As energy has become one of the key operating costs in running a data center and power waste commonly exists, it is essential to reduce energy inefficiency inside data centers. In this paper, we develop an innovative framework, called PowerTracer, for diagnosing energy inefficiency and saving power. Inside the framework, we first present a resource tracing method based on request tracing in multi-tier services of black boxes. Then, we propose a generalized methodology of applying a request tracing approach for energy inefficiency diagnosis and power saving in multi-tier service systems. With insights into service performance and resource consumption of individual requests, we develop (1) a bottleneck diagnosis tool that pinpoints the root causes of energy inefficiency, and (2) a power saving method that enables dynamic voltage and frequency scaling (DVFS) with online request tracing. We implement a prototype of PowerTracer, and conduct extensive experiments to validate its effectiveness. Our tool analyzes several state-of-thepractice and state-of-the-art DVFS control policies and uncovers existing energy inefficiencies. Meanwhile, the experimental results demonstrate that PowerTracer outperforms its peers in power saving.

No abstract

Recently, we develop a new method for reducing vibration named liquid film damping (LFD) which combines the mechanism of vibrational energy dissipation of liquid viscous damping (LVD) and air film damping (AFD). This paper use experiment to compare the capacities of vibration decreasing of LFD and the pore viscous damping (PVD) which is an extensive applied type of LVD. The results of experiment present LFD has better ability than traditional LVD in reducing vibration of structures in not only higher frequency but lower frequency.

This paper presents a two-stage energy-aware schedule strategy to solve the problem of effective scheduling task set with interdependence on chip multiprocessor (CMP) system while saving energy. We propose a tri-dimensional coding based hybrid genetic algorithm (TCH) to allocate the task set on processor cores to minimize the execution time. Compared with traditional genetic algorithm, TCH uses the tridimensional coding scheme to match the architectural characteristics of CMP. We represent a heuristic algorithm using dynamic voltage scaling (DVS) method to reduce the system energy consumption. The simulation experimental results demonstrate that the strategy proposed in this paper efficiently allocates and schedules the tasks on CMP system.

This paper proposes a Term Field Based TermCo-occurrence Model, which consults the concept of field in physics, interpreting how to get the functional relations of terms' correlation and their distance. The result of experiments illuminates that this model is not a "descending model" simply and there are two segments in the change trend of terms` correlation in evidence, which interprets the phenomenon from linguistics practice that terms' correlation is almost a constant in a small distance.