03/29/2023
By Rinith Pakala

The Richard A. Miner School of Computer & Information Sciences invites you to attend a master’s thesis defense by Rinith Pakala on "Distributed Edge Computing system setup for vehicle communication."

Candidate: Rinith Pakala
Degree: Master’s
Defense Date: Friday, April 7, 2023
Time: 10 to 11 a.m. EST
Location: Southwick 313, North Campus and via Zoom.
Thesis/Dissertation Title: Distributed Edge Computing system setup for vehicle communication

Committee Members:

  • Cindy Chen (advisor), Computer Science Department, University of Massachusetts Lowell
  • Kshitij Jerath, Mechanical Engineering Department, University of Massachusetts Lowell
  • Tingjian Ge, Computer Science Department, University of Massachusetts Lowell

Abstract:
The advancement of communication technologies in edge computing has led to progress in various applications, including those that require vehicle-to-vehicle (V2V) or vehicle-to-infrastructure (V2I) communication. The improvement of infrastructure has led to greater availability of data transmission networks, which facilitate enhanced connectivity and data collection from IoT devices. The increasing number of IoT devices results in a significant amount of data streams, which can be utilized to improve decision-making models. Typically, the training for such models occurs at the cloud level, which may cause issues with communication and computational delays.

These delays affect both the reception of data streams from IoT devices at the cloud level and the transmission of model-based predictions from the cloud level to IoT devices. Reducing latency between the vehicle-ware (IoT device) and the cloud network (database) is crucial for safety-critical vehicle operations, and our proposed system is instrumental in achieving this goal.

Moreover, our system is designed to enable swift updates of predictions, ensuring that the vehicle receives more relevant safety-critical model predictions. Specifically, We will show the construction of our system for V2V and V2I applications, incorporating cloud-ware, middle-ware, and vehicle-ware levels.