Article Preview
TopIn general, there are two main purposes of resource allocation in cloud computing, one is the resource allocation scheme for the purpose that reducing the energy consumption of the Cloud Computing center (Wang, Hung, & Yang, 2014), that is, green cloud computing (Gai, Qiu, & Zhao, 2016). Another is the resource allocation algorithm based on the economics.
According to Jebalia et al. (2013), the game theory is introduced to the resource allocation of cloud computing. Some researchers used the game method and Nash equilibrium theory to solve the game problem between resources and income (Wei, Vasilakos, & Zheng, 2010).
Some research shows that due to the large scale of cloud data center, its resource allocation problem is a discrete combinatorial optimization problem (Faragardi, Rajabi, & Shojaee, 2013), which belongs to NP problem. It is difficult to get the solution of the problem in a reasonable time by using the traditional algorithm. Therefore, more and more researchers use heuristic algorithm to solve the related problems, which is the most effective way to solve the problem of resource allocation in cloud computing.
Hua et al. (2010) using ant colony algorithm, Xie, Du, and Tian (2013) using particle swarm algorithm, and Pandit, Chattopadhyay, and Chattopadhyay (2014) using the simulated annealing algorithm to find the best matching relationship between the virtual machine and the server in cloud computing which can save energy and improve the resource utilization (Rahman, Imran, & Gias, 2013).
There are also research points that the method of machine learning can be applied to the resource allocation of PaaS platform. Xu et al. (2013) put forward the decision tree method to the resource allocation of cloud. Sun et al. (2013), introducing the neural network with feedback evaluation mechanism and support vector machine model to realize the cloud resource allocation. But the machine learning method requires large number of data for training, this is difficult for the resource allocation system.
Through intensive research, the researchers study and design a resource allocation model for PaaS platform, which provides flexible resource allocation for large-scale Web applications.
TopFigure 1. Resource allocation model of PaaS platform