Improvement of tasks scheduling algorithm based on load balancing candidate method under cloud computing environment

In recent years, cloud computing has become an ideal way to provide different types of applications. It can provide the processing, storage, web services, development platforms, and databases to enable the companies to scale their infrastructure and service types quickly. As the demand for higher processing power increases, large amounts of data will cause a significant burden on the cloud computing environment. Therefore, an efficient scheduling algorithm for tasks under the cloud computing environment has become a crucial issue. Some well-known algorithms such as Suffrage, MaxSuffrage, and AMS have been proposed to improve the scheduling performance. However, the above algorithms do not consider the load balancing problem of working nodes. This load balancing issue will limit the overall performance of the network system. Hence, the BCSV scheduling al-gorithm has been proposed to improve the above problems in this paper. The main idea of BCSV is to use the Smallest Suffrage Value (SSV), Largest Suffrage Value (LSV), and Criteria Suffrage Value (CSV) as the scheduling factor to enhance the performance of the task dispatch. According to the experiment results, the proposed BCSV algorithm can obtain better load balance and makespan than the existed algorithms under the HiHi, HiLo, LoHi, and LoLo heterogeneous network environment. In other words, the proposed BCSV algorithm can get better task scheduling results while considering the load balancing problem.

Automated summary

Cloud computing has become an ideal way to provide various applications, but efficient task scheduling algorithms are crucial. Existing algorithms lack consideration for load balancing among working nodes, so this paper proposes the BCSV scheduling algorithm, which uses different suffrage values to improve task dispatch performance.