RAFL: A hybrid metaheuristic based resource allocation framework for load balancing in cloud computing environment

Thakur, Avnish; Goraya, Major Singh

doi:10.1016/j.simpat.2021.102485

Cited by 32 publications

(18 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These algorithms, and algorithms derived from their base have been applied in several fields with promising outcomes. Some noteworthy examples of metaheuristics applied to optimization problems include examples for crude oil price forecasting ( Jovanovic et al, 2022 ; Al-Qaness et al, 2022 ), Ethereum and Bitcoin prices predictions ( Stankovic et al, 2022b ; Milicevic et al, 2023 ; Petrovic et al, 2023 ; Gupta & Nalavade, 2022 ), industry 4.0 ( Jovanovic et al, 2023b ; Dobrojevic et al, 2023 ; Para, Del Ser & Nebro, 2022 ), medicine ( Zivkovic et al, 2022a ; Bezdan et al, 2022 ; Budimirovic et al, 2022 ; Stankovic et al, 2022a ), security ( Zivkovic et al, 2022b ; Savanović et al, 2023 ; Jovanovic et al, 2023c ; Zivkovic et al, 2022c ), cloud computing ( Thakur & Goraya, 2022 ; Mirmohseni, Tang & Javadpour, 2022 ; Bacanin et al, 2022d ; Zivkovic et al, 2021 ), and environmental sciences ( Jovanovic et al, 2023d ; Bacanin et al, 2022b ; Kiani et al, 2022 ).…”

Section: Background and Preliminariesmentioning

confidence: 99%

Decomposition aided attention-based recurrent neural networks for multistep ahead time-series forecasting of renewable power generation

Damaševičius,

Jovanovic,

Petrovic

et al. 2024

PeerJ Computer Science

View full text Add to dashboard Cite

Renewable energy plays an increasingly important role in our future. As fossil fuels become more difficult to extract and effectively process, renewables offer a solution to the ever-increasing energy demands of the world. However, the shift toward renewable energy is not without challenges. While fossil fuels offer a more reliable means of energy storage that can be converted into usable energy, renewables are more dependent on external factors used for generation. Efficient storage of renewables is more difficult often relying on batteries that have a limited number of charge cycles. A robust and efficient system for forecasting power generation from renewable sources can help alleviate some of the difficulties associated with the transition toward renewable energy. Therefore, this study proposes an attention-based recurrent neural network approach for forecasting power generated from renewable sources. To help networks make more accurate forecasts, decomposition techniques utilized applied the time series, and a modified metaheuristic is introduced to optimized hyperparameter values of the utilized networks. This approach has been tested on two real-world renewable energy datasets covering both solar and wind farms. The models generated by the introduced metaheuristics were compared with those produced by other state-of-the-art optimizers in terms of standard regression metrics and statistical analysis. Finally, the best-performing model was interpreted using SHapley Additive exPlanations.

show abstract

Section: Background and Preliminariesmentioning

confidence: 99%

Decomposition aided attention-based recurrent neural networks for multistep ahead time-series forecasting of renewable power generation

Damaševičius,

Jovanovic,

Petrovic

et al. 2024

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…It is defined as the sum of the product of VM cost and its makespan. This cost is rounded to the closest integer as defined in Equation (26).…”

Section: Financial Cost (Cost)mentioning

confidence: 99%

“…From the outcomes, it is evident that the proposed PSO‐RDAL offers better results based on makespan, penalty cost, response time, resource utilization, meeting task deadline, and execution cost in contrast to present scheduling schemes. Thakur and Goraya 26 have proposed a hybrid optimization algorithm that involves Phasor PSO and Dragonfly Algorithm (PPSO‐DA) for generating ideal resource allocation for efficient LB. From the simulation carried out, load imbalance over physical machines and amid resource capacities is determined.…”

Section: Related Workmentioning

confidence: 99%

Adaptive Guided Differential Evolution‐based Slime Mould Algorithm‐based efficient Multi‐objective Task Scheduling for Cloud Computing Environments

Nithiavathy,

Janakiraman,

Deva Priya

2023

Trans Emerging Tel Tech

View full text Add to dashboard Cite

In a Cloud Computing (CC) environment, users are charged based on on‐demand resource utilization and expected Quality of Service (QoS). Multi‐Objective‐based Task Scheduling (MOTS) problem formulated for achieving the expected QoS in a CC scenario is always NP‐complete. The majority of existing Task Scheduling (TS) algorithms are not efficient in determining global optimal solutions due to huge space offered by large‐scale problem instances and characteristics inherent in NP‐complete problems. In this article, an Adaptive Guided Differential Evolution‐based Slime Mould Algorithm (AGDESMA) is proposed for dealing with the problem of Multi‐Objective large‐scale TS optimization over Infrastructure‐as‐a‐Service (IaaS) CC environment. The proposed AGDESMA is formulated with the merits of Slime Mould Algorithm (SMA) and Adaptive Guided Differential Evolution (AGDE) for achieving a proper balance amid exploitation and exploration phases and preventing the solutions from getting trapped into minimum local regions. It specifically adopts the method of AGDE for preventing premature convergence with maximized diversity of population and local search of swarm agents. The experimental validation of the proposed AGDESMA is conducted using CloudSim based on the synthesized and standard workload traces with larger instances up to a maximum of 5000. The results confirm the predominance of the proposed AGDESMA scheme over benchmarked schemes based on computational overhead and trade‐off between makespan and financial cost.

show abstract

“…The authors of [16] have promoted RAFL, a crossover metaheurisctic-based asset designation framework for load adjustment in distributed computing environments. The architecture incorporates three free metaheurisctic strategiesspecifically, Firefly Calculation (FA), Dark Wolf Streamlining agent (GWO), and Molecule Multitude Advancement (PSO)to accomplish effective load adjustment and asset allocation.…”

Section: Literature Surveymentioning

confidence: 99%

Capuchin Search Particle Swarm Optimization (CS-PSO) based Optimized Approach to Improve the QoS Provisioning in Cloud Computing Environment

Gupta,

Singh

2023

IJRITCC

View full text Add to dashboard Cite

This review introduces the methods for further enhancing resource assignment in distributed computing situations taking into account QoS restrictions. While resource distribution typically affects the quality of service (QoS) of cloud organizations, QoS constraints such as response time, throughput, hold-up time, and makespan are key factors to take into account. The approach makes use of a methodology from the Capuchin Search Particle Large Number Improvement (CS-PSO) apparatus to smooth out resource designation while taking QoS constraints into account. Throughput, reaction time, makespan, holding time, and resource use are just a few of the objectives the approach works on. The method divides the resources in an optimum way using the K-medoids batching scheme. During batching, projects are divided into two-pack assembles, and the resource segment method is enhanced to obtain the optimal configuration. The exploratory association makes use of the JAVA device and the GWA-T-12 Bitbrains dataset for replication. The outrageous worth advancement problem of the multivariable capacity is addressed using the superior calculation. The simulation findings demonstrate that the core (Cloud Molecule Multitude Improvement, CPSO) computation during 500 ages has not reached assembly repeatedly, repeatedly, repeatedly, and repeatedly, respectively.The connection analysis reveals that the developed model outperforms the state-of-the-art approaches. Generally speaking, this approach provides significant areas of strength for a successful procedure for improving resource designation in distributed processing conditions and can be applied to address a variety of resource segment challenges, such as virtual machine setup, work arranging, and resource allocation. Because of this, the capuchin search molecule enhancement algorithm (CSPSO) ensures the success of the improvement measures, such as minimal streamlined polynomial math, rapid consolidation speed, high productivity, and a wide variety of people.

show abstract

RAFL: A hybrid metaheuristic based resource allocation framework for load balancing in cloud computing environment

Cited by 32 publications

References 33 publications

Decomposition aided attention-based recurrent neural networks for multistep ahead time-series forecasting of renewable power generation

Decomposition aided attention-based recurrent neural networks for multistep ahead time-series forecasting of renewable power generation

Adaptive Guided Differential Evolution‐based Slime Mould Algorithm‐based efficient Multi‐objective Task Scheduling for Cloud Computing Environments

Capuchin Search Particle Swarm Optimization (CS-PSO) based Optimized Approach to Improve the QoS Provisioning in Cloud Computing Environment

Contact Info

Product

Resources

About