A Real-Time Train Timetable Rescheduling Method Based on Deep Learning for Metro Systems Energy Optimization under Random Disturbances

Table 8

Performances with three strategies in the three-train metro system.

Strategy	Calculation time (s)	Net traction energy consumption (kWh)	Energy-saving percentage compared with no-action strategy (%)
No action	0	412.23	—
MGA	13768.68	380.82	7.62
MGA-GRU	0.27	386.84	6.16