考虑劣化维护的单机调度深度强化学习模型和算法
|
|
陈勇,杜习之,姜一炜,易文超,裴植,纪祖臻
|
Deep reinforcement learning models and algorithms for single-machine scheduling considering deteriorated maintenance
|
|
Yong CHEN,Xizhi DU,Yiwei JIANG,Wenchao YI,Zhi PEI,Zuzhen JI
|
|
| 表 2 R-M集成优化策略下的成本均值和标准差 |
| Tab.2 Mean and standard deviation of cost with R-M integrated optimization strategies |
|
| 规模 | SPT-M | | LPT-M | | FCFS-M | | EDD-M | | Mean | Std | | Mean | Std | | Mean | Std | | Mean | Std | | 10 | 200.0 | 0.0 | | 258.0 | 0.0 | | 192.0 | 0.0 | | 227.0 | 0.0 | | 20 | 1005.6 | 10.2 | | 1682.0 | 108.8 | | 1058.7 | 27.1 | | 1334.2 | 82.1 | | 30 | 2160.6 | 58.1 | | 3725.4 | 110.3 | | 2678.0 | 113.1 | | 3075.8 | 143.8 | | 50 | 3610.0 | 157.5 | | 8074.8 | 212.7 | | 4679.4 | 291.3 | | 5065.8 | 229.9 | | 80 | 11198.2 | 450.4 | | 22474.8 | 752.1 | | 14871.1 | 597.9 | | 15306.1 | 665.6 | | 100 | 16709.3 | 553.8 | | 33877.2 | 1188.9 | | 21372.8 | 856.8 | | 23350.4 | 886.7 | | 150 | 32096.0 | 1198.4 | | 71634.7 | 2146.8 | | 42847.3 | 1791.3 | | 47919.0 | 1474.0 | | | 规模 | MST-M | | CR-M | | MDD-M | | 基准 | | Mean | Std | | Mean | Std | | Mean | Std | | Mean | Std | | 10 | 197.0 | 0.0 | | 226.0 | 0.0 | | 191.0 | 0.0 | | 191.0 | 0.0 | | 20 | 1163.0 | 20.6 | | 1053.5 | 27.7 | | 973.8 | 22.5 | | 973.8 | 22.5 | | 30 | 2879.3 | 73.2 | | 2269.0 | 109.5 | | 2103.9 | 102.9 | | 2103.9 | 102.9 | | 50 | 4858.1 | 307.3 | | 3597.3 | 191.6 | | 3310.6 | 172.1 | | 3310.6 | 172.1 | | 80 | 15181.1 | 687.8 | | 11678.6 | 519.0 | | 10642.0 | 494.0 | | 10642.0 | 494.0 | | 100 | 21907.0 | 937.2 | | 16753.6 | 800.7 | | 15763.6 | 766.8 | | 15763.6 | 766.8 | | 150 | 43670.2 | 1579.2 | | 32857.9 | 1266.6 | | 30546.1 | 1166.5 | | 30546.1 | 1166.5 |
|
|
|