Off-campus UMass Amherst users: To download campus access dissertations, please use the following link to log into our proxy server with your UMass Amherst user name and password.
Non-UMass Amherst users: Please talk to your librarian about requesting this dissertation through interlibrary loan.
Dissertations that have an embargo placed on them will not be available to anyone until the embargo expires.
ORCID
https://orcid.org/0009-0006-0579-6441
Access Type
Campus-Only Access for Five (5) Years
Document Type
thesis
Embargo Period
8-1-2024
Degree Program
Electrical & Computer Engineering
Degree Type
Master of Science in Electrical and Computer Engineering (M.S.E.C.E.)
Year Degree Awarded
2024
Month Degree Awarded
February
Abstract
Intelligent Transportation Systems (ITS) face important challenges in remote areas due to the lack of terrestrial infrastructure and low traffic flow, complicating the update of fundamental data for different applications. The integration of Geosynchronous Orbit (GEO) satellites, Low Earth Orbit (LEO) satellites, and High Altitude Platforms (HAP) in ITS offers a unique and effective solution to address these challenges. In this work, we design an ITS-enabled satellite-airborne-terrestrial network in which HAPs and RSUs are organized into clusters and cooperate for caching and computing. In particular, we study caching, bandwidth allocation, and computation offloading strategies to minimize latency and energy consumption. To solve this problem, a multi-agent cluster-based attention weight algorithm with federated update (Cluster-FCMC-Att) is proposed. The abbreviation FCMC stands for federated caching, matching, and computing. Federated learning supports information exchange between RSUs, and the attention mechanism assists HAPs in computing resource allocation and caching decisions. Our extensive numerical results show that our approach achieves fast and stable convergence, significantly decreases the delay and energy consumption, and computes about six times more data than existing schemes.
First Advisor
Beatriz Lorenzo
Recommended Citation
Yang, Shulun, "Collaborative Caching and Computation Offloading for Intelligent Transportation Systems enabled by Satellite-Airborne-Terrestrial Networks" (2024). Masters Theses. 1423.
https://scholarworks.umass.edu/masters_theses_2/1423