Modeling and simulation of energy-efficient cloud data centers

The rapid development of Internet has given birth to a new technology called cloud computing. Cloud computing is attractive to business owners as it provides several features, such as no up-front investment, lowering operating cost, highly scalable, reducing business risks and lowering maintenance expenses. However, cloud computing is still in its infancy, as many crucial problems need to be addressed. Energy saving is one of these problems; where efficient power management can help lower the cost of operating a large data center hosting massive computing resources. This paper studies a new proposed model that can reduce the system energy consumption by setting hystereses thresholds of activating and deactivating servers. The model is implemented and simulated using OPNET Modeler and Simulator to evaluate its performance metrics. Simulations have shown the effect of the model on reducing server activation/deactivation rates which consequently reduces the energy consumption. Moreover, simulations proved that the model is a generic model that works for non-Markovian assumptions.