A data-driven traction power supply capability situation awareness system and method

Abstract

The application discloses a data-driven traction power supply capacity situation awareness system, which comprises a device layer, a measurement layer, a network layer and an awareness layer; wherein the measurement layer comprises a distributed synchronous acquisition device for measuring and obtaining synchronous sampling data of each device in the device layer; the network layer is connected with the measurement layer and the awareness layer respectively, the synchronous sampling data obtained by the measurement layer is transmitted from the measurement layer to the awareness layer through the network layer; the awareness layer is used for generating a power flow solvable power supply quality compliance result according to the obtained synchronous sampling data, and then establishing a traction power supply system power supply capacity evaluation system database, realizing power supply capacity visual evaluation, completing traction power supply capacity situation analysis and prediction. The application also discloses a data-driven traction power supply capacity situation awareness method. The traction power supply capacity situation awareness system and method can realize real-time evaluation of power supply capacity under the traction power supply system, dynamic probabilistic power flow calculation and power supply quality prediction.

Description

Technical Field

[0001] This application relates to the field of traction power supply systems, and more specifically, to a data-driven traction power supply capability situational awareness system and method. Background Technology

[0002] Transportation is a key area for energy conservation and emission reduction. In its development, it should not only be a pioneer in economic development but also in green development. According to publicly available data, railway freight can reduce emissions by over 70 million tons compared to highway freight for the same volume. Railways consume only one-tenth of the energy required by the transportation industry to achieve 30% of the equivalent turnover. Meanwhile, the electrification rate of railways exceeds 70%, with electric traction becoming the mainstay of railway transportation. As a core component of electrified railways, the traction power supply system faces increasing challenges due to insufficient traction power supply capacity, becoming a bottleneck restricting the safe and reliable development of railways. Furthermore, the China State Railway Group Co., Ltd., in its "Notice on Doing a Good Job in Traction Power Supply Capacity Assessment" (Gongdian Power Supply

[2020] No. 130), put forward a new requirement for power supply capacity: "Ensuring maximum capacity guarantee for production and transportation while meeting the operational safety requirements of traction power supply equipment." This requires the traction power supply system to have the ability to perceive changes in traction power supply capacity over a long period.

[0003] Furthermore, flexible power source integration, represented by distributed renewable energy and energy storage, is becoming the development direction of the next generation of traction power supply systems (hereinafter referred to as the system). This has led to a shift in the system's energy consumption structure from a single, continuously controllable power source to multiple highly uncertain and weakly controllable power sources, and a change in the system's operating characteristics from a real-time source-load balance mode to a non-completely real-time balance mode with multi-source interaction. Under the requirement of ensuring the safety and reliability of railway transportation, the profound changes in energy consumption structure and operating characteristics will inevitably increase the demand for real-time perception of the system's power supply capacity.

[0004] now that Summary of the Invention

[0005] To address at least one deficiency or improvement need in the existing technology, this invention provides a data-driven traction power supply capability situational awareness system and method structure, which can accurately assess the system's power supply capability in real time and ensure the safety and reliability of railway transportation.

[0006] To achieve the above objectives, according to a first aspect of the present invention, a data-driven traction power supply capability situational awareness system is provided, characterized in that it includes a device layer, a measurement layer, a network layer, and a sensing layer; wherein,

[0007] The measurement layer is connected to the device layer via a cable and is used to measure and obtain synchronous sampling data of each device in the device layer.

[0008] The network layer is connected to the measurement layer and the sensing layer via optical fiber, and the synchronous sampling data obtained by the measurement layer is transmitted from the measurement layer to the sensing layer through the network layer.

[0009] The perception layer is used to generate power flow solvable power quality compliance results based on the acquired synchronous sampling data, thereby establishing a database of power supply capacity evaluation system for traction power supply system, realizing visualized assessment of power supply capacity, and completing traction power supply capacity situation analysis and prediction.

[0010] Furthermore, the perception layer includes a situational awareness engine module, which comprises a power generation distribution data processing submodule, a verification submodule, a predicted distribution data submodule, and a situational prediction submodule; wherein,

[0011] The power generation distribution data processing submodule is used to receive and analyze the synchronous sampling data generated by the measurement layer to obtain the probability ranking data of new energy power generation within the prediction period, and send it to the verification submodule.

[0012] The predicted distribution data submodule is used to receive and analyze the synchronous sampling data generated by the measurement layer to obtain the grid voltage, harmonic data and traction substation power flow data, and then generate the predicted power supply quality probability distribution data of the traction substation grid side and send it to the verification submodule.

[0013] The verification submodule receives and analyzes the synchronous sampling data generated by the measurement layer to obtain node power flow, grid voltage data and real-time state of charge data of energy storage devices. Based on the node power flow, grid voltage data, real-time state of charge data of energy storage devices and the predicted probability distribution data of power supply quality on the grid side of the traction substation, the power flow can be resolved to achieve the power supply quality compliance result.

[0014] The situation prediction submodule is used to establish a database of power supply capacity evaluation system for traction power supply system based on the power quality compliance results of the power flow solution, and then realize the visual assessment of power supply capacity, and complete the situation analysis and prediction of traction power supply capacity.

[0015] Furthermore, the verification submodule includes a synchronous data processing unit, an analysis unit, a calculation unit, and a diagnostic unit; wherein,

[0016] The synchronous data processing unit is used to receive and analyze the synchronous sampling data generated by the measurement layer to obtain node power flow, grid voltage data and real-time state of charge data of energy storage devices.

[0017] The analysis unit is used to combine the node power flow, grid voltage data, real-time state of charge data of energy storage devices with the probability ranking data of new energy power generation within the prediction period to obtain a set of probability distributions.

[0018] The calculation unit is used to input the probability distribution set as data-driven input to the traction power supply system probability power flow real-time simulation system, solve and generate multiple probability power flow distribution scenarios within the prediction period, verify the solvability of system power flow and the standardization of the traction network terminal voltage under multiple scenarios, obtain power flow calculation results and terminal voltage results, and send the power flow calculation results to the prediction distribution data submodule.

[0019] The diagnostic unit is used to obtain the power flow calculation results and the terminal grid voltage results to diagnose and generate power flow solvable power supply quality compliance results.

[0020] Furthermore, the predicted distribution data submodule includes a synchronous data processing unit and a prediction model calculation unit, wherein,

[0021] The synchronous data processing unit is used to obtain grid voltage and harmonic data and traction power flow data based on the synchronous sampling data generated by the measurement layer and the received and analyzed data.

[0022] The prediction model calculation unit is used to obtain the power flow calculation results as input to generate the probability distribution data of power supply quality on the grid side of the predicted traction substation.

[0023] Furthermore, the power generation distribution data processing submodule includes a synchronous data processing unit and a power generation model calculation unit, wherein,

[0024] The synchronous data processing unit is used to receive and analyze the synchronous sampling data generated by the measurement layer to obtain real-time distributed new energy trend data.

[0025] The power generation model calculation unit is used to generate probability ranking data of new energy power generation within the prediction period based on the historical dataset of distributed new energy power generation in the traction power supply system.

[0026] Furthermore, the equipment layer includes voltage and current transformers within the internal measurement and control circuits of one or more of the following: traction substations, section substations, AT substations, and switching substations in the traction power supply system. These transformers are used to acquire voltage and current measurement data to generate synchronous sampling data; or

[0027] The measurement layer includes distributed synchronous acquisition devices deployed in one or more of traction substations, section substations, AT substations, and switching substations. The measurement layer is connected to the voltage and current transformers of the equipment layer via cables, and is used to acquire measurement data output from the equipment layer to generate real-time synchronous sampling data; or

[0028] The network layer includes an optical fiber, which is connected to the data transmission interface of each synchronous acquisition device in the measurement layer through the optical fiber, and is used to transmit the synchronous sampling data obtained by the measurement layer to the sensing layer in real time.

[0029] The perception layer and the network layer are connected via optical fiber. The perception layer includes a situational awareness engine module, which is used to receive and process the real-time synchronous sampling data, analyze it, and output power supply capability situational evolution information to realize traction power supply capability situational understanding and prediction.

[0030] Furthermore, the situation prediction submodule is also used to analyze and obtain the new energy power dispatch instructions within the prediction period through the established traction power supply system power supply capacity evaluation system database, and send them to the power generation distribution data processing submodule for iterative verification.

[0031] Furthermore, the distributed synchronous acquisition device includes a front-end signal input circuit, a clock synchronization circuit, a high-speed sampling and calculation circuit, and a data transmission interface; wherein,

[0032] The front-end signal input circuit is connected to the high-speed sampling calculation circuit via a control line. It is used to receive electrical quantity acquisition signals, condition them to filter out noise, and transmit the conditioned signals to the high-speed sampling calculation circuit.

[0033] The clock synchronization circuit is used to obtain satellite signals through the GNSS receiver, condition the clock signals, and then transmit them to the high-speed sampling calculation circuit to achieve the synchronization of sampling among the various acquisition devices.

[0034] The high-speed sampling and calculation circuit is used to receive and process the electrical quantity acquisition signal;

[0035] The data transmission interface is connected to the switch and is used to send data to the outside world.

[0036] Furthermore, the verification submodule is also used to verify the solvability of the system power flow and whether the voltage at the end of the traction network meets the standard requirements under multiple scenarios to obtain the power flow calculation results. If the power flow model is not solvable or the voltage at the end of the traction network does not meet the requirements, it is determined that the system power supply capacity is insufficient, and the power flow calculation results are sent to the situation prediction submodule.

[0037] According to a second aspect of the present invention, a data-driven traction power supply capability situational awareness method is provided, which utilizes the traction power supply capability situational awareness system described in any of the preceding claims to perform traction power supply capability situational awareness, characterized by comprising the following steps:

[0038] The synchronous sampling data of each device in the equipment layer is obtained through measurement.

[0039] The synchronous sampling data is analyzed to obtain grid voltage measurement, harmonic data and traction substation power flow data, and then the probability distribution data of power supply quality on the grid side of the traction substation is generated to predict the power quality.

[0040] The synchronously sampled data is analyzed to obtain node power flow, grid voltage data and real-time state of charge data of energy storage devices. Based on the node power flow, grid voltage data, real-time state of charge data of energy storage devices and the predicted probability distribution data of power supply quality on the grid side of the traction substation, the power flow solvable power supply quality compliance result is generated.

[0041] Based on the power flow analysis results, a database for evaluating the power supply capacity of the traction power supply system can be established, thereby enabling a visual assessment of power supply capacity and completing the situational analysis and prediction of traction power supply capacity.

[0042] In summary, compared with the prior art, the above-described technical solutions conceived by this invention can achieve the following beneficial effects:

[0043] (1) This patent is based on a high-precision synchronous acquisition device and a high-performance computing server. It constructs a data-driven traction power supply capacity situational awareness system for new energy access, including a device layer, a measurement layer, a network layer, and a perception layer. The measurement layer is connected to the device layer via cables and is used to measure and obtain synchronous sampling data from each device in the device layer. The perception layer is used to generate power flow solvable power supply quality compliance results based on the acquired synchronous sampling data, thereby establishing a database for evaluating the power supply capacity of the traction power supply system, realizing a visual assessment of power supply capacity, and completing the situational analysis and prediction of traction power supply capacity. This makes up for the shortcomings of the existing SCADA system's single function.

[0044] 2) The measurement layer in this patent includes distributed synchronous acquisition devices deployed in one or more of the following: traction substations, section substations, AT substations, and switching substations. The measurement layer is connected to the voltage transformers and current transformers of the equipment layer via cables to acquire the measurement data output by the equipment layer. It can realize wide-area synchronous measurement and has the characteristics of high sampling rate sampling of multiple electrical quantities and fast and high-precision calculation of sampled data.

[0045] 3) The communication interface and data storage exchange format used in this patent are all standard documents, which facilitates the integration and connection of this system with other systems, as well as the distribution and interaction of data with other systems. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 A schematic diagram of a data-driven traction power supply capability situational awareness system provided in an embodiment of this application;

[0048] Figure 2 This is a schematic diagram of the situational awareness engine module provided in an embodiment of this application;

[0049] Figure 3 A schematic diagram of the power generation distribution data processing submodule is provided for embodiments of this application;

[0050] Figure 4 This is a schematic diagram of the structure of the verification submodule provided in an embodiment of this application;

[0051] Figure 5 This is a schematic diagram of the structure of the prediction distribution data submodule provided in an embodiment of this application;

[0052] Figure 6 This is a schematic diagram of the structure of the distributed synchronous acquisition device provided in the embodiments of this application;

[0053] Figure 7 This is a logical diagram illustrating a data-driven traction power supply capability situational awareness method provided in an embodiment of this application. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. Furthermore, the technical features involved in the various embodiments of this invention described below can be combined with each other as long as they do not conflict with each other.

[0055] The terms "first," "second," "third," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0056] Currently, the existing SCADA (Supervisory Control and Data Acquisition) dispatching and monitoring system for traction power supply systems suffers from low acquisition accuracy, poor clock synchronization, and fragmented data acquisition from various traction stations (stations), making it difficult to meet the requirements for power supply capacity situational awareness.

[0057] Power flow: The steady-state distribution of voltage (at each node) and power (active and reactive power) (at each branch) in a power system; parameters characterizing the operating state of the power system, including the direction and distribution of voltage, current, and power in each node and branch. In practical applications, it generally refers to the static power flow under steady-state operation. Power flow calculation: Given some parameters, known values, and assumed initial values ​​from unknown values ​​in the power grid, through repeated iterations, the precise value of the power flow distribution is finally obtained. That is, given the connection method, parameters, and operating conditions of the power grid, the calculation of the voltage of each bus, the current of each branch, the power, and the network loss in steady-state operation of the power system.

[0058] For operating power systems, power flow calculations can determine whether grid bus voltage, branch current, and power exceed limits. If limits are exceeded, measures should be taken to adjust the operating mode. For power systems under planning, power flow calculations can provide a basis for selecting grid power supply schemes and electrical equipment. Power flow calculations can also provide raw data for relay protection and automatic device setting calculations, power system fault calculations, and stability calculations. For operating power systems, power flow calculations can predict whether the voltage of all network buses can remain within allowable ranges as various power sources and loads change and the network structure changes, and whether various components will experience overload that endangers system safety, thereby enabling further research and development of corresponding safety measures.

[0059] like Figure 1 As shown, the proposed data-driven traction power supply capacity situational awareness system architecture includes an equipment layer, a measurement layer, a network layer, and a sensing layer. The measurement layer is connected to the equipment layer via cables and is used to measure and obtain synchronous sampling data from each device in the equipment layer. The network layer is connected to both the measurement layer and the sensing layer via optical fibers. The synchronous sampling data obtained by the measurement layer is transmitted from the measurement layer to the sensing layer through the network layer. The sensing layer is used to generate power flow-resolved power quality compliance results based on the acquired synchronous sampling data, thereby establishing a database for evaluating the power supply capacity of the traction power supply system, realizing a visualized assessment of power supply capacity, and completing the traction power supply capacity situational analysis and prediction.

[0060] Preferably, the equipment layer includes voltage transformers and current transformers in the internal measurement and control circuits of one or more of the traction substations, section substations, AT substations, and switching substations in the traction power supply system, which are used to acquire voltage and current measurement data to generate synchronous sampling data.

[0061] The measurement layer includes distributed synchronous acquisition devices deployed in one or more of the traction substations, section substations, AT substations, and switching substations. The measurement layer is connected to the voltage transformers and current transformers of the equipment layer via cables. It is used to acquire the measurement data output by the equipment layer to generate real-time synchronous sampling data.

[0062] Specifically, in a preferred embodiment, the perception layer and the network layer are connected via optical fiber. The perception layer includes a situational awareness engine module, which inputs data collected by the measurement layer into an embedded model, driving iterative calculations to obtain multiple probabilistic power flow distribution scenarios and the probability distribution of power supply and consumption quality on the grid side within the prediction period based on data-driven calculations. It then outputs information on the evolution of power supply capacity status, providing strong guidance for issuing renewable energy power dispatch instructions during the prediction period. Simultaneously, the situational awareness engine module assesses the system's power supply capacity by determining the solvability of the model and the compliance of the traction network's terminal voltage. This achieves situational understanding and prediction of traction power supply capacity.

[0063] Preferred, such as Figure 2 As shown, the situation awareness engine module includes a power generation distribution data processing submodule, a verification submodule, a predicted distribution data submodule, and a situation prediction submodule.

[0064] The power generation data processing submodule receives and analyzes the synchronous sampling data generated by the measurement layer to obtain the probability ranking data of new energy power generation within the prediction period and sends it to the verification submodule. The prediction distribution data submodule receives and analyzes the synchronous sampling data generated by the measurement layer to obtain grid voltage, harmonic data, and traction substation power flow data, and then generates the probability distribution data of power supply quality on the grid side of the traction substation and sends it to the verification submodule. The verification submodule receives and analyzes the synchronous sampling data generated by the measurement layer to obtain node power flow, grid voltage data, and real-time state of charge data of energy storage devices. Based on the node power flow, grid voltage data, real-time state of charge data of energy storage devices, and the probability distribution data of power supply quality on the grid side of the traction substation, it generates the power flow solvable power supply quality compliance result. The situation prediction submodule establishes a database of power supply capacity evaluation system for the traction power supply system based on the power flow solvable power supply quality compliance result, and then realizes the visual assessment of power supply capacity, completing the situation analysis and prediction of traction power supply capacity.

[0065] Specifically, such as Figure 3 As shown, the power generation data processing submodule includes a synchronous data processing unit and a power generation model calculation unit, wherein,

[0066] The distributed synchronous acquisition device inputs the power data output from the device layer and outputs high-precision synchronous sampling data to the network layer. The synchronous data processing unit receives and analyzes the synchronous sampling data generated by the distributed synchronous acquisition device to obtain real-time distributed new energy trend data.

[0067] The power generation model calculation unit establishes a Bayesian probability model of power generation output of multiple new energy systems based on the historical dataset of distributed new energy power generation within the traction power supply system. Real-time distributed new energy power flow data is used as the data driver input into the Bayesian probability model to generate probability ranking data of new energy power generation within the prediction period and send it to the verification submodule.

[0068] Preferred, such as Figure 4 As shown, the verification submodule includes a synchronous data processing unit, an analysis unit, a calculation unit, and a diagnostic unit.

[0069] The synchronous data processing unit receives and analyzes the synchronous sampling data generated by the distributed synchronous acquisition device to obtain node power flow, grid voltage data and real-time state of charge data of the energy storage device.

[0070] The analysis unit combines node power flow, grid voltage data, real-time state of charge data of energy storage devices with probability ranking data of renewable energy generation within the prediction period to obtain a set of probability distributions of renewable energy generation.

[0071] The calculation unit takes the probability distribution set of new energy power generation as data-driven input to the real-time simulation system of probabilistic power flow of the traction power supply system. The real-time simulation system of probabilistic power flow of the traction power supply system is a SCADA (Supervisory Control And Data Acquisition) scheduling and monitoring system for the traction power supply system, a common simulation system in this field. Various simulation systems capable of this function exist in the prior art, and those skilled in the art are familiar with the specific details, which will not be elaborated here. After generating multiple probabilistic power flow distribution scenarios within the prediction period using a power flow solution algorithm (such as the Newton-Raphson algorithm, or other power flow solution algorithms, which are not limited here), the solvability of the system power flow and the standardization of the traction network terminal voltage under multiple scenarios are verified, obtaining the power flow calculation results and the terminal network voltage results. The power flow calculation results are then sent to the prediction distribution data submodule.

[0072] The diagnostic unit acquires the power flow calculation results and the terminal grid voltage results to diagnose and generate a power flow solvable power supply quality compliance result. Specifically, if the power flow calculation result indicates that the power flow model is not solvable or the terminal grid voltage result indicates that the traction network terminal grid voltage does not meet the requirements, it indicates that the system power supply capacity is insufficient. The unit then generates a power flow solvable power supply quality compliance result and sends it to the situation prediction submodule.

[0073] Preferred, such as Figure 5 As shown, the predicted distribution data submodule includes a synchronous data processing unit and a prediction model calculation unit. The synchronous data processing unit obtains grid voltage measurement and harmonic data and traction power flow data based on the received and analyzed synchronous sampling data of the traction power supply system.

[0074] Based on Vine-Copula theory, grid voltage and harmonic data, and traction substation power flow data, the prediction model calculation unit establishes a correlation model between the power supply quality indicators on the grid side and the load power flow on the traction side. The obtained power flow calculation results are used as data inputs to the correlation model to obtain the probability distribution data of the power supply quality on the grid side of the traction substation.

[0075] The situation prediction submodule is used to establish a database for evaluating the power supply capacity of the traction power supply system based on the solvable power quality compliance results of the power flow, thereby realizing a visual assessment of power supply capacity and completing the situation analysis and prediction of traction power supply capacity. It is also used to analyze and obtain the renewable energy power dispatch instructions within the prediction period through the established database for evaluating the power supply capacity of the traction power supply system and send them to the power generation data processing submodule. Through power flow calculation, the solvability of the power flow model and the compliance of the grid voltage at the end of the traction network are iteratively verified. If the solvability and compliance verifications are passed, the renewable energy power dispatch instructions are issued normally; otherwise, the renewable energy power dispatch instructions are readjusted.

[0076] Preferred, such as Figure 6 As shown, the distributed synchronous acquisition device includes a front-end signal input circuit, a clock synchronization circuit, a high-speed sampling and calculation circuit, and a data transmission interface; among which,

[0077] The front-end signal input circuit is connected to the high-speed sampling and calculation circuit via a control line. It receives electrical quantity acquisition signals, conditions them to filter out noise, and then transmits the conditioned signal to the high-speed sampling and calculation circuit. Specifically, the front-end signal input circuit includes: an external signal input terminal, a front-end converter, and a conditioning and filtering circuit. The external signal input terminal acquires electrical quantity acquisition signals and transmits them to the front-end converter. The front-end converter receives the electrical quantity acquisition signals, converts the current or high voltage signals into low voltage signals, and then sends them to the conditioning and filtering circuit. The conditioning and filtering circuit receives the low voltage signals, filters out high-frequency noise, and transmits the conditioned signal to the high-speed sampling and calculation circuit.

[0078] The clock synchronization circuit is used to obtain satellite signals from the GNSS receiver, condition the clock signals, and then transmit them to the high-speed sampling calculation circuit to achieve the synchronization of sampling among the acquisition devices. Specifically, the output of the GNSS receiver is connected to the clock discipline circuit. The clock discipline circuit de-jitters and keeps the satellite signals in time, and then outputs them to the high-speed parallel processor of the high-speed sampling calculation circuit through the control line to ensure that the sampling synchronization among the acquisition devices can still be guaranteed when the satellite signal is lost or abnormally jumps.

[0079] The high-speed sampling and calculation loop is used to receive and process electrical quantity acquisition signals, and includes: a parallel AD sampling module, a high-speed parallel processor, a program memory, a parameter memory, and a preprocessing data buffer;

[0080] The parallel AD sampling module is used to acquire input AD data in parallel and send the acquired data to the high-speed parallel processor through a serial transmission bus. The high-parallel processor temporarily stores the data in a preprocessing data buffer. After a preset timeout, it selects valid data from the preprocessing data buffer, performs operations with the data in the parameter memory, and puts the operation result into the sending queue to wait for packaging and sending. The program storage is used to save the program code and supports online system programming technology to update the program online.

[0081] Preferably, the data transmission interface is connected to the switch and is based on the Fast Ethernet transmission medium standard 100BASE-TX to send data to the outside world with a time granularity of 100ms, which meets the requirements of real-time situational awareness.

[0082] This solution, based on a high-precision synchronous acquisition device and a high-performance computing server, constructs a data-driven traction power supply capacity situational awareness system for new energy access. The system comprises an equipment layer, a measurement layer, a network layer, and a perception layer. The measurement layer, connected to the equipment layer via cables, measures and acquires synchronous sampling data from each device within the equipment layer. The perception layer, based on the acquired synchronous sampling data, generates power flow-resolved power quality compliance results, thereby establishing a database for evaluating the traction power supply system's power supply capacity. This enables visualized assessment of power supply capacity and completes traction power supply capacity situational analysis and prediction. This solution overcomes the limitations of existing SCADA systems with their limited functionality.

[0083] This application also provides a data-driven traction power supply capability situational awareness method, which utilizes the aforementioned data-driven perception layer traction power supply capability situational awareness system to perform traction power supply capability situational awareness. For example... Figure 7 As shown, the method includes the following steps:

[0084] S100 measures and obtains synchronous sampling data from each device in the equipment layer.

[0085] The measurement layer is connected to the equipment layer via cables and is used to measure and obtain synchronous sampling data collected by each device in the equipment layer. The network layer is connected to the measurement layer and the sensing layer via optical fibers. The synchronous sampling data obtained by the measurement layer is transmitted from the measurement layer to the sensing layer through the network layer.

[0086] S200 analyzes the synchronously sampled data to obtain the probability ranking data of new energy power generation within the prediction period.

[0087] First, based on the historical dataset of distributed renewable energy generation within the traction power supply system, a Bayesian probability model of the power generation output of multiple renewable energy systems is established. Real-time distributed renewable energy power flow data is obtained by analyzing the synchronously sampled data. Then, using the real-time distributed renewable energy power flow data as the data-driven input model, the probability ranking data of renewable energy power generation within the prediction period is generated.

[0088] S300 analyzes the synchronous sampling data to obtain grid voltage, harmonic data and traction substation power flow data, and then generates probability distribution data for predicting the power supply quality of the traction substation grid side.

[0089] First, the synchronous sampling data is analyzed to obtain the grid voltage and harmonic data and the traction power flow data;

[0090] Then, based on Vine-Copula theory, grid voltage and harmonic data, and traction substation power flow data, a correlation model between grid power supply and consumption quality indicators and traction side load flow is established. This model generates probability distribution data for predicting the power supply and consumption quality of the traction substation grid side and evaluates whether the average value of the distribution meets national standards.

[0091] S400 analyzes the synchronously sampled data to obtain node power flow, grid voltage data, and real-time state of charge data of energy storage devices. Based on the node power flow, grid voltage data, real-time state of charge data of energy storage devices, and the predicted probability distribution data of power supply quality on the grid side of the traction substation, it generates the power flow solvable power supply quality compliance result.

[0092] Analyzing the synchronously sampled data yields nodal power flow, grid voltage data, and real-time state of charge (SOC) data for energy storage devices. By combining the nodal power flow, grid voltage, and SOC data with the probability ranking data of renewable energy generation within the prediction period, a set of probability distributions for renewable energy generation is obtained. This set of probability distributions is then used as data-driven input to the traction power supply system's probabilistic power flow real-time simulation system. The traction power supply system's probabilistic power flow real-time simulation system is a traction power supply system SCADA (Supervisory Control And Data Acquisition) scheduling and monitoring system, a common simulation system in this field. Various existing simulation systems capable of this function exist, and those skilled in the art are familiar with the specific details, which will not be elaborated upon here. Using power flow calculation algorithms (such as the Newton-Raphson algorithm, or other algorithms, which are not limited here), multiple probabilistic power flow distribution scenarios within the prediction period are generated. The solvability of the system's power flow and the standardization of the traction network's terminal grid voltage under multiple scenarios are verified to obtain the power flow calculation results and the terminal grid voltage results.

[0093] The system obtains power flow calculation results and terminal grid voltage results to diagnose and generate power flow solvability and power quality compliance results. Specifically, if the power flow calculation result indicates that the power flow model is not solvable or the terminal grid voltage result indicates that the traction network terminal voltage does not meet the requirements, it indicates that the system power supply capacity is insufficient, and a power flow solvability and power quality compliance result is generated.

[0094] Preferably, the power flow calculation results can also be used as data drivers for the correlation model between the power grid's power supply and consumption quality indicators and the traction side load power flow, to obtain the probability distribution data of the predicted power supply and consumption quality of the traction substation's power grid side.

[0095] S500 establishes a database for evaluating the power supply capacity of the traction power supply system based on the power quality compliance results of the power flow solution, and then realizes a visual assessment of the power supply capacity, and completes the situation analysis and prediction of the traction power supply capacity.

[0096] Based on the power flow calculation results obtained in step S300 and the compliant power quality results of the solvable power flow, a database for evaluating the power supply capacity of the traction power supply system is established. This enables a visualized assessment of power supply capacity and facilitates the analysis and prediction of the traction power supply capacity situation. Furthermore, the database is used to analyze and obtain renewable energy power dispatch instructions within the prediction period and incorporate them into the situational understanding to iteratively verify the solvability of the power flow model and the compliance of the traction network's terminal voltage. If the solvability and compliance verifications are passed, the renewable energy power dispatch instructions are issued normally; otherwise, the renewable energy power dispatch instructions are readjusted.

[0097] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0098] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0099] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some service interface; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0100] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0101] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0102] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). 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 the 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 cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0103] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0104] The foregoing description is merely an exemplary embodiment of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Those skilled in the art will readily conceive of embodiments of this disclosure upon considering the specification and practicing the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described herein. The specification and embodiments are to be considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.

[0105] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0106] Those skilled in the art will readily understand that the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A data-driven based power supply capability situation awareness system for traction, characterized in that, It comprises a device layer, a measurement layer, a network layer and a perception layer; wherein, The measurement layer is connected with the device layer through a cable, and is used for obtaining synchronous sampling data of each device in the device layer; The network layer is connected with the measurement layer and the perception layer through optical fibers, and the synchronous sampling data obtained by the measurement layer is transmitted to the perception layer through the network layer; The perception layer is used for generating a power quality compliance result of power flow solvability according to the obtained synchronous sampling data, and further establishing a power supply capability evaluation system database of the traction power supply system, realizing visual evaluation of power supply capability, and completing analysis and prediction of the power supply capability situation; wherein, the perception layer comprises a situation awareness engine module, which comprises a power generation sub-data processing submodule, a verification submodule, a prediction distribution data submodule and a situation prediction submodule; wherein, The power generation sub-data processing submodule is used for receiving and analyzing the synchronous sampling data generated by the measurement layer to obtain new energy power generation probability ranking data in a prediction period, and sending the new energy power generation probability ranking data to the verification submodule; The prediction distribution data submodule is used for receiving and analyzing the synchronous sampling data generated by the measurement layer to obtain grid voltage, harmonic data and traction power flow data, and further generating power quality probability distribution data of the grid side of the traction power grid and sending the power quality probability distribution data to the verification submodule; The verification submodule receives and analyzes the synchronous sampling data generated by the measurement layer to obtain node power flow, grid voltage data and real-time state of charge data of energy storage devices, and generates the power quality compliance result of power flow solvability according to the node power flow, grid voltage data and real-time state of charge data of energy storage devices and the power quality probability distribution data of the grid side of the traction power grid; The situation prediction submodule is used for establishing a power supply capability evaluation system database of the traction power supply system according to the power quality compliance result of power flow solvability, and further realizing visual evaluation of power supply capability, and completing analysis and prediction of the power supply capability situation; The verification submodule comprises a synchronous data processing unit, an analysis unit, a calculation unit and a diagnosis unit; The synchronous data processing unit is used for receiving and analyzing the synchronous sampling data generated by the measurement layer to obtain node power flow, grid voltage data and real-time state of charge data of energy storage devices; The analysis unit is used for obtaining a probability distribution set by combining and analyzing the node power flow, grid voltage data, real-time state of charge data of energy storage devices and new energy power generation probability ranking data in a prediction period; The calculation unit is used for inputting the probability distribution set as data driving into a real-time simulation system of the traction power supply system probability power flow, and after solving and generating a plurality of probability power flow distribution scenarios in a prediction period, verifying the solvability of system power flow and the standardization of traction grid terminal voltage in multiple scenarios, obtaining power flow calculation results and terminal voltage results, and sending the power flow calculation results to the prediction distribution data submodule; The diagnosis unit is used for obtaining the power flow calculation results and terminal voltage results to diagnose and generate the power quality compliance result of power flow solvability.

2. A data-driven based traction power supply capability situation awareness system as claimed in claim 1, wherein, The prediction distribution data submodule comprises a synchronous data processing unit and a prediction model calculation unit, wherein, The synchronous data processing unit is configured to obtain power grid measurement network voltage and harmonic data and traction power flow data according to the received and analyzed synchronous sampling data generated by the measurement layer; The prediction model calculation unit is configured to obtain the power flow calculation result as input driving to generate the predicted traction power grid side power supply quality probability distribution data.

3. A data-driven based traction power supply capability situation awareness system as claimed in claim 1, wherein, The power generation amount sub-module includes a synchronous data processing unit and a power generation model calculation unit, wherein, The synchronous data processing unit is configured to receive and analyze the synchronous sampling data generated by the measurement layer to obtain real-time distributed new energy power flow data; The power generation model calculation unit is configured to generate new energy power generation amount probability ranking data in the prediction period based on the distributed new energy power generation historical data set in the traction power supply system.

4. The data-driven traction power supply capability situation awareness system according to claim 1, wherein, The device layer includes voltage transformers and current transformers in one or more of traction substations, partition substations, AT substations, and open-close substations in the traction power supply system, which are configured to obtain voltage and current measurement data to generate synchronous sampling data; or The measurement layer includes distributed synchronous acquisition devices deployed in one or more of traction substations, partition substations, AT substations, and open-close substations, which are connected to the voltage transformers and current transformers of the device layer through cables and are configured to acquire measurement data output by the device layer to generate real-time synchronous sampling data; Or The network layer includes optical fibers, which are connected to the data transmission interfaces of the synchronous acquisition devices in the measurement layer through optical fibers and are configured to transmit the synchronous sampling data obtained by the measurement layer to the perception layer in real time; The perception layer is connected to the network layer through optical fibers, and the perception layer includes a situation awareness engine module configured to receive and process the real-time synchronous sampling data, analyze the data, and output power supply capability situation evolution information to realize traction power supply capability situation understanding and prediction.

5. A data-driven based traction power supply capability situation awareness system as claimed in claim 1, wherein, The situation prediction submodule is further configured to analyze the new energy power dispatching instructions in the prediction period through the established traction power supply system power supply capability evaluation system database and send the instructions to the power generation amount sub-module for iterative verification.

6. A data-driven based traction power supply capability situation awareness system as claimed in claim 4, wherein, The distributed synchronous acquisition device includes a front-end signal input circuit, a clock synchronization circuit, a high-speed sampling calculation circuit, and a data transmission interface, wherein, The front-end signal input circuit is connected to the high-speed sampling calculation circuit through a control line and is configured to receive and filter out noise after conditioning the electrical quantity acquisition signal, and transmit the conditioned signal to the high-speed sampling calculation circuit; The clock synchronization circuit is configured to obtain satellite signals through a GNSS receiver, condition the clock signals, and transmit the conditioned clock signals to the high-speed sampling calculation circuit to realize synchronization of sampling among the acquisition devices; The high-speed sampling calculation circuit is configured to receive and process the electrical quantity acquisition signal; The data transmission interface is connected to a switch and is configured to realize external data transmission.

7. The data-driven based rail transit traction power supply capability situation awareness system of claim 1, wherein, The check submodule is further configured to check whether the system power flow solvability and the traction network terminal network voltage meet the standard requirements to obtain the power flow calculation result, and if the power flow model does not have solvability or the traction network terminal network voltage does not meet the requirements, it is determined that the system power supply capacity is insufficient, and the power flow calculation result is sent to the situation prediction submodule.

8. A data-driven traction power supply capability situation awareness method, which utilizes the traction power supply capability situation awareness system of any one of claims 1-7 to perform traction power supply capability situation awareness, characterized in that, The method comprises the following steps: Synchronous sampling data of each device in the equipment layer is obtained by measurement; The synchronous sampling data is analyzed to obtain grid network voltage, harmonic data and traction substation power flow data, and further to generate predicted traction substation grid-side power supply quality probability distribution data; The synchronous sampling data is analyzed to obtain node power flow, network voltage data and real-time state of charge data of the energy storage device, and the node power flow, network voltage data and real-time state of charge data of the energy storage device and the predicted traction substation grid-side power supply quality probability distribution data are used to generate the power flow solvable power supply quality compliance result; A traction power supply system power supply capacity evaluation system database is established according to the power flow solvable power supply quality compliance result, and further power supply capacity visualization evaluation is realized to complete traction power supply capacity situation analysis and prediction.

Images