Advances, Systems and Applications
Table 1 Symbolic variables used by the system model
From: Distributed reinforcement learning-based memory allocation for edge-PLCs in industrial IoT
Variable | Meaning |
|---|---|
\(Tp_i\) | Data type i |
\(l_t ^ i\) | Absolute memory capacity allocated to \(Tp_i\) at time t |
\(x_i\) | The actual size of \(Tp_i\) type data |
\(n_t^i\) | The allocated data unit quantity for \(Tp_i\) at time t |
m | The total number of data types that exist in the system |
\(P_t\) | The partition of memory at time t. |
S | The set of all the states |
A | The set of all the actions |
\(R_{t+1}\) | The reward value corresponding to \((s_t,a_t)\) |
Mem | Edge PLC memory maximum capacity |
\(Ploss_t ^ i\) | Loss probability of \(Tp_i\) between t and \(t+1\) |
\(Ar_t ^ i\) | The amount of \(Tp_i\) that arrives between t and \(t+1\) |
\(loss_t ^ i\) | The amount of \(Tp_i\) that is lost between t and \(t+1\) |