An Efficient Intra-Server and Inter-Server Load Balancing Algorithm for Internet Distributed Systems

2017 ◽  
Vol 4 (1) ◽  
pp. 1-18 ◽  
Author(s):  
Sanjaya Kumar Panda ◽  
Swati Mishra ◽  
Satyabrata Das

The growing popularity of Internet Distributed System has drawn enormous attention in business and research communities for handling large number of client requests. These requests are managed by a set of servers. However, the requests may not be equally distributed due to their random nature of arrivals. The optimal assignment of the requests to the servers is a well-known NP-hard problem. Therefore, many algorithms have been proposed to address this problem. However, these algorithms suffer from an excessive number of comparisons. In this paper, a Swapping-based Intra- and inter-Server (SIS) load balancing with padding algorithm is proposed for its solution. The algorithm undergoes a three-phase process to balance the loads among the servers. The proposed algorithm is compared with a client-server load balancing algorithm and the performance is measured in terms of the number of load comparisons and load factor. The simulation outcomes show the efficacy of the proposed algorithm.

Author(s):  
Antonio Menendez Leonel de Cervantes ◽  
Hector Benitez Perez

<p>Node-Availability is a new metric that based on processor utilization, free RAM and number of processes queued at a node, compares different workload levels of the nodes participating in a distributed system. Dynamic scheduling and Load-Balancing in distributed systems can be achieved through the Node-Availability metric as decision criterion, even without previously knowing the execution time of the processes, nor other information about them such as process communication requirements.<br /> This paper also presents a case study which shows that the metric is feasible to implement in conjunction with a dynamic Load-Balancing algorithm, obtaining an acceptable performance.</p>


2017 ◽  
Vol 4 (4) ◽  
pp. 17-30
Author(s):  
Swati Mishra ◽  
Sanjaya Kumar Panda

The increasing use of online services leads to an unequal distribution of the loads among the servers. As a result, the problem is to balance the loads among the servers such that the total number of active servers is minimized. One of the possible solutions is to transfer the loads from the underutilized server to a suitable server and make the underutilized server to sleep mode. In this paper, a server minimization algorithm (SMA) is proposed for the solution of server minimization and the load balancing problem. The proposed algorithm reduces the number of servers by merging the loads of the two least loaded servers. Then it determines the standard deviation of the server loads for load balancing. The proposed SMA is compared with an existing load balancing algorithm using the number of minimized servers, load standard deviation and load factor. The simulation results show the efficacy of the SMA.


2021 ◽  
Vol 11 (1) ◽  
pp. 146-160
Author(s):  
Kaushik Mishra ◽  
Santosh Kumar Majhi

Abstract Task scheduling and load balancing are a concern for service providers in the cloud computing environment. The problem of scheduling tasks and balancing loads in a cloud is categorized under an NP-hard problem. Thus, it needs an efficient load scheduling algorithm that not only allocates the tasks onto appropriate VMs but also maintains the trade-off amidst VMs. It should keep an equilibrium among VMs in a way that reduces the makespan while maximizing the utilization of resources and throughput. In response to it, the authors propose a load balancing algorithm inspired by the mimicking behavior of a flock of birds, which is called the Bird Swarm Optimization Load Balancing (BSO-LB) algorithm that considers tasks as birds and VMs as destination food patches. In the considered cloud simulation environment, tasks are assumed to be independent and non-preemptive. To evaluate the efficacy of the proposed algorithm under real workloads, the authors consider a dataset (GoCJ) logged by Goggle in 2018 for the execution of cloudlets. The proposed algorithm aims to enhance the overall system performance by reducing response time and keeping the whole system balanced. The authors have integrated the binary variant of the BSO algorithm with the load balancing method. The proposed technique is analyzed and compared with other existing load balancing algorithms such as MAX-MIN, RASA, Improved PSO, and other scheduling algorithms as FCFS, SJF, and RR. The experimental results show that the proposed method outperforms when being compared with the different algorithms mentioned above. It is noteworthy that the proposed approach illustrates an improvement in resource utilization and reduces the makespan of tasks.


2016 ◽  
Vol 9 ◽  
pp. 145-161
Author(s):  
Mohamed Youssfi ◽  
Omar Bouattane ◽  
Abdelaziz Daaif ◽  
Mohammed Ouadi Bensalah

Author(s):  
ZULFIKHAR AHMAD ◽  
ASHIS KU. MISHRA ◽  
BIKASH CHANDRA ROUT

“Cloud computing” is a term, which involves virtualization, distributed computing, networking, software and Web services. Our Objective is to develop an effective load balancing algorithm using Divisible Load Scheduling Theorem to maximize or minimize different performance parameters (throughput, latency for example) for the clouds of different sizes. Central to these issues lays the establishment of an efficient load balancing algorithm. The load can be CPU load, memory capacity, delay or network load. Load balancing is the process of distributing the load among various nodes of a distributed system to improve both resource utilization and job response time while also avoiding a situation where some of the nodes are heavily loaded while other nodes are idle or doing very little work. Load balancing ensures that all processor in the system or every node in the network does approximately the equal amount of work at any instant of time.


Sign in / Sign up

Export Citation Format

Share Document