From: Intelligent deep reinforcement learning-based scheduling in relay-based HetNets
Notation | Description |
---|---|
N | Number of users |
I | \(:=\{1,\ldots ,N\}\), set of user indices |
K | Number of packets in a data block |
d | Coding field size |
\(X_0(t)\) | BS-to-RS channel’s state at time slot t |
\(X_i(t)\) | RS-to-user i channel’s state at time slot t |
X(t) | \(:=(X_0(t),X_1(t),\ldots ,X_N(t))\), aggregate CSI of the system at time slot t |
\(B_0(t)\) | Number of coded packets backlogged at the buffer of the RS at time slot t |
\(B_i(t)\) | Number of coded packets backlogged at the buffer of user i at time slot t |
B(t) | \(:=(B_0(t),B_1(t),\ldots ,B_N(t))\), aggregate BSI of the system at time slot t |
\(p_0\) | Probability that the BS-to-RS channel is in ON state at each time slot |
\(p_i\) | Probability that the RS-to-user i channel is in ON state at each time slot |
p | \(:=(p_0,p_1,\ldots ,p_N)\), aggregate channel parameters |