Optimal Server Allocation and Frequency Modulation on Multi-Core Based Server Clusters

Related Work

In recent years, power management has become one of the most important concerns on server clusters. Many previous work achieves energy saving by dynamically adjust processors’ frequency and voltage. Researchers have developed various DV/FS scheduling algorithms to save energy under timing deadlines (Vasic et al., 2008; Pinheiro et al., 2001). VOVF is a major policy applied in server clusters (Fan et al., 2007; Guerra et al., 2008; Sharma et al., 2005). In (Niyato, Chaisiri, & Sung, 2009), researchers constructed a constraint Markov model to adjust server numbers according to transition probability. In (Nedevschi et al., 2008), the authors proposed a method to reduce network energy consumption via sleeping and rate adaptation via combining VOVF and DV/FS. Combining DV/FS and VOVF potentially provide higher energy saving.