Cargando…
Multi-Task Assignment Method of the Cloud Computing Platform Based on Artificial Intelligence
To realize load balancing of cloud computing platforms in big data processing, the method of finding the optimal load balancing physical host in the algorithm cycle is adopted at present. This optimal load balancing strategy that overly focuses on the current deployment problem has certain limitatio...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Hindawi
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9584703/ https://www.ncbi.nlm.nih.gov/pubmed/36275963 http://dx.doi.org/10.1155/2022/1789490 |
_version_ | 1784813329227710464 |
---|---|
author | Zhang, Yongchang Geng, Panpan |
author_facet | Zhang, Yongchang Geng, Panpan |
author_sort | Zhang, Yongchang |
collection | PubMed |
description | To realize load balancing of cloud computing platforms in big data processing, the method of finding the optimal load balancing physical host in the algorithm cycle is adopted at present. This optimal load balancing strategy that overly focuses on the current deployment problem has certain limitations. It will make the system less efficient and the user's waiting time unnecessarily prolonged. This paper proposes a task assignment method for long-term resource load balancing of cloud platforms based on artificial intelligence and big data (TABAI). The maximum posterior probability for each physical host is calculated using Bayesian theory. Euler's formula is used to calculate the similarity between the host with the largest posterior probability and other hosts as a threshold. The hosts are classified according to the threshold to determine the optimal cluster and then form the final set of candidate physical hosts. It improves the resource utilization and external service capability of the cloud platform by combining cluster analysis with Bayes' theorem to achieve global load balancing in the time dimension. The experimental results show that: TABAI has a smaller processing time than the traditional load balancing multi-task assignment method. When the time is >600 s, the standard deviation of TABAI decreases to a greater extent, and it has stronger external service capabilities. |
format | Online Article Text |
id | pubmed-9584703 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Hindawi |
record_format | MEDLINE/PubMed |
spelling | pubmed-95847032022-10-21 Multi-Task Assignment Method of the Cloud Computing Platform Based on Artificial Intelligence Zhang, Yongchang Geng, Panpan Comput Intell Neurosci Research Article To realize load balancing of cloud computing platforms in big data processing, the method of finding the optimal load balancing physical host in the algorithm cycle is adopted at present. This optimal load balancing strategy that overly focuses on the current deployment problem has certain limitations. It will make the system less efficient and the user's waiting time unnecessarily prolonged. This paper proposes a task assignment method for long-term resource load balancing of cloud platforms based on artificial intelligence and big data (TABAI). The maximum posterior probability for each physical host is calculated using Bayesian theory. Euler's formula is used to calculate the similarity between the host with the largest posterior probability and other hosts as a threshold. The hosts are classified according to the threshold to determine the optimal cluster and then form the final set of candidate physical hosts. It improves the resource utilization and external service capability of the cloud platform by combining cluster analysis with Bayes' theorem to achieve global load balancing in the time dimension. The experimental results show that: TABAI has a smaller processing time than the traditional load balancing multi-task assignment method. When the time is >600 s, the standard deviation of TABAI decreases to a greater extent, and it has stronger external service capabilities. Hindawi 2022-10-13 /pmc/articles/PMC9584703/ /pubmed/36275963 http://dx.doi.org/10.1155/2022/1789490 Text en Copyright © 2022 Yongchang Zhang and Panpan Geng. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. |
spellingShingle | Research Article Zhang, Yongchang Geng, Panpan Multi-Task Assignment Method of the Cloud Computing Platform Based on Artificial Intelligence |
title | Multi-Task Assignment Method of the Cloud Computing Platform Based on Artificial Intelligence |
title_full | Multi-Task Assignment Method of the Cloud Computing Platform Based on Artificial Intelligence |
title_fullStr | Multi-Task Assignment Method of the Cloud Computing Platform Based on Artificial Intelligence |
title_full_unstemmed | Multi-Task Assignment Method of the Cloud Computing Platform Based on Artificial Intelligence |
title_short | Multi-Task Assignment Method of the Cloud Computing Platform Based on Artificial Intelligence |
title_sort | multi-task assignment method of the cloud computing platform based on artificial intelligence |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9584703/ https://www.ncbi.nlm.nih.gov/pubmed/36275963 http://dx.doi.org/10.1155/2022/1789490 |
work_keys_str_mv | AT zhangyongchang multitaskassignmentmethodofthecloudcomputingplatformbasedonartificialintelligence AT gengpanpan multitaskassignmentmethodofthecloudcomputingplatformbasedonartificialintelligence |