SNIC
SUPR
SNIC SUPR
Simulations on Cloud
Dnr:

SNIC 2018/5-30

Type:

SNAC Small

Principal Investigator:

Li Yan

Affiliation:

Chalmers tekniska högskola

Start Date:

2018-03-08

End Date:

2019-03-01

Primary Classification:

20203: Communication Systems

Webpage:

Allocation

Abstract

Simulation of optical network optimization, need to solve integer linear programming problems. Do simulations of networks, communication systems, and theoretical calculations. And analyze the network simulation data to detect or predict fault node in the network before it happens. This involves using machine learning and deep learning techniques and, thus, GPU computations. Also, the project plans to use reinforcement learning to control the network in dynamic scenario. This will use the deep Q-learning and other related techniques, which require GPU computations as well.