scholarly journals User Demand Aware Grid Scheduling Model with Hierarchical Load Balancing

2013 ◽  
Vol 2013 ◽  
pp. 1-8 ◽  
Author(s):  
P. Suresh ◽  
P. Balasubramanie
Keyword(s):  
Load Balancing ◽  
User Satisfaction ◽  
Scheduling Algorithm ◽  
Efficient Utilization ◽  
Grid Environment ◽  
Data Intensive ◽  
Scheduling Model ◽  
User Demand ◽  
Overall Performance ◽  
Data Intensive Applications

Grid computing is a collection of computational and data resources, providing the means to support both computational intensive applications and data intensive applications. In order to improve the overall performance and efficient utilization of the resources, an efficient load balanced scheduling algorithm has to be implemented. The scheduling approach also needs to consider user demand to improve user satisfaction. This paper proposes a dynamic hierarchical load balancing approach which considers load of each resource and performs load balancing. It minimizes the response time of the jobs and improves the utilization of the resources in grid environment. By considering the user demand of the jobs, the scheduling algorithm also improves the user satisfaction. The experimental results show the improvement of the proposed load balancing method.

scholarly journals A Multiconstrained Grid Scheduling Algorithm with Load Balancing and Fault Tolerance

2015 ◽  
Vol 2015 ◽  
pp. 1-10 ◽  
Author(s):  
P. Keerthika ◽  
P. Suresh
Keyword(s):  
Resource Allocation ◽  
Fault Tolerance ◽  
Load Balancing ◽  
User Satisfaction ◽  
Fault Tolerant ◽  
Scheduling Algorithm ◽  
Grid Environment ◽  
Resource Allocation Algorithm ◽  
Processing Cost ◽  
Comparison Results

Grid environment consists of millions of dynamic and heterogeneous resources. A grid environment which deals with computing resources is computational grid and is meant for applications that involve larger computations. A scheduling algorithm is said to be efficient if and only if it performs better resource allocation even in case of resource failure. Allocation of resources is a tedious issue since it has to consider several requirements such as system load, processing cost and time, user’s deadline, and resource failure. This work attempts to design a resource allocation algorithm which is budget constrained and also targets load balancing, fault tolerance, and user satisfaction by considering the above requirements. The proposed Multiconstrained Load Balancing Fault Tolerant algorithm (MLFT) reduces the schedule makespan, schedule cost, and task failure rate and improves resource utilization. The proposed MLFT algorithm is evaluated using Gridsim toolkit and the results are compared with the recent algorithms which separately concentrate on all these factors. The comparison results ensure that the proposed algorithm works better than its counterparts.

scholarly journals An Efficient Grid Scheduling Algorithm with Fault Tolerance and User Satisfaction

2013 ◽  
Vol 2013 ◽  
pp. 1-9 ◽  
Author(s):  
P. Keerthika ◽  
N. Kasthuri
Keyword(s):  
Fault Tolerance ◽  
User Satisfaction ◽  
Scheduling Algorithm ◽  
Computational Grids ◽  
Efficient Technology ◽  
Problem Statement ◽  
Grid Scheduling ◽  
Failure Handling ◽  
Communication Time ◽  
User Demand

Problem Statement. The advances in human civilization lead to more complications in problem solving. Grid computing serves as an efficient technology in solving those complicated problems. In computational grids, the grid scheduler schedules the task and finds the appropriate resource for each task. The scheduler must consider several factors such as user demand, communication time, failure handling mechanisms, and reduced makespan. Most of the existing algorithms do not consider user satisfaction. Thus a scheduling algorithm that handles failure of resources and achieves user satisfaction gains more importance.Approach. A new bicriteria scheduling algorithm (BSA) that considers user satisfaction along with fault tolerance has been introduced. The main contribution of this paper includes achieving user satisfaction along with fault tolerance and minimizing the makespan of jobs.Results. The performance of this proposed algorithm is evaluated using GridSim based on makespan and number of jobs completed successfully within user deadline.Conclusions/Recommendations. The proposed BSA algorithm achieves reduced makespan and better hit rate with higher user satisfaction and fault tolerance.

Resource Management Techniques to Manage the Load Balancing in Cloud Computing

2019 ◽  
pp. 170-195
Author(s):  
Pradeep Kumar Tiwari ◽  
Sandeep Joshi
Keyword(s):  
Cloud Computing ◽  
Load Balancing ◽  
Resource Utilization ◽  
Distributed System ◽  
User Satisfaction ◽  
Single Node ◽  
Load Imbalance ◽  
Management Techniques ◽  
Overall Performance ◽  
Utilization Ratio

Load balancing is one of the vital issues in cloud computing that needs to be achieved using proper techniques as it is directly related to higher resource utilization ratio and user satisfaction. By evenly distributing the dynamic local workload across all the nodes in the whole cloud, load balancing makes sure that no single node is overwhelmed, and some other nodes are kept idle. Hence, the technique helps to improve the overall performance resource utility of the system which will lead to high user satisfaction and resource utilization ratio. It also ensures the fair and effective distribution of each and every computing resource in the distributed system. Furthermore, the various load balancing techniques prevent the possible bottlenecks of the system created by the load imbalance. Maximization of the throughput, minimization of the response time, and avoidance of the overload are the other major advantages of the load balancing. Above all, by keeping resource consumption at the minimum, the load balancing techniques help to reduce costs.

Priority Based Load Balancing in Cloud for Data Intensive Applications

2012 ◽  
Vol 5 (4) ◽  
pp. 200-206
Author(s):  
E. Iniya Nehru ◽  
S. Sujatha ◽  
P. Seethalaks ◽  
N. Sridharan
Keyword(s):  
Load Balancing ◽  
Data Intensive ◽  
Data Intensive Applications

scholarly journals Adaptive Load Balancing of Parallel Applications with Multi-Agent Reinforcement Learning on Heterogeneous Systems

2004 ◽  
Vol 12 (2) ◽  
pp. 71-79 ◽  
Author(s):  
Johan Parent ◽  
Katja Verbeeck ◽  
Jan Lemeire ◽  
Ann Nowe ◽  
Kris Steenhaut ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Load Balancing ◽  
Heterogeneous Systems ◽  
Machine Learning Techniques ◽  
Parallel Applications ◽  
Communication Overhead ◽  
Data Intensive ◽  
Multi Agent ◽  
State Coordination ◽  
Data Intensive Applications

We report on the improvements that can be achieved by applying machine learning techniques, in particular reinforcement learning, for the dynamic load balancing of parallel applications. The applications being considered in this paper are coarse grain data intensive applications. Such applications put high pressure on the interconnect of the hardware. Synchronization and load balancing in complex, heterogeneous networks need fast, flexible, adaptive load balancing algorithms. Viewing a parallel application as a one-state coordination game in the framework of multi-agent reinforcement learning, and by using a recently introduced multi-agent exploration technique, we are able to improve upon the classic job farming approach. The improvements are achieved with limited computation and communication overhead.

Sign in / Sign up

Export Citation Format

Share Document