A Deep Reinforcement Learning Approach to the Optimization of Data Center Task Scheduling

Table 5

The task distribution in different delay time intervals.

Task delay time interval (T)	SJF (%)	FCFS (%)	Fair (%)	The proposed algorithm (%)
1	36.675	13.045	25.688	51.781
2	66.734	46.833	51.021	81.115
3	77.775	65.546	63.935	84.691
4	83.226	71.036	70.797	87.173
5	86.451	73.118	74.603	88.783
10	92.610	76.438	80.914	92.954
15	94.807	78.642	83.803	94.905
20	95.948	80.761	86.011	96.017