Use deep reinforcement learning to improve radio resource scheduling in advanced cellular networks (LTE/5G).
With the rising number of mobile users and the large set of critical applications, such as Internet of Things, Smart Grid, and Smart Cities, it is fundamental to wisely and efficiently allocate the available radio resources in 5G networks.
In this project, we aim at using deep reinforcement learning techniques to improve the scheduling of radio resources in advanced cellular networks (LTE/5G). OpenAI Gym, NS-3 and NS-3 gym will be used:
The objective is to use existing LTE/5G simulation libraries in NS-3 and integrate them with the NS3-gym framework
The objective is to use existing LTE/5G simulation libraries in NS-3 and integrate them with the NS3-gym framework. Possibility to present the outcome of this project at international conferences and to publish in peer-reviewed journals.
Length of commitment | At least a semester. |
Start time | Spring, Summer, Anytime |
In-person, remote, or hybrid? | Remote |
Level of collaboration | Large group collaboration (4+ students) |
Benefits | Academic Credit |
Who is eligible | Sophomores, Juniors and Seniors who have programming experience with Python and C++. Working knowledge of Machine learning concepts would be preferred, but it is not mandatory. |
Filippo Malandra
Assistant Professor of Research
Electrical Engineering
Phone: (716) 645-1151
Email: filippom@buffalo.edu
Once you begin the digital badge series, you will have access to all the necessary activities and instructions. Your mentor has indicated they would like you to also complete the specific preparation activities below. Please reference this when you get to Step 2 of the Preparation Phase.
Electrical Engineering