Y.B. Reddy (USA)
Reinforcement Learning, Heuristic Algorithm, frequency spectrum, OFDM, Subcarrier, modulation
An adaptive subcarrier and power allocation using Reinforcement Learning (RL) model for multiuser OFDM system is proposed. The goal of the proposed RL model is to minimize the Bit and Power requirement for each user. The RL model uses a form of discounted reward known as Q-learning to solve Quality of Services (QoS) provisioning for wireless adaptive subcarrier, bit, and power allocation. Q-learning does not require the explicit state transition model to solve the Markov decision problem; therefore more general and realistic assumptions can be applied to the underlying system model for this approach than in previous schemes [17-20]. The simulation results demonstrate that the proposed model can effectively handle the communications resources.
Important Links:
Go Back
