A method and system for predicting load power failure probability under wind and rain combined disasters

Abstract

The present invention provides a method and system for predicting the probability of load power outage under the disaster of wind and rain superposition, which relates to the technical field of distribution network fault prediction, including: obtaining typhoon parameters and rainfall parameters under the disaster of wind and rain superposition; inputting the typhoon parameters, rainfall parameters, and the distribution line to be detected into a power outage probability prediction model, and outputting the probability of power outage of each load on the distribution line to be detected caused by the wind and rain superposition disaster; wherein the power outage probability prediction model is obtained by correcting the constructed load power outage probability result matrix caused by typhoon through rainfall parameter samples. The method and system of the present invention are used to solve the defect of predicting the probability of load power outage in the prior art for a single disaster factor, accurately predict the probability of load power outage under the disaster of wind and rain superposition, and realize a more accurate and systematic evaluation of the distribution network's ability to resist and adapt to disasters.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network fault prediction, and in particular to a method and system for predicting load power failure probability under wind and rain combined disasters. Background Art

[0002] Due to the adverse impact of global warming on the earth's ecology, the frequency of extreme disasters has increased dramatically in recent years. Extreme disasters are characterized by high uncertainty and a wide range of impact, and the normal operation of the power system faces a great threat. As the most vulnerable link in the power system, the urban distribution network is more vulnerable to disaster damage.

[0003] Different types of natural disasters are often interrelated. One disaster can trigger another. Different disasters can be coupled with each other and can even transform into each other. For example, typhoons often bring heavy rains, which can trigger other secondary disasters, such as floods, mudslides, and even landslides. These secondary disasters form a chain reaction in time and space, causing the damage caused by the disasters to continue to expand in a cumulative form. This series of disaster chain occurrences is called a disaster chain. However, the probability of extreme compound disasters is very small, so they are usually ignored. However, the impact and losses they cause are huge. Therefore, this event is called a "high-risk low-probability event", and early warning work for this type of disaster is also very important.

[0004] However, in reality, most of the models of typhoon disaster warning systems for distribution networks that have been put into practical use only consider the typhoon forecast path and wind circle radius as input, correspond the typhoon location information with the distribution network geographic information, and believe that the distribution lines passing through the typhoon path and within the wind circle are prone to failure, and issue warnings for them. Some models also compare the wind speed information in the typhoon forecast with the wind speed that the actual line can withstand, believing that once the wind speed exceeds the actual line wind speed, there may be a risk of failure, thus establishing a threshold model.

[0005] The disaster-causing factors in these models are single, the analysis is not comprehensive, and other factors such as rainfall impact, terrain characteristics, and line structure are not considered, which greatly reduces the effectiveness and pertinence of the early warning system. For example, overhead lines are directly exposed to the external environment and are directly affected by extreme weather. However, when considering the impact of extreme disasters on lines, usually only the effects of ice and strong winds are considered in the modeling line loads. Most models ignore the impact of rainfall on lines, but a large number of accident cases have proved that when the combined effects of wind and rain loads occur, the lines are more vulnerable to damage. For example, the level of insulators will be damaged by the salt concentration of rainwater and reduced, which seriously threatens the safety and stability of line operation. Summary of the invention

[0006] The present invention provides a method and system for predicting the probability of load power outage under the combined disaster of wind and rain, so as to solve the defect of the prior art that when predicting the probability of load power outage, prediction is made for a single disaster factor, and the load power outage probability under the combined disaster of wind and rain is accurately predicted, so as to achieve a more accurate and systematic evaluation of the distribution network's ability to resist and adapt to disasters.

[0007] The present invention provides a method for predicting the probability of load power failure under the disaster of wind and rain superposition, comprising:

[0008] Obtain typhoon parameters and rainfall parameters under the disaster of wind and rain superposition;

[0009] The typhoon parameters, rainfall parameters and the distribution line to be detected are input into a power outage probability prediction model, and the power outage probability prediction model outputs the probability of power outage of each load on the distribution line to be detected due to the wind and rain superposition disaster;

[0010] The power outage probability prediction model is obtained by correcting the constructed load power outage probability result matrix caused by typhoon according to the rainfall parameters.

[0011] Preferably, according to the method for predicting load power failure probability under wind and rain superposition disasters of the present invention, the step of obtaining typhoon parameters and rainfall parameters under wind and rain superposition disasters specifically includes:

[0012] The structural parameters and rainfall intensity of a typhoon under the combined disaster of wind and rain are obtained; wherein the structural parameters include: the landing position, moving direction, moving speed, maximum speed and maximum wind circle radius of the typhoon.

[0013] Preferably, according to the method for predicting the probability of power failure of loads under the superposition of wind and rain disasters of the present invention, the typhoon parameters, rainfall parameters and the distribution line to be detected are input into the power failure probability prediction model, and the probability of power failure of each load on the distribution line to be detected caused by the superposition of wind and rain disasters is output, which specifically includes:

[0014] Inputting the power distribution line to be detected into the line parameter extraction layer of the power failure probability prediction model, the line parameter extraction layer outputs the power distribution line to be detected and the damage resistance parameters of each load divided by stages;

[0015] The damage resistance parameters of the distribution lines to be detected and each load at each stage, the typhoon parameters and the rainfall parameters are input into the analysis and judgment layer of the power outage probability prediction model, and the analysis and judgment layer outputs the probability of power outage of each load on the distribution lines to be detected.

[0016] Preferably, according to the load power outage probability prediction method under the wind and rain superposition disaster of the present invention, the line parameter extraction layer outputs the damage resistance parameters of the distribution line to be detected and each load divided by stages, specifically including:

[0017] Decomposing the distribution line to be detected according to set stages, and obtaining the wind resistance level of the distribution line to be detected in each stage respectively;

[0018] The information of the substation and the load switch cabinet connected to the load on the distribution line to be detected is obtained, and the rain protection level of each substation and load switch cabinet is obtained respectively.

[0019] Preferably, according to the method for predicting the probability of power outage of loads under the disaster of wind and rain superposition according to the present invention, the anti-damage capacity parameters of the distribution lines to be detected and each load at each stage, the typhoon parameters and the rainfall parameters are input into the analysis and judgment layer of the power outage probability prediction model, and the analysis and judgment layer outputs the probability of power outage of each load on the distribution lines to be detected, which specifically includes:

[0020] According to the distribution lines and loads to be detected in each stage, a correlation matrix between the line and load nodes of the distribution lines to be detected and the power supply nodes is constructed; wherein the power supply nodes include substations and load switch cabinets;

[0021] According to the damage resistance parameters of the distribution lines to be detected at each stage and the typhoon parameters, the correlation matrix is ​​corrected to obtain the state result matrix of the distribution lines to be detected at each stage;

[0022] After the state result matrix is ​​corrected according to the rainfall parameter, the state result of the distribution line to be detected in each stage under the condition of wind and rain is obtained;

[0023] According to the state result and the anti-damage capability parameter analysis of each load, the probability of power failure of each load on the distribution line to be detected is obtained.

[0024] Preferably, according to the method for predicting the probability of power outage of loads under the combined disaster of wind and rain according to the present invention, after the power outage probability prediction model outputs the probability of power outage of each load on the distribution line to be detected caused by the combined disaster of wind and rain, it also includes:

[0025] The probability of power failure of each load on the distribution line to be detected is compared with a preset threshold value, and the load with a probability greater than the threshold value is determined as a load prone to power failure.

[0026] The present invention also provides a load power failure probability prediction system under the disaster of wind and rain superposition, and the load power failure probability prediction system is applied to the above-mentioned load power failure probability prediction method, comprising:

[0027] An acquisition module, used to acquire typhoon parameters and rainfall parameters under the disaster of wind and rain superposition; and

[0028] A prediction module, used to input the typhoon parameters, rainfall parameters and the distribution line to be detected into a power failure probability prediction model, and output the probability of power failure of each load on the distribution line to be detected caused by the wind and rain superposition disaster;

[0029] The power outage probability prediction model is obtained by correcting the constructed load power outage probability result matrix caused by typhoons through rainfall parameter samples.

[0030] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the method for predicting the probability of load power failure under any of the above-mentioned wind and rain combined disasters are implemented.

[0031] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method for predicting the probability of load power failure under any of the above-mentioned wind and rain combined disasters are implemented.

[0032] The present invention also provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of any of the above-mentioned methods for predicting the probability of load power outage under the combined disaster of wind and rain.

[0033] The present invention provides a method and system for predicting the probability of load power outage under the superposition of wind and rain disasters. By inputting the acquired typhoon parameters and rainfall parameters under the superposition of wind and rain disasters, and the distribution line to be detected into the power outage probability prediction model obtained by correcting the constructed load power outage probability result matrix caused by the typhoon through rainfall parameter samples, the probability of power outage of each load on the distribution line to be detected can be output, so that the prediction of the power outage probability of each load takes typhoon and rainfall factors into comprehensive consideration, avoiding the defect of low accuracy in predicting the load power outage probability for a single disaster factor, thereby achieving more accurate and systematic consideration of the impact of the typhoon disaster chain as a whole on the distribution network. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 It is a flow chart of a method for predicting the probability of load power failure under wind and rain superimposed disasters provided by the present invention;

[0036] Figure 2It is a schematic diagram of an association matrix of an example provided by the present invention;

[0037] Figure 3 It is a path diagram for searching load nodes based on an association matrix instance provided by the present invention;

[0038] Figure 4 The present invention provides Figure 2 A comparison chart of the power outage probability of load node 5 in the correlation matrix shown in the figure considering the superposition of wind and rain and the power outage probability considering a single typhoon;

[0039] Figure 5 The present invention provides Figure 2 A comparison diagram of the power outage probability of load node 11 in the correlation matrix shown in the figure considering the superposition of wind and rain and the power outage probability considering a single typhoon;

[0040] Figure 6 It is a structural schematic diagram of a load power failure probability prediction system under wind and rain superimposed disasters provided by the present invention;

[0041] Figure 7 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are 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.

[0043] It should be noted that almost all national infrastructure is closely related to the supply of electricity. Ensuring safe and reliable power supply is conducive to economic prosperity and the stability of people's livelihood. However, once an accident occurs, due to the complexity of the power system structure, the fault will spread extremely quickly, affecting a wide range and causing serious harm. In addition to the power grid companies, the daily lives of power users and the production and construction of the country will suffer losses to varying degrees. The greenhouse effect has caused the overall deterioration of the global ecological environment, and extreme weather disasters such as typhoons, floods, and cold currents have become more frequent. The impact of extreme weather disasters on the power grid has the characteristics of large damage range, long duration, many affected equipment, and difficulty in restoring power supply. Different types of natural disasters are often interrelated. One disaster can induce another. Different disasters can have a mutually coupled relationship and can even transform into each other. For example, the occurrence of typhoons often brings heavy rains, which can trigger other secondary disasters, such as floods, mudslides, and even landslides. These secondary disasters form a chain reaction in time and space, causing the damage caused by the disasters to continue to expand in a cumulative form.

[0044] Therefore, when predicting the ability of distribution lines to resist extreme meteorological disasters, we cannot simply consider a single disaster-causing factor, but should consider it comprehensively to improve the accuracy of the overall prediction.

[0045] Based on this, the present invention provides a method and system for predicting the probability of load power outage under the superposition of wind and rain disasters. By modeling the superposition of wind and rain disasters, a more accurate and systematic evaluation of the distribution network's ability to resist and adapt to extreme meteorological disasters can be achieved.

[0046] Combine the following Figures 1 to 5 The present invention describes a method for predicting the probability of load power failure under a storm-superimposed disaster, such as Figure 1 As shown, the method comprises the following steps:

[0047] 101. Obtain typhoon parameters and rainfall parameters under the disaster of wind and rain superposition;

[0048] 102. Input the typhoon parameters, rainfall parameters and the distribution line to be detected into a power outage probability prediction model, and the power outage probability prediction model outputs the probability of power outage of each load on the distribution line to be detected due to the wind and rain superposition disaster;

[0049] The power outage probability prediction model is obtained by correcting the constructed load power outage probability result matrix caused by typhoon according to rainfall parameter samples.

[0050] It should be noted that, as mentioned above, for extreme meteorological disasters, there is often more than one disaster-causing factor. For example, after a typhoon makes landfall, heavy rainfall often occurs in the area along the typhoon path. Therefore, from a time scale, the present invention assumes that rainfall continues to accompany the typhoon from the time the typhoon makes landfall until the typhoon leaves the distribution line area to be tested, and assumes that the rainfall intensity is consistent for each location within the distribution line area to be tested.

[0051] The above-mentioned method for predicting the probability of load power outage under the combined disaster of wind and rain, after obtaining the typhoon parameters and rainfall parameters under the combined disaster of wind and rain, inputs the typhoon parameters and rainfall parameters as well as the distribution line to be detected into the power outage probability prediction model, and predicts the power outage probability of each load on the distribution line to be detected through the power outage probability prediction model, so that the prediction of the power outage probability of each load takes typhoon and rainfall factors into comprehensive consideration, avoiding the defect of low accuracy in predicting the load power outage probability for a single disaster factor, thereby achieving more accurate and systematic consideration of the impact of the overall typhoon disaster chain on the distribution network.

[0052] For the prediction of the probability of load power failure in the distribution line under the disaster of wind and rain superposition, the influence of wind and rain on the load and the line both have an impact on the probability of load power failure, and different parameters of wind or rain have certain differences in the influence on the load or line. Therefore, in one embodiment of the present invention, the typhoon parameters and rainfall parameters input into the power failure probability prediction model are specifically described, that is:

[0053] The structural parameters and rainfall intensity of a typhoon under the combined disaster of wind and rain are obtained; wherein the structural parameters include: the landing position, moving direction, moving speed, maximum speed and maximum wind circle radius of the typhoon.

[0054] It should be noted that since typhoon disasters are highly temporally and spatially correlated, when analyzing the impact of typhoons on distribution networks, it cannot be assumed that all distribution network loads are affected by typhoons of the same intensity at the same time, nor can it be assumed that the typhoon intensity experienced by a single load remains consistent over the disaster time scale. Therefore, when considering the impact of typhoons on distribution networks, the typhoon's path, wind speed, and typhoon structure are considered, that is, the structural parameters also include the wind speed of the typhoon when it reaches the corresponding load.

[0055] Furthermore, because the load needs to rely on the line for power supply, when considering the impact of rainfall on the probability of power failure of the load, the impact of rainfall on the line should also be taken into account. At the same time, it is understandable that when considering the damage to the line, it is generally believed that once the physical load borne by the line exceeds its originally designed rated load, the line may be damaged. Therefore, the impact of rainfall on the line can be treated as a load, that is, the rainfall intensity F r (t):

[0056]

[0057] Among them, d r is the diameter of a raindrop; n is the number of raindrops per unit volume; b is the affected area of ​​the equipment facing the direction of the rain; v s The speed at which raindrops fall toward the device.

[0058] Usually, raindrops 1 The number of them per unit volume is:

[0059] n(d 1 )=n 0 exp(-Λd 1 ) Formula 2;

[0060] Among them, n 0 is a constant, n 0 =8×10 3 pcs / (m 3 ·mm); Λ is the slope factor, which is negatively correlated with rainfall intensity, Λ=4.1I -0.21 .

[0061] In another embodiment of the present invention, the processing process of the power failure probability prediction model for the input typhoon parameters, rainfall parameters and the distribution line to be detected is further described, that is, the following steps are included:

[0062] 1021. Input the distribution line to be detected into the line parameter extraction layer of the power failure probability prediction model, and the line parameter extraction layer outputs the damage resistance parameters of the distribution line to be detected and each load divided into stages;

[0063] 1022. Input the damage resistance parameters of the distribution lines to be tested and each load at each stage, the typhoon parameters and the rainfall parameters into the analysis and judgment layer of the power outage probability prediction model, and the analysis and judgment layer outputs the probability of power outage of each load on the distribution lines to be tested.

[0064] It should be noted that the line parameter extraction layer of the power outage probability prediction model first obtains the damage resistance parameters of the lines and loads at each stage from the distribution line to be detected, and then the analysis and judgment layer performs analysis based on the damage resistance parameters and the input typhoon parameters and rainfall parameters to obtain the probability of power outage of each load on the distribution line to be detected.

[0065] Further, it can be understood that the typhoon parameters include: the landing position, moving direction, moving speed, maximum speed and maximum wind circle radius of the typhoon, and the rainfall parameters include rainfall intensity. Considering the probability of power outage of each load on the distribution line to be detected due to typhoon parameters is essentially considering the wind speed level that the line where the load is located is subjected to at a certain moment. Therefore, the typhoon parameters also include the wind resistance level of the line where the load is located. Similarly, for rainfall, it is necessary to consider whether the upstream substation or load switch cabinet that supplies power to the load is flooded, causing short circuits and other faults. Therefore, the rainfall parameters also include the rain protection level of the substation and load switch cabinet that supply power to the load. Based on this, in another embodiment of the present invention, the line parameter extraction layer of the power outage probability prediction model is specifically described by the specific content of the damage resistance parameters that need to be obtained by the distribution line to be detected:

[0066] 10211. Decomposing the power distribution line to be detected according to set stages, and obtaining the wind resistance level of the power distribution line to be detected in each stage respectively;

[0067] 10212. Obtain information about the substation and load switch cabinet connected to the load on the distribution line to be detected, and obtain the rain protection level of each substation and load switch cabinet respectively.

[0068] It should be noted that at the beginning of the design of the distribution line, the line has a certain wind resistance level. Once the wind speed exceeds this level, the line may be damaged or disconnected; once the wind speed is much greater than the wind resistance level of the line, the failure rate of the line is 100%. Similarly, the equipment also has a specified rain protection level at the beginning of the design, that is, when the rainfall is greater than the rain protection level of the equipment, the equipment is basically certain to fail. Therefore, the line parameter extraction layer of the power failure probability prediction model obtains the damage resistance parameters including: the wind resistance level of each stage of the distribution line to be detected, and the rain protection level of the substation and load switch cabinet to which the load is connected.

[0069] In another embodiment of the present invention, a method for predicting the load power failure probability of the distribution line to be detected by using the power failure probability prediction model is further described, which specifically includes:

[0070] 10221. Constructing a correlation matrix between the line and load nodes of the distribution line to be detected and the power supply nodes according to the distribution line and load to be detected in each stage; wherein the power supply nodes include substations and load switch cabinets;

[0071] 10222. According to the damage resistance parameters of the distribution lines to be detected at each stage and the typhoon parameters, the correlation matrix is ​​corrected to obtain a state result matrix of the distribution lines to be detected at each stage;

[0072] 10223. After correcting the state result matrix according to the rainfall parameter, the state result of the distribution line to be detected in each stage under the condition of wind and rain is obtained;

[0073] 10224. According to the state result and the damage resistance parameter of each load, the probability of power failure of each load on the distribution line to be detected is analyzed.

[0074] It should be noted that, due to the radial structure of the distribution network, all lines are connected in series starting from the feeder substation, and the line branches are connected in series downstream of the trunk line. Therefore, for each load, once its upstream line is damaged and shut down, the load will lose power supply. Therefore, for each line outage scenario, it is only necessary to search for the downstream load nodes of each line in each stage. Therefore, the analysis and judgment layer first constructs the line and load nodes of the distribution line to be detected according to the lines and loads of each stage of the distribution line to be detected, as well as the association matrix I between the power supply nodes to characterize the connection relationship between the lines and nodes. Figure 2 As shown, Figure 2 is an example of an association matrix, in which, if I(i, j)=0 in the i-th row and j-th column of the matrix, it indicates that there is no direct connection between line i and node j; if I(i, j)=1 in the i-th row and j-th column of the matrix, it indicates that node j is the upstream node immediately adjacent to line i; if I(i, j)=-1 in the i-th row and j-th column of the matrix, it indicates that node j is the downstream node immediately adjacent to line i; for each line i, the i-th row of the association matrix is ​​searched for the immediately downstream node of line i, that is, the column corresponding to the element with a value of -1, which may be recorded as j; for node j, the j-th column of the association matrix is ​​searched for the downstream line of the node (the line that takes the node as the upstream node), that is, the row corresponding to the element with a value of +1 (there may be multiple lines), and if such a line exists, the search for the immediately downstream node of each line is continued; if not, the search for the downstream node of line i is terminated.

[0075] More specifically, if Figure 3As shown, for example, a search is performed for all load nodes downstream of line 12. For the 12th row of the association matrix, I(12,4)=-1, so the immediately downstream node of line 12 is load node No. 4; for the 4th column of the association matrix, I(11,4)=1 and I(13,4)=1, so it can be considered that the downstream lines of load No. 4 are line No. 11 and line No. 13; first, continue searching line 13, in row 13, I(13,13)=-1, so the immediately downstream node of line 13 is load node No. 13; in column 13, since I(14,13)=1, it can be considered that the downstream line of load No. 13 is line No. 14, and continue searching line 14, I(14,14)=-1, and its immediately downstream node is load No. 14; return to another downstream line 11 of load No. 4 again, because the line switch is disconnected and not put into use (the use of the transfer is involved in the following text), there is no downstream node. Therefore, all downstream nodes of the line 12 include load nodes 4, 13, and 14. Once the line 12 is out of service, these nodes will lose power supply.

[0076] Afterwards, the formed association matrix is ​​corrected according to the damage resistance parameters and typhoon parameters of the lines in each stage. That is, when the typhoon wind speed exceeds the wind resistance level of the line in a certain stage, the nodes corresponding to the lines in the stage in the association matrix will lose power supply. Therefore, the probability of power loss of each line or node under the influence of wind speed is obtained.

[0077] As mentioned above, the impact of rainfall on the line can be treated as a load, that is, rainfall intensity. After correcting the state result matrix according to the rainfall parameters, the state results of the line in each stage under wind and rain conditions can be obtained.

[0078] Through the damage resistance parameters of each load, the power failure probability of the substation and load switch cabinet to which the load is connected can be obtained. By combining it with the status results of the lines in each stage under wind and rain conditions for analysis, the accurate probability of power failure of each load on the distribution line to be tested can be obtained.

[0079] Furthermore, after obtaining the accurate probability of power failure of each load on the distribution line to be detected, some loads are determined to be prone to power failure, which can help adjust the power supply of corresponding loads in advance before the disaster occurs to ensure the normal power supply of key loads.

[0080] Based on this, in another embodiment of the present invention, after the power failure probability prediction model outputs the probability of power failure of each load on the distribution line to be detected due to the wind and rain superposition disaster, it also includes:

[0081] 103. Compare the probability of power failure of each load on the distribution line to be detected with a preset threshold value, and determine the load with a probability greater than the threshold value as a load prone to power failure.

[0082] Specifically, by counting the power failure frequency of loads in disaster scenarios and comparing it with the set threshold, the charges that are prone to power failure in disasters can be obtained.

[0083] In the method for predicting the probability of load power outage under the combined disaster of wind and rain described in the present invention, rainstorm disasters are taken into consideration, and the impact of substations and load switch cabinets on load outages is added, making the prediction of the probability of load power outage under the combined disaster of wind and rain such as typhoons more accurate.

[0084] by Figure 2 Taking the distribution line with 14 load nodes shown in FIG. 1 as an example, the prediction method of the present invention is used to obtain the probability of load nodes 5 and 11 being out of power under the conditions of wind speed of 48 m / s and rainfall of 40 mm / h, and the power outage probability is compared with the load time-varying power outage probability of the typhoon disaster with only the wind speed of 48 m / s. The results are as follows: Figure 4 and Figure 5 As shown, it can be seen that after considering the superposition of wind and rain disasters, the load failure rate has a significant upward trend compared to considering only the typhoon disaster. Obviously, when wind and rain are superimposed on disasters, the load failure rate obtained by considering the superposition of wind and rain is more accurate.

[0085] Combine the following Figure 6 A load power outage probability prediction system under a wind and rain superimposed disaster provided by the present invention is described. The load power outage probability prediction system under a wind and rain superimposed disaster described below and the load power outage probability prediction method under a wind and rain superimposed disaster described above can correspond to each other.

[0086] like Figure 6 As shown, the present invention provides a load power failure probability prediction system under wind and rain combined disasters, including an acquisition module 610 and a prediction module 620; wherein,

[0087] The acquisition module 610 is used to obtain typhoon parameters and rainfall parameters under the disaster of wind and rain superposition;

[0088] The prediction module 620 is used to input the typhoon parameters, rainfall parameters and the distribution line to be detected into the power failure probability prediction model, and output the probability of power failure of each load on the distribution line to be detected caused by the wind and rain superposition disaster;

[0089] The power outage probability prediction model is obtained by correcting the constructed load power outage probability result matrix caused by typhoon according to rainfall parameter samples.

[0090] It should be noted that the load power outage probability prediction system under the combined disaster of wind and rain of the present invention can output the probability of power outage of each load on the distribution line to be detected by correcting the constructed load power outage probability result matrix caused by typhoon by the constructed typhoon parameter result matrix through rainfall parameter samples by inputting the typhoon parameters and rainfall parameters under the combined disaster of wind and rain, and the power outage probability prediction model obtained by inputting the distribution line to be detected, so that the prediction of the power outage probability of each load takes typhoon and rainfall factors into comprehensive consideration, avoiding the defect of low accuracy in predicting the load power outage probability for a single disaster factor, thereby achieving more accurate and systematic consideration of the impact of the typhoon disaster chain as a whole on the distribution network.

[0091] In a preferred embodiment, the acquisition module 610 is specifically used to obtain the structural parameters and rainfall intensity of the typhoon under the superposition of wind and rain disasters; wherein the structural parameters include: the typhoon's landing position, moving direction, moving speed, maximum speed and maximum wind circle radius.

[0092] In a preferred embodiment, the prediction module 620 includes an extraction unit and an analysis unit; wherein,

[0093] The extraction unit is used to input the distribution line to be detected into the line parameter extraction layer of the power failure probability prediction model, and the line parameter extraction layer outputs the damage resistance parameters of each stage line and each load of the distribution line to be detected;

[0094] The analysis unit is used to input the damage resistance parameters of each stage line and each load of the distribution line to be detected, the typhoon parameters and the rainfall parameters into the analysis and judgment layer of the power outage probability prediction model, and the analysis and judgment layer outputs the probability of power outage of each load on the distribution line to be detected.

[0095] In a preferred embodiment, the extraction unit is specifically used to decompose the lines of the distribution line to be tested, and obtain the wind resistance level of the lines in each stage respectively; and obtain the information of the substation and load switch cabinet connected to the load on the distribution line to be tested, and obtain the rain protection level of each substation and load switch cabinet respectively.

[0096] In a preferred embodiment, the analysis unit is specifically used to construct a correlation matrix between the line and load nodes of the distribution line to be detected, and the power supply nodes according to the lines and loads of each stage of the distribution line to be detected; wherein the power supply nodes include substations and load switch cabinets;

[0097] According to the damage resistance parameters of the line at each stage and the typhoon parameters, the correlation matrix is ​​corrected to obtain the state result matrix of the line at each stage;

[0098] After the state result matrix is ​​corrected according to the rainfall parameter, the state result of the line in each stage under the condition of wind and rain is obtained;

[0099] The state results and the damage resistance parameters of each load are combined to analyze and obtain the probability of power failure of each load on the distribution line to be detected.

[0100] In a preferred embodiment, it further includes a determination module, which is used to compare the probability of power failure of each load on the distribution line to be detected with a preset threshold value, and determine the load with a probability greater than the threshold value as a load prone to power failure.

[0101] The load power outage probability prediction system under the combined disaster of wind and rain described in the present invention takes rainstorm disasters into consideration, and at the same time increases the impact of substations and load switch cabinets on load outages, making the prediction of load power outage probability under the combined disaster of wind and rain such as typhoons more accurate.

[0102] Figure 7 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 7 As shown, the electronic device may include: a processor (processor) 710, a communication interface (Communications Interface) 720, a memory (memory) 730 and a communication bus 740, wherein the processor 710, the communication interface 720, and the memory 730 complete mutual communication through the communication bus 740. The processor 710 can call the logic instructions in the memory 730 to execute the load power failure probability prediction method under the wind and rain superposition disaster, the method comprising: obtaining typhoon parameters and rainfall parameters under the wind and rain superposition disaster; inputting the typhoon parameters, rainfall parameters, and the distribution line to be detected into the power failure probability prediction model, and outputting the probability of power failure of each load on the distribution line to be detected caused by the wind and rain superposition disaster; wherein the power failure probability prediction model is obtained by correcting the constructed load power failure probability result matrix caused by the typhoon through the rainfall parameter sample.

[0103] In addition, the logic instructions in the above-mentioned memory 730 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0104] On the other hand, the present invention also provides a computer program product, which includes a computer program, and the computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the load power outage probability prediction method under the wind and rain superposition disaster provided by the above-mentioned methods, and the method includes: obtaining typhoon parameters and rainfall parameters under the wind and rain superposition disaster; inputting the typhoon parameters, rainfall parameters, and the distribution line to be detected into a power outage probability prediction model, and outputting the probability of power outage of each load on the distribution line to be detected caused by the wind and rain superposition disaster; wherein the power outage probability prediction model is obtained by correcting the constructed load power outage probability result matrix caused by typhoon through rainfall parameter samples.

[0105] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the load power outage probability prediction method under the wind and rain superposition disaster provided by the above-mentioned methods, the method comprising: obtaining typhoon parameters and rainfall parameters under the wind and rain superposition disaster; inputting the typhoon parameters, rainfall parameters, and the distribution line to be detected into a power outage probability prediction model, and outputting the probability of power outage of each load on the distribution line to be detected caused by the wind and rain superposition disaster; wherein the power outage probability prediction model is obtained by correcting the constructed load power outage probability result matrix caused by typhoon through rainfall parameter samples.

[0106] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0107] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0108] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting the probability of load power failure under wind and rain combined disasters, characterized in that: include: Obtain typhoon parameters and rainfall parameters under the disaster of wind and rain superposition; The typhoon parameters, rainfall parameters and the distribution line to be detected are input into a power outage probability prediction model, and the power outage probability prediction model outputs the probability of power outage of each load on the distribution line to be detected caused by the wind and rain superposition disaster; Wherein, the power outage probability prediction model is obtained by correcting the constructed load power outage probability result matrix caused by typhoon according to the rainfall parameters; The step of inputting the typhoon parameters, rainfall parameters and the distribution line to be detected into the power failure probability prediction model, and outputting the probability of power failure of each load on the distribution line to be detected due to the wind and rain superposition disaster, specifically includes: Inputting the power distribution line to be detected into the line parameter extraction layer of the power failure probability prediction model, the line parameter extraction layer outputs the power distribution line to be detected and the damage resistance parameters of each load divided into stages; Input the damage resistance parameters of the distribution lines to be detected and each load at each stage, the typhoon parameters and the rainfall parameters into the analysis and judgment layer of the power outage probability prediction model, and the analysis and judgment layer outputs the probability of power outage of each load on the distribution lines to be detected; The inputting of the damage resistance parameters of the distribution lines to be detected and each load at each stage, the typhoon parameters and the rainfall parameters into the analysis and judgment layer of the power failure probability prediction model, and the analysis and judgment layer outputting the probability of power failure of each load on the distribution lines to be detected specifically includes: According to the distribution lines and loads to be detected in each stage, a correlation matrix between the line and load nodes of the distribution lines to be detected and the power supply nodes is constructed; wherein the power supply nodes include substations and load switch cabinets; According to the damage resistance parameters of the distribution lines to be detected at each stage and the typhoon parameters, the correlation matrix is ​​corrected to obtain the state result matrix of the distribution lines to be detected at each stage; After the state result matrix is ​​corrected according to the rainfall parameter, the state result of the distribution line to be detected in each stage under the condition of wind and rain is obtained; According to the state result and the anti-damage capability parameter analysis of each load, the probability of power failure of each load on the distribution line to be detected is obtained.

2. The method for predicting load power failure probability under wind and rain combined disasters according to claim 1 is characterized in that: The obtaining of typhoon parameters and rainfall parameters under the disaster of wind and rain superposition specifically includes: The structural parameters and rainfall intensity of a typhoon under the combined disaster of wind and rain are obtained; wherein the structural parameters include: the typhoon's landing position, moving direction, moving speed, maximum speed and maximum wind circle radius.

3. The method for predicting load power failure probability under wind and rain combined disasters according to claim 1 is characterized in that: The line parameter extraction layer outputs the damage resistance parameters of the distribution line to be detected and each load divided by stages, specifically including: Decomposing the distribution line to be detected according to the set stages, and obtaining the wind resistance level of the distribution line to be detected in each stage respectively; The information of the substation and the load switch cabinet connected to the load on the distribution line to be detected is obtained, and the rain protection level of each substation and load switch cabinet is obtained respectively.

4. The method for predicting load power failure probability under wind and rain combined disasters according to claim 1 is characterized in that: After the power failure probability prediction model outputs the probability of power failure of each load on the distribution line to be detected due to the wind and rain superposition disaster, the method further includes: The probability of power failure of each load on the distribution line to be detected is compared with a preset threshold value, and the load with a probability greater than the threshold value is determined as a load prone to power failure.

5. A load power failure probability prediction system under wind and rain combined disasters, the load power failure probability prediction system is applied to the load power failure probability prediction method according to any one of claims 1 to 4, characterized in that: include: An acquisition module is used to obtain typhoon parameters and rainfall parameters under the disaster of wind and rain superposition; and A prediction module, used to input the typhoon parameters, rainfall parameters and the distribution line to be detected into a power failure probability prediction model, and output the probability of power failure of each load on the distribution line to be detected caused by the wind and rain superposition disaster; The power outage probability prediction model is obtained by correcting the constructed load power outage probability result matrix caused by typhoons through rainfall parameter samples.

6. An electronic device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the method for predicting the probability of load power failure under the combined disaster of wind and rain as described in any one of claims 1 to 4 are implemented.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for predicting the probability of load power failure under the combined disaster of wind and rain as claimed in any one of claims 1 to 4 are implemented.

8. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method for predicting the probability of load power failure under the combined disaster of wind and rain as claimed in any one of claims 1 to 4 are implemented.

Images