Mayfly Taylor Optimisation-Based Scheduling Algorithm with Deep Reinforcement Learning for Dynamic Scheduling in Fog-Cloud Computing

Table 4

Comparative discussion.

Dataset/VM		Methods/metrics	CAG	DNGSA	Scheduling based on containers	Policy learning	Proposed MTOA-based DQN
Fast storage	625	Energy consumption	0.07654125	0.06142533	0.05985413	0.05854125	0.05514253
		SLA	0.07541258	0.06985413	0.05654125	0.03985785	0.01787909
		Cost	0.34125863	0.32451258	0.29874513	0.28541253	0.26637318
	1250	Energy consumption	0.09325413	0.09054125	0.08954725	0.08874513	0.08654125
		SLA	0.09874513	0.08954125	0.07784585	0.02547513	0.0114253
		Cost	0.24125833	0.22142533	0.21425325	0.19857458	0.1654125
Rnd	250	Energy consumption	0.06471258	0.04801425	0.04814253	0.04412583	0.03591231
		SLA	0.07142533	0.05741253	0.05014253	0.04142533	0.01597958
		Cost	0.31242533	0.27451253	0.26214253	0.24142533	0.23088294
	500	Energy consumption	0.06324126	0.05014753	0.04125325	0.03914253	0.0162121
		SLA	0.07325413	0.07142533	0.05987453	0.02654125	0.0116571
		Cost	0.26412583	0.22475125	0.21425325	0.15231121	0.0855121