Power supply scheduling method and system for railway traction substation based on photovoltaic grid-connected power generation

Abstract

A power supply dispatching method and system for a railway traction substation based on photovoltaic grid-connected power generation, which relates to the field of photovoltaic power generation. Among them, the method includes: obtaining the load information of the railway traction substations in the target area after a preset time period and the detection information of the corresponding photovoltaic grid-connected power generation system; determining the power supply mode of each traction substation according to the load information and the detection information, and the power supply mode includes any one of the photovoltaic grid-connected power generation system, the energy storage system, and the power grid continuously supplying power to the corresponding traction substation within the preset time period; within the preset time period, supplying power to each traction substation according to the power supply mode. Implementing the technical solution provided by this application can effectively suppress the fluctuations of photovoltaic power generation and improve the stability of the overall power supply.

Description

Technical Field

[0001] This application relates to the field of photovoltaic power generation, and specifically relates to a power supply scheduling method and system for a railway traction substation based on photovoltaic grid-connected power generation. Background Art

[0002] With the enhancement of environmental protection awareness and the development of renewable energy technologies, the railway industry is actively exploring the application of green energy. As an important part of the railway system, the power supply method of the traction substation directly affects the efficiency and environmental friendliness of railway operations. In recent years, the application of photovoltaic power generation technology in the railway system has become increasingly widespread, providing new possibilities for the power supply of railway traction substations.

[0003] Currently, some railway systems have begun to attempt to apply photovoltaic power generation technology to traction substation power supply. These systems usually adopt a combination of photovoltaic power generation and the traditional power grid, improving the utilization rate of renewable energy while meeting the load requirements of the traction substation.

[0004] However, this simple grid-connected method of traditional traction substation power supply often cannot effectively cope with the intermittent and fluctuating characteristics of photovoltaic power generation, making it difficult to maximize the utilization of photovoltaic power generation. Summary of the Invention

[0005] This application provides a power supply scheduling method and system for a railway traction substation based on photovoltaic grid-connected power generation, which can effectively suppress the fluctuations of photovoltaic power generation and improve the stability of the overall power supply.

[0006] In the first aspect of this application, a power supply scheduling method for a railway traction substation based on photovoltaic grid-connected power generation is provided, including:

[0007] Obtaining the load information of the railway traction substations in the target area after a preset time period and the detection information of the corresponding photovoltaic grid-connected power generation system;

[0008] Determining the power supply mode of each traction substation according to the load information and the detection information, where the power supply mode includes any one of the photovoltaic grid-connected power generation system, the energy storage system, and the power grid continuously supplying power to the corresponding traction substation within a preset time period;

[0009] Supplying power to each traction substation according to the power supply mode within the preset time period.

[0010] In the second aspect of this application, a power supply scheduling system for a railway traction substation based on photovoltaic grid-connected power generation is provided, including:

[0011] A prediction information acquisition module, configured to obtain the load information of the railway traction substations in the target area after a preset time period and the detection information of the corresponding photovoltaic grid-connected power generation system;

[0012] A power supply mode determination module, configured to determine the power supply modes of the traction substations according to the load information and the detection information, where the power supply modes include any one of a photovoltaic grid-connected power generation system, an energy storage system, and a power grid continuously supplying power to the corresponding traction substation within a preset duration;

[0013] A power supply mode application module, configured to supply power to each traction substation according to the power supply mode within the preset duration.

[0014] In a third aspect of the present application, a computer storage medium is provided. The computer storage medium stores multiple instructions, and the instructions are adapted to be loaded and executed by a processor to perform the above method steps.

[0015] In a fourth aspect of the present application, an electronic device is provided, including: a processor and a memory; wherein, the memory stores a computer program, and the computer program is adapted to be loaded and executed by the processor to perform the above method steps.

[0016] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0017] By obtaining the load information of the traction substations in the target area and the detection information of the photovoltaic grid-connected power generation system, the real-time conditions of both the supply and demand sides can be comprehensively grasped. Based on the above information, the method can dynamically determine the optimal power supply mode and flexibly allocate the power supply ratios of the photovoltaic power generation system, the energy storage system, and the power grid. This intelligent scheduling strategy based on real-time data significantly improves the system's adaptability to the volatility of photovoltaic power generation and effectively overcomes the defect that the traditional simple grid connection method is difficult to cope with the intermittency of photovoltaic power generation.

[0018] By pre-planning the power supply mode within a preset duration, the method can coordinate the outputs of each power supply source in advance and achieve the maximum utilization of photovoltaic power generation. This not only improves the utilization efficiency of renewable energy but also optimizes the power supply cost on the premise of ensuring power supply reliability. Especially by introducing the energy storage system as a regulation means, the flexibility of the system is further enhanced, the fluctuations of photovoltaic power generation can be effectively suppressed, and the overall power supply stability is improved.

[0019] Compared with the traditional simple grid connection method, by comprehensively considering the load demand, the photovoltaic power generation situation, and the capacity of the energy storage system, this method realizes the dynamic matching of supply and demand and the coordinated power supply of multiple sources. The intelligent scheduling strategy not only maximizes the utilization of photovoltaic power generation but also improves the reliability and economy of the entire power supply system. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a schematic flowchart of a power supply scheduling method for a railway traction substation based on photovoltaic grid-connected power generation provided by an embodiment of the present application;

[0021] Figure 2 It is a main wiring layout diagram of a photovoltaic power generation switch station provided by an embodiment of the present application;

[0022] Figure 3 It is a schematic structural diagram of a photovoltaic power generation switch station provided by an embodiment of the present application;

[0023] Figure 4 It is a main wiring layout diagram of a railway traction substation provided by an embodiment of the present application;

[0024] Figure 5 It is a schematic structural diagram of a power supply dispatching system of a railway traction substation based on photovoltaic grid-connected power generation provided by an embodiment of the present application;

[0025] Figure 6 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application. Specific embodiments

[0026] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments.

[0027] In the description of the embodiments of the present application, words such as "for example" or "for illustration" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "for example" or "for illustration" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "for example" or "for illustration" is intended to present the relevant concepts in a specific manner.

[0028] In the description of the embodiments of the present application, the meaning of the term "a plurality" refers to two or more. For example, a plurality of systems refers to two or more systems, and a plurality of screen terminals refers to two or more screen terminals. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly indicating the technical features indicated. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. The terms "include", "comprise", "have" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0029] The present application provides a power supply dispatching method for a railway traction substation based on photovoltaic grid-connected power generation. Refer to Figure 1 , Figure 1 It is a schematic flow diagram of a power supply dispatching method for a railway traction substation based on photovoltaic grid-connected power generation disclosed in an embodiment of the present application. The steps are as follows:

[0030] Step 101: Obtain the load information of the railway traction in the target area after a preset time period and the detection information of the corresponding photovoltaic grid-connected power generation system.

[0031] Among them, the target area refers to a specific railway network range, which can be understood as the smallest unit of centralized power supply dispatching management. This unit usually includes multiple interconnected traction substations and corresponding photovoltaic grid-connected power generation systems. For example, an operating section of a high-speed railway line, the subway network of a certain city, or the regional railway network responsible for a certain railway administration. Specifically, the target area may be a 100-kilometer-long high-speed railway line, with 5 traction substations along the line, and each traction substation is equipped with a corresponding photovoltaic grid-connected power generation system. These traction substations and photovoltaic grid-connected power generation systems are uniformly managed and controlled by the same dispatching center.

[0032] Among them, the load information refers to the power demand status of the railway traction within a specific time period. This power demand mainly comes from the traction power required for train operation and the power consumption of various auxiliary equipment along the line.

[0033] Correspondingly, the detection information refers to the operating status and performance parameters of the photovoltaic grid-connected power generation system. This information covers the working conditions of various components of the system, the impact of environmental factors on the system performance, and the overall power generation efficiency and grid connection situation of the system. The detection information is collected in real time through sensors and monitoring devices distributed at various key nodes of the photovoltaic grid-connected power generation system.

[0034] Among them, the photovoltaic grid-connected power generation system refers to a power generation system that connects the electric energy generated by a solar photovoltaic power generation device to the public power grid to achieve two-way power flow. This system usually includes solar panels, inverters, grid connection equipment, and related control and protection devices. The photovoltaic grid-connected power generation system can convert solar energy into electric energy and send the excess electric energy to the public power grid to achieve the efficient utilization of renewable energy.

[0035] In the embodiment of the present application, it can be understood as a photovoltaic power generation system specially designed for power supply to railway traction substations. This system boosts the electric energy generated by photovoltaic power generation to 27.5 kV through a step-up transformer to match the power supply voltage of the railway traction substation, and realizes coordinated power supply with the traditional power grid through an intelligent control system. This system also includes advanced technologies such as high-precision fault monitoring, comprehensive intelligent protection functions, and microgrid dispatching control to ensure the safety, reliability, and efficiency of the system.

[0036] Optionally, please refer to Figure 2 , Figure 2 which shows a main wiring layout diagram of a photovoltaic power generation switch station provided by the embodiment of the present application. As Figure 2As shown in the figure, the photovoltaic grid-connected power generation system includes photovoltaic panels, a busbar trunking unit, an inverter, a step-up transformer, and a grid-connected outgoing line cabinet. Among them, a photovoltaic power generation switch station is set in the grid-connected outgoing line cabinet, and the photovoltaic power generation switch station includes at least two switchable collector line inlet cabinets.

[0037] Specifically, as the core power generation unit of the system, the photovoltaic panels can be installed in spaces such as the roof of the station or the railway slope. The selection of the above installation locations not only makes full use of the idle space along the railway, but also maximizes the capture of solar energy. The photovoltaic panels can convert solar energy into direct current of 24V or 48V.

[0038] In order to improve the management efficiency of the system and the utilization rate of electric energy, the direct current generated by multiple photovoltaic panels is collected through the busbar trunking unit. The busbar trunking unit not only simplifies the line connection, but also realizes the preliminary current collection and electric energy management, providing a stable direct current input for the subsequent inversion process. The inverter converts the direct current output by the busbar trunking unit into alternating current with the same frequency and phase as the power grid. The voltage of the alternating current output by the inverter is usually about 800V.

[0039] Considering the special power supply requirements of the railway traction substation, the system is equipped with a step-up transformer. This component steps up the 800V alternating current output by the inverter to 27.5kV, realizing the voltage matching between the photovoltaic power generation system and the railway traction power supply system.

[0040] Furthermore, a photovoltaic power generation switch station can be set in the grid-connected outgoing line cabinet. The photovoltaic power generation switch station includes at least two switchable collector line inlet cabinets. The setting of multiple collector lines allows the system to flexibly switch between different photovoltaic power generation units or regions. For example, when the photovoltaic panels in a certain area are shaded or need to be maintained, the system can automatically switch to other normally operating collector lines to ensure the stability of the overall power generation. The switchable characteristic of the photovoltaic power generation switch station is realized through an intelligent control system. The control system real-time monitors the power generation status, load demand, and possible fault conditions of each collector line, and automatically switches the lines according to the preset logic. Finally, the boosted 27.5kV power is connected to the 27.5kV busbar of the traction substation through the grid-connected access cabinet, realizing the connection between the photovoltaic power generation system and the railway traction power supply system.

[0041] Based on the above embodiments, as an alternative embodiment, please refer to Figure 3 , Figure 3 which is a schematic structural diagram of a photovoltaic power generation switch station provided by an embodiment of the present application.

[0042] Specifically, the main wiring layout of the photovoltaic power generation switch station includes core equipment such as 27.5kV station service transformer cabinets, 27.5kV collector line incoming cabinets, busbar PT cabinets, metering cabinets, and 27.5kV photovoltaic grid-connected outgoing cabinets. These devices work together to ensure that the electricity of the photovoltaic power generation system can be stably and safely incorporated into the 27.5kV busbar system of the traction substation.

[0043] The 27.5kV station service transformer cabinet steps down the 27.5kV high-voltage electricity to 380V or 220V low-voltage electricity through the internal transformer, providing necessary power for auxiliary facilities such as the control system, monitoring equipment, and protection devices within the switch station. This ensures the normal operation of the internal equipment of the switch station, and improves the safety of the system through the equipped protection devices, which can be disconnected in time when the power supply is abnormal to protect the equipment from damage.

[0044] Among them, the 27.5kV collector line incoming cabinet is responsible for receiving the 27.5kV electricity processed by the photovoltaic panels through the inverter and step-up transformer. In the embodiment of the present application, the number of collector line incoming cabinets is designed to be adjustable. This flexibility enables the system to adapt to different scales of photovoltaic power generation requirements. For example, for a small-scale system, only 1-2 incoming cabinets may be required; while for a large-scale system, multiple incoming cabinets may be needed. This scalable design allows the system to be adjusted according to the actual power generation demand and the number of installed photovoltaic panels, improving the adaptability of the system and the possibility of future expansion.

[0045] Among them, the busbar PT cabinet converts the 27.5kV high voltage into a low-voltage signal of about 110V through a voltage transformer, providing real-time voltage data for monitoring equipment and protection devices. This design enables the system to detect abnormal busbar voltage conditions in a timely manner, such as overvoltage or undervoltage, thereby triggering corresponding protection mechanisms. In addition, the busbar PT cabinet is also equipped with overvoltage protection and lightning arresters, further improving the anti-interference ability of the system in the face of external power grid fluctuations or lightning strikes.

[0046] Among them, through the equipped high-precision current transformers and voltage transformers, the metering cabinet can accurately record the total power generation and grid-connected power of the photovoltaic power generation system. This design not only meets the needs of operation and management, but also provides a reliable data basis for possible settlement of surplus electricity fed into the grid.

[0047] Among them, the 27.5kV photovoltaic grid-connected outgoing cabinet can send electricity to the 27.5kV busbar of the traction substation under normal circumstances through the equipped circuit breakers and protection devices, and cut off the circuit in time when the system is abnormal to prevent the expansion of faults. This design greatly improves the safety and reliability of the system.

[0048] Based on the above embodiments, as an optional embodiment, please refer to Figure 4 , Figure 4A main wiring layout diagram provided by an embodiment of the present application for a railway traction substation.

[0049] Specifically, the main wiring layout of the traction substation includes two main power sources (incoming line 1 and incoming line 2), two traction transformers, multiple 27.5 kV incoming lines and feeder lines, and a circuit breaker for grid connection of the photovoltaic power station. The core objective of this design is to convert high-voltage electricity of 110 kV or 220 kV into single-phase alternating current of 27.5 kV while ensuring the reliability and flexibility of power supply.

[0050] Among them, incoming line 1 and incoming line 2 serve as the dual main power sources of the traction substation, taking power from the high-voltage power grid of 110 kV or 220 kV. This redundant design of dual power sources greatly improves the reliability of power supply. When one of the power sources fails or needs to be repaired, the other can immediately take over the power supply task to ensure uninterrupted power supply to the traction substation. To achieve this function, the system is equipped with an automatic control logic that can quickly switch when detecting power abnormalities, minimizing the risk of power interruption.

[0051] Among them, traction transformer 1 and traction transformer 2 are the core equipment of the system, responsible for converting high-voltage electricity into single-phase alternating current of 27.5 kV. Each transformer is respectively connected to one incoming line, further enhancing the redundancy of the system. This design ensures that even when one transformer fails or is under maintenance, the other transformer can still maintain normal power supply to the traction substation, greatly improving the reliability and maintenance flexibility of the system.

[0052] Among them, the design of the 27.5 kV incoming lines (incoming line 1, incoming line 2, incoming line 3, incoming line 4) reflects the flexibility and scalability of the system. Multiple incoming lines not only increase the redundancy of the system but also provide a larger power supply capacity and higher power supply flexibility. Each incoming line is equipped with a circuit breaker and protection device, which can quickly isolate the problem area in case of a fault, prevent the expansion of the fault, and protect the safety of the entire system.

[0053] Among them, the multi-channel design of the 27.5 kV feeder lines (feeder line 1, feeder line 2, feeder line 3, feeder line 4) meets the requirements of different catenary power supply sections. Each feeder line is responsible for supplying power to a specific catenary section. This way of sectional power supply not only improves the flexibility of power supply but also enhances the reliability of the system. When a fault occurs in a certain section, the power supply of other sections will not be affected. Each feeder line is equipped with a circuit breaker and relay protection device, which can cut off the circuit in time in case of a short circuit or overload to protect the catenary and other parts of the traction substation.

[0054] Based on the above embodiments, as an alternative embodiment, in step 101: The step of obtaining the load information of the traction substation of the railway in the target area after a preset time period and the detection information of the corresponding photovoltaic grid-connected power generation system may specifically further include the following steps:

[0055] Step 201: Obtain the train operation schedule of the traction substation of the railway within the target area and the detection signals collected by the sensors installed on the traction substation.

[0056] Among them, the train operation schedule refers to a time table that details the railway operation plan, which contains the operation arrangements of all trains within a specific time period. This form not only includes the departure and arrival times of the trains, but also key information such as train types, stopping stations, operation routes, etc. In the embodiments of the present application, it can be understood as a dynamically updated database, which contains the complete operation information of all trains within the power supply range of all traction substations in the target area. The train operation schedule is the basis for predicting the load of the traction substation. By analyzing the train operation schedule, the system can estimate how many trains are running within the power supply range of a certain traction substation at any given time point, so as to predict the power demand of the traction substation. For example, when multiple high-speed trains accelerate simultaneously within the power supply section of a traction substation, the system can anticipate the upcoming high-load demand.

[0057] Correspondingly, the detection signals refer to a set of electrical parameter and operation status data collected in real time by various high-precision sensors installed on the traction substation. It includes the electrical parameters of the 27.5kV bus, such as voltage and current, the power of each feeder, power factor, harmonic content and other electrical parameters, as well as the electrical parameters of the traction transformer, such as temperature, oil level, air pressure, and the equipment status of the circuit breaker, such as switch status and other information. At the same time, it also includes the environmental parameters inside the traction substation, such as temperature, humidity, smoke concentration, and the electrical parameters of the photovoltaic power generation system, such as output voltage, current, and the working status of the inverter. These signals are collected in real time at a high sampling rate by devices such as high-precision voltage transformers, current transformers, power analyzers, temperature sensors, and liquid level sensors.

[0058] During the acquisition process of the detection signals, the data is first subjected to preliminary preprocessing, including filtering and outlier detection, to ensure the quality and reliability of the data. Subsequently, these processed signals are transmitted to the control system in real time through an industrial communication network, such as industrial Ethernet or fiber optic network. This high-speed and real-time data transmission ensures that the system can timely obtain the latest operation status information, providing a basis for rapid decision-making and response.

[0059] Step 202: Input the train operation schedule and the detection signals into the prediction model to obtain the load information and detection information of each traction substation output by the prediction model after a preset time period.

[0060] A prediction model refers to a mathematical or statistical tool that uses historical data and the current state to estimate future results. In the embodiments of this application, it can be understood as a complex neural network system based on deep learning algorithms, specifically designed to process and analyze large-scale time-series data of the railway traction substation power supply system. This model is mainly composed of a Long Short-Term Memory network (LSTM). The prediction model is used to make high-precision predictions of the power load demand within a preset time period of the railway traction substation and the output of the photovoltaic power generation system. Specifically, the prediction model can process multi-source heterogeneous data, including but not limited to train operation schedules, historical load data, real-time detection signals, weather forecast information, etc. By deeply analyzing and learning these complex data, the model can identify the key factors affecting the traction substation load and photovoltaic power generation and their interactions, thereby generating accurate short-term and medium-term prediction results.

[0061] Specifically, comprehensive data collection is carried out first. The train operation schedule contains key information such as the arrival and departure times of trains, train types, load, and speed. At the same time, through sensors in the traction substation and photovoltaic power generation system, real-time electrical signals (such as voltage and current), environmental signals (such as light intensity, temperature, humidity, and wind speed), and equipment signals (such as the status of photovoltaic power generation equipment and the power of the energy storage system) are collected.

[0062] Subsequently, detailed data preprocessing is carried out. First is time synchronization, processing the data of the train schedule and sensor signals based on the same time stamp to ensure data consistency. Then data cleaning is performed to handle missing values and outliers. For missing values, methods such as deletion, interpolation filling, or default value filling are selected according to the importance of the data.

[0063] For the train schedule, the arrival and departure times are extracted, the train type is converted into numerical features through One-Hot encoding, and the load and speed are directly used as numerical features. For sensor signals, the change rate of electrical signals is calculated, statistical features of environmental signals are extracted, and the equipment status information is encoded into features available for the model. At the same time, time features and historical load features are considered.

[0064] The prediction model adopts a deep learning architecture based on the Long Short-Term Memory network. The model inputs include processed train features, current load, environmental data, and equipment status, etc. In the training stage, historical data is used to train the model. The mean squared error can be used as the loss function, and the model parameters are optimized through the backpropagation algorithm. To prevent overfitting, the validation set can be used to adjust the hyperparameters.

[0065] Data segmentation follows the characteristics of time series, and the data is divided into a training set, a validation set, and a test set in chronological order. For the case of insufficient data, data augmentation techniques such as data smoothing or generating synthetic data with similar time patterns can be considered.

[0066] After the prediction model is trained, by inputting the current train operation schedule and detection signals in real time, the prediction model can output the predicted values of the loads of traction substations and the expected outputs of photovoltaic systems at each time point (e.g., at 15-minute intervals) within a preset future duration (such as 24 hours). For example, the model can predict that the load demand of a traction substation will be 5.2 MW after 1 hour and 4.8 MW after 2 hours, and at the same time predict that the power generation capacity of the photovoltaic power generation system will be 2.3 MW in the next 1 hour and 1.9 MW after 2 hours.

[0067] Step 102: Determine the power supply modes of each traction substation according to the load information and detection information. The power supply modes include any one of the photovoltaic grid-connected power generation system, energy storage system, and power grid continuously supplying power to the corresponding traction substation within a preset duration.

[0068] Among them, the power supply mode refers to the specific schemes and strategies for providing electric energy to railway traction substations within a specific time period. In the embodiments of the present application, it can be understood as a dynamic scheduling mechanism for determining which one or a combination of the photovoltaic grid-connected power generation system, energy storage system, and power grid supplies power to the corresponding traction substation continuously at each time period within a preset duration. This power supply mode not only includes the selection of power sources but also the output power distribution ratios of each power source. Specifically, the power supply mode may cover various situations from pure photovoltaic power supply to hybrid power supply of the three, and the system will dynamically adjust according to the real-time power generation situation, load demand, and energy storage status.

[0069] For example, when the photovoltaic power generation is sufficient, the system may adopt a pure photovoltaic power supply mode; when the photovoltaic power generation is insufficient, it may switch to a mode combining photovoltaic and energy storage or introduce the power grid for supplementation.

[0070] Specifically, the system will first analyze the load information within a preset duration, which includes the electricity demand curves of each traction substation predicted based on the train operation schedule and historical data. At the same time, the system will also combine the detection information of the photovoltaic grid-connected power generation system, such as the current power generation, predicted power generation, equipment status, etc., and the information of the energy storage system, such as the capacity, charge and discharge status, etc. Based on this comprehensive data, the system will use optimization algorithms, such as mixed-integer linear programming algorithms, to determine the optimal power supply mode at each time period.

[0071] When determining the power supply mode, the system will give priority to using the output of the photovoltaic grid-connected power generation system. When the photovoltaic power generation is sufficient, the system will use it as the main power supply source, and the excess power can be used to charge the energy storage system or be fed back to the power grid. When the photovoltaic power generation is insufficient to meet the load demand, the system will decide whether to enable energy storage power supply according to the status of the energy storage system. Only when both the photovoltaic power generation and the energy storage system cannot meet the demand, the system will obtain power from the power grid. This strategy not only maximizes the use of renewable energy but also effectively reduces the dependence on the power grid and reduces electricity costs.

[0072] In actual operation, the system needs to consider factors such as the startup time of the equipment, switching losses, and power quality fluctuations. To avoid system instability caused by frequent switching, certain switching thresholds and delay times are set in the algorithm. For example, only when the change in photovoltaic power generation exceeds a preset threshold and lasts for a certain period of time, will the switching of the power supply mode be triggered.

[0073] Based on the above embodiments, as an alternative embodiment, in step 102: the step of determining the power supply mode of each traction substation according to the load information and the detection information may specifically further include the following steps:

[0074] Step 301: Determine the first available output power of the photovoltaic grid-connected power generation system within a preset duration according to the electrical detection information, environmental detection information, and equipment detection information of the photovoltaic grid-connected power generation system.

[0075] Specifically, the system comprehensively analyzes the electrical detection information, environmental detection information, and equipment detection information of the photovoltaic grid-connected power generation system. The electrical detection information includes parameters such as the current output voltage, current, and power factor, which reflect the real-time operating state of the system. The environmental detection information mainly involves meteorological factors such as light intensity, temperature, humidity, and wind speed, which directly affect the power generation efficiency of the photovoltaic panels. The equipment detection information includes the aging degree of the photovoltaic panels, the dust coverage, and the operating state of the inverters, which reflect the health status of the equipment and potential performance limitations.

[0076] In a feasible implementation manner, the system can determine the stability of the first collector line currently used by each traction substation through the detection information.

[0077] Specifically, when determining the first available output power of the photovoltaic grid-connected power generation system, the system first needs to evaluate the stability of the first collector line currently used by each traction substation, because the stability of the collector line directly affects the output quality and efficiency of the entire photovoltaic grid-connected power generation system.

[0078] Specifically, to accurately evaluate the stability of the first collector line, the system will real-time monitor and analyze key parameters in a series of detection information. These parameters include but are not limited to the voltage fluctuation range, current change rate, power factor, harmonic content, and line impedance. Specifically, the system collects the real-time electrical data of the collector line through high-precision voltage transformers and current transformers, and the sampling frequency can reach thousands of times per second to capture instantaneous electrical fluctuations. These raw data are preliminarily filtered and then input into a specially designed stability evaluation algorithm.

[0079] This algorithm comprehensively considers multiple factors to calculate the stability index. For example, it analyzes the amplitude and frequency of voltage fluctuations. Under normal circumstances, voltage fluctuations should be within ±5% of the rated value. At the same time, the algorithm also evaluates the rate of change of current. A sudden large change in current may indicate a sudden change in line load or a short - circuit fault. The fluctuation of the power factor is also an important indicator, which reflects the energy transmission efficiency of the system. In addition, the analysis of harmonic content can help identify potential power quality problems, and the monitoring of line impedance can timely detect potential hazards such as line aging or loose connections. The system compares the calculated stability index with a preset threshold. If the stability index is lower than the threshold, for example, the voltage fluctuation exceeds ±7%, or the current mutation rate exceeds 20% / second, the system will determine that the current first collector line is unstable.

[0080] When it is determined that the stability is less than the threshold, switch the first collector line to the idle second collector line.

[0081] When it is determined that the stability is greater than or equal to the threshold, directly obtain the output power of the photovoltaic grid - connected power generation system as the first available output power.

[0082] When the system detects that the stability of the first collector line is less than the preset threshold, it will immediately trigger the switching mechanism to switch the power supply line from the first collector line to the pre - prepared idle second collector line. The necessity of this switching operation is to prevent equipment damage or power supply interruption caused by unstable power transmission. The switching process is executed by the intelligent control system of the photovoltaic switching station and is achieved through high - speed switching equipment. Specifically, the control system first sends a disconnection command to the circuit breaker of the first collector line and prepares for the access of the second collector line. After confirming that the first collector line is completely disconnected, the system immediately closes the circuit breaker of the second collector line to complete the switching. The whole process can usually be completed within dozens of milliseconds, and this rapid response can minimize power loss and fluctuations during the switching process.

[0083] After the switching is completed, the system will immediately evaluate the stability of the second collector line to ensure that it can safely and stably undertake the power supply task. On the contrary, when the system determines that the stability of the first collector line is greater than or equal to the preset threshold, it indicates that the current line is in good operating condition and can safely and stably transmit electric energy. In this case, the system directly obtains the real - time output power of the photovoltaic grid - connected power generation system as the first available output power.

[0084] Step 302: Determine the second available output power of the energy storage system in the traction substation within a preset duration according to the first available output power and the load information.

[0085] Specifically, after determining the first available output power of the photovoltaic grid-connected power generation system, the system needs to further evaluate and optimize the usage strategy of the energy storage system to ensure the stability and efficiency of the entire power supply system. The above process first considers the priority use of photovoltaic power generation and then supplements the output of the energy storage system as needed, reflecting the principles of renewable energy priority and diversified power supply.

[0086] Specifically, the system first calculates the actual available output power P of the photovoltaic power generation system pv,used . This value depends on the smaller value of the current output power P of the photovoltaic system pv and the load demand P load , that is, P pv,used = min(P pv , P load ). The above calculation method ensures the maximum utilization of photovoltaic power generation and avoids energy waste caused by excessive power generation. For example, if the photovoltaic system can output 5 MW at a certain moment and the load demand is 4 MW, the actually used photovoltaic power will be 4 MW, and the remaining 1 MW can be used for charging the energy storage system or feeding back to the power grid.

[0087] When the photovoltaic power generation cannot fully meet the load demand, the system calculates the supplementary output power P of the energy storage system bat,used . This value is restricted by two main factors: the maximum output capacity P of the energy storage system bat,max and the actually required supplementary power, that is, (P load - P pv,used ). Therefore, the preliminary calculation formula for P bat,used is min(P bat,max , P load - P pv,used ). This ensures that the energy storage system does not exceed its designed maximum output capacity and also avoids unnecessary over-discharge.

[0088] However, the actual available output of the energy storage system is also restricted by its current remaining power E bat . To prevent the energy storage system from over-discharging, the system further restricts P bat,used within E bat / τ, where τ represents the considered time period. This means that even if the load demand is very high, the output of the energy storage system will not exceed the level supported by its current power. For example, if the energy storage system has a remaining 10 MWh and a 1-hour time period is considered, then its maximum output will not exceed 10 MW, even though it can theoretically output a higher power.

[0089] Step 303: Determine the preset power supply that can be allocated by the power grid for each traction substation according to the load information of each traction substation in the target area.

[0090] After determining the preset power supply of the power grid for each traction substation, the system also needs to consider a key issue: when multiple traction substations require power supply from the power grid simultaneously, how to ensure that the power grid will not be overloaded while fairly and reasonably allocating power resources. The solution to this problem is crucial for the stability and efficiency of the entire power supply system.

[0091] To address the above problem, the embodiment of the present application adopts a dynamic allocation strategy based on the load demand ratio. Specifically, assume there are N traction substations in the target area, and the total power supply capacity of the power grid is P grid,max . First, the system will collect the real-time load demands of each traction substation. Then, the system will calculate the total load demand of all traction substations. Based on the above data, the system can use the following formula to calculate the preset power supply that can be allocated from the power grid for each traction substation:

[0092] ;

[0093] In the formula, represents the power supply obtained by traction substation i from the power grid, represents the load demand of traction substation i, represents the sum of the total load demands of all N traction substations in the target area, represents the maximum power supply capacity of the power grid.

[0094] The above formula ensures the fairness of the power grid power supply, and each traction substation can obtain the corresponding proportion of power supply according to its actual demand. Secondly, this method effectively prevents the risk of power grid overload. Since the total allocated power will not exceed the maximum power supply capacity P of the power grid grid,max , the system generally will not be overloaded. Thirdly, this dynamic allocation method can flexibly respond to load changes. When the load demand of a certain traction substation increases, it will automatically obtain a larger proportion of the power grid power supply, while the power supply proportion of other traction substations will decrease accordingly, thus achieving the optimal utilization of resources.

[0095] In practical applications, the system will monitor the load demands of each traction substation in real time and update the power allocation at a relatively high frequency. This fast response mechanism ensures that the power allocation can follow the load changes in a timely manner, further improving the stability and efficiency of the system. In addition, to cope with sudden large load changes, the system also sets up a buffer mechanism. When the load demand of a certain traction substation suddenly increases significantly, the system will allow it to exceed the proportionally allocated power within a short period of time, but at the same time, it will quickly adjust the power supply of other traction substations to ensure that the total power supply does not exceed P grid,max .

[0096] Step 304: Adjust the preset power supply of each traction substation according to the first available output power and the second available output power of each traction substation to obtain the third available output power of the power grid of each traction substation.

[0097] Specifically, after determining the first available output power and the second available output power of each traction substation, the system needs to further adjust the pre-allocated power grid power supply to obtain a more accurate and efficient power supply plan, thereby optimizing the allocation of power grid resources and ensuring the stability and economy of power supply.

[0098] Specifically, the system first calculates the difference between the actual power demand of each traction substation and the power that can be provided by the photovoltaic and energy storage systems, that is, P deficit =P load -P pv,used -P bat,used . This difference represents the amount of power that each traction substation still needs to obtain from the power grid.

[0099] Then, the system will reallocate the power supply of the power grid according to the actual power demand of each traction substation. This process adopts a dynamic adjustment mechanism, the core of which is to recalculate the distribution ratio of the power grid power supply based on the actual power gap of each traction substation. First, the system calculates the power gap of each traction substation, that is, its load demand minus the actual output power of the photovoltaic power generation and energy storage systems. Then, the system calculates the total power gap of all traction substations. Next, the system reallocates the power supply of the power grid according to the proportion of the power gap of each traction substation in the total gap.

[0100] The above method can ensure that the power supply capacity of the power grid is most effectively allocated to the traction substations that really need it. For example, if the photovoltaic power generation of a certain traction substation exceeds expectations, resulting in a small power gap, then the power supply power allocated to it will also be reduced accordingly. On the contrary, if the load of a certain traction substation suddenly increases or its photovoltaic output decreases, resulting in a large power gap, then it will obtain more power supply power from the power grid. This dynamic adjustment mechanism can not only more accurately meet the real-time power supply needs of each traction substation, but also improve the power supply efficiency of the entire system, reduce power waste, and balance the power supply pressure between each traction substation to a certain extent.

[0101] Step 305: Determine the power supply mode of each traction substation according to the first available output power, the second available output power and the third available output power of each traction substation.

[0102] Specifically, after determining the first available output power, the second available output power, and the third available output power of each traction substation, the embodiment of the present application adopts an optimization method based on a mixed-integer linear programming algorithm to determine the optimal power supply mode. The core objective of this step is to maximize the utilization of renewable energy while ensuring power supply stability and meeting load requirements, and at the same time reduce grid consumption and the power supply switching frequency.

[0103] Based on the above embodiments, as an optional embodiment, this process may specifically further include the following steps:

[0104] Input the first available output power, the second available output power, and the third available output power of each traction substation into the power supply optimization model, and obtain the power supply mode output by the power supply optimization model. The power supply mode is used to characterize the way of supplying power to the traction substation by the photovoltaic grid-connected power generation system, the energy storage system, and the power grid at each time period within a preset duration. Wherein, the objective function of the power supply optimization model includes reducing the consumption of the power grid and reducing the switching of the power supply sources of the traction substation.

[0105] Among them, the power supply optimization model can be understood as an optimization algorithm that allows simultaneous processing of continuous variables and discrete variables. In the power supply scheduling problem of railway traction substations, the power supply optimization model can be used to optimize the power supply switching decision between the photovoltaic power generation system, the energy storage system, and the power grid, with the goal of minimizing the power cost and the number of power supply switches, while meeting the load requirements and various system constraints.

[0106] Furthermore, the system needs to reasonably allocate the power supply ratios of the photovoltaic power generation system (PV), the energy storage system (ES), and the power grid (Grid) on the premise of ensuring the load requirements of the traction substation, and minimize the number of switches when switching these power supply sources to avoid system instability. Specifically, the selection of the power supply mode for each time period can be based on the following conditions: when using the photovoltaic power generation system, give priority to its available power; when the photovoltaic power generation is insufficient, use the energy storage system for supplementation; when both the photovoltaic power generation and the energy storage system are insufficient, use the power grid to meet the load requirements; avoid frequent switching of the power supply mode.

[0107] The objective function of the power supply optimization model mainly involves two main objectives: (1) Minimize the power cost: Minimize the power consumption of the power grid as much as possible; (2) Minimize the number of switches of the power supply sources: Avoid frequent switching of the power supply sources and reduce instability. It can be expressed as:

[0108] ;

[0109] In the formula, T represents the preset duration, t represents the time period within the preset duration, represents the output power of the power grid at time period t, $C_t$ represents the cost of grid power supply during time period $t$, and $\lambda$ represents the weight of the switching penalty, which is used to balance the power cost and the cost of switching. $SwitchPV(t)$ represents whether the power supply switches from PV power generation during time period $t$. $SwitchES(t)$ represents whether the power supply switches from the energy storage system during time period $t$. $SwitchGrid(t)$ represents whether the power supply switches from the grid during time period $t$.

[0110] Among them, $Minimize()$ represents the objective function, which is mainly used to seek a balance between the two main objectives of minimizing the power cost and minimizing the number of power supply source switches. By adjusting $\lambda$, the minimum point of the objective function, that is, the optimal power supply scheduling strategy, can be found.

[0111] Among them, the objective of minimizing the power cost aims to minimize the consumption of grid power as much as possible. This can not only reduce the operating cost, but also improve the utilization rate of renewable energy, meeting the requirements of energy conservation and emission reduction. Specifically, the objective function includes a term for calculating the total cost of grid power supply, which is represented by the sum of the products of the grid output power in each time period and the unit cost of grid power supply in the corresponding time period. By minimizing this term, the system will preferentially select power supply methods with lower costs, that is, give priority to using PV power generation and the energy storage system.

[0112] Among them, the objective of minimizing the number of power supply source switches is to avoid the system instability caused by frequent switching of power supply sources. Frequent switching may lead to problems such as voltage fluctuations and increased equipment losses, affecting the reliability and lifespan of the entire power supply system. The objective function includes a term for representing the number of power supply source switches, which is represented by the sum of the switching states of PV power generation, the energy storage system, and grid power supply in each time period. Among them, the switching state of each time period is represented by a binary variable, which takes the value of 1 when switching occurs and 0 otherwise.

[0113] Furthermore, in order to balance the two potentially conflicting objectives of power cost and switching cost, the embodiment of the present application introduces the weight $\lambda$ of the switching penalty, which plays a penalty role in the number of switching of the power supply mode. By adjusting the value of $\lambda$, frequent switching of power sources can be effectively avoided:

[0114] Each time the power supply mode (PV power generation, energy storage, or grid) is switched, the switching variable $Switch(t)$ will become 1, thus increasing the penalty term in the objective function. This penalty term will drive the model to minimize the number of switches as much as possible during the solution process to minimize the total cost.

[0115] Furthermore, the switching frequency can be controlled by adjusting λ: the larger the λ value, the stronger the penalty for switching, and the model will be more inclined to keep the current power supply mode unchanged during optimization. Even if the power supply capacity of photovoltaic power generation decreases, the system will give priority to the energy storage system or grid power supply rather than switching frequently. When λ is large, the switching cost is high, and it will tend to reduce the number of switches, thus avoiding frequent switching of power sources. This means that the switching among photovoltaic power generation, energy storage system, and grid will be restricted, and the system will be more inclined to keep the current power source unchanged, even if this may mean a slightly higher power cost.

[0116] If the λ value is small, the system will pay more attention to minimizing the total power cost by frequently switching power sources. When λ is small, the switching cost is low, and the algorithm will focus more on minimizing the total power cost and less on the number of switches. This may cause the system to frequently switch power sources to pursue the lowest power cost. By reasonably setting λ, an optimal balance can be found between the stability and economy of the power supply system.

[0117] In practical applications, the system first needs to obtain key information such as the load demand in each period, the predicted output power of the photovoltaic power generation system, the available capacity of the energy storage system, and the cost of grid power supply. This information is obtained through data collection and analysis in the aforementioned steps. Then, this information is input into the mixed-integer linear programming algorithm, while considering various constraints, such as load balance constraints, power upper limit constraints of each power source, charge and discharge state constraints of the energy storage system, etc. The algorithm will find the power supply mode combination that can minimize the objective function through iterative calculations based on these inputs and constraints.

[0118] The above optimization method based on the objective function has multiple advantages. First, it can maximize economic benefits while ensuring power supply stability, achieving a balance between economy and reliability. Second, by adjusting the weight coefficients, the system can flexibly adapt to different operation strategies and environmental conditions, improving the applicability and scalability of the method. Third, this method considers the overall optimization of multiple periods instead of simply making decisions for each period separately, so it can obtain a more globally optimal solution. Finally, due to the adoption of the power supply optimization model, this method has good computational efficiency and convergence, and can obtain high-quality optimization results in a short time to meet the requirements of real-time scheduling.

[0119] Furthermore, when determining the power supply mode, a series of constraints are set in the embodiments of the present application to ensure the safety, reliability, and efficiency of the system. The above constraints not only ensure the feasibility of the power supply plan but also ensure the stability and economy of the system during operation.

[0120] Optionally, the defined constraints may include:

[0121] The total power supply for each time period t must be equal to the load demand, and the expression is:

[0122] ;

[0123] In the formula, represents the output power of the photovoltaic power generation system in time period t, represents the output power of the energy storage system in time period t, represents the output power of the power grid in time period t, represents the load demand of the traction substation.

[0124] First of all, the embodiment of the present application introduces a power balance constraint, requiring that the total power supply for each time period must be equal to the load demand. This constraint ensures that at any moment, the total output power of the photovoltaic power generation system, the energy storage system and the power grid can accurately match the load demand of the traction substation. This accurate matching can not only ensure the normal power supply of the traction substation, but also avoid energy waste and system overload. In actual operation, the system will monitor the load demand of the traction substation in real time and dynamically adjust the output power of each power supply according to this demand to maintain power balance.

[0125] The output power of the photovoltaic power generation system cannot exceed its maximum available power, and the expression is:

[0126] ;

[0127] In the formula, represents the first available output power of the photovoltaic power generation system in time period t.

[0128] Secondly, the embodiment of the present application sets an upper limit constraint on the output power of each power supply. For the photovoltaic power generation system, its output power cannot exceed the first available output power in the current time period. This constraint takes into account the real-time and volatility of photovoltaic power generation, ensuring that the system does not overly rely on unstable photovoltaic output. The system will calculate the maximum available power of the photovoltaic system in real time according to the current light conditions, temperature and other environmental factors, as well as the equipment status, and use it as the upper limit constraint.

[0129] The output power of the energy storage system cannot exceed its maximum available power, and the charge and discharge state of the energy storage system should be considered. The expression is:

[0130] ;

[0131] In the formula, represents the second available output power of the energy storage system in time period t.

[0132] For the energy storage system, its output power is also limited by the second available output power. This constraint not only considers the maximum discharge capacity of the energy storage system but also needs to consider its current state of charge to ensure the sustainable use of the energy storage system. The system dynamically calculates the maximum available power for each time period based on the characteristics of the energy storage device, its current state of charge, and the predicted future demand.

[0133] In addition, the available electricity of the energy storage system should be within its capacity range, and the expression is:

[0134] ;

[0135]

[0136] In addition, the embodiments of the present application also pay special attention to the management of the energy storage system. The available electricity of the energy storage system must be kept within its capacity range, and the system needs to dynamically track the charge and discharge state of the energy storage system. By setting the upper and lower limit constraints on the electricity of the energy storage system, overcharging or over-discharging of the energy storage system can be avoided, its service life can be extended, and sufficient electricity can be ensured for use when needed. The system will monitor the electricity state of the energy storage system in real time and consider the expected charge and discharge conditions in future time periods during the scheduling process to ensure that the energy storage system always operates within a safe working range.

[0137] The output power of the power grid cannot exceed its maximum available power:

[0138] ;

[0139] In the formula, represents the third available output power of the power grid at time period t.

[0140] For power grid power supply, its output power cannot exceed the pre-determined third available output power. This constraint considers the power supply capacity of the power grid and other electricity consumption demands to avoid excessive pressure on the power grid. The system determines the maximum power that the power grid can provide for each time period based on the agreement with the power grid company and the current power grid load conditions and uses it as a constraint condition.

[0141] The above-mentioned constraint conditions together constitute a complete operating framework for the power supply system. In each scheduling cycle, the system inputs these constraint conditions into the power supply optimization model. When solving the optimal power supply mode, the algorithm will strictly abide by these constraint conditions. For example, when allocating the output power of each power supply, the power supply optimization model will ensure that the sum is equal to the load demand, and at the same time, the output of each power supply does not exceed its maximum available power. For the energy storage system, the algorithm will also predict its charge and discharge state in future time periods to ensure that it always remains within a safe working range.

[0142] (5) When the power supply switches from one type to another, the switching variable is 1; otherwise, it is 0. This can be achieved through the following logical constraints:

[0143] ;

[0144] Similarly, for the switching between the energy storage system and the power grid:

[0145] ;

[0146]

[0147] In the formula, , and represent the switching tolerance (threshold), which is used to prevent frequent switching due to small power changes.

[0148] Specifically, in the process of determining the power supply mode, the embodiments of the present application particularly focus on the switching problem of the power supply. Frequent switching of the power supply may lead to problems such as system instability, increased equipment loss, and decreased power supply quality. Therefore, in order to optimize the power supply strategy, this embodiment introduces a switching variable and corresponding logical constraints to effectively control the switching frequency of the power supply.

[0149] Specifically, this embodiment defines switching variables for the photovoltaic power generation system, the energy storage system, and the power grid respectively. These switching variables are binary. When the corresponding power supply switches from one state to another, its value is 1; otherwise, it is 0. In this way, the system can accurately track the switching situation of the power supply in each time period.

[0150] To achieve this goal, this embodiment adopts a logical constraint based on power change. For the photovoltaic power generation system, the system compares the absolute value of the difference in output power between the current time period and the previous time period. If this difference exceeds the preset switching tolerance, it is considered that a switch has occurred, and the corresponding switching variable is set to 1. The same logic also applies to the switching judgment of the energy storage system and the power grid.

[0151] Among them, the switching tolerance is actually a threshold, which is used to prevent unnecessary switching operations triggered by small power fluctuations. The setting of this tolerance value needs to be adjusted according to the characteristics and operating requirements of the system. For example, for the photovoltaic power generation system, a relatively large tolerance value may need to be set to adapt to its inherent volatility; while for the relatively stable power grid power supply, a relatively small tolerance value can be set.

[0152] The implementation process of the above switching judgment mechanism is as follows: In each scheduling period, the system first obtains the current output power of each power supply and the output power of the previous period. Then, it calculates the power difference between the two periods and compares the absolute value with the preset switching tolerance. If the difference exceeds the tolerance, the corresponding switching variable is set to 1, indicating that a switch has occurred; otherwise, the switching variable remains 0, indicating that no switch has occurred.

[0153] The above switching judgment mechanism can effectively reduce unnecessary power supply switching and improve the stability of the system. For example, when there are short-term small fluctuations in photovoltaic power generation, the system will not immediately switch to other power supplies, but will only switch when the fluctuations exceed the tolerance, which greatly reduces the volatility of the system. Secondly, by controlling the switching frequency, the service life of the equipment is extended and the maintenance cost is reduced. Frequent switching will accelerate the wear of the switching equipment, while the method of this embodiment can effectively slow down this process. Thirdly, this mechanism improves the power supply quality. Reducing unnecessary switching can avoid voltage fluctuations caused by switching operations, thus ensuring the stability of power supply.

[0154] In the embodiment of this application, in order to efficiently solve complex power supply scheduling problems, a mixed integer linear programming (MILP) solver such as Gurobi or CPLEX is adopted. These advanced mathematical optimization tools can quickly process large-scale optimization problems containing continuous variables and discrete variables.

[0155] The main reason for using the MILP solver is the complexity and multi-dimensionality of the power supply scheduling problem. The system needs to simultaneously consider multiple periods, multiple power supplies, multiple constraint conditions, as well as continuous power distribution and discrete switching decisions. Traditional heuristic algorithms or simple rule-based methods are difficult to find the global optimal solution within a reasonable time, while the MILP solver can effectively handle this complexity and obtain a high-quality solution in a short time.

[0156] Specifically, the previously defined objective function, decision variables, and constraint conditions can be transformed into a mathematical model that the MILP solver can understand. This includes defining the output power of the photovoltaic power generation system, energy storage system, and power grid in each period as continuous variables, and defining the switching decision as a binary variable. Then, all constraint conditions such as power balance constraints, power upper limit constraints of each power supply, charge and discharge state constraints of the energy storage system, and switching logic constraints are input into the solver.

[0157] Next, the input data required by the solver needs to be provided. This data includes the predicted load demand, the predicted output of the photovoltaic power generation system, the initial state of the energy storage system, the grid power supply cost, etc. This data can be obtained through the prediction model and real-time monitoring system in the previous steps. At the same time, the parameters of the solver also need to be set, such as the solution time limit, the optimization accuracy requirement, etc., to balance the calculation time and the quality of the solution.

[0158] After completing the model setup and data input, start the MILP solver. The solver will use efficient algorithms, such as the branch and bound method, the cutting plane method, etc., to search for the optimal solution in the solution space. During the solving process, the solver will continuously update the upper and lower bounds, prune the infeasible or suboptimal solutions, and finally converge to the optimal solution or find the best feasible solution within the specified time.

[0159] After the solving is completed, the MILP solver will return the optimization results. These results include the optimal power supply scheme for each time period. The solver will output: the photovoltaic power generation power for each time period 、the power of the energy storage system for each time period t 、the grid power for each time period t and whether there is a switch for each time period 、 、 。

[0160] In summary, using the MILP solver can obtain high-quality optimization results in a very short time, meeting the requirements of real-time scheduling. Secondly, since all the constraint conditions and objective functions are considered, the obtained solution is globally optimal or approximately globally optimal, which ensures the economy and feasibility of the power supply scheme. Thirdly, the results of the MILP solver have good interpretability, and the power supply decisions for each time period can be clearly seen, which is conducive to the operation and maintenance personnel to understand and execute these decisions.

[0161] In addition, the use of the MILP solver also improves the flexibility and adaptability of the system. When the system parameters change, it can be quickly re-solved to obtain a new optimal solution. This dynamic optimization ability enables the system to better cope with various changes and uncertainties in actual operation.

[0162] Step 103: Supply power to each traction substation according to the power supply mode within a preset time period.

[0163] Specifically, the system will first convert the optimized power supply mode into a series of specific control instructions. These instructions include the set values of the output powers of the photovoltaic power generation system, the energy storage system, and the grid for each time period, as well as the corresponding switching operation instructions. The control system will adjust the output powers of each power supply source in real time according to these instructions and perform the switching operation of the power supply source when necessary.

[0164] To ensure a smooth transition of power supply and the stability of the system, soft switching strategies are usually adopted for switching operations. For example, when switching from photovoltaic power generation to power supply from the energy storage system, the system first gradually reduces the output power of photovoltaic power generation while gradually increasing the output power of the energy storage system until the switching is completed. This smooth switching can effectively reduce voltage fluctuations and current surges, improving the power supply quality.

[0165] During the power supply execution, the system also continuously monitors the actual operating conditions, including the actual output power of each power supply source, the actual load demand of the traction substation, the charge and discharge status of the energy storage system, etc. These real-time data will be compared with the results predicted by the optimization model. If there are significant deviations between the actual situation and the prediction, such as a sharp drop in photovoltaic power generation output due to weather changes or a sudden increase in load demand due to train scheduling changes, the system will trigger a real-time adjustment mechanism.

[0166] The real-time adjustment mechanism allows the system to quickly adjust the power supply strategy to adapt to new situations while maintaining the original optimization goals. This may include operations such as increasing the proportion of power grid supply and starting the discharge of the energy storage system in advance. In some cases, if the deviation is too large, the system may even trigger a re-optimization process to recalculate the optimal power supply mode using the latest real-time data.

[0167] Refer to Figure 5 , this application also provides a power supply scheduling system for a railway traction substation based on photovoltaic grid-connected power generation, including:

[0168] A prediction information acquisition module, configured to acquire the load information of the railway traction substations in the target area after a preset time period and the detection information of the corresponding photovoltaic grid-connected power generation system;

[0169] A power supply mode determination module, configured to determine the power supply mode of each traction substation according to the load information and the detection information, where the power supply mode includes any one of the photovoltaic grid-connected power generation system, the energy storage system, and the power grid continuously supplying power to the corresponding traction substation within a preset time period;

[0170] A power supply mode application module, configured to supply power to each traction substation according to the power supply mode within the preset time period.

[0171] Based on the above embodiments, as an optional embodiment, the prediction information acquisition module is further configured to acquire the train operation schedule of the railway traction substations in the target area and the detection signals collected by the sensors installed on the traction substations; input the train operation schedule and the detection signals into a prediction model to obtain the load information and detection information of each traction substation output by the prediction model after a preset time period.

[0172] Based on the above embodiments, as an alternative embodiment, the power supply mode determination module is further configured to determine the first available output power of the photovoltaic grid-connected power generation system within a preset duration according to the electrical detection information, environmental detection information, and equipment detection information of the photovoltaic grid-connected power generation system; determine the second available output power of the energy storage system in the traction substation within the preset duration according to the first available output power and the load information; determine the preset power supply that can be allocated by the power grid for each traction substation according to the load information of each traction substation in the target area; adjust the preset power supply of each traction substation according to the first available output power and the second available output power of each traction substation to obtain the third available output power of the power grid of each traction substation; and determine the power supply mode of each traction substation according to the first available output power, the second available output power, and the third available output power of each traction substation.

[0173] Based on the above embodiments, as an alternative embodiment, the power supply mode determination module is further configured to input the first available output power, the second available output power, and the third available output power of each traction substation into a power supply optimization model, and obtain the power supply mode output by the power supply optimization model. The power supply mode is used to characterize the power supply method for each traction substation using the photovoltaic grid-connected power generation system, the energy storage system, and the power grid at each time period within a preset duration. Among them, the objective function of the power supply optimization model includes reducing the consumption of the power grid and reducing the switching of the power supply sources of the traction substation.

[0174] Based on the above embodiments, as an alternative embodiment, the power supply dispatching system of the railway traction substation based on photovoltaic grid-connected power generation further includes a collector line switching module, which is configured to determine the stability of the first collector line currently used by each traction substation according to the detection information; when it is determined that the stability is less than a threshold, switch the first collector line to an idle second collector line.

[0175] It should be noted that when the device provided in the above embodiments implements its functions, only the above-mentioned division of each functional module is used for illustration. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be elaborated here.

[0176] The embodiment of the present application also provides a computer storage medium, which can store multiple instructions. The instructions are suitable for being loaded and executed by a processor to perform the power supply dispatching method of the railway traction substation based on photovoltaic grid-connected power generation as described in the above embodiments. The specific execution process can refer to the specific description of the illustrated embodiments and will not be elaborated here.

[0177] This application also discloses an electronic device. Refer to Figure 6 , Figure 6 which is a schematic structural diagram of an electronic device disclosed in an embodiment of this application. The electronic device 600 may include: at least one processor 601, at least one network interface 604, a user interface 603, a memory 605, and at least one communication bus 602.

[0178] Among them, the communication bus 602 is used to realize the connection and communication between these components.

[0179] Among them, the user interface 603 may include a display interface and a camera interface. Optionally, the user interface 603 may further include a standard wired interface and a wireless interface.

[0180] Among them, the network interface 604 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0181] Among them, the processor 601 may include one or more processing cores. The processor 601 uses various interfaces and lines to connect various parts within the entire server, and by running or executing instructions, programs, code sets, or instruction sets stored in the memory 605, and by calling the data stored in the memory 605, it executes various functions of the server and processes data. Optionally, the processor 601 may be implemented in at least one of the following hardware forms: digital signal processing (DSP), field-programmable gate array (FPGA), and programmable logic array (PLA). The processor 601 may integrate one or a combination of several of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes the operating system, user interface graphics, and application programs, etc.; the GPU is responsible for the rendering and drawing of the content to be displayed on the display screen; the modem is used to process wireless communication. It can be understood that the above-mentioned modem may not be integrated into the processor 601 and may be implemented separately by a single chip.

[0182] Among them, the memory 605 may include a Random Access Memory (RAM), or may also include a Read-Only Memory. Optionally, the memory 605 includes a non-transitory computer-readable storage medium. The memory 605 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 605 may include a program storage area and a data storage area. Among them, the program storage area can store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area can store the data involved in the above-mentioned method embodiments. Optionally, the memory 605 may also be at least one storage device located far from the aforementioned processor 601. Refer to Figure 6 , in the memory 605, as a computer storage medium, it may include an operating system, a network communication module, a user interface module, and an application program for a power supply scheduling method of a railway traction substation based on photovoltaic grid-connected power generation.

[0183] In Figure 6 In the electronic device 600 shown, the user interface 603 is mainly used to provide an input interface for the user and obtain the data input by the user; while the processor 601 can be used to call the application program for a power supply scheduling method of a railway traction substation based on photovoltaic grid-connected power generation stored in the memory 605. When executed by one or more processors 601, the electronic device 600 executes one or more of the methods as described in the above embodiments. It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0184] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0185] In several implementation manners provided in this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections between each other can be through some service interfaces. The indirect couplings or communication connections of devices or units can be in electrical or other forms.

[0186] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0187] In addition, in each embodiment of this application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0188] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in each embodiment of this application. And the aforementioned memory includes: various media such as USB flash drives, mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0189] The above are only exemplary embodiments of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, all equivalent changes and modifications made in accordance with the teachings of the present disclosure still fall within the scope covered by the present disclosure. Those skilled in the art will easily think of other implementation schemes of the present disclosure after considering the specification and the disclosure of the practical truth.

[0190] This application aims to cover any variations, uses, or adaptive changes of the present disclosure. These variations, uses, or adaptive changes follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not recorded in the present disclosure. The specification and the embodiments are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A power supply dispatching method for a railway traction substation based on photovoltaic grid-connected power generation, characterized in that, Including: Obtaining the load information of the traction substation within a preset duration in the target area and the detection information of the corresponding photovoltaic grid-connected power generation system; Determining the power supply mode of each traction substation according to the load information and the detection information, where the power supply mode includes continuous power supply to the corresponding traction substation by any one of the photovoltaic grid-connected power generation system, the energy storage system, and the power grid within a preset duration; During the preset duration, supplying power to each traction substation according to the power supply mode; Among them, the detection information includes electrical detection information, environmental detection information, and equipment detection information of the photovoltaic grid-connected power generation system. Among them, the electrical detection information includes electrical parameters of the busbar, electrical parameters of the traction transformer, and equipment status of the circuit breaker. The environmental detection information includes light intensity, temperature, humidity, and wind speed. The equipment detection information includes the working status of the inverter. The determining the power supply mode of each traction substation according to the load information and the detection information includes: Determining the first available output power of the photovoltaic grid-connected power generation system within a preset duration according to the electrical detection information, environmental detection information, and equipment detection information of the photovoltaic grid-connected power generation system; Determining the second available output power of the energy storage system in the traction substation within a preset duration according to the first available output power and the load information; Determining the preset power supply that can be allocated by the power grid for each traction substation according to the load information of each traction substation in the target area; Adjusting the preset power supply of each traction substation according to the first available output power and the second available output power of each traction substation to obtain the third available output power of the power grid of each traction substation; Determining the power supply mode of each traction substation according to the first available output power, the second available output power, and the third available output power of each traction substation; Among them, the determining the power supply mode of each traction substation according to the first available output power, the second available output power, and the third available output power of each traction substation includes: Inputting the first available output power, the second available output power, and the third available output power of each traction substation into the power supply optimization model, and obtaining the power supply mode output by the power supply optimization model. The power supply mode is used to represent the way of supplying power to the traction substation by the photovoltaic grid-connected power generation system, the energy storage system, and the power grid at each time period within a preset duration; Among them, the objective function of the power supply optimization model includes reducing the consumption of the power grid and reducing the switching of the power supply source of the traction substation; Among them, the power supply optimization model is expressed as: ； Wherein, T represents a preset duration, and t represents a time period within the preset duration. represents the output power of the power grid during the time period t. represents the cost of power grid power supply during the time period t, and λ represents the weight of the switching penalty, which is used to balance the power cost and the cost of switching. represents whether the photovoltaic power generation switches to power supply from photovoltaic power generation during the time period t. represents whether to switch to power supply from the energy storage system during the time period t. represents whether to switch to power supply from the power grid during the time period t.

2. The power supply dispatching method of the railway traction substation based on photovoltaic grid-connected power generation according to claim 1, characterized in that, The obtaining the load information of the traction substation of the railway in the target area and the detection information of the corresponding photovoltaic grid-connected power generation system within a preset duration includes: Obtaining the train operation schedule of the traction substation of the railway in the target area and the detection signals collected by the sensors arranged on the traction substation; Inputting the train operation schedule and the detection signals into the prediction model, and obtaining the load information and detection information of each traction substation output by the prediction model after a preset duration.

3. The power supply dispatching method of the railway traction substation based on photovoltaic grid-connected power generation according to claim 1 is characterized in that, The photovoltaic grid-connected power generation system includes a photovoltaic panel, a busbar trunking unit, an inverter, a step-up transformer, and a grid-connected outgoing line cabinet. Among them, the grid-connected outgoing line cabinet is provided with a photovoltaic power generation switch station, and the photovoltaic power generation switch station includes at least two switchable collector line incoming cabinets.

4. The power supply dispatching method for a railway traction substation based on photovoltaic grid-connected power generation according to claim 3, wherein, The method further includes: Determining the stability of the first collector line currently used by each traction substation according to the detection information; When it is determined that the stability is less than the threshold, switching the first collector line to the idle second collector line.

5. A power supply dispatching system for a railway traction substation based on photovoltaic grid-connected power generation for implementing the method according to any one of claims 1-4, characterized in that, Including: A prediction information acquisition module, configured to acquire the load information of the traction substations on the railway in the target area after a preset time period and the detection information of the corresponding photovoltaic grid-connected power generation system; A power supply mode determination module, configured to determine the power supply mode of each traction substation according to the load information and the detection information, where the power supply mode includes any one of a photovoltaic grid-connected power generation system, an energy storage system, and a power grid continuously supplying power to the corresponding traction substation within a preset time period; A power supply mode application module, configured to supply power to each traction substation according to the power supply mode within the preset time period.

6. An electronic device, characterized in that, Including a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method according to any one of claims 1-4.

7. A computer storage medium, characterized in that, The computer storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1-4 is executed.

Images