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

Algorithm 1 Priority evaluation for each subtask.

	Input: computational complexity , the amount of data , the tolerable delay
	Output: the priority of subtask z
(1)	Sort subtask’s factor according to equation (9) and construct matrix P
(2)	for to maximum rows of P do
(3)
(4)	for to maximum columns of P do
(5)
(6)	end for
(7)	end for
(8)	are transformed through equation (12) to obtain R
(9)	for to maximum rows of R do
(10)
(11)	for to maximum columns of R do
(12)	update via equation (13)
(13)	end for
(14)	end for
(15)	calculate the information entropy via equations (14) and (15)
(16)	obtain via (16)
(17)