Zhihang Song

Zhihang Song

Auto-generated profile, based on publicly available information

Zhihang Song

Northeastern University

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 November 2023 in IEEE Transactions on Intelligent Vehicles
Verified
Journal Article
Closed access
ZSZhihang Song
Zhihang Song
ZHZimin He
Zimin He
XLXingyu Li
Xingyu Li
QMQiming Ma
Qiming Ma
RMRuibo Ming
Ruibo Ming
YZYi Zhang
Yi Zhang
Autonomous driving techniques have been flourishing in recent years while thirsting for huge amounts of high-quality data. However, it is difficult for real-world datasets to keep up with the pace of changing requirements due to their expensive and time-consuming experimental and labeling costs. Therefore, more and more researchers are turning to synthetic datasets to easily generate rich and changeable data as an effective complement to the real world and to improve the performance of algorithms. In this paper, we summarize the evolution of synthetic dataset generation methods and review the work to date in synthetic datasets related to single and multi-task categories for the autonomous driving perception study. We also discuss the role that synthetic datasets play in the evaluation, gap test, and positive effect of autonomous driving-related algorithm testing, especially on trustworthiness and safety aspects, and provide examples of evaluation experiments. Finally, we discuss the limitations and future directions of synthetic datasets. To the best of our knowledge, this is the first survey focusing on the application of synthetic datasets in autonomous driving. This survey also raises awareness of the problems of real-world deployment of autonomous driving technology and provides researchers with a possible solution.

22 May 2013 in Numerical Heat Transfer, Part A: Applications
Verified
Journal Article
Closed access
ZSZhihang Song
Zhihang Song
BMBruce T. Murray
Bruce T. Murray
BSBahgat Sammakia
Bahgat Sammakia
Modeling the thermal environment for data centers, including prediction of airflow and temperature distributions, is generally an extremely time-consuming process using full-scale CFD analysis. Reduced order models are necessary in order to provide real-time assessment of cooling requirements. The use of a coarse-grained zonal model is being investigated as a predictive tool, and this article details the development and implementation of a three-dimensional, pressurized zonal model. To construct and validate the zonal model, a basic data center configuration was analyzed using a finite volume software package. The calculated flow fields provide the spatial flow coefficients required in the zonal model, which is based on the power law method (PLM). A physically-based mapping between the controllable spatial mass flow rate and temperature distribution was obtained. Good agreement (within 10% average relative error) was obtained between the zonal model predictions and the CFD results. These preliminary results show promise that zonal models may yield an effective real-time thermal management design tool for data centers.

16 November 2020
Verified
Conference Paper
Closed access
PDF file
ZSZhihang Song
Zhihang Song
QZQian Zhang
Qian Zhang
The real-time smart data center cooling has become a key to maintenance and operation of energy-efficient data centers, primarily including the server inlet airflow/thermal domains. Here, the cold-aisle airflow phenomena in a widely-used cold/hot aisle data center configuration was under parametric investigation, This concern is mainly because of the airflow separation and recirculation from the stream emerging from the server outlet and returning to the computer room air-conditioning unit. In order to achieve a better understanding and to correspondingly eliminate the negative effects of the hot air over-tack recirculation towards a satisfied effectiveness, an addition of a rack-level adjustable fan unit (AFU), which is placed inside the cold aisle, was considered at an early stage and the model prototype was numerically analyzed with respects to differently predefined parameters. The cooling performance consequence, consisting of the server-neighbored inflow rates and maximum server inlet temperatures explored by computational fluid dynamics (CFD) observation panel and sensors, demonstrates that the over-rack air recirculation and its resulting hot spot, in comparison with the case in absence of the AFU, can be suppressed. The results additionally concludes the extents to which the optimized airflow organization and temperature drop of the rack-level region (e.g., from the bottom towards the top of the rack unit) can be achieved with/without the AFU addition.

16 November 2020
Verified
Conference Paper
Closed access
PDF file
ZSZhihang Song
Zhihang Song
Qiang YueQiang Yue
Qiang Yue
The phenomena of over-cooling commonly exist in data center thermal environment, resulting in a substantial waste of energy. Previous study has proposed a solution that implementing a wind turbine in a raised-floor data center by which the over-provisioned airflow can be utilized. The impingement of the computer room air-conditioner (CRAC) flow on the plenum walls (e.g., the floor slab) may yield key causes of the energy losses. Therefore, studying the effects of the wind turbine on the CRAC flow in the data center is necessary. Here, the data center and wind turbine were simulated and modeled using Computational Fluid Dynamics (CFD) package. In this research, the numerical measure of the pressure distributed on the floor slab was numerically measured as key observations. The positioning and axial induction factors of the wind turbine were treated as the major research parameters. The consequence illustrates that implementing a wind turbine with well-tuned axial induction factor and operating height might be capable of effectively decreasing the CRAC flow impingement and increasing the turbine power efficiency. This research may provide meaningful references for effective wind turbine applications for data center energy efficiencies.