Address

Contact Information

Email: sbra0523 AT uni DOT sydney DOT edu DOT au

Sarah Bradley

Internship Student

2022

Biography

Sarah Bradley is a second-year undergraduate Dalyell Scholar, currently enrolled in a Bachelor of Advanced Computing at the University of Sydney. Sarah has been awarded the two highest diplomas in music through the AMEB (LMusA, AMusA), performed at the Sydney Opera House as a soloist twice, and competed internationally on the flute. Earlier this year Sarah worked as a Data Analyst Intern with an Indonesian EdTech startup, MyEduSolve, where she delivered data-driven insights on product, marketing, UX, and potential areas of growth for the company. Sarah has worked with the Sydney Symphony Orchestra as a Young Ambassador, and has privately taught mathematics, piano, and flute. Sarah is interested in Data Science and Machine Learning, and her hobbies include reading non-fiction, playing music, and working out.

Project Title:

Efficient Drone Delivery in a Multi-Drone Skyway Network 

Project Description:

Drones are a new type of IoT devices that offer cost-effective and fast delivery services. The potential utilization of drones is limited by payload capacity and battery consumption constraints. Drones may need multiple times of recharge for persistent delivery operation. The drone delivery environment is highly constrained because the availability of recharging stations is not guaranteed. We leverage the service paradigm to address the key challenges in delivery by drones. The functional and non-functional properties of drones are abstracted as Drone-as-a-Service (DaaS). The drone services operate in a skyway network which is constructed by linking the skyway segments. Each skyway segment connects two nodes which are the rooftops of the high-rise buildings. Each node is assumed to be a recharging station or a delivery target. Given a source and a destination, the objective of this project is to collect a trajectory dataset considering the battery limitations and availability of pads on recharging stations. The dataset will be used for predicting the arrival of drones at certain stations in a multi-drone network and help in computing the best skyway segments leading to the destination.