A power grid weather warning system based on multi-data cloud platform

Abstract

The present invention discloses a weather warning system for power grid based on a multi-data cloud platform, which relates to the field of meteorological forecasting technology, including: a geomorphic feature acquisition module, a multi-source meteorological data acquisition module, a data fusion prediction module, a risk assessment module and a warning module; the geomorphic feature acquisition module and the data fusion prediction module are electrically connected to obtain geomorphic data and historical meteorological data of the area where the power grid is located, and based on the historical meteorological data, the relationship between the influence of the geomorphic on the bad weather is analyzed to obtain the probability of the occurrence of bad weather in the current power grid geomorphic. The present invention can comprehensively and accurately predict the occurrence of future meteorological bad weather and the probability of power grid failure, and warn the staff to protect the power grid in bad weather. Based on the analysis of the geomorphic, the change of the geomorphic on the meteorology is reduced, and the difference between the result and the actual result in the power grid area is reduced, so as to make a more accurate prediction.

Description

Technical Field

[0001] The present invention relates to the technical field of meteorological forecasting, and in particular to a power grid weather meteorological early warning system based on a multi-data cloud platform. Background Art

[0002] With the continuous expansion of the scale of modern power grids and the increasing requirements for power supply reliability, the impact of weather and meteorological conditions on power grid operation has attracted more and more attention. Power grid weather is not a simple meteorological concept, but refers to various meteorological conditions and related situations that affect the operation of the power grid. The weather that affects the normal operation of the power grid includes heavy rain, lightning, strong winds, high temperature, low temperature rain and snow, and sandstorms. All kinds of severe weather may cause transmission line failures, substation equipment damage, power grid tripping and power outages, and many other problems, which bring great inconvenience and economic losses to social production and life. Traditional power grid meteorological warning methods often rely on meteorological data from a single source, such as relying solely on the regular weather forecast information issued by the local meteorological department to take protective measures for the power grid. However, the regular weather forecast information issued by the meteorological department has the problems of untimely data updates and limited spatial resolution. In addition, due to the geomorphological characteristics of the power grid area, the severe weather reported by some meteorological bureaus will have corresponding changes in different geomorphological characteristics, resulting in differences between the results predicted by the meteorological bureau and the actual results in the power grid area. In this regard, we propose a power grid weather meteorological warning system based on a multi-data cloud platform. Summary of the invention

[0003] In order to solve the above technical problems, a power grid weather meteorological early warning system based on a multi-data cloud platform is provided. This technical solution solves the problem of the difference between the above-mentioned prediction results and the actual results.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is: a power grid weather meteorological early warning system based on a multi-data cloud platform, comprising: a geomorphic feature acquisition module, a multi-source meteorological data acquisition module, a data fusion prediction module, a risk assessment module and a warning module;

[0005] The geomorphic feature acquisition module is electrically connected to the data fusion prediction module to obtain geomorphic data and historical meteorological data of the area where the power grid is located. Based on the historical meteorological data, the influence of geomorphology on severe weather is analyzed to obtain the probability of severe weather in the current power grid geomorphology, and the result is uploaded to the data fusion prediction module.

[0006] The multi-source meteorological data acquisition module is electrically connected to the data fusion prediction module, and the future weather data in the current power grid area is acquired based on the multi-source data platform and uploaded to the data fusion prediction module;

[0007] The data fusion prediction module fuses the future weather data obtained from multiple sources, obtains the future weather data prediction results based on the advantages of each data, combines the probability of severe weather in the grid topography, obtains the occurrence of severe weather in the future, and calculates the probability of grid failure;

[0008] The risk assessment module is electrically connected to the data fusion prediction module. Based on the predicted severe weather conditions, the safety risk value of the power grid under severe weather conditions is determined, and a safety threshold is established. The determined safety risk value is compared with the safety threshold. If the value is greater than the safety threshold, it is determined that there is a risk in the future weather, and the warning module is activated to alarm. If the value is less than the safety threshold, it is determined that there is no risk in the future weather.

[0009] The warning module is electrically connected to the risk assessment module. After determining that there is a risk, the warning module will sound an alarm to alert the staff to take timely action.

[0010] The multi-source meteorological data acquisition module includes a meteorological bureau acquisition unit and a quantum analysis unit. The meteorological bureau acquisition unit uploads the weather forecast results obtained by the meteorological bureau based on the results of future weather forecasts obtained by the meteorological bureau; the quantum analysis unit monitors microscopic changes in the atmosphere based on quantum sensors. The sensors measure the temperature, humidity and air pressure parameters in the atmosphere based on quantum effects, and obtain weather forecast results based on quantum algorithms.

[0011] The actual observable meteorological forecast results are obtained from the quantum state, and quantum measurement operations are performed. It is assumed that the measurement is performed at the final moment a. Based on the quantum mechanics measurement hypothesis, the quantum state corresponding to the meteorological element Ba is measured, and the result of the temperature in the nth interval is obtained with probability cn. The meteorological forecast results are obtained comprehensively, and multiple quantum simulations and strategies are performed. The frequency of occurrence of different results is statistically calculated to give the predicted probability distribution of the temperature, air pressure, and humidity meteorological elements at a certain moment in the future. Further, the presence or absence of other meteorological events is also represented by quantum states, and the corresponding future weather forecast value G is obtained through algorithm construction and measurement operations combined with the quantum state of the meteorological elements, and the prediction results are uploaded.

[0012] Preferably, the geomorphic feature acquisition module acquires the current geomorphic and topographical features of the power grid based on high-resolution satellite remote sensing images, the features including terrain undulations, mountain directions, plateau plain distribution, and basin and valley information. The acquired features are stored, and the local historical meteorological data of the power grid obtained from the Meteorological Bureau is analyzed, wherein severe weather includes heavy rain, lightning, strong winds, high temperatures, low temperatures, rain and snow, and sandstorms. Based on the acquired historical meteorological data and geomorphic feature data, the probability of severe weather occurring in the current power grid topography is obtained through statistical analysis and calculation, and the calculated results are uploaded.

[0013] Preferably, the statistical analysis adopts the establishment of a logistic regression model analysis, and the establishment form is:

[0014]

[0015] Where P is the precipitation series, E i represents the severe weather of the ith event, D is the geomorphic feature vector of the area where the power grid is located, M is the historical meteorological dataset, β i0 is the intercept term, β Dj is the coefficient corresponding to the jth geomorphic feature in the geomorphic feature D, Dj is the jth geomorphic feature in the geomorphic feature, k is the dimension of the geomorphic feature vector D, γ iL F is a meteorological feature ML The corresponding coefficient, s is the meteorological feature set F M dimension, L is the number of meteorological elements, F ML is the meteorological characteristic of the Lth;

[0016] Based on the trained model, the occurrence probability is calculated for the geomorphic characteristic values ​​and corresponding meteorological characteristic values ​​of the area where the current power grid is located. The calculation formula is:

[0017]

[0018] Where P(E i |D s , F MS ) is the probability of occurrence of each type of severe weather in the area where the current power grid is located, D s is the actual geomorphic characteristic value of the area where the current power grid is located, F MS is the corresponding meteorological characteristic value, E represents severe weather. Based on the acquired geomorphological data and historical meteorological data of the power grid area, the influence of topography on severe weather is analyzed, and the occurrence probability of various severe weather in the current power grid topography is obtained.

[0019] Preferably, the data fusion prediction module fuses the acquired multi-source future weather data based on a weighted fusion method, and the fusion formula is:

[0020] H=w1x+w2G

[0021] Among them, H is the fused future weather result, w1 and w2 are the corresponding weight coefficients, x is the future weather result predicted by the Meteorological Bureau, and G is the future weather forecast value obtained based on the quantum algorithm; the fused weather result is combined with the probability of severe weather in the power grid topography to calculate the probability value of power grid failure.

[0022] Preferably, the probability of severe weather is set to U, and the number of grid failures in severe weather is z. The probability of grid failure in severe weather is calculated as: K = z / U. Based on the formula, the probability of grid failure in severe weather is obtained.

[0023] Preferably, the risk assessment module determines the safety hazard risk value under different severe weather conditions using the following calculation formula: R=KO, where R is the safety risk value obtained through assessment, K is the probability of a power grid failure under severe weather conditions, and O is the impact value caused by a power grid failure. The safety risk value of the power grid under severe conditions is obtained based on the formula, which is based on the scope of the power outage, the duration of the power outage, and the economic losses.

[0024] Preferably, the risk assessment module obtains the safe operation threshold based on the national grid in accordance with the standard. The standard stipulates the performance indicators and safe operation requirements of power grid equipment under different voltage levels and different weather scenarios, including the rated voltage, rated current range and insulation withstand voltage level of electrical equipment. The corresponding safety threshold is set with reference to the standard specifications, and the calculated safety risk value is compared with the safety threshold to obtain the comparison result.

[0025] Preferably, the warning module determines the existence of risks by comparing the calculated security risk value with the security threshold, activates the alarm mechanism, issues a warning message, and takes protective measures. The alarm includes SMS notifications, mobile terminal push, system pop-up windows, and voice reports.

[0026] Compared with the prior art, the present invention has the following beneficial effects:

[0027] The present invention acquires meteorological data from multiple sources through the coordinated operation of a geomorphic feature acquisition module, a multi-source meteorological data acquisition module, and a data fusion prediction module, and updates the meteorological data in a timely manner. It can comprehensively and accurately predict the occurrence of future severe weather and the probability of power grid failures, and warn staff to protect the power grid in severe weather. Based on the analysis of the geomorphology, it reduces the changes in the meteorology caused by the geomorphology, reduces the difference between the results and the actual results in the power grid area, and achieves more accurate predictions. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a structural block diagram of the early warning system of the present invention;

[0029] Figure 2 This is a structural block diagram of the multi-source meteorological data acquisition module of the present invention. DETAILED DESCRIPTION

[0030] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0031] Reference Figure 1 and Figure 2 As shown, a power grid weather meteorological early warning system based on a multi-data cloud platform includes: a geomorphic feature acquisition module, a multi-source meteorological data acquisition module, a data fusion prediction module, a risk assessment module and a warning module;

[0032] The geomorphic feature acquisition module is electrically connected to the data fusion prediction module to obtain geomorphic data and historical meteorological data of the area where the power grid is located. Based on the historical meteorological data, the influence of geomorphology on severe weather is analyzed to obtain the probability of severe weather in the current power grid geomorphology, and the result is uploaded to the data fusion prediction module.

[0033] The multi-source meteorological data acquisition module is electrically connected to the data fusion prediction module, and the future weather data in the current power grid area is acquired based on the multi-source data platform and uploaded to the data fusion prediction module;

[0034] The data fusion prediction module fuses the future weather data obtained from multiple sources, obtains the future weather data prediction results based on the advantages of each data, combines the probability of severe weather in the grid topography, obtains the occurrence of severe weather in the future, and calculates the probability of grid failure;

[0035] The risk assessment module is electrically connected to the data fusion prediction module. Based on the predicted severe weather conditions, the safety risk value of the power grid under severe weather conditions is determined, and a safety threshold is established. The determined safety risk value is compared with the safety threshold. If the value is greater than the safety threshold, it is determined that there is a risk in the future weather, and the warning module is activated to alarm. If the value is less than the safety threshold, it is determined that there is no risk in the future weather.

[0036] The warning module is electrically connected to the risk assessment module. After determining that there is a risk, the warning module will sound an alarm to alert the staff to take timely action.

[0037] The multi-source meteorological data acquisition module includes a meteorological bureau acquisition unit and a quantum analysis unit. The meteorological bureau acquisition unit uploads the weather forecast results obtained by the meteorological bureau based on the results of future weather forecasts obtained by the meteorological bureau; the quantum analysis unit monitors microscopic changes in the atmosphere based on quantum sensors. The sensors measure the temperature, humidity and air pressure parameters in the atmosphere based on quantum effects, and obtain weather forecast results based on quantum algorithms.

[0038] The actual observable meteorological forecast results are obtained from the quantum state, and quantum measurement operations are performed. It is assumed that the measurement is performed at the final moment a. Based on the quantum mechanics measurement hypothesis, the quantum state corresponding to the meteorological element Ba is measured, and the result of the temperature in the nth interval is obtained with probability cn. The meteorological forecast results are obtained comprehensively, and multiple quantum simulations and strategies are performed. The frequency of occurrence of different results is statistically calculated to give the predicted probability distribution of the temperature, air pressure, and humidity meteorological elements at a certain moment in the future. Further, the presence or absence of other meteorological events is also represented by quantum states, and the corresponding future weather forecast value G is obtained through algorithm construction and measurement operations combined with the quantum state of the meteorological elements, and the prediction results are uploaded.

[0039] The meteorological bureau acquisition unit of this application relies on the meteorological bureau's mature meteorological observation network, numerical forecast models and the experience of professional meteorological personnel, and can provide relatively macro and comprehensive weather forecast results based on traditional meteorological methods. The quantum analysis unit relies on the unique quantum effect of quantum sensors to focus on microscopic changes in the atmosphere, accurately measure key parameters such as temperature, humidity and air pressure at the microscopic level, and analyze and predict through quantum algorithms. It can capture some subtle meteorological change trends that are difficult to detect with traditional means. The two complement each other, making the acquired weather forecast information more comprehensive and detailed, making up for the possible limitations of a single data source, thereby effectively improving the accuracy of the overall weather forecast.

[0040] This application can dig deep into the microscopic level of the atmosphere to mine information by measuring quantum states and performing operations based on the principles of quantum mechanics. Traditional meteorological forecasting methods are mostly based on macroscopic meteorological observation data and classical physical models, while quantum state-related operations can capture changes related to meteorological elements at the atomic and molecular microparticle levels. For example, quantum states are affected by the thermal motion and interaction of microscopic particles, and thus reflect the potential change trends of macroscopic meteorological elements such as temperature, air pressure, and humidity. This analysis method from micro to macro helps to more accurately grasp the subtle fluctuations of meteorological elements, thereby improving the accuracy of predictions and making the predicted probability distribution of meteorological elements at a certain moment in the future more in line with the actual situation. For example, it can more accurately predict the slight changes in temperature, fine fluctuations in air pressure, and subtle increases and decreases in humidity in a local area over a short period of time, providing more reliable data support for various meteorological-related activities.

[0041] Quantum effects play an important role in meteorology. For example, quantum entanglement in quantum mechanics may affect the formation of clouds and the occurrence of rainfall. Traditional meteorological models are based on macroscopic physical laws and cannot fully explain these phenomena. Quantum physics provides new perspectives and tools. Cloud formation is an important process in meteorology. Traditional models believe that cloud formation is mainly affected by temperature, humidity and air pressure. However, the phenomenon of quantum entanglement shows that the quantum state between water molecules may have an important influence on cloud formation. Specifically, quantum entanglement between water molecules can lead to nonlinear changes in clouds on a macroscopic scale, thereby affecting the weather. Rainfall is the process in which water vapor in the atmosphere condenses into droplets and falls to the ground. Traditional meteorology believes that the occurrence of rainfall is mainly affected by the temperature and humidity of the atmosphere. However, the quantum tunneling effect shows that water molecules can quickly condense into droplets through a quantum process called "tunneling". This process can explain why rainfall sometimes occurs suddenly when meteorological conditions are not met.

[0042] Through the coordinated operation of the geomorphic feature acquisition module, the multi-source meteorological data acquisition module and the data fusion prediction module, this application can comprehensively and accurately predict the occurrence of severe weather and the probability of power grid failure in the future. On this basis, the risk assessment module determines the safety risk value and establishes the safety threshold based on these prediction results, and then compares and obtains the risk status. The warning module issues an alarm in time after determining that there is a risk. This series of processes enables power grid operation and maintenance personnel to know in advance the severe weather and potential risks that they will face, and no longer be in a passive response situation;

[0043] Timely and accurate alarms are issued to inform staff of future weather risks. Grid management departments can then rationally allocate human and material resources based on risk levels and scope. The risk assessment module draws on risk judgments based on detailed data fusion analysis and the actual risk situation fed back by the warning module, providing a strong basis for refined management of the grid.

[0044] The geomorphic feature acquisition module obtains the current geomorphic and topographical features of the power grid based on high-resolution satellite remote sensing images. The features include terrain undulations, mountain directions, plateau plain distribution, and basin and valley information. The acquired features are stored and analyzed based on the local historical meteorological data of the power grid obtained from the Meteorological Bureau. Severe weather includes heavy rain, lightning, strong winds, high temperatures, low temperatures, rain and snow, and sandstorms. Based on the acquired historical meteorological data and geomorphic feature data, the probability of severe weather occurring in the current power grid topography is obtained through statistical analysis and calculation, and the calculated results are uploaded.

[0045] This application uses the terrain undulations, mountain directions, plateau and plain distribution, and detailed geomorphic features of basins and valleys obtained through high-resolution satellite remote sensing images. Grid planners can more accurately select the construction locations of substations, transmission lines, and grid infrastructure. For example, after understanding the direction of the mountains, they can try to avoid laying transmission lines along steep mountains that are prone to geological disasters, and instead choose relatively flat areas with stable geological conditions to reduce construction costs and subsequent operation and maintenance risks caused by terrain factors. At the same time, based on the distribution information of plateaus and plains, the directions of lines of different voltage levels can be reasonably planned to make the grid layout more in line with the geographical characteristics of the region, thereby improving the overall stability of the grid and power supply efficiency.

[0046] The statistical analysis adopts the establishment of logistic regression model analysis, and the establishment form is:

[0047]

[0048] Where P is the precipitation series, E i represents the severe weather of the ith event, D is the geomorphic feature vector of the area where the power grid is located, M is the historical meteorological dataset, β i0 is the intercept term, β Dj is the coefficient corresponding to the jth geomorphic feature in the geomorphic feature D, Dj is the jth geomorphic feature in the geomorphic feature, k is the dimension of the geomorphic feature vector D, γ iL F is a meteorological feature ML The corresponding coefficient, s is the meteorological feature set F M dimension, L is the number of meteorological elements, F ML is the meteorological characteristic of the Lth;

[0049] Based on the trained model, the occurrence probability is calculated for the geomorphic characteristic values ​​and corresponding meteorological characteristic values ​​of the area where the current power grid is located. The calculation formula is:

[0050]

[0051] Where P(E i |D s , F MS ) is the probability of occurrence of each type of severe weather in the area where the current power grid is located, D s is the actual geomorphic characteristic value of the area where the current power grid is located, F MS is the corresponding meteorological characteristic value, E represents severe weather. Based on the acquired geomorphological data and historical meteorological data of the power grid area, the influence of topography on severe weather is analyzed, and the occurrence probability of various severe weather in the current power grid topography is obtained.

[0052] The data fusion prediction module fuses the multi-source future weather data acquired based on weighted fusion. The fusion formula is:

[0053] H=w1x+w2G

[0054] Among them, H is the fused future weather result, w1 and w2 are the corresponding weight coefficients, x is the future weather result predicted by the Meteorological Bureau, and G is the future weather forecast value obtained based on the quantum algorithm; the fused weather result is combined with the probability of severe weather in the power grid topography to calculate the probability value of power grid failure.

[0055] Assuming the probability of bad weather to be U, and the number of grid failures in bad weather to be z, the probability of grid failures in bad weather is calculated as: K = z / U; based on the formula, the probability of grid failures in bad weather is obtained.

[0056] The risk assessment module determines the risk safety hazard value under different severe weather conditions using the following calculation formula: R=KO, where R is the assessed safety risk value, K is the probability of a power grid failure under severe weather conditions, and O is the impact value after a power grid failure. The safety risk value of the power grid under severe conditions is obtained based on the formula, which is based on the power outage scope, power outage duration, and economic losses.

[0057] The risk assessment module is based on the safe operation threshold obtained by the State Grid in accordance with the standard. The standard stipulates the performance indicators and safe operation requirements of power grid equipment under different voltage levels and different weather scenarios, including the rated voltage, rated current range and insulation withstand voltage level of electrical equipment. The corresponding safety threshold is set with reference to the standard specifications, and the calculated safety risk value is compared with the safety threshold to obtain the comparison result.

[0058] This application uses the safety thresholds set by standard specifications to provide a clear and definite comparative reference for the safety risk value, so that the risk assessment module can quantify and define the potential risks faced by the power grid. The staff can intuitively understand how far the current power grid operation status is from the safety boundary, whether it is in a normal state, close to the risk threshold, or has exceeded the safety range.

[0059] The warning module determines the existence of risks by comparing the calculated security risk value with the security threshold, activates the alarm mechanism, issues warning information, and takes protective measures. The alarms come in the form of SMS notifications, mobile push notifications, system pop-ups, and voice reports.

[0060] This application warning module uses multiple alarm forms such as SMS notification, mobile push, system pop-up window and voice broadcast, which can comprehensively cover relevant staff in different work scenarios and habits, and issue warnings to staff in time.

[0061] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments, and the above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention, and these changes and improvements fall within the scope of the present invention claimed.

Claims

1. A power grid weather warning system based on a multi-data cloud platform, characterized in that: include: Geomorphic feature acquisition module, multi-source meteorological data acquisition module, data fusion prediction module, risk assessment module and warning module; The geomorphic feature acquisition module is electrically connected to the data fusion prediction module to obtain geomorphic data and historical meteorological data of the area where the power grid is located. Based on the historical meteorological data, the influence of geomorphology on severe weather is analyzed to obtain the probability of severe weather in the current power grid geomorphology, and the result is uploaded to the data fusion prediction module. The multi-source meteorological data acquisition module is electrically connected to the data fusion prediction module, and the future weather data in the current power grid area is acquired based on the multi-source data platform and uploaded to the data fusion prediction module; The data fusion prediction module fuses the future weather data obtained from multiple sources, obtains the future weather data prediction results based on the advantages of each data, combines the probability of severe weather in the grid topography, obtains the occurrence of severe weather in the future, and calculates the probability of grid failure; The risk assessment module is electrically connected to the data fusion prediction module. Based on the predicted severe weather conditions, the safety risk value of the power grid under severe weather conditions is determined, and a safety threshold is established. The determined safety risk value is compared with the safety threshold. If the value is greater than the safety threshold, it is determined that there is a risk in the future weather, and the warning module is activated to alarm. If the value is less than the safety threshold, it is determined that there is no risk in the future weather. The warning module is electrically connected to the risk assessment module. After determining that there is a risk, the warning module will sound an alarm to alert the staff to take timely action. The multi-source meteorological data acquisition module includes a meteorological bureau acquisition unit and a quantum analysis unit. The meteorological bureau acquisition unit uploads the weather forecast results obtained by the meteorological bureau based on the results of future weather forecasts obtained by the meteorological bureau; the quantum analysis unit monitors microscopic changes in the atmosphere based on quantum sensors. The sensors measure the temperature, humidity and air pressure parameters in the atmosphere based on quantum effects, and obtain weather forecast results based on quantum algorithms. The actual observable meteorological forecast results are obtained from the quantum state, and quantum measurement operations are performed. It is assumed that the measurement is performed at the final moment a. Based on the quantum mechanics measurement hypothesis, the quantum state corresponding to the meteorological element Ba is measured, and the result of the temperature in the nth interval is obtained with probability cn. The meteorological forecast results are obtained comprehensively, and multiple quantum simulations and strategies are performed. The frequency of occurrence of different results is statistically calculated to give the predicted probability distribution of the temperature, air pressure, and humidity meteorological elements at a certain moment in the future. Further, the presence or absence of other meteorological events is also represented by quantum states, and the corresponding future weather forecast value G is obtained through algorithm construction and measurement operations combined with the quantum state of the meteorological elements, and the prediction results are uploaded.

2. A power grid weather and meteorological early warning system based on a multi-data cloud platform according to claim 1, characterized in that: The geomorphic feature acquisition module obtains the current geomorphic and topographical features of the power grid based on high-resolution satellite remote sensing images. The features include terrain undulations, mountain directions, plateau plain distribution, and basin and valley information. The acquired features are stored and analyzed based on the local historical meteorological data of the power grid obtained from the Meteorological Bureau. Severe weather includes heavy rain, lightning, strong winds, high temperatures, low temperatures, rain and snow, and sandstorms. Based on the acquired historical meteorological data and geomorphic feature data, the probability of severe weather occurring in the current power grid topography is obtained through statistical analysis and calculation, and the calculated results are uploaded.

3. A power grid weather and meteorological early warning system based on a multi-data cloud platform according to claim 2, characterized in that: The statistical analysis adopts the establishment of logistic regression model analysis, and the establishment form is: Where P is the precipitation series, E i represents the severe weather of the ith event, D is the geomorphic feature vector of the area where the power grid is located, M is the historical meteorological dataset, β i0 is the intercept term, β Dj is the coefficient corresponding to the jth geomorphic feature in the geomorphic feature D, Dj is the jth geomorphic feature in the geomorphic feature, k is the dimension of the geomorphic feature vector D, γ iL F is a meteorological feature ML The corresponding coefficient, s is the meteorological feature set F M dimension, L is the number of meteorological elements, F ML is the meteorological characteristic of the Lth; Based on the trained model, the occurrence probability is calculated for the geomorphic characteristic values ​​and corresponding meteorological characteristic values ​​of the area where the current power grid is located. The calculation formula is: Where P(E i |D s , F MS ) is the probability of occurrence of each type of severe weather in the area where the current power grid is located, D s is the actual geomorphic characteristic value of the area where the current power grid is located, F MS is the corresponding meteorological characteristic value, E represents severe weather. Based on the acquired geomorphological data and historical meteorological data of the power grid area, the influence of topography on severe weather is analyzed, and the occurrence probability of various severe weather in the current power grid topography is obtained.

4. A power grid weather and meteorological early warning system based on a multi-data cloud platform according to claim 1, characterized in that: The data fusion prediction module fuses the multi-source future weather data acquired based on weighted fusion. The fusion formula is: H=w1x+w2G Among them, H is the fused future weather result, w1 and w2 are the corresponding weight coefficients, x is the future weather result predicted by the Meteorological Bureau, and G is the future weather forecast value obtained based on the quantum algorithm; The fused weather results are combined with the probability of severe weather in the grid topography to calculate the probability value of grid failure.

5. A power grid weather meteorological early warning system based on a multi-data cloud platform according to claim 4, characterized in that: Assuming the probability of bad weather to be U, and the number of grid failures in bad weather to be z, the probability of grid failures in bad weather is calculated as: K = z / U; based on the formula, the probability of grid failures in bad weather is obtained.

6. A power grid weather meteorological early warning system based on a multi-data cloud platform according to claim 1, characterized in that: The risk assessment module determines the risk safety hazard value under different severe weather conditions using the following calculation formula: R=KO, where R is the assessed safety risk value, K is the probability of a power grid failure under severe weather conditions, and O is the impact value after a power grid failure. The safety risk value of the power grid under severe conditions is obtained based on the formula, which is based on the power outage scope, power outage duration, and economic losses.

7. A power grid weather and meteorological early warning system based on a multi-data cloud platform according to claim 6, characterized in that: The risk assessment module is based on the safe operation threshold obtained by the State Grid in accordance with the standard. The standard stipulates the performance indicators and safe operation requirements of power grid equipment under different voltage levels and different weather scenarios, including the rated voltage, rated current range and insulation withstand voltage level of electrical equipment. The corresponding safety threshold is set with reference to the standard specifications, and the calculated safety risk value is compared with the safety threshold to obtain the comparison result.

8. The power grid weather and meteorological early warning system based on a multi-data cloud platform according to claim 1 is characterized in that: The warning module determines the existence of risks by comparing the calculated security risk value with the security threshold, activates the alarm mechanism, issues warning information, and takes protective measures. The alarms come in the form of SMS notifications, mobile push notifications, system pop-ups, and voice reports.

Images