The Wireless Information Network Laboratory (WINLAB) at Rutgers University-New Brunswick has received a three-year, $1.5 million grant from the National Science Foundation to build a nationwide, community-based mobile edge sensing and computing infrastructure.
The collaborative effort will be led by Rutgers along with Indiana University, Temple University and New York Institute of Technology.
Traditional cloud computing occurs on remote central servers far from the user and devices, but mobile edge computing is computing that occurs near the user or devices, which include smart phones, smart appliances and voice-controlled systems like Amazon's Alexa. By placing computing services closer to their actual locations, users benefit from faster, more reliable services. Mobile edge computing is rooted in the need to process data locally in real time-situations where transmitting the data to a remote datacenter for processing causes unacceptable delays.
With autonomous vehicles, for example, mobile edge computing can share real-time information on road infrastructure, pedestrians and other cars, and weather conditions directly to the vehicles instead of interfacing with central cloud servers. By shifting the load of cloud computing to individual local servers, mobile edge computing helps reduce congestion and delays on mobile networks.
The current mobile edge sensing and computing research community suffers from labor-intense training, unrealistic experimental environments, dynamic interferences and security vulnerabilities in data/model sharing. Such issues are difficult to address with individual research groups conducting small-scale experiments at different locations.
"This is a new NSF project focusing on mobile edge sensing in various lab environments and developing artificial intelligence-based modeling to share with many other research groups nationwide. The infrastructure will provide remote accessible smart cars, robots and drones carrying mobile edge devices equipped with different types of sensors, such as WiFi, acoustic, electric, light and vibration," said Yingying (Jennifer) Chen, a professor of electrical and computer engineering and the associate director of WINLAB."
"This project aims to build a large-scale, community-based mobile edge sensing and computing infrastructure and facilitate low-effort data and model sharing on a national scale," said Chen, a pioneer in machine learning techniques and data mining methods to classify and model healthcare, security, system and network-related problems. "The proposed infrastructure can provide a solid foundation for interdisciplinary research in this community. It integrates multimodal experimental facilities to support practical and repeatable experimental evaluations."
The research tools and infrastructure services developed in this project will allow individual research groups in academia, industry and government to share their research data and models generated from practical experiments with low efforts.
Chen said researchers will be able to remotely configure the moving trajectories of smart cars and robots and adjust the sensors to study internal experimental environment factors and derive environment-independent models.
"This configuration capability flexibly provides many combinations of experimental setups, which can significantly reduce researchers' efforts in experimenting numerous environments or setups in order to understand edge device behaviors and derive computing models," she said.
