Time-Driven Scheduling Based on Reinforcement Learning for Reasoning Tasks in Vehicle Edge Computing

Algorithm 3

Algorithm implementation.

	Input:, , , ,
	Output:
(1)	Initialization: set the array , the subtask queue Q and the set of predecessor nodes R to
(2)	Use the constraint relationship to set the array
(3)	Enqueue the subtask with to Q and set the number of traversed subtasks , the number of subtasks in the current layer to the current queue size
(4)	whiledo
(5)	if u = k then
(6)	.
(7)	end if
(8)	The subtask is dequeued, and the task is expressed as ,
(9)	for to do
(10)	if there exists a directed edge of to i then
(11)	Add the subtask and its predecessor node set R() to R(i) I(i)- = 1
(12)	if I(i) = 0 then
(13)	enqueue the subtask to Q
(14)	end if
(15)	end if
(16)	end for
(17)	end while
(18)	According to , the subtasks are assigned to edge nodes.
(19)	Initialization: set the subtask completion list to , set the remaining execution latency of subtasks by , and set the current running time
(20)	whiledo
(21)	Determine the subtask to be assigned to each edge node, which satisfies the direct predecessor set is subset of
(22)	Find the minimum execution latency from the currently executed subtasks in parallel
(23)	, when , add the subtask to and set
(24)	end while
(25)	return h