Resource provision algorithms in cloud computing: A survey

• The resource provision algorithms are surveyed from a point view of top-do-down.
• The algorithms are classified into 11 kinds of models or algorithms.
• The algorithms are surveyed according to their objectives and VM placement phase.
• The properties of the algorithms are complemented in the summarized tables.

Efficient resource provision which can guarantee the satisfactory cloud computing services to the end user, lays the foundation for the success of commercial competition. In the Iaas model, services are deployed as virtual machines in the cloud computing infrastructure. So the resource provision problem is reduced to how to place the virtual machines to support the requested services. According to the deployment sequence, from the view point of top-to-down, we hackle the different deployment phases and the pursued objectives in each phase. More than 150 articles in the latest years are surveyed and the state art of the algorithms to realize these objectives is viewed. Techniques employed in these algorithms are categorized and analyzed systematically. Especially, the deficiency of the traditional research formulation to address the innovation of cloud computing is explored. At last, several tightly related topics, i.e., virtual machine migration, forecast methods, stability and availability are discussed.