Search

This paper discusses the load-balanced task allocation problem in the grid transaction processing system to maximize reliability. Finding the solution of optimal load-balanced task allocation is known to be an NP-hard. This paper presents a load-balanced task allocation based cuckoo search-ant colony optimization (LBTA_CSACO) method for this problem. The LBTA_CSACO is based on the cooperative behavior of cuckoo search and ant colony optimization to nd a collection of task allocation solutions. This paper also models the reliability of the system with the help of the availability of the system. The motive of this work is to maximize the reliability of the system. After the simulation, six existing algorithms are taken for the comparison of the results; Honey Bee Optimization (HBO), Ant Colony Optimization (ACO), Hierarchical Load Balanced Algorithm (HLBA), Dynamic and Decentralized Load Balancing (DLB), and Randomized respectively. [ABSTRACT FROM AUTHOR]

Due to the explosive increase in the production and sharing of digital visual media such as photos, animations, films and video clips, the need to intentionally or unintentionally create mosaic blocks to effectively cover user-designated regions within images has grown. In this paper, a method using boundary characteristics to effectively detect the grid-type mosaic blocks existing within the input image is proposed. Initially, the Canny edge is detected from the input image. Then, the boundary characteristics of mosaic blocks are extracted from the detected edges, and the candidate regions which may contain mosaic blocks are detected. After this stage, geometric characteristics are used to eliminate non-mosaic blocks and select actual mosaic blocks. In the experiment performed in this paper, it was observed that the method using boundary characteristics achieved more robust detection of the grid-type mosaic blocks from various input images than other existing methods. The mosaic-detection method proposed in this paper is expected to be valuable for applications in various fields. [ABSTRACT FROM AUTHOR]

Distributed e-Infrastructure is a key component of modern BIG Science. Service discovery in e-Science environments, such as Worldwide LHC Computing Grid (WLCG), is a crucial functionality that relies on service registry. In this paper we re-formulate the requirements for the service endpoint registry based on our more than 10 years experience with many systems designed or used within the WLCG e-Infrastructure. To satisfy those requirements the paper proposes a novel idea to use the existing well-established Domain Name System (DNS) infrastructure together with a suitable data model as a service endpoint registry. The presented ARC Hierarchical Endpoints Registry (ARCHERY) system consists of a minimalistic data model representing services and their endpoints within e-Infrastructures, a rendering of the data model embedded into DNS-records, a lightweight software layer for DNS-record management and client-side data discovery. Our approach for the ARCHERY registry required minimal software development and inherits all the benefits of one of the most reliable distributed information discovery source of the internet, the DNS infrastructure. In particular, deployment, management and operation of ARCHERY is fully relying on DNS. Results of ARCHERY deployment use-cases are provided together with performance analysis. [ABSTRACT FROM AUTHOR]

This paper applies the slicing technique to extract the contour feature line. The sliced data are projected on the plane to obtain the feature line of the slice profile by grid computing, which can directly establish a three-dimensional model. Due to redundancy and the uneven distribution of the point cloud, it is difficult to determine the slice thickness, causing projection error and disconnection of the contour line. In this paper, the projection error and efficiency of calculation are improved with twice data layer compression to extract the point cloud data generated by the contour. In the contour feature extraction, the line segment code is established using its structure to calculate the contour boundary by connectivity judgment. Through experimental comparison, the algorithm using the line segment to determine the boundary is more effective and robust than the eight neighborhood algorithm. [ABSTRACT FROM AUTHOR]

Cloud computing is the fastest growing distributed computing paradigm that provides online IT resources on demand by following a pay-as-you-go billing model. The success of this computing paradigm enables cloud providers to offer an extensive collection of parallel computing resources to deal with Big Data workflow scheduling problems. Although, workflow scheduling has been extensively studied, however, most of them are unable to achieve user-specified deadline constraints at the cheap cost. In this paper, a Dynamic Cost-Efficient Deadline-Aware (DCEDA) heuristic algorithm is proposed for scheduling Big Data workflow that produces the cheapest schedule while achieving the deadline constraints. DCEDA dynamically takes appropriate scheduling decisions for workflow tasks based on the fact that deadline constraint is not violated in the future. Also, it continuously monitors the VM pool for identifying the active idle VMs that incur extra costs and overheads, and subsequently de-provision them. The experimental analysis based on Montage workflow and randomly generated synthetic workflow with various characteristics prove that DCEDA delivers better performance in comparison to the existing algorithms. [ABSTRACT FROM AUTHOR]

Scheduling of transactions in the grid computing system is known to be an NP-hard problem. In order to solve this problem, this paper introduces a hybrid approach named cuckoo search-ant colony optimization. The approach is to dynamically generate an optimal schedule by clustering the resources considering their load so as to complete the transactions within their deadlines as well as utilizing the resources in an efficient way. The approach also balances the load of the system before scheduling the transactions. We use cuckoo search method for making clusters of resources based on their load. We use ant colony optimization for selecting the appropriate and optimal resources. We evaluate the performance of the proposed algorithm with six existing algorithms. The results illustrate that an important advantage of the cuckoo search-ant colony optimization algorithm is its speed of clustering and ability to obtain faster and feasible load balanced schedules. [ABSTRACT FROM AUTHOR]

Cloud computing has become the most attractive platform compared to grid computing, that offers several services such as infrastructure as a service, platform as a service, and software as a service, where the users can consume these services on the cloud and pay based on their consumption and on the fulfilment of Quality of Service (QoS) constraints such as deadline and budget. Hence, to schedule the tasks effectively, cost monetary must be considered while optimising implementation time performance under users' defined constraints. In this paper, the Deadline Budget Scheduling (DBS) model is proposed to execute the users' tasks on Virtual Machines (VMs) under the QoS constraints at less execution time. In our proposal, users' tasks will be assigned to appropriate VM which meets either of the two constraints namely (deadline and budget) or one of the constraints based on user satisfaction. Makespan and cost are calculated to evaluate our proposed DBS model with state of the art algorithms. The experimental results illustrate that DBS outperforms other algorithms by minimizing the makespan and cost. [ABSTRACT FROM AUTHOR]

Security is a major concern of modern real-time applications, besides requiring stringent latency bound. However, encryption algorithms are computation intensive task which impacts the timeliness of the real-time applications. Therefore, there exists a trade-off between the desired level of security and the service guarantee. In this paper, we propose a security-aware dynamic scheduling algorithm (SADSA) using a grid of computational elements (CEs) which performs this trade-off and tries to maximize the instantaneous average security level of the packets besides providing a guaranteed service. As packets arrive, we first assign them to the CEs based on the utilization value of a CE, which is the ratio of completion time and a deadline of the last packet in a CE. The security level of all the packets is then dynamically adjusted to meet the minimum required security level while maximizing the average security level of all the packets in that CE. We first show that the proposed assignment algorithm is NP-hard, is 2-competitive to the optimal solution, and that the proposed algorithm provides a sub-optimal solution. Further, using extensive simulation, we show that the proposed SADSA algorithm performs better in terms of guarantee ratio, average security level and overall performance compared to the existing algorithms. [ABSTRACT FROM AUTHOR]

Computational grids have the potential for solving large-scale scientific problems using heterogeneous and geographically distributed resources. At this scale, computer resources and network failures are no more exceptions, but belong to the normal system behavior. Therefore, one of the most valuable characteristics of grid tools, apart from the performance they can achieve, is fault tolerance, which is a significant and complex issue in grid computing systems. In this paper, we propose a fault tolerant model for grid computing systems namely DCFT. This model is based on dynamic colored graphs without replication of computer resources. The proposed faut tolerance model consists of two stages. In the first stage, each node is described by a state vector. We color each attribute of the state vector as three colors (green, blue and red) based on its level of performance. In the second stage, we classify the nodes of a grid into three categories: the identical computer resources in term of performance, the more efficient ones and the less efficient ones. We used the colors of the nodes to develop a new strategy for fault tolerance based on the level of performance. A simulation of the proposed model using SimGrid simulator and Graphstream is conducted. Experimental results show that the proposed model performs very well in a large grid environment. [ABSTRACT FROM AUTHOR]

Agent-based simulation models with large experiments for a precise and robust result over a vast parameter space are becoming a common practice, where enormous runs intrinsically require highly intensive computational resources. This paper proposes a grid based simulation environment, named Social Macro Scope (SOMAS) to support parallel exploration on agent-based models with vast parameter space. We focus on three types of simulation methods for agent-based models with various objectives (1) forward simulation to conduct experiments in a straightforward way by simply operating sets of parameter values to perform sensitivity analysis; (2) inverse simulation to search for solutions that reduce the error between simulated results and actual data by means of solving 'inverse problem', which executes the simulation steps in a reverse order and employs optimization algorithms to fit the simulation results to the desired objectives; and (3) model selection to find an optimal model structure with subset of parameters and procedures, which conducts two-layer optimization to obtain a simple and more accurate simulation result. We have confirmed the practical scalability and efficiency of SOMAS by one case study in history simulation domain. [ABSTRACT FROM AUTHOR]

For natural group movement of non player characters (NPCs) in a computer game, an efficient planning algorithm is necessary. This paper presents a grid window-based path planning algorithm for realistic group movement. The global path is planned in a static environment and the path is locally repaired to avoid dynamic obstacles during execution. The planning and execution processes are performed for the group, not for individual NPCs by using a 2D virtual grid window covering all the NPCs. The movement of each NPC is generated inside the grid window without complicated procedures to detect collisions. We implement and test the algorithm on a polygonal world modeling a real game background. The simulation results show that the proposed method provides natural group movement and dynamic obstacle avoidance, and the experimental result with various numbers of NPCs shows consistent performance. [ABSTRACT FROM AUTHOR]

Many research institutions are deploying computing clusters based on a shared/buy-in paradigm. Such clusters combine shared computers, which are free to be used by all users, and buy-in computers, which are computers purchased by users for semi-exclusive use. The purpose of this paper is to characterize the typical behavior and performance of a shared/buy-in computing cluster, using data traces from the Shared Computing Cluster (SCC) at Boston University that runs under this paradigm as a case study. Among our main findings, we show that the semi-exclusive policy, which allows any SCC user to use idle buy-in resources for a limited time, increases the utilization of buy-in resources by 17.4%, thus significantly improving the performance of the system as a whole. We find that jobs allowed to run on idle buy-in resources arrive more frequently and run for a shorter time than other jobs. Finally, we identify the run time limit (i.e., the maximum time during which a job is allowed to use resources) and the type of parallel environment as two factors that have a significant impact on the different performance experienced by shared and buy-in jobs. [ABSTRACT FROM AUTHOR]

Loosely coupled applications composed of a potentially very large number (from tens of thousands to even billions) of tasks are commonly used in high-throughput computing and many-task computing paradigms. To efficiently execute large-scale computations which can exceed the capability in a single type of computing resources within expected time, we should be able to effectively integrate resources from heterogeneous distributed computing (HDC) systems such as clusters, grids, and clouds. In this paper, we quantitatively analyze the performance of three different real scientific applications consisting of many tasks on top of HDC systems based on a partnership of distributed computing clusters, grids, and clouds to understand the application and resource characteristics, and show practical issues that normal scientific users can face during the course of leveraging these systems. Our experimental study shows that the performance of a loosely coupled application can be significantly affected by the characteristics of a HDC system, along with hardware specification of a node, and their impacts on the performance can vary widely depending on the resource usage pattern of each application. We then devise a preference-based scheduling algorithm that can reflect characteristics and resource usage patterns of various loosely coupled applications running on top of HDC systems from our experimental study. Our preference-based scheduling algorithm can allocate the resources from different HDC systems to loosely coupled applications based on the preferences of the applications for the HDC systems. We evaluate the overall system performance over various preference types, using trace-based simulations, which can be determined based on different factors such as CPU specifications and application throughputs. Our simulation results demonstrate the importance of understanding the application and resource characteristics on effective scheduling of loosely coupled applications on the HDC systems. [ABSTRACT FROM AUTHOR]

Data Grid integrates geographically distributed resources for solving data sensitive scientific applications. Dynamic data replication algorithms are becoming increasingly valuable in solving large-scale, realistic, difficult problems, and selecting replica with multiple selection criteria-availability, security and time- is one of these problems. The current algorithms do not offer balanced QoS levels and the mechanism of rating QoS parameters. In this paper, we propose a new replica selection strategy, which based on response time and security. However, replication should be used wisely because the storage size of each Data Grid site is limited. Thus, the site must keep only the important replicas. We also present a new replica replacement strategy based on the availability of the file, the last time the replica was requested, number of access, and size of replica. We evaluate our algorithm using the OptorSim simulator and find that it offers better performance in comparison with other algorithms in terms of mean job execution time, effective network usage, SE usage, replication frequency, and hit ratio. [ABSTRACT FROM AUTHOR]

Large-scale scientific applications from various scientific domains (e.g., astronomy, physics, pharmaceuticals, chemistry, etc.) usually require substantial amounts of computing resources and storage space. International Grid computing resources can be a viable choice for supporting these challenging applications so that effectively locating suitable computing resources with minimal allocation overhead can be crucial. However, Grid resource availability is highly unstable and current Grid Information Service (GIS) cannot provide accurate state information. This can make it very difficult for users to schedule the jobs on the Grid system and to map tasks on appropriate available resources. In this paper, we present SCOUT system that can periodically profile Grid computing elements based on available number of CPU cores and average response time, and monitor the performance of each CE in the Virtual Organizations (VO). Micro-benchmark experimental results demonstrate that leveraging profiled data by SCOUT can improve the success rate of task executions and reduce the average response time. [ABSTRACT FROM AUTHOR]

Cyber-physical systems (CPS) are composed of collaborating computational elements that control physical entities. The human desire to acquire useful information and to automatically control devices anytime and anywhere has increased the necessity to develop systems with high reliability. However, the CPS associated with the physical world and cyber world involve managing complexity and incurring the respective maintenance costs, such that it has been impossible to produce systems that are completely reliable. Thus, this paper presents an 'Autonomic Control System for High-reliable Cyber-Physical Systems' that is comprised of eight processes, including fault analysis, fault event analysis, fault modeling, fault state interpretation, fault strategy decision, fault detection, diagnosis & reasoning, and maneuver execution. These processes facilitate the design and implementation of an autonomic control system that is superior to what was available before. As proof of the approach, we used an intelligent service robot (ISR) as a case study. The experimental results show that the ISR is able to detect a fault event during autonomic control of the CPS. [ABSTRACT FROM AUTHOR]

Smart grid requires sharing sensitive data to external researchers. Attribute encryption is a common technique used in data sharing. Unfortunately, existing revocation mechanisms do not consider the following two issues. One is that the revoked user may save intermediate values computed in the past to illegally decrypt the updated cipher text. The other is that the update parameters of keys can be leaked to the revoked user, which leads to revocation failure. To address the above issues, we propose a verifiable outsourcing decryption and data sharing scheme, in which we introduce version parameters of ciphertexts and keys, and associate the update parameters of keys with each user to achieve security-enhanced revocation. In addition, a formal security proof is given under the DBDH assumption. Finally, we evaluate the performance of the scheme and the results show that the proposed scheme is more effective than current schemes. [ABSTRACT FROM AUTHOR]

Traditional centralized cloud services face challenges, such as high communication delay, single point of failure, etc. Edge computing is one of distributed computing services in which resources are placed closer to users, and thus is more robust and can reduce communication delay. Although outsourcing data to the edge servers can bring great convenience, it also brings serious security threats. In order to provide image retrieval while ensuring users' data privacy, a privacy-preserving content-based image retrieval scheme in edge environment is proposed. Considering the distributed characteristics of edge environment and the requirement of lightweight computing, we design a secure interaction protocol completed through the collaborative cooperation of two or more edge servers. This scheme not only protects data privacy, but also has low communication overhead and delay as well as low computing complexity, therefore it is more suitable for edge computing environment. Theoretical analysis and experiments show that our scheme has high security, retrieval accuracy and efficiency. [ABSTRACT FROM AUTHOR]

The home care crew scheduling (HCCS) problem is a planning task whose goal is to allocate a set of professional caregivers in the most efficient way to perform a number of assistencial and health care visits to the customers private homes. This is part of an important trend in advanced health care systems, to promote “independent living” specially in situations of dependency on long-term care. This not only ensures a higher quality of life but also a lower cost for society. Real instances of the HCCS problem are large and highly constrained due to both caregivers’ contract limitations and customers’ needs. This paper presents an advanced parallel model that solves HCCS problems using a grid-based asynchronous evolutionary algorithm (EA). Our approach has been tested using a grid computing facility of up to 300 nodes. The algorithm is a modified $$(1 + \lambda )$$(1+λ) EA, parallelized using a master/worker model that minimizes communication requirements and processor bottlenecks by distributing both the execution of the EA operators and the evaluation of solutions. We have used three large real-world instances provided by a private company to perform experimentation with different configurations of the EA and number of workers. Results show that our algorithm achieves solutions that clearly outperform the solution provided by the company and the grid-based algorithm is able to handle real world HCCS problemsThe home care crew scheduling (HCCS) problem is a planning task whose goal is to allocate a set of professional caregivers in the most efficient way to perform a number of assistencial and health care visits to the customers private homes. This is part of an important trend in advanced health care systems, to promote “independent living” specially in situations of dependency on long-term care. This not only ensures a higher quality of life but also a lower cost for society. Real instances of the HCCS problem are large and highly constrained due to both caregivers’ contract limitations and customers’ needs. This paper presents an advanced parallel model that solves HCCS problems using a grid-based asynchronous evolutionary algorithm (EA). Our approach has been tested using a grid computing facility of up to 300 nodes. The algorithm is a modified $$(1 + \lambda )$$(1+λ) EA, parallelized using a master/worker model that minimizes communication requirements and processor bottlenecks by distributing both the execution of the EA operators and the evaluation of solutions. We have used three large real-world instances provided by a private company to perform experimentation with different configurations of the EA and number of workers. Results show that our algorithm achieves solutions that clearly outperform the solution provided by the company and the grid-based algorithm is able to handle real world HCCS problemsThe home care crew scheduling (HCCS) problem is a planning task whose goal is to allocate a set of professional caregivers in the most efficient way to perform a number of assistencial and health care visits to the customers private homes. This is part of an important trend in advanced health care systems, to promote “independent living” specially in situations of dependency on long-term care. This not only ensures a higher quality of life but also a lower cost for society. Real instances of the HCCS problem are large and highly constrained due to both caregivers’ contract limitations and customers’ needs. This paper presents an advanced parallel model that solves HCCS problems using a grid-based asynchronous evolutionary algorithm (EA). Our approach has been tested using a grid computing facility of up to 300 nodes. The algorithm is a modified $$(1 + \lambda )$$(1+λ) EA, parallelized using a master/worker model that minimizes communication requirements and processor bottlenecks by distributing both the execution of the EA operators and the evaluation of solutions. We have used three large real-world instances provided by a private company to perform experimentation with different configurations of the EA and number of workers. Results show that our algorithm achieves solutions that clearly outperform the solution provided by the company and the grid-based algorithm is able to handle real world HCCS problemsThe home care crew scheduling (HCCS) problem is a planning task whose goal is to allocate a set of professional caregivers in the most efficient way to perform a number of assistencial and health care visits to the customers private homes. This is part of an important trend in advanced health care systems, to promote “independent living” specially in situations of dependency on long-term care. This not only ensures a higher quality of life but also a lower cost for society. Real instances of the HCCS problem are large and highly constrained due to both caregivers’ contract limitations and customers’ needs. This paper presents an advanced parallel model that solves HCCS problems using a grid-based asynchronous evolutionary algorithm (EA). Our approach has been tested using a grid computing facility of up to 300 nodes. The algorithm is a modified $$(1 + \lambda )$$(1+λ) EA, parallelized using a master/worker model that minimizes communication requirements and processor bottlenecks by distributing both the execution of the EA operators and the evaluation of solutions. We have used three large real-world instances provided by a private company to perform experimentation with different configurations of the EA and number of workers. Results show that our algorithm achieves solutions that clearly outperform the solution provided by the company and the grid-based algorithm is able to handle real world HCCS problemsThe home care crew scheduling (HCCS) problem is a planning task whose goal is to allocate a set of professional caregivers in the most efficient way to perform a number of assistencial and health care visits to the customers private homes. This is part of an important trend in advanced health care systems, to promote “independent living” specially in situations of dependency on long-term care. This not only ensures a higher quality of life but also a lower cost for society. Real instances of the HCCS problem are large and highly constrained due to both caregivers’ contract limitations and customers’ needs. This paper presents an advanced parallel model that solves HCCS problems using a grid-based asynchronous evolutionary algorithm (EA). Our approach has been tested using a grid computing facility of up to 300 nodes. The algorithm is a modified $$(1 + \lambda )$$(1+λ) EA, parallelized using a master/worker model that minimizes communication requirements and processor bottlenecks by distributing both the execution of the EA operators and the evaluation of solutions. We have used three large real-world instances provided by a private company to perform experimentation with different configurations of the EA and number of workers. Results show that our algorithm achieves solutions that clearly outperform the solution provided by the company and the grid-based algorithm is able to handle real world HCCS problemsThe home care crew scheduling (HCCS) problem is a planning task whose goal is to allocate a set of professional caregivers in the most efficient way to perform a number of assistencial and health care visits to the customers private homes. This is part of an important trend in advanced health care systems, to promote “independent living” specially in situations of dependency on long-term care. This not only ensures a higher quality of life but also a lower cost for society. Real instances of the HCCS problem are large and highly constrained due to both caregivers’ contract limitations and customers’ needs. This paper presents an advanced parallel model that solves HCCS problems using a grid-based asynchronous evolutionary algorithm (EA). Our approach has been tested using a grid computing facility of up to 300 nodes. The algorithm is a modified $$(1 + \lambda )$$(1+λ) EA, parallelized using a master/worker model that minimizes communication requirements and processor bottlenecks by distributing both the execution of the EA operators and the evaluation of solutions. We have used three large real-world instances provided by a private company to perform experimentation with different configurations of the EA and number of workers. Results show that our algorithm achieves solutions that clearly outperform the solution provided by the company and the grid-based algorithm is able to handle real world HCCS problemsThe home care crew scheduling (HCCS) problem is a planning task whose goal is to allocate a set of professional caregivers in the most efficient way to perform a number of assistencial and health care visits to the customers private homes. This is part of an important trend in advanced health care systems, to promote “independent living” specially in situations of dependency on long-term care. This not only ensures a higher quality of life but also a lower cost for society. Real instances of the HCCS problem are large and highly constrained due to both caregivers’ contract limitations and customers’ needs. This paper presents an advanced parallel model that solves HCCS problems using a grid-based asynchronous evolutionary algorithm (EA). Our approach has been tested using a grid computing facility of up to 300 nodes. The algorithm is a modified $$(1 + \lambda )$$(1+λ) EA, parallelized using a master/worker model that minimizes communication requirements and processor bottlenecks by distributing both the execution of the EA operators and the evaluation of solutions. We have used three large real-world instances provided by a private company to perform experimentation with different configurations of the EA and number of workers. Results show that our algorithm achieves solutions that clearly outperform the solution provided by the company and the grid-based algorithm is able to handle real world HCCS problemsThe home care crew scheduling (HCCS) problem is a planning task whose goal is to allocate a set of professional caregivers in the most efficient way to perform a number of assistencial and health care visits to the customers private homes. This is part of an important trend in advanced health care systems, to promote “independent living” specially in situations of dependency on long-term care. This not only ensures a higher quality of life but also a lower cost for society. Real instances of the HCCS problem are large and highly constrained due to both caregivers’ contract limitations and customers’ needs. This paper presents an advanced parallel model that solves HCCS problems using a grid-based asynchronous evolutionary algorithm (EA). Our approach has been tested using a grid computing facility of up to 300 nodes. The algorithm is a modified $$(1 + \lambda )$$(1+λ) EA, parallelized using a master/worker model that minimizes communication requirements and processor bottlenecks by distributing both the execution of the EA operators and the evaluation of solutions. We have used three large real-world instances provided by a private company to perform experimentation with different configurations of the EA and number of workers. Results show that our algorithm achieves solutions that clearly outperform the solution provided by the company and the grid-based algorithm is able to handle real world HCCS problems [ABSTRACT FROM AUTHOR]

With the first commercially available 5G infrastructures, worldwide's attention is shifting to the next generation of theorised technologies that might be finally deployable. In this context, the cybersecurity of edge equipment and end-devices must be a top priority as botnets see their spread remarkably increase. Most of them rely on algorithmically generated domain names (AGDs) to evade detection and remain shrouded from intrusion detection systems, via the so-called Domain Generation Algorithm (DGA). Despite the issue, by applying concepts such as distributed computing and federated learning, the cybersecurity community has prototyped and developed dynamic and scalable solutions that leverage the increased capabilities and connectivity of edge devices. This article proposes a lightweight and privacy-preserving framework that pushes the intelligence modules to the edges aiming to achieve early DGA-based botnet detection in mobile and edge-oriented scenarios. Experimental results prove the deployability of such architecture at all levels, including resource-constrained end-devices. [ABSTRACT FROM AUTHOR]

Cloud Computing has become the preferred choice of performing scientific applications over the cloud since the computing has become as a utility. Cloud-based services have evolved exponentially and also the sophistication of Cloud infrastructure supporting these services has grown. Running traditional applications such as scientific data processing on Cloud, needs to consider the suitability of the could for the compliance of the Cloud critical metrics. This article aims to study the performance of public clouds to support the scientific computing, which were performed on Grid computing, High performance computing or cluster computing. This article tries to address the issue by designing and developing a framework to measure the critical metrics. The performance of the public clouds was assessed through probing, simulation and historic data. The results indicate that only a few provide heterogeneous cloud services. Performance of some of the clouds services can be improved by tweaking the critical metrics. [ABSTRACT FROM AUTHOR]

With the development of the cloud and grid computing, the cloud infrastructures and grids provide a platform for workflow applications. It is very essential to meet the requirements of users and to complete workflow scheduling efficiently. The scheduling of the workflow is limited by quality of service (QoS) parameters. Many scheduling algorithms have been proposed for the execution of workflow applications using QoS parameters. In this study, we improved a scheduling algorithm that considers workflow applications under budget and deadline constraints. This algorithm provided a simple way to deal with the deadline and budget constraints. The algorithm was named BDSD and used to find a scheduling that satisfies of deadline and budget constraints required by a user. The planning success rate (PSR) was utilized to show the effectiveness of the proposed algorithm. For the simulation experiment, random and real workflow applications were exploited. Experimental results showed that compared with other algorithms the algorithm had a higher PSR. [ABSTRACT FROM AUTHOR]

Green technology or Green computing is a modern computer science field which emphasizes on reducing or improving the consumption of energy in platforms of distributed computing systems such as grid and cloud computing systems. Scheduling policy can play an essential role in reducing energy consumed in executing applications on these platforms. Most current scheduling techniques seek out to reduce response time without considering the amount of energy cost. Scheduling policy should select resources that impact over response time and energy consumed for performing tasks of customers' applications. In this publication, a scheduler to assign applications of customers to resources of data centers (DCs) in cloud computing systems with considering energy consumed and response time is proposed and evaluated. The scheduler has a scheduling algorithm that initially assigns applications to virtual resources of the DC. It also implements an algorithm for rescheduling time non-critical applications and another algorithm to deal with time critical applications. The results of simulation reveal that the proposed scheduler can considerably improve the performance in terms of energy consumption, efficiency, monetary cost, productivity and capacity. [ABSTRACT FROM AUTHOR]

In Grid computing, the interconnecting photo-voltaic (PV) control system needs an efficient converter to convert the low direct current (DC) voltage into DC. Design has been improved for the PV, by using a modified fuzzy logic along with an improved switched capacitor (SC) and a DC Converter. An optimized SC DC–DC converter's performance in steady state for improving the efficiency and the regulation of output for a class belonging to the SC converters that is applied to the PV systems control is proposed. The model has many power converters for efficiently managing the transfer of power of a long cable that has higher electro-magnetic interference. On the basis of the model proposed, this converter provides a suitable DC voltage conversion ratio. The capacitor's resistive output on the impedance accounts for the purpose of charging and discharging losses and the resistive conduction losses has been considered. This work will further extend this DC–DC converter into method of control for a maximum power point tracking which belongs to a PV system that makes use of the variable temperature as well as the irradiance conditions and the fuzzy logic controller (FLC). The FLC that is proposed is improved by using a stochastic diffusion search technique. [ABSTRACT FROM AUTHOR]

Grid computing is distributed computing that coordinates and utilizes computing power, data storage, applications and network resources in dynamic and geographically dispersed organizations. Resource management and application scheduling are two major grid computing problems. Resources are heterogeneous regarding power, architecture, configuration and availability complicating task scheduling. The aim of grid scheduling is in reducing makespan. In grid applications, users should be ensured reliable transactions. Trust is multi-dimensional factor and depends on components like entity reputation, policies and opinions of the entity. A trust based scheduling approach is proposed in this study. [ABSTRACT FROM AUTHOR]

Data in distributed systems are often replicated into different storage elements in order to facilitate their access. This allows optimizing execution time and bandwidth consumption, ensures load balancing and increases data availability and quality of service. Several replication strategies have then been proposed in the literature. In this work, a new evaluation metric for replication strategies is introduced and experimentally evaluated. This metric, called SAvE, serves to tackle a key feature, although neglected in the literature, which is the ability of a replication strategy to exploit the most available sites in the system. The design of such a metric requires an accurate determination of the availability degree of each site. A new measurement of site availability, denoted SA, is then designed to be integrated into SAvE while overcoming the drawbacks experienced by existing measurements. Extensive experiments are performed using the OptorSim simulator to show the accuracy and the effectiveness of our contributions. [ABSTRACT FROM AUTHOR]

Resources in a computational grid system fall under the purview of different administrative domains of varying policies for their usages. Commercial grid offers their services (resources) on use-and-pay basis. Resource management in computational grid, offers a market place for the two prominent grid market players i.e. resource provider and resource consumer. It has been observed that, in the grid, the request for the resources may not be uniform throughout. It fluctuates from very high demand at peak time to low or negligible at off-peak time. This information may be used to fetch the resource utilization and cost benefits out of the grid. The provider would prefer to charge extra for its resources at peak time, whereas users may shift their resources usage preference to off-peak time. This work proposes a model in which the resource provider and consumer play a non-cooperative game at different time-zones and act independently to choose their actions. Some characteristic parameters such as cost, execution time and reliability have been considered to facilitate the job execution. Based on the outcome of the game, the grid cluster offering maximum reliability within the desired execution time and/or cost for the job execution. The model has been simulated for performance evaluation with quite encouraging results. [ABSTRACT FROM AUTHOR]

Current replication strategies update replicas by analyzing the data access pattern for a certain period of time. Therefore, the access latency temporarily increases due to delayed responses to changing data access pattern during the interval of updating replicas. Thus, we propose a real-time data replication strategy that can update a replica by reflecting changes in the data access patterns in real time to solve this problem. The proposed replication strategy introduces a priority value (PV) as a criterion to generate and delete replicas in real time. The PV is calculated based on the previous data access patterns and is updated in real time. We perform simulations to evaluate the performance of the proposed replication strategy by comparing it with the popular file replicate first algorithm (PFRF). The simulation results show that the average job execution time of the proposed strategy is shorter than that of the PFRF by 34.0-38.0%. [ABSTRACT FROM AUTHOR]

Models of rectangular grid structures were constructed in the form of a colored Petri net. The basic model consists of a matrix of switching nodes that deliver packets to computing nodes which are attached to the matrix borders and produce and consume packets. Since grid structures are often employed to solve boundary value problems, square and torus surfaces were studied and generalized to hypercube and hypertorus in multidimensional space using a grid node that aggregates switching and computing nodes. Traffic guns were added to the models to represent traffic attacks. Simulation in CPN Tools revealed simple and dangerous traffic gun configurations, such as a traffic duel, focus, crossfire, and side shot, which bring the grid to complete deadlock at less than 5 % of the grid peak load. Comparably low gun intensity targeted to induce deadlock areas within a grid (network) is a key characteristic of disguised traffic attacks. The aim of future work will be to develop counter-measures for these attacks. [ABSTRACT FROM AUTHOR]

We address the challenge of both harvesting idle CPU resources on off-the-shelf desktops donated to Desktop Grid Computing while at once limiting the slowdown generated to the resource owner, also known as end-user, to customized values. In this context, slowdown is studied as the increase in completion times of end-user tasks while a Desktop Grid harvests idle CPU resources by executing CPU intensive workloads. To achieve this, we deploy two Desktop Grids, one virtualization-based (UnaCloud) and one agent-based (BOINC). We then quantify the slowdown generated to simultaneously-running, end-user tasks. The results show that dynamic performance and energy-efficient technologies, specifically overclocking features, directly affect the slowdown generated to the end-user when incorporated into the processor used by the Desktop Grid. Furthermore, we propose, implement, and test a first set of resource allocation policies for the BOINC client in order to effectively harvest idle CPU resources while avoiding to exceed a customizable slowdown limit. [ABSTRACT FROM AUTHOR]

Besides generating faster solutions, parallel computers can be used to solve bigger or more complex problems. In particular, they can be utilized to run simulations at finer resolutions and to model physical phenomena more realistically. We describe in this article the development of a parallel cellular automata algorithm used in the three-dimensional simulation of multicellular tissue growth. Computational models of this genre are becoming ever more important because they provide an alternative approach to continuous models and an ability to describe the dynamics of complex biological systems evolving in time. We report on the different components of the model where cellular automata is used to model different types of cell populations that execute persistent random walks on the computational grid, collide, aggregate, and proliferate until they reach confluence. We elaborate on the main issues encountered in the parallelization of the algorithm as well as its implementation on a parallel machine with a particular focus on maintaining determinism. By delaying the exchange of cells in the shared boundaries between neighboring processors till after all events related to cell division and motion are accounted for in a given time step, good parallel performance results are obtained on a high-performance cluster. [ABSTRACT FROM AUTHOR]

Aiming at the sensitive issues of service quality in cloud computing, a task scheduling tactic with multidimensional QoS constraints is studied. Based on cluster service and user QoS preference, this article constructs an immune optimization model to make a description through formulas and quantify the performance constraints; the utility function of multidimensional QoS is given and then the immune optimization operation is performed with the antibodies. It is beneficial to increase the prediction accuracy of the equality evaluation, and the search for a Pareto optimal set of multiobjective optimization problems is implemented. Finally, the optimum node distribution structure with the highest utility value is obtained. It's shown that the approach gives sufficient consideration of multidimensional user QoS requirements. The results from the test show a significant improvement in average rate of equipment utilization, service time and response time compared to similar algorithms. [ABSTRACT FROM AUTHOR]