Train timetable and speed curve optimization method and device and storage medium

Abstract

The invention relates to the technical field of train transportation, in particular to a train timetable and speed curve optimization method and device and a storage medium, and the method comprises the steps: obtaining the attribute information of a train and each operation interval of the train; by taking the minimum energy consumption as a target and taking the interval speed limit and punctuality operation of each operation interval as constraints, calculating to obtain an initial speed curve and an initial train timetable corresponding to each operation interval of each train; calculating traction network loss corresponding to each train under the same power supply arm according to the traction network equivalent model; and optimizing an initial speed curve and an initial train timetable by taking minimization of the sum of traction network loss of the trains under the whole line and maximization of overlapping time and on-time operation of traction and braking stages among the trains as targets. The optimization method disclosed by the invention has remarkable beneficial effects in the aspects of improving the energy utilization efficiency, improving the train operation efficiency, reliability and punctuality rate, promoting the sustainable development of a railway transportation system and the like.

Description

Technical Field

[0001] The present disclosure relates to the field of train transportation technology, and in particular to a method, device and storage medium for optimizing a train timetable and a speed curve. Background Art

[0002] With the rapid growth of rail transit systems, the cost of electricity consumption has also increased dramatically, becoming a major energy consumer in cities, and also bringing certain economic pressure to operating units. For example, about 50% of the total electricity consumed by urban rail systems is consumed by train traction energy, regenerative braking energy accounts for more than 30% of traction energy consumption, and about 40% of regenerative braking energy is not used in actual operation.

[0003] In the existing technology, most of them only consider the optimization of the operation of a single train, but have not considered the coordinated optimization of multiple trains and the utilization of regenerative braking energy. In fact, the regenerative braking energy generated by the train braking can be absorbed by the adjacent traction train. Therefore, the existing train speed optimization method has a low utilization rate of regenerative braking energy. Summary of the invention

[0004] The present invention provides a method, device and storage medium for optimizing a train timetable and a speed curve, so as to solve the problem that the utilization rate of regenerative braking energy in the existing train speed optimization method is low.

[0005] In a first aspect, the present disclosure provides a method for optimizing a train schedule and a speed curve, comprising:

[0006] Acquire the attribute information of the train to be operated on the target date and each operating range of the train;

[0007] Under a preset time optimization model, with minimum energy consumption as the goal, and with the speed limit and punctual operation of each operating interval as constraints, the running time of each train in each operating interval is calculated according to the attribute information of the train, and an initial train schedule and an initial speed curve corresponding to each operating interval are obtained according to the running time;

[0008] Obtaining an equivalent model of the traction network, and calculating, according to the equivalent model, when renewable energy is generated between multiple trains running under the same power supply arm, corresponding traction network losses when energy is transmitted to each train under the same power supply arm through the traction network;

[0009] With the goal of minimizing the sum of the traction network losses of each train on the entire line, maximizing the overlap time of the traction and braking phases between each train and on-time operation, the initial speed curve of each train is adjusted to obtain an optimized speed curve;

[0010] The initial train schedule is updated according to the optimized speed curve to obtain an optimized train schedule.

[0011] In one embodiment, under a preset time optimization model, with minimum energy consumption as the goal, and with the speed limit and punctual operation of each operating interval as constraints, the step of calculating the operating time of each train in each operating interval according to the attribute information of the train includes:

[0012] Calculating the shortest running time corresponding to each of the running intervals according to the speed limit constraints of each of the running intervals;

[0013] Inputting the attribute information of the train into the time optimization model, solving the model using a dynamic programming algorithm with the shortest running time of each running section and the maximum running time of the entire line as constraints, and obtaining an optimal solution set between running time and energy consumption;

[0014] According to the attribute information of the train, the line conditions of each operating interval and the time and energy consumption values ​​corresponding to each solution in the selected optimal solution set, the operating time of each train in each operating interval is calculated with the punctual operating time as a constraint condition, wherein the line conditions of the operating interval include at least one of interval distance, interval slope and track parameters.

[0015] In one embodiment, the step of solving the model using a dynamic programming algorithm to obtain an optimal solution set between the running time and energy consumption includes:

[0016] The model is solved by using a dynamic programming algorithm to obtain a first initial solution set;

[0017] All solutions in the first initial solution set are layered using a non-dominated sorting method, and the non-dominated solution set of the first layer is used as the optimal solution set.

[0018] In one embodiment, after the step of solving the model using a dynamic programming algorithm to obtain an optimal solution set between the running time and energy consumption, the method further includes:

[0019] Evaluate the merits of all solutions in the optimal solution set, delete solutions whose merits are less than a preset merit threshold, and obtain a non-dominated solution set;

[0020] The step of calculating the running time of each train in each running section based on the attribute information of the train, the line conditions of each running section, and the time and energy consumption values ​​corresponding to each solution in the selected optimal solution set, with the on-time running time as a constraint condition, comprises:

[0021] The time and energy consumption values ​​corresponding to each solution in the selected non-dominated solution set are used as the time and energy consumption values ​​corresponding to each solution in the selected optimal solution set. According to the attribute information of the train, the line conditions of each operating interval and the time and energy consumption values ​​corresponding to each solution in the selected optimal solution set, the running time of each train in each operating interval is calculated with the punctual running time as the constraint condition.

[0022] In one embodiment, the step of adjusting the initial speed curve of each train with the goal of minimizing the sum of the traction network losses of each train on the entire line, maximizing the overlap time of the traction and braking phases between each train, and on-time operation includes:

[0023] Inputting the line information of the operating section, the attribute information of the train and the information of the traction network into a preset multi-train speed curve collaborative optimization model to obtain a target multi-train speed curve collaborative optimization model;

[0024] Using a multi-objective particle swarm algorithm, the target multi-train speed curve collaborative optimization model is solved with the objectives of minimizing the total energy consumption of the train operation, maximizing the overlap time and on-time operation, and a target solution set is obtained, wherein the independent variables of the multi-train speed curve collaborative optimization model are the acceleration, departure time interval and station stop time of the train;

[0025] The initial speed curve of each train is updated according to the target solution set.

[0026] In one embodiment, the step of solving the target multi-train speed curve collaborative optimization model by using a multi-objective particle swarm algorithm with the goal of minimizing the total energy consumption of the train operation and maximizing the overlap time and punctual operation to obtain the target solution set includes:

[0027] Using a multi-objective particle swarm algorithm, the target multi-train speed curve collaborative optimization model is solved with the objectives of minimizing the total energy consumption of each train operation, maximizing the overlap time and running on time, and obtaining a second initial solution set;

[0028] The fitness of each solution in the second initial solution set is calculated, and a set of solutions corresponding to the fitness that meets a preset fitness screening rule is determined as the target solution set.

[0029] In one embodiment, in the step of calculating the fitness of each solution in the second initial solution set, the fitness is calculated as follows:

[0030]

[0031] Among them, E is the total energy consumption of each train operation, E i,tris the traction energy consumption of the i-th train, E i,reg is the regenerative braking energy of the i-th train, ω is the utilization rate of regenerative braking energy, E re is the overlapping energy of each train, E i,m,i,,m, is the energy used by train i, between stations m, during the traction phase from the regenerative braking energy fed back during the braking phase of train i, between stations m, T is the total on-time operation index of each train, T i is the running time of the i-th train, T i,0 The set running time of the i-th train.

[0032] In a second aspect, the present disclosure provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method described in the above aspect.

[0033] In a third aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method described in the above aspects when executed by a processor.

[0034] In a fourth aspect, the present disclosure provides a computer program product, including a computer program / instructions, which implements the steps of the method described in the above aspects when the computer program is executed by a processor.

[0035] The present disclosure provides a method, device and storage medium for optimizing a train schedule and speed curve. Through a preset time optimization model, the running time of each train in each operating interval is calculated with the goal of minimizing energy consumption. This step fully considers the attribute information of the train (such as vehicle type, traction performance, etc.) and the constraints such as the speed limit of the interval, thereby reducing the overall energy consumption under the premise of ensuring the safe operation of the train. Further, by calculating the traction network loss when the traction network transmits renewable energy between trains, and taking this as one of the optimization goals, the efficient use of energy is further promoted. In particular, when multiple trains are running under the same power supply arm, by optimizing the speed curve, the overlapping time of the traction and braking phases can be maximized, so that the renewable energy generated by the braking train can be effectively used by other trains, reducing unnecessary energy waste. Therefore, the formulation of the initial train schedule in this embodiment takes into account the running time of each operating interval, ensuring that the train can run according to the predetermined time node. The subsequent optimization process further considers multiple goals such as minimizing the traction network loss under the entire line, maximizing the overlapping time of the traction and braking phases, and punctual operation, and adjusting the speed curve makes the train operation more efficient and smooth. In the whole optimization process, on-time operation is always taken as one of the important constraints. By calculating the running time of each running section and adjusting the speed curve, it is ensured that the train can arrive and depart on time according to the scheduled timetable. That is, the optimization method of the train timetable and speed curve of this embodiment has significant beneficial effects in improving energy utilization efficiency, improving train operation efficiency, enhancing train operation reliability and punctuality, and promoting the sustainable development of the railway transportation system. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The present disclosure will be described in more detail below based on embodiments and with reference to the accompanying drawings:

[0037] Figure 1 A flow chart of a method for optimizing a train schedule and a speed curve provided in an embodiment of the present disclosure;

[0038] Figure 2 A schematic diagram of an equivalent circuit model of a traction substation provided by an embodiment of the present disclosure;

[0039] Figure 3 A schematic diagram of a system energy consumption model provided in an embodiment of the present disclosure;

[0040] Figure 4 A schematic diagram of energy distribution between adjacent trains under the same power supply arm provided in an embodiment of the present disclosure;

[0041] Figure 5 A schematic diagram of a flow chart for calculating the optimal running time of each train in each section provided in an embodiment of the present disclosure;

[0042] Figure 6 A schematic diagram of a multi-train speed curve collaborative optimization model process considering the utilization of renewable braking energy provided by an embodiment of the present disclosure;

[0043] Figure 7 An internal structural block diagram of a train schedule and speed curve optimization device provided by an embodiment of the present disclosure;

[0044] Figure 8 A flow chart of another method for optimizing a train schedule and speed curve provided in an embodiment of the present disclosure.

[0045] In the drawings, the same reference numerals are used for the same components and the drawings are not drawn to scale. DETAILED DESCRIPTION

[0046] In order to enable those skilled in the art to better understand the technical solution of the present disclosure, and to fully understand and implement how the present disclosure applies technical means to solve technical problems and achieve the corresponding technical effects, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only embodiments of a part of the present disclosure, not all of the embodiments. The embodiments of the present disclosure and the various features in the embodiments can be combined with each other without conflict, and the technical solutions formed are all within the scope of protection of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present disclosure.

[0047] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0048] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0049] Embodiment 1

[0050] Figure 1 The following is a flow chart of a method for optimizing a train schedule and speed curve provided by an embodiment of the present disclosure. Figure 1 As shown, a method for optimizing a train schedule and a speed curve comprises:

[0051] Step 110, obtaining attribute information of the train to be operated on the target date and each operating range of the train;

[0052] In this embodiment, the attribute information of the train includes the type of train (such as high-speed EMU (G prefix), intercity train (C prefix), ordinary EMU (D prefix), direct express (Z prefix), express (T prefix), fast (K prefix) and freight train (20,000 tons, 10,000 tons, ordinary train), etc.), marshaling information (including the number of carriages, the type of carriages and their arrangement order), the maximum operating speed and traction / braking performance (the acceleration and deceleration capabilities of the train), etc. The operating range refers to the interval between two stations. Different operating ranges have specific lengths and restrictions, such as the maximum operating speed and the minimum driving interval. The operating range may contain complex terrain and facilities such as curves, ramps, bridges and tunnels, which have a certain impact on the operation of the train. After obtaining the various operating ranges of the train, the line conditions and corresponding operating restrictions of different operating ranges can be further obtained.

[0053] Step 120, under a preset time optimization model, with minimum energy consumption as the goal, and with the speed limit and punctual operation of each operating interval as constraints, the running time of each train in each operating interval is calculated according to the attribute information of the train, and an initial train schedule and an initial speed curve corresponding to each operating interval are obtained according to the running time;

[0054] In this embodiment, the preset time optimization model comprehensively considers multiple factors such as train operation energy consumption, time, safety and comfort. The model is constructed based on the train attribute information (such as traction / braking performance, mass, air resistance, etc.), line conditions of the operating section (such as slope, curve radius and speed limit, etc.) and operation requirements (such as punctuality, stop time, etc.).

[0055] The goal of minimizing energy consumption means that during the optimization process, the primary goal is to minimize the energy consumption of the train. That is, under the premise of ensuring safety and punctuality, the energy consumption of the train during acceleration, uniform speed and deceleration should be minimized. Specifically, this goal can be achieved by adjusting the acceleration rate, maximum speed, deceleration rate and running speed in different sections of the train. Taking interval speed limit and punctual operation as constraints means that each operating section may have different speed limit requirements due to different line conditions. During the optimization process, it must be ensured that the running speed of the train does not exceed the speed limit of the corresponding section to ensure driving safety. At the same time, when optimizing the speed curve, it is necessary to consider constraints such as the departure time, arrival time and stop time of the train to ensure that the train can run on time.

[0056] The attribute information of the train has a direct impact on the running time of the train. In the optimization process, it is necessary to determine the optimal running time of the train in each running section through calculation or simulation based on these attribute information and line conditions. After determining the optimal running time of the train in each running section, the initial train schedule can be generated. The initial train schedule lists in detail the departure time, arrival time, and stop time of the train. At the same time, according to the running time and speed limit conditions, the initial speed curve corresponding to the train in each running section can be further obtained.

[0057] Step 130, obtaining an equivalent model of the traction network, and calculating, according to the equivalent model, when renewable energy is generated between multiple trains running under the same power supply arm, the corresponding traction network loss when the energy is transmitted to each train under the same power supply arm through the traction network;

[0058] In the railway transportation system, the traction network provides power for trains. The traction network is usually composed of contact network, feeder line, return line and other parts. When multiple trains run under the same power supply arm, renewable energy may be generated between trains, especially during the braking process of the train. In order to effectively utilize renewable energy and reduce traction network losses, it is necessary to calculate in real time the corresponding traction network losses when the traction network transmits energy to each train under the same power supply arm, and transmit the renewable energy to the train with smaller traction network losses to maximize energy utilization.

[0059] The equivalent model of the traction network is a simplified representation of the electrical characteristics of the actual traction network, which is used to simulate and analyze the current, voltage distribution and energy transmission process in the traction network. When the train is braking, its kinetic energy will be converted into electrical energy and fed back to the traction network to form renewable energy. This energy can be used by other trains that are accelerating or running at a constant speed under the same power supply arm, thereby reducing dependence on traditional energy and reducing operating costs. During the transmission of renewable energy, due to the resistance, inductance and other characteristics of the traction network, certain traction network losses will be generated. In order to calculate these traction network losses, an equivalent circuit (i.e., equivalent model) of the traction network is established for calculation.

[0060] In one embodiment, Figure 2 As shown in the figure, it is the equivalent circuit of the traction substation. Based on this circuit, the ∏-type equivalent circuit of the traction network under each power supply arm is established, and the corresponding traction network loss when the traction network transmits energy to each train under the same power supply arm is calculated. The specific calculation process is as follows:

[0061] Figure 2 In, E α and E β is an ideal voltage source, Z Τ is the equivalent impedance of the traction transformer, Z ex is the equivalent impedance of the traction network, Z eps is the equivalent impedance between the power supply arms.

[0062] 1. Calculate the output power of each motor, and the comprehensive energy consumption of the motor can be equivalent to the parallel connection of the induction motor and the dynamic load. Figure 3 As shown in the figure, it is a schematic diagram of the system energy consumption model, where:

[0063] Induction motor absorbed power model:

[0064]

[0065] Dynamic load model:

[0066]

[0067] Total power:

[0068]

[0069] Among them, E is the equivalent amplitude of the infinite bus, θ is the phase angle, X is the transient reactance, P S0 and Q S0 is the static initial value, V is the voltage at the generator end, and V0 is the rated voltage. v and Q v They are the indices of the motor's active and reactive power, respectively.

[0070] 2. According to the location of the train and the total power output of the motor, the line loss at this time is calculated using the power flow calculation method:

[0071]

[0072] Where ΔS is the power loss, U i is the point voltage at position i.

[0073] When multiple heavy-load trains are under the same power supply arm, the regenerative energy utilization mode is triggered. Figure 4 The figure shows the energy distribution diagram between adjacent trains. The train calculates the traction network loss according to its location and the power output of the motor, and supplies the regenerative braking energy to the train with smaller network loss in turn, thereby improving energy utilization.

[0074] Step 140, with the goal of minimizing the sum of the traction network losses of each train on the entire line, maximizing the overlap time of the traction and braking phases between each train, and punctual operation, adjusting the initial speed curve of each train to obtain an optimized speed curve;

[0075] In this embodiment, in order to improve the overall operational efficiency, reduce the loss of the traction network and ensure the punctual operation of the train, the initial speed curve of the train is optimized. The main goals of the optimization process are three:

[0076] 1. Minimize the traction network loss of the entire line: By adjusting the speed curve of the train, the energy loss generated by the train during traction and braking, especially the transmission loss in the traction network, is reduced, which helps to reduce operating costs and improve energy efficiency;

[0077] 2. Maximize the overlap time of the traction and braking phases between trains: When multiple trains are running under the same power supply arm, if their traction and braking phases can overlap, the renewable energy generated by the braking train can be used by the traction train. By optimizing the speed curve to maximize this overlap time, energy efficiency can be further improved;

[0078] 3. Ensure that trains run on time: During the optimization process, it is necessary to always ensure that the train's departure time, arrival time and stop time on the way meet the scheduled timetable requirements to ensure that the train runs on time.

[0079] In order to achieve the above objectives, in this embodiment, after comprehensively considering multiple factors such as the physical characteristics of the train, line conditions, operational requirements, and electrical characteristics of the traction network, a multi-objective optimization model can be established for the above optimization objectives, and a suitable optimization algorithm (such as genetic algorithm, particle swarm optimization algorithm, simulated annealing algorithm, etc.) can be used to solve the multi-objective optimization model. Afterwards, the initial speed curve of the train is adjusted according to the results of the optimization algorithm. During the adjustment process, it is necessary to consider the acceleration, uniform speed and deceleration processes of the train, as well as the operating speed limits and stop time requirements in different intervals. Through repeated iterations and adjustments, an optimized speed curve that meets the operational requirements, reduces traction network losses, and improves energy efficiency is obtained.

[0080] Step 150: Update the initial train schedule according to the optimized speed curve to obtain an optimized train schedule.

[0081] In this embodiment, the time nodes of the train at each key position (such as the starting point, end point, station, etc.) can be extracted from the optimized speed curve. The time nodes include the passing time, arrival time, and departure time of the train. Afterwards, the extracted time nodes are checked to ensure that the time nodes meet the operational requirements (such as the minimum stop time, interval operation time limit, etc.) and the actual situation (such as signal system control, turnout conversion time, etc.). According to the checked time nodes, the train timetable is recompiled to obtain the optimized train timetable.

[0082] In summary, the method for optimizing the train timetable and speed curve provided in this embodiment calculates the running time of each train in each operating section through a preset time optimization model with the goal of minimizing energy consumption. This step fully considers the attribute information of the train (such as vehicle type, traction performance, etc.) and constraints such as section speed limit, thereby reducing the overall energy consumption while ensuring the safe operation of the train. Furthermore, by calculating the traction network loss when the traction network transmits renewable energy between trains, and taking this as one of the optimization goals, the efficient use of energy is further promoted. In particular, when multiple trains are running under the same power supply arm, by optimizing the speed curve, the overlapping time of the traction and braking stages can be maximized, so that the renewable energy generated by the braking train can be effectively used by other trains, reducing unnecessary energy waste.

[0083] Therefore, the formulation of the initial train schedule in this embodiment takes into account the running time of each operating interval, ensuring that the train can run according to the predetermined time node. The subsequent optimization process further considers multiple goals such as minimizing the traction network loss under the entire line, maximizing the overlapping time of the traction and braking stages, and punctual operation. By adjusting the speed curve, the train operation is made more efficient and smooth. Throughout the optimization process, punctual operation is always regarded as one of the important constraints. By calculating the running time of each operating interval and adjusting the speed curve, it is ensured that the train can arrive and depart on time according to the predetermined schedule. That is, the optimization method of the train timetable and speed curve of this embodiment has significant beneficial effects in improving energy utilization efficiency, improving train operation efficiency, enhancing the reliability and punctuality of train operation, and promoting the sustainable development of the railway transportation system.

[0084] Embodiment 2

[0085] Based on the above embodiments, Figure 5 As shown, under the preset time optimization model, with the minimum energy consumption as the goal, and with the speed limit and punctual operation of each operating interval as constraints, the step of calculating the operating time of each train in each operating interval according to the attribute information of the train includes: calculating the shortest operating time corresponding to each operating interval according to the speed limit constraint of each operating interval; inputting the attribute information of the train into the time optimization model, using the shortest operating time of each operating interval and the maximum operating time of the entire line as constraints, solving the model using a dynamic programming algorithm to obtain an optimal solution set between the operating time and energy consumption; according to the attribute information of the train, the line conditions of each operating interval, and the time and energy consumption values ​​corresponding to each solution in the selected optimal solution set, with the punctual operating time as the constraint, calculating the operating time of each train in each operating interval, wherein the line conditions of the operating interval include at least one of interval distance, interval slope and track parameters.

[0086] In this embodiment, the model is solved using a dynamic programming algorithm with the shortest running time of each operating interval and the maximum running time of the entire line as constraints. The dynamic programming algorithm is a method for solving complex problems by decomposing the original problem into relatively simple sub-problems, so as to help find the optimal balance between energy consumption and running time under the premise of satisfying all constraints, that is, the optimal solution set. Each solution in the optimal solution set represents a possible train operation plan. According to the time and energy consumption values ​​corresponding to each solution, as well as the attribute information of the train and the line conditions of each operating interval (such as interval distance, slope, curve radius, etc.), the specific running time of each operating interval is further refined and calculated.

[0087] When calculating the running time of each operating section, the on-time running time is an important constraint. This constraint requires that the train needs to accurately control the time during the entire operation process, whether it is acceleration, constant speed or deceleration, to ensure that the train can arrive at each station on time according to the scheduled schedule. If it is found during the calculation process that the running time of a certain section cannot meet the requirements of on-time operation, it is necessary to adjust the operation strategy of the section (such as adjusting the speed curve, increasing or decreasing the stop time, etc.), or reselect other solutions in the optimal solution set as the operation plan.

[0088] In summary, this embodiment solves the problem of how to combine multiple factors (including train attribute information, line conditions of the operating section, and the optimal solution set obtained by the optimization algorithm) to calculate the specific operating time of the train in each operating section in the train operation optimization, and ensure that the train can run on time while optimizing energy consumption and operating time.

[0089] In one embodiment, Figure 5 As shown, the step of using a dynamic programming algorithm to solve the model to obtain the optimal solution set between running time and energy consumption includes: using a dynamic programming algorithm to solve the model to obtain a first initial solution set; using a non-dominated sorting method to stratify all solutions in the first initial solution set, and using the non-dominated solution set of the first layer as the optimal solution set.

[0090] The non-dominated sorting method is a method for sorting solution sets in multi-objective optimization problems. Based on the Pareto dominance relationship, the solutions in the solution set are divided into different levels (or frontiers). All solutions in the first initial solution set are layered according to the non-dominated sorting method: First, find all solutions that are not dominated by any other solution and put them into the first layer (i.e., the Pareto frontier). Then, continue to find new non-dominated solutions from the remaining solutions and put the new non-dominated solutions into the next layer. This process continues until all solutions are assigned to the corresponding levels.

[0091] After non-dominated sorting, the solution set of the first layer is the Pareto optimal solution set. These solutions achieve the best balance between running time and energy consumption, and there is no other solution that can reduce the running time without increasing energy consumption, or reduce energy consumption without increasing running time.

[0092] In this embodiment, a dynamic programming algorithm is combined with a non-dominated sorting method to solve the optimization problem between train running time and energy consumption. This can not only find the optimal solution, but also clearly show the trade-off relationship between different solutions, providing strong support for decision-making.

[0093] In one embodiment, Figure 5As shown, after the step of using a dynamic programming algorithm to solve the model and obtain the optimal solution set between the running time and the energy consumption, it also includes: evaluating the merits of all solutions in the optimal solution set, deleting the solutions whose merits are less than a preset merit threshold, and obtaining a non-dominated solution set; the step of calculating the running time of each train in each running interval based on the attribute information of the train, the line conditions of each running interval, and the time and energy consumption values ​​corresponding to each solution in the selected optimal solution set, with the punctual running time as the constraint condition, includes: using the time and energy consumption values ​​corresponding to each solution in the selected non-dominated solution set as the time and energy consumption values ​​corresponding to each solution in the selected optimal solution set, and calculating the running time of each train in each running interval based on the attribute information of the train, the line conditions of each running interval, and the time and energy consumption values ​​corresponding to each solution in the selected optimal solution set, with the punctual running time as the constraint condition.

[0094] In this embodiment, after the optimal solution set is calculated, the solutions in the optimal solution set are further screened, and the solutions whose merits are less than the preset merit threshold are deleted from the optimal solution set, and the remaining solution sets are used as non-dominated solution sets to reduce the redundancy of solutions and improve the calculation efficiency. In some embodiments, it is also possible to further control the number of solutions in the optimal solution set within a target range after deleting the solutions whose merits are less than the merit threshold based on the preset limit on the number of solution sets, and obtain a non-dominated solution set.

[0095] Specifically, the Euclidean distance calculation method can be used to evaluate the quality of the solutions in the optimal solution set. The calculation formula of the Euclidean distance is as follows:

[0096]

[0097] Where: d j is the Euclidean distance of the jth solution, y j,i is the i-th objective of the j-th solution.

[0098] Embodiment 3

[0099] On the basis of the above embodiment, the step of adjusting the initial speed curve of each train with the goal of minimizing the sum of the traction network losses of each train in the entire line, maximizing the overlapping time of the traction and braking stages between each train and on-time operation includes: inputting the line information of the operating section, the attribute information of the train and the information of the traction network into a preset multi-train speed curve collaborative optimization model to obtain a target multi-train speed curve collaborative optimization model; using a multi-objective particle swarm algorithm, solving the target multi-train speed curve collaborative optimization model with the goal of minimizing the total energy consumption of the train operation, maximizing the overlapping time and on-time operation to obtain a target solution set, wherein the independent variables of the multi-train speed curve collaborative optimization model are the acceleration, departure time interval and station stop time of the train; and updating the initial speed curve of each train according to the target solution set.

[0100] In this embodiment, the line information of the operating section (such as slope, curve radius, speed limit, etc.), the attribute information of the train (such as vehicle type, traction and braking performance, quality, etc.) and the information of the traction network (such as resistance, voltage drop, etc.) jointly determine the operating characteristics and energy consumption of the train in different sections. This information is input into the preset multi-train speed curve collaborative optimization model to build a target multi-train speed curve collaborative optimization model that can reflect the actual operating environment and train characteristics. This model will serve as the basic framework for the subsequent solution process.

[0101] Taking the train acceleration, departure time interval and station stop time as independent variables means that these parameters are the key factors that can be adjusted and controlled by the target multi-train speed curve collaborative optimization model during the optimization process. Specifically:

[0102] Train acceleration: Acceleration determines the rate of change of speed of the train during acceleration and braking. By adjusting the acceleration, the speed curve of the train can be optimized to meet the running time requirements while minimizing energy consumption. For example, a large acceleration can be used to accelerate quickly on a gentle slope, while on a steep slope or speed-limited section, the acceleration needs to be appropriately reduced to ensure safety and stability;

[0103] Departure time interval: The departure time interval refers to the time difference between two adjacent trains departing from the same station or different stations. By optimizing the departure time interval, the overlapping time of the traction and braking phases between trains can be maximized, thereby reducing the load fluctuation and energy consumption of the traction network. At the same time, a reasonable departure time interval can also ensure a safe distance between trains and avoid accidents such as rear-end collisions;

[0104] Stop time at a station: Stop time at a station refers to the time a train stays at a station, including the time required for passengers to get on and off the train, and for the train to change direction. This parameter has a direct impact on the train's operating efficiency and punctuality. By optimizing the stop time at a station, it can be ensured that the train can arrive at each station on time according to the scheduled schedule, improving operational reliability and passenger satisfaction. At the same time, reducing unnecessary stop time can also shorten the overall running time of the train and improve operational efficiency.

[0105] In the target multi-train speed curve collaborative optimization model, the above independent variables are interrelated and jointly determine the train's operating performance and energy consumption. By adjusting the values ​​of these independent variables, we can find the target solution set that minimizes the total energy consumption of train operation, maximizes the overlap time, and meets the requirements of punctual operation. The target solution set provides scientific guidance for the actual operation of the train.

[0106] In one embodiment, the step of using a multi-objective particle swarm algorithm to solve the target multi-train speed curve collaborative optimization model with the goals of minimizing the total energy consumption of the train operation, maximizing the overlapping time and running on time to obtain a target solution set includes: using a multi-objective particle swarm algorithm to solve the target multi-train speed curve collaborative optimization model with the goals of minimizing the total energy consumption of each train operation, maximizing the overlapping time and running on time to obtain a second initial solution set; calculating the fitness of each solution in the second initial solution set, and determining the set of solutions corresponding to the fitness that meets the preset fitness screening rules as the target solution set.

[0107] Specifically, Figure 6 As shown in FIG. 1 , a schematic diagram of the calculation process of the target multi-train speed curve collaborative optimization model considering the utilization of regenerative braking energy is shown. The specific calculation process is as follows:

[0108] 1. Initialize the particle swarm parameters and normalize the independent variables;

[0109] 2. Update the speed and position of the particles to generate the second initial solution set. Each particle represents a set of possible solutions, including the acceleration of the train, the departure time interval, and the stop time at the station. By updating the speed and position of the particles and continuously iterating to search for high-quality solutions, the second initial solution set is obtained;

[0110] 3. Denormalize the particles, feed them into the fitness function, and calculate the fitness; evaluate the quality of each particle based on the fitness;

[0111] 4. Store high-quality solutions into the target solution set. Further, the non-dominated sorting method and Euclidean distance calculation method can be used to maintain the optimal solution set.

[0112] 5. Determine whether the number of iterations has been reached. If so, the iteration ends and step 6 is executed; if not, step 3 is executed;

[0113] 6. Output the running timetable of each train and the running speed curve of each section.

[0114] In one embodiment, in the step of calculating the fitness of each solution in the second initial solution set, the fitness is calculated as follows:

[0115]

[0116] Among them, E is the total energy consumption of each train operation, E i,tr is the traction energy consumption of the i-th train, E i,reg is the regenerative braking energy of the i-th train, ω is the utilization rate of regenerative braking energy, E re is the overlapping energy of each train, E i,m,i,,m, is the energy used by train i, between stations m, during the traction phase from the regenerative braking energy fed back during the braking phase of train i, between stations m, T is the total on-time operation index of each train, T i is the running time of the i-th train, T i,0 The set running time of the i-th train.

[0117] Embodiment 4

[0118] Based on the above embodiment, this embodiment provides an application example, which is applied to the operation optimization of heavy-haul railway. Figure 8 As shown, the overall optimization process is as follows:

[0119] S1. Obtain heavy-load train information, line information, number of trains running on the day, and traction network data;

[0120] S2. Divide the entire line into sections for heavy-load trains according to the platform locations. According to the basic properties of the trains and lines running on that day, establish a train time optimization model for each train in each section. Solve the model using a multi-objective dynamic programming algorithm based on Pareto frontier maintenance to obtain the relationship between the energy consumption and time of each train in each section.

[0121] S3. Based on the relationship between the energy consumption and time of train operation in each section, the dynamic programming algorithm is used to solve the model to obtain the running time of each train in each section. The first train refers to the window time of each station (the window time is used for the maintenance and overhaul of the railway line) to obtain the running timetable of the first train;

[0122] S4. Establish an equivalent model of the traction network under multiple trains and multiple sections, trigger the use of renewable braking energy under the same power supply arm, and when renewable energy is transmitted to multiple trains, calculate the line loss of the traction network according to the location of the heavy-loaded train and the output power of the motor, so that the renewable energy can be transmitted to the train with smaller network loss, and complete the power distribution of the regenerative braking energy;

[0123] S5. Establish a multi-train speed curve collaborative optimization model that takes into account the utilization of renewable braking energy, with the goal of minimizing the traction energy consumption of heavy-load trains on the entire line, maximizing the overlapping time of the traction and braking phases of heavy-load trains, optimizing the speed curves of each heavy-load train, and adjusting the departure interval and station stay time of each train;

[0124] S6. Obtain the operation schedule of each train and the speed operation curve of each section, and determine the optimal operation plan for the entire line of trains.

[0125] Furthermore, the step S2 specifically includes the following sub-steps:

[0126] S21, dividing the line into several areas according to the station locations of the line;

[0127] S22. Calculate the shortest running time of each section according to the speed limit constraints of each section. Obtain the basic attributes of the heavy-load train in each section according to the marshaling conditions of each station;

[0128] S23. A model of train running energy consumption and time is established according to the heavy-load train attributes and line conditions. The shortest running time of each section and the maximum running time of the entire section are used as constraints, and a multi-objective dynamic programming algorithm based on Pareto frontier maintenance is used to solve the model.

[0129] S24, a multi-objective dynamic programming algorithm based on Pareto frontier maintenance, with train running time and energy consumption as the target, uses a dynamic programming algorithm to traverse all solutions, sorts all solutions into non-dominated order, and stores the non-dominated solution set of the first layer into the optimal solution set;

[0130] S25. Use the Euclidean distance calculation method to evaluate the quality of the solutions in the optimal solution set, delete the redundant solutions according to the set number of solution sets, and obtain the optimal solution set that meets the requirements of the relationship between train operation energy consumption and time.

[0131] The calculation formula of Euclidean distance is:

[0132]

[0133] Among them, d j is the Euclidean distance of the jth solution, y j,i is the i-th objective of the j-th solution.

[0134] Furthermore, the step S3 specifically includes the following steps:

[0135] S31, according to step S2, the Pareto relationship between the energy consumption and time of the train operation with constraints in each section is obtained, and the energy consumption corresponding to the operation time of each section is used as the independent variable, and the on-time operation time is used as the constraint to establish the energy-saving optimization model of the heavy-duty train;

[0136] S32, with the goal of minimizing energy consumption, a dynamic programming algorithm is used to traverse all solutions of the above model to obtain the optimal running time of each heavy-load train in each section;

[0137] S33. Obtain the operation schedule of the first train according to the skylight time of the first train and the operation time of the first train in each section.

[0138] Furthermore, the step S4 specifically includes the following steps:

[0139] An equivalent model of the traction network with multiple trains and multiple sections is established, and the utilization of renewable braking energy is triggered under the same power supply arm. When renewable energy is transmitted to multiple trains, the line loss of the traction network is calculated according to the position of the heavy-loaded train and the output power of the motor, so that the renewable energy can be transmitted to the train with smaller network loss.

[0140] S41, establish a ∏-type equivalent circuit of the traction network under each power supply arm, and calculate the corresponding traction network loss when the traction network transmits energy to each train under the same power supply arm. The specific calculation process is as follows:

[0141] like Figure 2 As shown in α and E β is an ideal voltage source, Z Τ is the equivalent impedance of the traction transformer, Z ex is the equivalent impedance of the traction network, Z eps is the equivalent impedance between the power supply arms.

[0142] S42. Calculate the output power of each motor, and the motor comprehensive energy consumption can be equivalent to the parallel connection of the induction motor and the dynamic load. Figure 3 As shown in the figure, it is a schematic diagram of the system energy consumption model, where:

[0143] Induction motor absorbed power model:

[0144]

[0145] Dynamic load model:

[0146]

[0147] Total power:

[0148]

[0149] Among them, E is the equivalent amplitude of the infinite bus, θ is the phase angle, X is the transient reactance, P S0 and Q S0 is the static initial value, V is the voltage at the generator end, and V0 is the rated voltage. v and Q v They are the indices of the motor's active and reactive power, respectively.

[0150] S43. According to the location of the train and the total power output by the motor, the line loss at this time is calculated using the power flow calculation method:

[0151]

[0152] Where ΔS is the power loss, U i is the point voltage at position i.

[0153] S44. When multiple heavy-load trains are under the same power supply arm, the regenerative energy utilization mode is triggered. The train calculates the traction network loss of the traction network according to its location and the power output of the motor, and supplies the regenerative braking energy to the trains with smaller network loss in turn, thereby improving energy utilization.

[0154] Furthermore, if Figure 6 As shown, step S5 includes the following steps:

[0155] S51. Obtain heavy-load train line information, basic train attributes, train status information, traction network data, the number of trains departing on the day, and the window time of each station. Establish an optimization model with train acceleration, departure time interval, and station stop time as independent variables;

[0156] S52, using multi-objective particle swarm algorithm to optimize and solve the problem with the goal of minimizing train running energy consumption and maximizing overlap time and punctual operation;

[0157] S53, initializing the particle swarm parameters and normalizing the independent variables;

[0158] S54, updating the velocity and position of the particle to generate an initial solution;

[0159] S55, denormalize the particles, send the particles into the objective function, and calculate the fitness value. The fitness calculation formula is as follows:

[0160]

[0161] Among them, E is the total energy consumption of each train operation, E i,tr is the traction energy consumption of the i-th train, E i,regis the regenerative braking energy of the i-th train, ω is the utilization rate of regenerative braking energy, E re is the overlapping energy of each train, E i,m,i,,m, is the energy used by train i, between stations m, during the traction phase from the regenerative braking energy fed back during the braking phase of train i, between stations m, T is the total on-time operation index of each train, T i is the running time of the i-th train, T i,0 The set running time of the i-th train.

[0162] S56, storing the obtained solution into the optimal solution set, and maintaining the optimal solution set using the methods of S24 and S25;

[0163] S57, determine whether the number of iterations has been reached, if yes, then the iteration ends and executes S58, otherwise, executes S54;

[0164] S58. Output the running timetable of each train and the running speed curve of each section.

[0165] The train schedule and speed curve optimization method provided in this embodiment realizes the distribution of regenerative energy based on the calculated traction network loss, maximizes the utilization of regenerative energy, and realizes the comprehensive optimization of energy saving of heavy-loaded trains and multiple trains and the rapid solution of traction network power flow. The positive effects are as follows:

[0166] (1) A dynamic programming method for heavy-load train transportation organization is proposed. Only the above basic data need to be obtained to complete the coordinated optimization of the operation schedule and speed curve of heavy-load multiple trains;

[0167] (2) Energy saving: A Π-type equivalent circuit of the traction network was built. The traction network loss of the heavy-load train was obtained by the location of the heavy-load train at a certain moment and the power consumed by the motor. The regenerative braking energy was distributed under the same power supply arm through the train network loss parameters. The utilization of regenerative braking energy was maximized by adjusting the departure interval, stop time and speed curve of each section of the heavy-load train. Energy-saving operation of multiple heavy-load trains was ensured.

[0168] Embodiment 5

[0169] Based on the above embodiments, Figure 7 As shown, this embodiment provides a train schedule and speed curve optimization device, including:

[0170] The information acquisition module 710 is used to acquire the attribute information of the train to be operated on the target date and each operating range of the train;

[0171] The initial speed calculation module 720 is used to calculate the running time of each train in each running section according to the attribute information of the train under the preset time optimization model, with the minimum energy consumption as the goal, and with the interval speed limit and punctual operation of each running section as the constraints, and obtain the initial train schedule and the initial speed curve corresponding to each running section according to the running time;

[0172] The traction network loss calculation module 730 is used to obtain an equivalent model of the traction network, and calculate, according to the equivalent model, when renewable energy is generated between multiple trains running under the same power supply arm, the corresponding traction network loss when the energy is transmitted to each train under the same power supply arm through the traction network;

[0173] The speed curve optimization module 740 is used to adjust the initial speed curve of each train to obtain an optimized speed curve with the goal of minimizing the sum of the traction network losses of each train in the entire line, maximizing the overlap time of the traction and braking phases between each train and running on time;

[0174] The schedule optimization module 750 is used to update the initial train schedule according to the optimized speed curve to obtain an optimized train schedule.

[0175] In one embodiment, the initial speed calculation module includes:

[0176] A shortest running time calculation unit, used to calculate the shortest running time corresponding to each of the running intervals according to the speed limit constraints of each of the running intervals;

[0177] An optimal solution set calculation unit, used to input the attribute information of the train into the time optimization model, and solve the model using a dynamic programming algorithm with the shortest running time of each running section and the maximum running time of the entire line as constraints to obtain an optimal solution set between the running time and energy consumption;

[0178] A running time calculation unit is used to calculate the running time of each train in each running section based on the attribute information of the train, the line conditions of each running section, and the time and energy consumption values ​​corresponding to each solution in the selected optimal solution set, with the punctual running time as a constraint condition, wherein the line conditions of the running section include at least one of the section distance, section slope and track parameters.

[0179] In one embodiment, the optimal solution set calculation unit includes:

[0180] A first initial solution set calculation subunit is used to solve the model using a dynamic programming algorithm to obtain a first initial solution set;

[0181] The non-dominated sorting subunit is used to stratify all solutions in the first initial solution set by using a non-dominated sorting method, and use the non-dominated solution set of the first layer as the optimal solution set.

[0182] In one embodiment, the initial speed calculation module further includes:

[0183] A solution set screening subunit is used to evaluate the merits of all solutions in the optimal solution set, delete the solutions whose merits are less than a preset merit threshold, and obtain a non-dominated solution set;

[0184] The running time calculation unit is also used to use the time and energy consumption values ​​corresponding to each solution in the selected non-dominated solution set as the time and energy consumption values ​​corresponding to each solution in the selected optimal solution set, and calculate the running time of each train in each running section based on the attribute information of the train, the line conditions of each running section and the time and energy consumption values ​​corresponding to each solution in the selected optimal solution set, with the punctual running time as the constraint condition.

[0185] In one embodiment, the speed curve optimization module includes:

[0186] A model initialization unit, used for inputting the line information of the operating section, the attribute information of the train and the information of the traction network into a preset multi-train speed curve collaborative optimization model to obtain a target multi-train speed curve collaborative optimization model;

[0187] a target solution set calculation unit, configured to solve the target multi-train speed curve collaborative optimization model by using a multi-objective particle swarm algorithm with the objectives of minimizing the total energy consumption of the train operation, maximizing the overlap time and running on time, and obtain a target solution set, wherein the independent variables of the multi-train speed curve collaborative optimization model are the acceleration, departure time interval and station stop time of the train;

[0188] A speed updating unit is used to update the initial speed curve of each train according to the target solution set.

[0189] In one embodiment, the target solution set calculation unit includes:

[0190] The second initial solution set calculation subunit is used to solve the target multi-train speed curve collaborative optimization model by using a multi-objective particle swarm algorithm with the objectives of minimizing the total energy consumption of each train operation, maximizing the overlap time and running on time, and obtain a second initial solution set;

[0191] The fitness calculation subunit is used to calculate the fitness of each solution in the second initial solution set, and determine the set of solutions corresponding to the fitness that meets the preset fitness screening rule as the target solution set.

[0192] The specific definition of the train schedule and speed curve optimization device can be found in the above definition of the train schedule and speed curve optimization method, which will not be repeated here. Each unit in the above train schedule and speed curve optimization device can be implemented in whole or in part by software, hardware and a combination thereof. The above units can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above units.

[0193] Embodiment 6

[0194] On the basis of the above embodiments, this embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method described in the above embodiments.

[0195] In some implementations of this embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described in the above embodiment are implemented.

[0196] In some implementations of this embodiment, a computer program product is provided, including a computer program / instructions, and when the computer program is executed by a processor, the steps of the method described in the above embodiment are implemented.

[0197] The processor may include, but is not limited to, one or more processors or microprocessors. Each processor may be an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a controller, a microcontroller, a microprocessor or other electronic components to execute the method in the above embodiments.

[0198] Computer-readable storage media can be implemented by any type of volatile or non-volatile storage device or a combination thereof. Computer-readable storage media may include, but are not limited to, for example, random access memory (RAM), read-only memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, computer storage media (such as hard disks, floppy disks, solid-state drives, removable disks, Blu-ray disks, etc.).

[0199] The computer-readable storage medium may also store at least one computer executable program / instruction, which may be, for example, a computer-readable instruction. The computer-readable storage medium includes, but is not limited to, for example, a volatile memory and / or a non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The computer-readable storage medium may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. For example, a non-transitory computer-readable storage medium may be connected to a computing device such as a computer, and then, when the computing device runs the computer-readable instructions stored on the computer-readable storage medium, the various methods described above may be performed.

[0200] In addition, the computer device may also include (but not limited to) a data bus, an input / output (I / O) bus, a display, and input / output devices (eg, keyboard, mouse, speaker, etc.), etc.

[0201] The processor may communicate with external devices via an I / O bus via a wired or wireless network.

[0202] In one embodiment, the at least one computer executable instruction may also be compiled into or constitute a software product / computer program product, wherein one or more computer executable instructions are executed by a processor to perform the various functions and / or method steps in the embodiments described in the present technology.

[0203] In the embodiments provided in the present disclosure, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the above-mentioned module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0204] It should be noted that in the present disclosure, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element limited by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0205] Although the embodiments disclosed in the present disclosure are as above, the above contents are only embodiments adopted for facilitating the understanding of the present disclosure and are not intended to limit the present disclosure. Any technician in the technical field to which the present disclosure belongs can make any modifications and changes in the form and details of the implementation without departing from the spirit and scope disclosed in the present disclosure, but the scope of patent protection of the present disclosure shall still be subject to the scope defined in the attached claims.

Claims

1. A method for optimizing a train schedule and a speed curve, characterized in that: include: Acquire the attribute information of the train to be operated on the target date and each operating range of the train; Under a preset time optimization model, with minimum energy consumption as the goal, and with the speed limit and punctual operation of each operating interval as constraints, the running time of each train in each operating interval is calculated according to the attribute information of the train, and an initial train schedule and an initial speed curve corresponding to each operating interval are obtained according to the running time; Obtaining an equivalent model of the traction network, and calculating, according to the equivalent model, when renewable energy is generated between multiple trains running under the same power supply arm, corresponding traction network losses when energy is transmitted to each train under the same power supply arm through the traction network; With the goal of minimizing the sum of the traction network losses of each train on the entire line, maximizing the overlap time of the traction and braking phases between each train and on-time operation, the initial speed curve of each train is adjusted to obtain an optimized speed curve; The initial train schedule is updated according to the optimized speed curve to obtain an optimized train schedule.

2. The method according to claim 1, characterized in that The step of calculating the running time of each train in each running section according to the attribute information of the train under the preset time optimization model with the minimum energy consumption as the goal and the speed limit and punctual running of each running section as the constraints includes: Calculating the shortest running time corresponding to each of the running intervals according to the speed limit constraints of each of the running intervals; Inputting the attribute information of the train into the time optimization model, solving the model using a dynamic programming algorithm with the shortest running time of each running section and the maximum running time of the entire line as constraints, and obtaining an optimal solution set between running time and energy consumption; According to the attribute information of the train, the line conditions of each operating interval and the time and energy consumption values ​​corresponding to each solution in the selected optimal solution set, the operating time of each train in each operating interval is calculated with the punctual operating time as a constraint condition, wherein the line conditions of the operating interval include at least one of interval distance, interval slope and track parameters.

3. The method according to claim 2, characterized in that The step of solving the model using a dynamic programming algorithm to obtain an optimal solution set between the running time and energy consumption includes: The model is solved by using a dynamic programming algorithm to obtain a first initial solution set; All solutions in the first initial solution set are layered using a non-dominated sorting method, and the non-dominated solution set of the first layer is used as the optimal solution set.

4. The method according to claim 2, characterized in that: After the step of using a dynamic programming algorithm to solve the model to obtain an optimal solution set between the running time and energy consumption, the method further includes: Evaluate the merits of all solutions in the optimal solution set, delete solutions whose merits are less than a preset merit threshold, and obtain a non-dominated solution set; The step of calculating the running time of each train in each running section based on the attribute information of the train, the line conditions of each running section, and the time and energy consumption values ​​corresponding to each solution in the selected optimal solution set, with the on-time running time as a constraint condition, comprises: The time and energy consumption values ​​corresponding to each solution in the selected non-dominated solution set are used as the time and energy consumption values ​​corresponding to each solution in the selected optimal solution set. According to the attribute information of the train, the line conditions of each operating interval and the time and energy consumption values ​​corresponding to each solution in the selected optimal solution set, the running time of each train in each operating interval is calculated with the punctual running time as the constraint condition.

5. The method according to claim 1, characterized in that The step of adjusting the initial speed curve of each train with the goal of minimizing the sum of the traction network losses of each train on the entire line, maximizing the overlap time of the traction and braking phases between each train, and punctual operation comprises: Inputting the line information of the operating section, the attribute information of the train and the information of the traction network into a preset multi-train speed curve collaborative optimization model to obtain a target multi-train speed curve collaborative optimization model; Using a multi-objective particle swarm algorithm, the target multi-train speed curve collaborative optimization model is solved with the objectives of minimizing the total energy consumption of the train operation, maximizing the overlap time and on-time operation, and a target solution set is obtained, wherein the independent variables of the multi-train speed curve collaborative optimization model are the acceleration, departure time interval and station stop time of the train; The initial speed curve of each train is updated according to the target solution set.

6. The method according to claim 5, characterized in that The step of solving the target multi-train speed curve collaborative optimization model by using a multi-objective particle swarm algorithm with the goal of minimizing the total energy consumption of the train operation and maximizing the overlap time and punctual operation to obtain the target solution set includes: Using a multi-objective particle swarm algorithm, the target multi-train speed curve collaborative optimization model is solved with the objectives of minimizing the total energy consumption of each train operation, maximizing the overlap time and running on time, and obtaining a second initial solution set; The fitness of each solution in the second initial solution set is calculated, and a set of solutions corresponding to the fitness that meets a preset fitness screening rule is determined as the target solution set.

7. The method according to claim 6, characterized in that In the step of calculating the fitness of each solution in the second initial solution set, the fitness is calculated as follows: Among them, E is the total energy consumption of each train operation, E i,tr is the traction energy consumption of the i-th train, E i,reg is the regenerative braking energy of the i-th train, ω is the utilization rate of regenerative braking energy, E re is the overlapping energy of each train, E i,m,i,,m, is the energy used by train i, between stations m, during the traction phase from the regenerative braking energy fed back during the braking phase of train i, between stations m, T is the total on-time operation index of each train, T i is the running time of the i-th train, T i,0 The set running time of the i-th train.

8. A computer device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the method according to any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images