CN-122000921-A - Power grid-traction network resource collaborative assessment method, system and electronic equipment

CN122000921ACN 122000921 ACN122000921 ACN 122000921ACN-122000921-A

Abstract

The invention relates to the technical field of cooperative operation of electrified railways and discloses a power grid-traction network resource cooperative evaluation method, a system and electronic equipment, wherein the method comprises the steps of collecting real-time data of a power grid side, a traction network side and a resource side, and preprocessing the real-time data to obtain a standardized data stream; based on the standardized data flow, respectively establishing adjustable potential models for traction load, regenerative braking energy, traction stored energy and Lu Yu photovoltaic/wind power to obtain adjustable potential ranges of each resource, dynamically optimizing and evaluating through an optimization algorithm based on the adjustable potential models to obtain an adjustable potential evaluation result and a scheduling strategy, outputting the adjustable potential evaluation result and the scheduling strategy, and executing peak clipping and valley filling, frequency response or renewable energy consumption application based on the scheduling strategy. The invention can integrate real-time operation information, overall multi-resource characteristics, realize daily dynamic evaluation and cooperation and fully mine the flexible resource potential of the power grid-traction network system.

Inventors

XIA MINGCHAO
FENG JIAWEI
LIANG WEI
LIN YUNZHI
REN LI
WANG HAIXIN
YANG JUNYOU
CHENG WEIJUN
MU SIYU
Fu tianhe
LI YUNLU

Assignees

中铁电气化局集团有限公司
沈阳工业大学

Dates

Publication Date: 20260508
Application Date: 20260212

Claims (10)

1. A grid-traction network resource collaborative assessment method, comprising: Collecting real-time data of a power grid side, a traction network side and a resource side, and preprocessing the real-time data to obtain a standardized data stream, wherein the power grid side data comprises active power requirements and frequency signals, the traction network side data comprises a train running state and a running plan, and the resource side data comprises an energy storage charge state and renewable energy output; Based on the standardized data flow, respectively establishing adjustable potential models for traction load, regenerative braking energy, traction stored energy and Lu Yu photovoltaic/wind power to obtain adjustable potential ranges of all resources, wherein the adjustable potential models quantify active power adjustment capability and process coupling relations among all the resources; Based on the adjustable potential model, carrying out dynamic optimization evaluation through an optimization algorithm to obtain an adjustable potential evaluation result and a scheduling strategy, wherein the optimization algorithm adopts model predictive control or mixed integer linear programming, and an optimization target comprises minimizing peak-valley difference of a power grid and maximizing renewable energy consumption; Outputting the adjustable potential evaluation result and a scheduling strategy, wherein the adjustable potential evaluation result comprises an adjustable potential curve and a statistical index, and the scheduling strategy comprises real-time control instructions of all resources; and executing peak clipping and valley filling, frequency response or energy consumption application based on the scheduling strategy.
2. The grid-traction network resource collaborative assessment method according to claim 1, wherein real-time data of a grid side, a traction network side and a resource side are collected and preprocessed to obtain a standardized data stream, wherein the grid side data comprises active power requirements and frequency signals, the traction network side data comprises a train running state and a running plan, the resource side data comprises an energy storage charge state and a renewable energy output, and further comprising: Active power demand, frequency signals and scheduling instructions on the power grid side are collected, train position, speed, braking state, load curve and operation schedule on the traction grid side are collected, and energy storage charge state, actual measurement value of renewable energy output and weather information on the resource side are collected; Carrying out data cleaning on the collected real-time data, processing measurement noise and abnormal data by using a filtering algorithm, and filling the missing data by adopting an interpolation method based on a historical data mode; Short-term prediction is carried out on the cleaned data, and a time sequence analysis model or a deep learning network model is adopted to predict the traction load change trend, the regenerative braking energy space-time distribution and the renewable energy output fluctuation characteristics of a future operation period; and carrying out unified format normalization processing on the multi-source heterogeneous prediction data and the real-time monitoring data to generate a standardized data stream.
3. The grid-traction network resource collaborative assessment method according to claim 1, wherein establishing an adjustable potential model for traction load based on the standardized data flow further comprises: Analyzing train operation state data and operation plan data based on the standardized data stream; Establishing an adjustable power model of traction load, and defining adjustable power as algebraic sum of power adjustment amounts of each train on discrete time sequences, wherein the power adjustment is realized through departure time optimization, speed curve adjustment and operation plan rearrangement; Setting multi-dimensional operation constraint conditions, including minimum safe departure interval limit, maximum allowable timetable offset range, speed operation interval limit and traction motor power output limit; And determining the dynamic upper limit and the lower limit of the adjustable potential according to the power adjustment quantity and the operation constraint condition, and integrating the traction load adjustable potential model into the multi-resource model in a linear combination mode.
4. The grid-traction network resource collaborative assessment method according to claim 1, wherein an adjustable potential model is built for regenerative braking energy, further comprising: Extracting train brake state characteristic data, space position data and real-time speed data based on the standardized data stream; establishing an adjustable power model of regenerative braking energy, and defining adjustable power as the product of each train braking power and a dynamically calibrated recovery efficiency coefficient, wherein the recovery efficiency coefficient is updated in real time according to the running state of equipment; Setting multi-level utilization constraint conditions, including a direct utilization priority rule, an energy storage system maximum charging power limit and a technical standard of a power grid feedback interface in the same power supply section; And determining the upper limit and the lower limit of the adjustable potential according to the adjustable power of the space-time distribution and the utilization constraint condition, and integrating the regenerated braking energy adjustable potential model into the multi-resource model in a power balance relation.
5. The grid-traction network resource collaborative assessment method according to claim 1, wherein an adjustable potential model is built for traction stored energy, further comprising: Acquiring charge state dynamic data, charge-discharge power historical data and environmental temperature data of an energy storage system based on the standardized data stream; Establishing an energy storage active power adjustable model, defining adjustable power as algebraic difference of charging power and discharging power, and constructing a charge state recurrence equation of charging and discharging efficiency and energy conservation; setting multi-type operation constraint conditions, including maximum charge and discharge power limit, charge state safe operation interval, performance limit under the influence of temperature and cycle life decay protection mechanism; and determining the upper limit and the lower limit of the adjustable potential according to the real-time charge and discharge power capability and the operation constraint condition, and integrating the energy storage adjustable potential model into the multi-resource model in an energy buffering mode.
6. The grid-traction network resource collaborative assessment method according to claim 1, wherein an adjustable potential model is established for road domain photovoltaic/wind power, further comprising: acquiring renewable energy output monitoring data, weather forecast data and power electronic equipment parameters based on the standardized data stream; Establishing a photovoltaic wind power active power adjustable model, and defining adjustable power as controllable deviation amount of actual output and predicted reference output, wherein the reference output is obtained by calculation through a physical characteristic equation; Setting equipment operation constraint conditions, including maximum available output limit, inverter maximum conversion power limit, fan operation wind speed interval limit and grid reverse power protection limit, which are determined by meteorological conditions; and determining upper and lower limits of adjustable potential according to the output adjustment capability and the equipment constraint condition, and integrating the photovoltaic wind power adjustable potential model into the multi-resource model in a power compensation mode.
7. The grid-traction network resource collaborative assessment method according to claim 1, wherein based on the adjustable potential model, dynamic optimization assessment is performed through an optimization algorithm to obtain an adjustable potential assessment result and a scheduling strategy, wherein the optimization algorithm adopts model predictive control or mixed integer linear programming, and the optimization objective comprises minimizing grid peak-valley differences and maximizing renewable energy consumption, and further comprising: Setting a multi-objective optimization function system, wherein the multi-objective optimization function system comprises a power grid load optimization target based on power balance and a renewable energy source absorption target considering fluctuation characteristics; setting complete system constraint conditions, including traction network electric safety operation constraint, train service reliability constraint, resource physical limit constraint and multi-resource cooperative coupling constraint; Adopting a model predictive control framework to perform rolling time window optimization, and using a mixed integer linear programming algorithm to process discrete and continuous decision variable combinations; And outputting an optimization result, wherein the optimization result comprises an adjustable potential dynamic curve of a future time sequence and a coordinated scheduling strategy of each resource.
8. A grid-traction grid resource collaborative assessment system, comprising: The system comprises a data acquisition and preprocessing module, a data processing module and a data processing module, wherein the data acquisition and preprocessing module is configured to acquire real-time data of a power grid side, a traction grid side and a resource side, and preprocesses the real-time data to obtain a standardized data stream, wherein the power grid side data comprises active power requirements and frequency signals, the traction grid side data comprises a train running state and a running plan, and the resource side data comprises an energy storage charge state and renewable energy output; The adjustable potential model building module is configured to respectively build adjustable potential models for traction load, regenerative braking energy, traction stored energy and Lu Yu photovoltaic/wind power based on the standardized data flow to obtain adjustable potential ranges of all resources, wherein the adjustable potential models quantify active power adjustment capability and process coupling relations among all the resources; The dynamic optimization evaluation module is configured to perform dynamic optimization evaluation through an optimization algorithm based on the adjustable potential model to obtain an adjustable potential evaluation result and a scheduling strategy, wherein the optimization algorithm adopts model predictive control or mixed integer linear programming, and an optimization target comprises minimizing peak-valley difference of a power grid and maximizing renewable energy consumption; The evaluation result and scheduling strategy output module is configured to output the adjustable potential evaluation result and the scheduling strategy, wherein the adjustable potential evaluation result comprises an adjustable potential curve and a statistical index, and the scheduling strategy comprises real-time control instructions of all resources; and the scheduling strategy executing module is configured to execute peak clipping and valley filling, frequency response or renewable energy source consuming application based on the scheduling strategy.
9. An electronic device comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface, the memory are in communication with each other via the communication bus, and wherein the memory has a computer program stored therein, which when executed by the processor, causes the processor to perform the steps of the method according to any 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 of any one of claims 1 to 7.

Description

Power grid-traction network resource collaborative assessment method, system and electronic equipment Technical Field The invention relates to the technical field of cooperative operation of electrified railways, in particular to a power grid-traction network resource cooperative evaluation method, a system and electronic equipment. Background With the rapid increase of electrified railway loads, the impact and random load characteristics of the electrified railway loads exert remarkable pressure on the safe operation and the electric energy quality of the power grid. Meanwhile, resources such as regenerative braking energy, an energy storage system, adjustable loads and the like distributed in the traction network system are not fully excavated and converted into flexible resources available for the power grid. The prior art mainly has the following limitations: the traditional adjustable potential evaluation method is mainly used for static evaluation based on a typical daily curve, and cannot consider real-time change factors such as dynamic adjustment of a daily train operation diagram, renewable energy fluctuation and the like, so that a larger deviation exists between an evaluation result and an actual operation condition. The power grid and the traction network system are independently operated and managed for a long time, and unified collaborative modeling of resources of the power grid and the traction network system is lacked. The isolated management mode causes the problems that the regenerative braking energy utilization rate is low, the energy storage system is not coordinated in scheduling, the load adjustment capability cannot be fully exerted, and the like. The prior art fails to fully utilize real-time information such as state sensing data of traction substation equipment and ultra-short-term load prediction, and cannot realize online dynamic update of potential evaluation results, so that the requirements of real-time dispatching of a power grid on precision and response speed are difficult to meet. Therefore, the application provides a power grid-traction network resource collaborative evaluation method to solve the technical problems. Disclosure of Invention The invention aims to provide a power grid-traction network resource collaborative assessment method, a system and electronic equipment, which are used for solving the technical problem that the flexible resource potential of a power grid-traction network system cannot be fully excavated in the prior art. In order to solve the technical problems, the invention provides a power grid-traction network resource collaborative evaluation method, which comprises the following steps: Collecting real-time data of a power grid side, a traction network side and a resource side, and preprocessing the real-time data to obtain a standardized data stream, wherein the power grid side data comprises active power requirements and frequency signals, the traction network side data comprises a train running state and a running plan, and the resource side data comprises an energy storage charge state and renewable energy output; Based on the standardized data flow, respectively establishing adjustable potential models for traction load, regenerative braking energy, traction stored energy and Lu Yu photovoltaic/wind power to obtain adjustable potential ranges of all resources, wherein the adjustable potential models quantify active power adjustment capability and process coupling relations among all the resources; Based on the adjustable potential model, carrying out dynamic optimization evaluation through an optimization algorithm to obtain an adjustable potential evaluation result and a scheduling strategy, wherein the optimization algorithm adopts model predictive control or mixed integer linear programming, and an optimization target comprises minimizing peak-valley difference of a power grid and maximizing renewable energy consumption; Outputting the adjustable potential evaluation result and a scheduling strategy, wherein the adjustable potential evaluation result comprises an adjustable potential curve and a statistical index, and the scheduling strategy comprises real-time control instructions of all resources; and executing peak clipping and valley filling, frequency response or energy consumption application based on the scheduling strategy. In some embodiments, real-time data of a power grid side, a traction grid side and a resource side are collected and preprocessed to obtain a standardized data stream, wherein the power grid side data comprises active power requirements and frequency signals, the traction grid side data comprises a train running state and a running plan, the resource side data comprises an energy storage charge state and renewable energy output, and the method further comprises the steps of: Active power demand, frequency signals and scheduling instructions on the power grid side are collected, train position, speed, braking