Performance Evaluation of Load-Balancing Algorithms with Different Service Broker Policies for Cloud Computing

Shahid, Muhammad Asim; Alam, Muhammad Mansoor; Su’ud, Mazliham Bin Mohd

doi:10.3390/app13031586

Cited by 19 publications

(7 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Shahid et al [ 20 ] this study compares the performance of existing load-balancing algorithms such as PSO, RR, ESCE, and throttled load balancing. Using a cloud analyst platform, this study provides a detailed performance evaluation of various load-balancing algorithms.…”

Section: Methodsmentioning

confidence: 99%

Improved accuracy and less fault prediction errors via modified sequential minimal optimization algorithm

Shahid

Alam²,

Su’ud³

2023

PLoS ONE

Self Cite

View full text Add to dashboard Cite

The benefits and opportunities offered by cloud computing are among the fastest-growing technologies in the computer industry. Additionally, it addresses the difficulties and issues that make more users more likely to accept and use the technology. The proposed research comprised of machine learning (ML) algorithms is Naïve Bayes (NB), Library Support Vector Machine (LibSVM), Multinomial Logistic Regression (MLR), Sequential Minimal Optimization (SMO), K Nearest Neighbor (KNN), and Random Forest (RF) to compare the classifier gives better results in accuracy and less fault prediction. In this research, the secondary data results (CPU-Mem Mono) give the highest percentage of accuracy and less fault prediction on the NB classifier in terms of 80/20 (77.01%), 70/30 (76.05%), and 5 folds cross-validation (74.88%), and (CPU-Mem Multi) in terms of 80/20 (89.72%), 70/30 (90.28%), and 5 folds cross-validation (92.83%). Furthermore, on (HDD Mono) the SMO classifier gives the highest percentage of accuracy and less fault prediction fault in terms of 80/20 (87.72%), 70/30 (89.41%), and 5 folds cross-validation (88.38%), and (HDD-Multi) in terms of 80/20 (93.64%), 70/30 (90.91%), and 5 folds cross-validation (88.20%). Whereas, primary data results found RF classifier gives the highest percentage of accuracy and less fault prediction in terms of 80/20 (97.14%), 70/30 (96.19%), and 5 folds cross-validation (95.85%) in the primary data results, but the algorithm complexity (0.17 seconds) is not good. In terms of 80/20 (95.71%), 70/30 (95.71%), and 5 folds cross-validation (95.71%), SMO has the second highest accuracy and less fault prediction, but the algorithm complexity is good (0.3 seconds). The difference in accuracy and less fault prediction between RF and SMO is only (.13%), and the difference in time complexity is (14 seconds). We have decided that we will modify SMO. Finally, the Modified Sequential Minimal Optimization (MSMO) Algorithm method has been proposed to get the highest accuracy & less fault prediction errors in terms of 80/20 (96.42%), 70/30 (96.42%), & 5 fold cross validation (96.50%).

show abstract

Section: Methodsmentioning

confidence: 99%

Improved accuracy and less fault prediction errors via modified sequential minimal optimization algorithm

Shahid

Alam²,

Su’ud³

2023

PLoS ONE

Self Cite

View full text Add to dashboard Cite

show abstract

“…The DCs may be situated within the same geographical region or across disparate regions. , The performance of DEThresh will be benchmarked against two prevalent DC policies, namely the Closest Datacenter Policy (CDC) and Optimized Response Time Policy (ORT), in conjunction with two widely adopted load balancing policies: Round Robin(RR) and Throttled Load Balancing (TLB) Policy [88].…”

Section: Experiments Setupmentioning

confidence: 99%

DEThresh: Enhancing Cloud Computing Performance with Differential Evolution-Driven Datacenter Selection and Threshold-based Load Balancing Optimization

Katangur,

Chowdhury

2024

Preprint

View full text Add to dashboard Cite

The advent of cloud computing has introduced a novel paradigm in user services, enabling on-demand access to information technology services, irrespective of time and location, with a pay-per-use model. Meeting user expectations necessitates cloud service providers to furnish an infrastructure that is efficient, reliable, and resilient to faults. Addressing the substantial volume of user requests, selecting cloud datacenters and load balancing strategies become pivotal for delivering real-time services economically and selecting appropriate datacenters and virtual machines. This research introduces DEThresh, combining a smart differential evolution-based datacenter selection method with a threshold-based load balancing mechanism aimed at enhancing resource management by focusing on cost and performance considerations. The differential evolution-based datacenter selection employs evolutionary operations to identify the most suitable DC for the userbase. Simultaneously, threshold-based load balancing ensures the reasonable distribution of tasks and optimal resource utilization, preventing task overload on virtual machines and underutilization due to task scarcity. Simulation results demonstrate that the proposed DEThresh algorithm exhibits superior response and data processing time compared to well-established popular algorithms currently in use, especially under varying userbase and datacenter conditions. Impressively, DEThresh achieves this even with fewer datacenters, ultimately reducing cloud service costs.

show abstract

“…The significance of load balancing within the cloud computing landscape, particularly concerning stakeholders such as Cloud Service Providers and Cloud Service Consumers, has garnered substantial scholarly attention. This attention is partly due to the absence of precise classification among numerous methodologies, which is the focus of this section providing a comprehensive overview of existing literature [11][12][13][14][15]. Ghomi et al [16][17] presented an outline of load balancing algorithms in distributed computing.…”

Section: Related Workmentioning

confidence: 99%

Cloud Storage Level Service Offering in Virtualized Load Balancer using AWS

Mohanaprakash T A

2023

IJRITCC

View full text Add to dashboard Cite

Distributed computing epitomizes an approach perfectly suited to the realm of IT commitments, leveraging the aggregation of information and resources through electronic cloud service providers utilizing interconnected hardware and software primarily based online, all at a reasonable cost. However, resource sharing can lead to challenges in their accessibility, potentially causing system crashes. To counter this, the technique of distributing network traffic across multiple servers, known as load balancing, plays a pivotal role. This paper ensures that no single server is overwhelmed, thereby preventing overloads and enhancing user responsiveness by equitably distributing tasks. Moreover, it significantly enhances the accessibility of tasks and websites to users. The fundamental objective of this concept is to comprehend load regulation, which operates in tandem with associated frameworks within communication structures like the Web. Load balancing stands as a critical domain within distributed computing, designed to prevent overburdening and to provide equally significant support. Various algorithms are employed to assess the system's complexity. In our proposed strategy, a process is outlined to determine optimal storage space utilization in real-time, utilizing 100 virtual computers, achieving an impressive 92% accuracy rate in its computations. This innovative approach promises efficient resource allocation within the distributed computing framework, thereby optimizing performance and accessibility for end-users.

show abstract

Performance Evaluation of Load-Balancing Algorithms with Different Service Broker Policies for Cloud Computing

Cited by 19 publications

References 33 publications

Improved accuracy and less fault prediction errors via modified sequential minimal optimization algorithm

Improved accuracy and less fault prediction errors via modified sequential minimal optimization algorithm

DEThresh: Enhancing Cloud Computing Performance with Differential Evolution-Driven Datacenter Selection and Threshold-based Load Balancing Optimization

Cloud Storage Level Service Offering in Virtualized Load Balancer using AWS

Contact Info

Product

Resources

About