Operation plan tuning method and system, storage medium and equipment

Abstract

The invention provides an operation plan tuning method and system, a storage medium and equipment. The method comprises the following steps: setting a control range and a visual range in different time periods; calculating dominant solutions for the parameters in each visual range; and performing regulation and control in a control range corresponding to the visual range according to the dominant solution. According to the operation plan tuning method, the calculation efficiency is improved.

Description

Technical Field

[0001] The present invention belongs to the field of rail transit technology, and in particular relates to an operation plan optimization method, system, storage medium and device. Background Art

[0002] In the field of urban rail transit, the operation plan can determine the operation order of multiple trains before the trains run. Due to the widespread use of ATO (Automatic Train Operation) automatic driving technology, the train operation punctuality rate is very high, and the actual operation of the train is consistent with the operation plan in most cases.

[0003] With the development of technology, more and more static operation requirements, such as energy saving in operation diagrams and trains entering stations at different times, or dynamic operation requirements, such as automatic adjustment of train formation according to passenger flow and automatic adjustment of train operation density, have emerged. Regardless of static or dynamic operation requirements, the time of planned arrival and departure is usually used as the solution to the problem. Such problems often have multiple possible solutions. Compared with accuracy, the role of quickly calculating feasible solutions is more important.

[0004] The existing operation plan optimization method mainly uses the calculation model to calculate the entire operation plan and obtain possible solutions. However, due to the long operation time of the operation plan and the large number of arrival and departure points, the total number of parameters that need to be solved is too large, so the amount of calculation is extremely large, the requirements for computing resources are high, and the computing efficiency is low. Although it can be processed by increasing hardware resources to ensure that all processing is completed within a limited time, excessive investment will bring other disadvantages.

[0005] At the same time, the solution process corresponding to static and dynamic operation requirements requires a lot of calculations during the solution process, but these operation requirements themselves are uneven, and different calculations are required in different situations. If the hardware is prepared according to the maximum calculation requirements, its usage frequency will fluctuate significantly, thus wasting some computing power and the economic effect of computing resources is relatively poor. Summary of the invention

[0006] In view of the shortcomings of the prior art, the present invention provides an operation plan tuning method, system, storage medium and device, which divides the time period to be calculated into segments and sets them into multiple control ranges and corresponding visible ranges, calculates the dominant solution for the parameters within the visible range, and performs regulation within the corresponding control range. The complexity of the operation plan tuning calculation process is simplified through segmented calculation, thereby improving the calculation efficiency.

[0007] The present invention is achieved through the following technical solutions:

[0008] Set the control range and visible range in different time periods;

[0009] Calculate the dominant solution for each parameter within the visible range;

[0010] The control is performed within the control range corresponding to the visual range according to the dominant solution.

[0011] Optional,

[0012] The control range and visual range are set in different time periods, including:

[0013] Divide the time period to be calculated into a preset number of control ranges;

[0014] Set the corresponding visible range for each control range.

[0015] Optional,

[0016] The step of setting a corresponding visible range for each control range includes: extending a preset time on the basis of the control range and setting the time as the visible range.

[0017] Optional,

[0018] The method of calculating the dominant solution for each parameter within each visible range includes:

[0019] Using the computational model, the dominant solution is calculated for each parameter within the visible range.

[0020] Optional,

[0021] Based on the operation plan in the previous control range after regulation according to the dominant solution, the dominant solution in the visible range corresponding to the next control range is calculated.

[0022] The present invention also provides an operation plan tuning system for implementing the above method, the system comprising:

[0023] A time period setting module is used to set the control range and the visible range for the time period to be calculated;

[0024] A calculation module, used for calculating a dominant solution for each parameter within each visible range;

[0025] The control module is used to perform control within a control range corresponding to the visual range according to the dominant solution.

[0026] Optional,

[0027] The time period setting module is also configured to:

[0028] Divide the time period to be calculated into a preset number of control ranges;

[0029] Set the corresponding visible range for each control range.

[0030] Optional,

[0031] The step of setting a corresponding visible range for each control range includes: extending a preset time on the basis of the control range and setting the time as the visible range.

[0032] Optional,

[0033] The computing module is further configured to:

[0034] Using the computational model, the dominant solution is calculated for each parameter within the visible range.

[0035] Optional,

[0036] Based on the operation plan in the previous control range after regulation according to the dominant solution, the dominant solution in the visible range corresponding to the next control range is calculated.

[0037] The present invention also provides a computer-readable storage medium storing one or more programs, which, when executed, can implement the aforementioned operation plan tuning method.

[0038] The present invention also provides a device, comprising a processor, a communication interface, a computer-readable storage medium and a communication bus; wherein the processor, the communication interface and the computer-readable storage medium communicate with each other via the communication bus;

[0039] The processor is configured to execute a program stored in a computer-readable storage medium.

[0040] Compared with the prior art, the present invention has the following advantages:

[0041] 1. The operation plan optimization method proposed in the present invention divides the time period to be calculated into segments, sets a control range and a corresponding visible range for each time period, and makes the control range of each time period independent, thereby greatly reducing the search range of the dominant solution for the entire time period and improving the calculation efficiency.

[0042] 2. Calculate the optimal solution for the parameters within the visible range of each period after segmentation. Simplify the complexity of the operation plan optimization calculation process through segmented calculation, reduce the amount of calculation, save hardware costs and calculation time, and improve calculation efficiency.

[0043] 3. By calculating the dominant solution for the parameters within the visible range of each time period after segmentation, and adjusting within the corresponding control range, the dominant solution for each time period can be guaranteed to be optimal. The dominant solution after combination is a global dominant solution, and it is not easy to fall into the local dominant solution of a large model, thereby improving the tuning effect.

[0044] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 A schematic diagram of the process of running a plan tuning method is shown;

[0047] Figure 2 The schematic structural diagram of the operation plan tuning system is shown;

[0048] Figure 3 It is a structural schematic diagram of a device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] See attached Figure 1 , the method of the present invention comprises:

[0051] S1. Set the control range and visible range in different time periods;

[0052] The control range and the visible range are set in different time periods, including:

[0053] Divide the time period to be calculated into a preset number of control ranges;

[0054] Set the corresponding visible range for each control range.

[0055] The step of setting a corresponding visible range for each control range includes: extending a preset time on the basis of the control range and setting the time as the visible range.

[0056] S2, calculating the dominant solution for each parameter within the visible range;

[0057] The step of calculating the dominant solution for each parameter within each visible range includes:

[0058] Using the computational model, the dominant solution is calculated for each parameter within the visible range.

[0059] S3. Perform regulation within the control range corresponding to the visible range according to the dominant solution.

[0060] Wherein, based on the operation plan in the previous control range after regulation according to the dominant solution, the dominant solution in the visible range corresponding to the next control range is calculated.

[0061] Specifically,

[0062] 1. Set the control range and visible range.

[0063] Set the control range and visible range by time period, including:

[0064] Divide the time period to be calculated into a preset number of control ranges;

[0065] Set the corresponding visible range for each control range.

[0066] The corresponding visible range is set for each control range, including: extending a preset time on the basis of the control range and setting it as the visible range, that is, the visible range is larger than the control range.

[0067] In this embodiment, the visible range is set to extend the preset time on the basis of the control range, and it is necessary to ensure that the train can reach the next station within the visible range.

[0068] The train operation plan includes various time periods of the day. In urban rail transit, the trains make turns, and the stations and order passed by each up train are almost the same, and the down trains are similar. Therefore, in many cases, the operation plans of multiple trains in each time period are very similar, which provides a basis for using multiple time period segmentation calculation.

[0069] Second, calculate the dominant solution for each parameter within the visible range.

[0070] Using the computational model, the dominant solution is calculated for each parameter within the visible range.

[0071] In this embodiment, the specific technical content of finding the dominant solution through the calculation model is the existing technology and will not be described in detail here.

[0072] In this embodiment, since the number of parameters has a relatively large impact on the calculation, the dominant solution is calculated for each parameter within the visible range respectively, which can effectively reduce the number of parameters calculated each time, thereby saving calculation time and improving calculation efficiency.

[0073] 3. Control is performed within the control range corresponding to the visual range according to the dominant solution.

[0074] According to the calculated advantage solution of each visible range, regulation is performed within the corresponding control range, and the operation plan within the control range is optimized.

[0075] In this embodiment, the dominant solution is calculated based on the parameters within the visible range, but the control tuning parameter changes are not involved; the parameters of the operation plan within the control range are tuned based on the dominant solution. This ensures that the tuning parameters within each visible range do not affect the control within the previous control range.

[0076] In this embodiment, the speed of calculating the dominant solution through the model is related to the scale of the model. If the model is too large, the overall calculation speed will be slow. At this time, if all information is used in one model, the operation efficiency is low. Therefore, dividing the time period to be calculated into segments and then calculating each segment separately can effectively improve the operation efficiency.

[0077] However, when optimizing calculations by segmentation, the mutual influence between time periods needs to be considered. If the entire time period is simply divided into multiple time periods and then calculated separately, when the control and optimization calculations use the same range, since some calculations need to rely on the arrival and departure times of adjacent stations, decisions within a time period may be affected by the previous time period, and the boundary of a time period may cause part of the content of the previous time period to change, and this change may cause the solution of the previous time period to no longer be optimal, thus affecting subsequent calculations. If the optimal solution cannot be maintained in each time period, the calculation cannot be continued based on the previous time period, and the full time period model will be returned.

[0078] Therefore, the dominant solution is calculated based on the parameters within the visible range, but the control tuning parameter changes are not involved; based on tuning the parameters within the control range according to the dominant solution, it can be ensured that the tuning parameters of each period do not affect the control of the previous period.

[0079] In this embodiment, based on the operation plan in the previous control range after regulation according to the dominant solution, the dominant solution in the visible range corresponding to the next control range is calculated.

[0080] After optimizing the operation plan within the previous control range, one of the best solutions is selected to change part of the original overall operation plan, and the next step of calculating the dominant solution is based on the partially optimized operation plan, and so on, to complete all time periods.

[0081] In this embodiment, for the tuning process, the tuning is completed for each control range respectively. When the dominant solution of the current control range is determined, the parameters converted into the visible range of the next section will also be determined, which will not affect the result.

[0082] In this embodiment, the calculation effects of the dominant solutions within all control ranges are added together to obtain a final dominant solution.

[0083] Since some visible ranges will be calculated twice when calculating each visible range separately, when calculating the final advantage solution, the calculation effects of the segmented advantage solutions cannot be added up. Instead, it is necessary to bring the overall operation plan model into the calculation and add up the calculation effects of the advantage solutions within all control ranges to obtain the final advantage solution.

[0084] Since the calculation is performed segment by segment, it is equivalent to determining the dominant solution for one segment and then determining the dominant solution for the next segment. The model scale is reasonable, the calculation speed is acceptable, and the final optimization result is also reasonable.

[0085] The following examples specifically disclose the comparison of the number of calculations required for optimizing the operation plan by the method of the present invention and by a conventional method without segmentation:

[0086] The operating parameters to be set include: time period length, time adjustment range and number of stations, etc.

[0087] Assume there are three stations, six trains, and each station stops;

[0088] It is assumed that in the operation plan to be optimized, any two trains maintain a sufficient time difference at the arrival and departure points of each station, and the time difference remains reasonable after adjustment, that is, the operation plans before and after the adjustment are reasonable.

[0089] The number of possible solutions obtained by the method of the present invention is:

[0090] Assume that according to the set time period length, the full time period to be calculated is divided into three time periods: T1, T2, and T3, that is, three control ranges;

[0091] Assume that the six trains are evenly distributed, and time periods T1, T2, and T3 each have 2 trains.

[0092] Assume that the time adjustment range is set to: Each parameter has 10 options.

[0093] For each control range extending a preset time period, three corresponding visible ranges are set, that is, the control range is within the visible range, and every two adjacent visible ranges have an overlapping time. The dominant solution is calculated for the parameters within each visible range.

[0094] In each control range, there are 2 train numbers, 3 stations, and 2 arrival and departure points, namely, 2×3×2=12 time-related calculation parameters.

[0095] Since adjacent visible ranges overlap, the parameters in the overlapping ranges need to participate in the calculation of adjacent visible ranges. Assuming that the overlapping time period of adjacent visible ranges contains 2 parameters, the visible range corresponding to T1 contains: 12+2=14 parameters, the visible range corresponding to T2 contains: 2+12+2=16 parameters, and the visible range corresponding to T3 contains: 12+2=14 parameters.

[0096] Among them, the parameters within the visible range participate in the calculation of the dominant solution, and the parameters that are only within the visible range but not within the control range cannot change their parameter values.

[0097] The time adjustment range is: each parameter has 10 options, that is, there are 10 options for parking time and departure time.

[0098] Then the number of possible solutions within the visible range corresponding to T1 is: 10 14 , the number of possible solutions within the visible range corresponding to T2 is: 10 16 , the number of possible solutions within the visible range corresponding to T1 is: 10 14 .

[0099] Therefore, the total number of possible solutions for T1, T2, and T3 is: 10 14 +10 16 +10 14 .

[0100] The number of possible solutions obtained by the conventional method without segmentation is:

[0101] Assuming that there is no time division and other conditions are the same, all train numbers and parameters are combined and calculated within a range without segmented calculation.

[0102] The entire time period includes: 6 train numbers, 3 stations, and 2 arrival and departure points, that is, 6×3×2=36 time-related calculation parameters.

[0103] The time adjustment range is: Each parameter has 10 options, that is, the options for parking time and departure time are 10, so the number of possible solutions for the entire period when the calculation is not divided into sections is: 10 36 .

[0104] It can be concluded that when the method of the present invention is used for segmented calculation, the number of possible solutions is much smaller than the number of possible solutions when the time periods are not divided, and the smaller the number of possible solutions, the smaller the number of required calculations.

[0105] In this embodiment, a single calculation complexity comparison is performed according to the following steps:

[0106] When the number of parameters in the segmented calculation is 12+2 or 2+12+2, the total number of parameters in the segmented calculation is: (12+2)+(2+12+2)+(2+12)=44, while the number of parameters in the overall calculation is 36. Although the number of parameters in the overall calculation is slightly less, considering that the parameter variation range is very different, the segmented calculation still has a great advantage in terms of overall calculation time.

[0107] In this embodiment, the number of possible solutions is significantly reduced through segmented processing, thereby reducing the complexity of calculation, so that the optimization strategy can obtain the dominant solution more quickly and improve the optimization efficiency. At the same time, the calculation method can be flexibly adjusted for different time periods and visual ranges to improve the accuracy of the final control and provide better optimization strategies under dynamic scheduling and complex systems.

[0108] The present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0109] See attached Figure 2 , shows the structure of an operation plan tuning system for implementing the above method, including a time period setting module, a calculation module, and a control module.

[0110] The time period setting module is used to set the control range and the visible range in different time periods;

[0111] The calculation module is used to calculate the dominant solution for each parameter within the visible range;

[0112] The control module is used to perform control within a control range corresponding to the visual range according to the dominant solution.

[0113] In addition, an embodiment of the present invention further provides an operation plan tuning device, including:

[0114] Time period setting: setting the control range and visible range by time period; wherein, the time period to be calculated is cut into a preset number of control ranges, and a corresponding visible range is set for each control range.

[0115] The calculation module calculates the dominant solution for each parameter within the visible range respectively; wherein the dominant solution is calculated for each parameter within the visible range respectively using the calculation model.

[0116] The control module performs control within the control range corresponding to the visible range according to the dominant solution; wherein, based on the operation plan within the previous control range after the control is performed according to the dominant solution, the dominant solution within the visible range corresponding to the next control range is calculated.

[0117] Based on the same inventive concept, the present invention also provides a computer-readable storage medium storing one or more programs, which, when executed, can implement the aforementioned operation plan tuning method.

[0118] like Figure 3 As shown, an embodiment of the present invention further provides a device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus.

[0119] The memory is a computer-readable storage medium for storing one or more programs.

[0120] The processor is used to execute the program stored in the computer-readable storage medium.

[0121] The computer-readable storage medium may be included in the device / apparatus described in the above embodiments; or may exist independently without being assembled into the device / apparatus.

[0122] Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent substitutions for some of the technical features therein; and these modifications or substitutions do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing an operation plan, characterized in that: include: Set the control range and visible range in different time periods; Calculate the dominant solution for each parameter within the visible range; The control is performed within the control range corresponding to the visual range according to the dominant solution.

2. The method according to claim 1, characterized in that: The control range and visual range are set in different time periods, including: Divide the time period to be calculated into a preset number of control ranges; Set the corresponding visible range for each control range.

3. The method according to claim 2, characterized in that The step of setting a corresponding visible range for each control range includes: extending a preset time on the basis of the control range and setting the time as the visible range.

4. The method according to claim 1, characterized in that: The method of calculating the dominant solution for each parameter within each visible range includes: Using the computational model, the dominant solution is calculated for each parameter within the visible range.

5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Based on the operation plan in the previous control range after regulation according to the dominant solution, the dominant solution in the visible range corresponding to the next control range is calculated.

6. An operation plan tuning system, characterized in that: The system comprises: The time period setting module is used to set the control range and visible range in different time periods; A calculation module, used for calculating a dominant solution for each parameter within each visible range; The control module is used to perform control within a control range corresponding to the visual range according to the dominant solution.

7. The system according to claim 6, characterized in that The time period setting module is also configured to: Divide the time period to be calculated into a preset number of control ranges; Set the corresponding visible range for each control range.

8. The system according to claim 7, characterized in that The step of setting a corresponding visible range for each control range includes: extending a preset time on the basis of the control range and setting the time as the visible range.

9. The system according to claim 6, characterized in that The computing module is further configured to: Using the computational model, the dominant solution is calculated for each parameter within the visible range.

10. The system according to any one of claims 6 to 9, characterized in that: The system is also configured to: Based on the operation plan in the previous control range after regulation according to the dominant solution, the dominant solution in the visible range corresponding to the next control range is calculated.

11. A computer-readable storage medium storing one or more programs, characterized in that: When the one or more programs are executed, the operation plan tuning method described in any one of claims 1 to 5 can be implemented.

12. An electronic device comprising a processor, a communication interface, the computer-readable storage medium of claim 11, and a communication bus; wherein: The processor, the communication interface, and the computer-readable storage medium communicate electronically with each other via a communication bus; characterized in that: The processor is configured to execute a program stored in a computer-readable storage medium.

Images