Download now Free registration required
In this paper, the authors propose two Reinforcement Learning (RL) algorithms as a solution for the aggregated interference management, in realistic femto networks characterized by high dynamism due to, e.g., mobility of users, lognormal shadowing, fast fading, random activity patterns of femto nodes, etc. They discuss the Q-Learning (QL) algorithm, presented in previous works, which allows to learn online the most appropriate resource allocation policy, by continuous interactions with the environment. They improve it by fuzzy logic, in the form of Fuzzy Q-Learning (FQL), which allows a continuous state and action representation and a faster learning process.
- Format: PDF
- Size: 160.9 KB