New Study by Zhou Presents Technique to Reduce Energy Consumption of Cloud Data Centers

With the rapid growth of cloud computing, frequent workload bursts show an increasing influence on the quality of service and energy efficiency of cloud-based data centers. Existing virtual machine placement schemes are expected to optimize either quality of service or energy efficiency for cloud data centers running under bursty workload conditions. To bridge this gap, new research by TSYS School computer scientist Yi Zhou and his colleagues at Jinan University, Hainan University, University of Exeter and Auburn University proposes a burst-aware and thermal-efficient virtual machine placement technique that leverages a split-and-recombine algorithm to deal with bursty workloads. Their technique prioritizes critical workloads while preventing low-priority workloads from starvation, thereby assuring quality of service. It does so by utilizing an enhanced simulated annealing algorithm to offer optimal thermal-efficient virtual machine placement solutions, aiming to minimize the energy consumption of data centers. To facilitate estimating energy consumption, a thermal model that takes into account heat re-circulation effects is integrated into their technique. Experiments discussed in the study, which is set to appear in a future issue of IEEE Transactions on Services Computing, indicate that the proposed new technique reduces workload delay by 18%, while also lowering total energy consumption by anywhere between 27.8% and 49.4%.