Semantic service composition model based on cloud computing

Abstract

The user group encountered in cloud computing is large, and the amount of tasks and data to be processed is also large. How to schedule tasks effectively becomes an important problem that can be solved in cloud computing. A binary fitness genetic algorithm (DFGA) is proposed, which is aimed at the programming model of cloud computing. Not only can the algorithm find a plan result with a short overall task completion time, but the short-term performance of the plan result is relatively short. The algorithm was compared with the adaptive genetic algorithm (AGA) through simulation experiments in a short time. The experimental results show that the algorithm is superior to the adaptive genetic algorithm and is an effective task planning algorithm in the cloud computing environment. Genetic algorithm is a global heuristic algorithm used to solve optimization problems. It is adaptive, learning, and parallel. Genetic algorithms have great advantages, especially when dealing with a large number of tasks. Tasks are assigned to multiple processors for processing simultaneously. At the same time, genetic algorithms are also extensible, which can be easily combined with other algorithms to absorb the advantages of other algorithms to make up for their own shortcomings. At present, many authors of scientific research have used the advantages of genetic algorithms to apply them to task scheduling problems, and the scheduling results obtained are superior to traditional scheduling solutions. This paper studies the task scheduling algorithm based on improved genetic algorithm in cloud computing environment. This article uses CloudSim as the object, and through data analysis, compared with HEFT, the SLR of the HEFTD algorithm is shortened by 10.55%, 8.99%, 16.99%, 19.79%, and 9.89%, that is, HEFTD in different CCR. When the CCR is 1 and 2, the algorithm performance is greatly improved.

KEYWORDS:

• Cloud computing
• genetic algorithm
• task scheduling
• simulation experiment

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This work was supported by the Key Scientific and Technological Research Projects of Henan Province, China (182102210416).