Natural disasters can destroy communication network components, potentially
leading to severe losses in connectivity. During those devastating events, network
connectivity is crucial for rescue teams as well as anyone in need of assistance.
Therefore, swift network restoration following a disaster is vital. However,
post-disaster network recovery efforts have been proven to be too slow in the
past.
Rapidly deployable networks (RDN) are communication networks that can
be configured as a wireless mesh network and can be integrated into an existing
communication network. As the name suggests, RDNs have a quick setup time
and are highly transportable. The technologies behind RDNs for communication
networks have received considerable advancements in recent times. Nonetheless,
the deployment strategy of such a network remains open.
The existing solutions on rapid post-disaster network recovery are built in
an inflexible way. First, each of them is designed around a specific problem.
Making slight modifications to the problem greatly increases the complexity of
the algorithm and can require major design changes to the system. Second,
the proposed solutions are unable to adapt to unexpected circumstances, such
as repair times taking longer than anticipated. We propose an online network
recovery approach to solve these flexibility issues.
With the optimization objective of maximizing a network's weighted connectivity
while minimizing the overall recovery process duration, we design a
Deep Reinforcement Learning (DRL) system to produce optimal RDN deployment
decisions. Experiments show our Deep Q-network (DQN) algorithm outperform
greedy and naive approaches on any disaster scenario.
Made an autonomous cloud-based video conversion system on AWS for the course Cloud Computing at TU Delft. The system consists of an EC2 instance that hosted a front end, made with Django, allowing users to upload video files to an S3 bucket. The upload gets logged in DynamoDB and the instance scales the amount of worker instances according to the demand. A worker instance automatically looks for the most recent job after getting launched, and starts working on transcoding it. The output file is then temporarily stored in a separate S3 bucket and supplied to the user.
Built an Android app that estimates the location of the device on the 5th floor of the EWI building at TU Delft. The app is capable of using both Bayesian localization, where prior training was done, and particle filtering. This project was done for the course Smart Phone Sensing.