Meteorological prediction method and system based on plateau mountain area power grid system

Abstract

The invention relates to the technical field of plateau mountainous area power grids, in particular to a meteorological prediction method and system based on a plateau mountainous area power grid system. Obtaining terrain, climate and ecological characteristics of the plateau mountain area, and constructing a comprehensive data fusion model; acquiring power grid data, and constructing a real-time monitoring model in combination with multi-source data; and taking the output of the data fusion model and the real-time monitoring model as the input, and constructing a meteorological-power grid coupling prediction model. According to the method, innovative indexes such as the terrain-ecology-weather fusion index and the hydrological influence comprehensive index are introduced, and accurate prediction and risk assessment of the plateau mountain area power grid system are realized through multi-dimensional assessment such as the environment state assessment model, the environment influence weight and the power grid health index. According to the method, prediction accuracy and early warning timeliness are remarkably improved, and powerful support is provided for safe and stable operation of a plateau mountain area power grid.

Description

Technical Field

[0001] The invention relates to the technical field of power grids in plateau mountainous areas, and in particular to a meteorological forecasting method and system based on a power grid system in plateau mountainous areas. Background Art

[0002] With the continuous development and complexity of the power system, especially in the plateau and mountainous areas with complex terrain, the safe and stable operation of the power grid faces increasing challenges. In recent years, the impact of meteorological conditions on the power grid system has become increasingly significant, especially in the special geographical environment of the plateau and mountainous areas, where extreme weather events occur frequently, bringing huge pressure to the power grid. Traditional meteorological forecasting methods mainly rely on single meteorological data or simple statistical models, which are difficult to accurately capture the comprehensive impact of the complex terrain, climate and ecological characteristics of the plateau and mountainous areas on the power grid system. In addition, the existing power grid monitoring system often separates meteorological factors from the operation status of the power grid and lacks an effective coupling mechanism, resulting in insufficient timeliness and accuracy in power grid dispatch and risk warning in the face of sudden meteorological events.

[0003] There are many deficiencies in existing technologies in dealing with meteorological forecasting issues in plateau mountainous power grid systems. First, most forecasting models fail to fully consider the unique topographic, ecological and hydrological characteristics of plateau mountainous areas, resulting in a large deviation between the forecast results and the actual situation. Secondly, the traditional power grid monitoring system mainly focuses on electrical parameters, ignores the potential impact of environmental factors on power grid operation, and cannot effectively identify and warn of potential risks caused by extreme meteorological conditions. Furthermore, the existing early warning systems often use fixed thresholds or simple linear models, which are difficult to adapt to the high changes and nonlinear characteristics of meteorological conditions in plateau mountainous areas. Finally, there is a lack of a comprehensive method that organically combines meteorological forecasting, power grid monitoring and risk assessment, which makes it difficult to provide timely and accurate decision support for power grid operators. These deficiencies have seriously restricted the safe and stable operation and efficiency improvement of the power grid system in plateau mountainous areas, and there is an urgent need for a new method that can comprehensively consider multi-source data and realize meteorological-power grid coupling prediction. Summary of the invention

[0004] In view of the problems existing in the prior art, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is that most prediction models fail to fully consider the unique topographic, ecological and hydrological characteristics of plateau mountainous areas, resulting in a large deviation between the prediction results and the actual situation. Secondly, the traditional power grid monitoring system mainly focuses on electrical parameters, ignores the potential impact of environmental factors on power grid operation, and cannot effectively identify and warn of potential risks caused by extreme meteorological conditions. Furthermore, existing early warning systems often use fixed thresholds or simple linear models, which are difficult to adapt to the high changes and nonlinear characteristics of meteorological conditions in plateau mountainous areas. Finally, the lack of a comprehensive method that organically combines meteorological forecasting, power grid monitoring and risk assessment makes it difficult to provide timely and accurate decision support for power grid operators.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a meteorological forecasting method based on a plateau mountainous area power grid system, which includes obtaining unique topographic, climate and ecological characteristics of the plateau mountainous area, and constructing a comprehensive data fusion model, wherein the comprehensive data fusion model processes multi-source data;

[0008] Acquire power grid data, wherein the multi-source data integrated based on the comprehensive data fusion model is combined with the power grid data to construct a real-time monitoring model for the plateau mountain power grid, and the operation status and potential risks of the power grid are obtained through the monitoring model;

[0009] By taking the multi-source data integrated by the comprehensive data fusion model and the real-time status data obtained by the real-time monitoring model as input, a meteorological-grid coupling prediction model is constructed to output the potential impact of future meteorological changes on the power grid system, meteorological warnings, and grid dispatching recommendations.

[0010] As a preferred solution of the weather forecasting method based on the plateau mountain power grid system of the present invention, wherein: the multi-source data includes terrain data, ecological data, hydrological data, and meteorological data, and the power grid data includes transmission line data and power load data;

[0011] Topographic data: altitude, slope, aspect, terrain relief;

[0012] Ecological data: vegetation cover type, vegetation index, soil type;

[0013] Hydrological data: river distribution, lake location, precipitation distribution;

[0014] Meteorological data: temperature, humidity, air pressure, wind speed, wind direction, precipitation, sunshine hours;

[0015] Transmission line data: voltage level, load current, line temperature;

[0016] Electricity load data: regional electricity consumption, load distribution, and peak electricity consumption periods.

[0017] As a preferred solution of the meteorological forecasting method based on the plateau mountain power grid system of the present invention, the following steps can be adopted to obtain the unique topography, climate and ecological characteristics of the plateau mountain area, build a comprehensive data fusion model, and process multi-source data in the comprehensive data fusion model:

[0018] The said construction of comprehensive data fusion model includes terrain-ecology-meteorology fusion index and hydrological impact comprehensive index and environmental status assessment model;

[0019] The terrain, vegetation and basic meteorological conditions are integrated to construct a terrain-ecology-meteorology fusion index. The sensitivity of the model to extreme values ​​is enhanced through exponential and logarithmic transformations. The variance reflects the impact of temperature and air pressure fluctuations on the overall environmental state. The terrain-ecology-meteorology fusion index is used to assess the environmental quality and potential ecological risks in a specific area. The following formula can be used:

[0020]

[0021] Among them, H k is the altitude of the kth position; E k is the vegetation index (NDVI) at the kth location; Slope k ,Aspect k is the slope and aspect of the k-th position; G is the terrain function, G (Slope k ,Aspect k ) = sin(Slope)·cos(Aspect) to simulate the effect of slope on sunshine and water flow; T is the temperature data set, P is the air pressure data set; Var represents the variance of the data, which is used to characterize environmental variability;

[0022] The impact of the hydrological environment on the overall region is evaluated using hydrological characteristics, including water body type, location and precipitation. A sine function is used to simulate the seasonal variation of precipitation, output the periodic impact of precipitation on the hydrological environment, and construct a comprehensive hydrological impact index. The comprehensive hydrological impact index quantifies the comprehensive impact of water body distribution, type and related meteorological conditions on a specific area, which can be expressed as follows:

[0023]

[0024] Among them, D j is the distance from the jth hydrological point (river or lake) to the nearest town; WaterType j is the water body type, which is converted into influence coefficient through IF function; R jis the water resource abundance of the jth hydrological point; is the average annual precipitation at the point; P max is the maximum precipitation in the record;

[0025] By combining the terrain-ecological-meteorological index and the hydrological impact index, and adding the sunshine hours adjusted by wind speed, an environmental status assessment model is constructed. This environmental status assessment model enhances the description of the interaction of environmental variables through logical and nonlinear functions, and uses rich geographical and meteorological data to accurately simulate the comprehensive impact of environmental and meteorological conditions on the environment in plateau mountainous areas, and outputs a comprehensive assessment of the environmental status, which can be expressed as follows:

[0026]

[0027] Among them, α, β, γ are adjustment parameters; V m is the number of hours of visible light sunshine at the mth monitoring point; WindSpeed m It is the wind speed, which is used to adjust the actual impact of sunshine hours on the environment.

[0028] As a preferred solution of the meteorological forecasting method based on the plateau mountain power grid system of the present invention, wherein: the acquisition of power grid data, the multi-source data integrated based on the comprehensive data fusion model and the power grid data are combined to build a real-time monitoring model of the plateau mountain power grid, and the operation status and potential risks of the power grid are obtained through the monitoring model. The following steps can be adopted:

[0029] The real-time monitoring model for the plateau mountain power grid includes an environmental impact weight, a power grid load prediction model, and a power grid health index;

[0030] Integrate environmental data and power grid operation data to achieve in-depth understanding and prediction of the power grid status. Use comprehensive environmental models and seasonal adjustments to evaluate the impact of the environment on the power grid and construct environmental impact weights. The following expression can be used:

[0031] EIW=ω1·CEM+ω2·sin(ω3·SeasonalAdjustment)

[0032] Among them, CEM is the output of the comprehensive environmental model, which reflects the comprehensive status of terrain, ecology, meteorology and hydrology data; SeasonalAdjustment is the parameter adjusted according to seasonal changes, which is a function of the date or month; ω1, ω2, ω3 are adjustment weights used to balance the influence of environmental status and seasonal factors;

[0033] The instantaneous load of the power grid is predicted by combining environmental impact and historical load data, and a power grid load prediction model is constructed. The power grid load prediction model enables power grid operators to adjust resource allocation and emergency response according to environmental conditions and predicted needs. It can be expressed as follows:

[0034] GridLoad=β1·EIW·(β2·HistoricLoad+β3·PredictedDemand)

[0035] Among them, EIW is the output of environmental impact weight; HistoricLoad is the historical load data; PredictedDemand is the demand based on current trends and economic activity forecasts; β1, β2, and β3 are adjustment coefficients used to adjust the impact of various factors on the predicted load;

[0036] By comparing the actual load and the safety margin, a grid health index is constructed. The grid health index is an indicator for evaluating the overall operation status of the grid. The index helps grid operators identify potential overload problems or equipment failure risks, so as to take preventive measures in advance. It can be expressed as follows:

[0037]

[0038] Among them, GridLoad is the output of the grid load forecasting model; SafetyMargin is the safety margin of the grid design, which may be based on the maximum load capacity; γ1 and γ2 are adjustment parameters used to adjust the impact of load and safety margin.

[0039] As a preferred solution of the meteorological forecasting method based on the plateau mountainous power grid system of the present invention, wherein: the meteorological-power grid coupling forecasting model is constructed by taking the multi-source data integrated by the comprehensive data fusion model and the real-time status data obtained by the real-time monitoring model as input, and outputting the potential impact of future meteorological changes on the power grid system and meteorological warnings and power grid dispatching suggestions, which can be specifically adopted in the following steps:

[0040] The weather-grid coupling prediction model constructed includes a weather and environment comprehensive impact index, a grid load and weather coupling model, and a warning prediction and operation suggestion model;

[0041] The terrain and ecological characteristics of the plateau and mountainous areas are integrated with the current meteorological data, and the impact of precipitation on the hydrological index is adjusted through a nonlinear function to construct a comprehensive meteorological and environmental impact index. The comprehensive meteorological and environmental impact index evaluates how the current meteorological conditions and terrain ecological characteristics jointly affect the power grid facilities, especially under extreme climate conditions. The comprehensive meteorological and environmental impact index can be expressed as follows:

[0042]

[0043] Among them, CEM is the output of the characteristic data fusion model of plateau mountainous areas; MeteorologicalData includes temperature, humidity, air pressure, wind speed and wind direction; WaterIndex is the impact index of hydrological data, including river distribution, lake location, and precipitation distribution; Precipitation is real-time precipitation data; λ1, λ2, and λ3 are weight parameters.

[0044] As a preferred solution of the meteorological forecasting method based on the plateau mountainous area power grid system of the present invention, the meteorological coupling model and the warning forecast and operation suggestion model are constructed by the following steps:

[0045] The grid load under specific environmental conditions is predicted by combining the meteorological and environmental comprehensive impact index with the actual operation data of the grid, and a grid load and meteorological coupling model is constructed to evaluate the load response capacity of the grid under extreme meteorological conditions to achieve optimal dispatch and early warning of the grid. The following expression can be used:

[0046]

[0047] Among them, MEII is the output of the comprehensive meteorological and environmental impact index; PeakLoadFactor is the load peak factor based on time and predicted demand; ReliabilityIndex is the grid reliability index, which is calculated based on historical fault and maintenance data; is the adjustment parameter;

[0048] The warning level is calculated by a logistic regression model. If the grid load and meteorological coupling model exceeds the threshold, the warning level increases. A warning prediction and operation suggestion model is constructed. The warning prediction and operation suggestion model can provide real-time dispatch suggestions to operators according to the severity of the meteorological and grid coupling status, including load reduction and startup of the backup system. The following expression is used:

[0049]

[0050] GMC is the output of the grid load and meteorological coupling model; Threshold is the warning threshold set based on historical data and safety standards; ξ1 and ξ2 are adjustment parameters.

[0051] As a preferred solution of the meteorological forecasting method based on the plateau mountain power grid system of the present invention, the warning level output by the meteorological-power grid coupling warning model is based on the meteorological-power grid coupling warning model, and the operation suggestions and warning information are classified as follows to ensure that appropriate response measures are taken at different risk levels:

[0052] Low risk level: When the warning index is lower than the first threshold, meteorological warning information is sent to relevant departments and the public that may be affected, and low-intensity power grid load distribution maps and environmental impact forecasts are generated and displayed for risk awareness training, monitoring of power grid load and environmental factors, and maintaining daily operation and maintenance status;

[0053] Medium risk level: When the warning index is between the first threshold and the second threshold, a warning message is sent to the relevant departments, and a medium-intensity grid resilience and environmental impact forecast is generated and displayed for risk communication and emergency drills, and emergency response plans are activated, including but not limited to adjusting grid load, activating backup power supplies, and preparing evacuation and rescue resources;

[0054] High-risk level: When the warning index exceeds the second threshold, an emergency warning is issued to all relevant departments and the public, and a high-intensity grid load anomaly and potential severe environmental impact forecast are generated and displayed for evacuation route planning and rescue strategy formulation. Evacuation procedures and emergency response measures are immediately initiated, including but not limited to cutting off power supply to high-risk areas to prevent equipment overload from causing greater safety accidents.

[0055] In a second aspect, an embodiment of the present invention provides a meteorological forecasting system based on a plateau mountainous area power grid system, which includes an acquisition module for acquiring unique topography, climate and ecological characteristics of the plateau mountainous area and constructing a comprehensive data fusion model, wherein the comprehensive data fusion model processes multi-source data;

[0056] A construction module is provided to obtain power grid data. The multi-source data integrated based on the comprehensive data fusion model is combined with the power grid data to construct a real-time monitoring model for the plateau mountain power grid. The operation status and potential risks of the power grid are obtained through the monitoring model.

[0057] The output module constructs a meteorological-grid coupling prediction model by taking the multi-source data integrated by the comprehensive data fusion model and the real-time status data obtained by the real-time monitoring model as input, and outputs the potential impact of future meteorological changes on the power grid system, meteorological warnings, and power grid dispatching recommendations.

[0058] In a third aspect, an embodiment of the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of the meteorological forecasting method based on the plateau mountainous power grid system as described in the first aspect of the present invention are implemented.

[0059] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, the steps of the meteorological forecasting method based on the plateau mountainous power grid system as described in the first aspect of the present invention are implemented.

[0060] The beneficial effects of the present invention are: by acquiring the unique topography, climate and ecological characteristics of plateau mountainous areas, a comprehensive data fusion model is constructed to achieve effective integration of multi-source data. This method fully considers the particularity of plateau mountainous areas, improves the integrity and representativeness of the data, and thus lays a solid data foundation for subsequent meteorological forecasting and power grid monitoring, and ultimately achieves the effect of improving the applicability and accuracy of the forecasting model.

[0061] By combining the multi-source data integrated by the comprehensive data fusion model with the power grid data, a real-time monitoring model for the plateau mountain power grid is constructed, realizing dynamic monitoring of the power grid operation status and potential risks. This method organically combines environmental factors with power grid operation data, enhances the comprehensiveness and real-time nature of monitoring, helps to timely discover and warn potential risks, and ultimately achieves the effect of improving the safety and reliability of power grid operation.

[0062] By building a meteorological-grid coupling prediction model, the output of the comprehensive data fusion model and the real-time monitoring model is used as input to predict future meteorological changes and their potential impact on the power grid system. This coupled prediction method takes into account the complex interaction between meteorological conditions and power grid operation, improves the accuracy and foresight of the prediction, and ultimately achieves the effect of providing more reliable decision support for power grid dispatching and risk management.

[0063] By introducing the terrain-ecology-meteorology fusion index and the hydrological impact comprehensive index, the quantitative characterization of the complex environmental factors in the plateau and mountainous areas is achieved. This innovative index design fully considers the mutual influence of multiple factors such as terrain, ecology, meteorology and hydrology, improves the accuracy and comprehensiveness of environmental status assessment, and ultimately achieves the effect of better reflecting the impact of the special environment of the plateau and mountainous areas on the power grid.

[0064] By constructing environmental impact weights, grid load prediction models and grid health indexes, a comprehensive assessment of environmental factors, grid load and operating status is achieved. This multi-dimensional assessment method takes into account multiple aspects such as the environment, load and health status, enhances the comprehensiveness and scientificity of grid status assessment, and ultimately achieves the effect of more accurately judging grid operation risks and optimizing operation strategies.

[0065] By introducing the meteorological and environmental comprehensive impact index and the grid load and meteorological coupling model, an in-depth analysis of the complex relationship between meteorological conditions and grid load is achieved. This coupling analysis method takes into account the nonlinear impact of meteorological changes on grid load, improves the accuracy and adaptability of load forecasting, and ultimately achieves the effect of better coping with grid load changes under extreme meteorological conditions.

[0066] By designing a graded early warning mechanism and corresponding operational suggestions, differentiated management for different risk levels is achieved. This flexible early warning and response mechanism takes into account the actual needs under different risk levels, improves the pertinence and effectiveness of risk management, and ultimately achieves the effect of timely and appropriate response to potential risks in various situations.

[0067] In summary, through multiple innovative steps, this plan has comprehensively improved the meteorological forecasting capability and risk management level of the power grid system in plateau and mountainous areas, providing strong technical support for the safe and stable operation of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0069] Figure 1 It is a flow chart of the meteorological forecasting method based on the plateau mountain power grid system;

[0070] Figure 2 A diagram of computer equipment for a meteorological forecasting method based on a highland mountain power grid system;

[0071] Figure 3 The diagrams for different geographical regions are based on the meteorological forecasting method for the plateau mountain power grid system;

[0072] Figure 4 An updated optimization diagram for monitoring the real-time operation data of the plateau mountainous power grid system based on the meteorological forecasting method of the plateau mountainous power grid system. DETAILED DESCRIPTION

[0073] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0074] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0075] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0076] Example 1

[0077] Reference Figure 1-2 , which is the first embodiment of the present invention, and provides a weather forecasting method based on a plateau mountainous area power grid system, comprising:

[0078] S100: Acquire the unique topography, climate and ecological characteristics of the plateau and mountainous areas, and construct a comprehensive data fusion model, wherein the comprehensive data fusion model processes multi-source data;

[0079] S101: The multi-source data includes terrain data, ecological data, hydrological data, and meteorological data, and the power grid data includes transmission line data and power load data;

[0080] Topographic data: altitude, slope, aspect, terrain relief;

[0081] Ecological data: vegetation cover type, vegetation index, soil type;

[0082] Hydrological data: river distribution, lake location, precipitation distribution;

[0083] Meteorological data: temperature, humidity, air pressure, wind speed, wind direction, precipitation, sunshine hours;

[0084] Transmission line data: voltage level, load current, line temperature;

[0085] Electricity load data: regional electricity consumption, load distribution, and peak electricity consumption periods.

[0086] S102: The unique topography, climate and ecological characteristics of the plateau mountainous area are obtained, and a comprehensive data fusion model is constructed. The comprehensive data fusion model processes multi-source data, and the following steps can be adopted:

[0087] The said construction of comprehensive data fusion model includes terrain-ecology-meteorology fusion index and hydrological impact comprehensive index and environmental status assessment model;

[0088] The terrain, vegetation and basic meteorological conditions are integrated to construct a terrain-ecology-meteorology fusion index. The sensitivity of the model to extreme values ​​is enhanced through exponential and logarithmic transformations. The variance reflects the impact of temperature and air pressure fluctuations on the overall environmental state. The terrain-ecology-meteorology fusion index is used to assess the environmental quality and potential ecological risks in a specific area. The following formula can be used:

[0089]

[0090] Among them, H k is the altitude of the kth position; E kis the vegetation index (NDVI) at the kth location; Slope k ,Aspect k is the slope and aspect of the k-th position; G is the terrain function, G (Slope k ,Aspect k ) = sin(Slope)·cos(Aspect) to simulate the effect of slope on sunshine and water flow; T is the temperature data set, P is the air pressure data set; Var represents the variance of the data, which is used to characterize environmental variability;

[0091] The impact of the hydrological environment on the overall region is evaluated using hydrological characteristics, including water body type, location and precipitation. A sine function is used to simulate the seasonal variation of precipitation, output the periodic impact of precipitation on the hydrological environment, and construct a comprehensive hydrological impact index. The comprehensive hydrological impact index quantifies the comprehensive impact of water body distribution, type and related meteorological conditions on a specific area, which can be expressed as follows:

[0092]

[0093] Among them, D j is the distance from the jth hydrological point (river or lake) to the nearest town; WaterType j is the water body type, which is converted into influence coefficient through IF function; R j is the water resource abundance of the jth hydrological point; is the average annual precipitation at the point; P max is the maximum precipitation in the record;

[0094] By combining the terrain-ecological-meteorological index and the hydrological impact index, and adding the sunshine hours adjusted by wind speed, an environmental status assessment model is constructed. This environmental status assessment model enhances the description of the interaction of environmental variables through logical and nonlinear functions, and uses rich geographical and meteorological data to accurately simulate the comprehensive impact of environmental and meteorological conditions on the environment in plateau mountainous areas, and outputs a comprehensive assessment of the environmental status, which can be expressed as follows:

[0095]

[0096] Among them, α, β, γ are adjustment parameters; V m is the number of hours of visible light sunshine at the mth monitoring point; WindSpeed m It is the wind speed, which is used to adjust the actual impact of sunshine hours on the environment.

[0097] S200: Acquire power grid data, wherein the multi-source data integrated based on the comprehensive data fusion model is combined with the power grid data to construct a real-time monitoring model for the plateau mountain power grid, and the operation status and potential risks of the power grid are obtained through the monitoring model;

[0098] S201: The power grid data is obtained, and the multi-source data integrated based on the comprehensive data fusion model is combined with the power grid data to build a real-time monitoring model for the plateau mountain power grid. The operation status and potential risks of the power grid can be obtained through the monitoring model by adopting the following steps:

[0099] The real-time monitoring model for the plateau mountain power grid includes an environmental impact weight, a power grid load prediction model, and a power grid health index;

[0100] Integrate environmental data and power grid operation data to achieve in-depth understanding and prediction of the power grid status. Use comprehensive environmental models and seasonal adjustments to evaluate the impact of the environment on the power grid and construct environmental impact weights. The following expression can be used:

[0101] EIW=ω1·CEM+ω2·sin(ω3·SeasonalAdjustment)

[0102] Among them, CEM is the output of the comprehensive environmental model, which reflects the comprehensive status of terrain, ecology, meteorology and hydrology data; SeasonalAdjustment is the parameter adjusted according to seasonal changes, which is a function of the date or month; ω1, ω2, ω3 are adjustment weights used to balance the influence of environmental status and seasonal factors;

[0103] The instantaneous load of the power grid is predicted by combining environmental impact and historical load data, and a power grid load prediction model is constructed. The power grid load prediction model enables power grid operators to adjust resource allocation and emergency response according to environmental conditions and predicted needs. It can be expressed as follows:

[0104] GridLoad=β1·EIW·(β2·HistoricLoad+β3·PredictedDemand)

[0105] Among them, EIW is the output of environmental impact weight; HistoricLoad is the historical load data; PredictedDemand is the demand based on current trends and economic activity forecasts; β1, β2, and β3 are adjustment coefficients used to adjust the impact of various factors on the predicted load;

[0106] By comparing the actual load and the safety margin, a grid health index is constructed. The grid health index is an indicator for evaluating the overall operation status of the grid. The index helps grid operators identify potential overload problems or equipment failure risks, so as to take preventive measures in advance. It can be expressed as follows:

[0107]

[0108] Among them, GridLoad is the output of the grid load forecasting model; SafetyMargin is the safety margin of the grid design, which may be based on the maximum load capacity; γ1 and γ2 are adjustment parameters used to adjust the impact of load and safety margin.

[0109] S300: By taking the multi-source data integrated by the comprehensive data fusion model and the real-time status data obtained by the real-time monitoring model as input, a meteorological-grid coupling prediction model is constructed to output the potential impact of future meteorological changes on the power grid system, meteorological warnings, and grid dispatching recommendations.

[0110] S301: The multi-source data integrated by the comprehensive data fusion model and the real-time status data obtained by the real-time monitoring model are used as input to construct a meteorological-grid coupling prediction model, output the potential impact of future meteorological changes on the power grid system, meteorological warnings, and grid dispatching suggestions, and the specific steps are as follows:

[0111] The weather-grid coupling prediction model constructed includes a weather and environment comprehensive impact index, a grid load and weather coupling model, and a warning prediction and operation suggestion model;

[0112] The terrain and ecological characteristics of the plateau and mountainous areas are integrated with the current meteorological data, and the impact of precipitation on the hydrological index is adjusted through a nonlinear function to construct a comprehensive meteorological and environmental impact index. The comprehensive meteorological and environmental impact index evaluates how the current meteorological conditions and terrain ecological characteristics jointly affect the power grid facilities, especially under extreme climate conditions. The comprehensive meteorological and environmental impact index can be expressed as follows:

[0113]

[0114] Among them, CEM is the output of the characteristic data fusion model of plateau mountainous areas; MeteorologicalData includes temperature, humidity, air pressure, wind speed and wind direction; WaterIndex is the impact index of hydrological data, including river distribution, lake location, and precipitation distribution; Precipitation is real-time precipitation data; λ1, λ2, and λ3 are weight parameters.

[0115] S302: The meteorological coupling model and the warning prediction and operation suggestion model are constructed by the following steps:

[0116] The grid load under specific environmental conditions is predicted by combining the meteorological and environmental comprehensive impact index with the actual operation data of the grid, and a grid load and meteorological coupling model is constructed to evaluate the load response capacity of the grid under extreme meteorological conditions to achieve optimal dispatch and early warning of the grid. The following expression can be used:

[0117]

[0118] Among them, MEII is the output of the comprehensive meteorological and environmental impact index; PeakLoadFactor is the load peak factor based on time and predicted demand; ReliabilityIndex is the grid reliability index, which is calculated based on historical fault and maintenance data; is the adjustment parameter;

[0119] The warning level is calculated by a logistic regression model. If the grid load and meteorological coupling model exceeds the threshold, the warning level increases. A warning prediction and operation suggestion model is constructed. The warning prediction and operation suggestion model can provide real-time dispatch suggestions to operators according to the severity of the meteorological and grid coupling status, including load reduction and startup of the backup system. The following expression is used:

[0120]

[0121] GMC is the output of the grid load and meteorological coupling model; Threshold is the warning threshold set based on historical data and safety standards; ξ1 and ξ2 are adjustment parameters.

[0122] S303: Based on the weather-grid coupling early warning model, the weather-grid coupling early warning model outputs the early warning level, and classifies the operation suggestions and early warning information as follows to ensure that appropriate response measures are taken at different risk levels:

[0123] Low risk level: When the warning index is lower than the first threshold, meteorological warning information is sent to relevant departments and the public that may be affected, and low-intensity power grid load distribution maps and environmental impact forecasts are generated and displayed for risk awareness training, monitoring of power grid load and environmental factors, and maintaining daily operation and maintenance status;

[0124] Medium risk level: When the warning index is between the first threshold and the second threshold, a warning message is sent to the relevant departments, and a medium-intensity grid resilience and environmental impact forecast is generated and displayed for risk communication and emergency drills, and emergency response plans are activated, including but not limited to adjusting grid load, activating backup power supplies, and preparing evacuation and rescue resources;

[0125] High-risk level: When the warning index exceeds the second threshold, an emergency warning is issued to all relevant departments and the public, and a high-intensity grid load anomaly and potential severe environmental impact forecast are generated and displayed for evacuation route planning and rescue strategy formulation. Evacuation procedures and emergency response measures are immediately initiated, including but not limited to cutting off power supply to high-risk areas to prevent equipment overload from causing greater safety accidents.

[0126] Topographic-Ecological-Meteorological Integration Index (TEMCI): Quantifies the combined effects of topography, vegetation, and meteorological conditions in plateau mountainous areas.

[0127] Hydrological Impact Index (WHCI): Assess the potential impact of hydrological characteristics on the power grid system.

[0128] Environmental Status Assessment Model (CEM): Integrates TEMCI and WHCI to provide a comprehensive environmental status assessment.

[0129] Comprehensive data fusion model: By integrating multi-source data, the integrity and representativeness of the data are improved, laying the foundation for subsequent predictions.

[0130] Real-time monitoring model: Combining environmental factors with grid operation data, it realizes dynamic monitoring of grid status and improves the timeliness of risk warning.

[0131] Meteorological-grid coupling prediction model: takes into account the interaction between meteorological conditions and grid operation, improving the accuracy and foresight of predictions.

[0132] The present invention introduces an innovative concept of environmental impact weight (EIW), which more accurately describes the impact of seasonal changes on the power grid through a nonlinear function:

[0133] EIW=ω1·CEM+ω2·sin(ω3·SeasonalAdjustment)

[0134] Among them, SeasonalAdjustment is the seasonal adjustment factor, and ω1, ω2, and ω3 are weight coefficients. This method effectively captures the periodic changes of environmental factors and improves the adaptability of the prediction model.

[0135] In the embodiment, the scheme adopts a dynamic threshold mechanism to optimize the early warning system. The low risk threshold is set to the 75th percentile of EIW, the medium risk threshold is set to the 90th percentile, and the high risk threshold is set to the 97.5th percentile. This dynamic threshold mechanism takes into account the spatiotemporal variability of environmental conditions and can better reflect the actual risk level than fixed thresholds.

[0136] For example, in a certain plateau mountainous area, the 75th percentile of EIW is 0.65, the 90th percentile is 0.80, and the 97.5th percentile is 0.90. When EIW<0.65, it is low risk, 0.65≤EIW<0.80 is medium risk, and EIW≥0.80 is high risk. This grading mechanism can guide grid operation decisions more accurately.

[0137] Through multi-dimensional data fusion, nonlinear model construction and dynamic threshold setting, this solution significantly improves the meteorological forecasting capability and risk management level of the power grid system in plateau and mountainous areas, providing strong technical support for the safe and stable operation of the power grid.

[0138] Furthermore, this embodiment also provides a weather forecasting system based on a plateau mountain area power grid system, comprising:

[0139] An acquisition module, which acquires the unique topography, climate and ecological characteristics of the plateau and mountainous areas and constructs a comprehensive data fusion model, which processes multi-source data;

[0140] A construction module is provided to obtain power grid data. The multi-source data integrated based on the comprehensive data fusion model is combined with the power grid data to construct a real-time monitoring model for the plateau mountain power grid, and the operation status and potential risks of the power grid are obtained through the monitoring model.

[0141] The output module constructs a meteorological-grid coupling prediction model by taking the multi-source data integrated by the comprehensive data fusion model and the real-time status data obtained by the real-time monitoring model as input, and outputs the potential impact of future meteorological changes on the power grid system, meteorological warnings, and power grid dispatching recommendations.

[0142] This embodiment also provides a computer device, which is suitable for the case of a meteorological forecasting method based on a plateau mountainous power grid system, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the meteorological forecasting method based on a plateau mountainous power grid system proposed in the above embodiment.

[0143] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0144] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for implementing a meteorological forecasting method based on a plateau mountainous area power grid system as proposed in the above embodiment is implemented.

[0145] In summary, the comprehensive data fusion model:

[0146] By acquiring the unique topography, climate and ecological characteristics of the plateau mountainous areas, a comprehensive data fusion model was constructed to achieve the integration and processing of multi-source data. This step fully considered the complex environmental characteristics of the plateau mountainous areas and effectively improved the comprehensiveness and representativeness of the data. Ultimately, it achieved the beneficial effect of more accurately reflecting the actual environmental conditions of the plateau mountainous areas, providing a reliable data basis for subsequent predictions.

[0147] Real-time monitoring model of power grid in plateau mountainous area:

[0148] By combining the multi-source data integrated by the comprehensive data fusion model with the power grid data, a real-time monitoring model for the plateau mountain power grid was constructed. This step realizes real-time monitoring of the power grid operation status and potential risks, greatly improving the comprehensiveness and timeliness of power grid monitoring. Ultimately, it achieves the beneficial effect of quickly identifying abnormal power grid conditions and potential risks, providing a more reliable basis for decision-making for power grid operators.

[0149] Weather-grid coupling prediction model:

[0150] By taking the multi-source data integrated by the comprehensive data fusion model and the real-time status data obtained by the real-time monitoring model as input, a meteorological-grid coupling prediction model is constructed. This step realizes the dynamic correlation analysis between meteorological conditions and grid operation status, significantly improving the accuracy and pertinence of the prediction. Ultimately, the beneficial effect of accurately predicting the potential impact of future meteorological changes on the power grid system is achieved, providing a scientific basis for formulating effective early warning strategies and dispatching recommendations.

[0151] Environmental status assessment model:

[0152] By combining the terrain-ecology-meteorology fusion index, the hydrological impact comprehensive index and the sunshine hours adjusted by wind speed, an environmental status assessment model was constructed. This step achieved a comprehensive assessment of the complex environmental factors in the plateau and mountainous areas, greatly improving the accuracy and comprehensiveness of the environmental status assessment. Ultimately, it achieved the beneficial effect of more accurately simulating the impact of the plateau and mountainous environment and meteorological conditions on the power grid, providing more reliable input data for subsequent meteorological forecasts and risk assessments.

[0153] Grid load and meteorological coupling model:

[0154] By combining the meteorological and environmental comprehensive impact index with the actual operation data of the power grid, a grid load and meteorological coupling model was constructed. This step achieves accurate prediction of the grid load under specific environmental conditions, significantly improving the accuracy and adaptability of grid load prediction. Ultimately, it achieves the beneficial effect of evaluating the grid load response capacity under extreme meteorological conditions, providing strong support for the optimized dispatching and early warning of the power grid.

[0155] Warning prediction and action recommendation model:

[0156] The warning level was calculated by the logistic regression model, and a warning prediction and operation suggestion model was constructed. This step realized the function of providing real-time dispatch suggestions based on the severity of the meteorological and power grid coupling status, greatly improving the intelligence level and practicality of the early warning system. Ultimately, it achieved the beneficial effect of providing timely and effective decision support for operators, which helped to prevent and respond to potential power grid risks.

[0157] Grading early warning mechanism:

[0158] By setting multiple risk level thresholds, a three-level early warning mechanism of low, medium and high levels is implemented. This step makes the early warning information more refined and targeted, significantly improving the practicality and operability of the early warning system. Ultimately, the beneficial effect of taking corresponding response measures according to different risk levels is achieved, effectively improving the safety and reliability of the power grid system.

[0159] The meteorological forecasting method and system based on the plateau mountain power grid system has achieved comprehensive monitoring, accurate forecasting and intelligent early warning of the power grid system in the complex environment of the plateau mountain area through multiple innovative models and steps. It not only improves the accuracy and timeliness of the forecast, but also provides more reliable and practical decision-making support for power grid operators, and ultimately achieves the comprehensive beneficial effect of improving the safety, reliability and operation efficiency of the plateau mountain power grid system.

[0160] Example 2

[0161] Reference Figure 1 - Figure 4 , which is the second embodiment of the present invention, provides a meteorological forecasting method based on a plateau mountain power grid system. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0162] To verify the effectiveness of the method of the present invention, a one-year field test was conducted in Yushu Tibetan Autonomous Prefecture, Qinghai Province. The region is located in the eastern part of the Qinghai-Tibet Plateau, with an average altitude of more than 4,000 meters, complex terrain, and changeable climate. It is a typical plateau mountain environment. The test process is as follows:

[0163] First, detailed topographic, ecological and meteorological data of the area were collected. Topographic data included digital elevation models with a resolution of 1 km, slope and aspect data; ecological data included 16-day synthetic NDVI data and soil type data obtained by the MODIS satellite; hydrological data included the distribution of major rivers and lakes and precipitation records over the past 30 years; meteorological data were obtained from 12 local weather stations, including hourly temperature, humidity, air pressure, wind speed, wind direction and sunshine hours data.

[0164] Next, we obtained grid operation data from the local power company, including the voltage level, load current, line temperature of the main transmission lines, as well as the power load distribution in each region and historical peak power consumption records.

[0165] Then, a comprehensive data fusion model was constructed according to the method of the present invention. First, the terrain-ecology-meteorology fusion index was calculated to enhance the sensitivity of the model to extreme values ​​through exponential and logarithmic transformation. Then, the hydrological impact comprehensive index was calculated, and the seasonal variation of precipitation was simulated using a sine function. Finally, the environmental status assessment model was constructed by combining it with the sunshine hours adjusted by wind speed.

[0166] Based on the environmental status assessment model and power grid operation data, a real-time monitoring model for the plateau mountain power grid was constructed. First, the environmental impact weight was calculated, and the output of the environmental status assessment model was combined with the seasonal adjustment factor; then a power grid load forecasting model was constructed, integrating the environmental impact weight, historical load and forecast demand; finally, the power grid health index was calculated by comparing the actual load and safety margin.

[0167] Finally, all the above models were integrated to build a meteorological-grid coupling prediction model. The model first calculated the comprehensive impact index of meteorology and environment, and then built a grid load and meteorological coupling model based on the actual operation data of the grid. Based on the output of the grid load and meteorological coupling model, the warning level was calculated through a logistic regression model, realizing a graded early warning mechanism.

[0168] In order to compare the effect of the method of the present invention with the traditional method, two commonly used prediction methods in the region were selected for comparison: ARIMA model based on time series analysis (method A) and BP model based on neural network (method B). The prediction results of the three methods under different weather conditions are shown in the following table:

[0169] Table 1 shows the prediction results of the three methods under different weather conditions

[0170]

[0171]

[0172] It can be clearly seen from the table data that the method of the present invention has shown obvious advantages under various weather conditions. First, in terms of prediction accuracy, the average absolute error and root mean square error of the method of the present invention are significantly lower than those of the traditional method. Taking blizzard weather as an example, the average absolute error of the method of the present invention is 29.8MW, which is 41.9% lower than method A and 33.6% lower than method B. This shows that the method of the present invention can more accurately predict the power grid load and provide a more reliable basis for power grid dispatching.

[0173] Secondly, in terms of early warning effect, the method of the present invention also showed excellent performance. Under all weather conditions, the accurate early warning rate of the method of the present invention remained above 89%, while the accuracy of traditional methods dropped significantly under extreme weather conditions. Especially in blizzard weather, the accurate early warning rate of the method of the present invention reached 89.4%, which was 16.2 percentage points higher than method A and 10.8 percentage points higher than method B. This shows that the method of the present invention can better cope with the complex and changeable meteorological conditions in plateau and mountainous areas, and provide more timely and accurate early warnings for the safe operation of the power grid.

[0174] In addition, the false alarm rate and false alarm rate of the method of the present invention are also significantly lower than those of the traditional methods. Taking rainy weather as an example, the false alarm rate of the method of the present invention is 3.3% and the false alarm rate is 5.2%, while the false alarm rate and false alarm rate of method A are 8.7% and 11.6% respectively, and the false alarm rate of method B is 7.1% and 9.8%. A lower false alarm rate means that potential risks can be identified more comprehensively, while a lower false alarm rate can reduce unnecessary emergency responses, thereby improving the efficiency and reliability of power grid operations.

[0175] It is worth noting that the performance degradation of the method of the present invention under different weather conditions is significantly smaller than that of the traditional method. From clear weather to blizzard weather, the accurate warning rate of the method of the present invention only dropped by 8.1 percentage points, while method A and method B dropped by 18.1 and 15.2 percentage points respectively. This fully demonstrates the strong adaptability and stability of the method of the present invention in dealing with complex and changeable meteorological conditions in plateau and mountainous areas.

[0176] In summary, actual test data proves that the method of the present invention is significantly superior to traditional methods in terms of prediction accuracy, early warning effect and adaptability. This advantage stems from the comprehensive consideration of the unique topographic, ecological and meteorological characteristics of plateau mountainous areas by the method of the present invention, as well as the in-depth analysis of the complex relationship between the power grid operation status and meteorological conditions. This method provides strong technical support for the safe and stable operation of the power grid in plateau mountainous areas, and is expected to create significant economic and social benefits in practical applications.

[0177] Example 3

[0178] Reference Figure 3 - Figure 4, which is the third embodiment of the present invention, provides a meteorological forecasting method based on a plateau mountain power grid system. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0179] like Figure 1 As shown, the meteorological forecasting method for the plateau mountain power grid system includes the following steps:

[0180] Step 1: Obtain meteorological data from multiple data sources;

[0181] Step 2: Fuse the meteorological data provided by different data sources and extract the features related to the operation of the power grid system in plateau mountainous areas;

[0182] Step 3: Establish a weather forecast model;

[0183] Step 4: Use historical meteorological observation data to train the model, and use a certain proportion of the data to verify and evaluate the accuracy of the model;

[0184] Step 5: Apply the future meteorological results obtained by the prediction model to the energy management and dispatching decision-making of the plateau mountain power grid system;

[0185] Step 6: Optimize and adjust the prediction model based on the actual operating conditions and the accuracy of the prediction results.

[0186] Through the above steps, the weather forecasting method provided by the present invention can effectively improve the reliability and economy of the plateau mountainous area power grid system. By accurately predicting future weather conditions, the plateau mountainous area power grid system can better plan and dispatch energy resources, reduce energy consumption and carbon emissions. At the same time, it can also adapt to plateau mountainous area power grid systems of different sizes and types, and has certain versatility and flexibility.

[0187] Specifically, in step one, multiple data sources include but are not limited to meteorological sensors, satellite images, meteorological forecast models, etc. Meteorological data can be obtained by directly accessing the API of the data provider, using special data acquisition tools, crawling data websites or subscribing to data services. Different data sources may provide different meteorological data. Multiple data sources can fill the problem of missing or incomplete data that may exist in one data source. By integrating multiple data sources, more comprehensive and complete meteorological data can be obtained, and the quality and reliability of the data can be improved. Different data sources may use different meteorological observation facilities and methods, or have different meteorological data collection and processing processes. The use of multiple data sources can verify the accuracy of data with each other, reduce errors and deviations that may exist in a single data source, and improve the accuracy of meteorological data. Meteorological phenomena have certain changes and differences in space. By obtaining meteorological data from multiple data sources, a wider spatial range can be covered.

[0188] Including different geographical areas such as cities, rural areas, oceans, and mountains, such as Figure 3 Shown

[0189] In order to obtain more comprehensive and representative meteorological observations, the temporal continuity of meteorological data is crucial for meteorological forecasting and analysis. Sometimes, a data source may not be able to provide real-time or continuous observation data within a certain period of time, for example, due to equipment maintenance or failure. By utilizing multiple data sources, these time gaps can be filled to ensure the continuity and timeliness of the data. By comparing data from different data sources, outliers, abnormal events or systematic errors can be discovered, and deviations and errors caused by a single data source can be eliminated.

[0190] Specifically, in step 2, these features may include basic meteorological parameters such as temperature, humidity, wind speed, light intensity, and more complex indicators such as sunshine hours, wind energy potential, etc. Feature extraction may be achieved by calculating statistics, frequency domain analysis, time series analysis, etc. Meteorological data from different data sources are fused. Fusion may be performed by weighted averaging, principal component analysis, and other techniques. The weighted averaging may assign appropriate weights to each data source based on the reliability and importance of different data sources. Principal component analysis may reduce data dimensions and extract the main components that represent the overall data characteristics. The fused data is preprocessed, including data cleaning, denoising, and normalization. Data cleaning may remove outliers or missing data to ensure data integrity and accuracy. Figure 4 As shown;

[0191] Denoising can use filtering algorithms or signal processing techniques to remove noise from data; normalization can convert data into a unified standard to facilitate subsequent analysis and modeling, and extract features related to the operation of the plateau mountain power grid system from the fused meteorological data. These features can include basic meteorological parameters such as temperature, humidity, wind speed, and light intensity, as well as more complex indicators such as sunshine hours and wind energy potential. Feature extraction can be achieved through methods such as calculating statistics, frequency domain analysis, and time series analysis.

[0192] Specifically, in step three, a meteorological forecasting model is established using random forest (RF), the fused meteorological data and historical meteorological observation data are input, and the meteorological conditions in the future are output. The scikit-learn (Python) algorithm library is selected, and the parameters of the random forest model are configured. The parameters can be adjusted through cross-validation or grid search to obtain the best model performance.

[0193] Specifically, in step 4, the collected historical meteorological observation data set is divided into a training set and a validation set, wherein the training set accounts for 80% of the total data and the validation set accounts for 20% of the total data. The training set is used for model training and the validation set is used for model evaluation. Common evaluation indicators such as root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), etc. are used to evaluate the prediction accuracy and stability of the model, and the model is optimized and adjusted according to the verification results. The structure, hyperparameters or feature selection methods of the model can be adjusted to improve the performance and generalization ability of the model. In addition, according to the characteristics and needs of the plateau mountain power grid system, the prediction model can be customized and optimized to improve the accuracy and reliability of the prediction results.

[0194] Specifically, in step five, based on the prediction results, the energy supply and storage equipment in the plateau mountainous area power grid system are reasonably dispatched, the operation strategy of the plateau mountainous area power grid system is adjusted to improve energy utilization efficiency and economy, and a reasonable load management strategy is formulated. For example, if it is predicted that there will be clear and hot weather in the future, the utilization of solar power generation equipment can be increased and the dependence on other energy sources can be reduced. When strong winds are predicted in the future, the output power of wind power generation equipment can be adjusted to make full use of wind energy resources. If high temperatures are predicted in the future, the operation strategy of the air-conditioning system can be adjusted in advance to optimize energy consumption.

[0195] Specifically, in step 6, the real-time operation data of the plateau mountain power grid system is monitored, including energy generation and consumption data, and actual meteorological observation data, etc., and these data are fed back to the prediction model for updating and optimizing the model to adapt to the changing environment and needs, such as Figure 4 shown.

[0196] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A meteorological forecasting method based on a plateau mountainous area power grid system, characterized by: include, Acquire the unique topography, climate and ecological characteristics of plateau and mountainous areas and construct a comprehensive data fusion model that processes multi-source data; Acquire power grid data, wherein the multi-source data integrated based on the comprehensive data fusion model is combined with the power grid data to construct a real-time monitoring model for the plateau mountain power grid, and the operation status and potential risks of the power grid are obtained through the monitoring model; By taking the multi-source data integrated by the comprehensive data fusion model and the real-time status data obtained by the real-time monitoring model as input, a meteorological-grid coupling prediction model is constructed to output the potential impact of future meteorological changes on the power grid system, meteorological warnings, and grid dispatching recommendations.

2. The weather forecasting method based on the plateau mountainous area power grid system according to claim 1, characterized in that: The multi-source data includes terrain data, ecological data, hydrological data, and meteorological data, and the power grid data includes transmission line data and power load data; Topographic data: altitude, slope, aspect, terrain relief; Ecological data: vegetation cover type, vegetation index, soil type; Hydrological data: river distribution, lake location, precipitation distribution; Meteorological data: temperature, humidity, air pressure, wind speed, wind direction, precipitation, sunshine hours; Transmission line data: voltage level, load current, line temperature; Electricity load data: regional electricity consumption, load distribution, and peak electricity consumption periods.

3. The weather forecasting method based on the plateau mountainous area power grid system as claimed in claim 2, characterized in that: The unique topography, climate and ecological characteristics of the plateau and mountainous areas are obtained, and a comprehensive data fusion model is constructed. The comprehensive data fusion model processes multi-source data, and the following steps can be adopted: The construction of the comprehensive data fusion model includes a terrain-ecology-meteorology fusion index and a hydrological impact comprehensive index as well as an environmental status assessment model; The terrain, vegetation and basic meteorological conditions are integrated to construct a terrain-ecology-meteorology fusion index. The sensitivity of the model to extreme values ​​is enhanced through exponential and logarithmic transformations. The variance reflects the impact of temperature and air pressure fluctuations on the overall environmental state. The terrain-ecology-meteorology fusion index is used to assess the environmental quality and potential ecological risks in a specific area. The following formula can be used: Among them, H k is the altitude of the kth position; E k is the vegetation index (NDVI) at the kth location; Slope k ,Aspect k is the slope and aspect of the k-th position; G is the terrain function, G (Slope k ,Aspect k ) = sin(Slope)·cos(Aspect) to simulate the effect of slope on sunshine and water flow; T is the temperature data set, P is the air pressure data set; Var represents the variance of the data, which is used to characterize environmental variability; The impact of the hydrological environment on the overall region is evaluated using hydrological characteristics, including water body type, location and precipitation. A sine function is used to simulate the seasonal variation of precipitation, output the periodic impact of precipitation on the hydrological environment, and construct a comprehensive hydrological impact index. The comprehensive hydrological impact index quantifies the comprehensive impact of water body distribution, type and related meteorological conditions on a specific area, which can be expressed as follows: Among them, D j is the distance from the jth hydrological point (river or lake) to the nearest town; WaterType j is the water body type, which is converted into influence coefficient through IF function; R j is the water resource abundance of the jth hydrological point; is the average annual precipitation at the point; P max is the maximum precipitation in the record; By combining the terrain-ecological-meteorological index and the hydrological impact index, and adding the sunshine hours adjusted by wind speed, an environmental status assessment model is constructed. This environmental status assessment model enhances the description of the interaction of environmental variables through logical and nonlinear functions, and uses rich geographical and meteorological data to accurately simulate the comprehensive impact of environmental and meteorological conditions on the environment in plateau mountainous areas, and outputs a comprehensive assessment of the environmental status, which can be expressed as follows: Among them, α, β, γ are adjustment parameters; V m is the number of hours of visible light sunshine at the mth monitoring point; WindSpeed m It is the wind speed, which is used to adjust the actual impact of sunshine hours on the environment.

4. The weather forecasting method based on the plateau mountain area power grid system as claimed in claim 3 is characterized by: The acquisition of power grid data, the combination of the multi-source data integrated based on the comprehensive data fusion model and the power grid data to build a real-time monitoring model for the plateau mountain power grid, and the acquisition of the operation status and potential risks of the power grid through the monitoring model can be carried out in the following steps: The real-time monitoring model for the plateau mountain power grid includes an environmental impact weight, a power grid load prediction model, and a power grid health index; Integrate environmental data and power grid operation data to achieve in-depth understanding and prediction of the power grid status. Use comprehensive environmental models and seasonal adjustments to evaluate the impact of the environment on the power grid and construct environmental impact weights. The following expression can be used: EIW=ω1·CEM+ω2·sin(ω3·SeasonalAdjustment) Among them, CEM is the output of the comprehensive environmental model, which reflects the comprehensive status of terrain, ecology, meteorology and hydrology data; SeasonalAdjustment is the parameter adjusted according to seasonal changes, which is a function of the date or month; ω1, ω2, ω3 are adjustment weights used to balance the influence of environmental status and seasonal factors; The instantaneous load of the power grid is predicted by combining environmental impact and historical load data, and a power grid load prediction model is constructed. The power grid load prediction model enables power grid operators to adjust resource allocation and emergency response according to environmental conditions and predicted needs. It can be expressed as follows: GridLoad=β1·EIW·(β2·HistoricLoad+β3·PredictedDemand) Among them, EIW is the output of environmental impact weight; HistoricLoad is the historical load data; PredictedDemand is the demand based on current trends and economic activity forecasts; β1, β2, and β3 are adjustment coefficients used to adjust the impact of various factors on the predicted load; By comparing the actual load and the safety margin, a grid health index is constructed. The grid health index is an indicator for evaluating the overall operation status of the grid. The index helps grid operators identify potential overload problems or equipment failure risks, so as to take preventive measures in advance. It can be expressed as follows: Among them, GridLoad is the output of the grid load forecasting model; SafetyMargin is the safety margin of the grid design, which may be based on the maximum load capacity; γ1 and γ2 are adjustment parameters used to adjust the impact of load and safety margin.

5. The weather forecasting method based on the plateau mountain area power grid system as claimed in claim 4, characterized in that: By taking the multi-source data integrated by the comprehensive data fusion model and the real-time status data obtained by the real-time monitoring model as input, a meteorological-grid coupling prediction model is constructed to output the potential impact of future meteorological changes on the power grid system, meteorological warnings, and grid dispatching suggestions. The specific steps are as follows: The weather-grid coupling prediction model constructed includes a weather and environment comprehensive impact index, a grid load and weather coupling model, and a warning prediction and operation suggestion model; The terrain and ecological characteristics of the plateau and mountainous areas are integrated with the current meteorological data, and the impact of precipitation on the hydrological index is adjusted through a nonlinear function to construct a comprehensive meteorological and environmental impact index. The comprehensive meteorological and environmental impact index evaluates how the current meteorological conditions and terrain ecological characteristics jointly affect the power grid facilities, especially under extreme climate conditions. The comprehensive meteorological and environmental impact index can be expressed as follows: Among them, CEM is the output of the characteristic data fusion model of plateau mountainous areas; MeteorologicalData includes temperature, humidity, air pressure, wind speed and wind direction; WaterIndex is the impact index of hydrological data, including river distribution, lake location, and precipitation distribution; Precipitation is real-time precipitation data; λ1, λ2, and λ3 are weight parameters.

6. The weather forecasting method based on the plateau mountain area power grid system according to claim 5, characterized in that: The meteorological coupling model and the warning prediction and operation suggestion model are constructed by the following steps: The grid load under specific environmental conditions is predicted by combining the meteorological and environmental comprehensive impact index with the actual operation data of the grid, and a grid load and meteorological coupling model is constructed to evaluate the load response capacity of the grid under extreme meteorological conditions to achieve optimal dispatch and early warning of the grid. The following expression can be used: Among them, MEII is the output of the comprehensive meteorological and environmental impact index; PeakLoadFactor is the load peak factor based on time and predicted demand; ReliabilityIndex is the grid reliability index, which is calculated based on historical fault and maintenance data; is the adjustment parameter; The warning level is calculated by a logistic regression model. If the grid load and meteorological coupling model exceeds the threshold, the warning level increases. A warning prediction and operation suggestion model is constructed. The warning prediction and operation suggestion model can provide real-time dispatch suggestions to operators according to the severity of the meteorological and grid coupling status, including load reduction and startup of the backup system. The following expression is used: GMC is the output of the grid load and meteorological coupling model; Threshold is the warning threshold set based on historical data and safety standards; ξ1 and ξ2 are adjustment parameters.

7. The weather forecasting method based on the plateau mountain area power grid system according to claim 6, characterized in that: Based on the weather-grid coupling early warning model, the warning level output by the weather-grid coupling early warning model classifies the operation suggestions and warning information as follows to ensure that appropriate response measures are taken at different risk levels: Low risk level: When the warning index is lower than the first threshold, meteorological warning information is sent to relevant departments and the public that may be affected, and low-intensity power grid load distribution maps and environmental impact forecasts are generated and displayed for risk awareness training, monitoring of power grid load and environmental factors, and maintaining daily operation and maintenance status; Medium risk level: When the warning index is between the first threshold and the second threshold, a warning message is sent to the relevant departments, and a medium-intensity grid resilience and environmental impact forecast is generated and displayed for risk communication and emergency drills, and emergency response plans are activated, including but not limited to adjusting grid load, activating backup power supplies, and preparing evacuation and rescue resources; High-risk level: When the warning index exceeds the second threshold, an emergency warning is issued to all relevant departments and the public, and a high-intensity grid load anomaly and potential severe environmental impact forecast are generated and displayed for evacuation route planning and rescue strategy formulation. Evacuation procedures and emergency response measures are immediately initiated, including but not limited to cutting off power supply to high-risk areas to prevent equipment overload from causing greater safety accidents.

8. A weather forecasting system based on a plateau mountainous area power grid system, based on the weather forecasting method based on a plateau mountainous area power grid system according to any one of claims 1 to 7, characterized in that: Also includes, An acquisition module, which acquires the unique topography, climate and ecological characteristics of the plateau and mountainous areas and constructs a comprehensive data fusion model, which processes multi-source data; A construction module is provided to obtain power grid data. The multi-source data integrated based on the comprehensive data fusion model is combined with the power grid data to construct a real-time monitoring model for the plateau mountain power grid. The operation status and potential risks of the power grid are obtained through the monitoring model. The output module constructs a meteorological-grid coupling prediction model by taking the multi-source data integrated by the comprehensive data fusion model and the real-time status data obtained by the real-time monitoring model as input, and outputs the potential impact of future meteorological changes on the power grid system, meteorological warnings, and power grid dispatching recommendations.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the weather forecasting method based on the plateau mountainous area power grid system according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the weather forecasting method based on a plateau mountainous area power grid system according to any one of claims 1 to 7 are implemented.

Images