Optimization of virtual machines placement based on microeconomics theory in cloud network
Alireza Mohammadi, Mohammad Hossein Rezvani · 2017
Virtual Machines (VMs) placement has always been one of the major issues for researchers in the area of Cloud Networking. This challenge has a major impact on the performance of Cloud Service Providers (CSPs) and also has been studied to be optimized with respect to different criteria. The most relevant criteria in order to investigate the amount of improvements are energy consumption, load balancing, and fault tolerance. Recently, significant research activities have been conducted in the area of resource management in cloud networking in order to optimize economic criterias using a variety of pricing mechanisms and games theoretic approaches. These categories of researches consider the cloud network as a market, the users as the customers, the physical hosts as the providers, and the service features as the commodities. In this market the cloud broker plays a significant role concerning the economical regulations across the market. We believe that some other microeconomics theories can be applied to achieve a better and simpler management and placement of VMs in such a way that leads to optimal economic equilibrium, especially Social Welfare (SW) of the users, known as tenants. In other words, our goal in this research is to find the best hosts among the Data Centers (DCs) for VMs, taking into account the new proposed pricing mechanism, named Walrasian equilibrium method. Using the CloudSim simulator, we have shown that the proposed method improves the social welfare of the tenants.