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

Table 7

The rescheduled timetable with the MGA-GRU method of the three-train system.

Section	Spacing (m)	Train no.	Departure instant	Arrival instant	Dwell time (s)	Coasting speed (m/s)
Xujiahui ⟶ Hengshan Road	1458.5	1	8:00:00	8:01:41	20	18.12
		2	8:02:00	8:03:29	29.9	19.88
		3	8:04:00	8:05:35	26.8	18
Hengshan Road ⟶ Changshu Road	1125.7	1	8:02:01	8:03:18	17.6	21.8
		2	8:03:59	8:05:13	20	20.92
		3	8:06:01	8:07:15	20.1	21.84
Changshu Road ⟶ South Shaanxi Road	979.2	1	8:03:35	8:04:42	27.3	20.68
		2	8:05:33	8:06:39	28.1	20.76
		3	8:07:35	8:08:41	20	18.76
South Shaanxi Road ⟶ South Huangpi Road	1377.4	1	8:05:09	8:06:35	24	18.76
		2	8:07:07	8:08:32	21.5	19.92
		3	8:09:01	8:10:26	20.1	21.76
South Huangpi Road ⟶ People’s Square	1526.8	1	8:06:59	8:08:31	21.7	19.52
		2	8:08:54	8:10:27	25.8	19
		3	8:10:47	8:12:19	22.8	19.08
People’s Square ⟶ Xinzha Road	961.2	1	8:08:53	8:09:59	—	18.2
		2	8:10:52	8:11:58	—	20.56
		3	8:12:42	8:13:47	—	18