FPSO-GA: A Fuzzy Metaheuristic Load Balancing Algorithm to Reduce Energy Consumption in Cloud Networks

Mirmohseni, Seyedeh Maedeh; Tang, Chunming; Javadpour, Amir

doi:10.1007/s11277-022-09897-3

Cited by 10 publications

(4 citation statements)

References 35 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 specifies that 2 instances of type1 virtual machine can be executed, but if it supposes there are continuous type 1 request, then the type 1 and type 2 instances will be pushed to a starvation state. This is the problem considered and solved [20][21][22][23][24][25].…”

Section: Literature Surveymentioning

confidence: 99%

An Enhanced Trust Scheduling Algorithm for Medical Applications in a Heterogeneous Cloud Computing Environment

2024

Teh. vjesn.

View full text Add to dashboard Cite

This paper aims to present and deploy an improved task scheduling algorithm for the allocation of user tasks across multiple computing resources. The primary goal of this algorithm is to minimize both execution time and costs while simultaneously enhancing resource utilization within the context of medical applications. Virtual machine scheduling in a heterogeneous cloud environment needs significant attention with the increase in the usage of cloud resources by end users and enterprises. It is one of the significant parameters that affects cloud data centers. The resources requested by every user vary in their configuration. Finding a suitable virtual machine for each process is dynamically a time-consuming process. Virtual machines are classified based on resources such as memory and processing units. Upon the arrival of a request with specific requirements, it can be effortlessly mapped to a corresponding virtual machine. This process is followed by a bilateral method encompassing queuing and scheduling. Queues are formed for requests with different requirements, which are followed by a scheduling algorithm that allocates VMs based on the minimum remaining resources in the resource pool. A scheduling mechanism has been designed to solve the problem of starvation that occurs with the Min-Min fit scheduling policy. The average turnaround time and waiting times are observed to be significantly reduced, which has an impact on the performance of the data center for medical applications. Using the CloudSim Plus tool, the experimental outcomes demonstrated that the proposed approach exhibited remarkable superiority over competing methods in relation to metrics such as average waiting time, turnaround time, and response time. This advantage was observed when compared to multiple algorithms that were examined during the study.

show abstract

“…From the results, it evident that GSAGA showed a huge impact over the compared approaches while maximizing its processing capacity and minimizing the energy consumption. In [ 21 ], a hybridized task scheduling approach was formulated using the FPSO and GA. The main aim of this approach was to efficiently balance the tasks among VMs.…”

Section: Related Workmentioning

confidence: 99%

An Efficient Trust-Aware Task Scheduling Algorithm in Cloud Computing Using Firefly Optimization

Mangalampalli

Karri

Elngar

2023

Sensors

View full text Add to dashboard Cite

Task scheduling in the cloud computing paradigm poses a challenge for researchers as the workloads that come onto cloud platforms are dynamic and heterogeneous. Therefore, scheduling these heterogeneous tasks to the appropriate virtual resources is a huge challenge. The inappropriate assignment of tasks to virtual resources leads to the degradation of the quality of services and thereby leads to a violation of the SLA metrics, ultimately leading to the degradation of trust in the cloud provider by the cloud user. Therefore, to preserve trust in the cloud provider and to improve the scheduling process in the cloud paradigm, we propose an efficient task scheduling algorithm that considers the priorities of tasks as well as virtual machines, thereby scheduling tasks accurately to appropriate VMs. This scheduling algorithm is modeled using firefly optimization. The workload for this approach is considered by using fabricated datasets with different distributions and the real-time worklogs of HPC2N and NASA were considered. This algorithm was implemented by using a Cloudsim simulation environment and, finally, our proposed approach is compared over the baseline approaches of ACO, PSO, and the GA. The simulation results revealed that our proposed approach has shown a significant impact over the baseline approaches by minimizing the makespan, availability, success rate, and turnaround efficiency.

show abstract

FPSO-GA: A Fuzzy Metaheuristic Load Balancing Algorithm to Reduce Energy Consumption in Cloud Networks

Cited by 10 publications

References 35 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

An Enhanced Trust Scheduling Algorithm for Medical Applications in a Heterogeneous Cloud Computing Environment

An Efficient Trust-Aware Task Scheduling Algorithm in Cloud Computing Using Firefly Optimization

Contact Info

Product

Resources

About