Guoliang Xing's Group in Sustainability
Prof. Guoliang Xing's group is conducting research on sustainability issues with focuses on thermal monitoring in data centers, volcano monitoring, residential power usage profiling, and aquatic monitoring using robotic sensor networks.
Data centers have become a critical computing infrastructure in the era of cloud computing. The common practice to prevent server shutdowns caused by overheating is to overcool the server rooms, leading to excessive power consumption of the cooling systems. Prof. Xing's group has developed novel temperature monitoring and forecasting techniques that can not only prevent server shutdowns because of overheating, but also improve a data center's energy efficiency. The new approach integrates Computational Fluid Dynamics (CFD) modeling, in situ wireless sensing, with real-time data-driven temperature prediction.
In the last two decades, volcanic eruptions have led to a death toll of over 30,000 and damage of billions of dollars. Volcano monitoring is of great interest to public safety and environmental sustainability. Traditional broadband seismometers used in volcano monitoring systems are expensive, power-hungry, bulky, and difficult to install. Prof. Xing's group is working with geophysicists to create a new paradigm for real-time volcano monitoring using a large-scale sensor network consisting of hundreds of inexpensive wireless nodes.
Research has shown that providing users fine-grained information concerning their power usage in the home fosters conservation. However, existing approaches for residential power usage profiling require labor-intensive in-situ training processes to collect appliances' power usage signatures. Prof. Xing's group designed an ad hoc sensor system that can monitor appliance power usage without supervised training. By exploiting multi-sensor fusion and unsupervised machine learning algorithms, the new approach can classify the appliance events of interest and autonomously associate the power usage with respective appliances.
Monitoring important aquatic processes like harmful algal blooms (HABs) is of increasing interests to public health, ecosystem sustainability, marine biology, and aquaculture industry. In collaboration with Prof. Xiaobo Tan in the Dept. of ECE at MSU, Prof. Xing's group designed a novel approach for spatiotemporal aquatic field reconstruction using inexpensive, low-power, mobile sensing platforms called robotic fish. The new approach includes a rendezvous-based mobility control scheme where sensors collaborate in the form of a swarm to sense the environment, a novel feedback control algorithm that maintains the desirable level of wireless connectivity for a sensor swarm in the presence of significant environmental dynamics, and an information-theoretic model to maximize the accuracy of spatiotemporal field reconstruction accuracy.
Fig. 1 (right). Sensor deployment for thermal monitoring at MSU High Performance Computer Center.