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

Algorithm 1

Modified Genetic Algorithm (MGA).

	Randomly generate the first generation. The population contains many individuals, and each individual contains a series of decision variables: coasting speed (V), dwell time (T). is used as a series of decision variables, which means . .
	whiledo
	Initialize the neighborhood structures set .
	, .
	whiledo
	whiledo
	Randomly generate a series of V and T within constraints to serve as a set of solutions in the neighborhood of .
	.
	end while
	, .
	end while
	Equations (9) and (10) are used to evaluate the fitness of the solution without a disturbance and under a disturbance, respectively.
	ifthen
	.
	else ifthen
	.
	end if
	.
	Decrease .
	if the probability of crossover then
	Crossover.
	end if
	if the probability of mutation then
	Mutation.
	end if
	end while
	Output the global optimum.