QoS Aware Group-Based Workload Scheduling in Cloud Environment

Mohanty, Suneeta; Moharana, Suresh Chandra; Das, Himansu; Satpathy, Suresh Chandra

doi:10.1007/978-981-15-1097-7_81

Cited by 8 publications

(5 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This hybrid model was found to surpass traditional GA-based methods, including Max-Min and Min-Min algorithms, in performance metrics. Mohanty and Moharana [17] developed a group-based scheduling strategy in cloud environments, focusing on the available processing power and bandwidth of resources. Their method involved clustering jobs by required Million Instructions per Second (MIPS) and aimed to satisfy client QoS requirements while optimizing resource usage.…”

Section: Related Workmentioning

confidence: 99%

Optimizing Task Scheduling in Cloud Computing Environments using Hybrid Swarm Optimization

Kumar,

Dugal,

Singh

2023

J. Comput. Mech. Manag

View full text Add to dashboard Cite

Cloud computing has revolutionized the Information Technology (IT) landscape by offering on-demand access to a shared pool of computing resources over the internet. Effective task scheduling is pivotal in optimizing resource utilization and enhancing the overall performance of cloud systems. Tasks are allocated to virtual machines (VMs) based on a server's workload capacity, aiming to minimize traffic congestion and waiting times. Although Particle Swarm Optimization (PSO) is currently the most effective algorithm for task scheduling in cloud environments, this study introduces a Hybrid Swarm Optimization (HSO) algorithm that combines the strengths of PSO and Salp Swarm Optimization (SSO). The proposed hybrid algorithm addresses the challenges associated with task scheduling in cloud computing. The performance of the HSO algorithm is evaluated using the CloudSim simulator and compared against traditional scheduling algorithms. Simulation results indicate that the hybrid PSO-SSO algorithm outperforms existing methods regarding makespan time, cloud throughput, and task execution efficiency. Consequently, the hybrid approach significantly improves resource utilization and overall system performance in cloud computing environments.

show abstract

Section: Related Workmentioning

confidence: 99%

Optimizing Task Scheduling in Cloud Computing Environments using Hybrid Swarm Optimization

Kumar,

Dugal,

Singh

2023

J. Comput. Mech. Manag

View full text Add to dashboard Cite

show abstract

“…The obtained results found to be better than the standard GA algorithm. In Mohanty et al, 12 the authors proposed a group‐based scheduling algorithm for individual tasks according to its bandwidth (BW) and processing capability of the resource, which is available in the cloud environment. The proposed method clusters the jobs based on the required Million Instructions Per Second (MIPS) and later schedules them to computing resources.…”

Section: Related Workmentioning

confidence: 99%

Hybrid swarm optimization algorithm based on task scheduling in a cloud environment

Eldesokey

El-atty

El‐Shafai

et al. 2021

Int J Communication

View full text Add to dashboard Cite

Summary Cloud computing is the current computing standard, which provides information technology (IT) services over the Internet on demand. In the cloud environment, a task is mapped with an available resource to attain a good result. Task scheduling is the technique that is used to allocate tasks on virtual machines (VMs) of a server based on its capacity of workload. Tasks are scheduled to the server in such a way to minimize traffic and time delay. Particle swarm optimization (PSO) is the best existing algorithm used to schedule a task to an existing resource on the environment of the cloud. By PSO, the task is scheduled for an existing resource to reduce computational cost. In this paper, a hybrid swarm optimization (HSO) algorithm, which is the combination of PSO and salp swarm optimization (SSO), is proposed to resolve task scheduling issues in the cloud environment. The main goal of HSO is to schedule the task to the available resource in such a way to reduce the execution time and computation cost. Multilayer logistic regression (MLR) is an approach used to detect the overloaded VMs, so that a task can be scheduled to a VM according to its capacity of workload. The proposed HSO algorithm with MLR is simulated on the cloudsim toolkit, and the results reveal the efficiency of the proposed algorithm in terms of cost, execution time, and makespan. Compared to the existing algorithms such as the genetic algorithms (GAs), the improved efficiency evolution (IDEA), and the PSO, the proposed algorithm reveals superiority in terms of efficiency, resource utilization, and speed.

show abstract

“…As observed in Section 2, the allocation may be done at process-level [15], user-level [16], or group-level [21]. The faucet system that we contribute is designed so as to provide fair distribution of internal currency among users, with the assumption that the users are identified and registered for making demands.…”

Section: Abstraction For Demands: the Level At Which Distribution Is ...mentioning

confidence: 99%

Max-min Fairness Based Faucet Design for Blockchains

Metin¹,

Özturan²

2021

Preprint

View full text Add to dashboard Cite

In order to have transactions executed and recorded on blockchains such as the Ethereum Mainnet, fees expressed in crypto-currency units of the blockchain must be paid. One can buy crypto-currency called Ether of the Ethereum blockchain from exchanges and pay for the transaction fees. In the case of test networks (such as Rinkeby) or scientific research blockchains (such as Bloxberg), free crypto-currency, Ether, is distributed to users via faucets. Since transaction slots on the blocks, storage and smart contract executions are consuming blockchain resources, Ethers are distributed by fixed small amounts to users. Users may have different amount of Ether requirements; some small amounts and some large amounts during different times. As a result, rather than allowing the user to get a fixed small amount of Ether, a more general distribution mechanism that allows a user to demand and claim arbitrary amounts of Ether, while satisfying fairness among users, is needed. For this end, Max-min Fairness based schemes have been used in centralized settings. Our work contributes a Max-min Fairness based algorithm and its Solidity smart contract implementation that requires low transaction costs independent of the number of users. This is important on the Ethereum blockchain, since a smart contract execution with transaction costs depending on the number of users would mean block gas limit exhaustion problem will eventually be met, making the smart contract ineffective. We report tests which confirm that the low transaction cost aims have been achieved by our algorithm.

show abstract

QoS Aware Group-Based Workload Scheduling in Cloud Environment

Cited by 8 publications

References 5 publications

Optimizing Task Scheduling in Cloud Computing Environments using Hybrid Swarm Optimization

Optimizing Task Scheduling in Cloud Computing Environments using Hybrid Swarm Optimization

Hybrid swarm optimization algorithm based on task scheduling in a cloud environment

Max-min Fairness Based Faucet Design for Blockchains

Contact Info

Product

Resources

About