functional responses on a single resource do not occur. Both types of cost can produce decreasing functional responses when there are two resource types and a trade-off relationship between consumption of one and consumption of the other. Decreasing functional responses seem to be most likely to occur on a food that yields high benefits and costs per unit of foraging time or effort when there is an alternative resource which yields low benefits and costs. Given this type of foraging choice, the functional response is most likely to decrease when the benefits of ingestion increase at a decreasing rate, and the costs of ingestion increase at an increasing rate with amount ingested. An important and unique consequence of decreasing functional responses is the possibility of population cycles in differential equation models of consumer-resource systems with non-reproducing resources; this is illustrated with a simple comsumer-resource model.     

Distraction sneakers decrease the expected level of aggression within groups: a game-theoretic model

Hawk-dove games have been extensively used to predict the conditions under which group-living animals should defend their resources against potential usurpers. Typically, game-theoretic models on aggression consider that resource defense may entail energetic and injury costs. However, intruders may also take advantage of owners who are busy fighting to sneak access to unguarded resources, imposing thereby an additional cost on the use of the escalated hawk strategy. In this article we modify the two-strategy hawk-dove game into a three-strategy hawk-dove-sneaker game that incorporates a distraction-sneaking tactic, allowing us to explore its consequences on the expected level of aggression within groups. Our model predicts a lower proportion of hawks and hence lower frequencies of aggressive interactions within groups than do previous two-strategy hawk-dove games. The extent to which distraction sneakers decrease the frequency of aggression within groups, however, depends on whether they search only for opportunities to join resources uncovered by other group members or for both unchallenged resources and opportunities to usurp.     

Clutch-size behavior and coexistence in ephemeral-patch competition models

Systems of patchy, ephemeral resources often support surprisingly diverse assemblages of consumer insects. Aggregation of consumer individuals over the landscape of patches has been suggested as one mechanism that can stabilize competition among consumer species. One mechanism for larval aggregation is the laying of eggs in clutches by females traveling among patches to distribute their total fecundity. We use simulation models to explore the consequences, for coexistence of competitors, of larval aggregation that arises from clutch laying. Contrary to some previous treatments, we find that clutch laying can be strongly stabilizing and under certain conditions can be sufficient to allow competitors to coexist stably. We extend these models by considering clutch size as a variable that responds to the abundance of resource patches. Such a relationship might be expected because females should lay their eggs in fewer but larger clutches when the cost of travel among patches is high (because patches are rare). When females adjust clutch size in response to resource abundance, coexistence can be easiest when resource patches are scarce and most difficult when resources are abundant.     

Response Surface Modelling for Performance Analysis of Scientific Workflow Application in Cloud

Scientific workflow applications are used by scientists to carry out research in various domains such as Physics, Chemistry, Astronomy etc. These applications require huge computational resources and currently cloud platform is used for efficiently running these applications. To improve the makespan and cost in workflow execution in cloud platform it requires to identify proper number of Virtual Machines (VM) and choose proper VM type. As cloud platform is dynamic, the available resources and the type of the resources are the two important factors on the cost and makespan of workflow execution. The primary objective of this work is to analyze the relationship among the cloud configuration parameters (Number of VM, Type of VM, VM configurations) for executing scientific workflow applications in cloud platform. In this work, to accurately analyze the influence of cloud platform resource configuration and scheduling polices a new predictive modelling using Box–Behnken design which is one of the modelling technique of Response Surface Methodology (RSM). It is used to build quadratic mathematical models that can be used to analyze relationships among input and output variables. Workflow cost and makespan models were built for real world scientific workflows using ANOVA and it was observed that the models fit well and can be useful in analyzing the performance of scientific workflow applications in cloud

     

Local competition sparks concerns for fairness in the ultimatum game

Humans reject uneven divisions of resources, even at personal cost. This is observed in countless experiments using the ultimatum game, where a proposer offers to divide a resource with a responder who either accepts the division or rejects it (whereupon both earn zero). Researchers debate why humans evolved a psychology that is so averse to inequity within partnerships. We suggest that the scale of competition is crucial: under local competition with few competitors, individuals reject low offers, because they cannot afford to be disadvantaged relative to competitors. If one competes against the broader population (i.e. global competition), then it pays to accept low offers to increase one''s absolute pay-off. We support this intuition with an illustrative game-theoretical model. We also conducted ultimatum games where participants received prizes based on pay-offs relative to immediate partners (local competition) versus a larger group (global competition). Participants demanded higher offers under local competition, suggesting that local competition increases people''s demands for fairness and aversion to inequality.     

Competition over Personal Resources Favors Contribution to Shared Resources in Human Groups

Members of social groups face a trade-off between investing selfish effort for themselves and investing cooperative effort to produce a shared group resource. Many group resources are shared equitably: they may be intrinsically non-excludable public goods, such as vigilance against predators, or so large that there is little cost to sharing, such as cooperatively hunted big game. However, group members'' personal resources, such as food hunted individually, may be monopolizable. In such cases, an individual may benefit by investing effort in taking others'' personal resources, and in defending one''s own resources against others. We use a game theoretic “tug-of-war” model to predict that when such competition over personal resources is possible, players will contribute more towards a group resource, and also obtain higher payoffs from doing so. We test and find support for these predictions in two laboratory economic games with humans, comparing people''s investment decisions in games with and without the options to compete over personal resources or invest in a group resource. Our results help explain why people cooperatively contribute to group resources, suggest how a tragedy of the commons may be avoided, and highlight unifying features in the evolution of cooperation and competition in human and non-human societies.     

ALTERNATIVE MODELS OF CHARACTER DISPLACEMENT AND NICHE SHIFT. I. ADAPTIVE SHIFTS IN RESOURCE USE WHEN THERE IS COMPETITION FOR NUTRITIONALLY NONSUBSTITUTABLE RESOURCES

This paper analyzes the influence of the nutritional status of resources on the adaptive response to interspecific competition in a consumer of those resources. The two cases compared are that in which the resources are nutritionally perfectly substitutable (in the sense of Leon and Tumpson [1975]) and that in which the resources are nonsubstitutable. Each nonsubstitutable resource must be consumed at a certain rate for population growth to occur. Evolutionarily stable strategies of resource utilization are found using models of competition for two resources. If competition occurs solely via the consumer species's effects on resource density, the adaptive response in a consumer's resource-acquisition traits is: a) divergence away from its competitor's resource-acquisition traits if resources are perfectly substitutable and b) convergence towards the competitor's resource-acquisition traits if resources are nonsubstitutable. Exceptions to both of these generalizations may occur if competitor population density affects a consumer species's per capita growth rate independently of effects on resource density. Plants and herbivores often use nonsubstitutable resources. The lack of studies of adaptive responses to competition in these organisms may be responsible for the lack of documented examples of competitive convergence.     

Evolutionary computation and grid computing to optimise nuclear fusion devices

Nuclear fusion is the next generation of energy, but many problems are still present in current nuclear fusion devices. Some of these problems can be solved by means of modeling tools. These tools usually require a large time to finish their computations and they also use a large number of parameters to represent the behaviour of nuclear fusion devices. Here, the possibility to introduce evolutionary algorithms (EAs) like genetic algorithms (GAs) or Scatter Search (SS) to look for optimised configurations offers a great solution for some of these problems. Since these applications require a high computational cost to perform their operations, the use of the grid arises as an ideal environment to carry out these tests. Because of the high complexity of the problems we are trying to optimise, the distributed paradigm as well as the number of computational resources of the grid represents an excellent alternative to carry out experiments to modelize and improve nuclear fusion devices by executing these tools. The results obtained clearly improve the configuration of existing devices.     

SpeQuloS: a QoS service for hybrid and elastic computing infrastructures

The large choice of Distributed Computing Infrastructures (DCIs) available allows users to select and combine their preferred architectures amongst Clusters, Grids, Clouds, Desktop Grids and more. In these hybrid DCIs, elasticity is emerging as a key property. In elastic infrastructures, resources available to execute application continuously vary, either because of application requirements or because of constraints on the infrastructure, such as node volatility. In the former case, there is no guarantee that the computing resources will remain available during the entire execution of an application. In this paper, we show that Bag-of-Tasks (BoT) execution on these “Best-Effort” infrastructures suffer from a drop of the task completion rate at the end of the execution. The SpeQuloS service presented in this paper improves the Quality of Service (QoS) of BoT applications executed on hybrid and elastic infrastructures. SpeQuloS monitors the execution of the BoT, and dynamically supplies fast and reliable Cloud resources when the critical part of the BoT is executed. SpeQuloS offers several features to hybrid DCIs users, such as estimating completion time and execution speedup. Performance evaluation shows that BoT executions can be accelerated by a factor 2, while offloading less than 2.5 % of the workload to the Cloud. We report on several scenarios where SpeQuloS is deployed on hybrid infrastructures featuring a large variety of infrastructures combinations. In the context of the European Desktop Grid Initiative (EDGI), SpeQuloS is operated to improve QoS of Desktop Grids using resources from private Clouds. We present a use case where SpeQuloS uses both EC2 regular and spot instances to decrease the cost of computation while preserving a similar QoS level. Finally, in the last scenario SpeQuloS allows to optimize Grid5000 resources utilization.