Table 23 Mean ± standard deviation over 30 independent trials (lower values are preferable for all parameters except success rate).

From: NF-MORL: a neuro-fuzzy multi-objective reinforcement learning framework for task scheduling in fog computing environments

Method

Makespan (s)

Energy (kWh)

Cost ($)

Task success rate (%)

NF-MORL

141.8 ± 3.9

9.74 ± 0.31

2.38 ± 0.09

95.9 ± 1.1

HTSFFDRL

207.4 ± 12.6

13.88 ± 0.94

3.61 ± 0.27

81.4 ± 4.3

DDPG-TS

229.6 ± 15.8

14.61 ± 1.12

3.89 ± 0.34

78.2 ± 5.1

DQN-TS+

218.3 ± 14.2

14.29 ± 1.05

3.77 ± 0.31

80.1 ± 4.8

GA-TS

263.9 ± 21.7

16.28 ± 1.46

4.31 ± 0.42

69.7 ± 6.4

Back to article page