Distributed photovoltaic cluster regulation and control simulation method, system and device and storage medium

By constructing a power grid model and a high-precision photovoltaic power generation prediction model, the problem of low accuracy in distributed photovoltaic regulation simulation is solved, and more accurate reflection of the power grid operation status and formulation of regulation strategies is achieved, which improves the regulation effect of distributed photovoltaic clusters.

CN118983784AInactive Publication Date: 2024-11-19HENAN LONGXIANG EDUCATION INFORMATION TECHNOLOGY CO LTD +1
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411057336.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-02
Publication Date
2024-11-19
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Due to the limitation of computing power and inaccurate predictions of existing distributed photovoltaic regulation simulation methods, the accuracy of simulation results is poor and cannot meet the needs of actual engineering applications.

Method used

By constructing a grid model in the target area, multi-source and multi-time grid data are obtained, including photovoltaic power generation and load prediction data, and simulation analysis is performed using a pre-established simulation model, considering the dynamic characteristics of the power grid and the power generation characteristics of different photovoltaic equipment, combined with Meteorological data are accurately predicted, and a high-precision photovoltaic power generation prediction model and residual life prediction model are established.

Benefits of technology

The accuracy of distributed photovoltaic regulation simulation is improved, and the simulation results are more in line with the actual situation. It provides effective support for formulating scientific and reasonable regulatory strategies, and improves the reliability of photovoltaic cluster planning and regulatory decision-making.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118983784A_ABST
    Figure CN118983784A_ABST
Patent Text Reader

Abstract

The invention provides a distributed photovoltaic cluster regulation and control simulation method, system and device and a storage medium, and relates to the field of power transmission network planning. The method comprises the steps that a power grid model of a target area is constructed, multi-source and multi-period power grid data of a power grid of the target area are acquired based on the power grid model, and the multi-source and multi-period power grid data comprise photovoltaic predicted generating capacity of different periods in a preset period; and inputting the multi-source multi-period power grid data into a pre-established simulation model to obtain n power flow sections of the power grid. According to the method, through comprehensive operation of various data, the power flow distribution condition of the power grid in multiple periods can be obtained, and the accuracy of distributed photovoltaic regulation and control simulation is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of power transmission network planning, and specifically to a distributed photovoltaic cluster control simulation method, system, device and storage medium. Background Art

[0002] With the rapid development of the distributed photovoltaic power generation industry, it is imperative to regulate it scientifically and rationally. However, due to the characteristics of distributed photovoltaic power generation, such as strong dispersion, small capacity, and great operational flexibility, it brings great difficulties to its regulation. At present, the use of simulation to verify and analyze the regulation strategy of distributed photovoltaic power generation has become an effective means. However, due to factors such as computer processing power and inaccurate prediction of photovoltaic power generation, the existing distributed photovoltaic regulation simulation method has poor accuracy of simulation results and cannot meet the needs of actual engineering applications. Summary of the invention

[0003] The present application provides a distributed photovoltaic cluster control simulation method, system, device and storage medium to improve the accuracy of distributed photovoltaic control simulation.

[0004] In a first aspect, the present application provides a distributed photovoltaic cluster control simulation method, the method comprising: Constructing a power grid model of the target area, and acquiring multi-source and multi-period power grid data of the power grid in the target area based on the power grid model; The multi-source and multi-time period power grid data are input into a pre-established simulation model to obtain n power flow sections of the power grid.

[0005] By adopting the above technical solution and constructing a power grid model of the target area, it is possible to obtain multi-source and multi-period power grid data for the area, including photovoltaic power generation forecast data, load forecast data, etc., so that the input data of the subsequent simulation model is more comprehensive and accurate, which is conducive to improving the accuracy of the simulation results. On the basis of obtaining accurate multi-source and multi-period power grid data, the method inputs the power grid data into a pre-established simulation model for simulation analysis. Compared with a simple static model, the pre-established simulation model can fully consider the dynamic characteristics of the power grid. Through the comprehensive calculation of various types of data, the power grid flow distribution in multiple time periods can be obtained, thereby improving the accuracy of the distributed photovoltaic control simulation. The obtained power grid flow section reflects the detailed operating status of the power grid in the target area, and provides effective support for the formulation and evaluation of subsequent distributed photovoltaic cluster control strategies.

[0006] Optionally, the multi-source and multi-time period grid data includes photovoltaic predicted power generation in different time periods within a preset time period; and obtaining photovoltaic predicted power generation in different time periods within the preset time period includes: Acquire meteorological data within a preset time period of each target area and equipment model of each distributed photovoltaic power station within the target area; The meteorological data is input into a preset photovoltaic power generation prediction model to output the photovoltaic power generation prediction and power generation probability at different time periods within a preset time period.

[0007] By adopting the above technical solution, by obtaining the equipment model of each distributed photovoltaic power station in the target area, the power generation characteristics of different photovoltaic equipment can be distinguished. On the basis of knowing the equipment model, combined with the meteorological data obtained in the preset time period of the target area as input, the preset photovoltaic power generation prediction model is input. The prediction model can accurately predict the photovoltaic power generation and power generation probability in different time periods within the preset time period according to the meteorological data of different time periods and the power generation characteristics of different equipment models. Compared with simple meteorological data prediction, this method can improve the accuracy of photovoltaic power generation prediction by considering equipment differences. The photovoltaic power generation prediction data obtained in different time periods, as an important part of multi-source and multi-time period power grid data, helps to improve the accuracy of subsequent distributed photovoltaic cluster control simulation, make the simulation results more in line with the actual situation, and provide support for the formulation of scientific and reasonable control strategies.

[0008] Optionally, obtaining the preset photovoltaic power generation prediction model includes: According to the preset photovoltaic power generation sample data, the photovoltaic power generation sample data is fitted by a least square method and a polynomial regression algorithm to obtain the photovoltaic power generation sample data after fitting; Based on the photovoltaic power generation sample data after the fitting process, the photovoltaic power generation prediction model is constructed, and the photovoltaic power generation prediction model is trained to obtain the preset photovoltaic power generation prediction model, wherein the photovoltaic power generation sample data includes: equipment information of multiple photovoltaic power station samples, photovoltaic power station power generation sample data and meteorological sample data of a preset area.

[0009] By adopting the above technical solution, by fitting the preset photovoltaic power generation sample data, a mathematical model between the sample data and the actual power generation can be established, and the least square method and polynomial regression algorithm can be used to reduce the fitting error. On the basis of obtaining the sample data after accurate fitting, a photovoltaic power generation prediction model is further constructed, and the model is trained to continuously optimize its parameters, thereby obtaining a preset prediction model with higher accuracy. Among them, the training process makes full use of the rich photovoltaic power generation sample data containing equipment information, power generation data and meteorological data, so that the prediction model can adapt to the influence of different equipment conditions and meteorological environment, and the prediction results are more accurate and reliable. The preset photovoltaic power generation prediction model obtained by this method can provide strong support for the subsequent acquisition of multi-source and multi-period power grid data, which is helpful to improve the overall effect of distributed photovoltaic cluster control simulation, make the simulation results more in line with the actual situation, and provide a basis for the planning and control decision-making of photovoltaic clusters.

[0010] Optionally, the target area is a county or district, and the meteorological data includes ambient temperature, relative humidity, wind speed, and air pressure.

[0011] By adopting the above technical solution, the target area is selected as a county or region, and such a regional scope is conducive to the acquisition and processing of meteorological data. The meteorological data obtained for the target area include ambient temperature, relative humidity, wind speed and air pressure, which can fully reflect the spatiotemporal distribution and changing trends of regional meteorological conditions. On the basis of obtaining extensive and accurate meteorological data, these data are used as input into the preset photovoltaic power generation prediction model, which can accurately predict photovoltaic power generation according to the influence of different meteorological parameters. Compared with simple predictions that only use some meteorological factors, this method of integrating key meteorological data can improve the accuracy and reliability of the prediction results. The accurate photovoltaic power generation prediction data obtained will become an important part of the subsequent multi-source and multi-period power grid data, which will help improve the accuracy of distributed photovoltaic cluster control simulation and provide strong support for control decisions.

[0012] Optionally, the photovoltaic power generation sample data is fitted by least square method and polynomial regression algorithm according to preset photovoltaic power generation sample data to obtain fitted photovoltaic power generation sample data, and a photovoltaic power generation remaining life prediction model is constructed based on the fitted photovoltaic power generation sample data, including: Classifying the preset photovoltaic power generation sample data based on the photovoltaic power generation equipment information, and classifying the photovoltaic power generation sample data with the same photovoltaic power generation equipment information into one category; Photovoltaic power generation sample data with the same equipment information are fitted by the least square method and the polynomial regression algorithm to obtain the fitted photovoltaic power generation sample data.

[0013] By adopting the above technical means, the equipment information of photovoltaic power generation sample data is first classified, so that the sample data of the same type of equipment are gathered together, and then the sample data of each type of equipment is fitted. This fitting method that takes into account equipment differences can improve the fitting accuracy. On the basis of the fitting process, a photovoltaic power generation remaining life prediction model is constructed. The model can accurately predict the remaining life of different types of equipment according to the change law of historical power generation data of each type of photovoltaic equipment. Compared with the traditional formula method for estimating life, this model based on sample data fitting can make the prediction closer to the actual situation. The constructed remaining life prediction model can evaluate the aging status of photovoltaic power station equipment, provide a basis for subsequent operation and maintenance, and provide equipment status information for power grid data acquisition, which is conducive to improving the accuracy of distributed photovoltaic cluster control simulation.

[0014] Optionally, the step of pre-establishing a simulation model on the multi-source and multi-period power grid data input board to obtain n power flow sections of the power grid includes: Take the state estimation section of the latest moment in the multi-source and multi-period power grid data; The state estimation section includes simulation model information and current grid operation data, wherein the grid operation data includes multi-temporal data of power generation plan, load forecast, new energy output forecast, maintenance plan and tie line plan; The power grid model in the state estimation section is matched with the power grid operation data to form n power flow sections.

[0015] By adopting the above technical solution, the latest state estimation section is taken from the multi-source and multi-period power grid data. The state estimation section contains simulation model information and current power grid operation data. The power grid operation data fully reflects the actual situation of the current power grid, including multi-period information such as power generation plan, load forecast, and new energy output forecast, and also considers other influencing factors such as power grid maintenance and tie line plan. On the basis of obtaining sufficient state data, the state estimation section is matched with the pre-built power grid simulation model to generate multiple flow sections to reflect the power grid flow distribution state under different conditions. This multi-section generation method combined with the current detailed state data can make subsequent simulations more in line with the actual situation and improve the accuracy of the results. The obtained multi-section flow data can provide a detailed basis for the evaluation of the control strategy of distributed photovoltaic clusters.

[0016] Optionally, constructing a power grid model of the target area includes: The power grid engineering data of the target area is acquired, and the power grid model is constructed based on the power grid engineering data.

[0017] By adopting the above technical solution, by obtaining the power grid engineering data of the target area, these engineering data can fully and accurately reflect the network structure, line parameters and equipment conditions of the regional power grid. On the basis of obtaining sufficient power grid engineering data, a model of the regional power grid is further constructed based on these data. Compared with the simple typical system model, this power grid model based on actual engineering data can fully consider the actual situation of the regional power grid, making the model closer to the characteristics of the actual power grid. In the specific distributed photovoltaic cluster control simulation, this accurate power grid model can provide an accurate background environment, which helps to improve the accuracy of the simulation.

[0018] In a second aspect of the present application, a distributed photovoltaic cluster control simulation method system is provided, comprising: A data acquisition module is used to construct a power grid model of the target area and acquire multi-source and multi-period power grid data of the power grid in the target area based on the power grid model; The power flow section generation module is used to input the multi-source and multi-time period power grid data into a pre-established simulation model to obtain n power flow sections of the power grid.

[0019] In a third aspect of the present application, a computer storage medium is provided, wherein the computer storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the above method steps.

[0020] In the fourth aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the above method.

[0021] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. This application can obtain multi-source and multi-time period power grid data for the target area, including photovoltaic power generation forecast data, load forecast data, etc., by constructing a power grid model for the target area, so that the input data of the subsequent simulation model is more comprehensive and accurate, which is conducive to improving the accuracy of the simulation results. On the basis of obtaining accurate multi-source and multi-time period power grid data, the method inputs the power grid data into a pre-established simulation model for simulation analysis. Compared with a simple static model, the pre-established simulation model can fully consider the dynamic characteristics of the power grid. Through the comprehensive calculation of various types of data, the power grid flow distribution in multiple time periods can be obtained, thereby improving the accuracy of the distributed photovoltaic control simulation. The obtained power grid flow section reflects the detailed operating status of the power grid in the target area, and provides effective support for the formulation and evaluation of subsequent distributed photovoltaic cluster control strategies.

[0022] 2. This application can distinguish the power generation characteristics of different photovoltaic equipment by obtaining the equipment model of each distributed photovoltaic power station in the target area. On the basis of knowing the equipment model, combined with the meteorological data obtained in the preset time period of the target area as input, the preset photovoltaic power generation prediction model is input. The prediction model can accurately predict the photovoltaic power generation and power generation probability in different time periods within the preset time period according to the meteorological data of different time periods and the power generation characteristics of different equipment models. Compared with simple meteorological data prediction, this method can improve the accuracy of photovoltaic power generation prediction by considering equipment differences. The obtained photovoltaic power generation prediction data for different time periods, as an important part of multi-source and multi-time period power grid data, helps to improve the accuracy of subsequent distributed photovoltaic cluster control simulation, make the simulation results more in line with the actual situation, and provide support for the formulation of scientific and reasonable control strategies.

[0023] 3. This application can establish a mathematical model between sample data and actual power generation by fitting the preset photovoltaic power generation sample data, and use the least squares method and polynomial regression algorithm to reduce the fitting error. On the basis of obtaining the sample data after accurate fitting, a photovoltaic power generation prediction model is further constructed, and the model is trained to continuously optimize its parameters, thereby obtaining a preset prediction model with higher accuracy. Among them, the training process makes full use of the rich photovoltaic power generation sample data containing equipment information, power generation data and meteorological data, so that the prediction model can adapt to the influence of different equipment conditions and meteorological environment, and the prediction results are more accurate and reliable. The preset photovoltaic power generation prediction model obtained by this method can provide strong support for the subsequent acquisition of multi-source and multi-period power grid data, help to improve the overall effect of distributed photovoltaic cluster control simulation, make the simulation results more in line with the actual situation, and provide a basis for the planning and control decisions of photovoltaic clusters. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A schematic diagram of a distributed photovoltaic cluster control simulation method provided in an embodiment of the present application; Figure 2 An architecture diagram of a distributed photovoltaic cluster control simulation system provided in an embodiment of the present application; Figure 3 A schematic diagram of the structure of an electronic device provided in this application. DETAILED DESCRIPTION

[0025] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0026] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0027] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0028] In order to facilitate understanding of the method and system provided by the embodiments of the present application, before introducing the embodiments of the present application, the background of the embodiments of the present application is first introduced.

[0029] As the scale of distributed photovoltaic power generation continues to expand, its random fluctuations have brought challenges to the operation of the power grid. How to achieve the effective use of distributed photovoltaics and the stable operation of the power grid has become an urgent problem to be solved. Distributed photovoltaic power generation has the characteristics of small capacity, dispersed geographical location and large power generation fluctuations, which brings difficulties to its reasonable and effective dispatching and control. The use of simulation methods to simulate and verify different control strategies can provide important decision-making support. However, the existing distributed photovoltaic control simulation models and methods have problems such as inaccurate prediction and large amount of calculation, resulting in large deviations in simulation results and unable to meet the needs of engineering applications. Therefore, it is urgent to propose a distributed photovoltaic control simulation method with higher computational efficiency and more accurate prediction to improve the accuracy of simulation results and provide strong support for power grid companies to formulate scientific control strategies.

[0030] After the background introduction of the above content, those skilled in the art can understand the problems existing in the prior art. The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments.

[0031] Based on the above background technology, please refer to Figure 1 , Figure 1A flow chart of a distributed photovoltaic cluster control simulation method provided in an embodiment of the present application. The system can be implemented by a computer program or run as an independent tool application. Specifically, in an embodiment of the present application, the method can be applied on a server, but can also be applied to electronic devices such as servers. A distributed photovoltaic cluster control simulation method includes the following steps: S101, constructing a power grid model of a target area, and acquiring multi-source and multi-period power grid data of a power grid in the target area based on the power grid model; Specifically, in order to improve the accuracy of the subsequent distributed photovoltaic cluster control simulation, an accurate power grid model of the target area is first constructed. The scope of the target area is determined, and then the power grid operation data of the area is comprehensively collected, including detailed information such as power grid topology, node parameters, and line parameters. On the basis of fully obtaining regional power grid data, the traditional pure static power system modeling method is adopted to establish a regional static power grid model containing components such as generators, loads, transformers, and lines. Then, the dynamic characteristics of the power grid are considered on this static model to form a regional dynamic power grid model. The established target regional power grid model can fully reflect the electrical characteristics and dynamic response characteristics of the regional power grid. After obtaining an accurate regional power grid model, the load curve, power generation curve, photovoltaic power generation curve and other data of the power grid in multiple time periods can be obtained based on the model to form multi-source and multi-time grid data of the target area, providing an accurate background environment model and detailed input data for the subsequent photovoltaic cluster control simulation.

[0032] Based on the above embodiment, as an optional embodiment, the multi-source multi-time period grid data includes photovoltaic predicted power generation in different time periods within a preset time period; the obtaining photovoltaic predicted power generation in different time periods within the preset time period includes: S201, obtaining meteorological data within a preset time period of each target area and the equipment model of each distributed photovoltaic power station in the target area; Specifically, in order to improve the accuracy of photovoltaic power generation prediction, it is necessary to consider the impact of regional meteorological conditions and differences in photovoltaic power station equipment. First, determine the scope of the target area and obtain historical meteorological data of the target area. At the same time, investigate and count the model information of each distributed photovoltaic power station in the area, such as polycrystalline silicon battery packs or thin-film battery packs. Then, process the historical meteorological data to obtain meteorological forecast data for different locations in the area within a preset time period. Combining meteorological data and power station equipment models, a photovoltaic power generation prediction model that considers equipment differences can be established. Using this model, the power generation of each power station in each period can be accurately predicted based on the meteorological parameters of different time periods and different equipment, and a probability prediction interval can also be given. Obtaining accurate equipment model information can improve the accuracy of the prediction results. The obtained photovoltaic power generation forecast data can be used as an important part of multi-source power grid data for subsequent distributed photovoltaic cluster control simulation.

[0033] S202, inputting the meteorological data into a preset photovoltaic power generation prediction model, and outputting the predicted photovoltaic power generation and power generation probability at different time periods within a preset time period.

[0034] Specifically, in order to improve the accuracy of photovoltaic power generation prediction, it is necessary to establish a prediction model that comprehensively considers meteorological factors. After obtaining the meteorological monitoring data of each distributed photovoltaic power station in the target area, a power generation prediction model based on an artificial neural network algorithm is constructed. The model has been pre-trained and can consider the influence of multiple meteorological factors such as temperature, humidity, and wind speed. The actual meteorological data obtained are input into the constructed prediction model in chronological order. The model can calculate the predicted power generation value of each power station in this period based on the input meteorological parameters. At the same time, the model can give the power generation range under different probabilities based on multiple simulations to reflect the uncertainty of the prediction. Compared with the prediction of a single meteorological factor, the comprehensive multi-factor prediction model can fully consider the comprehensive influence of different meteorological conditions and improve the accuracy of power generation prediction. The power generation prediction data and probability interval information obtained can be used as important input data for subsequent distributed photovoltaic cluster control simulation.

[0035] Based on the above embodiment, as an optional embodiment, obtaining the preset photovoltaic power generation prediction model includes: S301, according to preset photovoltaic power generation sample data, fitting processing is performed on the photovoltaic power generation sample data by using a least square method and a polynomial regression algorithm to obtain photovoltaic power generation sample data after fitting processing; Specifically, in order to improve the fitting accuracy of the photovoltaic power generation prediction model, it is necessary to accurately fit the curve of the sample data. First, the power generation sample data of a photovoltaic power station in the past year and the meteorological data of the corresponding period are collected. Then the polynomial regression algorithm is used to establish a mathematical relationship model between power generation and meteorological factors. In the process of model establishment, the least squares method is used to continuously optimize the parameters of the model so that the sum of square errors between the fitting curve and the sample data is minimized. After multiple iterations of optimization, a power generation fitting model that takes into account multiple factors such as temperature and humidity and minimizes errors can be obtained. This model can accurately reflect the curve characteristics of the sample data and filter out the influence of sampling errors. When constructing a photovoltaic power generation prediction model in the future, this high-precision fitting model can improve the accuracy of the prediction results. The obtained prediction data will provide important support for the planning and regulation of photovoltaic clusters.

[0036] On the basis of the above embodiment, as an optional embodiment, according to the preset photovoltaic power generation sample data, the photovoltaic power generation sample data is fitted by the least square method and the polynomial regression algorithm to obtain the photovoltaic power generation sample data after fitting, and based on the photovoltaic power generation sample data after fitting, a photovoltaic power generation remaining life prediction model is constructed, including: S401, classifying the preset photovoltaic power generation sample data based on the photovoltaic power generation equipment information, and classifying the photovoltaic power generation sample data with the same photovoltaic power generation equipment information into one category; Specifically, in order to improve the accuracy of photovoltaic power generation curve fitting, the differences between different types of equipment need to be considered. First, collect the power generation sample data of multiple photovoltaic power stations in the past year, and record the equipment parameters of each sample power station, such as monocrystalline silicon, polycrystalline silicon, thin-film photovoltaic modules and other information. Then classify the sample data according to the equipment type information, and classify the sample data of the same type of equipment into one category. In this way, multiple groups of power generation sample data sets of the same type of equipment can be obtained. For each type of equipment, a power generation fitting model is established separately. Because the power generation characteristics of the same type of equipment are similar, this classification fitting method can improve the fitting accuracy and obtain a more accurate curve model. When constructing the photovoltaic power generation prediction model in the future, these high-quality fitting models can improve the accuracy of the prediction and better guide the operation and management of photovoltaic power stations.

[0037] S402, performing fitting processing on photovoltaic power generation sample data with the same device information by using a least square method and a polynomial regression algorithm to obtain photovoltaic power generation sample data after fitting processing.

[0038] Specifically, in order to obtain more accurate power generation curves specific to the equipment type, it is necessary to use an efficient algorithm to optimize the fitting of the sample data. After classifying the sample data by equipment type, a polynomial regression model is established for each type of sample. Then the least squares method is used to iterate continuously to minimize the sum of the squares of the distances from each sample point to the fitting curve to eliminate the influence of random errors. After multiple optimization iterations, a set of best fitting curves for this type of equipment can be obtained. These fitting models can accurately reflect the power generation characteristics of each type of photovoltaic equipment, such as the mapping relationship between the power generation and temperature of monocrystalline silicon modules. Using these high-precision equipment-specific fitting models, a more accurate photovoltaic power generation prediction model can be established. The prediction results will also be more in line with the power generation laws of photovoltaic power station equipment actually operating in the area, thereby guiding the scientific management of equipment.

[0039] S302, based on the photovoltaic power generation sample data after the fitting process, construct the photovoltaic power generation prediction model, and train the photovoltaic power generation prediction model to obtain the preset photovoltaic power generation prediction model, wherein the photovoltaic power generation sample data includes: equipment information of multiple photovoltaic power station samples, photovoltaic power station power generation sample data and meteorological sample data of a preset area.

[0040] Specifically, in order to further improve the accuracy of photovoltaic power generation prediction, it is necessary to establish and train a prediction model that comprehensively considers influencing factors. After polynomial fitting of the sample data, the data points of these fitting curves are used as training samples, and the power generation prediction model is constructed using an artificial neural network algorithm. The model contains multiple input layer nodes, which can simultaneously receive input of information such as equipment model, historical power generation data and meteorological data. A large amount of training data enables the model to learn the complex mapping relationship of photovoltaic power generation. Then, through multiple training iterations to optimize the network weights, a preset prediction model with a good fitting effect on the sample data is finally obtained. The model comprehensively considers equipment differences, historical laws and meteorological influencing factors, and can accurately predict the newly input meteorological information. The accurate prediction results obtained can provide support for the scientific planning of distributed photovoltaic clusters, and can also verify the effects of different regulation strategies.

[0041] S102, inputting the multi-source and multi-time period power grid data into a pre-established simulation model to obtain n power flow sections of the power grid.

[0042] Specifically, in order to evaluate the impact of photovoltaic clusters on the power grid under different circumstances, it is necessary to obtain the power flow distribution of the power grid under various circumstances. First, obtain the dynamic power grid model constructed in the target area, as well as multi-source and multi-period power grid data including multi-period load curves, power generation plans, photovoltaic power generation forecasts, etc. Then establish a power grid simulation model based on steady-state analysis, which contains detailed information such as power grid branch parameters and generator parameters. After obtaining sufficient input data and establishing an accurate simulation model, the two are effectively matched, that is, the multi-period power grid data is configured to the corresponding time of the simulation model to form steady-state simulation cases for multiple periods. Start the simulation calculation for each case, and you can get the voltage, phase angle and other information of all nodes in the power grid in that period, reflecting the power flow distribution of the power grid in that period, and finally form the power flow section results for multiple periods. These sections reflect the operating status of the power grid in the target area under different circumstances, and provide detailed basic data for the subsequent evaluation of the impact of photovoltaic cluster regulation strategies.

[0043] It should be noted that a power flow section refers to a snapshot of the state of the power system at a specific moment, including the voltage magnitude and phase angle of each node in the power grid, as well as the power flow of each transmission line and transformer. Power flow sections are usually conducted under steady-state conditions, that is, it is assumed that the system's load and power generation conditions do not change over time. The stability analysis, planning, and operation optimization of the power system all rely on the results of power flow section analysis.

[0044] Based on the above embodiment, as an optional embodiment, the multi-source multi-period power grid data input board is used to pre-establish a simulation model to obtain n power flow sections of the power grid, including: S501, obtaining a state estimation section at the latest moment in multi-source and multi-period power grid data; Specifically, in order to make the power grid simulation more in line with the current actual situation, it is necessary to obtain the latest power grid state data as the input of the simulation. First, the power grid topology and parameter data are extracted from the constructed regional dynamic power grid model as basic data. Then, the load data, power generation data, power dispatch data and other information at each time of the day are collected from the SCADA real-time monitoring system of the power grid. When simulating, select the latest moment, such as the current moment, and extract its load value, power generation output value, AC line power and other information from the real-time data, and combine it with the power grid model to form the state estimation section data at the current moment. These data can reflect the actual operating status of the current power grid. When using this data for subsequent simulation, the simulation results can be made more in line with the actual situation of the power grid, providing an important reference for evaluating the impact of distributed photovoltaic clusters on the power grid.

[0045] S502 The state estimation section includes simulation model information and current grid operation data, wherein the grid operation data includes multi-temporal data of power generation plan, load forecast, new energy output forecast, maintenance plan and tie line plan; Specifically, the state estimation section contains both the information in the pre-built power grid simulation model and the actual operation data of the power grid at the current moment. The information provided by the power grid model includes static data such as the topology, line parameters, and load of the regional power grid. The current operation data contains dynamic information in many aspects, such as the planned power generation of the generator set at this moment, the estimated load value of each node from the load forecasting model, the photovoltaic power generation forecast value, and the equipment maintenance plan and line contact plan compiled by the operation and maintenance personnel. This information comprehensively reflects the state of the planned operation of the power grid at the current moment. The two types of data are organically combined to form a three-dimensional state estimation section that fully considers the static characteristics and dynamic state. This can make the subsequent power grid simulation closer to the actual situation and the evaluation results more reliable.

[0046] S503 matches the power grid model in the state estimation section with the power grid operation data to form n power flow sections.

[0047] Specifically, in order to evaluate the impact of photovoltaic clusters under different circumstances, it is necessary to obtain the power grid flow distribution data under multiple time states. First, obtain the state estimation section containing static model information and dynamic operation data. Then, in the steady-state power flow calculation platform, import the power grid model reflecting the static characteristics, input dynamic information such as real-time power generation load data in the state estimation section, and set multiple simulation time periods. By effectively matching the static model and dynamic data, multiple simulation cases of different time periods can be formed. By performing power flow calculations for each case, the corresponding multi-time period power flow results can be obtained, reflecting the power flow distribution of node voltage, line power, etc. in the time period. These section data can provide the basic operation status of the power grid under different scenarios, laying the foundation for the subsequent evaluation of the impact of photovoltaic cluster dispatching and control strategies.

[0048] Based on the above embodiment, as an optional embodiment, the target area is a county or district, and the meteorological data includes ambient temperature, relative humidity, wind speed, and air pressure.

[0049] Specifically, in order to improve the representativeness of meteorological data and the scope of application of photovoltaic power generation prediction, counties or districts are selected as target areas. The area is moderate, which can not only ensure the relative consistency of meteorological conditions, but also cover multiple distributed photovoltaic power stations. Obtaining regional meteorological data can effectively reflect the overall meteorological conditions of the area. These parameters comprehensively characterize the meteorological environment and are also key factors affecting photovoltaic power generation. After analyzing and processing the collected meteorological data, accurate meteorological input data can be provided for distributed photovoltaic power stations in the area. When establishing a photovoltaic power generation prediction model in the future, these high-quality meteorological data will help improve the accuracy of the prediction results and provide support for the evaluation of photovoltaic cluster control strategies.

[0050] Based on the above embodiment, as an optional embodiment, the step of constructing a power grid model of a target area includes: The power grid engineering data of the target area is acquired, and the power grid model is constructed based on the power grid engineering data.

[0051] Specifically, in order to make the constructed power grid model more consistent with the actual situation of the power grid in the target area, it is necessary to obtain sufficiently detailed power grid engineering data as a basis. First, the target area is determined to be a power grid within a provincial bureau level, and then the power grid planning and design information and actual operation data are collected from the power company in the region. These data include detailed information such as power grid topology diagram, line parameter table, substation equipment parameters, etc. After obtaining the complete power grid engineering data, the traditional static power grid modeling method is used to build an open line diagram model of the regional power grid based on the connection relationship, electrical parameters and other data of each line. The model established in this way can fully reflect the actual line and equipment conditions of the power grid in the target area. Simulation calculation based on an accurate power grid model can improve the accuracy of the results and have more reference value for evaluating the impact of photovoltaic clusters.

[0052] See also Figure 2 , Figure 2 An architecture diagram of a distributed photovoltaic cluster control simulation system provided in an embodiment of the present application, the distributed photovoltaic cluster control simulation system may include: A data acquisition module 1 is used to construct a power grid model of a target area and acquire multi-source and multi-period power grid data of a power grid in the target area based on the power grid model; The power flow section generation module 2 is used to input the multi-source and multi-time period power grid data into a pre-established simulation model to obtain n power flow sections of the power grid.

[0053] It should be noted that: when the system provided in the above embodiment realizes its functions, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0054] Please refer to Figure 3 The application also discloses an electronic device. Figure 3 It is a structural diagram of an electronic device disclosed in an embodiment of the present application. The electronic device 300 may include: at least one processor 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302. Among them, the communication bus 302 is used to realize the connection and communication between these components. Among them, the user interface 303 may include a display screen (Display), a camera (Camera), and the optional user interface 303 may also include a standard wired interface and a wireless interface. Among them, the network interface 304 may optionally include a standard wired interface and a wireless interface (such as a WI~FI interface).

[0055] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field~Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0056] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read~Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally be at least one storage system located away from the aforementioned processor 301. Refer to Figure 3 , the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application program of a distributed photovoltaic cluster control simulation method.

[0057] exist Figure 3 In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the application program storing the road assessment method in the memory 305. When executed by one or more processors 301, the electronic device 300 executes one or more methods in the above-mentioned embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited to the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application. In the above embodiments, the description of each embodiment has its own emphasis. For the parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0058] In the several implementations provided in this application, it should be understood that the disclosed system can be implemented in other ways. For example, the system embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of the system or unit can be electrical or other forms.

[0059] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0060] The present application also provides a computer storage medium that can store multiple instructions, which are suitable for being loaded and executed by a processor as described above. Figure 1 The road assessment method of the embodiment shown in the figure can be found in the specific implementation process. Figure 1 The specific description of the illustrated embodiment will not be repeated here.

[0061] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0062] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory, including a number of instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0063] The above are only exemplary embodiments of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present disclosure.

[0064] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not described in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A distributed photovoltaic cluster control simulation method, characterized in that: The method comprises: Constructing a power grid model of the target area, and acquiring multi-source and multi-period power grid data of the power grid in the target area based on the power grid model, wherein the multi-source and multi-period power grid data includes photovoltaic predicted power generation in different periods within a preset time period; The multi-source and multi-time period power grid data are input into a pre-established simulation model to obtain n power flow sections of the power grid.

2. A distributed photovoltaic cluster control simulation method according to claim 1, characterized in that: Obtaining the predicted photovoltaic power generation at different time periods within the preset time period, including: Acquire meteorological data within a preset time period of each target area and equipment model of each distributed photovoltaic power station within the target area; The meteorological data is input into a preset photovoltaic power generation prediction model to output the photovoltaic power generation prediction and power generation probability at different time periods within a preset time period.

3. A distributed photovoltaic cluster control simulation method according to claim 2, characterized in that: Obtaining the preset photovoltaic power generation prediction model includes: According to the preset photovoltaic power generation sample data, the photovoltaic power generation sample data is fitted by a least square method and a polynomial regression algorithm to obtain the photovoltaic power generation sample data after fitting; Based on the photovoltaic power generation sample data after the fitting process, the photovoltaic power generation prediction model is constructed, and the photovoltaic power generation prediction model is trained to obtain the preset photovoltaic power generation prediction model, wherein the photovoltaic power generation sample data includes: equipment information of multiple photovoltaic power station samples, photovoltaic power station power generation sample data and meteorological sample data of a preset area.

4. A distributed photovoltaic cluster control simulation method according to claim 2, characterized in that: The target area is a county or district, and the meteorological data includes ambient temperature, relative humidity, wind speed, and air pressure.

5. A distributed photovoltaic cluster control simulation method according to claim 3, characterized in that: According to the preset photovoltaic power generation sample data, the photovoltaic power generation sample data is fitted by the least square method and the polynomial regression algorithm to obtain the photovoltaic power generation sample data after fitting, and based on the photovoltaic power generation sample data after fitting, a photovoltaic power generation remaining life prediction model is constructed, including: Classifying the preset photovoltaic power generation sample data based on the photovoltaic power generation equipment information, and classifying the photovoltaic power generation sample data with the same photovoltaic power generation equipment information into one category; Photovoltaic power generation sample data with the same equipment information are fitted by the least square method and the polynomial regression algorithm to obtain the fitted photovoltaic power generation sample data.

6. A distributed photovoltaic cluster control simulation method according to claim 1, characterized in that: The method of inputting the multi-source and multi-period power grid data into the board to establish a simulation model in advance and obtain n power flow sections of the power grid includes: Take the state estimation section of the latest moment in the multi-source and multi-period power grid data; The state estimation section includes simulation model information and current grid operation data, wherein the grid operation data includes multi-temporal data of power generation plan, load forecast, new energy output forecast, maintenance plan and tie line plan; The power grid model in the state estimation section is matched with the power grid operation data to form n power flow sections.

7. A distributed photovoltaic cluster control simulation method according to claim 1, characterized in that: The constructing of the power grid model of the target area includes: The power grid engineering data of the target area is acquired, and the power grid model is constructed based on the power grid engineering data.

8. A distributed photovoltaic cluster control simulation method system, characterized in that: The system comprises: A data acquisition module, used to construct a power grid model of a target area, and acquire multi-source and multi-period power grid data of a power grid in the target area based on the power grid model; The power flow section generation module is used to input the multi-source and multi-time period power grid data into a pre-established simulation model to obtain n power flow sections of the power grid.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: It includes a processor, a memory and a transceiver, the memory is used to store instructions, the transceiver is used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method according to any one of claims 1 to 7.

Citation Information

Cited By

  • Distributed power supply regulation and control scheduling method and data interaction module

    CN119298245A