Power supply guaranteeing method, system and equipment for monitoring real-time state of power grid and medium

Abstract

The invention relates to the technical field of power grid monitoring, and discloses a power supply guaranteeing method, system and device for power grid real-time state monitoring and a medium, and the method comprises the steps: obtaining first data of a target power grid, and carrying out the first preprocessing of the first data, and obtaining a second data set; the method comprises the steps of presetting a first rule base, establishing a first static prediction model, establishing a second dynamic prediction model, and obtaining a real-time state monitoring result and prediction feedback information based on first data in combination with the first static prediction model and the second dynamic prediction model. The accuracy of power supply risk level prediction is improved, and accurate prediction of a future power supply state is realized, so that corresponding measures can be taken in time, and stable operation of a power grid is ensured. And a powerful technical guarantee is provided for safe operation of a power grid. Real-time state monitoring and power supply guaranteeing of the mountainous area micro-grid are achieved, the power supply reliability and stability are remarkably improved, and an innovative solution is provided for development of an intelligent power grid.

Description

Technical Field

[0001] This application relates to the field of power grid monitoring technology, and in particular to a method, system, equipment and medium for real-time power grid status monitoring and power supply assurance. Background Technology

[0002] With the rapid development of smart grid technology, microgrids, as an important carrier of distributed energy, have been widely used in remote mountainous areas and other regions where traditional power grids are difficult to cover. However, the operating environment of microgrids in mountainous areas is complex, the output of distributed energy sources (such as photovoltaic, wind power, and small hydropower stations) fluctuates greatly, and extreme weather events (such as rainstorms, snowstorms, and lightning) occur frequently, which can easily lead to equipment failure or power outages.

[0003] Existing technologies typically employ traditional real-time monitoring systems and static risk assessment models. While these methods offer some monitoring and early warning capabilities, they suffer from significant limitations when processing multi-source heterogeneous data (such as meteorological data, equipment status data, and geographic information data). For example, traditional methods struggle to effectively integrate spatiotemporal data, resulting in low prediction accuracy. Furthermore, existing technologies lack adaptability to the unique geographical environment of mountain microgrids, failing to dynamically adjust power supply strategies to cope with extreme weather and load fluctuations. Therefore, there is an urgent need for an intelligent method that combines real-time monitoring and dynamic prediction to improve the reliability and stability of power supply in mountain microgrids. Summary of the Invention

[0004] In view of the aforementioned existing problems, this application is hereby filed.

[0005] Therefore, this application provides a power supply guarantee method, system, equipment and medium for real-time power grid status monitoring, which can solve the problem of fusion of multi-source heterogeneous data, improve prediction accuracy, adapt to the special geographical environment of mountain microgrids, dynamically adjust power supply strategies, and thus improve power supply reliability and stability.

[0006] To solve the above-mentioned technical problems, this application provides the following technical solution:

[0007] Firstly, this application provides a method for ensuring power supply through real-time monitoring of the power grid's status, including:

[0008] First data of the target power grid is acquired, and first preprocessing is performed on the first data to obtain a second dataset;

[0009] The first data is the real-time operating data of the target power grid;

[0010] The second dataset includes meteorological risk factors, equipment status factors, and geographical risk factors;

[0011] A first rule base is preset, which is used to obtain the target time-series power supply risk level based on the second dataset.

[0012] A first static prediction model is established, which is used to obtain the prediction result of the power supply status within a fixed time period in the future based on the target time-series power supply risk level.

[0013] A second dynamic prediction model is established based on the second dataset and the power supply status prediction results within a fixed future time period.

[0014] Based on the first data, combined with the first static prediction model and the second dynamic prediction model, real-time status monitoring results and prediction feedback information are obtained.

[0015] As a preferred embodiment of the power supply guarantee method for real-time power grid status monitoring described in this application, the second dynamic prediction model includes:

[0016] A second dynamic prediction model is established based on the topology of the target power grid.

[0017] Obtain the second dataset and the power supply status prediction results for a fixed future time period;

[0018] The second dynamic prediction model is initialized based on the second dataset and the power supply status prediction results within a fixed future time period;

[0019] The first data is input into the initialized second dynamic prediction model to dynamically update the model state variables.

[0020] As a preferred embodiment of the power supply guarantee method for real-time power grid status monitoring described in this application, the first static prediction model includes:

[0021] Preset neural network model;

[0022] Input the time series data and spatial series data into the neural network model;

[0023] The time-series data includes equipment processing, load demand, and meteorological data; the spatial-series data includes geographic information data.

[0024] The neural network is used to predict the power supply status within a future fixed period, which includes distributed energy output, load demand, and energy storage status.

[0025] This preferred scheme comprehensively considers multiple factors from both time and spatial series, enabling a more comprehensive and accurate prediction of power supply status. By incorporating diverse information such as equipment processing capacity, load demand, meteorological data, and geographic information data, the model can better capture the dynamic characteristics and spatial distribution features of the power grid operation, improving prediction accuracy. Furthermore, this preferred scheme can also predict key power supply indicators such as distributed energy output, load demand, and energy storage status, providing more refined decision support for power grid dispatch and operation, and contributing to the safe, stable, and efficient operation of the power grid.

[0026] As a preferred embodiment of the power supply guarantee method for real-time power grid status monitoring described in this application, wherein: obtaining the target time-series power supply risk level based on the second dataset includes:

[0027] Establish a fuzzy rule base based on the second dataset;

[0028] Calculate the membership degree of the output variable based on the fuzzy rule base;

[0029] The membership degree of the output variable is fuzzified, and the centroid method is used to calculate the specific value of the power supply risk level.

[0030] The meteorological risk factors include lightning activity intensity, rainfall, and wind speed; the equipment status factors include equipment failure probability, output fluctuation, and remaining energy storage capacity; and the geographical risk factors include terrain complexity and vegetation coverage.

[0031] As a preferred embodiment of the power supply guarantee method for real-time power grid status monitoring described in this application, the first preprocessing includes:

[0032] The real-time operation data of the target power grid is multi-source heterogeneous data, which includes meteorological data, equipment status data, geographic information data, and load demand data.

[0033] Extract timestamps from various data sources in the multi-source heterogeneous data and convert them into a unified time format. For data with different timestamps, use linear interpolation to fill in missing values. Align the processed data with a unified timestamp to obtain the first time-aligned data.

[0034] The first data undergoes spatial alignment processing, and is combined with the collected geospatial information for spatial alignment. In this process, the geographical location information is mapped to a unified geographic coordinate system, and the Kriging interpolation algorithm is used for spatial expansion to fill the blank areas caused by the sparse weather stations in the mountainous area, thus obtaining the spatially aligned first data.

[0035] Kriging interpolation was performed on the meteorological data in the spatially aligned second dataset to obtain a spatiotemporally aligned multi-source heterogeneous dataset.

[0036] As a preferred embodiment of the power supply guarantee method for real-time power grid status monitoring described in this application, the real-time status monitoring results and predictive feedback information include:

[0037] The real-time status monitoring results include risk type, risk level, and risk location;

[0038] The predictive feedback information includes predictions of power supply status over a fixed future period and predictions of potential power supply risks.

[0039] As a preferred embodiment of the power supply guarantee method for real-time power grid status monitoring described in this application, it further includes: designing an adaptive control strategy and optimizing parameters based on real-time status monitoring results and predictive feedback information, thereby obtaining an optimized power supply strategy and model parameters.

[0040] Secondly, this application provides a power supply guarantee system for real-time monitoring of power grid status, comprising:

[0041] The data acquisition module is used to acquire first data of the target power grid and perform first preprocessing on the first data to obtain a second dataset;

[0042] The first data is the real-time operating data of the target power grid;

[0043] The second dataset includes meteorological risk factors, equipment status factors, and geographical risk factors;

[0044] The rule base establishment module is used to preset a first rule base, which is used to obtain the target time-series power supply risk level based on the second dataset.

[0045] The first model building module is used to build a first static prediction model. The first static prediction model is used to obtain the power supply status prediction result within a future fixed time period based on the target time-series power supply risk level.

[0046] The second model building module is used to build a second dynamic prediction model, which is built based on the second dataset and the power supply status prediction results within a future fixed time period.

[0047] The monitoring module is used to obtain real-time status monitoring results and prediction feedback information based on the first data, combined with the first static prediction model and the second dynamic prediction model.

[0048] Thirdly, this application provides an electronic device including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described above.

[0049] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described above.

[0050] Compared with existing technologies, the beneficial effects of this application are as follows: This application proposes a power supply guarantee method for real-time power grid status monitoring. It acquires first data of the target power grid, performs a first preprocessing on the first data to obtain a second dataset; pre-sets a first rule base, establishes a first static prediction model, and establishes a second dynamic prediction model. Based on the first data, and combining the first static prediction model and the second dynamic prediction model, it obtains real-time status monitoring results and prediction feedback information. This not only improves the accuracy of power supply risk level prediction but also achieves accurate prediction of future power supply status, enabling timely implementation of corresponding measures to ensure the stable operation of the power grid. Furthermore, by combining the first static prediction model and the second dynamic prediction model, this application can comprehensively consider historical and real-time data, further improving the reliability and practicality of the prediction results. This power supply guarantee method for real-time power grid status monitoring provides strong technical support for the safe operation of the power grid. It realizes real-time status monitoring and power supply guarantee for mountain microgrids, significantly improving power supply reliability and stability, and providing an innovative solution for the development of smart grids. Attached Figure Description

[0051] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1 This is a flowchart illustrating a method for ensuring power supply through real-time monitoring of the power grid status, provided as an embodiment of this application.

[0053] Figure 2 This is an internal structural diagram of an electronic device for a power supply guarantee method for real-time monitoring of power grid status, provided as an embodiment of this application. Detailed Implementation

[0054] To make the above-mentioned objectives, features, and advantages of this application more apparent and understandable, the specific embodiments of this application will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without inventive effort should fall within the scope of protection of this application.

[0055] Example 1, referring to Figure 1-Figure 2This is the first embodiment of the present application, which provides a power supply guarantee method for real-time monitoring of power grid status, including:

[0056] Existing technologies face several challenges. For instance, traditional monitoring methods and risk assessment models struggle to integrate multi-source heterogeneous data, leading to insufficient prediction accuracy. This is particularly true in mountainous microgrid environments, where complex geographical conditions, large fluctuations in distributed energy output, and frequent extreme weather events pose significant challenges to power supply stability.

[0057] This application provides a method that can effectively solve the problems mentioned above. The following will describe in detail how to implement the power supply guarantee method for real-time monitoring of the power grid status using multiple embodiments.

[0058] Figure 1 A flowchart of a power supply guarantee method for real-time power grid status monitoring is shown, including:

[0059] S101, acquire the first data of the target power grid, and perform a first preprocessing on the first data to obtain the second dataset;

[0060] It should be noted that in order to implement the power supply guarantee method for real-time power grid status monitoring, it is necessary to obtain some patterns from some existing or real-time data of the target power grid. Therefore, it is necessary to obtain the first data of the target power grid. Moreover, the obtained first data is relatively messy and redundant, and it is necessary to preprocess this data. Therefore, after obtaining the first data, the first preprocessing operation is required.

[0061] In an optional embodiment, the first data of the target power grid may be structural data, operational data, meteorological data, equipment status data, geographic information data, etc. This data is acquired in real time and reflects the current state and environmental conditions of the target power grid.

[0062] In this embodiment of the application, the first data is the real-time operation data of the target power grid, which includes meteorological data, equipment status data, geographic information data and load demand data.

[0063] In this embodiment, the power supply design is carried out in a mountain microgrid scenario. The first output collected is multi-source heterogeneous data, which includes:

[0064] 1. Meteorological data: Data such as temperature, humidity, wind speed, rainfall, and lightning activity obtained from weather stations. Meteorological data in mountainous areas exhibits high spatial heterogeneity, and weather stations are sparsely distributed, therefore requiring correction based on geographic information.

[0065] 2. Equipment status data: Real-time operating data collected from distributed energy equipment (such as photovoltaic inverters, wind turbines, and small hydropower stations) and energy storage systems (such as battery energy storage and pumped storage), including voltage, current, power, temperature, fault alarms, etc.

[0066] 3. Geographic information data: including topographic data (such as digital elevation model DEM), vegetation cover, slope, aspect, etc., used to analyze the output characteristics of distributed energy (such as the impact of terrain shading on photovoltaics).

[0067] 4. Load demand data: Real-time electricity load data collected from users is analyzed in conjunction with the distribution characteristics of users in mountainous areas (such as scattered villages and seasonal fluctuations in electricity consumption).

[0068] In an optional embodiment, the first preprocessing operation may include steps such as data cleaning, data transformation, and data alignment. Data cleaning refers to removing duplicate data, filling in missing values, and handling outliers to ensure the accuracy and completeness of the data. Data transformation refers to uniformly converting data of different formats and units to facilitate subsequent processing and analysis. Data alignment refers to aligning data from different data sources according to timestamps or geographical locations to ensure spatiotemporal consistency. Through these preprocessing steps, a well-structured and complete second dataset can be obtained, providing a reliable data foundation for subsequent analysis and prediction.

[0069] However, general data processing operations cannot meet the data processing requirements of this application, so the following first preprocessing step is designed.

[0070] In this embodiment of the application, the first preprocessing includes:

[0071] The real-time operation data of the target power grid is multi-source heterogeneous data, which includes meteorological data, equipment status data, geographic information data, and load demand data.

[0072] Extract timestamps from various data sources in the multi-source heterogeneous data and convert them into a unified time format. For data with different timestamps, use linear interpolation to fill in missing values. Align the processed data with a unified timestamp to obtain the first time-aligned data.

[0073] Specifically, the calculation formula is as follows:

[0074]

[0075] In the formula, y(t) is the data value at timestamp t, and y(t1) and y(t2) are the data values ​​at adjacent timestamps t1 and t2, respectively;

[0076] In an optional embodiment, the first data is spatially aligned by combining it with the collected geospatial information. The geographical location information is mapped to a unified geographic coordinate system, and the Kriging interpolation algorithm is used for spatial expansion to fill the blank areas caused by the sparse weather stations in the mountainous area, thus obtaining the spatially aligned first data.

[0077] Kriging interpolation is performed on the meteorological data in the spatially aligned first dataset to obtain the spatiotemporally aligned multi-source heterogeneous dataset, i.e., the second dataset.

[0078] Specifically, the semivariogram of known meteorological stations in the first spatially aligned dataset is calculated using the following formula:

[0079]

[0080] In the formula, γ(h) is the semivariogram value at a distance h, N(h) is the number of meteorological stations within a distance h, and z(x) is the number of stations within a distance h. i ) and z(x i +h) are the positions x and x respectively. i and x i Meteorological data value at +h;

[0081] The meteorological data values ​​for unknown locations are calculated using the semivariogram, and the formula is as follows:

[0082]

[0083] In the formula, Z(s0) represents the meteorological data of the point to be interpolated, and Z(s i ) represents meteorological data from known meteorological stations, and λ represents... i These are weighting coefficients, calculated using constraints that minimize interpolation error.

[0084] The reason for processing only meteorological data (i.e., using the Kriging interpolation algorithm for spatial expansion) in this embodiment is as follows:

[0085] In mountainous scenarios, weather stations are sparsely distributed, and the complex terrain results in uneven spatial coverage of meteorological data. To obtain more comprehensive meteorological information (such as temperature, humidity, wind speed, and rainfall), spatial interpolation of the meteorological data is necessary to fill in the gaps. Furthermore, meteorological data has a significant impact on the operation of microgrids. For example, sunlight intensity affects photovoltaic power generation output, wind speed affects wind power generation output, and rainfall affects hydropower station output. Therefore, accurate meteorological data is fundamental to assessing power supply risks and predicting future power supply conditions.

[0086] In one alternative embodiment, device status data (such as photovoltaic inverters, wind turbines, and energy storage systems) are typically installed in fixed locations, with known spatial distribution and no need for interpolation; geographic information data (such as altitude, slope, and aspect) are continuous spatial data based on digital elevation models (DEMs), covering the entire area and requiring no further processing; load demand data are typically related to user locations, with known spatial distribution and no need for interpolation. Interpolation is only performed on meteorological data, which avoids redundant processing of other aligned data, improves computational efficiency, and ensures data quality.

[0087] In one alternative embodiment, inconsistent timestamps from multiple data sources can lead to errors in data analysis. Timestamp alignment ensures consistency across all data over time, providing a reliable data foundation for subsequent real-time status monitoring and risk assessment. Furthermore, in mountainous microgrids, the geographical location of distributed energy devices and load nodes significantly impacts power supply strategies. Spatial alignment allows for more accurate analysis of the spatial distribution of device output and load demand, supporting the optimization of power supply strategies.

[0088] In this embodiment of the application, the second dataset includes meteorological risk factors, equipment status factors, and geographical risk factors;

[0089] In an optional embodiment, in this step, the input variables (meteorological risk factors, equipment status factors, and geographical risk factors) are extracted from the spatiotemporally aligned multi-source heterogeneous dataset obtained in step S101. Specifically: the meteorological risk factors (lightning activity intensity, rainfall, and wind speed) come from the meteorological data collected and spatiotemporally aligned in the above steps; the equipment status factors (equipment failure probability, output fluctuation, and remaining energy storage capacity) come from the equipment status data collected and spatiotemporally aligned in the above steps; and the geographical risk factors (terrain complexity and vegetation cover) come from the geographical information data collected and spatiotemporally aligned in the above steps.

[0090] In an optional embodiment, geolocation information is extracted from weather stations, distributed energy devices, energy storage systems, and load nodes (such as latitude, longitude, and altitude); while mapping to a unified geographic coordinate system maps the geolocation information to a unified geographic coordinate system (such as the WGS84 coordinate system) to ensure that all data have a consistent reference system in space.

[0091] It should be noted that acquiring the first data from the target power grid and performing the first preprocessing on it to obtain the second dataset provides a structured and standardized dataset, offering accurate and reliable data input for subsequent risk assessment and prediction models. This data preprocessing process ensures that data from different sources and in different formats can be analyzed within a unified temporal and spatial framework, thereby improving the accuracy and efficiency of data analysis. Furthermore, by comprehensively processing meteorological data, equipment status data, and geographic information data, the potential correlations and mutual influences between them can be revealed, providing strong data support for a deeper understanding of the power grid's operational status and the prediction of power supply risks. This data preprocessing method is one of the key steps in achieving real-time power grid status monitoring and power supply assurance, laying a solid foundation for subsequent risk assessment and decision-making.

[0092] S102, a first rule base is preset, which is used to obtain the target time-series power supply risk level based on the second dataset;

[0093] In an optional embodiment, the fuzzy rule base can be built based on expert experience and historical data, containing a series of fuzzy rules used to map meteorological risk factors, equipment status factors, and geographical risk factors in the second dataset to a target time-series power supply risk level. These fuzzy rules define the correspondence between different combinations of risk factors and power supply risk levels, enabling the system to automatically assess power supply risk based on real-time data.

[0094] In this embodiment of the application, obtaining the target timing power supply risk level based on the second dataset includes:

[0095] Establish a fuzzy rule base based on the second dataset;

[0096] Calculate the membership degree of the output variable based on the fuzzy rule base;

[0097] The membership degree of the output variable is fuzzified, and the centroid method is used to calculate the specific value of the power supply risk level.

[0098] The meteorological risk factors include lightning activity intensity, rainfall, and wind speed; the equipment status factors include equipment failure probability, output fluctuation, and remaining energy storage capacity; and the geographical risk factors include terrain complexity and vegetation coverage.

[0099] Specifically, a fuzzy rule base is defined, with the following rules:

[0100] If x1 is A1 and x2 is A2, then y is B.

[0101] Where x1 and x2 are input variables, A1 and A2 are fuzzy sets, y is the power supply risk level, and B is a fuzzy set;

[0102] In this step, A1 and A2 are fuzzy sets of input variables (such as "high", "medium", and "low"); B is a fuzzy set of output variables (such as "low", "medium", "high", and "extremely high").

[0103] Based on the fuzzy rule base, the membership degree of the output variable is calculated using fuzzy inference methods. The calculation formula is as follows:

[0104]

[0105] Where, μ B (y) is the membership degree of the output variable y. and These are the membership degrees of the input variables x1 and x2, respectively.

[0106] The membership degree of the variables is fuzzyened, and the centroid method is used to calculate the specific value of the power supply risk level. The calculation formula is as follows:

[0107]

[0108] In the formula, y is the specific value of the power supply risk level. i μ represents the possible values ​​of the output variable. B (y i ) is y i The degree of membership is used to obtain the current and future power supply risk levels.

[0109] It should be noted that the fuzzy rule base is built based on expert experience and historical data to provide high-precision risk assessment. Fuzzy reasoning and defuzzification are used to convert the results of the fuzzy logic model into specific power supply risk levels through fuzzy reasoning and defuzzification methods, providing a basis for subsequent power supply guarantee strategies.

[0110] In an optional embodiment, the fuzzy rule base can also be continuously updated and optimized based on historical power supply events and expert knowledge to improve the accuracy and adaptability of risk assessment. For example, when new extreme weather events or equipment failure modes occur, new fuzzy rules can be adjusted or added by analyzing the data characteristics of these events, enabling the rule base to better reflect the actual situation and improve the timeliness of risk assessment.

[0111] To establish the first rule base, it is necessary to define power supply risk levels. In one optional embodiment, power supply risk levels can be divided into three levels: low, medium, and high, or more precisely, into five or even more levels to more accurately reflect the actual situation of power supply risks. Each risk level corresponds to a different risk threshold and corresponding handling measures.

[0112] Next, based on historical data and expert experience, the mapping relationship between each risk factor (meteorological risk factor, equipment condition factor, geographical risk factor) and the power supply risk level is determined. This can be achieved through statistical analysis, machine learning algorithms, or expert systems.

[0113] Each rule in the fuzzy rule base defines a method for assessing the power supply risk level under specific conditions. For example, a rule might state: "If lightning activity is strong, rainfall is moderate, and equipment failure probability is low, then the power supply risk level is high." Here, "strong lightning activity," "moderate rainfall," and "low equipment failure probability" are fuzzy conditions, which are described by membership functions to indicate different degrees of fuzziness; "high power supply risk level" is a fuzzy conclusion, representing the power supply risk level assessed under these conditions.

[0114] In practical applications, when the system acquires the second dataset, it performs matching and reasoning based on the rules in the fuzzy rule base to obtain the target time-series power supply risk level. This process may involve parallel or serial processing of multiple rules, as well as fuzzy logic operations (such as taking the largest, smallest, and synthesizing), ultimately yielding an assessment result for one or more power supply risk levels.

[0115] It should be noted that the establishment and use of the first rule base enables the real-time power grid status monitoring and power supply guarantee method to more accurately assess power supply risks, providing strong support for subsequent decision-making. Furthermore, because the rule base can be updated and optimized according to actual conditions, this method has good adaptability and scalability.

[0116] S103, Establish a first static prediction model, the first static prediction model is used to obtain the power supply status prediction result within a future fixed time period based on the target time-series power supply risk level;

[0117] In this embodiment of the application, the first static prediction model includes:

[0118] Preset neural network model;

[0119] Input the time series data and spatial series data into the neural network model;

[0120] The time-series data includes equipment processing, load demand, and meteorological data; the spatial-series data includes geographic information data.

[0121] The neural network is used to predict the power supply status within a future fixed period, which includes distributed energy output, load demand, and energy storage status.

[0122] In an optional embodiment, the first static prediction model can be trained and learned from collected historical power supply data to optimize model parameters and improve prediction accuracy. Specifically, time-series and spatial-series data from the historical power supply data can be used as input, and the corresponding power supply status can be used as output. By continuously adjusting parameters such as weights and biases in the neural network, the model's prediction results can be made as close as possible to the actual power supply status.

[0123] In an optional embodiment, an ensemble learning approach can be employed to further improve prediction accuracy. Specifically, multiple different neural network models can be constructed, each trained using the same historical power supply data but with different model structures and parameter settings. The predictions from multiple models are then integrated, and the final prediction result is obtained through weighted averaging or voting. This method can fully leverage the strengths of different models, improving the robustness and accuracy of the prediction.

[0124] Specifically, the first static prediction model of this application adopts an LSTM model, wherein the structure of the LSTM model is designed, including an input layer, a hidden layer and an output layer. The LSTM model is trained using the input dataset of the spatiotemporal sequence prediction model, and the hyperparameters (such as learning rate and number of hidden layer nodes) are optimized to obtain a trained LSTM model.

[0125] Next, time-series data (such as equipment output, load demand, and meteorological data) and spatial data (such as geographic information) are input into the LSTM model. The LSTM model is then used to calculate the power supply status (such as distributed energy output, load demand, and energy storage status) over a future period, as shown in the following formula:

[0126] y t =W y ·h t +b y

[0127] In the formula, y t W is the predicted power supply state at time t. y and b y These are the weights and biases of the output layer, h t It is in a hidden state.

[0128] It should be noted that by constructing the input dataset for the spatiotemporal sequence prediction model, a data foundation was provided for the training of the LSTM model. Through the training of the LSTM model, a spatiotemporal sequence prediction model suitable for mountain microgrids was obtained. Through spatiotemporal sequence prediction, the power supply status prediction results for a period of time in the future were obtained, and the spatial blank areas of the power supply status prediction results were filled, providing more comprehensive prediction information.

[0129] S104, Establish a second dynamic prediction model, which is established based on the second dataset and the power supply status prediction results within a future fixed time period;

[0130] In this embodiment of the application, the second dynamic prediction model includes:

[0131] A second dynamic prediction model is established based on the topology of the target power grid.

[0132] Obtain the second dataset and the power supply status prediction results for a fixed future time period;

[0133] The second dynamic prediction model is initialized based on the second dataset and the power supply status prediction results within a fixed future time period;

[0134] The first data is input into the initialized second dynamic prediction model to dynamically update the model state variables.

[0135] Specifically, the second dynamic prediction model is the digital twin model, and the design steps are as follows:

[0136] Based on the microgrid topology, a mathematical model of the physical power grid is constructed, and the calculation formula is as follows:

[0137] G = (N, E)

[0138] In the formula, G represents the topology of the microgrid, N represents the set of nodes, which includes distributed energy sources, energy storage systems, and load nodes, and E represents the set of edges, which includes transmission lines.

[0139] Design a real-time data interface to connect the real-time operation data of the physical power grid to the digital twin model; based on the multi-source heterogeneous dataset and power supply status prediction results, initialize the state variables of the digital twin model to obtain the initialized digital twin model;

[0140] Real-time operational data is collected from the physical power grid and input into the digital twin model to dynamically update the model's state variables. The calculation formula is as follows:

[0141] X(t+1)=f(X(t),U(t))

[0142] In the formula, X(t) represents the state variables of the model at time t, U(t) represents the real-time input data, and f represents the state update function;

[0143] Based on the updated model status, potential power supply risks are identified, and real-time status monitoring results and predictive feedback information are obtained.

[0144] It should be noted that the identification rules for power supply risks are defined based on expert experience and historical data. For example, if the node voltage exceeds the allowable range (e.g., below 0.9 pu or above 1.1 pu), it is considered a voltage exceedance risk. If the line power exceeds the rated capacity, it is considered an overload risk. If the equipment operates abnormally (e.g., excessively high temperature, fault alarm), it is considered an equipment failure risk.

[0145] S105, based on the first data, combined with the first static prediction model and the second dynamic prediction model, the real-time status monitoring results and prediction feedback information are obtained.

[0146] In this embodiment of the application, the real-time status monitoring results and prediction feedback information include:

[0147] The real-time status monitoring results include risk type, risk level, and risk location;

[0148] The predictive feedback information includes predictions of power supply status over a fixed future period and predictions of potential power supply risks.

[0149] In this embodiment, an adaptive control strategy and optimized parameters are designed based on real-time status monitoring results and predictive feedback information to obtain an optimized power supply strategy and model parameters.

[0150] In summary, this application proposes a power supply guarantee method for real-time power grid status monitoring. It acquires first data of the target power grid, performs a first preprocessing step on the first data to obtain a second dataset, pre-defines a first rule base, establishes a first static prediction model, and establishes a second dynamic prediction model. Based on the first data, and combining the first static prediction model and the second dynamic prediction model, it obtains real-time status monitoring results and prediction feedback information. This not only improves the accuracy of power supply risk level prediction but also achieves accurate prediction of future power supply status, enabling timely implementation of corresponding measures to ensure the stable operation of the power grid. Furthermore, by combining the first static prediction model and the second dynamic prediction model, this application comprehensively considers historical and real-time data, further enhancing the reliability and practicality of the prediction results. This power supply guarantee method for real-time power grid status monitoring provides strong technical support for the safe operation of the power grid. It realizes real-time status monitoring and power supply guarantee for mountain microgrids, significantly improving power supply reliability and stability, and providing an innovative solution for the development of smart grids.

[0151] Example 2, in a preferred embodiment, quantifies and classifies potential power supply risks according to identification rules. For example: voltage over-limit risk: classified into low risk, medium risk, and high risk based on the degree of voltage deviation; overload risk: classified into low risk, medium risk, and high risk based on the ratio of line power to rated capacity; equipment failure risk: classified into low risk, medium risk, and high risk based on the degree of abnormality of equipment status data.

[0152] Then, the identified and quantified power supply risks are used to generate real-time status monitoring results, including: risk type (e.g., voltage exceedance, overload, equipment failure); risk level (e.g., low, medium, high); and risk location (e.g., node number, line number, equipment number). Based on the prediction results of the digital twin model, predictive feedback information is generated, including: power supply status prediction for a future period (e.g., distributed energy output, load demand, energy storage status); and prediction of potential power supply risks (e.g., potential future voltage exceedances, overloads, and equipment failures).

[0153] The risk assessment formula is as follows:

[0154]

[0155] Based on real-time status monitoring results and predictive feedback information, an adaptive control strategy and optimized parameters are designed to obtain the optimized power supply strategy and model parameters.

[0156] Understandably, in this step, adaptive control strategies are designed based on real-time status monitoring results (such as risk type, risk level, and risk location) and predictive feedback information (such as future power supply status and potential risks). These strategies include: Prioritization: Power supply priorities are assigned based on user type (such as hospitals, communication base stations, and ordinary users) and geographical location. For example, priority is given to ensuring power supply to critical loads (such as hospitals and communication base stations), while reducing power supply to non-critical loads; Energy storage scheduling: The charging and discharging strategies of the energy storage system are dynamically adjusted based on predictive feedback information. For example, if insufficient photovoltaic output is predicted, energy storage capacity is released in advance; Distributed energy coordination: Based on predictive feedback information, the output of photovoltaic, wind, and hydropower stations is coordinated to ensure power supply balance. For example, if insufficient wind power generation is predicted, the output of photovoltaic and hydropower stations is increased.

[0157] Furthermore, optimization algorithms (such as reinforcement learning and genetic algorithms) can be used to optimize the control strategy, defining an optimization objective function, such as minimizing power supply risk, maximizing power supply reliability, and minimizing operating costs. Optimization algorithms can be used to adjust the parameters of the control strategy (such as energy storage charging and discharging power, and distributed energy output) to minimize the objective function. For example, reinforcement learning algorithms can be used to optimize parameters through trial and error. Based on real-time status monitoring results and prediction feedback information, the parameters of the digital twin model and the spatiotemporal sequence prediction model are optimized. The specific steps are as follows: Error analysis: Analyze the difference between the actual power supply results and the predicted results, and calculate the error (such as mean square error and mean absolute error); then, based on the error analysis results, adjust the model parameters (such as the weights and biases of the LSTM model, and the membership functions of the fuzzy logic model). For example, gradient descent can be used to adjust the parameters of the LSTM model.

[0158] Therefore, by designing adaptive control strategies and optimizing parameters, the power supply strategy is dynamically adjusted to ensure the power supply stability of the microgrid under extreme conditions, significantly improving power supply reliability and operational efficiency. Simultaneously, by optimizing model parameters, the prediction accuracy of the digital twin model and the spatiotemporal sequence prediction model is improved, providing reliable support for real-time monitoring and power supply assurance of the smart grid.

[0159] Example 3: This example also provides a power supply guarantee system for real-time monitoring of the power grid status, including:

[0160] The data acquisition module is used to acquire first data of the target power grid and perform first preprocessing on the first data to obtain a second dataset;

[0161] The first data is the real-time operating data of the target power grid;

[0162] The second dataset includes meteorological risk factors, equipment status factors, and geographical risk factors;

[0163] The rule base establishment module is used to preset a first rule base, which is used to obtain the target time-series power supply risk level based on the second dataset.

[0164] The first model building module is used to build a first static prediction model. The first static prediction model is used to obtain the power supply status prediction result within a future fixed time period based on the target time-series power supply risk level.

[0165] The second model building module is used to build a second dynamic prediction model, which is built based on the second dataset and the power supply status prediction results within a future fixed time period.

[0166] The monitoring module is used to obtain real-time status monitoring results and prediction feedback information based on the first data, combined with the first static prediction model and the second dynamic prediction model.

[0167] The above-mentioned unit modules can be embedded in the processor of the electronic device in hardware form or independent of it, or they can be stored in the memory of the electronic device in software form, so that the processor can call and execute the corresponding operations of the above modules.

[0168] This embodiment also provides an electronic device, which can be a terminal, and its internal structure diagram can be as follows. Figure 2 As shown, the electronic device includes a processor, memory, communication interface, display screen, and input device connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage medium. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a power supply guarantee method for real-time monitoring of the power grid's status. The display screen can be an LCD screen or an e-ink screen. The input device can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the device's casing, or an external keyboard, touchpad, or mouse.

[0169] This embodiment also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, it performs the following steps:

[0170] First data of the target power grid is acquired, and first preprocessing is performed on the first data to obtain a second dataset;

[0171] The first data is the real-time operating data of the target power grid;

[0172] The second dataset includes meteorological risk factors, equipment status factors, and geographical risk factors;

[0173] A first rule base is preset, which is used to obtain the target time-series power supply risk level based on the second dataset.

[0174] A first static prediction model is established, which is used to obtain the prediction result of the power supply status within a fixed time period in the future based on the target time-series power supply risk level.

[0175] A second dynamic prediction model is established based on the second dataset and the power supply status prediction results within a fixed future time period.

[0176] Based on the first data, combined with the first static prediction model and the second dynamic prediction model, real-time status monitoring results and prediction feedback information are obtained.

[0177] It should be noted that the above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit it. Although this application has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of this application without departing from the spirit and scope of the technical solutions of this application, and all such modifications and substitutions should be covered within the scope of the claims of this application.

[0178] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of this application can be implemented using various computer languages.

[0179] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0180] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0181] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0182] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0183] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for ensuring power supply through real-time monitoring of power grid status, characterized in that, include: First data of the target power grid is acquired, and first preprocessing is performed on the first data to obtain a second dataset; The first data is the real-time operating data of the target power grid; The second dataset includes meteorological risk factors, equipment status factors, and geographical risk factors; A first rule base is preset, which is used to obtain the target time-series power supply risk level based on the second dataset. A first static prediction model is established, which is used to obtain the prediction result of the power supply status within a fixed time period in the future based on the target time-series power supply risk level. A second dynamic prediction model is established based on the second dataset and the power supply status prediction results within a fixed future time period. Based on the first data, combined with the first static prediction model and the second dynamic prediction model, real-time status monitoring results and prediction feedback information are obtained.

2. The power supply guarantee method for real-time power grid status monitoring as described in claim 1, characterized in that, The second dynamic prediction model includes: A second dynamic prediction model is established based on the topology of the target power grid. Obtain the second dataset and the power supply status prediction results for a fixed future time period; The second dynamic prediction model is initialized based on the second dataset and the power supply status prediction results within a fixed future time period; The first data is input into the initialized second dynamic prediction model to dynamically update the model state variables.

3. The power supply guarantee method for real-time power grid status monitoring as described in claim 2, characterized in that, The first static prediction model includes: Preset neural network model; Input the time series data and spatial series data into the neural network model; The time-series data includes equipment processing, load demand, and meteorological data; the spatial-series data includes geographic information data. The neural network is used to predict the power supply status within a future fixed period, which includes distributed energy output, load demand, and energy storage status.

4. The power supply guarantee method for real-time power grid status monitoring as described in claim 3, characterized in that, The target time-series power supply risk level obtained by mapping based on the second dataset includes: Establish a fuzzy rule base based on the second dataset; Calculate the membership degree of the output variable based on the fuzzy rule base; The membership degree of the output variable is fuzzified, and the centroid method is used to calculate the specific value of the power supply risk level. The meteorological risk factors include lightning activity intensity, rainfall, and wind speed; the equipment status factors include equipment failure probability, output fluctuation, and remaining energy storage capacity; and the geographical risk factors include terrain complexity and vegetation coverage.

5. The power supply guarantee method for real-time power grid status monitoring as described in claim 4, characterized in that, The first preprocessing includes: The real-time operation data of the target power grid is multi-source heterogeneous data, which includes meteorological data, equipment status data, geographic information data, and load demand data. Extract timestamps from various data sources in the multi-source heterogeneous data and convert them into a unified time format. For data with different timestamps, use linear interpolation to fill in missing values. Align the processed data with a unified timestamp to obtain the first time-aligned data. The first data undergoes spatial alignment processing, and is combined with the collected geospatial information for spatial alignment. In this process, the geographical location information is mapped to a unified geographic coordinate system, and the Kriging interpolation algorithm is used for spatial expansion to fill the blank areas caused by the sparse weather stations in the mountainous area, thus obtaining the spatially aligned first data. Kriging interpolation was performed on the meteorological data in the spatially aligned second dataset to obtain a spatiotemporally aligned multi-source heterogeneous dataset.

6. The power supply guarantee method for real-time power grid status monitoring as described in claim 5, characterized in that, The real-time status monitoring results and prediction feedback information include: The real-time status monitoring results include risk type, risk level, and risk location; The predictive feedback information includes predictions of power supply status over a fixed future period and predictions of potential power supply risks.

7. The power supply guarantee method for real-time power grid status monitoring as described in claim 6, characterized in that, Also includes: Based on real-time status monitoring results and predictive feedback information, an adaptive control strategy and optimized parameters are designed to obtain the optimized power supply strategy and model parameters.

8. A power supply guarantee system for real-time monitoring of power grid status, using the method described in any one of claims 1 to 7, characterized in that, include: The data acquisition module is used to acquire first data of the target power grid and perform first preprocessing on the first data to obtain a second dataset; The first data is the real-time operating data of the target power grid; The second dataset includes meteorological risk factors, equipment status factors, and geographical risk factors; The rule base establishment module is used to preset a first rule base, which is used to obtain the target time-series power supply risk level based on the second dataset. The first model building module is used to build a first static prediction model. The first static prediction model is used to obtain the power supply status prediction result within a future fixed time period based on the target time-series power supply risk level. The second model building module is used to build a second dynamic prediction model, which is built based on the second dataset and the power supply status prediction results within a future fixed time period. The monitoring module is used to obtain real-time status monitoring results and prediction feedback information based on the first data, combined with the first static prediction model and the second dynamic prediction model.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the power supply guarantee method for real-time monitoring of power grid status as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the power supply guarantee method for real-time monitoring of power grid status as described in any one of claims 1 to 7.

Images