A Grid is a computational system consisting of a large number of geographically distributed and heterogeneous resources. Job scheduling is the key component of a Grid, and plays an important role in the efficient and ...
详细信息
A Grid is a computational system consisting of a large number of geographically distributed and heterogeneous resources. Job scheduling is the key component of a Grid, and plays an important role in the efficient and effective execution of various kinds of scientific and engineering applications. This paper presents a comparative performance analysis of our proposed job scheduling algorithms along with other well known job scheduling algorithms, considering the quality of service (QoS) parameters such as waiting time, turnaround time, response time, total completion time, bounded slowdown and stretch time. The main thrust of this work was to conduct a QoS based evaluation of the scheduling algorithms on an experimental Grid using real workload traces. The experimental evaluation confirmed that the proposed scheduling algorithms possess a high degree of optimality in performance, efficiency and scalability.
The intent of 4G technology is to converge high speed data application requirements and compete with other technologies. Different techniques i.e relaying, carrier aggregation, multiple input multiple output, and hete...
详细信息
The intent of 4G technology is to converge high speed data application requirements and compete with other technologies. Different techniques i.e relaying, carrier aggregation, multiple input multiple output, and heterogeneous networks provide higher throughputs, low latency and enable LTE to become a Standard for Wireless broadband. Due to almost exponential increase in demand for high data rates it is expected that network will be occupied by more resource demanding applications. Therefore efficient scheduling of radio resources is required for better performance of LTE system. Proportional Fair scheduler is adopted to LTE system to achieve Orthogonal Frequency Division Multiple Access (OFDMA) potentiality in Time Domain systems (TDS) and Frequency Domain scheduling systems (FDS). This paper aims at enhancing the functionality of Proportional Fair algorithm by making future estimation of the channel quality index (CQI) to offer higher data rate among all users according to their running applications, at high mobility. Performance of proposed algorithm on the downlink is measured in terms of throughput and block error rate using a MATLAB-based system level simulator.
Over past few years there is continuous increase in computational capacity and hence there is enormous data flow (i.e., Big Data) which surpasses the capacity of traditional processing tools. These processing demands ...
详细信息
ISBN:
(数字)9781538649855
ISBN:
(纸本)9781538649862
Over past few years there is continuous increase in computational capacity and hence there is enormous data flow (i.e., Big Data) which surpasses the capacity of traditional processing tools. These processing demands of Big Data in real time applications produce a big challenge to attain required levels of performance. Map reduce is one of the most efficient parallel distributed programming models for maintaining huge unorganized data sets present in cloud applications. This Map reduce model is implemented in Hadoop which is an open source Java based programming framework. It is widely used for large and high performance data processing with low response time in Big Data. The Hadoop implementation is made on Homogeneous Environment. Since, it reduces the overhead in data transmission and each participating cluster node possesses ideal computing speed and workload as well. However in real time applications the processing nodes may have unique computational capacity and workload emerging in a heterogeneous environment. The regular Hadoop implementation does not produce the required performance into heterogeneous environment. This paper presents a survey on various Map reduce scheduling algorithms with its taxonomy, advantages and disadvantages in heterogeneous environment.
A downlink MAC scheduler aims to improve the radio resources utilization in the Long Term Evolution (LTE) network. The MAC scheduler is responsible for sharing the available radio Resource Blocks (RBs) among different...
详细信息
A downlink MAC scheduler aims to improve the radio resources utilization in the Long Term Evolution (LTE) network. The MAC scheduler is responsible for sharing the available radio Resource Blocks (RBs) among different User Equipment (UEs) in time and frequency domains. Several downlink MAC schedulers have been proposed and implemented; however, providing fairness in terms of granting resources to different UEs with different QoS requirements remains a challenge. This paper presents the results of a comparative simulation study with respect to a fairness criterion for three well-known downlink schedulers.
As applications grow increasingly complex, so do the complexities of the microcontroller-based embedded devices such as cell phones, digital TVs, smart cars, washing machines and so on. Although these recent applicati...
详细信息
As applications grow increasingly complex, so do the complexities of the microcontroller-based embedded devices such as cell phones, digital TVs, smart cars, washing machines and so on. Although these recent applications operate in hard constraint conditions, embedded systems are required to respond to external events in a shortest possible time. In this paper, we present a variety of scheduling algorithms for a single microcontroller-based embedded devises with static and dynamic priorities and show a study on different parameters, such as computing time, burst time, waiting times and average turnaround time for each algorithm. This study aims to select the appropriate operating system for the particular situation and also to conceive new solutions that can improve several features such as waiting times and average turnaround time.
Currently, a new type of wireless sensor network (WSN) named as battery-free network (BF-WSN), has been proposed and widely studied. Compared with traditional battery-powered WSN (BP-WSN), nodes in BF-WSN can harvest ...
详细信息
ISBN:
(数字)9781728146010
ISBN:
(纸本)9781728146027
Currently, a new type of wireless sensor network (WSN) named as battery-free network (BF-WSN), has been proposed and widely studied. Compared with traditional battery-powered WSN (BP-WSN), nodes in BF-WSN can harvest energy from ambient environment, prolonging the lifetime of the network greatly. Multicast is an important way for data dissemination in WSNs. The problem of minimum latency multicast scheduling (MLMS) that seeks a fast schedule without collision for data multicast has been studied extensively in BP-WSNs. However, existing algorithms are not suitable in BF-WSNs. In this paper we study the MLMS problem in BF-WSNs (BF-MLMS). To reduce latency, we investigate how to compute the end-to-end transmission delay. By considering both energy supply and collision, we propose centralized and distributed algorithms for constructing collision-free multicast trees in BF-WSNs. To the best of our knowledge, this is the first work to consider the BF-MLMS problem. Simulation results verify our protocols have high performance in terms of multicast latency and message volume.
Trust has been recognized as important factor for Grid computing security. Trust is the degree of belief in the resource provider's competence to complete user's task dependably, securely and reliably in a spe...
详细信息
Trust has been recognized as important factor for Grid computing security. Trust is the degree of belief in the resource provider's competence to complete user's task dependably, securely and reliably in a specific context at a given time. In this paper, we propose the trust model in Grid system. It consists of Application Domain (AD), Client Domain (CD), Resource Domain (RD), and Trust Manager (TM). TM controls the relationship between RD and CD depending on trust level value of each client and classification of each resource. Trust level's values are from 0 (untrusted) to 1 (trusted). These values are changed to reflect the trust level of every client in every context. Performance metrics are makespan and utilization. We evaluated three batch mode scheduling algorithms. The experimental results show that the trust model can reduce makespan and can make little maximization of utilization. When we compare the conventional trust model and proposed trust model, the proposed trust model is better than the conventional trust model.
Migration schedulers of data centers have an important impact on cost, energy consumption and service qualities. Several virtual machines are migrated inside a datacenter to stabilize the load, save energy or make con...
详细信息
Migration schedulers of data centers have an important impact on cost, energy consumption and service qualities. Several virtual machines are migrated inside a datacenter to stabilize the load, save energy or make construction servers for maintenance. This paper presents a comparison of Virtual Machine (VM) scheduling within cloud environment. The objective of this paper is to demonstrate that the choice of VM scheduling algorithm in Cloud computing model implicitly improves the application performance under resource and service demand variations. We will discuss different VM schedulers implemented and their performance analysis in Virtual environment of cloud computing in order to achieve better the energy consumption using GreenCloud simulator.
Cloud computing restructured the entire world of IT by providing shared scalable resources to the organization. Cloud establishes a huge path to find the solution for many major problems found in the industry. Cloud o...
详细信息
ISBN:
(纸本)9781665487351
Cloud computing restructured the entire world of IT by providing shared scalable resources to the organization. Cloud establishes a huge path to find the solution for many major problems found in the industry. Cloud offers virtualized resources such as applications, software, networks, servers, and storage services. Cloud enables all the virtualized resources to clients on a pay-per-use basis. Because of handling the vast request sent by multiple clients and providing more versatile services to the organization, the cloud faces many critical problems such as security issues, dissatisfied Quality-Of-Services, and sometimes an unbalanced load arises. Among those, the most serious problem is balancing the load across the network. Load balancing issues can be handled by scheduling the work eventually to all nodes without overloading any single node. This paper gives an overview idea of different load balancing algorithms and provides comparative results on its quality metrics.
In this paper, we are trying to find a algorithm for scheduling DAG (Directed Acyclic Graph) tasks in heterogeneous embedded systems to minimize energy consumption while meeting the reliability requirement. Like many ...
详细信息
In this paper, we are trying to find a algorithm for scheduling DAG (Directed Acyclic Graph) tasks in heterogeneous embedded systems to minimize energy consumption while meeting the reliability requirement. Like many traditional algorithms, we divide the task scheduling algorithm into two phases, the task priority calculation phase and the task allocation phase. In the task priority calculation phase, we proposes a priority calculation algorithm IOD based on the difference in task’s input and output data. In the task allocation stage, we proposes a task allocation algorithm based on fault-tolerant technology of task replication and DVFS technology. Combining the two phase, we get three scheduling algorithms, IODS, IODQ and IODR. In the experimental part, we compare the performance of the algorithm proposed in this paper with existing research algorithms (EFSRG algorithm and HRRM algorithm). The analysis of experimental results shows that the IODS algorithm is a better choice.
暂无评论