Foreword to the special issue of green cloud computing: Methodology and practice

The purpose of this special issue is to collate a selection of representative research articles that were primarily presented at the Ninth “Green Cloud Computing: Methodology and Practice,” held in conjunction with SC'14. This annual conference brings together practitioners, researchers, students, and scholars interested in updating their knowledge about or active in green cloud computing, in order to foster state-of-the-art research in the area of green cloud computing including the topics of modeling, algorithm development, implementation, and execution. Although cloud computing has been widely adopted by the industry, it still suffers from different challenging issues, one of which is efficient energy management. The cloud may comprise thousands of servers, network devices, and disks and typically serve millions of users globally. Such a large-scale data center will consume considerable amount of energy. Therefore, optimizing the efficiency of the application's use of cloud resources and improving the energy efficiency in cloud, without sacrificing Service Level Agreements (SLA), cannot only save significant budget for cloud users and owners but also make a significant contribution to greater environmental sustainability. This special issue will serve as a landmark source for education, information, and reference to practitioners, researchers, students, and scholars. This issue would be incomplete without in-VM management and it is very useful in green cloud computing because it provides the abilities of in-VM monitoring, VM reconfiguration, and performance measurement. Zhan et al3 propose a secure automated in-VM management approach, a hypervisor-based shell managing the VMs in an out-of-box way. In addition, it presents a dummy process selection and a system call injection method to further enhance the system security and transparency. Large-scale data processing is a problem that must be faced in green cloud computing. Ding et al4 consider the data structure of the graph and propose an index structure named Closure+-tree to process the subgraph query efficiently. Wang et al5 consider the shortcoming of collaborative filtering in processing large-scale data and propose a new method for training autoencoder-based CF. We encourage the reader to review the works of Ye et al,6 Chen et al,7 and He et al8 to get more information about the topics of modeling, algorithm development, implementation, and execution.