Optimal Probabilistic Policy for Dynamic Resource Activation Using Markov Decision Process in Green Wireless Networks.

Published in: IEEE Trans. Mob. Comput. (2014)

Keyphrases

wireless networks
markov decision process
finite horizon
optimal policy
state space
stationary policies
markov decision processes
infinite horizon
dynamic programming

reinforcement learning
average cost
wireless communication
base station
ad hoc networks
low bandwidth
initial state
cellular networks

wireless technologies
policy iteration
bayesian networks
generative model
mobile networks
machine learning
optimal control
reward function

finite state
network coding
supply chain
cooperative
optimal solution
average reward
multimedia services
decision problems