Abstract With energy consumption in high-performance computing clouds growing rapidly, energy saving has become an important topic. Virtualization provides opportunities to save energy by enabling one physical machine (PM) to host multiple virtual machines (VMs). Dynamic voltage and frequency scaling (DVFS) is another technology to reduce energy consumption. However, in heterogeneous cloud environments where DVFS may be applied at the chip level or the core level, it is a great challenge to combine these two technologies efficiently. On per-core DVFS servers, cloud managers should carefully determine VM placements to minimize performance interference. On full-chip DVFS servers, cloud managers further face the choice of whether to combine VMs with different characteristics to reduce performance interference or to combine VMs with similar characteristics to take better advantage of DVFS. This paper presents a novel mechanism combining a VM placement algorithm and a frequency scaling method. We formulate this VM placement problem as an integer programming (IP) to find appropriate placement configurations, and we utilize support vector machines to select suitable frequencies. We conduct detailed experiments and simulations, showing that our scheme effectively reduces energy consumption with modest impact on performance. Particularly, the total energy delay product is reduced by up to 60%.

The study of the carbon obligation allocation among different members in the power system holds significant theoretical and practical value. Existing methods for carbon emission estimation usually attribute the emission responsibility to single side (either generation side or demand side). However, both the generation side and the demand side should take the responsibility of carbon reduction and thus carbon obligation is supposed to be allocated between both sides. Consequently, the carbon obligation allocation between generation side and demand side is studied and it is formulated as a cooperative game problem in this paper. The Shapley value method, as a classic single-valued solution concept of cooperative game theory, is adopted. In the meanwhile, within bilateral bidding electricity market, different bidding strategies and the alliance of generators or loads are also discussed. The Shapley value based method can allocate appropriate carbon obligation to generators and loads according to their contributions to the power system in terms of carbon emission under certain bidding strategy, which can fully exploit the carbon abatement potential of all relative members and promote the development of low-carbon power.

The device-free (DF) object tracking in wireless networks requires a tracked object neither be equipped with a transceiver nor actively participate in the tracking process. One of methods to implement a DF tracking system is to leverage the variation of radio signals introduced by object intrusion. However, many factors may result in the variation of radio signals and it is hard to distinguish which variation is caused by object intrusion. In this paper, we investigate how some factors impact signal variations, and in further impact the effectiveness of DF tracking. Based on analysis, we conduct experiments with TelosB motes, which are carried out in three representative environments with different system parameters. Different wireless channel quality indicators are employed to monitor signal variations. The experiment results provide a significant guidance on how to choose environments, system parameters, channel quality indicators, and metrics to implement an effective DF tracking system.