Performance model and system optimization of an energy-saving strategy based on adaptive service rate tuning in cloud data centers with micro-burst traffic

With the increasing competition in cloud market, reducing operating costs and improving Quality of Service (QoS) are two of the key issues that cloud vendors need to consider. In order to reduce the power consumption while mitigating the negative impact of micro-burst traffic in Cloud Data Centers (CDCs) on performance, and make cloud vendors more competitive, we design an Energy-saving Strategy based on Sleep and Adaptive Service-rate Tuning (ES-SAST) in this paper. We model the arrivals of the cloud task requests as an environment-dependent $R$-phase Markov Arrival Process (MAP$\left(R\right)$), and we establish a multi-server synchronous multi-vacation queue with adaptive service rate tuning. We construct a four-dimensional Markov chain to analyze the queue, and we calculate some measures to evaluate the energy efficiency and QoS in the steady state. Then we develop an objective function composed of three performance measures. Finally, we propose an Improved Fire Hawk Optimizer (IFHO) with multi-strategy integration, and IFHO jointly optimizes two system parameters. An empirical study shows that IFHO chooses a lower system expected cost, where the power consumption of the system falls by 3%, the latency of tasks decreases by 19%, and the loss rate of the system reduces by 37%, on average.