Power grid icing monitoring stationing optimization method and system

Abstract

The invention provides a power grid icing monitoring stationing optimization method and system, and relates to the field of data processing, and the method comprises the steps: determining a plurality of first risk sub-regions of a to-be-monitored region based on the landform information of the to-be-monitored region; determining a plurality of second risk sub-regions of the to-be-monitored region according to historical meteorological data of the to-be-monitored region; determining a plurality of third insurance sub-regions of the to-be-monitored region according to the historical icing data of the to-be-monitored region; determining a plurality of target areas of the to-be-monitored area according to the plurality of first target sub-areas, the plurality of second target sub-areas and the plurality of third target sub-areas of the to-be-monitored area; determining a plurality of risk power transmission lines according to the plurality of target areas of the to-be-monitored area; determining an icing risk value of each risk power transmission line; according to the icing risk value of each risk power transmission line, the optimal power grid icing monitoring point distribution scheme is determined, and the method has the advantage of optimizing the icing monitoring quality of the power transmission line.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a method and system for optimizing the distribution of power grid icing monitoring points. Background Art

[0002] Icing on transmission lines can greatly reduce their mechanical and electrical performance, leading to accidents such as shaking, collapse, and line breakage, which have a serious impact on people's lives and production and cause huge economic losses.

[0003] At present, the design and site selection of existing ice monitoring devices are mostly based on manual experience. Manual experience selection is subjective and it is difficult to fully consider the micro-topography and micro-meteorological characteristics of the power grid lines in the entire region. As a result, some line areas have dense monitoring points, while there is a lack of effective ice monitoring in the micro-topography areas prone to ice on the transmission lines, resulting in redundant monitoring device deployment and a lack of monitoring devices in the micro-topography and micro-meteorological sections prone to ice.

[0004] Therefore, it is necessary to provide a method and system for optimizing the deployment of power grid icing monitoring points, so as to optimize the quality of icing monitoring of transmission lines. Summary of the invention

[0005] The present invention provides a method for optimizing the deployment of ice monitoring points in a power grid, comprising: acquiring topographic information of a to-be-monitored area; determining a plurality of first risk sub-areas of the to-be-monitored area based on the topographic information of the to-be-monitored area; determining a plurality of second risk sub-areas of the to-be-monitored area according to historical meteorological data of the to-be-monitored area; determining a plurality of third risk sub-areas of the to-be-monitored area according to historical ice data of the to-be-monitored area; determining a plurality of target areas of the to-be-monitored area according to a plurality of first target sub-areas, a plurality of second target sub-areas and a plurality of third risk sub-areas of the to-be-monitored area; determining a plurality of risky power transmission lines according to the plurality of target areas of the to-be-monitored area; determining an icing risk value of each of the risky transmission lines for each of the risky transmission lines; and determining an optimal plan for deploying ice monitoring points in a power grid according to the icing risk value of each of the risky transmission lines.

[0006] Furthermore, topographic information of the area to be monitored is obtained, including: obtaining digital elevation model data of the area to be monitored; for each grid point, judging whether the grid point is a pass grid point or a wind outlet grid point according to the slope of the grid point, the elevation value of the grid point, the elevation values ​​of the grid point's adjacent grid points and wind speed simulation data; using connectivity analysis to determine ridge grid points, col grid points and saddle grid points; determining windward slope grid points and leeward slope grid points according to wind direction data and the slope direction of each grid point; and determining water body grid points according to the elevation value of each grid point.

[0007] Furthermore, based on the topographic and geomorphic information of the area to be monitored, multiple first risk sub-areas are determined, including: based on the pass grid points, wind outlet grid points, ridge grid points, col grid points, saddle grid points, windward slope grid points, leeward slope grid points and water body grid points of the area to be monitored, the area to be monitored is divided into multiple unit areas; for each of the unit areas, based on the topographic and geomorphic information of the area to be monitored, the slope and terrain undulation of the unit area are determined; according to the slope and terrain undulation of each of the unit areas, the multiple first risk sub-areas are determined.

[0008] Furthermore, based on the historical meteorological data of the area to be monitored, multiple second risk sub-areas of the area to be monitored are determined, including: determining the associated meteorological elements of the area to be monitored; for each of the unit areas, based on the historical meteorological data of the area to be monitored, calculating the meteorological element change gradient corresponding to each of the associated meteorological elements in the unit area; and determining the multiple second risk sub-areas of the area to be monitored based on the meteorological element change gradient corresponding to each of the associated meteorological elements in each of the unit areas.

[0009] Furthermore, based on the historical icing data of the area to be monitored, multiple third-risk sub-areas of the area to be monitored are determined, including: establishing an icing sensitivity prediction model; for each of the unit areas, judging whether the unit area is an icing risk unit area based on the historical icing data of the area to be monitored; for each of the icing risk unit areas, determining the icing sensitivity of the unit area based on the historical icing data, topographic information and historical meteorological data of the area to be monitored through the icing sensitivity prediction model; and determining multiple third-risk sub-areas of the area to be monitored based on the icing sensitivity of each of the unit areas.

[0010] Furthermore, based on the multiple first target sub-areas, multiple second target sub-areas and multiple third dangerous sub-areas of the area to be monitored, the multiple target areas of the area to be monitored are determined, including: based on the intersection of the multiple first target sub-areas, multiple second target sub-areas and multiple third dangerous sub-areas of the area to be monitored, the multiple target areas of the area to be monitored are determined.

[0011] Furthermore, determining the icing risk value of the risky transmission line includes: establishing a risk prediction model; obtaining local topographic information, local historical meteorological data and local historical icing data of the risky transmission line; and determining the icing risk value of the risky transmission line according to the local topographic information, local historical meteorological data and local historical icing data of the risky transmission line through the risk prediction model.

[0012] Furthermore, based on the icing risk value of each of the risky transmission lines, an optimal grid icing monitoring point layout plan is determined, including: determining multiple target transmission lines based on the icing risk value of each of the risky transmission lines; generating an initial grid icing monitoring point layout plan based on the multiple target transmission lines; and optimizing the initial grid icing monitoring point layout plan to generate the optimal grid icing monitoring point layout plan.

[0013] Furthermore, the initial grid icing monitoring point layout plan is optimized to generate the optimal grid icing monitoring point layout plan, including: calculating icing association parameters of any two target transmission lines; clustering the multiple target transmission lines according to the icing association parameters of any two target transmission lines to determine multiple target transmission line clusters; for each of the target transmission line clusters, determining the layout density corresponding to the target transmission line cluster according to the icing risk value of each target transmission line included in the target transmission line cluster, and determining the representative transmission line corresponding to the target transmission line cluster according to the layout density; generating the optimal grid icing monitoring point layout plan according to the representative transmission line corresponding to each of the target transmission line clusters.

[0014] The present invention provides a grid icing monitoring point optimization system, which applies the above-mentioned grid icing monitoring point optimization method and includes: an information acquisition module, which is used to acquire topographic and geomorphic information of a to-be-monitored area; an area determination module, which is used to determine a plurality of first risk sub-areas of the to-be-monitored area based on the topographic and geomorphic information of the to-be-monitored area, and is also used to determine a plurality of second risk sub-areas of the to-be-monitored area according to historical meteorological data of the to-be-monitored area, and is also used to determine a plurality of third risk sub-areas of the to-be-monitored area according to historical icing data of the to-be-monitored area, and is also used to determine a plurality of target areas of the to-be-monitored area according to a plurality of first target sub-areas, a plurality of second target sub-areas and a plurality of third risk sub-areas of the to-be-monitored area; a line determination module, which is used to determine a plurality of risky transmission lines according to a plurality of target areas of the to-be-monitored area; a risk determination module, which is used to determine an icing risk value of each of the risky transmission lines; and a scheme generation module, which is used to determine an optimal grid icing monitoring point layout scheme according to the icing risk value of each of the risky transmission lines.

[0015] Compared with the prior art, the present invention provides a method and system for optimizing the layout of power grid ice monitoring points, which at least has the following features:

[0016] Beneficial effects:

[0017] 1. Comprehensively consider the impact of terrain on icing disasters, the distribution characteristics of icing in the local power grid, and the operation distribution of existing power grid lines, refer to the relevant observation business standards and specifications of the meteorological industry, and formulate an implementation plan for the micro-topography and micro-meteorological points of icing. Focus on monitoring key areas, combine meteorological data such as automatic observation stations of meteorological systems, and power grid line operation and maintenance experience to scientifically and reasonably set up monitoring stations. Form a power grid meteorological disaster monitoring system, making it a three-dimensional comprehensive meteorological monitoring system with appropriate coverage density and reasonable layout, to achieve effective monitoring of typical meteorological disasters, improve the level of forecasting and early warning of icing disasters, and enhance the comprehensive defense capabilities of power grids against meteorological disasters;

[0018] 2. By dividing the area to be monitored into multiple unit areas and determining the risk sub-areas based on topography, historical meteorological data and historical icing data, it is possible to more accurately locate those areas where power grid icing is more likely to occur. In this way, monitoring resources can be more targeted and deployed in these high-risk areas, thereby improving monitoring efficiency. Since monitoring resources are more accurately allocated to high-risk areas, monitoring investment in unnecessary areas can be reduced, thereby reducing the overall monitoring cost. By establishing an icing sensitivity prediction model and combining historical icing data, topography information and historical meteorological data, the icing sensitivity of each unit area can be more accurately assessed. This helps to warn and prevent the risk of power grid icing in advance, and reduce power grid failures and power outages caused by icing. By optimizing the monitoring points, power grid icing problems can be discovered and handled more promptly, thereby effectively avoiding or reducing power grid damage and safety accidents caused by icing, and improving the overall safety of the power grid. The comprehensive analysis of topography, meteorological data and icing data embodies the concept of intelligent management. Through a data-driven approach, power grid icing monitoring can be managed more scientifically and efficiently, providing stronger support for the safe operation of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0020] Figure 1 It is a flow chart of a method for optimizing the deployment of power grid icing monitoring points according to some embodiments of this specification;

[0021] Figure 2 It is a module schematic diagram of a power grid icing monitoring and point optimization system shown in some embodiments of this specification. DETAILED DESCRIPTION

[0022] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0023] Figure 1 is a flow chart of a method for optimizing the deployment of power grid icing monitoring points according to some embodiments of this specification, such as Figure 1 As shown, a method for optimizing the layout of power grid icing monitoring points may include the following steps.

[0024] Step 110, obtaining topographic information of the area to be monitored.

[0025] Specifically, the topographic information of the area to be monitored can be obtained through the Digital Elevation Model (DEM) data. The Digital Elevation Model (DEM) is a digital representation of the terrain of a geographical area, specifically a data set of plane coordinates (X, Y) and elevations (Z) of regular grid points on a certain projection plane (e.g., Gaussian projection plane). DEM data is usually composed of a series of elevation values ​​of regular grid points, which form a regular grid on the map.

[0026] Step 120: determining a plurality of first risk sub-areas of the area to be monitored based on the topographic information of the area to be monitored.

[0027] Specifically include:

[0028] Divide the area to be monitored into multiple unit areas;

[0029] For each unit area, the slope and terrain relief of the unit area are determined based on the topographic information of the area to be monitored;

[0030] A plurality of first risk sub-areas are determined according to the slope and terrain undulation of each unit area.

[0031] Specifically, the area to be monitored can be divided into a plurality of unit areas according to the elevation value of each grid point in the area to be monitored by a region division model, wherein the region division model can be a convolutional neural network model.

[0032] Since extreme weather and climate events are more likely to occur in areas with dramatic terrain fluctuations, the selection of key areas should focus on topographic and geomorphic factors, and use the most important geographical factors such as slope and terrain undulation.

[0033] The elevation difference between the elevation value of the highest point and the elevation value of the lowest point of multiple consecutive grid points in the unit area and the horizontal distance between the highest point and the lowest point can be determined to calculate the slope.

[0034] The slope of the unit area is calculated according to the following formula:

[0035]

[0036] Among them, slope is the slope, ΔE is the elevation difference, and ΔD is the horizontal distance.

[0037] The topographic relief of a unit area can be calculated according to the following formula:

[0038] relief=A max -A min

[0039] Among them, relief is the terrain relief, A max is the altitude of the highest point in the unit area, A min is the lowest point in the unit area.

[0040] The unit area with a slope greater than a slope threshold (for example, 40°) and a terrain relief greater than a terrain relief threshold (for example, 200 meters) is taken as the first risk sub-area.

[0041] Step 130: determining a plurality of second risk sub-areas of the area to be monitored based on historical meteorological data of the area to be monitored.

[0042] Specifically include:

[0043] Determine the relevant meteorological elements of the area to be monitored;

[0044] For each unit area, the meteorological element change gradient corresponding to each associated meteorological element in the unit area is calculated based on the historical meteorological data of the area to be monitored;

[0045] The meteorological element change gradient corresponding to each associated meteorological element in each unit area determines multiple second risk sub-areas of the area to be monitored.

[0046] Specifically, multiple meteorological elements play a major role in the occurrence of ice damage events. Temperature is the core factor affecting ice damage, especially when the temperature fluctuates around 0℃, it is easy to cause sleet or freezing rain, which affects the power system; high humidity is conducive to the freezing process, especially under low temperature conditions, increased humidity can easily cause water droplets to freeze and form ice accumulation; when the atmosphere is in a stable state, cold air is easy to stay on the ground or in the lower layers, and the temperature near the ground will be lower than the temperature in the upper layers, which is conducive to keeping the ground temperature around 0℃, increasing the possibility of freezing rain or sleet, and ultimately leading to the formation and aggravation of ice damage. Therefore, we should pay attention to the coordinated changes of meteorological elements and screen out multiple second risk sub-areas.

[0047] The relevant meteorological elements of the area to be monitored can be determined according to the following process:

[0048] S11, obtaining relevant meteorological elements of multiple sample monitoring areas;

[0049] S12, calculating the topographic similarity between the digital elevation model data of the area to be monitored and the digital elevation model data of each sample monitoring area, and taking the sample monitoring area whose topographic similarity is greater than the topographic similarity threshold as a similar sample monitoring area;

[0050] S13. Use the associated meteorological elements of the similar sample monitoring area as the associated meteorological elements of the area to be monitored.

[0051] According to the fifth generation of atmospheric reanalysis data set (ECMWF Reanalysisv5, ERA5) for global climate provided by the European Centre for Medium-Range Weather Forecasts (ECMWF), historical meteorological data of the monitored area can be obtained, and then historical meteorological data of each unit area can be obtained. The fifth generation of atmospheric reanalysis data set provides high spatial resolution and temporal resolution, which can describe the changes in atmospheric state more finely. It covers the global range and includes a variety of meteorological elements, such as temperature, air pressure, humidity, wind speed, wind direction, precipitation, etc., and has been processed by advanced numerical models and data assimilation technology, so the accuracy and reliability of the data are relatively high. At the same time, the use of high-resolution reanalysis data can make up for the deficiencies caused by incomplete data or low resolution of ground observation stations.

[0052] For each associated meteorological element, the maximum and minimum values ​​of the associated meteorological element in the unit area can be calculated based on the historical meteorological data of the unit area, and the meteorological element change gradient of the associated meteorological element can be calculated based on the difference between the maximum and minimum values ​​of the associated meteorological element and the time difference.

[0053] The risk value of the unit area can be calculated based on the change gradient of the meteorological elements corresponding to each associated meteorological element in each unit area:

[0054]

[0055] Among them, R j is the risk value of the jth unit area, M is the total number of associated meteorological elements in the area to be monitored, and a 2m is the weight corresponding to the mth associated meteorological element in the monitored area, a 2m greater than 0, η (i，m) is the meteorological element change gradient corresponding to the mth associated meteorological element in the jth unit area, η (0，m) It is the preset meteorological element change gradient corresponding to the mth associated meteorological element.

[0056] The meteorological elements in the unit area with a risk value greater than the risk value threshold change complexly, which is easy to form meteorological disaster events and cause damage to the towers on the transmission line. The unit area with a risk value greater than the risk value threshold can be used as the second risk sub-area.

[0057] Step 140: determining a plurality of third-risk sub-areas of the area to be monitored based on historical ice coverage data of the area to be monitored.

[0058] Specifically include:

[0059] Establishing an ice-cover sensitivity prediction model, wherein the ice-cover sensitivity prediction model may be a convolutional neural network model;

[0060] For each unit area, determine whether the unit area is an icing risk unit area based on the historical icing data of the area to be monitored;

[0061] For each icing risk unit area, the icing sensitivity of the unit area is determined according to the historical icing data, topographic information and historical meteorological data of the monitored area through an icing sensitivity prediction model, wherein the icing sensitivity prediction model may be a convolutional neural network model;

[0062] According to the ice coverage sensitivity of each unit area, a plurality of third-risk sub-areas of the area to be monitored are determined.

[0063] Specifically, a neural network is a computational model that mimics the structure and function of biological neural networks and is suitable for different tasks and data types. It consists of a large number of neurons (nodes) connected to each other, each neuron receives input signals from other neurons, processes them through activation functions, and then passes the output signal to the next layer of neurons. Neural networks learn and adapt to data by adjusting the connection weights between neurons. During the training process, a large number of training samples are used to iteratively optimize the network to minimize the error between the predicted results and the actual labels.

[0064] The unit area whose ice coverage sensitivity is greater than the ice coverage sensitivity threshold may be used as the third risk sub-area.

[0065] Step 150: determining a plurality of target areas of the area to be monitored according to a plurality of first target sub-areas, a plurality of second target sub-areas and a plurality of third target sub-areas of the area to be monitored.

[0066] Specifically, a plurality of target areas of the area to be monitored are determined according to the intersection of a plurality of first target sub-areas, a plurality of second target sub-areas and a plurality of third target sub-areas of the area to be monitored.

[0067] Step 160, determining a plurality of risky transmission lines according to a plurality of target areas in the area to be monitored.

[0068] Specifically include:

[0069] For each grid point included in the multiple target areas of the area to be monitored, judging whether the grid point is a pass grid point or a wind outlet grid point according to the slope of the grid point, the elevation value of the grid point, the elevation value of the adjacent grid points of the grid point and the wind speed simulation data;

[0070] Using connectivity analysis, determining the ridge grid points, col grid points and saddle grid points included in the plurality of target areas of the area to be monitored;

[0071] Determine the windward slope grid points and leeward slope grid points included in the multiple target areas of the area to be monitored according to the wind direction data and the slope direction of each grid point;

[0072] Determine the water body grid points included in the multiple target areas of the area to be monitored according to the elevation value of each grid point;

[0073] Based on multiple target areas in the monitored area, including pass grid points, wind outlet grid points, ridge grid points, col grid points, saddle grid points, windward slope grid points, leeward slope grid points and water body grid points, multiple risky transmission lines are identified.

[0074] A pass is a lower area between two mountain ranges or peaks, usually a path to a valley or plain on the other side. A pass is often a passage for wind because air will choose to flow through places with less resistance. In meteorology, a pass can affect local wind speed and direction. When wind passes through a pass, the narrow terrain will cause a local increase in wind speed. The wind speed affected by a pass can be described by the following formula:

[0075]

[0076] Among them, U p is the wind speed at the pass; U0 is the background wind speed not affected by the pass; H0 is the average height of the peaks on both sides of the pass; H P It is the height of the pass.

[0077] A wind outlet is an area where strong winds are generated when the wind passes through the terrain, usually due to the local terrain effect that causes the wind speed to increase. For example, valleys, straits or canyons are often called wind outlets because these terrains can guide and accelerate the flow of wind. At the wind outlet, the wind speed will increase significantly due to the narrowing of the channel, similar to the pipe contraction effect in the Bernoulli effect.

[0078] For the wind speed increase at the vent, the following formula can be used to describe the wind speed change:

[0079]

[0080] Among them, U f is the wind speed at the outlet; U0 is the background wind speed; A0 is the cross-sectional area outside the outlet (or the width of the wind flow); A f It is the cross-sectional area in the tuyere (or the width of the wind flow).

[0081] Specifically, whether a grid point is a pass grid point or a vent grid point can be determined according to the following process:

[0082] S11. For each grid point, the possibility of the grid point being a pass grid point or a vent grid point is calculated according to the slope of the grid point, the elevation value of the grid point, and the elevation values ​​of the grid points adjacent to the grid point;

[0083] S12. For each grid point whose probability is greater than the probability threshold, numerical simulation is performed in combination with wind speed data to verify whether the grid point is a pass grid point or a wind outlet grid point.

[0084] The possibility of a grid point being a pass grid point or a vent grid point can be calculated according to the following formula:

[0085]

[0086] Among them, P (i，1)is the possibility that the i-th grid point is a pass grid point or a vent grid point, a 11 and a 12 is the preset weight, a 11 and a 12 Greater than 0, a 11 +a 12 =1, G i is the slope of the ith grid point, G0 is the preset slope, E (i，n) is the elevation value of the nth adjacent grid point of the ith grid point, E i is the elevation value of the ith grid point, N is the total number of adjacent grid points of the ith grid point, and ΔE0 is the mean of the preset elevation value difference. It can be understood that the area with a large slope or the relatively low point in the terrain is more likely to be a pass or a wind outlet.

[0087] Select or develop a numerical simulation model suitable for the study area and purpose. These models can be based on computational fluid dynamics (CFD), numerical weather prediction models in atmospheric science (such as WRF (Weather Research and Forecasting Model), MM5 (Mesoscale Model 5), etc.), or other models specifically used for wind field simulation.

[0088] Input terrain data into the numerical simulation model to create a three-dimensional terrain representation of the study area. Configure the model parameters such as initial conditions, boundary conditions, time step, etc. as required. Run the numerical simulation model to simulate the flow of wind fields in the study area. Extract wind speed information from the simulation results, especially focusing on the changes in wind speed in the low-point areas identified by terrain analysis. Analyze whether the wind speed in the low-point area increases significantly and whether the pattern of wind speed increase is consistent with expectations (for example, whether a wind channel or wind speed acceleration zone is formed). If the simulation results show that the wind speed in the low-point area increases significantly and is consistent with the results of the terrain analysis, these low-point areas can be considered to be wind outlets.

[0089] A ridge is a high part of a mountain range, usually a long, narrow plateau running along the highest part of a mountain range. A col is a lower part of a mountain range, usually between two ridges or peaks. A saddle is a low area of ​​land between two relatively high peaks. A saddle is often considered the transition point between two peaks in a mountain range.

[0090] Identify grid points with elevation values ​​greater than the elevation value threshold (called candidate ridge grid points), and use connectivity analysis to find multiple continuous candidate ridge grid points, and use the multiple continuous candidate ridge grid points as ridge grid points. In order to more accurately identify cols and saddles, a low-value filtering method can be used. This method involves selecting points with relatively low elevation values ​​and analyzing the terrain features around them. Cols are usually located in low-lying areas between two ridges or peaks. Cols can be identified by comparing the elevation values ​​of these low-lying areas with the elevation values ​​of the surrounding terrain. Cols usually have relatively flat terrain and low elevations. Saddles are low areas between two relatively high peaks. Saddles are usually located at the intersection of ridge lines and are transition points connecting two peaks. Saddles can be identified by comparing the elevation values ​​of saddles with the elevation values ​​of surrounding peaks. Saddles usually have low elevation values ​​and relatively flat terrain, but are narrower than cols. For example, the ridge grid points, col grid points and saddle grid points can be identified according to the elevation value of each grid point through the first micro-topography recognition model, wherein the first micro-topography recognition model can be a convolutional neural network (CNN) model.

[0091] The windward slope refers to the side of the hillside or terrain facing the wind source, and the leeward slope is the slope on the other side of the mountain or highland, away from the wind source. The windward slope and leeward slope will change under different wind direction conditions. According to the wind direction data, find the slopes whose slope direction is consistent with the wind direction. The grid points of these slopes are the windward slope grid points. Find the slopes whose slope direction is opposite to the wind direction. The grid points of these slopes are the leeward slope grid points.

[0092] The impact of large water bodies on ice cover is mainly reflected in their ability to regulate local climate. The air humidity near the water body is high and the temperature is relatively stable, which affects the formation and thickness of ice cover. The location of the water body can be identified by the low elevation value area in the DEM data. For example, the water body grid point is determined according to the elevation value of each grid point through the second micro-topography recognition model, where the second micro-topography recognition model can be a convolutional neural network model.

[0093] Transmission lines located at or near pass grid points, wind outlet grid points, ridge grid points, col grid points, saddle grid points, windward slope grid points, leeward slope grid points and water body grid points can be regarded as risky transmission lines.

[0094] Step 170: for each risky power transmission line, determine the icing risk value of the risky power transmission line.

[0095] Specifically include:

[0096] Establishing a risk prediction model, wherein the risk prediction model may be a convolutional neural network model;

[0097] Obtain local topographic information, local historical meteorological data, and local historical ice cover data of risky transmission lines;

[0098] The icing risk value of the risky transmission line is determined through the risk prediction model based on the local topographic information, local historical meteorological data and local historical icing data of the risky transmission line.

[0099] Step 180, determining the optimal grid icing monitoring point layout plan based on the icing risk value of each risky transmission line.

[0100] Specifically include:

[0101] According to the icing risk value of each risky transmission line, a plurality of target transmission lines are determined. For example, a risky transmission line whose icing risk value is greater than an icing risk value threshold is taken as a target transmission line.

[0102] According to the multiple target transmission lines, an initial grid ice monitoring point layout plan is generated. For example, the initial grid ice monitoring point layout plan may be to set a monitoring station on each target transmission line;

[0103] The initial grid icing monitoring point layout plan is optimized to generate the optimal grid icing monitoring point layout plan.

[0104] Preferably, the initial grid icing monitoring point layout scheme is optimized to generate an optimal grid icing monitoring point layout scheme, including:

[0105] Calculate the ice-covering correlation parameters of any two target transmission lines;

[0106] According to ice-covered correlation parameters of any two target transmission lines, multiple target transmission lines are clustered to determine multiple target transmission line clusters;

[0107] For each target transmission line cluster, according to the icing risk value of each target transmission line included in the target transmission line cluster, the layout density corresponding to the target transmission line cluster is determined, and according to the layout density, the representative transmission line corresponding to the target transmission line cluster is determined;

[0108] An optimal grid icing monitoring point layout plan is generated according to the representative transmission lines corresponding to each target transmission line cluster. For example, the optimal grid icing monitoring point layout plan may be to set a monitoring station on each representative transmission line.

[0109] Specifically, the ice-covering correlation parameters of the two target transmission lines can be calculated according to the following formula:

[0110] C (e，f )=a 31 ×S ((e，f)，icing) +a 32 ×S ((e，f)，microtopography) +a33 ×S ((e，f)，meteorology)

[0111] Among them, C (e，f) is the ice coverage correlation parameter of the e-th target transmission line and the f-th target transmission line, S ((e，f)，icing) is the ice coverage similarity between the e-th target transmission line and the f-th target transmission line, S ((e，f)，microtopography) is the terrain similarity between the e-th target transmission line and the f-th target transmission line, S ((e，f)，meteorology ) is the meteorological similarity between the e-th target transmission line and the f-th target transmission line, a 31 、a 32 and a 33 is the weight, a 31 、a 32 and a 33 Greater than 0, a 31 +a 32 +a 33 =1.

[0112] The ice similarity between the e-th target transmission line and the f-th target transmission line can be calculated based on the ice coverage values ​​of the e-th target transmission line and the f-th target transmission line at multiple historical time points. The terrain similarity between the e-th target transmission line and the f-th target transmission line can be calculated based on the elevation values ​​of multiple adjacent grid points of the e-th target transmission line and the elevation values ​​of multiple adjacent grid points of the f-th target transmission line. The meteorological similarity between the e-th target transmission line and the f-th target transmission line can be calculated based on the meteorological data of the e-th target transmission line and the f-th target transmission line at multiple historical time points.

[0113] A clustering algorithm (eg, a hierarchical clustering algorithm) may be used to cluster multiple target transmission lines according to ice-covered associated parameters and distances between any two target transmission lines to determine multiple target transmission line clusters.

[0114] The layout density corresponding to the target transmission line cluster can be calculated according to the following formula:

[0115]

[0116] Among them, ρ g is the layout density corresponding to the g-th target transmission line cluster, ρ0 is the preset layout density, R g is the mean of the icing risk values ​​of each target transmission line included in the target transmission line cluster, and R0 is the preset mean.

[0117] The number of representative transmission lines corresponding to the target transmission line cluster can be determined according to the layout density corresponding to the target transmission line cluster and the number of target transmission lines included in the target transmission line cluster, and the target transmission lines corresponding to the layout density and number can be sampled from the target transmission line cluster as representative transmission lines.

[0118] The monitoring station is composed of sensors, converters, data processing devices, data transmission devices and power supplies. The sensors are responsible for detecting meteorological elements, the converters are responsible for converting meteorological parameters into voltage, current and other signals, the data processing devices process the electrical signals and convert them into corresponding meteorological element values, and the data transmission devices are responsible for transmitting the detected meteorological element data to the terminal or control center. The data measured by the sensors mainly include wind speed, wind direction, temperature, humidity, air pressure, precipitation, etc. The sensors involved include wind speed, wind direction sensors, temperature and humidity sensors, air pressure sensors and rainfall sensors.

[0119] Due to the impact of micro-meteorological disasters and differences in detection elements, the instrument selection should be able to adapt to the needs of different environments. The following three aspects can be considered:

[0120] 1. Lightning protection design to prevent the automatic station equipment from being damaged and stopping working due to lightning strikes;

[0121] 2. Waterproof design to prevent the instrument from being damaged by heavy rainfall or excessive humidity in the field;

[0122] 3. Anti-corrosion design to prevent sensors from being damaged by atmospheric pollution and corrosion.

[0123] Comprehensively analyzing the geographical environment conditions of field observations and combining the use of instruments, the daily maintenance and management of monitoring sites should be considered from the following three aspects:

[0124] 1. Environmental safety. Since there is no dedicated person on duty at the automatic station, potential safety hazards may occur at any time, such as natural or man-made damage to the instrument. Therefore, the existing online monitoring equipment and safety protection experience of the power grid should be combined to prevent theft and loss of the instrument;

[0125] 2. Management responsibilities: formulate practical systems, arrange dedicated personnel to be on duty, do a good job in automatic station data collection and monitoring management, and keep abreast of the site operation status at any time.

[0126] 3. Regular maintenance: According to the actual operation of the automatic station, regular and comprehensive inspection and maintenance of various sensors, collectors, etc., as well as whether the cables and communication lines are disconnected, etc.

[0127] The distance between the edge of the row of buildings, trees and other obstructions around the monitoring station (measured from the outer edge of the automatic station, the visual angle is greater than 22.5 degrees) and the automatic station must be at least 10 times the height of the obstruction; the distance between the automatic station and the isolated obstacles around it (measured from the outer edge of the automatic station, the visual angle is ≤ 22.5 degrees) must be at least 8 times the height of the obstacle; the closest lateral distance between two isolated obstacles must not be less than 30 meters. The edge of various sources that affect the accuracy of the observation data must be at least 500 meters away from the automatic station, except for special observation purposes. Try not to plant high-pole (more than 1 meter) crops within 10 meters around the monitoring station to ensure smooth airflow.

[0128] Figure 2 is a module schematic diagram of a power grid ice monitoring and point optimization system according to some embodiments of this specification, such as Figure 2 As shown, a power grid icing monitoring point optimization system may include an information acquisition module, a region determination module, a line determination module, a risk determination module and a solution generation module.

[0129] The information acquisition module can be used to obtain topographic information of the area to be monitored;

[0130] The area determination module can be used to determine multiple first risk sub-areas of the area to be monitored based on the topographic information of the area to be monitored, and is also used to determine multiple second risk sub-areas of the area to be monitored based on the historical meteorological data of the area to be monitored, and is also used to determine multiple third risk sub-areas of the area to be monitored based on the historical ice cover data of the area to be monitored, and is also used to determine multiple target areas of the area to be monitored based on multiple first target sub-areas, multiple second target sub-areas and multiple third risk sub-areas of the area to be monitored;

[0131] The line determination module can be used to determine multiple risky transmission lines based on multiple target areas in the area to be monitored;

[0132] The risk determination module may be used to determine the icing risk value of each risky transmission line;

[0133] The scheme generation module can be used to determine the optimal grid icing monitoring point layout scheme based on the icing risk value of each risky transmission line.

[0134] A power grid icing monitoring point optimization system can be used to execute a power grid icing monitoring point optimization method. For more descriptions of a power grid icing monitoring point optimization system, please refer to the relevant descriptions of a power grid icing monitoring point optimization method, which will not be repeated here.

[0135] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A method for optimizing the layout of power grid icing monitoring points, characterized in that: include: Obtain topographic information of the area to be monitored; Based on the topographic information of the area to be monitored, determining a plurality of first risk sub-areas of the area to be monitored; Determining a plurality of second risk sub-areas of the area to be monitored based on historical meteorological data of the area to be monitored; Determine a plurality of third-risk sub-areas of the area to be monitored according to historical ice coverage data of the area to be monitored; Determine a plurality of target areas of the area to be monitored according to a plurality of first target sub-areas, a plurality of second target sub-areas and a plurality of third target sub-areas of the area to be monitored; Determining a plurality of risky power transmission lines according to a plurality of target areas in the area to be monitored; For each of the risky power transmission lines, determining an icing risk value of the risky power transmission line; According to the icing risk value of each risky transmission line, the optimal grid icing monitoring point layout plan is determined.

2. A method for optimizing the layout of power grid icing monitoring points according to claim 1, characterized in that: Based on the topographic information of the area to be monitored, a plurality of first risk sub-areas are determined, including: Dividing the area to be monitored into a plurality of unit areas; For each of the unit areas, based on the topographic information of the area to be monitored, determining the slope and topographic relief of the unit area; The plurality of first risk sub-areas are determined according to the slope and terrain undulation of each of the unit areas.

3. A method for optimizing the layout of power grid icing monitoring points according to claim 2, characterized in that: Determine multiple second risk sub-areas of the area to be monitored based on the historical meteorological data of the area to be monitored, including: Determining the relevant meteorological elements of the area to be monitored; For each of the unit areas, calculating the meteorological element change gradient corresponding to each of the associated meteorological elements in the unit area according to the historical meteorological data of the area to be monitored; A plurality of second risk sub-areas of the area to be monitored are determined by a change gradient of the meteorological element corresponding to each of the associated meteorological elements in each of the unit areas.

4. A method for optimizing the layout of power grid icing monitoring points according to claim 2, characterized in that: According to the historical ice coverage data of the area to be monitored, a plurality of third-risk sub-areas of the area to be monitored are determined, including: Establish an ice cover sensitivity prediction model; For each of the unit areas, judging whether the unit area is an icing risk unit area according to the historical icing data of the area to be monitored; For each of the icing risk unit areas, the icing sensitivity of the unit area is determined by the icing sensitivity prediction model according to the historical icing data, topographic information and historical meteorological data of the area to be monitored; According to the ice coverage sensitivity of each of the unit areas, a plurality of third-risk sub-areas of the area to be monitored are determined.

5. A method for optimizing the placement of power grid icing monitoring points according to any one of claims 1 to 4, characterized in that: Determining multiple target areas of the area to be monitored according to multiple first target sub-areas, multiple second target sub-areas and multiple third target sub-areas of the area to be monitored includes: According to the intersection of the plurality of first target sub-areas, the plurality of second target sub-areas and the plurality of third target sub-areas of the area to be monitored, the plurality of target areas of the area to be monitored are determined.

6. A method for optimizing the placement of power grid icing monitoring points according to any one of claims 1 to 4, characterized in that: According to the multiple target areas of the area to be monitored, multiple risky transmission lines are determined, including: For each grid point included in the multiple target areas of the to-be-monitored area, judging whether the grid point is a pass grid point or a wind outlet grid point according to the slope of the grid point, the elevation value of the grid point, the elevation values ​​of adjacent grid points of the grid point, and wind speed simulation data; Using connectivity analysis, determining the ridge grid points, col grid points and saddle grid points included in the plurality of target areas of the area to be monitored; Determine the windward slope grid points and leeward slope grid points included in the multiple target areas of the area to be monitored according to the wind direction data and the slope direction of each grid point; Determine the water body grid points included in the multiple target areas of the area to be monitored according to the elevation value of each grid point; Based on the multiple target areas of the area to be monitored, including pass grid points, wind outlet grid points, ridge grid points, col grid points, saddle grid points, windward slope grid points, leeward slope grid points and water body grid points, multiple risky transmission lines are determined.

7. A method for optimizing the placement of power grid icing monitoring points according to any one of claims 1 to 4, characterized in that: Determining the icing risk value of the risky transmission line includes: Establish risk prediction models; Obtaining local topographic information, local historical meteorological data and local historical ice coverage data of the risky transmission line; The risk prediction model is used to determine the icing risk value of the risky power transmission line based on the local topographic information, local historical meteorological data and local historical icing data of the risky power transmission line.

8. A method for optimizing the placement of power grid icing monitoring points according to any one of claims 1 to 4, characterized in that: According to the icing risk value of each risky transmission line, the optimal grid icing monitoring point layout plan is determined, including: Determining a plurality of target transmission lines according to the icing risk value of each of the risky transmission lines; Generate an initial grid ice monitoring point layout plan based on multiple target transmission lines; The initial grid icing monitoring point layout plan is optimized to generate the optimal grid icing monitoring point layout plan.

9. A method for optimizing the layout of power grid icing monitoring points according to claim 8, characterized in that: Optimizing the initial grid icing monitoring point layout plan to generate the optimal grid icing monitoring point layout plan, including: Calculate the ice-covering correlation parameters of any two target transmission lines; Clustering the plurality of target transmission lines according to ice-covered correlation parameters of any two target transmission lines to determine a plurality of target transmission line clusters; For each of the target transmission line clusters, determining a layout density corresponding to the target transmission line cluster according to the icing risk value of each target transmission line included in the target transmission line cluster, and determining a representative transmission line corresponding to the target transmission line cluster according to the layout density; The optimal grid icing monitoring point layout plan is generated according to the representative transmission line corresponding to each target transmission line cluster.

10. A grid icing monitoring and point optimization system, characterized in that: A method for optimizing the deployment of power grid icing monitoring points according to any one of claims 1 to 9 is applied, comprising: An information acquisition module is used to obtain topographic information of the area to be monitored; an area determination module, for determining a plurality of first risk sub-areas of the area to be monitored based on the topographic information of the area to be monitored, for determining a plurality of second risk sub-areas of the area to be monitored based on the historical meteorological data of the area to be monitored, for determining a plurality of third risk sub-areas of the area to be monitored based on the historical ice cover data of the area to be monitored, and for determining a plurality of target areas of the area to be monitored based on a plurality of first target sub-areas, a plurality of second target sub-areas and a plurality of third risk sub-areas of the area to be monitored; A line determination module, used for determining a plurality of risky power transmission lines according to a plurality of target areas in the area to be monitored; A risk determination module, used for determining, for each of the risky power transmission lines, an icing risk value of the risky power transmission line; The scheme generation module is used to determine the optimal grid icing monitoring point layout scheme according to the icing risk value of each risky transmission line.

Images