Power grid meteorological data monitoring and evaluation method and system and storage medium

Abstract

The invention discloses a power grid meteorological data monitoring and evaluation method and system and a storage medium, relates to the technical field of electric power meteorological monitoring, and solves the problems that the power generation efficiency is low and the power consumption is low due to the fact that the influence degree of meteorological abnormity on the power loss and the equipment state of related equipment during operation is not considered in the prior art. And supply and demand imbalance of electric energy is caused. A meteorological anomaly coefficient is generated according to an environmental parameter and a weather forecast; generating an equipment state score according to the power plant data and the environment data; generating a power supply amount according to the equipment parameters and the equipment state score, and generating an adjustment scheme according to the power supply amount; and generating an alarm signal according to the meteorological abnormal coefficient and the equipment state score, quantifying the monitoring results of various types of meteorology and calculating the future meteorological abnormal coefficient, considering the influence of the meteorology on the future generating capacity, and dynamically adjusting the power supply of the region according to the demand data in the supply region. And the supply and demand balance of electric energy and the accuracy and comprehensiveness of meteorological monitoring are improved.

Description

Technical Field

[0001] This application belongs to the technical field of power meteorological monitoring, and specifically relates to a method, system and storage medium for monitoring and evaluating power grid meteorological data. Background Art

[0002] Power grid meteorological monitoring is an important means to ensure the safe and stable operation of the power grid. It helps the power department take preventive measures in a timely manner by monitoring and warning the meteorological environment around power grid equipment in real time, reducing power grid failures and power outages caused by meteorological disasters. Power grid equipment is exposed to a complex and changeable meteorological environment for a long time and is extremely vulnerable to the influence of meteorological disasters such as strong winds. These disasters may not only damage power grid equipment but also cause large-scale power outages, seriously affecting social production and people's lives.

[0003] The prior art (a patent application for invention with the publication number CN117609802A) discloses a method for evaluating power grid meteorological monitoring data, including the following steps: A. First, collect meteorological data in the power grid area and preprocess the data; B. Then, transmit the collected monitoring data to the processor module; C. The processor module transmits the meteorological monitoring data to the comparison module to compare it with the meteorological monitoring data in the same period of the historical period and outputs the comparison result; D. Transmit the comparison result to the meteorological data prediction model to obtain the prediction data of the target to be evaluated in the current period; E. Transmit the prediction data of the current period to the evaluation module for evaluation and output the evaluation result.

[0004] The above patent obtains the current meteorological anomalies by comparing the data collected by multiple sensors with historical data; it lacks consideration of the influence degree of meteorological anomalies on the power loss and equipment status of relevant equipment during operation, resulting in a low power generation efficiency and an imbalance between power supply and demand; for example, the frequent change of wind direction causes the wind blades to rotate accordingly, affecting power generation and exacerbating equipment wear; therefore, the power grid meteorological data monitoring and evaluation system still needs further improvement. Summary of the Invention

[0005] This application aims to solve at least one of the technical problems existing in the prior art; for this purpose, this application proposes a method, system and storage medium for monitoring and evaluating power grid meteorological data, which is used to solve the technical problem that the prior art lacks consideration of the influence degree of meteorological anomalies on the power loss and equipment status of relevant equipment during operation, resulting in a low power generation efficiency and an imbalance between power supply and demand.

[0006] To achieve the above object, the first aspect of this application provides a power grid meteorological data monitoring and evaluation system, including: a data collection module, a data analysis module, an early warning module and a database;

[0007] The data acquisition module: obtains power plant data, environmental data, and demand data through data acquisition devices; the environmental data includes environmental parameters and weather forecasts; the power plant data includes power generation equipment IDs and equipment parameters;

[0008] The data analysis module: generates a meteorological anomaly coefficient based on environmental parameters and weather forecasts; generates an equipment status score based on power plant data and environmental data; obtains equipment parameters in real time, and generates the available power based on the equipment parameters and the equipment status score; generates an adjustment plan based on the available power and demand data; generates an alarm signal based on the meteorological anomaly coefficient and the equipment status score;

[0009] The early warning module: gives a prompt according to the alarm signal and contacts the management personnel;

[0010] The database is used to store the data of each module and the historical data required for training the model.

[0011] Through the above steps, this application can quantitatively process the monitoring data of various meteorological elements, and calculate the future meteorological anomaly coefficient accordingly; in this process, fully consider the potential impact of meteorological conditions on future power generation, and at the same time combine the actual electricity demand data in the supply area to dynamically optimize and adjust the regional power supply plan, which not only helps to improve the balance level of power supply and demand, but also effectively improves the accuracy and comprehensiveness of meteorological monitoring.

[0012] Further, generating the meteorological anomaly coefficient according to the environmental parameters and weather forecasts includes:

[0013] Obtain the environmental parameters, equipment parameters, and weather forecasts within the time period T; the environmental parameters include wind speed, wind direction, temperature, and humidity; the equipment parameters include the number of equipment rotations and the amplitude of equipment rotation; the weather forecasts include wind speed, temperature, and humidity; the environmental parameters and weather forecasts are expressed as environmental data corresponding to different time periods;

[0014] Obtain the historical environmental parameters, historical equipment parameters, and their corresponding historical weather forecasts and prediction labels corresponding to a number of historical time periods;

[0015] Integrate the historical environmental parameters, historical equipment parameters, and their corresponding historical weather forecasts corresponding to a number of historical time periods into a parameter prediction sequence;

[0016] Input the prediction label and the parameter prediction sequence into a multi-modal prediction model to obtain the predicted equipment parameters corresponding to a number of time periods; the multi-modal prediction model is constructed through an artificial intelligence model;

[0017] Generate the meteorological anomaly coefficient according to the environmental data and equipment parameters within the time period.

[0018] Further, generating a meteorological anomaly coefficient based on environmental data and equipment parameters within a time period includes:

[0019] Obtain environmental data and equipment parameters within a time period; the environmental data includes environmental parameters and weather forecasts; the equipment parameters include equipment parameters within the current time period and predicted equipment parameters within a future time period;

[0020] Extract the wind speed FV, temperature WD, and humidity SD from the environmental parameters and weather forecasts;

[0021] Extract the number of equipment rotations SZC and the equipment rotation amplitude SZF from the equipment parameters;

[0022] Construct an environmental impact function HYF(FV, WD, SD) through the non - linear relationship between the wind speed FV, temperature WD, humidity SD, and the meteorological anomaly coefficient; construct an equipment impact function SYF(SZC, SZF) through the non - linear relationship between the number of rotations SZC, the equipment rotation amplitude SZF, and the meteorological anomaly coefficient;

[0023] Through linear weighted fusion of the environmental impact function and the equipment impact function, and substituting several parameters within the time period into the calculation to obtain the meteorological anomaly coefficient corresponding to the time period.

[0024] Further, generating an equipment status score based on power plant data and environmental data includes:

[0025] Obtain power plant data and environmental data corresponding to several time periods; the power plant data includes the power generation equipment ID and equipment parameters; the equipment parameters include the start - stop times QT, the rotational speed ZV, and the operation duration YS; the environmental data includes the temperature WD and the humidity SD;

[0026] Construct a period score function ZPF(QT, ZV, YS, WD, SD) through the non - linear relationship between the equipment parameters, environmental data, and the period equipment score;

[0027] Input the corresponding equipment parameters and environmental data within the time period into the period score function to calculate the period equipment score;

[0028] Divide several time periods according to the period equipment score to obtain several period clusters;

[0029] According to the formula CZSP = ∑ i ZSP i ×e ω×(i-1) Calculate the cluster - period equipment score CZSP corresponding to several period clusters; where, i represents the number of the time period within the period cluster; ω represents the cooperation factor, ω ∈ (0, 1), characterizing the amplification effect of the previous wear on the subsequent time period;

[0030] The device status score corresponding to the current monitoring time point is obtained by summing up the scores of several clusters of periodic devices before the current monitoring time point.

[0031] In this application, first, for each time period, the device status score is calculated to obtain the periodic device score; then, clustering analysis is performed on multiple time periods according to the influence degree of the periodic device score on the device status; after clustering, the cluster-period device scores of different time clusters are recalculated and these scores are cumulatively summed to obtain the device status score corresponding to the current monitoring time point; considering that in frequently changing time periods, the device wear is relatively serious and the wear shows the characteristic of non-linear accumulation, this scoring method adopted in this application can make the device status score more in line with the actual situation and significantly improve the accuracy of the device status score; and the accurate device status score also provides a solid and reliable data support for subsequent power generation prediction.

[0032] Further, the obtaining of several period clusters by dividing several time periods according to the periodic device score includes the following steps:

[0033] Step 1: Obtain several historical period device scores ZSP j and their corresponding several time periods SZ j ;

[0034] Step 2: Create a new list of period clusters;

[0035] Step 3: Judge whether ZSP j is greater than the score threshold;

[0036] If yes, place ZSP j into the list of period clusters and proceed to the next time period; go to Step 3;

[0037] If no, judge whether the list of period clusters is an empty list. If yes, place ZSP j into the list of period clusters and proceed to the next time period; go to Step 2; if no, create a new list of period clusters, place ZSP j into the list of period clusters and proceed to the next time period, go to Step 2; where j represents the number corresponding to the time period.

[0038] Further, the generation of the available power according to the device parameters and the device status score includes:

[0039] Obtain several historical device parameters, historical device status scores, historical environmental data, meteorological anomaly coefficients, and prediction labels, and integrate the several historical device parameters, historical device status scores, historical environmental data, and meteorological anomaly coefficients into a power prediction sequence;

[0040] Input the predicted label and the power prediction sequence into a multi-modal prediction model to obtain the predicted power generation; the multi-modal prediction model is constructed through an artificial intelligence model;

[0041] Extract the energy storage power in the power plant data in real time;

[0042] Obtain the available power by summing the energy storage power and the predicted power generation.

[0043] Furthermore, the multi-modal prediction model is constructed through an artificial intelligence model, including:

[0044] Obtain historical predicted labels and their corresponding several historical parameter prediction sequences or historical power prediction sequences, as well as their corresponding historical equipment parameters or historical power generation; the predicted labels include parameter prediction labels and power prediction labels;

[0045] Divide the several historical parameter prediction sequences and historical equipment parameters, as well as several historical power prediction sequences and historical power generation into several historical parameter prediction sequences and historical equipment parameters corresponding to the parameter prediction label, and several historical power prediction sequences and historical power generation corresponding to the power prediction label according to the predicted label;

[0046] Divide the several historical parameter prediction sequences and historical equipment parameters, as well as several historical power prediction sequences and historical power generation into training data, validation data, and test data corresponding to the parameter prediction label, and training data, validation data, and test data corresponding to the power prediction label according to the predicted label; perform data preprocessing on the training data, validation data, and test data to obtain a training set, a validation set, and a test set;

[0047] Select two machine learning models as the basic models for the multi-task branches;

[0048] Train their corresponding basic models through their respective training sets, and adjust the learning rate and other hyperparameters on their respective validation sets to obtain their respective pre-trained models;

[0049] Verify their respective pre-trained models on their respective test sets, and finally obtain a multi-modal prediction model that inputs the predicted label and its corresponding parameter prediction sequence or power prediction sequence and outputs the predicted equipment parameters or predicted power generation.

[0050] Furthermore, the generation of the adjustment plan according to the available power and the demand data includes:

[0051] Obtain the available power and the demand data; the demand data includes the total demand power and the regional power demand and regional parameters corresponding to several regions;

[0052] Determine whether the available power is greater than the total required power; if so, do nothing; if not, generate an electricity shortage warning signal, obtain the maximum purchasable power, and obtain the maximum available power by summing the maximum purchasable power and the available power; determine whether the maximum available power is greater than the total required power; if so, do nothing, if not, generate an area electricity shortage alarm signal; generate a number of area allocated powers according to the maximum available power and area parameters; supply power to a number of areas according to the area allocated powers.

[0053] Further, the generating a number of area allocated powers according to the maximum available power and area parameters includes:

[0054] Obtain the maximum available power and area parameters; the area parameters include building grade, population density, and the number of special population; the special population includes the elderly, the sick, and the disabled;

[0055] Extract the electricity required for buildings with a building grade higher than the grade threshold in a number of areas;

[0056] Obtain the population density RM and the number of special population TS corresponding to a number of areas;

[0057] Construct a priority function YF(RM, TS) through the non-linear relationship between population density, the number of special population and area priority; among them, the priority function is an increasing function;

[0058] Input the population density and the number of special population in a number of areas into the priority function to calculate the area priority;

[0059] Calculate the divisible power by taking the difference between the maximum available power and the sum of the electricity required for a number of buildings;

[0060] Determine whether the divisible power is greater than 0; if so, perform a normalization operation on the area priorities of a number of areas to obtain the normalized area priorities, and calculate the divisible powers of a number of areas by multiplying the divisible power by the area priorities; if not, generate a power outage alarm signal;

[0061] Obtain the area allocated powers by summing the divisible powers of the areas and the electricity required for the buildings in their corresponding areas.

[0062] Further, the generating an alarm signal according to the meteorological anomaly coefficient and the equipment status score includes:

[0063] Obtain the meteorological anomaly coefficient and the equipment status score;

[0064] Determine whether the meteorological anomaly coefficient is greater than the meteorological anomaly threshold; if so, generate a meteorological alarm signal; if not, do nothing;

[0065] Determine whether the device status score is greater than the device scrapping threshold; if yes, generate a device scrapping alarm signal; if no, determine whether the device status score is greater than D times the device scrapping threshold, if yes, generate a device maintenance warning signal; if no, do nothing; where D represents a proportionality coefficient, D ∈ (0, 1).

[0066] This application monitors the meteorological anomaly coefficient and the device status score in real time. Once an abnormal state occurs, an alarm signal is sent in a timely manner, and corresponding measures are taken to avoid wasting time and resources caused by the device still working in a poor state, improving the efficiency and comprehensiveness of the power grid meteorological data monitoring and evaluation system.

[0067] The second aspect of the present invention provides a method for monitoring and evaluating power grid meteorological data, including:

[0068] S0: Obtain power plant data, environmental data, and demand data; the environmental data includes environmental parameters and weather forecasts; the power plant data includes power generation equipment IDs and equipment parameters;

[0069] S1: Generate a meteorological anomaly coefficient based on environmental parameters and weather forecasts; generate a device status score based on power plant data and environmental data;

[0070] S2: Obtain equipment parameters in real time, and generate the available power based on the equipment parameters and the device status score;

[0071] S3: Generate an adjustment plan based on the available power and demand data; generate an alarm signal based on the meteorological anomaly coefficient and the device status score;

[0072] S4: Make a prompt according to the alarm signal and contact the management personnel.

[0073] Another aspect of the present invention provides a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements a power grid meteorological data monitoring and evaluation system according to the first aspect of the present invention.

[0074] Compared with the prior art, the beneficial effects of this application are:

[0075] 1. This application generates a meteorological anomaly coefficient based on environmental parameters and weather forecasts; generates a device status score based on power plant data and environmental data; obtains equipment parameters in real time, and generates the available power based on the equipment parameters and the device status score; generates an adjustment plan based on the available power and demand data; generates an alarm signal based on the meteorological anomaly coefficient and the device status score, quantifies the monitoring results of various meteorologies and calculates the future meteorological anomaly coefficient, considers the impact of meteorology on future power generation, and dynamically adjusts the power supply of the region according to the demand data in the supply area, improving the balance between power supply and demand and the accuracy and comprehensiveness of meteorological monitoring.

[0076] 2. This application represents the influence data of the wind turbine blades under the condition of frequent wind direction changes through the number of device rotations and the rotation amplitude of the device, predicts the number of device rotations and the rotation amplitude of the device within a future time period through a pre-trained multi-modal prediction model, and combines weather forecasts to quantify the meteorological anomaly coefficient at future times, improving the accuracy of meteorological anomaly calculation and meteorological prediction.

[0077] 3. This application calculates the periodic device score by calculating the device status score for each time period, then clusters several time periods according to the influence degree of the periodic device score on the device status, recalculates the cluster periodic device scores of different time clusters, and performs cumulative summation to obtain the device status score corresponding to the current monitoring time point. Considering that severe wear in frequent time periods will lead to non-linear accumulation of wear, the device status score can better fit the actual situation, improving the accuracy of the device status score and providing strong data support for subsequent power generation prediction.

[0078] 4. This application first compares the available power supply of the power plant with the demand data. If the supply of the demand data can be achieved, there is no need to purchase electric energy; otherwise, after purchasing electric energy and still failing to achieve power coverage in all regions, priority supply is carried out according to the regional priority and regional special buildings to ensure the power supply of important buildings. Subsequently, the available power in each region is dynamically allocated, and corresponding alarm signals are sent to take preventive measures in advance to reduce the occurrence of poor user experience caused by sudden power supply imbalance. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0080] Figure 1 Schematic diagram of the principle of a power grid meteorological data monitoring and evaluation system of the present application;

[0081] Figure 2 Flowchart of the generation of periodic clusters of the present application;

[0082] Figure 3 Flowchart of the generation of adjustment schemes of the present application;

[0083] Figure 4 Flowchart of a method for monitoring and evaluating power grid meteorological data of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0084] The technical solutions of the present application will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative work belong to the scope of protection of the present application.

[0085] Please refer to Figure 1 , an embodiment of the first aspect of the present application provides a power grid meteorological data monitoring and evaluation system, including: a data acquisition module, a data analysis module, an early warning module, and a database;

[0086] Data acquisition module: Obtain power plant data, environmental data, and demand data through data acquisition devices; the environmental data includes environmental parameters and weather forecasts; the power plant data includes power generation equipment IDs and equipment parameters; the data acquisition devices include several sensors, etc.;

[0087] Data analysis module: Generate a meteorological anomaly coefficient according to the environmental parameters and weather forecasts. The meteorological anomaly coefficient refers to the degree level of meteorological anomalies; generate an equipment status score according to the power plant data and environmental data. The equipment status score refers to the score of the power generation equipment status; obtain the equipment parameters in real time, and generate the available power supply according to the equipment parameters and the equipment status score. The available power supply refers to the power that the power plant can supply at different times; generate an adjustment plan according to the available power supply and demand data. The adjustment plan refers to a plan for adjusting between the available power supply and demand data; generate an alarm signal according to the meteorological anomaly coefficient and the equipment status score;

[0088] Early warning module: Make a prompt according to the alarm signal and contact the management personnel; the alarm signals include meteorological alarm signals, equipment maintenance early warning signals, power shortage early warning signals, etc.;

[0089] The database is used to store the data of each module and the historical data required for training the model.

[0090] In this embodiment, meteorological anomaly monitoring is carried out in a wind farm. In existing wind power generation equipment, the wind blades are not fixed in position and then remain unchanged, but change according to the change of the wind direction. Then, when the wind direction changes frequently, the wind blades will rotate accordingly to achieve the best power generation effect. At this time, the number of rotations and the rotation amplitude generated by the rotation of the wind blades can represent the change of the wind direction within the time period. Quantifying the anomaly of the wind direction by the number of rotations and the rotation amplitude can make meteorological monitoring more accurate.

[0091] The generation of the meteorological anomaly coefficient according to the environmental parameters and weather forecasts in this embodiment includes:

[0092] Obtain the environmental parameters, device parameters, and weather forecast within the time period T. The time period T is set according to experience and can be set to 1 hour or 1 day. In this embodiment, T is set to 3 hours. The environmental parameters include wind speed, wind direction, temperature, and humidity. The device parameters include the number of device rotations and the rotation amplitude of the device. The weather forecast includes wind speed, temperature, and humidity. The environmental parameters and the weather forecast are represented as environmental data corresponding to different time periods.

[0093] Obtain the historical environmental parameters, historical device parameters, and their corresponding historical weather forecasts and prediction labels for several historical time periods. The prediction labels include parameter prediction labels and power prediction labels. One is used for predicting parameters, and the other is used for predicting power.

[0094] Integrate the historical environmental parameters, historical device parameters, and their corresponding historical weather forecasts for several historical time periods into a parameter prediction sequence.

[0095] Input the prediction labels and the parameter prediction sequence into a multi-modal prediction model to obtain the predicted device parameters for several time periods. The multi-modal prediction model is constructed through an artificial intelligence model.

[0096] Generate a meteorological anomaly coefficient based on the environmental data and device parameters within the time period.

[0097] In this embodiment, the two indicators of the number of device rotations and the rotation amplitude of the device are used to characterize the influence data of the wind turbine blades when the wind direction changes frequently. With the help of a pre-trained multi-modal prediction model, the number of device rotations and the rotation amplitude within a specific future time period are accurately predicted. At the same time, combined with the weather forecast information, a quantitative analysis of the meteorological anomaly coefficient for the future period is carried out, effectively improving the accuracy of meteorological anomaly calculation and the accuracy of meteorological prediction.

[0098] The generation of the meteorological anomaly coefficient based on the environmental data and device parameters in this embodiment includes:

[0099] Obtain the environmental data and device parameters within the time period. The environmental data includes environmental parameters and weather forecasts. The device parameters include the device parameters within the current time period and the predicted device parameters within the future time period.

[0100] Extract the wind speed FV, temperature WD, and humidity SD from the environmental parameters and weather forecasts.

[0101] Extract the number of device rotations SZC and the rotation amplitude SZF of the device parameters.

[0102] The environmental impact function HYF(FV, WD, SD) constructed through the non-linear relationship between the wind speed FV, temperature WD, humidity SD and the meteorological anomaly coefficient; the equipment impact function SYF(SZC, SZF) constructed through the non-linear relationship between the number of rotations SZC and the equipment rotation amplitude SZF and the meteorological anomaly coefficient;

[0103] The meteorological anomaly coefficient is calculated through the formula: QYX = γ × HYF(FV, WD, SD) + (1 - γ) × SYF(SZC, SZF); where γ is the weight coefficient, γ ∈ (0, 1), and the specific value is set according to experience. If it is considered that the value calculated by the environmental impact function has a greater impact on the meteorological anomaly coefficient, then γ can be set larger, such as γ is set to 0.7; if it is considered that the value calculated by the environmental impact function has a smaller impact on the meteorological anomaly coefficient, then γ can be set smaller, such as γ is set to 0.3; in this embodiment, γ is set to 0.4;

[0104] Among them, the environmental impact function HYF(FV, WD, SD) can be expressed as: δ represents the wind speed non-linear attenuation coefficient, δ ∈ (0, 1), and the specific value is set according to experience. In this embodiment, δ is set to 0.7. The setting of δ is to suppress the marginal effect of extreme wind speeds; WMD represents the temperature deviation sensitivity, which is to control the exponential decay rate of temperature anomalies, and the specific value is set according to experience. In this embodiment, WMD is set to 3°C; BW and BS represent the standard temperature and standard humidity, and the specific values are set according to experience. In this embodiment, BW is set to 25°C and BS is set to 70%;

[0105] The equipment impact function SYF(SZC, SZF) can be expressed as represents the rotation number sensitivity coefficient, The specific value is set according to experience. In this embodiment, is set to 0.5, The setting of is to control the saturation speed of the hyperbolic tangent function; ρ represents the rotation amplitude attenuation coefficient, ρ ∈ (0, 1), and the specific value is set according to experience. In this embodiment, ρ is set to 0.6. The setting of ρ is to suppress the marginal effect caused by excessive amplitudes; SZC base and SZF base represent the equipment rotation number reference value and the equipment rotation amplitude reference value respectively, and the specific values are set according to experience;

[0106] By linearly weighted fusing the environmental impact function and the equipment impact function, and substituting a number of parameters within the time period for calculation, the meteorological anomaly coefficient corresponding to the time period is obtained.

[0107] Generating an equipment status score based on power plant data and environmental data in this embodiment includes:

[0108] Obtaining power plant data and environmental data corresponding to a number of time periods; the power plant data includes a power generation equipment ID and equipment parameters; the equipment parameters include the start-stop times QT, the rotation speed ZV, and the operation duration YS; the environmental data includes the temperature WD and the humidity SD;

[0109] Constructing a period scoring function ZPF(QT, ZV, YS, WD, SD) through the non-linear relationship between the equipment parameters, environmental data, and the period equipment score; and the period scoring function is an increasing function, and the specific representation of the function is: where QT max is expressed as the maximum start-stop times, and the specific value is set according to the relevant parameters of the fan design. ZV rated is expressed as the rated rotation speed, YS design is expressed as the total design life duration, BW and BS are expressed as the standard temperature and standard humidity, and the specific values are set according to experience. In this embodiment, BW is set to 25°C and BS is set to 70%;

[0110] Inputting the corresponding equipment parameters and environmental data within the time period into the period scoring function to calculate the period equipment score; since the period scoring function is known, substituting the corresponding parameter values can calculate the period equipment score. The higher the values of the equipment parameters and environmental data within the time period, the higher the calculated period equipment score, indicating that the degree of wear caused by the equipment within the period is greater;

[0111] Dividing a number of time periods according to the period equipment score to obtain a number of period clusters; calculating the period clusters is because considering that the higher the equipment damage caused in adjacent periods, then the overall cumulative wear usually shows a non-linear superposition effect, resulting in a total wear degree significantly higher than the linear superposition value under normal circumstances;

[0112] According to the formula CZSP = ∑ i ZSP i ×e ω×(i-1) Calculate the cluster period equipment score CZSP corresponding to a number of period clusters; where i represents the number of the time period within the period cluster; ω represents the cooperation factor, ω ∈ (0, 1), and the specific value is set according to experience. In this embodiment, ω is set to 0.15. The setting of ω is to characterize the amplification effect of the previous wear on the subsequent time period; the higher the period equipment score corresponding to the earlier time period, and the more the number of time periods within the period cluster, then the cluster period equipment score corresponding to this period cluster will gradually increase;

[0113] The device status score corresponding to the current monitoring time point is obtained by summing up the scores of several clusters of periodic devices before the current monitoring time point.

[0114] Please refer to Figure 2 , in this embodiment, dividing several time periods according to the periodic device scores to obtain several periodic clusters includes the following steps:

[0115] Step 1: Obtain several historical periodic device scores ZSP j and their corresponding several time periods SZ j ;

[0116] Step 2: Create a new periodic cluster list; the new periodic cluster list is used to store several time periods;

[0117] Step 3: Determine whether ZSP j is greater than the score threshold, and the score threshold is set according to experience; if yes, put ZSP j into the periodic cluster list, and enter the next time period; enter Step 3; if no, determine whether the periodic cluster list is an empty list. If yes, put ZSP j into the periodic cluster list, and enter the next time period; enter Step 2; if no, create a new periodic cluster list, put ZSP j into the periodic cluster list, and enter the next time period, enter Step 2; where j represents the number corresponding to the time period; through the above steps, all adjacent time periods with periodic device scores higher than the score threshold can be aggregated, so that the device score can be closer to the actual situation when performing the device score, and the accuracy of the device score can be improved.

[0118] Generating the available power according to the device parameters and the device status score in this embodiment includes:

[0119] Obtain several historical device parameters, historical device status scores, historical environmental data, meteorological anomaly coefficients, and prediction labels, and integrate the several historical device parameters, historical device status scores, historical environmental data, and meteorological anomaly coefficients into a power prediction sequence;

[0120] Input the prediction label and the power prediction sequence into a multi-modal prediction model to obtain the predicted power generation; the multi-modal prediction model is constructed by an artificial intelligence model;

[0121] Extract the stored energy power in the power plant data in real time; the power obtained by model prediction refers to the power that can be generated from the current time to the prediction time point, and the available power refers to all the power that can be generated at the prediction time point. At this time, it is necessary to add the power stored in the energy storage device in the power plant to obtain the available power;

[0122] The available power is obtained by summing up the stored energy power and the predicted power generation.

[0123] In this embodiment, through multi-source data such as environmental data, equipment status scores, and meteorological data, the power generation in the future time is predicted by a pre-trained multi-modal prediction model, and the sum of the predicted power generation and the power storage capacity of the power plant is obtained to get the available power supply. The prediction of power generation through multi-source data makes the prediction of power production more accurate, providing a good foundation for the subsequent power supply scheme.

[0124] The multi-modal prediction model in this embodiment is constructed by an artificial intelligence model, including:

[0125] Obtain historical prediction labels and their corresponding several historical parameter prediction sequences or historical power prediction sequences, as well as their corresponding historical equipment parameters or historical power generation; the prediction labels include parameter prediction labels and power prediction labels;

[0126] Divide the several historical parameter prediction sequences and historical equipment parameters, as well as several historical power prediction sequences and historical power generation into multi-task branches according to the prediction labels;

[0127] Divide the several historical parameter prediction sequences and historical equipment parameters, as well as several historical power prediction sequences and historical power generation into training data, validation data, and test data corresponding to the parameter prediction label, and training data, validation data, and test data corresponding to the power prediction label; perform data preprocessing on the training data, validation data, and test data to obtain a training set, a validation set, and a test set; the ratio among the training set, the test set, and the validation set is 7:2:1;

[0128] Select two machine learning models as the basic models for the multi-task branches; both of the two machine learning models adopt the LSTM model;

[0129] Train their corresponding basic models through their respective training sets, and adjust the learning rate and other hyperparameters on their respective validation sets to obtain their respective pre-trained models;

[0130] Verify their respective pre-trained models on their respective test sets, and finally obtain a multi-modal prediction model with input prediction labels and their corresponding parameter prediction sequences or power prediction sequences, and output prediction equipment parameters or predicted power generation.

[0131] Please refer to Figure 3 , the generation of the adjustment plan according to the available power supply and demand data in this embodiment includes:

[0132] Obtain the available power supply and demand data; the demand data includes the total demand power and the regional power demand and regional parameters corresponding to several regions;

[0133] Determine whether the available power is greater than the total required power; if yes, do nothing; if no, generate an emergency power warning signal, obtain the maximum purchase power, which is set by the power plant according to the cost, and obtain the maximum supply power by summing the maximum purchase power and the available power; determine whether the maximum supply power is greater than the total required power; if yes, do nothing, if no, generate an alarm signal for insufficient regional power; generate several regional allocated powers according to the maximum supply power and regional parameters; supply power to several regions according to the regional allocated powers.

[0134] Generating several regional allocated powers according to the maximum supply power and regional parameters in this embodiment includes:

[0135] Obtain the maximum supply power and regional parameters; regional parameters include building grade, population density, and the number of special groups; special groups include the elderly, the sick, and the disabled, etc.; considering special buildings such as hospitals, their corresponding building grades are higher, and the building grade is evaluated by experts according to the impact caused by power shortage, and give priority to ensuring the power supply in buildings with higher building grades in the region;

[0136] Extract the power required by buildings with a building grade higher than the grade threshold in several regions;

[0137] Obtain the population density RM and the number of special groups TS corresponding to several regions;

[0138] Construct a priority function YF(RM, TS) through the non-linear relationship between population density and the number of special groups and regional priority; among them, the priority function is an increasing function; specifically expressed as: Among them, α is the exponential coefficient, α ∈ (0, 1), and the specific value is set according to experience. In this embodiment, α is set to 0.8. The setting of α reflects the marginal diminishing effect. The higher the population density, the smaller the marginal increase in power demand per unit population, avoiding over-concentration of resources; β is the proportionality coefficient, β > 0, and the specific value is set according to experience. In this embodiment, β is set to 2. The setting of β is to control the intensity of the synergy effect. When RM and TS both exceed the reference value, the regional priority is significantly improved; RM base and TS base respectively represent the reference density and the reference quantity, and the specific values are set according to experience;

[0139] Input the population density and the number of special groups in several regions into the priority function to calculate the regional priority;

[0140] Calculate the divisible power by taking the difference between the maximum supply power and the sum of the power required by several buildings; ensure the priority supply of the power required by buildings with higher building grades, and after the supply, allocate the remaining divisible power according to the priority;

[0141] Judge whether the divisible power is greater than 0; if yes, perform a normalization operation on the priorities of several regions to obtain the normalized region priorities, and calculate the divisible power of several regions by multiplying the divisible power by the region priorities; if no, generate a power outage alarm signal;

[0142] Obtain the region allocation power by summing the divisible power of the region and the power required by the buildings within its corresponding region.

[0143] In this embodiment, first, the available power of the power plant is compared with the actual demand data; if the available power can meet the demand data, there is no need to perform an additional power purchase operation; if the available power cannot meet the demand, after implementing the power purchase measures, there are still some regions where power coverage cannot be achieved. At this time, according to the priorities of the regions and the importance of special buildings within the regions, power will be provided preferentially to these regions and buildings to ensure the power consumption needs of important buildings; after that, the available power of each region will be dynamically allocated, and corresponding alarm signals will be sent simultaneously to make preparations in advance and reduce the probability of a poor user experience caused by a sudden imbalance in power supply.

[0144] Generating an alarm signal according to the meteorological anomaly coefficient and the equipment status score in this embodiment includes:

[0145] Obtain the meteorological anomaly coefficient and the equipment status score;

[0146] Judge whether the meteorological anomaly coefficient is greater than the meteorological anomaly threshold, and the meteorological anomaly threshold is set according to experience; if yes, generate a meteorological alarm signal; if no, do nothing;

[0147] Judge whether the equipment status score is greater than the equipment scrapping threshold, and the equipment scrapping threshold is set according to experience; if yes, generate an equipment scrapping alarm signal; if no, judge whether the equipment status score is greater than D times the equipment scrapping threshold, if yes, generate an equipment maintenance warning signal; if no, do nothing; where D represents a proportionality coefficient, D ∈ (0, 1), and the specific value is set according to experience. In this embodiment, D is set to 0.6.

[0148] Please refer to Figure 4 , the second aspect embodiment of this application provides a power grid meteorological data monitoring and evaluation method, including:

[0149] S0: Obtain power plant data, environmental data, and demand data; the environmental data includes environmental parameters and weather forecasts; the power plant data includes power generation equipment IDs and equipment parameters;

[0150] S1: Generate a meteorological anomaly coefficient according to the environmental parameters and weather forecasts; generate an equipment status score according to the power plant data and environmental data;

[0151] S2: Obtain device parameters in real time, and generate available power according to the device parameters and the device status score.

[0152] S3: Generate an adjustment plan according to the available power and demand data; generate an alarm signal according to the meteorological anomaly coefficient and the device status score.

[0153] S4: Make a prompt according to the alarm signal and contact the management personnel.

[0154] Another embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements a power grid meteorological data monitoring and evaluation system according to the first aspect embodiment of the present application.

[0155] Some of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is obtained by software simulation of a large amount of collected data to get a formula closest to the real situation; the preset parameters and preset thresholds in the formula are set by those skilled in the art according to the actual situation or obtained by simulation of a large amount of data.

[0156] The working principle of the present application: By obtaining power plant data, environmental data and demand data; generating a meteorological anomaly coefficient according to environmental parameters and weather forecasts; generating a device status score according to power plant data and environmental data; obtaining device parameters in real time, and generating available power according to the device parameters and the device status score; generating an adjustment plan according to the available power and demand data; generating an alarm signal according to the meteorological anomaly coefficient and the device status score; making a prompt according to the alarm signal and contacting the management personnel, quantifying the monitoring results of multiple meteorologies and calculating the future meteorological anomaly coefficient, considering the impact of meteorology on future power generation, and dynamically adjusting the power supply of the region according to the demand data in the supply area, improving the balance between power supply and demand and the accuracy and comprehensiveness of meteorological monitoring, and avoiding the problem that the prior art lacks consideration of the power loss of related devices during operation and the impact degree of the device status caused by meteorological anomalies, resulting in low power generation efficiency and imbalance between power supply and demand.

[0157] The above embodiments are only used to illustrate the technical method of the present application and not to limit it. Although the present application has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present application can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present application.

Claims

1. A power grid meteorological data monitoring and evaluation system, characterized in that Including: A data acquisition module, a data analysis module, an early warning module, and a database; The data acquisition module: Obtains power plant data, environmental data, and demand data through data acquisition devices; The environmental data includes environmental parameters and weather forecasts; The power plant data includes power generation equipment IDs and equipment parameters; The data analysis module: Generates a meteorological anomaly coefficient based on environmental parameters and weather forecasts; Generates an equipment status score based on power plant data and environmental data; Obtains equipment parameters in real time, and generates the available power according to the equipment parameters and the equipment status score; Generates an adjustment plan based on the available power and demand data; Generates an alarm signal based on the meteorological anomaly coefficient and the equipment status score.

2. The grid meteorological data monitoring and evaluation system according to claim 1, wherein The generating of the meteorological anomaly coefficient according to environmental parameters and weather forecasts includes: Obtaining environmental parameters, equipment parameters, and weather forecasts within a time period T; The environmental parameters include wind speed, wind direction, temperature, and humidity; The equipment parameters include the number of equipment rotations and the amplitude of equipment rotations; The weather forecasts include wind speed, temperature, and humidity; The environmental parameters and weather forecasts are represented as environmental data corresponding to different time periods; Obtaining historical environmental parameters, historical equipment parameters, and their corresponding historical weather forecasts and prediction labels for a number of historical time periods; Integrating the historical environmental parameters, historical equipment parameters, and their corresponding historical weather forecasts for a number of historical time periods into a parameter prediction sequence; Inputting the prediction labels and the parameter prediction sequence into a multi-modal prediction model to obtain predicted equipment parameters for a number of time periods; The multi-modal prediction model is constructed through an artificial intelligence model; Generating a meteorological anomaly coefficient based on the environmental data and equipment parameters within a time period.

3. The grid meteorological data monitoring and evaluation system according to claim 1, characterized in that The generating of the meteorological anomaly coefficient according to the environmental data and equipment parameters within a time period includes: Obtaining the environmental data and equipment parameters within a time period; The environmental data includes environmental parameters and weather forecasts; The equipment parameters include the equipment parameters within the current time period and the predicted equipment parameters within the future time period; Extracting the wind speed FV, temperature WD, and humidity SD from the environmental parameters and weather forecasts; Extracting the number of equipment rotations SZC and the amplitude of equipment rotations SZF from the equipment parameters; Constructing an environmental impact function HYF(FV, WD, SD) through the non-linear relationship between the wind speed FV, temperature WD, and humidity SD and the meteorological anomaly coefficient; Constructing an equipment impact function SYF(SZC, SZF) through the non-linear relationship between the number of equipment rotations SZC and the amplitude of equipment rotations SZF and the meteorological anomaly coefficient; Performing linear weighted fusion on the environmental impact function and the equipment impact function, and substituting a number of parameters within the time period into the calculation to obtain the meteorological anomaly coefficient corresponding to the time period.

4. The grid meteorological data monitoring and evaluation system according to claim 1, wherein The generating of the equipment status score according to power plant data and environmental data includes: Obtaining power plant data and environmental data for a number of time periods; The power plant data includes power generation equipment IDs and equipment parameters; The equipment parameters include the number of start-stop times QT, rotational speed ZV, and operating duration YS; The environmental data includes temperature WD and humidity SD; Construct a periodic scoring function ZPF(QT, ZV, YS, WD, SD) based on the non-linear relationship between device parameters, environmental data, and periodic device scores; Input the corresponding device parameters and environmental data within a time period into the periodic scoring function to calculate the periodic device score; Divide several time periods according to the periodic device scores to obtain several periodic clusters; According to the formula CZSP = ∑ i ZSP i ×e ω×(i-1) the cluster period device scores CZSP corresponding to several period clusters are calculated; where i represents the number of time periods within the period cluster; ω represents the cooperation factor, ω ∈ (0, 1); Sum the device scores of several cluster periods before the current monitoring time point to obtain the device status score corresponding to the current monitoring time point.

5. The grid meteorological data monitoring and evaluation system according to claim 4, characterized in that, The step of dividing several time periods according to the periodic device scores to obtain several periodic clusters includes the following steps: Step 1: Obtain a number of historical cycle device scores ZSP j and their corresponding number of time cycles SZ j ; Step two: Create a new list of periodic clusters; Step 3: Determine ZSP j Whether it is greater than the scoring threshold; Yes, place the ZSP j into the said periodic cluster list, and enter the next time period; proceed to Step Three; No, determine whether the cycle cluster list is an empty list. If yes, place ZSP j into the cycle cluster list and enter the next time cycle; go to step two; if not, create a new cycle cluster list, place ZSP j into the cycle cluster list and enter the next time cycle, and go to step two; where j represents the number corresponding to the time cycle.

6. The meteorological data monitoring and evaluation system for power grid according to claim 1, wherein, The generation of available power according to device parameters and device status scores includes: Obtain several historical device parameters, historical device status scores, historical environmental data, meteorological anomaly coefficients, and prediction labels, and integrate the several historical device parameters, historical device status scores, historical environmental data, and meteorological anomaly coefficients into a power prediction sequence; Input the prediction label and the power prediction sequence into a multi-modal prediction model to obtain the predicted power generation; the multi-modal prediction model is constructed through an artificial intelligence model; Extract the stored energy power in the power plant data in real time; Sum the stored energy power and the predicted power generation to obtain the available power.

7. A power grid meteorological data monitoring and evaluation system according to claim 2 or claim 6, characterized in that, The construction of the multi-modal prediction model through an artificial intelligence model includes: Obtain historical prediction labels and their corresponding several historical parameter prediction sequences or historical power prediction sequences, and their corresponding historical device parameters or historical power generations; the prediction labels include parameter prediction labels and power prediction labels; Divide them into several historical parameter prediction sequences and historical device parameters with multi-task branches according to the prediction labels, and several historical power prediction sequences and historical power generations; Divide the several historical parameter prediction sequences and historical device parameters, and several historical power prediction sequences and historical power generations into training data, validation data, and test data corresponding to the parameter prediction label, and training data, validation data, and test data corresponding to the power prediction label; perform data preprocessing on the training data, validation data, and test data to obtain a training set, a validation set, and a test set; Select two machine learning models as the basic models for multi-task branches; Train their corresponding basic models through their respective training sets, and adjust the learning rate and other hyperparameters on their respective validation sets to obtain their respective pre-trained models; Verify the respective pre-trained models on their respective test sets, and finally obtain a multi-modal prediction model that inputs the prediction label and its corresponding parameter prediction sequence or power prediction sequence, and outputs the predicted device parameter or predicted power generation.

8. The meteorological data monitoring and evaluation system for power grid according to claim 1, characterized in that The generation of an adjustment plan according to the available power and demand data includes: Obtain the available power and demand data; the demand data includes the total demand power and the regional power demand and regional parameters corresponding to several regions; Judge whether the available power is greater than the total demand power; if yes, do nothing; if no, generate an early warning signal for power shortage, obtain the maximum purchase power, and sum the maximum purchase power and the available power to obtain the maximum supply power; Determine whether the maximum power supply is greater than the total demand power; if yes, do nothing; if no, generate an alarm signal for insufficient regional power; generate a number of regional allocated powers according to the maximum power supply and regional parameters; supply power to a number of regions according to the regional allocated powers.

9. The grid meteorological data monitoring and evaluation system according to claim 8, characterized in that The generating a number of regional allocated powers according to the maximum power supply and regional parameters includes: Obtain the maximum power supply and regional parameters; the regional parameters include building grade, population density, and the number of special groups; the special groups include the elderly, the sick, and the disabled; Extract the power required for buildings with a building grade higher than the grade threshold in a number of regions; Obtain the population density RM and the number of special groups TS corresponding to a number of regions; Construct a priority function YF(RM, TS) through the non-linear relationship between population density, the number of special groups, and regional priority; among them, the priority function is an increasing function; Input the population density and the number of special groups in a number of regions into the priority function to calculate the regional priority; Calculate the divisible power by taking the difference between the maximum power supply and the sum of the power required for a number of buildings; Determine whether the divisible power is greater than 0; if yes, perform a normalization operation on the regional priorities of a number of regions to obtain the normalized regional priorities, and calculate the divisible powers of a number of regions by multiplying the divisible power by the regional priorities; if no, generate a power outage alarm signal; Obtain the regional allocated power by summing the divisible power of a region and the power required for the buildings in its corresponding region.

10. A method for monitoring and evaluating power grid meteorological data, which is applied to a power grid meteorological data monitoring and evaluating system according to any one of claims 1-9, and is characterized in that, Includes: S0: Obtain power plant data, environmental data, and demand data; the environmental data includes environmental parameters and weather forecasts; the power plant data includes the power generation equipment ID and equipment parameters; S1: Generate a meteorological anomaly coefficient according to the environmental parameters and weather forecasts; generate an equipment status score according to the power plant data and environmental data; S2: Obtain the equipment parameters in real time, and generate the available power supply according to the equipment parameters and the equipment status score; S3: Generate an adjustment plan according to the available power supply and demand data; generate an alarm signal according to the meteorological anomaly coefficient and the equipment status score.

Images