Rail transit dynamic scheduling and energy consumption optimization method, device, equipment and system

Abstract

The application provides a kind of dynamic scheduling and energy consumption optimization method, device, equipment and system of rail transit, belong to intelligent transportation field.Method includes: obtaining train operation data and passenger flow variation trend data from the edge node;According to the passenger flow variation trend data and the train operation data generation train scheduling instruction, and send the train scheduling instruction to the edge node, the train scheduling instruction is used to adjust train running interval;And / or, according to the train operation data determines energy recovery strategy, and sends the energy recovery strategy to the edge node, the energy recovery strategy is used to optimize train energy consumption.Can reduce the load of server, improve the reliability, stability and response timeliness of system, simultaneously based on real-time data scheduling adjustment and energy recovery, improve train operation efficiency, increase energy recovery rate.

Description

Technical Field

[0001] This application belongs to the field of intelligent transportation, specifically relating to a method, apparatus, equipment, and system for dynamic scheduling and energy consumption optimization of rail transit. Background Technology

[0002] As a crucial component of urban public transportation, rail transit's operation scheduling and energy consumption management are key factors affecting the overall system efficiency and user experience. Existing dynamic dispatching systems for rail transit typically employ a centralized control approach, where all data processing and decision-making take place within a central control system. The advantage of this approach is centralized management and ease of unified scheduling. However, the heavy load on the central control system can lead to problems such as large communication delays, concentrated computational load, and slow response times. Furthermore, existing technologies primarily rely on fixed rules or empirical models for scheduling and energy consumption optimization, lacking dynamic optimization based on real-time data. The disadvantage of this approach is its inability to respond promptly to sudden changes in passenger flow and complex operating environments, potentially resulting in resource waste or a decline in passenger experience. Summary of the Invention

[0003] This application provides a method, apparatus, equipment, and system for dynamic scheduling and energy consumption optimization of rail transit, which reduces server load, improves system reliability, stability, and responsiveness, and improves train operation efficiency and energy recovery rate by performing scheduling adjustments and energy recovery based on real-time data.

[0004] This application provides a dynamic scheduling and energy consumption optimization method for rail transit, used in a cloud server of an intelligent transportation system. The intelligent transportation system includes the cloud server and edge nodes, and the cloud server and edge nodes are communicatively connected. The method includes: Acquire train operation data and passenger flow trend data from the edge nodes; Based on the passenger flow trend data and the train operation data, a train dispatching instruction is generated and sent to the edge node. The train dispatching instruction is used to adjust train intervals; and / or, An energy recovery strategy is determined based on the train operation data and sent to the edge node. The energy recovery strategy is used to optimize train energy consumption.

[0005] According to the dynamic scheduling and energy consumption optimization method for rail transit provided in this application, the step of generating train scheduling instructions based on the passenger flow change trend data and the train operation data includes: obtaining the train speed and train position of each train corresponding to the edge node based on the train operation data; and generating train scheduling instructions based on the passenger flow change trend data and the train speed and train position of each train through a scheduling optimization algorithm.

[0006] According to the dynamic scheduling and energy consumption optimization method for rail transit provided in this application, the step of determining the energy recovery strategy based on the train operation data includes: obtaining train energy consumption data, train position, and train speed based on the train operation data; inputting the train energy consumption data, the train position, and the train speed into a deep learning model to obtain the energy recovery strategy output by the deep learning model.

[0007] According to the dynamic scheduling and energy consumption optimization method for rail transit provided in this application, the step of generating train scheduling instructions based on the passenger flow trend and the train operation data, and / or determining an energy recovery strategy based on the train operation data, includes: determining whether the passenger flow trend data has been obtained; if the passenger flow trend data has not been obtained, determining an energy recovery strategy based on the train operation data; if the passenger flow trend data has been obtained, determining whether an energy recovery strategy adjustment request has been obtained; if the energy recovery strategy adjustment request has been obtained, generating train scheduling instructions based on the passenger flow trend and the train operation data, and determining an energy recovery strategy based on the train operation data; if the energy recovery strategy adjustment request has not been obtained, generating train scheduling instructions based on the passenger flow trend and the train operation data.

[0008] According to the dynamic scheduling and energy consumption optimization method for rail transit provided in this application, the edge node and the cloud server are connected through a distributed communication framework.

[0009] This application provides a dynamic scheduling and energy consumption optimization method for rail transit, applied to the edge nodes of an intelligent transportation system. The intelligent transportation system includes a cloud server and the edge nodes, which are communicatively connected. The method includes: Passenger flow is obtained from the first Internet of Things (IoT) devices deployed at train stations; The number of passengers is input into the prediction model included in the edge node to obtain the passenger flow change trend data output by the prediction model, and it is determined whether the train running interval needs to be adjusted based on the passenger flow change trend data. Train operation data is obtained from a second IoT device deployed on the train, and the need to adjust the energy recovery strategy is determined based on the train operation data. When it is necessary to adjust the train interval, the passenger flow trend data and the train operation data are sent to the cloud server. If it is necessary to adjust the energy recovery strategy, the train operation data is sent to the cloud server.

[0010] This application provides a dynamic scheduling and energy consumption optimization device for rail transit, applied to a cloud server of an intelligent transportation system. The intelligent transportation system includes the cloud server and edge nodes, and the cloud server and edge nodes are communicatively connected. The device includes: The first acquisition unit is used to acquire train operation data and passenger flow trend data from the edge nodes; The generation unit is configured to generate train dispatching instructions based on the passenger flow trend data and the train operation data, and send the train dispatching instructions to the edge node, wherein the train dispatching instructions are used to adjust train intervals; and / or, The determining unit is used to determine an energy recovery strategy based on the train operation data and send the energy recovery strategy to the edge node. The energy recovery strategy is used to optimize train energy consumption.

[0011] This application also provides a dynamic scheduling and energy consumption optimization device for rail transit, applied to the edge node of an intelligent transportation system. The intelligent transportation system includes a cloud server and the edge node, which are communicatively connected. The device includes: The second acquisition unit is used to acquire passenger flow based on the first Internet of Things device deployed at the train station. The third acquisition unit is used to input the number of passengers into the prediction model included in the edge node, obtain the passenger flow change trend data output by the prediction model, and determine whether the train running interval needs to be adjusted based on the passenger flow change trend data. The fourth acquisition unit is used to acquire train operation data based on the second Internet of Things device deployed on the train, and determine whether the energy recovery strategy needs to be adjusted based on the train operation data. The first sending unit is used to send the passenger flow change trend data and the train operation status data to the cloud server when it is necessary to adjust the train operation interval; The second sending unit is used to send the train operation data to the cloud server when the energy recovery strategy needs to be adjusted.

[0012] This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the above-described methods for dynamic scheduling and energy consumption optimization of rail transit.

[0013] This application also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements any of the above-described methods for dynamic scheduling and energy consumption optimization of rail transit.

[0014] This application also provides a computer program product, including a computer program that, when executed by a processor, implements any of the above-described methods for dynamic scheduling and energy consumption optimization of rail transit.

[0015] This application also provides an intelligent transportation system, which includes a cloud server and edge nodes, and the cloud server and the edge nodes are communicatively connected. The cloud server is used to execute the steps performed by the cloud server in any of the above-described methods for dynamic scheduling and energy consumption optimization of rail transit. The edge node is used to execute the steps performed by the edge node in the above-described dynamic scheduling and energy consumption optimization method for rail transit.

[0016] The dynamic scheduling and energy consumption optimization method, apparatus, equipment, and system for rail transit provided in this application involve a cloud server first acquiring train operation data and passenger flow trend data from edge nodes. Then, based on the passenger flow trend data and the train operation data, a train scheduling instruction is generated and sent to the edge nodes. This train scheduling instruction is used to adjust train intervals. And / or, an energy recovery strategy is determined based on the train operation data and sent to the edge nodes. This energy recovery strategy is used to optimize train energy consumption. This allows for preliminary calculations based on real-time data from edge nodes. The cloud server only needs to generate train scheduling instructions or energy recovery strategies based on the calculation results uploaded by the edge nodes, reducing server load and improving system reliability, stability, and responsiveness. Simultaneously, scheduling adjustments and energy recovery based on real-time data improve train operation efficiency and increase the energy recovery rate. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 This is a block diagram of the intelligent transportation system provided in this application.

[0019] Figure 2 This is one of the flowcharts illustrating the dynamic scheduling and energy consumption optimization method for rail transit provided in this application.

[0020] Figure 3 This is the second flowchart of the dynamic scheduling and energy consumption optimization method for rail transit provided in this application.

[0021] Figure 4 This is the third flowchart of the dynamic scheduling and energy consumption optimization method for rail transit provided in this application.

[0022] Figure 5 This is one of the functional unit block diagrams of the dynamic scheduling and energy consumption optimization device for rail transit provided in this application.

[0023] Figure 6 This is the second functional unit block diagram of the dynamic scheduling and energy consumption optimization device for rail transit provided in this application.

[0024] Figure 7 This is a schematic diagram of the structure of the electronic device provided in this application. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0026] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0027] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0028] Existing dynamic dispatching systems for rail transit typically employ centralized control methods and rely primarily on fixed rules or empirical models for dispatching and energy consumption optimization. This results in excessive system load and an inability to respond promptly to sudden changes in passenger flow and complex operating environments.

[0029] To address the aforementioned problems, this application provides a method, apparatus, equipment, and system for dynamic scheduling and energy consumption optimization of rail transit. The following is a detailed description of this application in conjunction with the accompanying drawings.

[0030] Please see Figure 1 The intelligent transportation system 10 provided in this application includes a cloud server 101 and edge nodes 102, which are communicatively connected. Specifically, the cloud server 101 and edge nodes 102 can communicate through a distributed communication framework. The cloud server 101 includes a deep learning model for generating scheduling instructions and adjusting energy recovery strategies. The edge nodes 102 are deployed at trains and stations of the rail transit system, each equipped with IoT devices for real-time data collection. Simultaneously, the edge nodes may include AI models that can perform preliminary analysis on the real-time collected data and upload the data to the cloud server 101 based on the preliminary analysis results.

[0031] Please see Figure 2 The dynamic scheduling and energy consumption optimization method for rail transit provided in this application is applied to the aforementioned remote server 101 and specifically includes the following steps.

[0032] S201, Obtain train operation data and passenger flow trend data from the edge node.

[0033] The edge nodes can acquire passenger flow data based on a first IoT device deployed at train stations. The AI ​​models within these edge nodes can then analyze passenger flow trends to obtain passenger flow trend data. Simultaneously, the edge nodes can also acquire train operation data based on a second IoT device deployed on the train, determining train location, speed, and energy consumption. Finally, the edge nodes transmit the analyzed passenger flow trend data and train operation data to a cloud server via a distributed communication framework.

[0034] S202, generate train dispatch instructions based on the passenger flow trend data and the train operation data, and send the train dispatch instructions to the edge node.

[0035] Train dispatching instructions are used to adjust train intervals. In practice, if an edge node sends passenger flow trend data to the cloud server, the cloud server determines that a train dispatching instruction needs to be generated. When sending train dispatching instructions to edge nodes, communication can be achieved through a distributed communication framework. After receiving the train dispatching instruction, the edge node forwards it to the train station, which then adjusts the train intervals based on the instruction. Alternatively, the edge node can directly control the train intervals based on the received train dispatching instructions.

[0036] S203, determine the energy recovery strategy based on the train operation data, and send the energy recovery strategy to the edge node.

[0037] The energy recovery strategy is used to optimize train energy consumption. The system can determine different energy recovery strategies based on the real-time operation of the train. For example, when the train accelerates, it needs more electricity, while when the train decelerates or stops, a first energy recovery strategy can convert some energy into electricity and feed it back to the power grid. When going uphill, the train needs additional energy to overcome gravity, and the cloud server generates a second energy recovery strategy based on the train's operating conditions to adjust the power supply in advance.

[0038] Specifically, when edge nodes acquire train operation data, they can analyze whether the train needs to adjust its energy recovery strategy based on the data. If so, they can send a corresponding adjustment request. Only after the cloud server receives the adjustment request can the energy recovery strategy be adjusted.

[0039] As can be seen, in this embodiment, the cloud server first acquires train operation data and passenger flow trend data from the edge nodes, then generates train dispatching instructions based on the passenger flow trend data and the train operation data, and sends the train dispatching instructions to the edge nodes. The train dispatching instructions are used to adjust train intervals; and / or, determines an energy recovery strategy based on the train operation data, and sends the energy recovery strategy to the edge nodes. The energy recovery strategy is used to optimize train energy consumption. This allows the cloud server to perform preliminary calculations based on real-time data from the edge nodes, and only needs to generate train dispatching instructions or energy recovery strategies based on the calculation results uploaded by the edge nodes. This reduces the server load. Compared to the overloaded central control system in existing technologies, which is prone to bottlenecks and affects system reliability and stability, this technical solution achieves decentralized management and optimization of the system through the combination of distributed computing and edge computing, improving system reliability and stability. Simultaneously, scheduling adjustments and energy recovery based on real-time data improve train operation efficiency and increase the energy recovery rate.

[0040] In one possible embodiment, generating train dispatch instructions based on the passenger flow trend data and the train operation data includes: obtaining the train speed and position of each train corresponding to the edge node based on the train operation data; and generating train dispatch instructions based on the passenger flow trend data and the train speed and position of each train using a dispatch optimization algorithm.

[0041] The edge nodes can simultaneously acquire the current train position and speed from multiple trains. This scheduling optimization algorithm can be implemented based on genetic algorithms and ant colony algorithms. Simultaneously, the cloud server can access a cloud database storing historical scheduling information. This scheduling optimization algorithm can determine the departure time, stops, and speed of each train based on train operation status data, passenger flow trends, and historical scheduling information, generating scheduling instructions. For example, it can adjust train departure times based on predicted passenger flow and train positions. It can dynamically adjust train speeds considering train spacing, train operation efficiency, and safety requirements. It can adjust train dwell times at various stations based on passenger flow distribution to improve overall passenger throughput. It can dynamically adjust train spacing to avoid delays caused by overly dense trains or inefficiencies caused by excessively long intervals.

[0042] As can be seen, in this embodiment, the technical solution reduces passenger waiting time and improves line capacity by dynamically adjusting train intervals. Generating train dispatch instructions based on real-time data also improves passenger comfort while ensuring transportation efficiency. Compared to existing technologies that rely on fixed rules or empirical models for dispatching and energy consumption optimization, this technical solution can respond to sudden changes in passenger flow and complex operating environments in real time, improving the system's response speed and flexibility.

[0043] In one possible embodiment, determining the energy recovery strategy based on the train operation data includes: acquiring train energy consumption data, train position, and train speed based on the train operation data; inputting the train energy consumption data, train position, and train speed into a deep learning model to obtain the energy recovery strategy output by the deep learning model.

[0044] In a rail transit system with multiple trains in operation, when a train accelerates, a cloud server can monitor its power demand based on acquired train energy consumption data, ensuring it receives sufficient energy from the grid. Simultaneously, if the train's speed indicates it is entering the braking phase, the cloud server adjusts the energy recovery strategy, causing the train to enter regenerative braking mode, converting kinetic energy into electrical energy and returning excess energy to the grid. If the acquired train position and speed indicate the train is descending a slope and decelerating, the cloud server's deep learning model can determine that the train can utilize downhill potential energy and reduce energy consumption. Therefore, it adjusts the energy recovery strategy to enhance energy recovery, ensuring the energy balance of the entire system and maximizing energy utilization efficiency.

[0045] As can be seen, in this embodiment, energy recovery efficiency is improved through real-time analysis and dynamic optimization. Compared with existing technologies that lack dynamic optimization based on real-time data, resulting in low energy recovery efficiency, this technical solution can fully utilize dynamic energy recovery technology to improve train operating efficiency, reduce energy waste, and lower operating costs.

[0046] In one possible embodiment, the step of generating train dispatching instructions based on the passenger flow trend and the train operation data, and / or determining an energy recovery strategy based on the train operation data, includes: determining whether the passenger flow trend data has been obtained; if the passenger flow trend data has not been obtained, determining an energy recovery strategy based on the train operation data; if the passenger flow trend data has been obtained, determining whether an energy recovery strategy adjustment request has been obtained; if the energy recovery strategy adjustment request has been obtained, generating train dispatching instructions based on the passenger flow trend and the train operation data, and determining an energy recovery strategy based on the train operation data; if the energy recovery strategy adjustment request has not been obtained, generating train dispatching instructions based on the passenger flow trend and the train operation data.

[0047] The edge nodes can predict passenger flow trends based on passenger numbers, and then analyze this data to determine if the cloud server needs to adjust train scheduling. If adjustments are needed, the edge server simultaneously sends both passenger flow trend data and train operation data to the cloud server. Upon receiving this data, the cloud server determines that scheduling instructions need to be adjusted and then generates the necessary instructions.

[0048] When the cloud server simultaneously acquires passenger flow trend data and train operation data, it also needs to determine whether it has received an energy recovery strategy adjustment request from the edge node. That is, the edge node can first determine whether an energy recovery strategy adjustment is needed based on the acquired train energy consumption, train location, and train speed. If so, it will send an energy recovery strategy adjustment request simultaneously when sending train operation data and passenger flow trend data to the cloud server.

[0049] As can be seen, in this embodiment, if the cloud server only obtains train operation data from the edge nodes, it determines the energy recovery strategy based on the train operation data. If the cloud server only obtains passenger flow trend data from the edge nodes, it generates train dispatching instructions based on the passenger flow trend. If the cloud server simultaneously obtains train operation data, passenger flow trend data, and energy recovery strategy adjustment requests from the edge nodes, it generates train dispatching instructions and determines the energy recovery requirements. That is, the cloud server can flexibly determine the computation content based on the obtained data types, improving the flexibility and adaptability of cloud server computation to requirements, and reducing the computational burden on the cloud server. At the same time, it does not need to send a separate request to the server to inform it of the computational requirements each time, reducing resource consumption.

[0050] In one possible embodiment, the edge node communicates with the cloud server via a distributed communication framework.

[0051] The distributed communication framework can be Kafka or Redis. Kafka is responsible for high-throughput data transmission, while Redis is responsible for fast data access and storage.

[0052] As can be seen, in this embodiment, the technical solution reduces data processing and decision-making latency and improves system response speed through a distributed architecture.

[0053] Please see Figure 3 This application also provides a dynamic scheduling and energy consumption optimization method for rail transit, applied to the aforementioned edge node 102, which includes the following steps.

[0054] S301 obtains passenger flow data based on the first IoT device deployed at the train station.

[0055] The passenger flow includes the current real-time passenger flow and the historical passenger flow obtained based on the first IoT device.

[0056] S302, input the number of passengers into the prediction model included in the edge node, obtain the passenger flow change trend data output by the prediction model, and determine whether it is necessary to adjust the train running interval based on the passenger flow change trend data.

[0057] This can be achieved by using AI models within edge nodes to analyze passenger flow trends based on passenger numbers. If the current passenger flow trend is significant, it's considered necessary to adjust train intervals; if the trend is minor, it's considered unnecessary. Alternatively, the AI ​​model can obtain the current train intervals and determine whether they align with the passenger flow trend. If they do, it's considered unnecessary to adjust train intervals; otherwise, adjustments are required.

[0058] Specifically, the AI ​​model included in the edge nodes can be a lightweight AI model. This AI model can be trained using the TensorFlow deep learning framework, based on historical passenger flow data, train operation data, and energy consumption data, employing supervised learning methods. The AI ​​model structure includes an input layer, a hidden layer, and an output layer. The input layer receives the collected data, the hidden layer performs data processing and feature extraction, and the output layer outputs the prediction result. This AI model can be trained in the cloud and inference performed on the edge nodes.

[0059] S303: Obtain train operation data from a second IoT device deployed on the train, and determine whether the energy recovery strategy needs to be adjusted based on the train operation data.

[0060] The train operation data includes train location, speed, and energy consumption. When determining whether to adjust the energy recovery strategy, it's first determined whether the current energy recovery efficiency is higher than a preset value. If it is, no adjustment is needed; if it's lower, adjustment is determined based on the train location and speed. Specifically, the AI ​​model can acquire historical train locations and speeds, and then determine the energy recovery strategy based on these historical data and the currently acquired train location and speed.

[0061] S304, when it is necessary to adjust the train interval, send the passenger flow trend data and the train operation data to the cloud server; S305, if it is necessary to adjust the energy recovery strategy, send the train operation data to the cloud server.

[0062] If both train intervals and energy recovery strategies need to be adjusted simultaneously, an energy recovery strategy adjustment request must be sent concurrently with passenger flow trend data and train operation data to the cloud server. Edge nodes can transmit data to the cloud server via a distributed communication framework.

[0063] As can be seen, in this embodiment, the edge server obtains passenger flow data based on the first IoT device deployed at the train station, then inputs the passenger flow data into the prediction model included in the edge node to obtain passenger flow trend data output by the prediction model. Based on the passenger flow trend data, it determines whether the train interval needs to be adjusted. Next, it obtains train operation data based on the second IoT device deployed on the train, and determines whether the energy recovery strategy needs to be adjusted based on the train operation data. Then, if the train interval needs to be adjusted, it sends the passenger flow trend data and the train operation data to the cloud server. Finally, if the energy recovery strategy needs to be adjusted, it sends the train operation data to the cloud server. This solution deploys edge nodes at the train and station, utilizes IoT devices to collect passenger flow data, train status data, and energy consumption data in real time, and runs a lightweight AI model on the edge nodes for preliminary analysis and prediction. Compared to existing technologies where all data is transmitted to the central control system for processing, this solution reduces data transmission latency and bandwidth requirements, improving the system's real-time performance and efficiency.

[0064] This application also provides an intelligent transportation system, which includes a cloud server and edge nodes, and the cloud server and the edge nodes are communicatively connected; the cloud server is used to execute the steps performed by the cloud server in the dynamic scheduling and energy consumption optimization method for rail transit as described in any of the above embodiments; the edge nodes are used to execute the steps performed by the edge nodes in the dynamic scheduling and energy consumption optimization method for rail transit as described in the above embodiments.

[0065] Please see Figure 4 ,based on Figure 4 The overall process of the intelligent transportation system is explained.

[0066] First, data is collected through edge nodes, including passenger flow and train movement data. This collected data is then input into the input layer of an AI model, followed by data processing and feature extraction in the hidden layer, and finally output as a predictive analysis result. This prediction includes passenger flow trends and train operation data. The predictive analysis is then uploaded to the cloud via a distributed communication framework such as Kafka or Redis. The cloud performs optimization calculations to generate scheduling instructions and energy recovery strategies, achieving scheduling and energy consumption optimization. The cloud then sends the generated scheduling instructions to the edge nodes, which in turn send the instructions to the stations for execution. Next, the edge nodes acquire real-time data and assess whether they need to request computation from the cloud. If so, they send the acquired real-time data to the cloud, repeating the cloud execution process; otherwise, the edge nodes continue acquiring real-time data.

[0067] As can be seen, this embodiment reduces data processing and decision-making latency and improves system response speed through a distributed architecture. Compared with existing technologies that rely on fixed rules or empirical models for scheduling and energy consumption optimization, this solution can respond to sudden changes in passenger flow and complex operating environments in real time, improving the system's response speed and flexibility.

[0068] Meanwhile, energy recovery efficiency is improved through real-time analysis and dynamic optimization. Compared to existing technologies that lack dynamic optimization based on real-time data, resulting in low energy recovery efficiency, this technical solution can fully utilize dynamic energy recovery technology to improve train operation efficiency, reduce energy waste, and lower operating costs.

[0069] Furthermore, by dynamically adjusting train intervals, passenger waiting times are reduced, and line capacity is improved. Compared to existing technologies where the central control system is overloaded and prone to bottlenecks, affecting system reliability and stability, this technical solution combines distributed computing and edge computing to achieve decentralized management and optimization of the system, thereby improving system reliability and stability.

[0070] This approach involves deploying edge nodes on trains and at stations to collect real-time passenger flow, train status, and energy consumption data using IoT devices. Lightweight AI models are then run on these edge nodes for preliminary analysis and prediction. Compared to existing technologies where all data is transmitted to a central control system for processing, this solution reduces data transmission latency and bandwidth requirements, improving system real-time performance and efficiency.

[0071] Furthermore, by employing a distributed communication framework, edge node data is transmitted to the cloud for global optimization calculations, including train interval adjustments and dynamic energy consumption allocation. Compared to existing technologies that rely solely on local optimization or fixed rules for scheduling and energy consumption optimization, this technical solution achieves the goal of global optimization, improving the overall efficiency and performance of the system.

[0072] The following describes a method and apparatus for dynamic scheduling and energy consumption optimization of rail transit provided in this application. The method and apparatus for dynamic scheduling and energy consumption optimization of rail transit described below correspond to the method for dynamic scheduling and energy consumption optimization of rail transit described above.

[0073] Please see Figure 5 The dynamic scheduling and energy consumption optimization device 500 for rail transit is applied to the cloud server of an intelligent transportation system. The intelligent transportation system includes the cloud server and edge nodes, which are communicatively connected. The dynamic scheduling and energy consumption optimization device 500 for rail transit includes: a first acquisition unit 510, used to acquire train operation data and passenger flow trend data from the edge nodes; a generation unit 511, used to generate train scheduling instructions based on the passenger flow trend data and the train operation data, and send the train scheduling instructions to the edge nodes, the train scheduling instructions being used to adjust train intervals; and / or, a determination unit 512, used to determine an energy recovery strategy based on the train operation data, and send the energy recovery strategy to the edge nodes, the energy recovery strategy being used to optimize train energy consumption.

[0074] In one possible embodiment, in generating train dispatch instructions based on the passenger flow trend data and the train operation data, the generation unit 511 is specifically used to: obtain the train speed and train position of each train corresponding to the edge node based on the train operation data; and generate train dispatch instructions based on the passenger flow trend data and the train speed and train position of each train using a dispatch optimization algorithm.

[0075] In one possible embodiment, in determining the energy recovery strategy based on the train operation data, the determining unit 512 is specifically configured to: acquire train energy consumption data, train position, and train speed based on the train operation data; input the train energy consumption data, train position, and train speed into a deep learning model to obtain the energy recovery strategy output by the deep learning model.

[0076] In one possible embodiment, regarding the generation of train dispatching instructions based on the passenger flow trend and the train operation data, and / or the determination of an energy recovery strategy based on the train operation data, the dynamic dispatching and energy consumption optimization device 500 for rail transit is further configured to: determine whether the passenger flow trend data has been obtained; if the passenger flow trend data has not been obtained, determine an energy recovery strategy based on the train operation data; if the passenger flow trend data has been obtained, determine whether an energy recovery strategy adjustment request has been obtained; if the energy recovery strategy adjustment request has been obtained, generate train dispatching instructions based on the passenger flow trend and the train operation data, and determine an energy recovery strategy based on the train operation data; if the energy recovery strategy adjustment request has not been obtained, generate train dispatching instructions based on the passenger flow trend and the train operation data.

[0077] In one possible embodiment, the edge node communicates with the cloud server via a distributed communication framework.

[0078] Please see Figure 6 The dynamic scheduling and energy consumption optimization device 500 for rail transit is also applied to the edge nodes of an intelligent transportation system. The intelligent transportation system includes a cloud server and the edge nodes, which are communicatively connected. The dynamic scheduling and energy consumption optimization device 500 for rail transit includes: a second acquisition unit 520, used to acquire passenger flow data based on a first Internet of Things (IoT) device deployed at the train station; a third acquisition unit 521, used to input the passenger flow data into a prediction model included in the edge node, obtain passenger flow trend data output by the prediction model, and determine whether to adjust the train interval based on the passenger flow trend data; a fourth acquisition unit 522, used to acquire train operation data based on a second IoT device deployed on the train, and determine whether to adjust the energy recovery strategy based on the train operation data; a first sending unit 523, used to send the passenger flow trend data and the train operation data to the cloud server when the train interval needs to be adjusted; and a second sending unit 524, used to send the train operation data to the cloud server when the energy recovery strategy needs to be adjusted.

[0079] This application also provides an intelligent transportation system, which includes a cloud server and edge nodes, and the cloud server and the edge nodes are communicatively connected. The cloud server is used to execute the steps performed by the cloud server in the dynamic scheduling and energy consumption optimization method for rail transit as described in any of the above embodiments; The edge node is used to perform the steps executed by the edge node in the dynamic scheduling and energy consumption optimization method for rail transit as described in any of the above embodiments.

[0080] Please see Figure 7 , Figure 7 This is a schematic diagram of the structure of the electronic device provided in this application. For example... Figure 7 As shown, the electronic device may include: a processor 710, a communications interface 720, a memory 730, and a communication bus 740, wherein the processor 710, the communications interface 720, and the memory 730 communicate with each other through the communication bus 740. The processor 710 can call logical instructions in the memory 730 to execute a dynamic scheduling and energy consumption optimization method for rail transit. This dynamic scheduling and energy consumption optimization method for rail transit is applied to a cloud server of an intelligent transportation system. The intelligent transportation system includes the cloud server and edge nodes, which are communicatively connected. The method includes: acquiring train operation data and passenger flow trend data from the edge nodes; generating train scheduling instructions based on the passenger flow trend data and the train operation data, and sending the train scheduling instructions to the edge nodes, wherein the train scheduling instructions are used to adjust train intervals; and / or determining an energy recovery strategy based on the train operation data, and sending the energy recovery strategy to the edge nodes, wherein the energy recovery strategy is used to optimize train energy consumption.

[0081] Alternatively, the processor 710 can call logic instructions in the memory 730 to execute a dynamic scheduling and energy consumption optimization method for rail transit. This method is applied to the edge nodes of an intelligent transportation system, which includes a cloud server and the edge nodes. The cloud server and the edge nodes are communicatively connected. The method includes: acquiring passenger flow data based on a first Internet of Things (IoT) device deployed at a train station; inputting the passenger flow data into a prediction model included in the edge node to obtain passenger flow trend data output by the prediction model, and determining whether to adjust train intervals based on the passenger flow trend data; acquiring train operation data based on a second IoT device deployed on the train, and determining whether to adjust an energy recovery strategy based on the train operation data; if the train interval needs to be adjusted, sending the passenger flow trend data and the train operation data to the cloud server; and if the energy recovery strategy needs to be adjusted, sending the train operation data to the cloud server.

[0082] Furthermore, the logical instructions in the aforementioned memory 730 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0083] On the other hand, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements the dynamic scheduling and energy consumption optimization method for rail transit provided by the above methods. This dynamic scheduling and energy consumption optimization method for rail transit is applied to a cloud server of an intelligent transportation system. The intelligent transportation system includes the cloud server and edge nodes, which are communicatively connected. The method includes: acquiring train operation data and passenger flow trend data from the edge nodes; generating train scheduling instructions based on the passenger flow trend data and the train operation data, and sending the train scheduling instructions to the edge nodes, wherein the train scheduling instructions are used to adjust train intervals; and / or determining an energy recovery strategy based on the train operation data, and sending the energy recovery strategy to the edge nodes, wherein the energy recovery strategy is used to optimize train energy consumption.

[0084] Alternatively, when a computer program is executed by a processor, it implements the dynamic scheduling and energy consumption optimization methods for rail transit provided by the above methods. These methods are applied to edge nodes of an intelligent transportation system, which includes a cloud server and the edge nodes, and the cloud server and edge nodes are communicatively connected. The method includes: acquiring passenger flow data based on a first Internet of Things (IoT) device deployed at train stations; inputting the passenger flow data into a prediction model included in the edge node to obtain passenger flow trend data output by the prediction model, and determining whether to adjust train intervals based on the passenger flow trend data; acquiring train operation data based on a second IoT device deployed on the train, and determining whether to adjust the energy recovery strategy based on the train operation data; if the train interval needs adjustment, sending the passenger flow trend data and the train operation data to the cloud server; and if the energy recovery strategy needs adjustment, sending the train operation data to the cloud server.

[0085] In another aspect, this application also provides a computer program product, including a computer program that, when executed by a processor, implements any of the above-described methods for dynamic scheduling and energy consumption optimization of rail transit. This method is applied to a cloud server of an intelligent transportation system, which includes the cloud server and edge nodes, and the cloud server and edge nodes are communicatively connected. The method includes: acquiring train operation data and passenger flow trend data from the edge nodes; generating train scheduling instructions based on the passenger flow trend data and the train operation data, and sending the train scheduling instructions to the edge nodes, wherein the train scheduling instructions are used to adjust train intervals; and / or determining an energy recovery strategy based on the train operation data, and sending the energy recovery strategy to the edge nodes, wherein the energy recovery strategy is used to optimize train energy consumption.

[0086] Alternatively, when a computer program is executed by a processor, it implements any of the above-described methods for dynamic scheduling and energy consumption optimization of rail transit. This method is applied to the edge nodes of an intelligent transportation system, which includes a cloud server and the edge nodes, and the cloud server and the edge nodes are communicatively connected. The method includes: acquiring passenger flow data based on a first Internet of Things (IoT) device deployed at a train station; inputting the passenger flow data into a prediction model included in the edge node to obtain passenger flow trend data output by the prediction model, and determining whether to adjust train intervals based on the passenger flow trend data; acquiring train operation data based on a second IoT device deployed on the train, and determining whether to adjust an energy recovery strategy based on the train operation data; if the train interval needs to be adjusted, sending the passenger flow trend data and the train operation data to the cloud server; and if the energy recovery strategy needs to be adjusted, sending the train operation data to the cloud server.

[0087] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0088] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0089] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for dynamic scheduling and energy consumption optimization of rail transit, characterized in that, A cloud server applied to an intelligent transportation system, the intelligent transportation system including the cloud server and edge nodes, the cloud server and edge nodes being communicatively connected, the method comprising: Acquire train operation data and passenger flow trend data from the edge nodes; Based on the passenger flow trend data and the train operation data, a train dispatching instruction is generated and sent to the edge node. The train dispatching instruction is used to adjust train intervals; and / or, An energy recovery strategy is determined based on the train operation data and sent to the edge node. The energy recovery strategy is used to optimize train energy consumption. The step of generating train dispatching instructions based on the passenger flow trend and the train operation data, and / or determining the energy recovery strategy based on the train operation data, includes: Determine whether the aforementioned passenger flow trend data has been obtained; If the passenger flow trend data is not obtained, an energy recovery strategy is determined based on the train operation data. If the passenger flow trend data is obtained, determine whether an energy recovery strategy adjustment request has been obtained; If the energy recovery strategy adjustment request is received, a train dispatching instruction is generated based on the passenger flow change trend and the train operation data, and an energy recovery strategy is determined based on the train operation data. If the energy recovery strategy adjustment request is not received, a train dispatching instruction is generated based on the passenger flow trend and the train operation data.

2. The method according to claim 1, characterized in that, The step of generating train dispatch instructions based on the passenger flow trend data and the train operation data includes: Based on the train operation data, obtain the train speed and position of each train corresponding to the edge node; Train scheduling instructions are generated based on the passenger flow trend data and the train speed and position of each train through a scheduling optimization algorithm.

3. The method according to claim 1, characterized in that, The step of determining the energy recovery strategy based on the train operation data includes: Based on the train operation data, obtain train energy consumption data, train location, and train speed; The train energy consumption data, the train position, and the train speed are input into a deep learning model to obtain the energy recovery strategy output by the deep learning model.

4. The method according to claim 1, characterized in that, The edge node and the cloud server are connected via a distributed communication framework.

5. A method for dynamic scheduling and energy consumption optimization of rail transit, characterized in that, An edge node applied to an intelligent transportation system, the intelligent transportation system including a cloud server and the edge node, the cloud server and the edge node being communicatively connected, the method comprising: Passenger flow is obtained from the first Internet of Things (IoT) devices deployed at train stations; The number of passengers is input into the prediction model included in the edge node to obtain the passenger flow change trend data output by the prediction model, and the need to adjust the train running interval is determined based on the passenger flow change trend data. Train operation data is obtained from a second IoT device deployed on the train, and the need to adjust the energy recovery strategy is determined based on the train operation data. When it is necessary to adjust the train interval, the passenger flow trend data and the train operation data are sent to the cloud server. If it is necessary to adjust the energy recovery strategy, the train operation data shall be sent to the cloud server. When it is necessary to adjust both the train interval and the energy recovery strategy, an energy recovery strategy adjustment request needs to be sent simultaneously when sending the passenger flow trend data and the train operation data to the cloud server.

6. A dynamic scheduling and energy consumption optimization device for rail transit, characterized in that, A cloud server for use in an intelligent transportation system, the intelligent transportation system including the cloud server and edge nodes, the cloud server and edge nodes being communicatively connected, the device comprising: The first acquisition unit is used to acquire train operation data and passenger flow trend data from the edge nodes; The generation unit is configured to generate train dispatching instructions based on the passenger flow trend data and the train operation data, and send the train dispatching instructions to the edge node, wherein the train dispatching instructions are used to adjust train intervals; and / or, The determining unit is configured to determine an energy recovery strategy based on the train operation data and send the energy recovery strategy to the edge node, wherein the energy recovery strategy is used to optimize train energy consumption. The step of generating train dispatching instructions based on the passenger flow trend and the train operation data, and / or determining the energy recovery strategy based on the train operation data, is specifically used for: Determine whether the aforementioned passenger flow trend data has been obtained; If the passenger flow trend data is not obtained, an energy recovery strategy is determined based on the train operation data. If the passenger flow trend data is obtained, determine whether an energy recovery strategy adjustment request has been obtained; If the energy recovery strategy adjustment request is received, a train dispatching instruction is generated based on the passenger flow change trend and the train operation data, and an energy recovery strategy is determined based on the train operation data. If the energy recovery strategy adjustment request is not received, a train dispatching instruction is generated based on the passenger flow trend and the train operation data.

7. A dynamic scheduling and energy consumption optimization device for rail transit, characterized in that, An edge node for use in an intelligent transportation system, the intelligent transportation system including a cloud server and the edge node, the cloud server and the edge node being communicatively connected, the device comprising: The second acquisition unit is used to acquire passenger flow based on the first Internet of Things device deployed at the train station. The third acquisition unit is used to input the number of passengers into the prediction model included in the edge node, obtain the passenger flow change trend data output by the prediction model, and determine whether the train running interval needs to be adjusted based on the passenger flow change trend data. The fourth acquisition unit is used to acquire train operation data based on the second Internet of Things device deployed on the train, and determine whether the energy recovery strategy needs to be adjusted based on the train operation data. The first sending unit is used to send the passenger flow change trend data and the train operation status data to the cloud server when it is necessary to adjust the train operation interval; The second sending unit is used to send the train operation data to the cloud server when the energy recovery strategy needs to be adjusted. The third sending unit is used to send an energy recovery strategy adjustment request simultaneously when sending the passenger flow change trend data and the train operation status data to the cloud server, in the case where it is necessary to adjust the train running interval and the energy recovery strategy at the same time.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the dynamic scheduling and energy consumption optimization method for rail transit as described in any one of claims 1 to 5.

9. An intelligent transportation system, characterized in that, The intelligent transportation system includes a cloud server and edge nodes, and the cloud server and the edge nodes are communicatively connected. The cloud server is used to execute the steps performed by the cloud server in the dynamic scheduling and energy consumption optimization method for rail transit as described in any one of claims 1-4; The edge node is used to execute the steps performed by the edge node in the dynamic scheduling and energy consumption optimization method for rail transit as described in claim 5.

Images