Heavy overload advanced early warning method and system for high-proportion new energy power grid, electronic equipment and storage medium

Abstract

The invention discloses a high-proportion new energy power grid heavy overload advanced early warning method and system, electronic equipment and a storage medium, and the method comprises the steps: obtaining new energy historical data accessed to each node of a power grid, and carrying out the data preprocessing of the new energy historical data; performing new energy short-term prediction by adopting a long short-term memory network model based on the preprocessed new energy historical data to obtain a prediction result of new energy power of each node; based on the prediction result of the new energy power of each node, carrying out load flow calculation analysis of multiple time sections, and solving to obtain a power grid load flow distribution prediction result; and according to a power grid power flow distribution prediction result and a power grid equipment power flow threshold value, carrying out advanced early warning on predicted power grid equipment heavy overload. Based on short-term prediction of new energy, advanced early warning of possible heavy overload of power grid equipment is realized, the power grid operation situation prediction capability is improved, safe operation of a power grid is guaranteed, and new energy consumption of the power grid is promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a method, system, electronic equipment and storage medium for early warning of heavy overload in a high-proportion new energy power grid. Background Art

[0002] With the continuous increase in the number and scale of new energy sources, the large-scale and high-proportion access to the power grid, such as wind energy and solar energy, has the characteristics of randomness, intermittency and volatility. This will lead to power imbalance, equipment overload and other system safety risks in the local power grid. In order to ensure the safety and stability of the power grid after the access of new energy sources, it is particularly important to provide advance warning for possible power grid operation risks such as equipment overload when a high proportion of new energy sources are connected to the power grid.

[0003] At present, the analysis of possible operation risks of power grids in the future period mainly considers the impact of equipment out of operation due to maintenance or failure on the power grid. There are relatively few studies on the quantitative analysis of the impact of large-scale access to new energy and the volatility of its output. There is still a lack of effective advance warning methods for safety risks such as heavy overload of power grid equipment caused by high proportion of new energy access to the power grid. Based on the above analysis, it is necessary to carry out research on advance warning technology for heavy overload of power grids with high proportion of new energy to provide technical support for ensuring the safe operation of the power grid. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the above existing problems, the present invention is proposed.

[0006] Therefore, the present invention provides a method, system, electronic device and storage medium for advance warning of heavy overload of a high-proportion new energy power grid to solve the problem of lack of effective advance warning means for safety risks such as heavy overload of power grid equipment caused by the access of a high proportion of new energy to the power grid.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, the present invention provides a method for early warning of heavy overload of a high-proportion new energy power grid, comprising:

[0009] Obtain the historical data of new energy connected to each node of the power grid, and perform data preprocessing on the historical data of new energy;

[0010] Based on the preprocessed new energy historical data, the long short-term memory network model is used to perform short-term prediction of new energy and obtain the prediction results of the new energy power of each node;

[0011] Based on the prediction results of the new energy power of each node, multi-time section power flow calculation and analysis are performed to obtain the power grid power flow distribution prediction results;

[0012] According to the grid power flow distribution prediction results and the threshold value of the grid equipment power flow, advance warning is given for the predicted heavy overload of the grid equipment.

[0013] As a preferred solution of the method for early warning of heavy overload of a high-proportion new energy power grid according to the present invention, wherein:

[0014] The method of using the long short-term memory network model to perform short-term prediction of new energy includes the following steps:

[0015] By screening the parameters of the long short-term memory model, the long short-term memory network model is optimized;

[0016] The preprocessed new energy historical data is used as network input information and input into the optimized LSTM network model for prediction analysis;

[0017] Output the new energy power prediction results based on historical data.

[0018] As a preferred solution of the method for early warning of heavy overload of a high-proportion new energy power grid according to the present invention, wherein:

[0019] The method of optimizing the long short-term memory network model by screening the long short-term memory model parameters comprises the following steps:

[0020] Set different numbers of long short-term memory hidden layers and hidden layer neurons, and conduct comparative analysis on the training speed and prediction accuracy of the models under different settings;

[0021] The number of hidden layers and the number of hidden layer neurons with the highest prediction accuracy and the fastest training speed are selected as the long short-term memory model parameters for new energy prediction.

[0022] As a preferred solution of the method for early warning of heavy overload of a high-proportion new energy power grid according to the present invention, wherein:

[0023] The method of performing multi-time section power flow calculation and analysis based on the prediction results of the new energy power of each node to obtain the power grid power flow distribution prediction results includes the following steps:

[0024] By taking the new energy power forecast results as input, a future period power flow calculation model taking into account the new energy power forecast results is constructed;

[0025] Define the time range for multi-time section power flow calculation and analysis, and select a suitable analysis time window;

[0026] In the set time window, the threshold is set as a time section, and a power flow calculation is performed based on a time section plan value and forecast data;

[0027] According to a selected time section, the power flow calculation is repeated within the analysis time window until all the predetermined time sections are completed;

[0028] By calculating the power flow at each time section, the power grid power flow distribution forecast results for a period of time in the future are obtained.

[0029] As a preferred solution of the method for early warning of heavy overload of a high-proportion new energy power grid according to the present invention, wherein:

[0030] The future time period power flow calculation model taking into account the new energy power forecast results is expressed as:

[0031]

[0032] Where T represents the Tth future period, PG i is the predicted output value of the renewable energy at the i-th node in this period, PD i is the power of the i-th node load in this period, V i and V j are the voltage amplitudes of the i-th node and the j-th node in this period, θ i and θ j are the voltage phase angles of the i-th node and the j-th node in this period, S i Node is the set of nodes that are interconnected with the ith node by lines, G ij and B ij are the conductance and susceptance of the connection line between the ith node and the jth node, respectively.

[0033] As a preferred solution of the method for early warning of heavy overload of a high-proportion new energy power grid according to the present invention, wherein:

[0034] The method of providing advance warning for predicted heavy overload of power grid equipment according to the power grid flow distribution prediction result and the threshold value of the power grid equipment flow includes the following steps:

[0035] Compare the predicted active power of the grid equipment in the future period with the power flow threshold value of the equipment;

[0036] If the predicted active power exceeds the equipment overload threshold, the power grid equipment is overloaded;

[0037] If the predicted active power exceeds the equipment overload threshold, the power grid equipment is overloaded;

[0038] Issue early warning for equipment that will be heavily overloaded in the future according to the power flow distribution forecast results;

[0039] The equipment overload threshold is 80% of the equipment rated power;

[0040] The device overload threshold is the rated power of the device.

[0041] In a second aspect, the present invention provides a high-proportion new energy power grid heavy overload advance warning system, comprising:

[0042] The data acquisition module is used to obtain the historical data of new energy connected to each node of the power grid and perform data preprocessing on the historical data of new energy;

[0043] The new energy power prediction module is used to perform short-term prediction of new energy based on the pre-processed new energy historical data using the long short-term memory network model to obtain the prediction results of the new energy power of each node;

[0044] The power flow calculation module is used to perform power flow calculation and analysis on multiple time sections based on the prediction results of the new energy power of each node, and obtain the power grid power flow distribution prediction results;

[0045] The power grid heavy overload advance warning module is used to provide advance warning for predicted heavy overload of power grid equipment based on the power grid flow distribution prediction results and the threshold value of the power grid equipment flow.

[0046] As a preferred solution of the high-proportion new energy power grid heavy overload advance warning system described in the present invention, wherein:

[0047] An optimization module is used to optimize the long short-term memory network model by screening the long short-term memory model parameters;

[0048] The input module is used to input the preprocessed new energy historical data as network input information into the optimized LSTM network model for predictive analysis;

[0049] The output module is used to output the new energy power prediction results obtained based on historical data.

[0050] In a third aspect, the present invention provides a computing device, comprising:

[0051] Memory, used to store programs;

[0052] A processor is used to execute the computer executable instructions, which, when executed by the processor, implement the steps of the high-proportion new energy power grid heavy overload advance warning method.

[0053] In a fourth aspect, the present invention provides a computer-readable storage medium, comprising: when the program is executed by a processor, the steps of implementing the method for advance warning of severe overload of a high-proportion new energy power grid are implemented.

[0054] The beneficial effects of the present invention are as follows: the present invention uses an LSTM network model to predict the new energy power of each node in a data-driven manner, and combines the short-term prediction results of new energy to perform multi-time section power grid flow calculation and analysis, so as to achieve advance warning of heavy overloads of power grid equipment that may occur in the future, which helps to improve the power grid operation status prediction capability, ensure the safe operation of the power grid, and promote the consumption of new energy in the power grid, and has good application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0056] Figure 1 A basic flow chart of a method for early warning of severe overload in a power grid with a high proportion of new energy provided by an embodiment of the present invention;

[0057] Figure 2 A system schematic diagram of a method for early warning of severe overload in a high-proportion new energy power grid provided by an embodiment of the present invention;

[0058] Figure 3 A graph of the forecast results of new energy output on December 1, 2023 for a method for advance warning of severe overload of a high-proportion new energy power grid provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0059] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0060] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0061] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0062] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0063] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0064] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0065] Example 1

[0066] Referring to the figure, an embodiment of the present invention provides a method for early warning of heavy overload of a high-proportion new energy power grid, including:

[0067] S1: Obtain the historical data of new energy sources connected to each node of the power grid, and perform data preprocessing on the historical data of new energy sources;

[0068] In the embodiment of the present application, the new energy historical data is the new energy historical measured power;

[0069] In the embodiment of the present application, the time range for obtaining the historical data of the new energy connected to each node of the power grid is the past three months. If it is less than three months, all historical data are obtained; the sampling frequency is to collect measured data once every 15 minutes;

[0070] In an embodiment of the present application, data preprocessing of new energy historical data includes: removing abnormal data in the new energy historical data and completing missing data.

[0071] S2: Based on the pre-processed new energy historical data, the long short-term memory network model is used to perform short-term prediction of new energy and obtain the prediction results of the new energy power of each node;

[0072] In the embodiment of the present application, a long short-term memory (LSTM) network model is used to perform short-term prediction of new energy to obtain the prediction result of the new energy power of each node, including the following steps:

[0073] Optimize the LSTM network model by screening LSTM model parameters;

[0074] The preprocessed new energy historical data is used as the network input information, and the optimized LSTM network model is used to perform predictive analysis and output the new energy power prediction results based on the historical data.

[0075] In an optional embodiment, different numbers of LSTM hidden layers and numbers of hidden layer neurons are set, and the training speed and prediction accuracy are compared and analyzed under different settings;

[0076] The number of hidden layers and neurons in the hidden layer with fast training speed and high prediction accuracy are used as the LSTM model parameters for subsequent new energy prediction;

[0077] The training results under different settings use the root mean square error RMSE indicator and the determination coefficient R 2 The indicators are used to compare the prediction accuracy, which is expressed as:

[0078]

[0079] Among them, Y pred is the predicted value, Y test is the verification value, n is the number of data;

[0080] When the root mean square error RMSE is the smallest, the determination coefficient R 2 When is maximum, the prediction accuracy is the highest.

[0081] S3: Based on the prediction results of the new energy power of each node, multi-time section power flow calculation and analysis are performed to obtain the power grid power flow distribution prediction results;

[0082] In the embodiment of the present application, based on the prediction results of the new energy power of each node, a power flow calculation analysis of multiple time sections is performed to obtain the power grid power flow distribution prediction results, including the following steps:

[0083] By taking the new energy power forecast results as input, a future period power flow calculation model taking into account the new energy power forecast results is constructed;

[0084] Define the time range for multi-time section power flow calculation and analysis, and select a suitable analysis time window;

[0085] In the set time window, the threshold is set as a time section, and a power flow calculation is performed based on a time section plan value and forecast data;

[0086] According to a selected time section, the power flow calculation is repeated within the analysis time window until all the predetermined time sections are completed;

[0087] By calculating the power flow at each time section, the power grid power flow distribution forecast results for a period of time in the future are obtained.

[0088] In the embodiment of the present application, the time range of the multi-time section power flow calculation and analysis is defined as the next 24 hours;

[0089] In the next 24 hours, every 15 minutes is regarded as a time section, and a power flow calculation is performed based on the planned value and forecast data every 15 minutes. A total of 96 future time periods are calculated to obtain the power grid power flow distribution prediction results of each time section.

[0090] In the embodiment of the present application, the future time period power flow calculation model taking into account the new energy power prediction result is expressed as:

[0091]

[0092] Where T represents the Tth future period, PG i is the predicted output value of the renewable energy at the i-th node in this period, PD i is the power of the i-th node load in this period, V i and V j are the voltage amplitudes of the i-th node and the j-th node in this period, θ i and θ j are the voltage phase angles of the i-th node and the j-th node in this period, S i Node is the set of nodes that are interconnected with the ith node by lines, G ij and B ij are the conductance and susceptance of the connection line between the ith node and the jth node, respectively.

[0093] S4: Based on the power grid flow distribution prediction results and the threshold value of the power grid equipment flow, advance warning is given for the predicted heavy overload of the power grid equipment.

[0094] In the embodiment of the present application, according to the power grid flow distribution prediction result and the threshold value of the power grid equipment flow, an advance warning is given to the predicted power grid equipment heavy overload, including the following steps:

[0095] Compare the predicted active power of the grid equipment in the future period with the power flow threshold value of the equipment;

[0096] If the predicted active power exceeds the equipment overload threshold, the power grid equipment is overloaded;

[0097] If the predicted active power exceeds the equipment overload threshold, the power grid equipment is overloaded;

[0098] Issue early warning for equipment that will be heavily overloaded in the future according to the power flow distribution forecast results;

[0099] The equipment overload threshold is 80% of the equipment rated power;

[0100] The device overload threshold is the rated power of the device.

[0101] It should be noted that the existing power grid overload warning method mainly considers the impact of equipment out of operation due to maintenance or failure on the power grid, lacks quantitative analysis of the impact of large-scale access to new energy and its output volatility, and is difficult to adapt to the current development status of power grids with a high proportion of new energy access. The method proposed in the present invention considers the uncertainty impact brought by large-scale access to new energy in a data-driven manner, realizes a more accurate advance warning of heavy overload of high-proportion new energy power grids, and ensures the safe operation of the power grid.

[0102] It should be noted that the future time period power flow calculation model formula taking into account the new energy power forecast results is improved on the basis of the existing formula. The new energy forecast output in the future time period replaces the conventional generator set output in the traditional power flow formula, thereby realizing the calculation of the corresponding power grid power flow distribution forecast results for the future time period.

[0103] This embodiment also provides a high-proportion new energy power grid heavy overload advance warning system, including:

[0104] The data acquisition module is used to obtain the historical data of new energy connected to each node of the power grid and perform data preprocessing on the historical data of new energy;

[0105] The new energy power prediction module is used to perform short-term prediction of new energy based on the pre-processed new energy historical data using the long short-term memory network model to obtain the prediction results of the new energy power of each node;

[0106] The power flow calculation module is used to perform power flow calculation and analysis on multiple time sections based on the prediction results of the new energy power of each node, and obtain the power grid power flow distribution prediction results;

[0107] The power grid heavy overload advance warning module is used to provide advance warning for predicted heavy overload of power grid equipment based on the power grid flow distribution prediction results and the threshold value of the power grid equipment flow.

[0108] Furthermore, an optimization module is used to optimize the long short-term memory network model by screening the long short-term memory model parameters;

[0109] The input module is used to input the preprocessed new energy historical data as network input information into the optimized LSTM network model for predictive analysis;

[0110] The output module is used to output the new energy power prediction results obtained based on historical data.

[0111] Furthermore, it also includes:

[0112] Memory, used to store programs;

[0113] A processor is used to load the program to execute the high-proportion new energy power grid heavy overload advance warning method.

[0114] This embodiment also provides a computer-readable storage medium storing a program, which, when executed by a processor, implements the method for advance warning of heavy overload of a high-proportion new energy power grid.

[0115] The storage medium proposed in this embodiment and the high-proportion new energy power grid heavy overload advance warning method proposed in the above embodiment belong to the same inventive concept. The technical details not described in detail in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0116] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ReadOnly, Memory, ROM), random access memory (RandomAccess Memory, RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform the methods of various embodiments of the present invention.

[0117] Example 2

[0118] Reference Figure 3 Tables 1-2 are an embodiment of the present invention, which provides a method for advance warning of heavy overload of a high-proportion new energy power grid. In order to verify its beneficial effects, a specific example of advance warning of heavy overload of power grid equipment is provided.

[0119] The specific embodiments are as follows:

[0120] In this embodiment, the historical measured power of new energy connected to each node of a regional power grid from September 1 to November 30, 2023 is obtained, and the historical data of new energy is preprocessed; the LSTM model parameters for short-term prediction of new energy are screened, and the LSTM network model is optimized: by setting different numbers of LSTM hidden layers and numbers of hidden layer neurons, the training speed and prediction accuracy are statistically analyzed under different settings, and the statistical results are shown in Table 1:

[0121] Table 1 Statistics of LSTM training results under different numbers of hidden layers and neurons

[0122] Number of hidden layers Number of neurons in the hidden layer RMSE <![CDATA[R 2 ]]> Training speed / s 1 100 35.2984 0.9396 8.1 1 200 45.1525 0.9014 20.8 2 100 29.7771 0.9571 19.5 2 200 45.0323 0.9024 51.4 3 100 39.4635 0.925 30.7

[0123] As shown in Table 1, when the number of hidden layers is 2 and the number of neurons is 100, the root mean square error RMSE is the smallest, the correlation index R2 is the largest, and the training speed is low. Therefore, the number of LSTM hidden layers is set to 2 and the number of hidden layer neurons is set to 100.

[0124] The optimized LSTM model is used to perform short-term forecasting of new energy for the preprocessed new energy historical data. The predicted output of new energy connected to a node in the power grid within one day on December 1, 2023 is as follows: Figure 3 shown.

[0125] According to the prediction results of the new energy power of each node, based on the planned value and forecast data every 15 minutes, the power flow calculation and analysis is carried out for 96 future time periods within one day on December 1, 2023, and the corresponding power grid power flow distribution prediction results are calculated;

[0126] According to the obtained power grid flow distribution prediction results and the threshold value of the power grid equipment flow, an advance warning is given for the possible overload of the power grid equipment. The warning situation is shown in Table 2:

[0127] Table 2 Power grid equipment heavy overload advance warning situation table

[0128]

[0129] In summary, the power grid equipment heavy overload advance warning method of the present invention can obtain the power grid equipment heavy overload advance warning results in the future period. Compared with the traditional power grid risk warning method, it takes into account the uncertainty impact brought by the large-scale access of new energy through a data-driven approach, and realizes a more accurate advance warning of the operation risks such as heavy overload of power grid equipment after a high proportion of new energy is connected, thereby ensuring the safe operation of the power grid.

[0130] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for early warning of heavy overload of a high-proportion new energy power grid, characterized in that: include: Obtain the historical data of new energy connected to each node of the power grid, and perform data preprocessing on the historical data of new energy; Based on the preprocessed new energy historical data, the long short-term memory network model is used to perform short-term prediction of new energy and obtain the prediction results of the new energy power of each node; Based on the prediction results of the new energy power of each node, multi-time section power flow calculation and analysis are performed to obtain the power grid power flow distribution prediction results; According to the grid power flow distribution prediction results and the threshold value of the grid equipment power flow, advance warning is given for the predicted heavy overload of the grid equipment.

2. The method for early warning of heavy overload of a high-proportion new energy power grid according to claim 1, characterized in that: The method of using the long short-term memory network model to perform short-term prediction of new energy includes the following steps: By screening the parameters of the long short-term memory model, the long short-term memory network model is optimized; The preprocessed new energy historical data is used as network input information and input into the optimized LSTM network model for prediction analysis; Output the new energy power prediction results based on historical data.

3. The high-proportion new energy power grid heavy overload advance warning method according to claim 1 or 2, characterized in that: The method of optimizing the long short-term memory network model by screening the long short-term memory model parameters comprises the following steps: Set different numbers of long short-term memory hidden layers and hidden layer neurons, and conduct comparative analysis on the training speed and prediction accuracy of the models under different settings; The number of hidden layers and the number of hidden layer neurons with the highest prediction accuracy and the fastest training speed are selected as the long short-term memory model parameters for new energy prediction.

4. The method for early warning of heavy overload of a high-proportion new energy power grid according to claim 3, characterized in that: The method of performing multi-time section power flow calculation and analysis based on the prediction results of the new energy power of each node to obtain the power grid power flow distribution prediction results includes the following steps: By taking the new energy power forecast results as input, a future period power flow calculation model taking into account the new energy power forecast results is constructed; Define the time range for multi-time section power flow calculation analysis and select an analysis time window; In the set time window, the threshold is set as a time section, and a power flow calculation is performed based on a time section plan value and forecast data; According to a selected time section, the power flow calculation is repeated within the analysis time window until all the predetermined time sections are completed; By calculating the power flow at each time section, the power grid power flow distribution forecast results for a period of time in the future are obtained.

5. The method for early warning of heavy overload of a high-proportion new energy power grid according to claim 4, characterized in that: The future time period power flow calculation model taking into account the new energy power forecast results is expressed as: Where T represents the Tth future period, PG i is the predicted output value of the renewable energy source at the i-th node in this period, PD i is the power of the i-th node load in this period, V i and V j are the voltage amplitudes of the i-th node and the j-th node in this period, θ i and θ j are the voltage phase angles of the i-th node and the j-th node in this period, S i Node is the set of nodes that are interconnected with the ith node by lines, G ij and B ij are the conductance and susceptance of the connection line between the ith node and the jth node, respectively.

6. The method for early warning of heavy overload of a high-proportion new energy power grid according to claim 5, characterized in that: The method of providing advance warning for predicted heavy overload of power grid equipment according to the power grid flow distribution prediction result and the threshold value of the power grid equipment flow includes the following steps: Compare the predicted active power of the grid equipment in the future period with the power flow threshold value of the equipment; If the predicted active power exceeds the equipment overload threshold, the power grid equipment is overloaded; If the predicted active power exceeds the equipment overload threshold, the power grid equipment is overloaded; Issue early warning for equipment that will be heavily overloaded in the future according to the power flow distribution forecast results; The equipment overload threshold is 80% of the equipment rated power; The device overload threshold is the rated power of the device.

7. A system for realizing advanced warning of heavy overload of high-proportion new energy power grid, characterized by: The data acquisition module is used to obtain the historical data of new energy connected to each node of the power grid and perform data preprocessing on the historical data of new energy; The new energy power prediction module is used to perform short-term prediction of new energy based on the pre-processed new energy historical data using the long short-term memory network model to obtain the prediction results of the new energy power of each node; The power flow calculation module is used to perform power flow calculation and analysis on multiple time sections based on the prediction results of the new energy power of each node, and obtain the power grid power flow distribution prediction results; The power grid heavy overload advance warning module is used to provide advance warning for predicted heavy overload of power grid equipment based on the power grid flow distribution prediction results and the threshold value of the power grid equipment flow.

8. The high-proportion new energy power grid heavy overload advance warning system according to claim 7 is characterized by: An optimization module is used to optimize the long short-term memory network model by screening the long short-term memory model parameters; The input module is used to input the preprocessed new energy historical data as network input information into the optimized LSTM network model for predictive analysis; The output module is used to output the new energy power prediction results obtained based on historical data.

9. An electronic device, characterized in that: include: Memory, used to store programs; A processor is used to load the program to execute the steps of the high-proportion new energy power grid heavy overload advance warning method as described in any one of claims 1-7.

10. A computer-readable storage medium storing a program, characterized in that: When the program is executed by the processor, the steps of the high-proportion new energy power grid heavy overload advance warning method as described in any one of claims 1-7 are implemented.

Images