Power grid-traction network resource collaborative evaluation method and system, and electronic equipment

Abstract

The invention relates to the technical field of electrified railway collaborative operation, and discloses a power grid-traction network resource collaborative evaluation method and system, and electronic equipment, and the method comprises the steps: collecting real-time data of a power grid side, a traction network side and a resource side, and carrying out the preprocessing of the real-time data, and obtaining a standardized data flow; based on the standardized data flow, adjustable potential models are established for traction load, regenerative braking energy, traction station energy storage and road area photovoltaic / wind power respectively, and the adjustable potential range of each resource is obtained; based on the adjustable potential model, performing dynamic optimization evaluation through an optimization algorithm to obtain an adjustable potential evaluation result and a scheduling strategy; outputting an adjustable potential evaluation result and a scheduling strategy; based on the scheduling policy, a peak load shifting, frequency response, or renewable energy consumption application is performed. According to the method, real-time operation information can be fused, multi-resource characteristics are planned as a whole, intraday dynamic evaluation and collaboration are realized, and the flexibility resource potential of a power grid-traction network system is fully excavated.

Description

Technical Field

[0001] This invention relates to the field of electrified railway cooperative operation technology, specifically to a method, system, and electronic equipment for collaborative assessment of power grid-traction network resources. Background Technology

[0002] With the rapid growth of electrified railway loads, their impulsive and random load characteristics have placed significant pressure on the safe operation of the power grid and power quality. Meanwhile, resources such as regenerative braking energy, energy storage systems, and adjustable loads distributed in the traction network system have not been fully utilized and transformed into flexible resources usable by the power grid. Existing technologies mainly have the following limitations:

[0003] Traditional methods for assessing adjustable potential are mostly based on static assessments of typical daily curves, failing to consider real-time changes such as dynamic adjustments to daily train schedules and fluctuations in renewable energy, resulting in significant discrepancies between assessment results and actual operating conditions.

[0004] For a long time, the power grid and traction network systems have been operated and managed independently, lacking unified and collaborative modeling of their resources. This isolated management model has led to problems such as low utilization of regenerative braking energy, uncoordinated scheduling of energy storage systems, and insufficient utilization of load regulation capabilities.

[0005] Existing technologies fail to fully utilize real-time information such as traction substation status perception data and ultra-short-term load forecasts, making it impossible to achieve online dynamic updates of potential assessment results and failing to meet the requirements of real-time grid dispatch for accuracy and response speed.

[0006] Therefore, this application provides a method for collaborative evaluation of power grid and traction network resources to solve the above-mentioned technical problems. Summary of the Invention

[0007] The purpose of this invention is to provide a method, system, and electronic device for collaborative evaluation of power grid-traction network resources, in order to solve the technical problem that the existing technology cannot fully tap the flexibility resource potential of the power grid-traction network system.

[0008] To address the aforementioned technical problems, this invention provides a method for coordinated assessment of power grid and traction network resources, comprising:

[0009] Real-time data from the power grid side, traction network side, and resource side are collected and preprocessed to obtain a standardized data stream. The power grid side data includes active power demand and frequency signals, the traction network side data includes train operation status and operation plan, and the resource side data includes energy storage charge status and renewable energy output.

[0010] Based on the standardized data stream, adjustable potential models are established for traction load, regenerative braking energy, traction substation energy storage, and roadside photovoltaic / wind power, respectively, to obtain the adjustable potential range of each resource. The adjustable potential model quantifies the active power regulation capability and handles the coupling relationship between each resource.

[0011] Based on the adjustable potential model, dynamic optimization evaluation is performed through optimization algorithms to obtain adjustable potential evaluation results and scheduling strategies. The optimization algorithms adopt model predictive control or mixed integer linear programming, and the optimization objectives include minimizing the peak-valley difference of the power grid and maximizing the consumption of renewable energy.

[0012] Output the adjustable potential assessment results and scheduling strategy, wherein the adjustable potential assessment results include adjustable potential curves and statistical indicators, and the scheduling strategy includes real-time control instructions for each resource;

[0013] Based on the aforementioned scheduling strategy, peak shaving and valley filling, frequency response, or renewable energy consumption applications are implemented.

[0014] In some specific embodiments, real-time data from the power grid side, traction network side, and resource side are collected, and the real-time data is preprocessed to obtain a standardized data stream; wherein, the power grid side data includes active power demand and frequency signals, the traction network side data includes train operating status and operating plans, and the resource side data includes energy storage charge status and renewable energy output, further including:

[0015] Collect active power demand, frequency signals and dispatch instructions from the power grid side; collect train position, speed, braking status, load curve and operation plan from the traction network side; and collect energy storage charge status, measured values ​​of renewable energy output and weather information from the resource side.

[0016] The collected real-time data is cleaned, and filtering algorithms are used to process measurement noise and abnormal data. A method based on historical data patterns is used to fill in missing data.

[0017] Short-term forecasts are made on the cleaned data using time series analysis models or deep learning network models to predict the traction load change trend, spatiotemporal distribution of regenerative braking energy, and fluctuation characteristics of renewable energy output in future operating cycles.

[0018] The multi-source heterogeneous prediction data and real-time monitoring data are normalized in a unified format to generate a standardized data stream.

[0019] In some specific embodiments, based on the standardized data stream, establishing an adjustable potential model for the traction load further includes:

[0020] Based on the standardized data stream, train operation status data and operation plan data are analyzed;

[0021] An adjustable power model for traction load is established, and the adjustable power is defined as the algebraic sum of the power adjustments of each train in the discrete time series. The power adjustment is achieved through departure time optimization, speed curve adjustment and operation plan rearrangement.

[0022] Set multi-dimensional operating constraints, including minimum safe departure interval limit, maximum allowable timetable offset range, speed operating range limit and traction motor power output limit;

[0023] Based on the power adjustment amount and operating constraints, the dynamic upper and lower limits of the adjustable potential are determined, and the traction load adjustable potential model is integrated into the multi-resource model in a linear combination manner.

[0024] In some specific embodiments, establishing an adjustable potential model for regenerative braking energy further includes:

[0025] Based on the standardized data stream, train braking status feature data, spatial position data, and real-time speed data are extracted;

[0026] An adjustable power model for regenerative braking energy is established, and the adjustable power is defined as the product of the braking power of each train and the dynamically calibrated recovery efficiency coefficient, wherein the recovery efficiency coefficient is updated in real time according to the equipment operating status.

[0027] Set multi-level utilization constraints, including direct utilization priority rules within the same power supply section, maximum charging power limit of energy storage system, and technical standards for grid feedback interface;

[0028] Based on the adjustable power distribution in time and space and the constraints, the upper and lower limits of the adjustable potential are determined, and the adjustable potential model of regenerative braking energy is integrated into the multi-resource model with a power balance relationship.

[0029] In some specific embodiments, establishing an adjustable potential model for traction substation energy storage further includes:

[0030] Based on the standardized data stream, acquire dynamic data of charge state of the energy storage system, historical data of charge and discharge power, and ambient temperature data.

[0031] Establish an adjustable active power model for energy storage, define the adjustable power as the algebraic difference between charging power and discharging power, and construct charge state recursive equations for charging and discharging efficiency and energy conservation.

[0032] Set multiple types of operating constraints, including maximum charge and discharge power limits, safe operating range for charge state, performance limits under temperature influence, and cycle life decay protection mechanisms;

[0033] The upper and lower limits of the adjustable potential are determined based on the real-time charging and discharging power capability and operating constraints. The energy storage adjustable potential model is then integrated into the multi-resource model in an energy buffer manner.

[0034] In some specific embodiments, establishing an adjustable potential model for roadside photovoltaic / wind power further includes:

[0035] Based on the standardized data stream, renewable energy output monitoring data, weather forecast data, and power electronic equipment parameters are acquired.

[0036] A photovoltaic wind power active power adjustable model is established, and the adjustable power is defined as the controllable deviation between the actual output and the predicted reference output. The reference output is calculated by physical characteristic equations.

[0037] Set equipment operating constraints, including the maximum available output limit determined by meteorological conditions, the maximum conversion power limit of the inverter, the wind speed range limit of the wind turbine, and the grid reverse power protection limit;

[0038] The upper and lower limits of the adjustable potential are determined based on the power output adjustment capacity and equipment constraints, and the photovoltaic and wind power adjustable potential model is integrated into the multi-resource model in a power compensation manner.

[0039] In some specific embodiments, based on the adjustable potential model, dynamic optimization evaluation is performed through an optimization algorithm to obtain the adjustable potential evaluation result and scheduling strategy. The optimization algorithm employs model predictive control or mixed-integer linear programming, and the optimization objectives include minimizing the grid peak-to-valley difference and maximizing renewable energy consumption. Further, it includes:

[0040] A multi-objective optimization function system is established, including grid load optimization objectives based on power balance and renewable energy consumption objectives considering fluctuation characteristics;

[0041] Set complete system constraints, including constraints on the electrical safety operation of the traction network, constraints on the reliability of train services, constraints on the physical limitations of resources, and constraints on the cooperative coupling of multiple resources;

[0042] A model predictive control framework is used for rolling time window optimization, and a mixed-integer linear programming algorithm is used to handle combinations of discrete and continuous decision variables.

[0043] The output optimization results include dynamic curves of the adjustable potential of future time series and coordination and scheduling strategies for each resource.

[0044] Based on the same concept, the present invention also provides a power grid-traction network resource collaborative assessment system, comprising:

[0045] The data acquisition and preprocessing module is configured to collect real-time data from the power grid side, traction network side, and resource side, and preprocess the real-time data to obtain a standardized data stream. Among them, the power grid side data includes active power demand and frequency signals, the traction network side data includes train operation status and operation plan, and the resource side data includes energy storage charge status and renewable energy output.

[0046] The adjustable potential model building module is configured to build adjustable potential models for traction load, regenerative braking energy, traction substation energy storage and roadside photovoltaic / wind power based on the standardized data stream, so as to obtain the adjustable potential range of each resource. The adjustable potential model quantifies the active power regulation capability and handles the coupling relationship between each resource.

[0047] The dynamic optimization evaluation module is configured to perform dynamic optimization evaluation based on the adjustable potential model through an optimization algorithm to obtain the adjustable potential evaluation result and scheduling strategy. The optimization algorithm adopts model predictive control or mixed integer linear programming, and the optimization objectives include minimizing the peak-valley difference of the power grid and maximizing the consumption of renewable energy.

[0048] The evaluation result and scheduling strategy output module is configured to output the adjustable potential evaluation result and scheduling strategy, wherein the adjustable potential evaluation result includes an adjustable potential curve and statistical indicators, and the scheduling strategy includes real-time control instructions for each resource.

[0049] The scheduling strategy execution module is configured to perform peak shaving and valley filling, frequency response, or renewable energy consumption applications based on the scheduling strategy.

[0050] Based on the same concept, the present invention also provides an electronic device, including: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of a power grid-traction network resource collaborative evaluation method.

[0051] Based on the same concept, the present invention also provides a computer-readable storage medium storing a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of a power grid-traction network resource collaborative assessment method.

[0052] Compared with existing technologies, its advantages are as follows:

[0053] This invention discloses a method, system, and electronic equipment for coordinated assessment of power grid and traction network resources, achieving unified modeling and coordinated optimization of multiple resources. By establishing a unified adjustable potential model that includes traction load, regenerative braking energy, traction substation energy storage, and roadside photovoltaic / wind power, it overcomes the shortcomings of isolated resource management in traditional technologies. This model focuses on active power management, simplifies the complex reactive power or voltage control problems in traditional methods, and improves the model's practicality and computational efficiency.

[0054] Improved assessment accuracy and real-time performance: Dynamic assessment is performed based on real-time information at the second to minute level, and rolling optimization is carried out using a model predictive control framework. This can adapt to real-time changes in power grid fluctuations and traction network demand, effectively reducing assessment errors caused by prediction uncertainties.

[0055] Enhancing system flexibility and stability: By introducing flexible adjustment of the operation plan as the core mechanism for traction load regulation, proactive response capabilities of demand-side resources are achieved. Combined with the spatiotemporal coordinated management of regenerative braking energy and the rapid power support of energy storage, load fluctuations are effectively mitigated, and the stability of grid operation is improved.

[0056] Improving energy efficiency and economy: By optimizing the utilization path of regenerative braking energy and the charging and discharging strategies of energy storage systems, energy waste is reduced. Simultaneously, through multi-resource coordinated scheduling, goals such as peak shaving and valley filling, and maximizing the absorption of renewable energy are achieved, reducing grid reserve requirements and lowering overall system operating costs. Attached Figure Description

[0057] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0058] Figure 1 This is a flowchart illustrating some specific embodiments of the power grid-traction network resource collaborative assessment method of the present invention;

[0059] Figure 2 This is a schematic diagram of the structure of a power grid-traction network resource collaborative assessment system according to some specific embodiments of the present invention;

[0060] Figure 3 This is a schematic diagram of the structure of an electronic device according to some specific embodiments of the present invention;

[0061] In the diagram, 710 is the processor; 720 is the memory; 730 is the input device; and 740 is the output device. Detailed Implementation

[0062] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0063] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the application. The singular forms “a,” “said,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0064] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0065] It should be understood that although the terms first, second, third, etc., may be used in the embodiments of this application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, first may also be referred to as second without departing from the scope of the embodiments of this application, and similarly, second may also be referred to as first.

[0066] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0067] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the article or device that includes said element.

[0068] It should be noted that any symbols and / or numbers present in the specification that are not marked in the accompanying drawings are not reference numerals.

[0069] Reference Figure 1 A method for collaborative assessment of power grid and traction network resources, comprising:

[0070] S101, collect real-time data from the power grid side, traction network side, and resource side, and preprocess the real-time data to obtain a standardized data stream; wherein, the power grid side data includes active power demand and frequency signals, the traction network side data includes train operation status and operation plan, and the resource side data includes energy storage charge status and renewable energy output;

[0071] S102, Based on the standardized data stream, establish adjustable potential models for traction load, regenerative braking energy, traction substation energy storage and roadside photovoltaic / wind power respectively, and obtain the adjustable potential range of each resource. The adjustable potential model quantifies the active power regulation capability and handles the coupling relationship between each resource.

[0072] S103, Based on the adjustable potential model, dynamic optimization evaluation is performed through optimization algorithm to obtain adjustable potential evaluation results and scheduling strategy. The optimization algorithm adopts model predictive control or mixed integer linear programming, and the optimization objectives include minimizing the peak-valley difference of the power grid and maximizing the consumption of renewable energy.

[0073] S104, output the adjustable potential assessment result and scheduling strategy, wherein the adjustable potential assessment result includes the adjustable potential curve and statistical indicators, and the scheduling strategy includes real-time control instructions for each resource;

[0074] S105, based on the scheduling strategy, perform peak shaving and valley filling, frequency response, or renewable energy consumption applications.

[0075] Specifically, in this embodiment of the invention, a multi-source data acquisition system is established. Real-time operational data, including active power demand and frequency signals, is acquired from the power grid side; dynamic data, including train position, speed, braking status, and operating plans, is acquired from the traction network side; and status information, including energy storage charge status and renewable energy output, is acquired from the resource side. The acquired raw data undergoes sequential data cleaning, short-term forecasting, and data normalization. Data cleaning uses filtering algorithms to identify and process abnormal data points; short-term forecasting uses a time series analysis model to generate prediction curves for future time periods; and data normalization converts multi-source heterogeneous data into a standardized data stream with unified dimensions. Based on the standardized data stream, adjustable potential models for traction load, regenerative braking energy, traction depot energy storage, and roadside photovoltaic / wind power are constructed. The traction load model quantifies the power adjustment range by analyzing adjustments to train operating parameters; the regenerative braking energy model calculates adjustable power by multiplying braking power by the efficiency coefficient; the energy storage model determines the charging and discharging power boundary based on the charge state dynamic equation; and the renewable energy model defines the adjustable power range through an output adjustment mechanism. The models are collaboratively correlated through power balance relationships and spatiotemporal coupling constraints. Based on the characteristics of the optimization problem, a Model Predictive Control (MPC) framework is adopted for dynamic optimization evaluation. A multi-objective function is constructed, encompassing minimizing the peak-to-valley difference in the power grid and maximizing renewable energy absorption. Considering operational safety constraints and resource physical limitations, the optimal scheduling strategy is solved within a rolling time window. The length and update cycle of the rolling time window can be set according to different resource characteristics and scheduling requirements. The output includes evaluation results containing adjustable potential curves and statistical indicators, as well as a scheduling strategy containing real-time control commands for each resource. Practical applications such as peak shaving and valley filling, frequency response, and renewable energy absorption are executed through the system interface.

[0076] In some applications, real-time data from the power grid, traction network, and resource side are collected and preprocessed to obtain a standardized data stream. The power grid data includes active power demand and frequency signals; the traction network data includes train operating status and operating plans; and the resource side data includes energy storage charge status and renewable energy output. This includes collecting active power demand, frequency signals, and dispatch instructions from the power grid; collecting train position, speed, braking status, load curves, and operating plans from the traction network; and collecting energy storage charge status, measured renewable energy output, and weather information from the resource side. The collected real-time data undergoes data cleaning, using filtering algorithms to process measurement noise and abnormal data, and employing interpolation methods based on historical data patterns to fill in missing data. Short-term forecasts are performed on the cleaned data using time series analysis models or deep learning network models to predict future operating cycle trends in traction load, spatiotemporal distribution of regenerative braking energy, and fluctuation characteristics of renewable energy output. The multi-source heterogeneous forecast data and real-time monitoring data are then normalized to a unified format to generate a standardized data stream.

[0077] Understandably, a complete data acquisition network covering the power grid, traction network, and resource side is constructed. This network continuously acquires operational parameters from the power grid, including active power demand, frequency signals, and dispatch instructions. It simultaneously acquires dynamic operational data from the traction network, including train position, speed, braking status, load curves, and operation schedules. From the resource side, it monitors status parameters in real time, including energy storage charge status, measured renewable energy output, and weather information. The raw data stream undergoes multi-level processing. A data cleaning module based on filtering algorithms eliminates measurement noise and identifies abnormal data points. An interpolation algorithm based on historical data patterns fills in missing data caused by equipment failures or communication interruptions. Short-term predictions are made on the cleaned data using time series analysis models or deep learning network models, generating traction load change trend curves, spatiotemporal distribution maps of regenerative braking energy, and renewable energy output fluctuation characteristic curves for future operating cycles. A unified-format normalization processing engine converts multi-source heterogeneous prediction data and real-time monitoring data into a standardized data stream with the same dimensions and data structure, providing standardized data input for subsequent modeling.

[0078] In some applications, an adjustable potential model for traction load is established based on the standardized data stream. This includes parsing train operation status data and operation plan data based on the standardized data stream; establishing an adjustable power model for traction load, defining adjustable power as the algebraic sum of power adjustments for each train in a discrete time series, wherein the power adjustment is achieved through departure time optimization, speed curve adjustment, and operation plan rearrangement; setting multi-dimensional operation constraints, including minimum safe departure interval limits, maximum allowable timetable offset range, speed operation interval limits, and traction motor power output limits; determining the dynamic upper and lower limits of adjustable potential based on power adjustments and operation constraints; and integrating the adjustable potential model of traction load into a multi-resource model in a linear combination manner.

[0079] Understandably, this involves parsing standardized data streams to obtain operational status data including train position, speed, and braking status, as well as operational plan data including timetables and departure intervals; establishing an adjustable power model for traction load, defining adjustable power as the algebraic sum of power adjustments for each train relative to the baseline operational plan over discrete time series. Power adjustment is achieved collaboratively through three mechanisms: optimized departure time adjustment, smoothed speed curve adjustment, and intelligent operational plan rearrangement; setting a multi-dimensional operational constraint system, including minimum safe departure interval limits to ensure operational safety, maximum allowable timetable offset range to guarantee service quality, speed operating range limits conforming to operational specifications, and traction motor power output limits based on equipment capabilities; determining the dynamic upper and lower limits of adjustable potential based on the calculated power adjustment values ​​and operational constraint boundaries; and finally integrating the traction load adjustable potential model into a multi-resource collaborative optimization model through linear combination.

[0080] In some applications, an adjustable potential model for regenerative braking energy is established, including extracting train braking state characteristic data, spatial location data, and real-time speed data based on the standardized data stream; establishing an adjustable power model for regenerative braking energy, defining the adjustable power as the product of the braking power of each train and the dynamically calibrated recovery efficiency coefficient, which is updated in real time according to the equipment operating status; setting multi-level utilization constraints, including direct utilization priority rules within the same power supply section, maximum charging power limits of the energy storage system, and technical standards for the grid feedback interface; determining the upper and lower limits of the adjustable potential based on the spatiotemporally distributed adjustable power and utilization constraints; and integrating the adjustable potential model of regenerative braking energy into a multi-resource model based on power balance relationships.

[0081] Understandably, this involves extracting braking state characteristic data, including train braking event features, deceleration rate of change, and braking duration, based on standardized data streams. This data is then combined with the train's spatial position coordinates and real-time speed change curves within the power supply section. An adjustable power model for regenerative braking energy is established, defining the adjustable power as the product of each train's braking power and a dynamically calibrated recovery efficiency coefficient. This recovery efficiency coefficient is updated in real-time based on the traction motor's operating temperature, inverter aging, and line impedance characteristics. Multi-level utilization constraints are set, including priority rules for the nearby utilization of regenerative energy within the same power supply section, the maximum acceptable charging power limit for the energy storage system, and feedback interface technical specifications that meet grid power quality standards. Based on the distribution characteristics of braking energy in time and space dimensions, combined with the utilization constraints, the upper and lower limits of the adjustable potential are determined. Finally, the adjustable potential model of regenerative braking energy is integrated into a multi-resource collaborative optimization model through power balance relationships.

[0082] In some applications, an adjustable potential model is established for traction substation energy storage. This includes acquiring dynamic data on the charge state of the energy storage system, historical data on charge and discharge power, and ambient temperature data based on the standardized data stream; establishing an adjustable active power model for energy storage, defining the adjustable power as the algebraic difference between charging power and discharging power, and constructing charge state recursive equations for charge and discharge efficiency and energy conservation; setting multiple types of operating constraints, including maximum charge and discharge power limits, safe operating range for charge state, performance limitations under temperature influence, and cycle life decay protection mechanisms; determining the upper and lower limits of adjustable potential based on real-time charge and discharge power capabilities and operating constraints; and integrating the adjustable potential model of energy storage into a multi-resource model in an energy buffer manner.

[0083] Understandably, the process involves acquiring dynamic changes in the state of charge (SPC) of the energy storage system, historical operating data of charge and discharge power, and ambient temperature monitoring data based on standardized data streams; establishing an adjustable active power model for energy storage, defining adjustable power as the algebraic difference between charging and discharging power, and constructing a recursive equation for SPC that considers charge-discharge conversion efficiency and the law of conservation of energy; setting multiple types of operational constraints, including maximum charge-discharge power limits based on equipment rated parameters, a safe operating range for SPC to ensure safe operation, performance limitations considering temperature effects, and a cycle life degradation protection mechanism to protect battery health; determining the dynamic upper and lower limits of adjustable potential based on real-time charge-discharge power capabilities and operational constraints; and finally integrating the adjustable potential model of energy storage into a multi-resource collaborative optimization model using an energy buffer approach.

[0084] In some applications, adjustable potential models for roadside photovoltaic / wind power are established, including acquiring renewable energy output monitoring data, weather forecast data, and power electronic equipment parameters based on the standardized data stream; establishing an adjustable active power model for photovoltaic and wind power, defining adjustable power as the controllable deviation between actual output and predicted baseline output, wherein the baseline output is calculated through physical characteristic equations; setting equipment operating constraints, including the maximum available output limit determined by weather conditions, the maximum conversion power limit of the inverter, the wind speed range limit for wind turbine operation, and the grid reverse power protection limit; determining the upper and lower limits of adjustable potential based on output adjustment capability and equipment constraints, and integrating the photovoltaic and wind power adjustable potential model into the multi-resource model in a power compensation manner.

[0085] Understandably, this involves acquiring renewable energy output monitoring data (including real-time output values, historical output curves, and current operating status) based on standardized data streams; meteorological forecast data (including irradiance, temperature, wind speed, and cloud cover predictions); and power electronic equipment parameters (including rated power, efficiency curves, and operating parameters). A photovoltaic and wind power adjustable active power model is established, defining adjustable power as the controllable deviation between actual output and the predicted baseline output calculated using physical characteristic equations. The photovoltaic baseline output is calculated using the irradiance-power characteristic equation, and the wind power baseline output is calculated using the wind speed-power characteristic equation. Equipment operating constraints are set, including maximum available output limits determined by real-time meteorological conditions, power conversion limits determined by inverter capacity, wind speed range limits to meet wind turbine safety operation requirements, and reverse power protection limits to prevent grid backflow. Dynamic upper and lower limits of the adjustable potential are determined based on the actual output adjustment capability and equipment constraints. Finally, the photovoltaic and wind power adjustable potential model is integrated into a multi-resource collaborative optimization model using a power compensation method.

[0086] In some applications, based on the adjustable potential model, dynamic optimization evaluation is performed using optimization algorithms to obtain adjustable potential evaluation results and scheduling strategies. The optimization algorithms employ model predictive control or mixed-integer linear programming. Optimization objectives include minimizing the peak-to-valley difference in the power grid and maximizing renewable energy absorption. This involves setting a multi-objective optimization function system, including a power grid load optimization objective based on power balance and a renewable energy absorption objective considering fluctuation characteristics; setting complete system constraints, including constraints on the electrical safety operation of the traction network, train service reliability, resource physical limitations, and multi-resource collaborative coupling; using a model predictive control framework for rolling time window optimization; and employing mixed-integer linear programming algorithms to handle combinations of discrete and continuous decision variables. The output optimization results include the dynamic curve of adjustable potential for future time series and the coordinated scheduling strategies for each resource.

[0087] Understandably, a multi-objective optimization function system is established, encompassing both grid load optimization and renewable energy consumption objectives. The grid load optimization objective is constructed based on the power balance principle, smoothing the grid load curve by adjusting the output of multiple resources. The renewable energy consumption objective considers the fluctuation characteristics of photovoltaic and wind power to maximize the utilization rate of clean energy. Secondly, complete system constraints are set, including constraints on the safe operation of traction grid voltage and current, service reliability constraints on train punctuality rate and minimum departure interval, physical constraints on the power capacity and energy storage of each resource, and synergistic coupling constraints on power allocation and timing coordination among multiple resources. Based on the characteristics of the optimization problem, a rolling time window optimization framework is chosen, updating the optimization problem based on the latest data at each decision point, or a mixed-integer linear programming (MILP) algorithm is used to simultaneously process discrete decision variables such as departure time adjustment and continuous decision variables such as power allocation. The output includes the dynamic change curve of adjustable potential in future time periods and the optimization results of resource coordination schemes.

[0088] The following describes another embodiment of the power grid-traction network resource collaborative assessment method of the present invention:

[0089] In this embodiment, a hierarchical modular design is adopted, which achieves accurate quantification of adjustable potential within a day (usually within 24 hours) through four core layers: real-time data acquisition, multi-resource modeling, dynamic optimization evaluation, and result output.

[0090] Resource Integration: Regenerative braking energy, traction load (including flexible adjustments to the operation plan), traction substation energy storage, and regional photovoltaic / wind power are modeled in a unified manner within the traction network, focusing on active power and energy management to avoid complex reactive power or voltage control issues. Real-time Dynamics: Based on second- to minute-level real-time information (such as load, weather, and operating status), the evaluation results are dynamically updated to adapt to grid fluctuations and traction network demands. Optimization-Driven: Model predictive control (MPC) is used for rolling optimization to maximize adjustable potential while ensuring safety constraints; for optimization problems involving discrete decision variables (such as departure time adjustments and energy storage switch states), mixed-integer linear programming (MILP) can be employed.

[0091] Detailed architecture components:

[0092] Real-time Data Acquisition and Preprocessing Layer: Acquires multi-source real-time data and performs cleaning, normalization, and short-term forecasting. Data Sources: Grid Side: Active power demand, frequency signals, dispatch instructions. Traction Network Side: Train position, speed, braking status (for regenerative braking energy), load curve, operation schedule. Resource Side: Energy storage SOC (state of charge), measured PV / wind power output data, weather information (such as irradiance, wind speed). Preprocessing Module: Data Cleaning: Removes outliers and fills in missing data. Short-Term Forecasting: Uses ARIMA or machine learning models (such as LSTM) to predict traction load, regenerative braking energy, and PV / wind power output for the next 15 minutes to 4 hours. Output: Standardized data stream for use by upper-layer models.

[0093] Multi-resource adjustable potential modeling layer: Establishes an active power adjustable potential model for each type of resource, quantifying its dynamic adjustment capability. Traction load model: Based on flexible adjustments to the operation plan (such as departure interval optimization and speed control), quantifies its active power adjustable range.

[0094] Mathematical expression: Adjustable potential , where N represents the total number of trains included. This represents the power adjustment (in kW) of the i-th train at time t relative to the baseline operating plan. A positive value indicates an increase in load, and a negative value indicates a decrease in load. t represents a discrete time variable, in minutes or seconds. This represents the total active power adjustment of the traction load that can be achieved by adjusting the operating plan at time t.

[0095] Regenerative braking energy model: quantifies the energy fed back to the traction network when the train brakes, taking into account recovery efficiency and spatiotemporal distribution.

[0096] Mathematical expression: Adjustable potential ,in For recycling efficiency, Let M be the braking energy of the j-th train. M represents the total number of trains in braking condition. This represents the total adjustable regenerative braking power at time t.

[0097] Traction substation energy storage model: Based on a battery energy storage system, the model includes charging / discharging power and energy limitations. Mathematical expression: Defines the adjustable variable of energy storage active power. ,in >0 indicates discharge. <0 indicates charging; the adjustable potential is dynamically constrained by SOC (state of charge), and the SOC update equation is:

[0098] ;

[0099] in: The charging power (kW) at time t is negative.

[0100] Let be the discharge power (kW) at time t, and take a positive value;

[0101] Charging efficiency (dimensionless, typical value 0.95);

[0102] Discharge efficiency (dimensionless, typical value 0.97);

[0103] For time intervals (hours);

[0104] Rated energy storage capacity (kWh).

[0105] Adjustable potential range: The upper and lower limits of the adjustable potential are subject to the SOC safety range (e.g., ) and power limitation constraints, specifically defined as (Minimum adjustable power, corresponding to maximum charging) and (Maximum adjustable power, corresponding to maximum discharge).

[0106] Regional PV / Wind Power Model: Based on inverter control, the model's output is adjustable (e.g., limited or increased generation). Mathematical expression: Adjustable potential. ,in To maximize available output, Output power as a benchmark.

[0107] Integrated model: Total adjustable potential Considering resource coupling (such as prioritizing the use of regenerative braking energy for energy storage charging), where, This represents the adjustable variable of active power in energy storage.

[0108] Dynamic Optimization Evaluation Layer: Based on real-time data and resource models, optimization algorithms are used to dynamically evaluate adjustable potential and generate scheduling strategies. Optimization Objectives: Maximize intraday adjustable potential utility; minimize grid peak-to-valley difference; maximize renewable energy absorption; minimize operating costs. Constraints: Operational safety: traction grid voltage and current limits; train operation reliability (e.g., minimum departure interval). Resource constraints: energy storage SOC range, photovoltaic / wind power output boundaries, load adjustment range. Optimization Algorithm: Based on the characteristics of the optimization problem, Model Predictive Control (MPC) is selected for rolling optimization. The rolling time window length and update cycle can be set according to scheduling requirements. For optimization problems involving discrete decision variables (e.g., departure time adjustment, energy storage switch status), Mixed Integer Linear Programming (MILP) can be used. Output: Dynamic adjustable potential curve. And the optimal scheduling plan for each resource.

[0109] Results Output and Application Layer: Visualize the evaluation results and interface with the power grid dispatching system or traction network control system. Output Content: Adjustable potential indicators: such as maximum / minimum adjustable power, duration, and total energy. Dispatch Suggestions: Real-time control commands for each resource (such as energy storage charging and discharging power, train operation adjustments). Application Interface: Send the results to the power grid dispatching center via API or SCADA system for peak shaving and valley filling or frequency response. Feedback is then sent to the traction network intelligent control system to execute resource scheduling.

[0110] Traction load assessment method:

[0111] Traction load adjustability is defined as the ability, within an electrified railway traction network, to proactively adjust the active power of the traction load by flexibly adjusting train operation plans (such as departure intervals, speed curves, and timetable offsets) while meeting operational safety and passenger service constraints. This potential supports applications such as peak shaving and valley filling, frequency response, and renewable energy integration for the power grid. The core of the assessment lies in quantifying the adjustable range of the load (unit: kW or MW) and generating dynamic dispatch instructions.

[0112] The evaluation process is based on real-time data and adopts a hierarchical optimization architecture, including four stages: data acquisition, modeling, optimization calculation, and result output.

[0113] Real-time data acquisition and preprocessing: Collect real-time information such as train operating status and grid demand, and perform data cleaning and short-term forecasting. Adjustable potential modeling: Establish a mathematical model of traction load, and define the adjustable power range and its constraints. Dynamic optimization evaluation: Calculate the adjustable potential using optimization algorithms, considering multi-resource coordination. Result output and application: Generate adjustable potential curves and scheduling recommendations, and interface with the power grid or traction network control system.

[0114] Data Acquisition and Preprocessing: Data Input: Real-time Data: Train position, speed, acceleration, braking status, current active power demand (obtained through the traction substation monitoring system). Operational Plan Data: Predefined timetables, departure intervals, station dwell times, line topology (e.g., gradient, curve radius). Grid Interaction Data: Grid dispatching instructions (e.g., active power demand signals), frequency deviation information. External Data: Weather information (affecting train running resistance), passenger flow forecasts (used for service constraints).

[0115] Preprocessing: Data cleaning: Outliers are removed using filtering algorithms (such as Kalman filtering), and missing data is imputed (e.g., by interpolating with historical means). Short-term forecasting: Time series models (such as ARIMA) or machine learning models (such as LSTM) are used to forecast the traction load base curve (unadjusted state) and operating status changes for the next 15 minutes to 2 hours. Forecast output includes: base load power. Train arrival / departure time probability distribution. Normalization: Standardizing the data into a uniform format to facilitate model processing.

[0116] Adjustable potential modeling: The adjustable potential of traction load is achieved by adjusting train operating parameters, and is modeled as the sum of the power adjustments for each train. Key variables and constraints are defined: Mathematical model: Assume the system has N trains, and time is discretized as... (For example, at 1-minute intervals). For the i-th train, define adjustable power. (Unit: kW) represents the amount of power change relative to a baseline operating plan achieved through operational adjustments over time t. Positive values ​​indicate increased load (e.g., acceleration), and negative values ​​indicate decreased load (e.g., deceleration or delay). Traction load adjustable potential. Defined as the sum of the power adjustments of all trains in the system at time t, i.e. It characterizes the adjustable power of the traction load at time t.

[0117] Adjustment Mechanisms and Constraints: Train Departure Interval Optimization: By adjusting train departure times, peak load can be altered. For example, increasing departure intervals can reduce instantaneous load. Constraint: Minimum departure interval (For example, two minutes), maximum permissible delay (For example, 5 minutes). Mathematical expression: Let the original planned departure time be... After adjustment, it is: ,but ,and For adjacent trains .

[0118] Speed ​​control: By adjusting the train speed curve, the active power demand is changed. Deceleration reduces power, while acceleration increases power (but is limited by motor capacity). Constraints: Speed ​​range. Acceleration / deceleration rate limit ;

[0119] Power adjustment amount correlation: , where f is the train power characteristic function (which can be calibrated through experiments or simulations). This represents the instantaneous speed of the i-th train at time t. Let represent the instantaneous acceleration of the i-th train at time t.

[0120] Flexible operation plan adjustments: Allows for minor timetable shifts or task reassignment (e.g., merging low-passenger-flow trains). Constraints: Service reliability metrics (e.g., passenger waiting times not exceeding thresholds). Physical constraints: Maximum / minimum train power limits. ;

[0121] Energy conservation: Adjustments should not lead to a significant increase in total energy consumption (this can be expressed through integral constraints). Adjustable potential range: Define the upper and lower limits of the adjustable potential. Among them, the lower limit Maximum load reduction capacity (through deceleration or delay), upper limit To maximize load capacity (by accelerating or starting the train earlier).

[0122] Dynamic optimization assessment: Based on real-time data and models, optimization algorithms are used to calculate the adjustable potential, ensuring synergy with resources such as regenerative braking energy and energy storage. Optimization objectives: Main objective: Maximize the utility of the adjustable potential, for example: supporting grid peak shaving and valley filling: minimizing the load peak-valley difference; or responding to grid commands: tracking the target power curve. (From power grid dispatch) Format (example): ;in This includes the total adjustable potential of multiple resources, including traction load.

[0123] Optimization Algorithm: Based on the response characteristics of traction load adjustment, Model Predictive Control (MPC) can be used for rolling optimization. The rolling time window can be set to 30 minutes, updated every 5 minutes to adapt to real-time changes. For optimization problems involving discrete decisions such as departure time adjustments, Mixed Integer Linear Programming (MILP) can be used. Specific steps: At the current time... An optimization problem is established based on the predicted data. Decision variables: the train's... And operational adjustment parameters. Constraints: Including the above-mentioned operational, power, and safety constraints. Solution: Use mixed-integer linear programming (MILP) or quadratic programming (QP) to handle discrete decisions (such as departure time adjustments). Output: Optimal adjustable potential curve. And corresponding operational adjustment plans. Synergistic considerations: Synergy with regenerative braking energy: Prioritize the use of braking energy to compensate for load adjustments, reducing net power fluctuations. Synergy with energy storage: Energy storage can provide a buffer, enhancing the reliability of adjustable potential.

[0124] Results and Applications: Output Content: Adjustable Potential Indicators: Time Series Curves: Upper and lower limits. Statistical indicators: maximum adjustable power, average adjustable energy (kWh), adjustable duration. Dispatch recommendations: specific adjustment instructions: for example, "train i decelerates by 10% at time t" or "departure interval increases by 15 seconds". Priority recommendations: rapid response strategies for grid emergencies (such as frequency drops). Application interface: results are sent via API or industry protocols (such as IEC 61850) to: Grid dispatch center: for real-time power balancing. Traction network intelligent control system: to execute train operation adjustments. Visualization: display adjustable potential trends and alarm information on the HMI interface.

[0125] Regenerative braking energy assessment method:

[0126] The adjustable potential of regenerative braking energy is defined as the active power regulation capability in an electrified railway traction network that allows the regenerative electrical energy generated during train braking through the reverse operation of the traction motor, taking into account recovery efficiency, spatiotemporal distribution, and safety constraints, to be flexibly dispatched to support the operation of other trains, energy storage charging, or feedback to the grid. This potential can reduce net load fluctuations in the traction network, improve energy efficiency, and support peak shaving and valley filling or frequency response of the grid. The core of the evaluation lies in quantifying the adjustable power (unit: kW or MW) and adjustable energy (unit: kWh) of regenerative braking energy and generating dynamic dispatch strategies.

[0127] The evaluation process is based on real-time data and adopts a hierarchical optimization architecture, including four stages: data acquisition, modeling, optimization calculation, and result output.

[0128] Real-time data acquisition and preprocessing: Collects real-time information such as train braking status, position, and speed, and performs data cleaning and short-term forecasting. Adjustable potential modeling: Establishes a mathematical model of regenerative braking energy, defining the adjustable power range and its constraints. Dynamic optimization evaluation: Calculates the adjustable potential using optimization algorithms, considering coordination with traction load, energy storage, and other resources. Result output and application: Generates adjustable potential curves and scheduling recommendations, interfaced with the power grid or traction network control system.

[0129] Data Acquisition and Preprocessing: Data Input: Real-time Data: Train Braking Status: Braking events (such as deceleration and brake pedal signals) are acquired through onboard sensors or the train control system. Train Position and Speed: Acquired via GPS or trackside positioning systems for spatiotemporal distribution analysis. Measured Regenerative Energy Values: Feedback power (unit: kW) is obtained from the energy metering device at the traction substation. Grid Status: Active power demand and frequency signals are used for dispatch coordination. Static Data: Line Topology: Gradient and curve radius (affecting braking energy generation). Equipment Parameters: Traction motor efficiency, inverter recovery efficiency, and line impedance. Operation Plan: Train timetable for predicting braking event occurrence times. External Data: Weather information (such as temperature, affecting braking efficiency).

[0130] Preprocessing: Data cleaning: Noise and outliers (e.g., power spikes due to sensor malfunctions) are removed using filtering algorithms (such as low-pass filtering or anomaly detection algorithms). Short-term prediction: A machine learning model (such as LSTM or random forest) is used to predict the regenerative braking energy generation curve for the next 15 minutes to 1 hour based on historical data and real-time conditions. Input features include train speed, location, track gradient, and planned braking point. Predicted output: Base regenerative braking power. (Unscheduled state) and total energy Efficiency calibration: Dynamically update the recovery efficiency coefficient based on equipment aging or environmental factors. (Typical value 0.7-0.9).

[0131] Adjustable potential modeling: The adjustable potential of regenerative braking energy is realized by quantifying recoverable power and energy, modeled as an integration of multiple train braking events. Key variables and constraints are defined: Mathematical model: Assume the system has M trains, and time is discretized as... (For example, intervals of 1 second or 1 minute, depending on real-time requirements). For the j-th train at time t, define the regenerative braking power. (Unit: kW), representing the initial power generated during braking. Adjustable regenerative braking power. Considering recycling efficiency for the portion that can actually be utilized: ;in Let be the recovery efficiency of the j-th train (including inverter and line losses). The total adjustable regenerative braking power is: The total adjustable energy is the time integral: ,in, Represents the time variable of integration. Representing the time infinitesimal element, It indicates that at any time The regenerative braking power is adjustable.

[0132] Adjustable Mechanism and Constraints: Direct Utilization: Renewable electrical energy is prioritized for traction of other trains within the same power supply section, reducing net load. Constraints: It is necessary to match the power demands and time synchronization of other trains to avoid energy waste. Mathematical Expression: Let... Given the traction load power, the net adjustable potential is: The available portion. Energy storage charging: Regenerated electrical energy is stored in the traction substation's energy storage system (such as batteries) for subsequent discharge. Constraints: Energy storage charging power limitations. and energy capacity Correlation Model: Adjustable potential is affected by the energy storage SOC (state of charge); for example, when the SOC is high, the adjustable potential decreases. Feedback to the Grid: Regenerated electricity is fed back to the public grid through converters to support grid dispatch. Constraints: Grid access standards (such as voltage and frequency limits) and contractual restrictions. Spatiotemporal Distribution Constraints: Spatial Constraints: The location of renewable energy generation must match the location of utilization (through power supply section division). Temporal Constraints: Braking events are brief (usually on the order of seconds), requiring rapid response to avoid energy dissipation. Physical Limitations: Maximum Adjustable Power: Subject to the upper limit of train braking power. Line capacity limitations. Minimum adjustable power: typically 0 (without braking), but basic braking energy must be considered. Adjustable potential range: defines the upper and lower limits of the adjustable potential. Wherein: lower limit The minimum power that can be guaranteed to be utilized (e.g., based on a historical low). Upper limit. To predict the maximum adjustable power, braking events and efficiency of all trains are taken into account.

[0133] Dynamic optimization assessment: Based on real-time data and models, optimization algorithms are used to calculate adjustable potential, ensuring coordination with resources such as traction load and energy storage. Optimization objectives: Primary objective: Maximize the utilization rate of regenerative braking energy, for example: minimize energy waste (i.e., unused regenerative energy). Or support grid demand: such as tracking grid dispatch instructions and using regenerative energy for peak shaving. Mathematical form: ;in This refers to the regenerative power actually utilized (including direct utilization, energy storage charging, or grid feedback). Optimization algorithm: To address the rapid fluctuations in regenerative braking energy, Model Predictive Control (MPC) can be used for rolling optimization. The rolling time window can be set to 5-10 minutes, updated every 10-30 seconds to adapt to rapid changes in braking events. For optimization problems involving discrete decisions such as energy storage switching, Mixed Integer Linear Programming (MILP) can be employed.

[0134] Specific steps: At the current time An optimization problem is established based on predicted data. Decision variables: the allocation strategy of braking energy for each train (e.g., direct utilization ratio, energy storage charging power). Constraints: including the aforementioned efficiency, spatiotemporal distribution, physical, and safety constraints. Solution: Linear programming (LP) or quadratic programming (QP) is used to handle continuous variables; for discrete decisions (e.g., energy storage switching), mixed integer programming (MILP) can be used. Output: the optimal adjustable potential curve. And energy allocation planning. Synergistic considerations: Synergizing with traction loads: Prioritizing the use of renewable energy for the traction of adjacent trains reduces dependence on the external power grid. Synergizing with energy storage: Energy storage acts as a buffer, storing excess renewable energy and discharging it when needed. Synergizing with regional solar / wind power: Renewable energy can compensate for fluctuations in renewable energy, improving system stability.

[0135] Results and Applications: Output Content: Adjustable Potential Indicators: Time Series Curves: Predicted and actual values. Statistical indicators: maximum adjustable power, average adjustable energy (kWh), utilization rate (utilized energy / total generated energy). Reliability indicators: such as the confidence interval of adjustable potential (based on prediction error analysis). Dispatch recommendations: real-time control commands: for example, "prioritize charging the energy storage system with the regenerative energy of train j" or "adjust converter settings to feed back to the grid". Alarm information: prompts for optimized operation plan when the adjustable potential is below the threshold. Application interface: sends results to: Traction network energy management system (for dynamic allocation of regenerative energy) and grid dispatch center (for grid ancillary services such as frequency regulation) via industrial communication protocols (such as IEC 61850 or Modbus). Visualization: displays trends in regenerative energy generation, utilization rate, and adjustable potential on the monitoring interface.

[0136] Traction station energy storage assessment method:

[0137] The adjustable potential of traction substation energy storage is defined as: in electrified railway traction networks, the energy storage system (such as lithium-ion batteries, supercapacitors, or flywheel energy storage) installed in traction substations or along the line, under the premise of considering charge and discharge efficiency, state of charge (SOC) limitations, lifespan constraints, and safe operation, can dynamically adjust its active power (charge and discharge) and energy state to respond to grid dispatch instructions or traction network demands. This potential can provide rapid power support (such as second-level response), energy time shifting (such as peak shaving and valley filling), and reserve capacity. The core lies in quantifying the adjustable power range (unit: kW or MW) and adjustable energy capacity (unit: kWh) of energy storage.

[0138] The evaluation process is based on real-time data and adopts a hierarchical optimization architecture, including four stages: data acquisition, modeling, optimization calculation, and result output.

[0139] Real-time data acquisition and preprocessing: Collect data on energy storage system status, grid demand, and external environment, and perform cleaning, normalization, and short-term forecasting. Adjustable potential modeling: Establish mathematical models of energy storage active power and energy, defining the adjustable range and its physical and operational constraints. Dynamic optimization evaluation: Calculate adjustable potential using optimization algorithms, considering coordination with resources such as regenerative braking energy and traction load. Result output and application: Generate adjustable potential curves and scheduling recommendations, interfaced with the power grid or traction network control system.

[0140] Data Acquisition and Preprocessing: Data Input: Real-time Data: Energy Storage Status: SOC (state of charge), measured charge / discharge power, voltage, current, and temperature (obtained through the Battery Management System (BMS)). Operating Parameters: Maximum charge / discharge power limit, efficiency coefficient (charge / discharge efficiency). ), State of Health (SOH). Grid interaction data: Active power demand signals, frequency deviation, dispatching instructions (such as peak shaving or valley filling commands). Traction network data: Regenerative braking energy availability, traction load curves (for collaborative optimization). Static data: Energy storage device specifications: rated capacity (kWh), power limit (kW), SOC safety range (such as... to ), Cycle life data. Operating strategy: Preset charge / discharge strategy (e.g., based on electricity price or load forecast). External data: Ambient temperature (affects battery performance), grid electricity price signal (used for economic evaluation).

[0141] Preprocessing: Data cleaning: Noise and faulty data (e.g., SOC jumps due to sensor errors) are processed using filtering algorithms (such as moving average filtering or outlier detection). Short-term forecasting: Machine learning models (such as Support Vector Machines (SVR) or Gradient Boosting Trees) are used to predict SOC changes and available power range for the next 15 minutes to 4 hours based on historical data and real-time conditions. Input features include current SOC, charge / discharge history, temperature, and load forecast. Forecast output: Baseline charge / discharge power curve. and SOC trajectory Efficiency calibration: Dynamically updates charge and discharge efficiency coefficients (typical values: charging efficiency 0.95, discharging efficiency 0.95), based on real-time temperature and equipment aging model.

[0142] Adjustable potential modeling: The adjustable potential of traction substation energy storage is realized by quantifying charging and discharging power and energy capacity, and modeled as a dynamic system subject to multiple constraints. Key variables and constraints are defined: Mathematical model: Assume time discretization is... (For example, at 1-minute intervals, suitable for intraday assessments). Define the adjustable variable of energy storage active power. (Unit: kW): Indicates discharge. Indicates charging. SOC dynamic equation: ; in: The charging power (kW) at time t is negative. Let be the discharge power (kW) at time t, and take a positive value; Charging efficiency (dimensionless, typical value 0.95); Discharge efficiency (dimensionless, typical value 0.97); For time intervals (hours); Rated energy storage capacity (kWh).

[0143] Adjustable mechanism and constraints: Adjustable power range: Charging power limit: ,in Maximum charging power. Discharging power limit: ,in Maximum discharge power. Total adjustable range: Energy adjustable range: SOC constraint: ,in and For safety limits (e.g., 20% and 90%). Adjustable energy capacity: Operational constraints: Lifetime protection: Limit charge / discharge rate ( ) and the number of loops, for example, maximum Temperature constraints: Battery temperature must be within a safe range. Response time: Energy storage can provide a response time in the second, but the minimum action time (e.g., 1 second) is considered in the evaluation.

[0144] Coordination Constraints: Coordination with Regenerative Braking Energy: Prioritize charging with regenerative energy to reduce grid dependence. Coordination with Traction Load: Prioritize supporting peak loads during discharge. Adjustable Potential Range: Define upper and lower limits for adjustable power. in: (Minimum adjustable power, i.e. maximum charging). (Maximum adjustable power, i.e., maximum discharge). However, the actual range is dynamically adjusted by the SOC: for example, when the SOC approaches... hour, Limited; when SOC is close to hour, Restricted.

[0145] Dynamic Optimization Assessment: Based on real-time data and models, optimization algorithms are used to calculate the adjustable potential and ensure multi-resource synergy. Optimization Objectives: Main objectives: Maximize the utility of energy storage's adjustable potential, for example: Economic efficiency: Minimize operating costs (considering electricity prices and lifetime losses). Grid support: Track grid dispatch instructions, such as peak shaving (discharge) or valley filling (charging). Stability: Smooth out power fluctuations in the traction network. Mathematical form: ;in: The target power (from grid command). Cost of lifetime loss (based on charge-discharge cycle model). These are the weighting coefficients.

[0146] Optimization Algorithm: Model Predictive Control (MPC) is used for rolling optimization, with a rolling time window set to 30 minutes and updated every 5 minutes to adapt to changes in SOC and external factors. For optimization problems involving discrete decisions such as energy storage switching, Mixed Integer Linear Programming (MILP) can be used. Specific steps: At the current time... An optimization problem is established based on predicted data (SOC, load, regenerative energy). Decision variables: Sequence. Constraints: Including the power, energy, lifetime, and cooperative constraints mentioned above. Solution: Use linear programming (LP) or quadratic programming (QP); for handling discrete events (such as energy storage switching), mixed-integer linear programming (MILP) can be used. Output: Optimal adjustable potential curve. And the SOC plan.

[0147] Synergistic Considerations: Synergizing with regenerative braking energy: Optimizing charging timing to absorb excess braking energy. Synergizing with traction loads: Discharging during peak load periods to reduce grid impact. Synergizing with roadside solar / wind power: Energy storage compensates for renewable energy fluctuations, improving forecast availability.

[0148] Results and Applications: Output Content: Adjustable Potential Indicators: Time Series Curves: Adjustable range (upper and lower limits) and optimal value. Statistical indicators: maximum adjustable power (kW), available energy capacity (kWh), response time (seconds), cycle efficiency. Economic indicators: expected cost savings, lifetime impact assessment. Dispatch recommendations: real-time control commands: for example, "discharge 500 kW at time t" or "charge to 80% SOC". Alarm information: prompts for maintenance or adjustment strategies when SOC exceeds limits or performance degrades. Application interface: sends results to: power grid dispatch center via industrial communication protocols (such as IEC 61850, DNP3): for participation in the ancillary services market (such as frequency regulation). Traction network energy management system: performs local charge and discharge control. Visualization: displays SOC trends, adjustable potential curves, and performance indicators on the monitoring interface.

[0149] Roadside Solar / Wind Power Assessment Methodology:

[0150] The adjustable potential of solar / wind power along railway lines is defined as follows: Solar and wind power systems installed around or along the electrified railway traction network, under the premise of considering weather conditions, equipment characteristics, operational constraints, and safety limitations, can dynamically adjust their active power output through active control (such as power limiting, increasing power generation, or power adjustment) to respond to grid dispatch instructions, match traction network demand, or improve the capacity for renewable energy consumption. This potential can provide clean energy support, reduce grid dependence, and participate in peak shaving and valley filling or frequency regulation. The core of the assessment lies in quantifying the adjustable power range (unit: kW or MW) and adjustable energy capacity (unit: kWh) of solar / wind power.

[0151] The evaluation process is based on real-time data and adopts a hierarchical optimization architecture, including four stages: data acquisition, modeling, optimization calculation, and result output.

[0152] Real-time data acquisition and preprocessing: Collect real-time information such as weather, power output data, and grid demand, and perform cleaning, normalization, and short-term forecasting. Adjustable potential modeling: Establish a mathematical model of photovoltaic / wind power active power, defining the adjustable range and its physical and operational constraints. Dynamic optimization evaluation: Calculate the adjustable potential using optimization algorithms, considering synergy with resources such as energy storage and traction loads. Result output and application: Generate adjustable potential curves and scheduling recommendations, interfaced with the grid or traction network control system.

[0153] Data Acquisition and Preprocessing: Data Input: Real-time Data: Photovoltaic System: Irradiance (W / m²) 2 ), Panel temperature, inverter output power (kW), DC / AC conversion efficiency. Wind power system: Wind speed (m / s), wind direction, turbine speed, output power (kW), turbine characteristics. Equipment status: Inverter operating status, fault signals, available capacity. Grid interaction data: Active power demand signals, frequency deviation, dispatching instructions (such as power rationing orders). Traction network data: Load curve, regenerative braking energy availability (for coordination). Static data: Equipment specifications: Rated power of photovoltaic panels (kWp), rated power of wind turbines (kW), inverter maximum power point tracking (MPPT) range, efficiency curve. Geographic location: Installation location, tilt angle (photovoltaics), altitude (wind power). Operating strategy: Preset output limits (such as based on grid constraints). External data: Weather forecast: Short-term irradiance, wind speed, temperature, cloud cover forecast (obtained from meteorological services). Electricity price signals: Used for economic optimization.

[0154] Preprocessing: Data cleaning: Noise and outlier data (e.g., power spikes due to sensor malfunctions) are removed using filtering algorithms (such as sliding window averaging or outlier detection). Short-term forecasting: Machine learning models (such as random forest or LSTM) are used to predict PV / wind power output curves for the next 15 minutes to 4 hours based on historical data and real-time weather information. Input features include: PV: Irradiance, temperature, time (daily cycle). Wind: Wind speed, wind direction, air pressure. Forecast output: Baseline power output curve. (Unadjusted state) and uncertainty range (e.g., confidence interval). Efficiency calibration: Dynamically update equipment efficiency coefficients (e.g., inverter efficiency). (Based on real-time temperature and aging models).

[0155] Adjustable potential modeling: The adjustable potential of roadside photovoltaic / wind power is realized by quantifying the adjustable range of active power, modeled as a dynamic system constrained by weather, equipment, and operation. Key variables and constraints are defined: Mathematical model: Assume time discretization is... (For example, at 15-minute intervals, suitable for intraday assessments). Define the total active power output of photovoltaic / wind power. (Unit: kW), where: , representing photovoltaic and wind power output respectively. Adjustable power variable. This indicates the amount of power adjustment achieved through control: ;in To adjust the output, It can be positive (increased issuance) or negative (limited issuance). The total adjustable potential is the power adjustment range: ;in and The upper and lower limits are adjustable.

[0156] Adjustable Mechanisms and Constraints: Photovoltaic Adjustable Potential: Adjustment Mechanism: Curtailment or increased generation (e.g., utilizing reserve capacity) is achieved through inverter control. Constraints: Maximum available output. Based on irradiance and temperature predictions, calculations are performed using physical models (e.g., ,in Where A is the photovoltaic efficiency and A is the area. (Irradiance). Inverter limitations: ,in This represents the inverter's maximum power. Minimum output: typically 0 (without sunlight), but base values ​​for nighttime or cloudy days need to be considered. Wind power adjustable potential:

[0157] Adjustment mechanism: Limited or increased power output is achieved through pitch control or speed regulation. Constraint: Maximum available output. Based on wind speed prediction and wind turbine power curves (e.g.) ,in (Wind speed). Fan operating range: Cut-in wind speed Cut-off wind speed Rated wind speed Minimum output: Due to limitations in wind turbine technology, it is usually 0.

[0158] Operational Constraints: Grid Connection Standards: such as voltage and frequency limits, to avoid reverse power flow issues. Equipment Safety: Inverter temperature and wind turbine mechanical stress limits. Prediction Uncertainty: Confidence interval processing ensures the reliability of adjustable potential. Coordination Constraints: Coordination with Energy Storage: Excess power is stored in energy storage systems to compensate for power fluctuations. Coordination with Traction Loads: Power is prioritized for local loads to reduce grid interaction. Adjustable Potential Range: Defines the upper and lower limits of adjustable power. ; ;

[0159] in: This represents the maximum available output. Maximum firing capacity (based on device limitations). This is the maximum issuance capacity (if there is spare capacity).

[0160] Dynamic Optimization Assessment: Based on real-time data and models, optimization algorithms are used to calculate adjustable potential and ensure multi-resource synergy. Optimization Objectives: Main Objective: Maximize the utility of photovoltaic / wind power adjustable potential. Economic Efficiency: Maximize renewable energy revenue or minimize curtailment of solar / wind power. Grid Support: Track grid dispatch instructions, such as peak shaving (increased generation) or valley filling (limited generation). Stability: Smooth out output fluctuations and improve forecast availability. Mathematical Form: ;in: The target power (from grid command). Costs of curtailing solar / wind power (based on electricity prices or environmental costs). These are the weighting coefficients.

[0161] Optimization Algorithm: Model Predictive Control (MPC) is used for rolling optimization. The rolling time window can be set to 1 hour and updated every 15 minutes to adapt to weather changes. For optimization problems involving discrete decisions such as inverter switching, Mixed Integer Linear Programming (MILP) can be used. Specific steps: At the current time... An optimization problem is established based on predicted data (output, weather, load). Decision variables: Sequence. Constraints: Including the aforementioned equipment, operational, and coordination constraints. Solution: Use linear programming (LP) or quadratic programming (QP); for handling discrete events (such as inverter switching), mixed integer programming (MILP) can be used. Output: Optimal adjustable potential curve. And adjust the plan.

[0162] Synergistic Considerations: Synergy with energy storage: Energy storage stores excess output and discharges it during periods of low output, smoothing out the overall output. Synergy with traction loads: Optimizes output timing to match peak loads and reduce grid dependence. Synergy with regenerative braking energy: Coordinates output and braking events to improve overall energy efficiency.

[0163] Results and Applications: Output Content: Adjustable Potential Indicators: Time Series Curves: Adjustable range (upper and lower limits) and optimal value. Statistical indicators: maximum adjustable power (kW), average adjustable energy (kWh), utilization rate (actual output / available output), prediction error. Economic indicators: expected revenue, curtailment of solar / wind power.

[0164] Dispatch Recommendations: Real-time Control Commands: For example, "Limit photovoltaic power generation to 200 kW at time t" or "Increase wind power generation to rated capacity." Alarm Information: Prompts for strategy adjustment or maintenance when prediction errors are large or equipment malfunctions. Application Interface: Sends results via industrial communication protocols (such as IEC 61850, Modbus TCP) to: Grid Dispatch Center: for renewable energy integration and ancillary services; Traction Grid Energy Management System: for executing local output control. Visualization: Displays power forecasts, adjustable potential curves, and performance indicators on the monitoring interface.

[0165] The following describes this embodiment in conjunction with an application scenario:

[0166] Traction load assessment:

[0167] Taking an electrified railway hub as an example: Input: Real-time monitoring of 10 trains, with a peak basic load of 5MW. Processing: Through MPC optimization, the adjustable potential range is calculated to be -1MW (load reduction) to +0.5MW (load increase). Output: During peak grid periods, the dispatching system automatically delays the departure of 3 trains, reducing the load by 0.8MW, supporting peak shaving.

[0168] Regenerative braking energy assessment:

[0169] Taking a subway line as an example: Input: Real-time monitoring of 5 trains, predicting a peak regenerative braking energy of 2MW in the next 10 minutes. Processing: Through MPC optimization, the adjustable potential is calculated to be 1.8MW (considering efficiency losses). The allocation strategy is: 1.0MW for adjacent train traction, 0.5MW for charging and energy storage, and 0.3MW for grid feedback. Output: The dispatching system automatically adjusts converter parameters to achieve efficient energy utilization and supports 0.3MW of peak shaving for the grid.

[0170] Traction station energy storage assessment:

[0171] Taking a lithium-ion battery energy storage system in a traction substation as an example: Input: Rated energy storage capacity 1MWh, power limit 500kW, current SOC 50%, safety range 20-90%. Processing: Through MPC optimization, based on grid peak shaving commands, the adjustable potential is calculated to be either 500kW discharge (for 1 hour) or 500kW charge (for 1 hour), constrained by SOC. Output: During peak grid periods, the dispatch system triggers a 500kW discharge, supporting peak shaving; simultaneously, regenerative braking energy is used for charging, reducing grid power purchases.

[0172] Roadside Solar / Wind Power Assessment:

[0173] Taking a photovoltaic and wind power system along a certain traction network as an example: Input: Rated photovoltaic power is 500kW, rated wind power is 300kW, and the predicted peak available output for the next hour is 400kW (photovoltaic) and 200kW (wind power). Processing: Through MPC optimization, based on grid peak shaving commands, the adjustable potential is calculated to be either limited to 100kW (photovoltaic) or increased to 50kW (wind power), subject to equipment limitations. Output: The dispatch system automatically adjusts the inverters to achieve output control, supporting grid peak shaving of 150kW, while utilizing energy storage to store excess energy.

[0174] For the purpose of simplicity, the method steps disclosed in the above embodiments are described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0175] like Figure 2 As shown, the present invention also provides a power grid-traction network resource collaborative assessment system, comprising:

[0176] The data acquisition and preprocessing module 201 is configured to collect real-time data from the power grid side, traction network side, and resource side, and preprocess the real-time data to obtain a standardized data stream; wherein, the power grid side data includes active power demand and frequency signals, the traction network side data includes train operation status and operation plan, and the resource side data includes energy storage charge status and renewable energy output.

[0177] Adjustable potential model establishment module 202 is configured to establish adjustable potential models for traction load, regenerative braking energy, traction station energy storage and roadside photovoltaic / wind power based on the standardized data stream, so as to obtain the adjustable potential range of each resource. The adjustable potential model quantifies the active power regulation capability and handles the coupling relationship between each resource.

[0178] The dynamic optimization evaluation module 203 is configured to perform dynamic optimization evaluation based on the adjustable potential model through an optimization algorithm to obtain the adjustable potential evaluation result and scheduling strategy. The optimization algorithm adopts model predictive control or mixed integer linear programming, and the optimization objectives include minimizing the peak-valley difference of the power grid and maximizing the consumption of renewable energy.

[0179] The evaluation result and scheduling strategy output module 204 is configured to output the adjustable potential evaluation result and scheduling strategy, wherein the adjustable potential evaluation result includes an adjustable potential curve and statistical indicators, and the scheduling strategy includes real-time control instructions for each resource.

[0180] The scheduling strategy execution module 205 is configured to perform peak shaving and valley filling, frequency response, or renewable energy consumption applications based on the scheduling strategy.

[0181] It is worth noting that although only some basic functional modules are disclosed in the embodiments of this invention, it does not mean that the composition of this system is limited to the above-mentioned basic functional modules. On the contrary, what this embodiment intends to express is that, based on the above-mentioned basic functional modules, those skilled in the art can arbitrarily add one or more functional modules in combination with existing technology to form an infinite number of embodiments or technical solutions. That is to say, this system is open rather than closed. The fact that this embodiment only discloses a few basic functional modules should not be considered as the scope of protection of the claims of this invention being limited to the disclosed basic functional modules. At the same time, for the convenience of description, the above device is described separately according to its functions as various units and modules. Of course, in implementing this invention, the functions of each unit and module can be implemented in one or more software and / or hardware.

[0182] like Figure 3 As shown, the present invention also provides an electronic device, including: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of a power grid-traction network resource collaborative evaluation method.

[0183] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. For example... Figure 3 The structure shown in this embodiment of the invention includes an electronic device comprising one or more processors 710 and a memory 720; the processors 710 in this electronic device may be one or more. Figure 3Taking a processor 710 as an example; a memory 720 is used to store one or more programs; the one or more programs are executed by the one or more processors 710, so that the one or more processors 710 implement a power grid-traction network resource collaborative evaluation method as described in any one of the embodiments of the present invention.

[0184] The electronic device may also include an input device 730 and an output device 740.

[0185] The processor 710, memory 720, input device 730, and output device 740 in this electronic device can be connected via a bus or other means. Figure 3 Taking the example of a connection between China and Israel via a bus.

[0186] The memory 720 in this electronic device serves as a computer-readable storage medium, capable of storing one or more programs. These programs can be software programs, computer-executable programs, or modules, such as the program instructions / modules corresponding to the power grid-traction network resource collaborative assessment method provided in this embodiment of the invention. The processor 710 executes various functional applications and data processing of the electronic device by running the software programs, instructions, and modules stored in the memory 720, thereby realizing the power grid-traction network resource collaborative assessment method described in the above embodiment.

[0187] The memory 720 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the electronic device. Furthermore, the memory 720 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 720 may further include memory remotely located relative to the processor 710, which can be connected to the device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0188] Input device 730 can be used to receive input digital or character information, and to generate key signal inputs related to user settings and function control of the electronic device. Output device 740 may include display devices such as a display screen.

[0189] The present invention also provides a computer-readable storage medium storing a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of a power grid-traction network resource collaborative assessment method.

[0190] Specifically, the computer storage medium in this embodiment of the invention can be any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. For example, a computer-readable storage medium can be—but is not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0191] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for collaborative assessment of power grid and traction network resources, characterized in that, include: Real-time data from the power grid side, traction network side, and resource side are collected and preprocessed to obtain a standardized data stream. The power grid side data includes active power demand and frequency signals, the traction network side data includes train operation status and operation plan, and the resource side data includes energy storage charge status and renewable energy output. Based on the standardized data stream, adjustable potential models are established for traction load, regenerative braking energy, traction substation energy storage, and roadside photovoltaic / wind power, respectively, to obtain the adjustable potential range of each resource. The adjustable potential model quantifies the active power regulation capability and handles the coupling relationship between each resource. Based on the adjustable potential model, dynamic optimization evaluation is performed through optimization algorithms to obtain adjustable potential evaluation results and scheduling strategies. The optimization algorithms adopt model predictive control or mixed integer linear programming, and the optimization objectives include minimizing the peak-valley difference of the power grid and maximizing the consumption of renewable energy. Output the adjustable potential assessment results and scheduling strategy, wherein the adjustable potential assessment results include adjustable potential curves and statistical indicators, and the scheduling strategy includes real-time control instructions for each resource; Based on the aforementioned scheduling strategy, peak shaving and valley filling, frequency response, or renewable energy consumption applications are implemented.

2. The power grid-traction network resource collaborative assessment method according to claim 1, characterized in that, Real-time data from the power grid side, traction network side, and resource side are collected and preprocessed to obtain a standardized data stream. The power grid side data includes active power demand and frequency signals; the traction network side data includes train operating status and operating plans; and the resource side data includes energy storage charge status and renewable energy output. Further, it includes: Collect active power demand, frequency signals and dispatch instructions from the power grid side; collect train position, speed, braking status, load curve and operation plan from the traction network side; and collect energy storage charge status, measured values ​​of renewable energy output and weather information from the resource side. The collected real-time data is cleaned, and filtering algorithms are used to process measurement noise and abnormal data. A method based on historical data patterns is used to fill in missing data. Short-term forecasts are made on the cleaned data using time series analysis models or deep learning network models to predict the traction load change trend, spatiotemporal distribution of regenerative braking energy, and fluctuation characteristics of renewable energy output in future operating cycles. The multi-source heterogeneous prediction data and real-time monitoring data are normalized in a unified format to generate a standardized data stream.

3. The power grid-traction network resource collaborative assessment method according to claim 1, characterized in that, Based on the standardized data stream, an adjustable potential model for traction load is established, further including: Based on the standardized data stream, train operation status data and operation plan data are analyzed; An adjustable power model for traction load is established, and the adjustable power is defined as the algebraic sum of the power adjustments of each train in the discrete time series. The power adjustment is achieved through departure time optimization, speed curve adjustment and operation plan rearrangement. Set multi-dimensional operating constraints, including minimum safe departure interval limit, maximum allowable timetable offset range, speed operating range limit and traction motor power output limit; Based on the power adjustment amount and operating constraints, the dynamic upper and lower limits of the adjustable potential are determined, and the traction load adjustable potential model is integrated into the multi-resource model in a linear combination manner.

4. The method for collaborative assessment of power grid-traction network resources according to claim 1, characterized in that, A tunable potential model for regenerative braking energy is established, further including: Based on the standardized data stream, train braking status feature data, spatial position data, and real-time speed data are extracted; An adjustable power model for regenerative braking energy is established, and the adjustable power is defined as the product of the braking power of each train and the dynamically calibrated recovery efficiency coefficient, wherein the recovery efficiency coefficient is updated in real time according to the equipment operating status. Set multi-level utilization constraints, including direct utilization priority rules within the same power supply section, maximum charging power limit of energy storage system, and technical standards for grid feedback interface; Based on the adjustable power distribution in time and space and the constraints, the upper and lower limits of the adjustable potential are determined, and the adjustable potential model of regenerative braking energy is integrated into the multi-resource model with a power balance relationship.

5. The power grid-traction network resource collaborative assessment method according to claim 1, characterized in that, To establish an adjustable potential model for energy storage in traction substations, further including: Based on the standardized data stream, acquire dynamic data of charge state of the energy storage system, historical data of charge and discharge power, and ambient temperature data. Establish an adjustable active power model for energy storage, define the adjustable power as the algebraic difference between charging power and discharging power, and construct charge state recursive equations for charging and discharging efficiency and energy conservation. Set multiple types of operating constraints, including maximum charge and discharge power limits, safe operating range for charge state, performance limits under temperature influence, and cycle life decay protection mechanisms; The upper and lower limits of the adjustable potential are determined based on the real-time charging and discharging power capability and operating constraints. The energy storage adjustable potential model is then integrated into the multi-resource model in an energy buffer manner.

6. The method for collaborative assessment of power grid-traction network resources according to claim 1, characterized in that, Establish an adjustable potential model for roadside photovoltaic / wind power, further including: Based on the standardized data stream, renewable energy output monitoring data, weather forecast data, and power electronic equipment parameters are acquired. A photovoltaic wind power active power adjustable model is established, and the adjustable power is defined as the controllable deviation between the actual output and the predicted reference output. The reference output is calculated by physical characteristic equations. Set equipment operating constraints, including the maximum available output limit determined by meteorological conditions, the maximum conversion power limit of the inverter, the wind speed range limit of the wind turbine, and the grid reverse power protection limit; The upper and lower limits of the adjustable potential are determined based on the power output adjustment capacity and equipment constraints, and the photovoltaic and wind power adjustable potential model is integrated into the multi-resource model in a power compensation manner.

7. The method for collaborative assessment of power grid-traction network resources according to claim 1, characterized in that, Based on the aforementioned adjustable potential model, dynamic optimization evaluation is performed using an optimization algorithm to obtain the adjustable potential evaluation results and scheduling strategy. The optimization algorithm employs model predictive control or mixed-integer linear programming, and the optimization objectives include minimizing the peak-to-valley difference in the power grid and maximizing renewable energy absorption. Further, it includes: A multi-objective optimization function system is established, including grid load optimization objectives based on power balance and renewable energy consumption objectives considering fluctuation characteristics; Set complete system constraints, including constraints on the electrical safety operation of the traction network, constraints on the reliability of train services, constraints on the physical limitations of resources, and constraints on the cooperative coupling of multiple resources; A model predictive control framework is used for rolling time window optimization, and a mixed-integer linear programming algorithm is used to handle combinations of discrete and continuous decision variables. The output optimization results include dynamic curves of the adjustable potential of future time series and coordination and scheduling strategies for each resource.

8. A power grid-traction network resource collaborative assessment system, characterized in that, include: The data acquisition and preprocessing module is configured to collect real-time data from the power grid side, traction network side, and resource side, and preprocess the real-time data to obtain a standardized data stream. Among them, the power grid side data includes active power demand and frequency signals, the traction network side data includes train operation status and operation plan, and the resource side data includes energy storage charge status and renewable energy output. The adjustable potential model building module is configured to build adjustable potential models for traction load, regenerative braking energy, traction substation energy storage and roadside photovoltaic / wind power based on the standardized data stream, so as to obtain the adjustable potential range of each resource. The adjustable potential model quantifies the active power regulation capability and handles the coupling relationship between each resource. The dynamic optimization evaluation module is configured to perform dynamic optimization evaluation based on the adjustable potential model through an optimization algorithm to obtain the adjustable potential evaluation result and scheduling strategy. The optimization algorithm adopts model predictive control or mixed integer linear programming, and the optimization objectives include minimizing the peak-valley difference of the power grid and maximizing the consumption of renewable energy. The evaluation result and scheduling strategy output module is configured to output the adjustable potential evaluation result and scheduling strategy, wherein the adjustable potential evaluation result includes an adjustable potential curve and statistical indicators, and the scheduling strategy includes real-time control instructions for each resource. The scheduling strategy execution module is configured to perform peak shaving and valley filling, frequency response, or renewable energy consumption applications based on the scheduling strategy.

9. An electronic device, characterized in that, include: The system includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus; the memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It stores a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of the method according to any one of claims 1 to 7.

Images