1 Full Duplex MAC
Existing devices communicate in half-duplex due to self-interference.
However, as a result of advancing self-interference cancellation (SIC) technologies, full-duplex radio is now a plausible technology.
Modeling Full-Duplex MAC Design
Full-duplex link can be converted to a combination of symmetric and asymmetric links. Transmitting and receiving stations function the same way in symmetric full-duplex link operations but they operate differently in the asymmetric link operations. Two types have different characteristics when stations communicate with each other. We research the efficient MAC protocols to reflect them.
2 Reinforcement Learning for SON
It has become telco's burden to manually configure parameters of each base station in heterogeneous network (HetNet).
To tackle this issue, we are studying self-optimization of self-organizing network (SON).
Handover & Mobile Load Balancing Optimization
Handover (HO) and mobile load balancing (MLB) influence each other by moving users to other base stations, so their operations must be simultaneously optimized. However, it is difficult to get a closed-form solution of the joint-optimization problem because of a complex network topology. Therefore, we are trying to solve this problem through deep reinforcement learning which can handle complicated states.