Reinforcement Learning-Based Routing Protocol to Minimize Channel Switching and Interference for Cognitive Radio Networks

Algorithm 2

Channel switching control in SUs during transmission.

(1)	Initialization: CSE ⟶ 0; DSF ⟶ 0; NAC ⟶ 0; LAC ⟶ θ;
(2)	for j  0 to j  M do
(3)	Learning LP (Nj(t) = 0), LP (tj,off > 0);
(4)	end for
(5)	if LP (Ni(t) = 0) < τL and DAT = 1 then
(6)	CSE  1;
(7)	end if
(8)	if CSE 1 then
(9)	for k  0 to k ≤ M do
(10)	if LP (Nj(t) = 0) τH ≥ And LP(tj,off) ≥ θ then
(11)	NAC ⟵ NAC + 1;
(12)	LAC(NAC) ⟵ k;
(13)	end if
(14)	end for
(15)	end if
(16)	if CSE ⟵ θ then
(17)	Stop transmission and goto Line 1;
(18)	else if LAC = θ then
(19)	Start scanning radio;
(20)	Launch channel selection of Algorithm 1 for LAC;
(21)	Send CSR packet;
(22)	end if
(23)	if CSA packet is received then
(24)	Switch to selected channel and start scanning radio;
(25)	end if
(26)	if channel is busy then
(27)	Stop transmission and goto Line 1;
(28)	else
(29)	DSF ⟵ 1; CSE ⟵ 0;
(30)	end if
(31)	if DSF ⟵ 1 then
(32)	DSF ⟵ 0;
(33)	Transmit a DATA packet;
(34)	DAT ⟵ 0 when transmission ends;
(35)	end if
Note. CSE–Channel Switching Event, DSF–Data Sending for Current Channel, NAC–Next Available Channel, LAC–List of Available Channel and DAT–Data Sending for next channel.