Event Driven Duty Cycling with Reinforcement Learning and Monte Carlo Technique for Wireless Network

Table 1

The notations used in the paper.

Notation	Description
qi	The capacity of the queue for nodes as node-i (i = 1, ..., N)
S, A, P, R	Components of MDP: state space, action space, transition probability, the reward function
α	Learning rate
γ	Discount factor
(i)	Value of node-i
G = (V, E)	WSN with the set of nodes, V, and edges, E
r	Transmission range of a node
NB(i)	Neighbor nodes of node-i
(i)	Duration of slots when node-i works
wk(i)	Slot when node-i is wake-up
p(i)	The parent node of node-i
c(i)	The child node of node-i
sch(i)	Transmission schedule of node-i
F(i)	Nodes of NB(i) forbidden to wake up
pc(i)	Candidate parent nodes of node-i
τ = (ns, …, nd)	The path from the source to the destination node