云中基于蟻群算法改進(jìn)的負(fù)載均衡策略
發(fā)布時(shí)間:2019-07-26 08:54
【摘要】:針對(duì)云計(jì)算虛擬化資源中,提高資源利用率、負(fù)載均衡度的問(wèn)題,在蟻群算法的基礎(chǔ)上,提出云中節(jié)點(diǎn)間負(fù)載均衡的改進(jìn)算法。前向螞蟻檢測(cè)節(jié)點(diǎn)的類型、記錄節(jié)點(diǎn)信息,遇到負(fù)載節(jié)點(diǎn)時(shí)留下覓食信息素;后向螞蟻依據(jù)循跡信息素追溯回負(fù)載節(jié)點(diǎn),合理分配超載節(jié)點(diǎn)任務(wù)。所有螞蟻不再更新自己的結(jié)果集,而是致力于更新單個(gè)結(jié)果集,在搜索過(guò)程中依據(jù)節(jié)點(diǎn)類型動(dòng)態(tài)地修改路徑信息素。在Cloudsim平臺(tái)下進(jìn)行的仿真實(shí)驗(yàn)驗(yàn)證了改進(jìn)算法的有效性。
[Abstract]:In order to improve the resource utilization and load balance in cloud computing virtualization resources, an improved load balancing algorithm between nodes in the cloud is proposed on the basis of ant colony algorithm. The forward ant detects the type of the node, records the node information, and leaves the foraging pheromone when the load node is encountered. The backward ant traces back to the load node according to the trace pheromone, and reasonably allocates the task of the overload node. Instead of updating their own result sets, all ants are committed to updating a single result set and dynamically modifying path pheromones according to the node type during the search. The simulation results on Cloudsim platform verify the effectiveness of the improved algorithm.
【作者單位】: 太原理工大學(xué)計(jì)算機(jī)科學(xué)與技術(shù)學(xué)院;
【基金】:山西省科技攻關(guān)基金項(xiàng)目(20120321024-02)
【分類號(hào)】:TP18;TP3
,
本文編號(hào):2519465
[Abstract]:In order to improve the resource utilization and load balance in cloud computing virtualization resources, an improved load balancing algorithm between nodes in the cloud is proposed on the basis of ant colony algorithm. The forward ant detects the type of the node, records the node information, and leaves the foraging pheromone when the load node is encountered. The backward ant traces back to the load node according to the trace pheromone, and reasonably allocates the task of the overload node. Instead of updating their own result sets, all ants are committed to updating a single result set and dynamically modifying path pheromones according to the node type during the search. The simulation results on Cloudsim platform verify the effectiveness of the improved algorithm.
【作者單位】: 太原理工大學(xué)計(jì)算機(jī)科學(xué)與技術(shù)學(xué)院;
【基金】:山西省科技攻關(guān)基金項(xiàng)目(20120321024-02)
【分類號(hào)】:TP18;TP3
,
本文編號(hào):2519465
本文鏈接:http://sikaile.net/kejilunwen/jisuanjikexuelunwen/2519465.html
最近更新
教材專著