Cloud computing is known as a dynamic service provider using highly scalable and virtualized resources on the Internet. Many industries have started offering cloud services on a "pay-as-you-go" basis. Advances have led to the concept of marketplace exchanges, which enable trade between cloud providers and consumers. Lightweight and Platform are presented as independent frameworks called "marketplace environments" that allow consumers and providers to trade computing resources according to their needs. Resource by optimizing the amount of processing resources needed by cloud infrastructure customers. Therefore, our goal is to find the optimal number of virtual machines and how to properly arrange cloud services on them by observing service quality criteria such as response time and service delivery error. In this article, we are going to design and implement a new scheduling system with evolutionary algorithms combined with genetic algorithm, so that we can improve the scheduling problem in dependent tasks to a great extent. Finally, the combined algorithms proposed by the GA_SA algorithm have shown impressive efficiency. Is. In addition to being successful in improving the completion time of tasks in the cloud system, this algorithm has also been shown to be better than other evolutionary algorithms in the time flow of tasks. Another feature of this algorithm is to have a suitable speed to find the global optimum.
