Railway train operation scheduling method based on autonomous collaboration

Abstract

The invention discloses a railway train operation scheduling method based on autonomous coordination. The method comprises the following steps: inputting a train operation plan and emergency information; establishing a scheduling sub-group, and determining key information related to the group; establishing a scheduling agent group distributed optimization model; designing an intelligent agent distributed collaboration method; and a train operation plan in the jurisdiction range of the whole dispatching center is formed. According to the method, scheduling sub-groups corresponding to different stations are established according to emergency interference conditions, a scheduling agent group optimization model is established, cooperative solution of train receiving and departure operations of different stations in the groups is realized through an agent distributed cooperation method, and a whole operation adjustment scheme is obtained through combination. According to the method, a large-scale optimization problem is decomposed into a plurality of small-scale sub-problems to be dispersedly solved, so that the solving efficiency can be effectively improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of railway operation dispatching and command, and relates to a railway operation dispatching method based on autonomous cooperation. Background Art

[0002] Operation dispatching is the core of high-speed railway operation and one of the key technologies to ensure the safe and efficient operation of trains. At present, the railway dispatching and command system mainly uses a centralized method to issue stage plans from the dispatching center to stations. Stations single-mindedly and passively execute the stage plans issued by the dispatching center to generate route control instructions, so as to realize railway operation dispatching and command. When emergencies occur externally (including infrastructure failures, adverse weather conditions such as wind, rain, snow, etc.), which lead to conflicts in train operation resources and affect the scheduled operation of trains, the train operation plan is adjusted by the experience of dispatchers. The dispatching and command system lacks the autonomous decision-making ability to actively and accurately adjust the content of station arrival and departure operations in a timely manner according to changes in train status, operation environment, etc. Therefore, it is necessary to conduct collaborative command and decision-making on the train operation plan independently by stations and the dispatching center to further improve the train operation efficiency. Summary of the Invention

[0003] The purpose of the present invention is to provide a railway operation dispatching method based on autonomous cooperation, which can effectively realize the autonomous cooperative dispatching of railway operation under the interference of emergencies. The technical solution is as follows;

[0004] A railway operation dispatching method based on autonomous cooperation includes the following steps: Step 1: Input the train operation plan and emergency information, where the emergency information includes the train delay duration, infrastructure failure, and environmental interference data; Step 2: Based on the train set N and station set J in the current dispatching section, establish multiple dispatching sub-groups, each dispatching sub-group corresponding to a main station agent and associated neighbor station agents. The dispatching sub-groups are used to dynamically obtain train operation situation information and determine the train operation dispatching tasks within the group; Step 3: For each dispatching sub-group, establish a distributed optimization model, which takes minimizing the total train delay time and the number of arrival and departure track adjustments as the optimization goal, and calculates the comprehensive optimization goal through weighted summation; Step 4: Based on the distributed optimization model, design agent cooperation rules, including the determination of arrival and departure operation priorities, dynamic allocation of arrival and departure tracks, and data interaction mechanisms between groups, to generate local adjustment plans; Step 5: Merge the local adjustment plans of all dispatching sub-groups, update the global train operation plan, and achieve dynamic optimization through event-triggered or timed synchronization mechanisms.

[0005] The present invention also discloses a non-volatile storage medium, characterized in that a computer program is stored therein, and when the computer program is executed by a processor, the above-mentioned railway traffic scheduling method based on autonomous collaboration is implemented, wherein the method generates a train operation plan by dynamically establishing scheduling subgroups and distributed optimization models.

[0006] The present invention also discloses an electronic device, characterized in that it includes a processor and a memory, wherein the memory stores a computer program, and when the processor executes the computer program, it adjusts the railway traffic plan in real time based on the above-mentioned railway traffic scheduling method based on autonomous collaboration.

[0007] Beneficial Effects

[0008] In view of the interference of emergencies, the present invention establishes dispatching subgroups corresponding to different stations, and establishes a dispatching agent group optimization model. Through the distributed collaborative method of agents, the collaborative solution of the receiving and dispatching operations of different stations in the group is realized, and the entire operation adjustment plan is obtained by merging. This method decomposes a large-scale optimization problem into multiple small-scale sub-problems for decentralized solution, which can effectively improve the solution efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 It is a flow chart of a railway traffic dispatching method based on autonomous collaboration;

[0010] Figure 2 It is a schematic diagram of the train receiving and dispatching operations involved in different station dispatching groups. DETAILED DESCRIPTION

[0011] A railway traffic dispatching method based on autonomous collaboration, such as Figure 1 As shown, the following steps are included:

[0012] Step 1: Input train operation plan and emergency information.

[0013] The train operation plan is the key information for train dispatching. According to the train operation plan, the train operation diagram determines the arrival and departure times of trains at different stations, the use of station arrival and departure lines, the number of trains, the number of stations, the minimum safe interval time for stops, the minimum running time of the section, the minimum tracking interval time of trains and other information. Emergency events cause the train to be unable to run according to the scheduled plan, and the train operation status information deviates from the plan, resulting in train delays. Specific emergency event information includes delayed trains and their delay duration (including arrival delays and departure delays).

[0014] Step 2: Establish a dispatching subgroup and determine the key information involved in the group, including train operation status information, train dispatching tasks, station intelligent entities, etc.

[0015] Autonomous and collaborative railway train operation dispatching takes stations as individuals (also known as station agents). Each station agent completes functions such as route execution and active adjustment, and at the same time interacts with other station agents in the group to complete collaborative decision-making within the group.

[0016] Step 2.1: For a certain dispatching section, N and J are the train set and the station set respectively. Set dispatching sub-groups, that is, each station corresponds to a dispatching group. This group contains multiple station agents, including the current main station agent and neighbor station agents. There are duplicates among the station agents in different groups.

[0017] Step 2.2: Obtain the train operation situation information. This includes the running time of the train in the section and the stopping time at the station.

[0018] Step 2.3: Determine the train operation dispatching tasks and the scope of the dispatching group. Set the station dispatching time range T. For station j, according to the moment of the first incoming and outgoing train operation that has not been completed and the time period corresponding to the dispatching time range T for the trains involved in the station, determine the number of trains and the route information involved in each station agent. At the same time, each dispatching group determines the neighbor station agents belonging to the group according to the other stations passed by the trains involved in the main station agent within this time range . For group j (main station agent j), the train set involved is , and the station set is . Figure 2 Figure 23 is a schematic diagram of the incoming and outgoing train operations involved in 4 station dispatching groups. The stations, trains and their station operations involved in the group are respectively in the corresponding solid-line frames.

[0019] Step 2.4: The dispatching center can set a timed trigger mode or an event-driven trigger mode. After triggering, the train operation dispatching tasks of the group and the scope of the dispatching group will be updated. For example, if there is a new incoming and outgoing train operation within the station time range , the group will be updated and distributed collaborative optimization will be executed. Or if there is a new sudden interference scenario, the groups involved will be updated and distributed collaborative optimization will be executed.

[0020] Step 3: Establish a distributed optimization model for the dispatching agent group.

[0021] Its overall decision variable is the train operation plan of the group within a given time. Each agent jointly optimizes the overall objective function in the group by sharing local optimization decision variables. The local decision variable of the agent is the state of the route control information for the incoming and outgoing train operations of the trains at the corresponding station, including the arrival and departure times, order, and arrival and departure track allocation plan of the trains.

[0022] By establishing an individual utility value evaluation method (such as the total train delay time, the number of arrival and departure track adjustments, etc.), calculating the local optimization objective function, and considering the relevant constraints of the arrival and departure tracks of the station, the model construction is completed.

[0023] Step 3.1: Design the optimization objective of a single station agent.

[0024] (1) Minimize the total train delay time. For station j within group j (the main station agent j), the total delay time of the trains involved is minimized.

[0025] (1)

[0026] In the formula, , is the actual arrival time of train i at station j, is the actual departure time of train i from station j, is the planned arrival time of train i at station j, is the planned departure time of train i from station j.

[0027] (2) Minimize the number of arrival and departure track adjustments. For station j, the total number of arrival and departure tracks adjusted for the trains involved is minimized.

[0028] (2)

[0029] In the formula, , is whether train i actually occupies an arrival and departure track at station j , when occupied, it is 1, otherwise it is 0. is whether train i is planned to occupy an arrival and departure track at station j , when occupied, it is 1, otherwise it is 0. is the set of arrival and departure tracks of station j.

[0030] For the above two optimization objectives, the comprehensive optimization objective of a single station agent (station j) is calculated through weighted sum :

[0031] (3)

[0032] In the formula, , w1 and w2 are weights.

[0033] Step 3.2: Construct the optimization model involved in the decision-making within the group. For group j (the main station agent j), its corresponding optimization objective is the sum of the comprehensive optimization objectives of the corresponding stations within the group. For this optimization index, the station weights or train weights can be set specifically.

[0034] (4)

[0035] Optimization decisions within a group do not involve the time range within the group The train operation plan outside the group and the train operation plan of the corresponding station outside the group. Therefore, other decision plans are processed as constraints of the current group. Subsequent operations outside the station time range are postponed in the order of plan. For example, for downline trains, the train operation plan before entering the station involved in group j, including parameters such as arrival order, arrival and departure line occupancy, and arrival time, constrains the corresponding decision variables in group j. The plan after group j completes the optimization decision is used as the parameter of the subsequent group.

[0036] Step 3.3: Build a global optimization model. In the global optimization model, local optimization is no longer performed based on the stations and trains in the group, but for all stations and trains in the entire section. It can be used to verify the approximation of the distributed computing results.

[0037] Step 4: Design a distributed collaborative method for intelligent agents. Each intelligent agent achieves collaborative decision-making among different groups through heuristic methods based on the current situation information and the local optimization indicators of decision-making within the group.

[0038] For train receiving and dispatching operations that are not disturbed, they are executed as planned without adjustment. Therefore, distributed collaborative solution is performed for the receiving and dispatching operations affected by the situation that there is interference in the section operation before the execution of the train receiving operation or the station operation interference before the execution of the train departure operation.

[0039] Step 4.1: Consider the train in the down direction, taking station j as an example, there is a delay caused by arrival or departure interference, station The corresponding train receiving and dispatching operation sequence and time have been determined as known parameters. The disturbed receiving and dispatching operation of station j is taken as the decision variable to be optimized. Since the order of receiving and dispatching operations at station j is known, it is mainly necessary to determine the order of dispatching operations in the entire station operation. Establish a set of operations to be executed, and use the following rules to establish a constructive heuristic algorithm to determine the receiving and dispatching operations of the current station in turn:

[0040] (1) The corresponding train receiving operation for any train must be earlier than the train departure operation;

[0041] (2) When there is no unexecuted train pick-up operation at the station, the current train pick-up operation is executed;

[0042] (3) If the number of train receiving operations at the current station is the same as the number of train arrival and departure lines, only the departure operation is performed;

[0043] (4) The more the objective function (4) corresponding to the train receiving and dispatching operation at a certain station decreases, the higher the priority of executing this train receiving and dispatching operation;

[0044] (5) For train receiving operations, the planned arrival and departure lines should be used as much as possible. If the planned arrival and departure lines are occupied, other unoccupied arrival and departure lines should be selected.

[0045] Step 4.2: Method for allocating train receiving and dispatching operations at the station.

[0046] Step 4.2.1: When determining each operation at the station, first determine the type of operation that can be executed currently (train receiving operation or train dispatching operation) according to the set of operations to be executed.

[0047] Step 4.2.2: If it only contains train receiving operations, directly select this operation as the operation allocated at the current station. This conforms to the second rule in Step 4.1.

[0048] Step 4.2.3: If there are train receiving operations and train dispatching operations respectively currently, then according to the fourth rule in Step 4.1, calculate the difference between the objective function (4) under the train receiving operation (Plan 1) and the objective function (4) under the train dispatching operation (from Plan 2 to the maximum, with at most trains waiting to be dispatched) and the objective function (4) under the first-come-first-served rule. The larger the difference, the better the effect of using this operation plan on the recovery of train delays, and select this plan as the operation allocated at the current station. trains waiting to be dispatched) and the objective function (4) under the first-come-first-served rule. The larger the difference, the better the effect of using this operation plan on the recovery of train delays, and select this plan as the operation allocated at the current station.

[0049] It should be noted that the objective function (4) involves the arrival and departure times of all trains at the station in the set of stations of group j at the same time. For down trains, the arrival and departure times of the trains before station j have been determined. On the basis of determining some operations at the station in Step 4.2, determine the station operation plan by executing the current train receiving operation or train dispatching operation respectively. The subsequent operations are calculated according to the first-come-first-served rule. The arrival and departure times of station j and the subsequent stations are determined by running against the clock according to conditions such as train tracking interval constraints, arrival and departure line occupancy safety constraints, and minimum running time in the interval under the condition that the above station operation sequence is determined; the arrival and departure line allocation is carried out according to the fifth rule in Step 4.1. Calculate the objective function of all possible station operation plans respectively. It should be noted that the objective function (4) involves the arrival and departure times of all trains at the station in the set of stations of group j at the same time. For down trains, the arrival and departure times of the trains before station j have been determined. On the basis of determining some operations at the station in Step 4.2, determine the station operation plan by executing the current train receiving operation or train dispatching operation respectively. The subsequent operations are calculated according to the first-come-first-served rule. The arrival and departure times of station j and the subsequent stations are determined by running against the clock according to conditions such as train tracking interval constraints, arrival and departure line occupancy safety constraints, and minimum running time in the interval under the condition that the above station operation sequence is determined; the arrival and departure line allocation is carried out according to the fifth rule in Step 4.1. Calculate the objective function of all possible station operation plans respectively.

[0050] Step 4.2.4: If it only contains train dispatching operations, then according to the third rule in Step 4.1, calculate the train dispatching operations (from Plan 1 to Plan trains waiting to be dispatched The difference between the objective function (4) under this situation and the objective function (4) under the first-come, first-served rule. The larger the difference, the better the effect of using this operation plan on train delay recovery. Then select this plan as the operation assigned to the current station. The specific method is similar to the departure operation part in Step 4.2.3.

[0051] Step 4.2.5: After completing the assignment of station arrival and departure operations in Station j, continue to calculate the assignment of station arrival and departure operations in the station. The train arrival and departure times and the arrival and departure track assignment plan of Station j are used as model parameters. Until the assignment of arrival and departure operations for all stations in the entire section is completed, collaborative decision-making within the group is realized.

[0052] Step 5: After completing the autonomous collaboration within the group, the operation plans involved by all station agents are merged and provided to the dispatching center to form the train operation plan within the jurisdiction of the entire dispatching center. The global train operation plan is updated after any station agent within the group completes distributed collaborative optimization. If any current group has not completed the autonomous collaboration within the group, the previous stage plan is used as the global train operation plan.

[0053] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification is only the principle of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A railway train operation dispatching method based on autonomous collaboration, characterized in that It includes the following steps: Step 1: Input the train operation plan and emergency information, where the emergency information includes the train delay duration, infrastructure failures, and environmental interference data; Step 2: Based on the train set N and station set J in the current dispatching section, establish multiple dispatching sub-groups. Each dispatching sub-group corresponds to a main station agent and associated neighbor station agents. The dispatching sub-groups are used to dynamically obtain train operation situation information and determine the train operation dispatching tasks within the group; Step 3: For each dispatching sub-group, establish a distributed optimization model. The model aims to minimize the total train delay time and the number of arrival / departure track adjustments, and calculates the comprehensive optimization objective through weighted summation; Step 4: Based on the distributed optimization model, design agent cooperation rules, including the determination of the priority of arrival / departure operations, the dynamic allocation of arrival / departure tracks, and the data interaction mechanism between groups, to generate a local adjustment plan; Step 5: Merge the local adjustment plans of all dispatching sub-groups, update the global train operation plan, and achieve dynamic optimization through event-triggered or timed synchronization mechanisms.

2. The method for railway train operation dispatching based on autonomous collaboration according to claim 1 is characterized in that, The neighbor station agents of the dispatching sub-groups are dynamically associated through the train operation path, and the coverage time range T of each dispatching sub-group is determined according to the moment of the first unfinished arrival / departure operation.

3. The method for railway train operation scheduling based on autonomous collaboration according to claim 2, characterized in that, The further content of Step 2 is as follows: Step 2.1: For a certain scheduling section, N and J are respectively the train set and the station set; set scheduling sub-groups, that is, each station corresponds to a scheduling group; this group contains multiple station agents, including the current main station agent and neighbor station agents; there are duplicates among the station agents in different groups; Step 2.2: Obtain train operation situation information; It includes the running time of the train in the section and the stop time at the station; Step 2.3: Determine the train operation dispatching tasks and the scope of the dispatching group; Step 2.4: The dispatching center sets a timed trigger mode or an event active trigger mode.

4. The method for railway train operation dispatching based on autonomous cooperation according to claim 1, characterized in that the further content of Step 3 is as follows: By establishing an individual utility value evaluation method, calculate the local optimization objective function, and consider the relevant constraints of the station arrival / departure tracks to complete the model construction; Step 3.1: Design the optimization objective of a single station agent; (1) Minimize the total train delay time: For station j within group j, the total delay time of the trains involved is minimized; （1） Wherein, , is the actual arrival time of train i at station j, is the actual departure time of train i from station j, is the planned arrival time of train i at station j, is the planned departure time of train i from station j; (2) Minimize the number of arrival / departure track adjustments: For station j, the total number of arrival / departure tracks involved in train adjustments is the smallest. （2） wherein, , indicates whether train i actually occupies the arrival and departure track at station j , being 1 when occupied, otherwise 0; indicates whether train i is scheduled to occupy the arrival and departure track at station j , being 1 when occupied, otherwise 0; is the set of arrival and departure tracks at station j; For the above two optimization objectives, the comprehensive optimization objective of a single station agent is calculated through weighted summation : （3） In the formula, , w1 and w2 are weights; Step 3.2: Construct the optimization model involved in the intra-group decision-making. For group j, its corresponding optimization objective is the sum of the comprehensive optimization objectives of the corresponding stations within the group; for this optimization objective, set the station weights or train weights specifically: （4） The optimization decision within the group does not involve the train operation plan outside the time range within the group and the train operation plan of the corresponding stations outside the group; and the train operation plan of the corresponding stations outside the group; Step 3.3: Construct a global optimization model; in the global optimization model, local optimization is no longer carried out according to the stations and trains within the group, but for all stations and trains in the entire section, which is used to verify the degree of the distributed calculation results.

5. The method for railway train operation scheduling based on autonomous collaboration according to claim 1, wherein The content of Step 4 is as follows: Step 4.1: Considering the trains in the downward direction, there is a delay situation at Station j caused by arrival or departure interference. The train receiving and dispatching operation sequence and time at the station have been determined and are used as known parameters; the receiving and dispatching operations at Station j affected by interference are used as decision variables to be optimized; since the sequence of train receiving operations at Station j is known, it is mainly necessary to determine the sequence of departure operations in the overall station operations; establish a set of operations to be executed; (1) The arrival operation corresponding to any train must be earlier than the departure operation; (2) When there is no unexecuted arrival operation at the station, execute the current arrival operation; (3) If the number of arrival operations and the number of arrival / departure tracks at the current station are the same, only execute the departure operation; (4) The more the objective function (4) corresponding to the arrival / departure operation at a certain station decreases, the higher the priority of executing this arrival / departure operation; (5) Try to use the planned arrival / departure tracks for arrival operations. If the planned arrival / departure tracks are occupied, select other unoccupied arrival / departure tracks; Step 4.2: The method for allocating arrival / departure operations at the station.

6. The method for railway train operation dispatching based on autonomous cooperation according to claim 5, characterized in that the further content of Step 4.2 is as follows: Step 4.2.1: When determining each operation at the station, first determine the current executable operation type according to the set of operations to be executed; Step 4.2.2: If it only contains the train receiving operation, directly select this operation as the operation assigned to the current station; Step 4.2.3: If there are train receiving operations and train departure operations respectively at present, calculate the difference between the objective function (4) under the train receiving operation and the objective function (4) under the train departure operation and the objective function (4) under the first-come-first-served basis according to Rule 4 in Step 4.

1. The larger the difference is, the better the effect of using this operation plan on train delay recovery. Select this plan as the operation assigned to the current station; Step 4.2.4: If it only contains the train departure operation, calculate the difference between the objective function (4) under the train departure operation and the objective function (4) under the first-come-first-served basis according to Rule 3 in Step 4.

1. The larger the difference is, the better the effect of using this operation plan on train delay recovery. Select this plan as the operation assigned to the current station; Step 4.2.5: Complete the assignment of train receiving and dispatching operations at station j, and then continue to calculate the assignment of train receiving and dispatching operations at the station; the train arrival and departure times and the assignment plan of arrival and departure tracks at station j are used as model parameters; until the assignment of train receiving and dispatching operations at all stations in the entire section is completed, collaborative decision-making within the group is realized.

7. A non-volatile storage medium, characterized in that, A computer program is stored. When the computer program is executed by a processor, it implements the autonomous collaborative-based railway train operation scheduling method according to any one of claims 1-6. Among them, the method generates a train operation plan by dynamically establishing a scheduling subgroup and a distributed optimization model.

8. An electronic device, characterized in that, It includes a processor and a memory. The memory stores a computer program. When the processor executes the computer program, based on the autonomous collaborative-based railway train operation scheduling method according to any one of claims 1-6, it adjusts the railway train operation plan in real time.

Images