Continuous abnormal weather power grid monitoring method, electronic equipment and storage medium

Abstract

The invention relates to the related technical field of power grids, in particular to a continuous abnormal weather power grid monitoring method, electronic equipment and a storage medium. The method comprises the following steps: acquiring weather data; wherein the weather data comprises ocean thermal anomaly data, underlying surface anomaly data and ocean-land-atmosphere interaction data; based on a preset weather analysis module, analysis is carried out to obtain an analysis result, and the weather analysis module comprises an ocean thermal anomaly analysis sub-module, an underlying surface forced analysis sub-module and an ocean-land-atmosphere interaction analysis sub-module; obtaining power grid operation data; and performing analysis based on a preset power grid influence analysis module to obtain a result. Wherein the power grid influence analysis module comprises a line influence analysis sub-module, an equipment influence analysis sub-module and a load influence analysis sub-module; and according to a preset rule, generating an early warning and coping strategy based on the influence of the continuous abnormal weather on the power transmission line, the equipment and the load.

Description

Technical Field

[0001] The present application relates to the technical field related to power grids, and in particular to a method, electronic device and storage medium for monitoring power grids under continuous abnormal weather conditions. Background Art

[0002] As global climate change intensifies, persistent abnormal weather events, such as persistent heavy rain, high temperature, low temperature, etc., pose a serious threat to the safe and stable operation of the power grid. These extreme weather conditions not only affect the reliability of power supply, but may also cause damage to power grid facilities, leading to large-scale power outages, which have a profound impact on the social economy and people's lives.

[0003] In the existing technical solutions, the power grid monitoring system mainly relies on the regular collection of basic meteorological data such as temperature and air pressure by ground meteorological stations, and the real-time monitoring of local environmental parameters by micro-meteorological monitoring devices installed at key locations of transmission lines. In this way, the monitoring effect of the power grid in continuous abnormal weather is not ideal. Summary of the invention

[0004] In view of this, the embodiments of the present application are committed to providing a method, electronic device and storage medium for monitoring a power grid during continuous abnormal weather, so as to improve the effect of monitoring a power grid during continuous abnormal weather.

[0005] The present application provides a method for monitoring a power grid during abnormal weather conditions, comprising:

[0006] Acquiring weather data; wherein the weather data includes: ocean thermal anomaly data, underlying surface anomaly data and ocean-land-atmosphere interaction data;

[0007] Based on a preset weather analysis module, the weather data is analyzed to obtain analysis results: wherein the weather analysis module includes: an ocean thermal anomaly analysis submodule, an underlying surface forcing analysis submodule and an ocean-land-atmosphere interaction analysis submodule;

[0008] Obtain power grid operation data;

[0009] Based on a preset power grid impact analysis module, the power grid operation data and the analysis results are analyzed to obtain the impact of persistent abnormal weather on transmission lines, equipment, and loads;

[0010] Wherein, the power grid impact analysis module includes: a line impact analysis submodule, a device impact analysis submodule and a load impact analysis submodule;

[0011] According to preset rules, early warning and response strategies are generated based on the impact of the persistent abnormal weather on transmission lines, equipment, and loads.

[0012] In some embodiments, obtaining weather data includes:

[0013] Ocean thermal anomaly data, underlying surface anomaly data and ocean-land-atmosphere interaction data are collected through sea temperature sensors, ground-based meteorological observation stations, satellite remote sensing equipment and various sensors installed at coastal and land meteorological stations and ocean observation platforms.

[0014] In some embodiments, the analyzing the weather data and obtaining the analysis results further comprises:

[0015] The collected data are processed using multi-source heterogeneous data fusion technology.

[0016] In some embodiments, the formula of the multi-source heterogeneous data fusion technology is as follows:

[0017]

[0018] Among them, FusedData represents the comprehensive data obtained after multi-source heterogeneous data fusion processing for subsequent continuous abnormal weather analysis, n represents the number of data sources involved in the fusion, and w i is the weight assigned to the ith data source, Data i Represents the original data collected by the i-th data source.

[0019] In some embodiments, the ocean thermal anomaly analysis submodule is used to perform sensitivity experimental analysis on the collected sea temperature anomaly values, so as to analyze the impact of sea temperature anomaly on circulation anomaly in the southern region, and its algorithm formula is as follows:

[0020]

[0021] Where ΔC circ represents the comprehensive change of circulation anomaly in the preset area, β0 is the intercept term of the regression equation, n represents the number of sea temperature anomaly data in different sea areas involved in the analysis, and β i is the regression coefficient corresponding to the i-th SST anomaly factor, reflecting the anomaly change of SST in the i-th sea area ΔSST i The abnormal change of circulation in the southern region ΔC circ the extent of the impact;

[0022] The underlying surface forced analysis submodule is used to receive the underlying surface abnormal data and analyze the impact of the underlying surface on the abnormal circulation of persistent abnormal weather. The analysis formula is as follows:

[0023]

[0024] Among them, ΔC′ circrepresents the comprehensive change of circulation anomaly in the southern region caused by the underlying surface anomaly, α0 is the intercept term of the regression equation, and α j is the regression coefficient corresponding to the jth underlying surface anomaly factor, ΔL j is the key parameter variation of the jth underlying surface anomaly, λ j is the exponential parameter, f phys (X j ) is a function based on physical principles, X j is the physical parameter related to the jth underlying surface anomaly factor, ∈′ is the error term;

[0025] The ocean-land-atmosphere interaction analysis submodule is used to analyze the characteristics and effects of the coupling process based on the collected ocean-land-atmosphere interaction data, and analyze the causal impact on the persistent abnormal atmosphere. The analysis formula is as follows:

[0026]

[0027] Among them, P(A t |B t-1 ,C t -1) indicates that a specific persistent abnormal weather event A at the current moment is known under the state of ocean-land-atmosphere interaction related factors at the previous moment. t The probability of occurrence is calculated by conditional probability, so as to dynamically analyze the change of the causal influence of various factors on the occurrence of persistent abnormal weather over time, P(B t-1 ,C t-1 |A t ) represents a specific persistent abnormal weather event A at the current time t t The probability that the relevant factors of the ocean-land-atmosphere interaction are in a specific state at the previous moment (t-1) under the condition of occurrence, P(A t ) is a specific persistent abnormal weather event A t The prior probability of its occurrence, P(B t-1 ,C t-1 ) represents the probability that the ocean-land-atmosphere interaction-related factors themselves are in a specific state at the previous moment (t-1), μ t-1 (A t ) is the Markov chain transition probability, which represents the continuous abnormal weather event A from the current time (t) t The transition probability of a persistent abnormal weather event occurring at the next moment (t+1).

[0028] In some embodiments, the obtaining of power grid operation data includes:

[0029] Sensors are installed at various nodes of the power grid to collect and obtain power grid operation data;

[0030] The nodes include: transmission line towers, substations and distribution network branch nodes.

[0031] In some embodiments, the calculation formula of the line impact analysis submodule is as follows:

[0032]

[0033] Among them, R line represents the operation risk value of the transmission line, n represents the number of factors that affect the operation risk of the transmission line, is the weight assigned to the ith risk factor affecting the operation of the transmission line, It represents the influence index of the i-th risk factor affecting the operation of the transmission line;

[0034] The calculation formula of the device impact analysis submodule is as follows:

[0035]

[0036] Among them, f j (x) = a j tanh(b j x j +c j )+d j, P fault (x) represents the probability of failure of substation or distribution network equipment, m represents the number of input features involved in analyzing the probability of equipment failure, is the weight assigned to the jth input feature, f j (x) is the j-th input feature x learned by the neural network model j A nonlinear function is used to capture the complex nonlinear relationship between input features and equipment failure probability. j , b j 、c j ,d j is the parameter obtained by neural network training, x j Represents the value of the jth input feature;

[0037] The calculation formula of the load impact analysis submodule is as follows:

[0038]

[0039] Among them, ΔL k It can be predicted by the time series analysis model. The specific prediction formula is ΔL k =α k ×L k-1 +β k ×ε k,L impact It represents the impact degree index of persistent abnormal weather on power grid load, r represents the number of load data points in different time periods or different regions involved in calculating the load impact degree index, is the weight assigned to the kth load data point or region, ΔL k represents the predicted load change of the kth load data point or area, represents the long-term average load of the kth load data point or area, α k and β k is a parameter in the time series analysis model, obtained by analyzing and fitting historical load data, ε k is the error term in the time series analysis model.

[0040] In some embodiments, generating an early warning and response strategy according to preset rules based on the impact of the persistent abnormal weather on the transmission lines, equipment, and loads includes:

[0041] The early warning submodule determines whether there is a risk in the operation of the power grid based on the preset risk threshold. If there is a risk, an early warning message is issued to relevant personnel. At the same time, the response strategy submodule provides response strategies for relevant personnel by querying the response strategy database for different risk types.

[0042] The present application also provides an electronic device, including:

[0043] A processor, and a memory for storing a program executable by the processor;

[0044] The processor is used to implement the above-mentioned method for monitoring power grid during continuous abnormal weather by running the program in the memory.

[0045] The present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the processor executes the above-mentioned method for monitoring power grids under continuous abnormal weather.

[0046] The present application provides a method for monitoring a power grid under persistent abnormal weather, firstly obtaining weather data; wherein the weather data includes: ocean thermal anomaly data, underlying surface anomaly data and ocean-land-atmosphere interaction data; based on a preset weather analysis module, analyzing the weather data to obtain analysis results: wherein the weather analysis module includes: ocean thermal anomaly analysis submodule, underlying surface forced analysis submodule and ocean-land-atmosphere interaction analysis submodule; obtaining power grid operation data; based on a preset power grid impact analysis module, analyzing the power grid operation data and the analysis results to obtain the impact of persistent abnormal weather on transmission lines, equipment and loads; wherein the power grid impact analysis module includes: line impact analysis submodule, equipment impact analysis submodule and load impact analysis submodule; according to preset rules, based on the impact of the persistent abnormal weather on transmission lines, equipment and loads, generating early warning and response strategies. In this way, by integrating the ocean thermal anomaly data, underlying surface anomaly data and ocean-land-atmosphere interaction data, and using multi-source heterogeneous data fusion technology, the comprehensiveness and accuracy of the data are improved, thereby making the analysis of persistent abnormal weather more accurate. Through the subdivided analysis submodules, the system can conduct specialized analysis on different types of meteorological data, improve the understanding of the specific mechanisms of various meteorological factors affecting the power grid, and enhance the depth of risk assessment. The system can monitor the power grid operation data and weather data in real time, analyze the impact of abnormal weather on the power grid in a timely manner, and generate early warning information to help operation and maintenance personnel take preventive measures in advance to reduce power grid failures and power outages. According to different risk types and impact levels, the system can provide customized response strategies, making the response measures more accurate and effective, and improving the power grid's ability to respond to abnormal weather. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0048] Figure 1 It is a flow chart of a method for monitoring a power grid during continuous abnormal weather provided by an embodiment of the present application.

[0049] Figure 2 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] As global climate change intensifies, persistent abnormal weather events, such as persistent heavy rain, high temperature, low temperature, etc., pose a serious threat to the safe and stable operation of the power grid. These extreme weather conditions not only affect the reliability of power supply, but may also cause damage to power grid facilities, leading to large-scale power outages, which have a profound impact on the social economy and people's lives.

[0052] Existing technologies have many deficiencies in abnormal weather power grid monitoring. The integration and analysis of meteorological data and power grid operation data is not deep enough. Meteorological data is simply considered as an external factor affecting power grid operation, without digging deep into the deep causal relationship between the two. It is difficult to comprehensively evaluate the impact of persistent abnormal weather on all levels of the power grid. In addition, the understanding of complex meteorological mechanisms is limited. Most of them are based on conventional observations and simple analysis methods. It is impossible to fully grasp the interaction of meteorological factors and the indirect impact on the power grid. It is difficult to accurately predict the risks faced by the power grid. The impact assessment of the power grid is not accurate and comprehensive enough. Most of them use a single method. It is difficult to comprehensively consider multiple factors and their dynamic changes and interrelationships. It is easy to miss potential important risk factors and cannot provide accurate decision-making basis. There is a lack of systematic response strategies. Most actions are taken after the problem occurs. There is no complete process. The response is relatively passive, and it is impossible to effectively ensure the safe and stable operation of the power grid.

[0053] In view of this, the present application provides a method for monitoring power grids during persistent abnormal weather. By comprehensively collecting and analyzing external forcing process data such as ocean thermal anomalies, underlying surface anomalies, and ocean-land-atmosphere interactions, combined with power grid operation data, persistent abnormal weather and its impact on power grid operation are comprehensively monitored and analyzed. In addition, by introducing an analysis framework based on causal inference in the ocean-land-atmosphere interaction analysis submodule, the inherent mechanism between the sea-land-atmosphere coupling process and persistent abnormal weather is more deeply understood, so as to more accurately judge whether persistent abnormal weather will be triggered and determine its specific characteristics and scope of impact.

[0054] After introducing the basic principles of the present application, various non-limiting embodiments of the present application will be described in detail with reference to the accompanying drawings.

[0055] Figure 1 FIG. 1 is a flow chart of a method for monitoring a power grid during abnormal weather conditions provided by an embodiment of the present application. Figure 1 As shown, the method includes the following contents.

[0056] Step S110, obtaining weather data; wherein the weather data includes: ocean thermal anomaly data, underlying surface anomaly data and ocean-land-atmosphere interaction data;

[0057] In this step, the system first needs to collect weather data related to power grid operation, including but not limited to:

[0058] Ocean thermal anomaly data: Collected by sea temperature sensors deployed in specific sea areas, these data reflect abnormal changes in ocean temperature and may have an impact on weather patterns.

[0059] Underlying surface anomaly data: collected through ground meteorological observation stations and satellite remote sensing equipment, including surface temperature, humidity and other parameters. These data are crucial for understanding the interaction between the surface and the atmosphere.

[0060] Ocean-land-atmosphere interaction data: Collected by a variety of sensors set up at coastal and land meteorological stations and ocean observation platforms, these data help analyze the complex interactions between the sea, land and atmosphere.

[0061] Step S120, analyzing the weather data based on a preset weather analysis module to obtain an analysis result: wherein the weather analysis module includes: an ocean thermal anomaly analysis submodule, an underlying surface forcing analysis submodule and an ocean-land-atmosphere interaction analysis submodule;

[0062] Specifically, the submodule of ocean thermal anomaly analysis focuses on collecting abnormal sea temperature values ​​and conducting sensitivity experimental analysis. Based on a large amount of historical meteorological and oceanographic data, a sea temperature-circulation correlation model is constructed by using statistical regression analysis technology to accurately quantify the weight and nonlinear relationship of the impact of sea temperature anomalies in different sea areas on circulation anomalies in the southern region. Through intuitive presentation of sensitivity coefficients, it helps to determine the key role of sea temperature anomalies in the triggering and propagation of persistent abnormal weather, predict the trend of weather disasters caused by circulation anomalies, and provide accurate prediction of power grid risk warning from an ocean thermal perspective.

[0063] Sub-module for surface forced analysis: After receiving the multi-parameter data of the underlying surface, it is input into the advanced numerical model system, integrated with the physical process parameterization scheme, and simulated the temporal and spatial changes of the thermal and dynamic characteristics of the underlying surface on the atmospheric circulation. In-depth analysis of the mechanism of the influence of terrain undulation, surface roughness, soil moisture, and vegetation cover changes on the weather system, and the model outputs the circulation anomaly response index, quantitatively evaluating the intensity, path, and precipitation distribution characteristics of persistent abnormal weather caused by the underlying surface anomaly, providing a detailed basis for the positioning of the power grid affected by the weather and the prediction of disaster types.

[0064] Ocean-land-atmosphere interaction analysis submodule: mining the rich data of the sea-land-air coupling exchange process, and constructing a dynamic causal model by integrating causal inference algorithms with complex network theory. Accurately identify the key paths and nodes of heat, water vapor, and momentum exchange, quantify the interactive causal strength, time lag effect, and feedback loop contribution of each factor, draw a multi-dimensional causal relationship topology map, and monitor dynamic evolution in real time. Provide core support for analyzing the generation and maintenance mechanism of persistent abnormal weather and predicting development trends, and help power grid operation and maintenance to deploy defense strategies in advance to deal with chain reactions.

[0065] Step S130, obtaining power grid operation data;

[0066] In this step, the system needs to collect real-time operation data of the power grid, including:

[0067] Voltage, current and temperature of transmission lines: collected by sensors installed on transmission line towers.

[0068] Substation equipment operating status parameters: collected through the monitoring system within the substation.

[0069] Distribution network load conditions: collected through distribution network monitoring equipment.

[0070] These data provide the necessary input information for the grid impact analysis module.

[0071] Step S140, based on a preset power grid impact analysis module, the power grid operation data and the analysis results are analyzed to obtain the impact of persistent abnormal weather on transmission lines, equipment, and loads; wherein the power grid impact analysis module includes: a line impact analysis submodule, an equipment impact analysis submodule, and a load impact analysis submodule;

[0072] Grid operation data and weather analysis results will be input into the Grid Impact Analysis module, which includes:

[0073] Line impact analysis submodule: Analyze the impact of weather on transmission lines, such as icing, wind load, etc.

[0074] Equipment impact analysis submodule: Analyze the impact of weather on substation and distribution network equipment, such as equipment overheating, short circuit, etc.

[0075] Load impact analysis submodule: Analyzes the impact of weather on grid load, such as peak electricity consumption caused by extreme weather.

[0076] These submodules use complex algorithms and models, such as neural networks, time series analysis, etc., to assess the impact of weather on various aspects of the power grid.

[0077] Step S150, generating an early warning and response strategy according to preset rules based on the impact of the persistent abnormal weather on the transmission lines, equipment, and loads.

[0078] Based on the output of the power grid impact analysis module, the system will generate early warning and response strategies according to preset rules. This includes:

[0079] Early warning submodule: Determine whether there is risk in power grid operation based on risk thresholds, and issue early warning information to relevant personnel when necessary.

[0080] Response strategy submodule: query the response strategy database for different risk types and provide response strategies to relevant personnel so that timely measures can be taken to deal with power grid operation risks.

[0081] This step ensures that grid operation and maintenance personnel can take effective preventive and response measures based on the warnings and strategies provided by the system to ensure the safe and stable operation of the grid.

[0082] In practical applications, the specific implementation process of the solution provided by this application is as follows:

[0083] Data collection of external forcing process: By deploying sea temperature sensors in specific sea areas, using ground meteorological observation stations and satellite remote sensing methods, and setting up various sensors at coastal and land meteorological stations and ocean observation platforms, ocean thermal anomaly data, underlying surface anomaly data and ocean-land-atmosphere interaction data are collected respectively. Multi-source heterogeneous data fusion technology is used to pre-process the collected data, extract and select features, and use fusion algorithms for processing. The calculation formula of the fusion algorithm is as follows:

[0084]

[0085] FusedData represents the comprehensive data obtained after multi-source heterogeneous data fusion for subsequent continuous abnormal weather analysis, n represents the number of data sources involved in the fusion, and w i is the weight assigned to the ith data source, Data i Represents the original data collected by the i-th data source.

[0086] Persistent abnormal weather analysis: Receive the collected external forcing process data and analyze these data based on the preset analysis model. This module includes the ocean thermal anomaly analysis submodule, the underlying surface forcing analysis submodule and the ocean-land-atmosphere interaction analysis submodule. The ocean thermal anomaly analysis submodule conducts sensitivity experimental analysis on the collected sea temperature anomaly values. Its algorithm formula is:

[0087]

[0088] Where ΔCcirc represents the comprehensive change of circulation anomaly in the southern region, β0 is the intercept term of the regression equation, n represents the number of sea temperature anomaly data in different sea areas involved in the analysis, and β i is the regression coefficient corresponding to the i-th SST anomaly factor, reflecting the anomaly change of SST in the i-th sea area ΔSST i The abnormal change of circulation in the southern region ΔC circ The influence of β0 and β i and k values, and the ΔSST of each sea area collected in real time i Substitute into the formula to calculate ΔC circ , so as to analyze the impact of sea temperature anomaly on circulation anomaly in the southern region, and then determine whether it will be caused by sea temperature anomaly. The underlying surface forced analysis submodule uses the received non-uniform underlying surface related parameters to analyze the impact of non-uniform underlying surface on persistent abnormal weather circulation anomaly through numerical model. The analysis formula is:

[0089]

[0090] Among them, ΔC′ circ represents the comprehensive change of circulation anomaly in the southern region caused by the underlying surface anomaly, α0 is the intercept term of the regression equation, and α j is the regression coefficient corresponding to the jth underlying surface anomaly factor, ΔL j is the key parameter variation of the jth underlying surface anomaly, λ j is the exponential parameter, f phys (X j ) is a function based on physical principles, X j is the physical parameter related to the jth underlying surface anomaly factor, ∈′ is the error term, and the values ​​of each parameter are determined by analyzing historical data. The ΔL of each underlying surface anomaly collected in real time is j Substitute into the formula and combine with the corresponding f phys (X j ) function calculation, calculate ΔC′ circ′ To analyze the impact of the pad on the abnormal circulation of persistent abnormal weather, the ocean-land-atmosphere interaction analysis submodule: Based on the collected data on heat, momentum and water vapor exchange in the sea-land-air coupling process, the characteristics and effects of the coupling process are analyzed. The analysis formula is:

[0091]

[0092] Among them, P(A t |B t-1 ,C t-1) indicates that a specific persistent abnormal weather event A at the current moment is known under the state of ocean-land-atmosphere interaction related factors at the previous moment. t The probability of occurrence is calculated by conditional probability, so as to dynamically analyze the change of the causal influence of various factors on the occurrence of persistent abnormal weather over time, P(B t-1 ,C t-1 |A t ) represents a specific persistent abnormal weather event A at the current time t t The probability that the relevant factors of the ocean-land-atmosphere interaction are in a specific state at the previous moment (t-1) under the condition of occurrence, P(A t ) is a specific persistent abnormal weather event A t The prior probability of its occurrence, P(B t-1 ,C t-1 ) represents the probability that the ocean-land-atmosphere interaction-related factors themselves are in a specific state at the previous moment (t-1), μ t-1 (A t ) is the Markov chain transition probability, which represents the continuous abnormal weather event A from the current time (t) t The transition probability of a persistent abnormal weather event to the next moment (t+1) is calculated based on historical data to determine P(A t )、P(B t-1 ,C t-1 ) and P(B t-1 ,C t-1 |A t ) value, the event B corresponding to the relevant data collected in real time at the previous moment t-1 and C t-1 Substitute into the formula and calculate P(A t |B t-1 ,C t-1 ), so as to analyze the causal impact of various factors on the persistent abnormal atmosphere, and further determine whether the persistent abnormal atmosphere will be caused by the sea-land-air coupling process, as well as its specific characteristics and impact range.

[0093] Grid operation data acquisition module: corresponding sensors are set at each node of the grid, namely, transmission line towers, substations and distribution network branch nodes, to collect grid operation data, and transmit the collected data to the grid impact analysis module through wired or wireless communication.

[0094] Grid impact analysis module: After receiving the continuous abnormal weather analysis results and grid operation data, the line impact analysis submodule, equipment impact analysis submodule and load impact analysis submodule analyze the impact of continuous abnormal weather on transmission lines, equipment and loads based on the established correlation database and analysis algorithm. The calculation formula of the line impact analysis submodule is:

[0095]

[0096] Among them, R line represents the operation risk value of the transmission line, n represents the number of factors that affect the operation risk of the transmission line, is the weight assigned to the ith risk factor affecting the operation of the transmission line, It represents the influence index of the i-th risk factor affecting the operation of the transmission line. By determining the weight of each factor and impact indicators Substitute the formula to calculate the operation risk value R of the transmission line l ine, in order to comprehensively evaluate the impact of persistent abnormal weather on transmission lines, the calculation formula of the equipment impact analysis submodule is:

[0097]

[0098] Among them, f j (x) = a j tanh(b j x j +c j )+d j ,P fault (x) represents the probability of failure of substation or distribution network equipment, m represents the number of input features involved in analyzing the probability of equipment failure, is the weight assigned to the jth input feature, f j (x) is the j-th input feature x learned by the neural network model j A nonlinear function is used to capture the complex nonlinear relationship between input features and equipment failure probability. j , b j 、c j ,d j is the parameter obtained by neural network training, x j represents the value of the jth input feature. By collecting a large amount of historical data to train the neural network, the values ​​of each parameter are determined, and the input feature data x collected in real time is converted into j Substitute into the formula to calculate the probability of equipment failure P fault(x), in order to accurately determine whether the equipment is in normal operation and predict the probability of failure, load impact analysis submodule: the analysis algorithm formula is:

[0099]

[0100] Where, ΔL k It can be predicted by the time series analysis model. The specific prediction formula is:

[0101] ΔL k =α k ×L k-1 +β k ×ε k

[0102] L impact It represents the impact degree index of persistent abnormal weather on power grid load, and p represents the number of load data points in different time periods or different regions involved in calculating the load impact degree index. is the weight assigned to the kth load data point or region, ΔL k represents the predicted load change of the kth load data point or area, represents the long-term average load of the kth load data point or area, α k and β k is a parameter in the time series analysis model, obtained by analyzing and fitting historical load data, ε k is the error term in the time series analysis model.

[0103] Early warning and response: After receiving the analysis results transmitted by it, the early warning submodule determines whether there is a risk in the operation of the power grid based on the preset risk threshold. If there is a risk, an early warning message is issued to relevant personnel. At the same time, the response strategy submodule provides response strategies for relevant personnel by querying the response strategy database for different risk types, and takes timely measures to deal with the risks of power grid operation.

[0104] The present invention realizes real-time monitoring and analysis of persistent abnormal weather and power grid operation status by comprehensively collecting a variety of data related to the external forcing process, including ocean thermal anomaly data, underlying surface anomaly data, ocean-land-atmosphere interaction data and power grid operation data. It not only makes up for the shortcomings of the existing power grid monitoring system in the analysis of the correlation between the external forcing process and the power grid operation, but also enables the system to predict in advance whether persistent abnormal weather will occur in the southern region and its possible impact on the power grid. In addition, by introducing an analysis framework based on causal inference in the ocean-land-atmosphere interaction analysis submodule, a causal relationship between various factors in the sea-land-atmosphere coupling process is described by constructing a causal graph, and the causal influence of these factors on persistent abnormal weather is analyzed by using a causal inference algorithm, so that the system can more accurately judge whether persistent abnormal weather will be triggered and determine its specific characteristics and scope of influence, further enhancing the ability of the power grid monitoring system in dealing with persistent abnormal weather, and providing a stronger guarantee for the safe and stable operation of the power grid.

[0105] Below, reference Figure 2 To describe an electronic device according to an embodiment of the present application. Figure 2 A block diagram of an electronic device according to an embodiment of the present application is illustrated.

[0106] like Figure 2 As shown, the electronic device 200 includes one or more processors 210 and a memory 220 .

[0107] The processor 210 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 200 to perform desired functions.

[0108] The memory 220 may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 210 may run the program instructions to implement the continuous abnormal weather power grid monitoring method of each embodiment of the present application described above and / or other desired functions. Various contents such as category correspondences may also be stored in the computer-readable storage medium.

[0109] In one example, the electronic device 200 may further include: an input device 230 and an output device 240 , and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0110] In addition, the input device 230 may also include, for example, a keyboard, a mouse, an interface, etc. The output device 240 may output various information to the outside, including analysis results, etc. The output device 240 may include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, etc.

[0111] Of course, to simplify, Figure 2 Only some of the components in the electronic device related to the present application are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, the electronic device may further include any other appropriate components according to specific application conditions.

[0112] Exemplary computer program products and computer-readable storage media

[0113] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the continuous abnormal weather power grid monitoring method according to various embodiments of the present application described in the above-mentioned "Exemplary Method" section of this specification.

[0114] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0115] In addition, an embodiment of the present application may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, enables the processor to execute the steps of the method for continuous abnormal weather power grid monitoring according to various embodiments of the present application described in the above “Exemplary Method” section of this specification.

[0116] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0117] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A method for monitoring power grid during continuous abnormal weather, characterized in that: include: Acquiring weather data; wherein the weather data includes: ocean thermal anomaly data, underlying surface anomaly data and ocean-land-atmosphere interaction data; Based on a preset weather analysis module, the weather data is analyzed to obtain analysis results: wherein the weather analysis module includes: an ocean thermal anomaly analysis submodule, an underlying surface forcing analysis submodule and an ocean-land-atmosphere interaction analysis submodule; Obtaining grid operation data; Based on a preset power grid impact analysis module, the power grid operation data and the analysis results are analyzed to obtain the impact of persistent abnormal weather on transmission lines, equipment, and loads; Wherein, the power grid impact analysis module includes: a line impact analysis submodule, a device impact analysis submodule and a load impact analysis submodule; According to preset rules, early warning and response strategies are generated based on the impact of the persistent abnormal weather on transmission lines, equipment, and loads.

2. The method for monitoring power grid during continuous abnormal weather according to claim 1, characterized in that: The obtaining of weather data comprises: Ocean thermal anomaly data, underlying surface anomaly data and ocean-land-atmosphere interaction data are collected through sea temperature sensors, ground-based meteorological observation stations, satellite remote sensing equipment and various sensors installed at coastal and land meteorological stations and ocean observation platforms.

3. The method for monitoring power grid during continuous abnormal weather according to claim 1, characterized in that: The analyzing the weather data and obtaining the analysis result further comprises: The collected data are processed using multi-source heterogeneous data fusion technology.

4. The method for monitoring power grid during continuous abnormal weather according to claim 3, characterized in that: The formula of multi-source heterogeneous data fusion technology is as follows: Among them, FusedData represents the comprehensive data obtained after multi-source heterogeneous data fusion processing for subsequent continuous abnormal weather analysis, n represents the number of data sources involved in the fusion, and w i is the weight assigned to the ith data source, Data i Represents the original data collected by the i-th data source.

5. The method for monitoring power grid during continuous abnormal weather according to claim 1, characterized in that: The ocean thermal anomaly analysis submodule is used to perform sensitivity experimental analysis on the collected sea temperature anomaly values, so as to analyze the impact of sea temperature anomaly on circulation anomaly in the southern region. The algorithm formula is as follows: Where ΔC circ represents the comprehensive change of circulation anomaly in the preset area, β0 is the intercept term of the regression equation, n represents the number of sea temperature anomaly data in different sea areas involved in the analysis, and β i is the regression coefficient corresponding to the i-th SST anomaly factor, reflecting the anomaly change of SST in the i-th sea area ΔSST i The abnormal change of circulation in the southern region ΔC circ the extent of the impact; The underlying surface forced analysis submodule is used to receive the underlying surface abnormal data and analyze the impact of the underlying surface on the abnormal circulation of persistent abnormal weather. The analysis formula is as follows: Among them, ΔC′ circ represents the comprehensive change of circulation anomaly in the southern region caused by the underlying surface anomaly, α0 is the intercept term of the regression equation, and α j is the regression coefficient corresponding to the jth underlying surface anomaly factor, ΔL j is the key parameter variation of the jth underlying surface anomaly, λ j is the exponential parameter, f phys (X j ) is a function based on physical principles, X j is the physical parameter related to the jth underlying surface anomaly factor, ∈′ is the error term; The ocean-land-atmosphere interaction analysis submodule is used to analyze the characteristics and effects of the coupling process based on the collected ocean-land-atmosphere interaction data, and analyze the causal impact on the persistent abnormal atmosphere. The analysis formula is as follows: Among them, P(A t |B t-1 ,C t-1 ) indicates that a specific persistent abnormal weather event A at the current moment is known under the state of ocean-land-atmosphere interaction related factors at the previous moment. t The probability of occurrence is calculated by conditional probability, so as to dynamically analyze the change of the causal influence of various factors on the occurrence of persistent abnormal weather over time, P ( B t-1 ,C t-1 |A t) Represents a specific persistent abnormal weather event A at the current time t t The probability that the relevant factors of the ocean-land-atmosphere interaction are in a specific state at the previous moment (t-1) under the condition of occurrence, P(A t ) is a specific persistent abnormal weather event A t The prior probability of its occurrence, P(B t-1 ,C t-1 ) represents the probability that the ocean-land-atmosphere interaction-related factors themselves are in a specific state at the previous moment (t-1), μ t-1 (A t ) is the Markov chain transition probability, which represents the continuous abnormal weather event A from the current time (t) t The transition probability of a persistent abnormal weather event occurring at the next moment (t+1).

6. The method for monitoring power grid during continuous abnormal weather according to claim 1, characterized in that: The obtaining of power grid operation data includes: Sensors are installed at various nodes of the power grid to collect and obtain power grid operation data; The nodes include: transmission line towers, substations and distribution network branch nodes.

7. The method for monitoring power grid during continuous abnormal weather according to claim 1, characterized in that: The calculation formula of the line impact analysis submodule is as follows: Among them, R line represents the operation risk value of the transmission line, n represents the number of factors that affect the operation risk of the transmission line, is the weight assigned to the ith risk factor affecting the operation of the transmission line, It represents the influence index of the i-th risk factor affecting the operation of the transmission line; The calculation formula of the device impact analysis submodule is as follows: Among them, f j (x) = a j tanh(b j x j +c j )+d j, P fault (x) represents the probability of failure of substation or distribution network equipment, m represents the number of input features involved in analyzing the probability of equipment failure, is the weight assigned to the jth input feature, f j ( x ) is the j-th input feature x obtained through learning of the neural network model j A nonlinear function is used to capture the complex nonlinear relationship between input features and equipment failure probability. j 、b j 、c j ,d j is the parameter obtained by neural network training, x j Represents the value of the jth input feature; The calculation formula of the load impact analysis submodule is as follows: Where, ΔL k It can be predicted by the time series analysis model. The specific prediction formula is ΔL k =α k ×L k-1 +β k ×ε k ,L impact It represents the impact degree index of persistent abnormal weather on power grid load, r represents the number of load data points in different time periods or different regions involved in calculating the load impact degree index, is the weight assigned to the kth load data point or region, ΔL k represents the predicted load change of the kth load data point or area, represents the long-term average load of the kth load data point or area, α k and β k is a parameter in the time series analysis model, obtained by analyzing and fitting historical load data, ε k is the error term in the time series analysis model.

8. The method for monitoring power grid during continuous abnormal weather according to claim 1, characterized in that: The generating of early warning and response strategies according to preset rules and based on the impact of the persistent abnormal weather on the transmission lines, equipment and loads includes: The early warning submodule determines whether there is a risk in the operation of the power grid based on the preset risk threshold. If there is a risk, an early warning message is issued to relevant personnel. At the same time, the response strategy submodule provides response strategies for relevant personnel by querying the response strategy database for different risk types.

9. An electronic device, characterized in that: include: A processor, and a memory for storing a program executable by the processor; The processor is used to implement the method for monitoring power grid during continuous abnormal weather as described in any one of claims 1 to 7 by running the program in the memory.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes the method for monitoring a power grid in continuous abnormal weather according to any one of claims 1 to 7.

Images