A method and system for power grid security assessment based on weather conditions

Abstract

The application discloses a kind of power grid safety evaluation method and system based on meteorological condition, it is related to power grid safety planning technical field, by collecting the historical operation data of power grid;Using pre-training artificial neural network to calculate the power flow distribution corresponding to each single fault, obtain the total expected power supply shortage of the power grid;According to historical operation data, the failure rate of the power grid, equipment repair speed and load demand probability are analyzed, and then the risk assessment model of the power grid is established;In the process of power grid operation, input real-time power grid operation data into the risk assessment model, obtain the risk value for evaluating the safety of power grid.Using the embodiment of the application, the operation risk and reliability of power grid under typhoon and heavy rain meteorological conditions can be quickly and effectively evaluated, so as to help power grid dispatchers to take appropriate preventive and control measures, and ensure the stable operation of power system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power grid safety planning, in particular to a power grid safety evaluation method and system based on meteorological conditions. BACKGROUND

[0002] Frequent natural disasters have a non-negligible impact on the normal operation of the power system. Risk assessment plays a key role in the operation of the power grid, helping the dispatching personnel of the power grid to fully understand and master the level of risk and its trend in the operation of the power grid.

[0003] The existing risk assessment methods often do not fully utilize the key features in the data, which may lead to the selection of features irrelevant or redundant to the safety evaluation of the power grid. This not only reduces the accuracy of model evaluation, but also increases the problems of computational complexity and feature dimension. SUMMARY

[0004] The technical problem to be solved by the present application is how to improve the stability of the power system under extreme weather conditions. The present application provides a power grid safety evaluation method and system suitable for extreme weather conditions, which can quickly and accurately evaluate the risk of the power system under extreme weather conditions, and combines the power flow distribution to ensure the reliability and safety of power supply.

[0005] To solve the above technical problems, the present application provides a power grid safety evaluation method based on meteorological conditions, comprising:

[0006] Collecting historical operation data of the power grid; the historical operation data includes load demand, fault condition and meteorological condition;

[0007] Using a pre-trained artificial neural network to calculate the power flow distribution corresponding to each single fault, to obtain the total expected power supply shortage of the power grid;

[0008] According to the fault condition and the meteorological condition, the failure rate of the power grid is obtained;

[0009] Obtaining the rated wind speed and the key wind speed parameter, and combining the meteorological condition to obtain the equipment repair speed;

[0010] According to the load demand, the total load of each node of the power grid at time t is expressed as a normal distribution, and the load demand probability is calculated;

[0011] According to the total expected power supply shortage, the failure rate, the equipment repair speed and the load demand probability, a risk assessment model of the power grid is established;

[0012] The real-time power grid operation data is input into the risk assessment model to obtain the risk value for evaluating the safety of the power grid.

[0013] As an improvement of the above scheme, the pre-trained artificial neural network is used to calculate the power flow distribution corresponding to each single fault, and the total expected power supply shortage of the power grid is obtained, comprising:

[0014] The pre-trained artificial neural network is used to simulate the single fault of the power grid, and the optimal power flow under the single fault is obtained;

[0015] According to the optimal power flow, the node expected power supply shortage of each node of the power grid and the number of load reduction nodes are obtained;

[0016] By The total expected power supply shortage of the power grid corresponding to each single fault is calculated; wherein G i is the node expected power supply shortage of node i; N s is the total number of nodes of the power grid; D s is the number of load reduction nodes.

[0017] As an improvement of the above scheme, the fault rate of the power grid is obtained according to the fault condition and the meteorological condition, comprising:

[0018] According to the fault condition, the random probability of fault occurrence under general meteorological conditions is modeled by using HPP distribution, and the first fault rate of the power grid under general meteorological conditions is obtained;

[0019] The key wind speed is obtained from the meteorological condition, and the second fault rate of the power grid under the first extreme meteorological condition is calculated in combination with the fault condition;

[0020] The lightning ground flash density is obtained from the meteorological condition, and the third fault rate of the power grid under the second extreme meteorological condition is calculated in combination with the fault condition;

[0021] The fault rate of the power grid is obtained according to the first fault rate, the second fault rate and the third fault rate.

[0022] As an improvement of the above scheme, the first fault rate of the power grid under general meteorological conditions is obtained according to the fault condition by using HPP distribution to model the random probability of fault occurrence under general meteorological conditions, comprising:

[0023] According to the fault condition, the fault times per kilometer line in a preset time period are obtained;

[0024] By The random probability of fault occurrence under general meteorological conditions is modeled; wherein C f (t) is the fault times per kilometer line in time t; k is the kth fault; ξ n is the first fault rate of the power grid under general meteorological conditions.

[0025] As an improvement to the above scheme, the step of obtaining the key wind speed from the meteorological conditions and calculating the second failure rate of the power grid under the first extreme meteorological conditions, in conjunction with the fault situation, includes:

[0026] The key wind speed is obtained from the meteorological conditions. When the key wind speed is greater than the preset wind speed threshold, it is determined to be the first extreme meteorological condition.

[0027] Through W w (t)=W c (t)+Δ w (t) Calculate the wind speed intensity within time t under the first extreme weather conditions;

[0028] pass Calculate the second failure rate of the power grid under the first extreme weather conditions;

[0029] Where, ξ n The first failure rate of the power grid under normal meteorological conditions; W c (t) represents the critical wind speed; Δ w (t) represents the preset key wind speed random threshold; W w (t) represents the wind speed intensity within time t under the first extreme weather condition; a w This is the adjustment coefficient for the second failure rate.

[0030] As an improvement to the above scheme, the step of obtaining the lightning flash density from the meteorological conditions and calculating the third failure rate of the power grid under the second extreme meteorological conditions, in conjunction with the fault situation, includes:

[0031] The lightning density is obtained from the meteorological conditions. When the lightning density is greater than a preset lightning density threshold, it is determined to be a second extreme meteorological condition. The change in the lightning density follows a logarithmic distribution.

[0032] Through ξ lg (C g (t))=ξ n β1C g (t) Calculate the third failure rate of the power grid under the second extreme weather conditions; where, ξ n β1 is the first failure rate of the power grid under normal meteorological conditions; C is a preset parameter. g (t) represents the ground flash density.

[0033] As an improvement to the above solution, the step of obtaining the rated wind speed and key wind speed parameters, and combining them with the meteorological conditions to determine the equipment repair speed, includes:

[0034] When the meteorological conditions are general and the wind speed intensity is not less than the preset wind speed intensity threshold, by The repair speed of the computing device;

[0035] When the weather condition is an extreme weather condition and the wind speed intensity is less than a preset wind speed intensity threshold, by The repair speed of the computing device;

[0036] When the weather condition is an extreme weather condition and the wind speed intensity is not less than a preset wind speed intensity threshold, by The repair speed of the computing device;

[0037] Wherein, v n is a preset rated wind speed; η is a preset first positive parameter; W w (t) is the wind speed intensity; W c (t) is the critical wind speed; ψ is a preset second positive parameter; N g is a preset extreme weather condition parameter.

[0038] As an improvement of the above scheme, the total load of each node of the power grid at time t is represented as a normal distribution according to the load demand, and the load demand probability is calculated, including:

[0039] According to the load demand, the total load of each node of the power grid at time t is represented as a normal distribution, and the normal distribution parameters are obtained;

[0040] The load demand probability is calculated by ; wherein, μ is the mean of the total load; σ is the standard deviation of the total load; θ is the normal distribution parameter.

[0041] As an improvement of the above scheme, the risk assessment model of the power grid is established according to the total expected power shortage, the failure rate, the device repair speed and the load demand probability, including:

[0042] The unit output of the power grid is calculated by P g = α (E, v, G) + β (ξ);

[0043] The load reduction of the power grid is calculated by P c = γ (E, v, G) + ε (ξ);

[0044] The risk assessment model of the power grid is established by F = minf (P g , P c );

[0045] Wherein, E is the total expected power shortage; v is the device repair speed; G is the load demand probability; ξ is the failure rate; α and ε are preset positive parameters; β and γ are preset negative parameters.

[0046] The embodiment of the present application also provides a power grid safety evaluation system based on meteorological conditions, comprising:

[0047] a historical operation data acquisition module for acquiring historical operation data of the power grid, wherein the historical operation data comprises load demand, fault condition and meteorological condition;

[0048] a total expected power supply shortage amount calculation module for calculating a power flow distribution corresponding to each single fault by using a pre-trained artificial neural network to obtain a total expected power supply shortage amount of the power grid;

[0049] a fault rate calculation module for obtaining a fault rate of the power grid according to the fault condition and the meteorological condition;

[0050] a device repair speed calculation module for obtaining a rated wind speed and a key wind speed parameter, and combining the meteorological condition to obtain a device repair speed;

[0051] a load demand probability calculation module for representing total load of each node of the power grid at time t as a normal distribution according to the load demand to calculate a load demand probability;

[0052] a model establishment module for establishing a risk evaluation model of the power grid according to the total expected power supply shortage amount, the fault rate, the device repair speed and the load demand probability;

[0053] a safety evaluation module for inputting real-time power grid operation data into the risk evaluation model to obtain a risk value for evaluating power grid safety.

[0054] Compared with the prior art, the power grid safety evaluation method and system based on meteorological conditions disclosed by the present application can acquire historical operation data of the power grid, wherein the historical operation data comprises load demand, fault condition and meteorological condition; calculate a power flow distribution corresponding to each single fault by using a pre-trained artificial neural network to obtain a total expected power supply shortage amount of the power grid; obtain a fault rate of the power grid according to the fault condition and the meteorological condition; obtain a rated wind speed and a key wind speed parameter, and combine the meteorological condition to obtain a device repair speed; represent total load of each node of the power grid at time t as a normal distribution according to the load demand to calculate a load demand probability; establish a risk evaluation model of the power grid according to the total expected power supply shortage amount, the fault rate, the device repair speed and the load demand probability; and input real-time power grid operation data into the risk evaluation model to obtain a risk value for evaluating power grid safety. By using the embodiment of the present application, the operation risk and reliability of the power grid under typhoon and heavy rainfall meteorological conditions can be quickly and effectively evaluated, thereby helping power grid dispatchers to take appropriate prevention and control measures to ensure stable operation of the power system. BRIEF DESCRIPTION OF DRAWINGS

[0055] Figure 1 is a step flow schematic diagram of a power grid safety evaluation method based on weather conditions provided by an embodiment of the present application.

[0056] Figure 2 is a structural schematic diagram of a power grid safety evaluation system based on weather conditions provided by an embodiment of the present application. DETAILED DESCRIPTION

[0057] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0058] In the description and claims of the specification, it is to be understood that the terms first, second, etc. are used only for the purpose of description and are not to be construed as indicating or implying relative importance or an indicated number of features. They are not necessarily used to describe a sequence or an order, unless explicitly stated otherwise. The terms are interchangeable under appropriate circumstances. Thus, a feature described as“first” can be described as“second” or vice versa, without departing from the scope of the present application.

[0059] The embodiments of the present application provide a power grid safety evaluation method based on weather conditions. Please refer to Figure 1 In the present embodiment, the power grid safety evaluation method based on weather conditions is specifically executed through steps S1 to S7:

[0060] S1, collecting historical operation data of a power grid; the historical operation data includes load demand, fault condition and weather condition.

[0061] S2, calculating a power flow distribution corresponding to each single fault by using a pre-trained artificial neural network, to obtain a total expected power supply shortage of the power grid.

[0062] It should be noted that the expected power supply shortage is an expected value for measuring the reduction of load demand of a power system due to insufficient power generation capacity or grid restriction in a specific time period. In the present embodiment, the total expected power supply shortage is used to reflect the resilience of the power grid.

[0063] In the present embodiment, the pre-trained artificial neural network can quickly realize the expected calculation and reduce the solution time.

[0064] S3, obtaining a failure rate of the power grid according to the fault condition and the weather condition.

[0065] It should be noted that the fault conditions corresponding to different weather conditions are different, and the faults under general weather conditions mainly include events with low correlation with weather conditions, such as natural aging of equipment and equipment failure. The faults under extreme weather conditions involve problems that may occur under severe weather conditions, such as breakdown of insulating medium and damage of equipment caused by excessive wind speed. The failure rate in the embodiment of the present application comprehensively considers the influence of general weather condition failure mode and extreme weather condition failure mode.

[0066] S4, obtaining rated wind speed and key wind speed parameters, combining the weather conditions to obtain the equipment repair speed.

[0067] In the embodiment of the present application, it is assumed that the fault repair personnel can arrive at the fault point in time to perform the repair task, the network can reach the normal operation level after the fault line is repaired, and the fault time is extremely short compared with the repair time and can be ignored.

[0068] S5, according to the load demand, the total load of each node of the power grid at time t is expressed as a normal distribution, and the load demand probability is calculated.

[0069] It should be noted that the load demand changes with time and space scale, and is a physical quantity associated with the two-dimensional characteristics of time and space. A random model can be used to explain the time correlation.

[0070] S6, according to the total expected power supply shortage, the failure rate, the equipment repair speed and the load demand probability, a risk assessment model of the power grid is established.

[0071] S7, inputting real-time power grid operation data into the risk assessment model to obtain a risk value for evaluating the safety of the power grid.

[0072] The risk value can represent the risk level of the power grid under each weather condition, thereby guiding the power grid dispatcher to take corresponding power grid scheduling strategies for power grid scheduling. Exemplarily, the power grid scheduling strategies include increasing standby capacity, optimizing line layout, reducing power supply pressure, etc.

[0073] In the above scheme, the total expected power supply shortage, the failure rate, the equipment repair speed and the load demand probability are comprehensively considered, which can quickly and effectively evaluate the operation risk and reliability of the power grid under typhoon and heavy rain weather conditions, thereby helping the power grid dispatcher to take appropriate prevention and control measures to ensure the stable operation of the power system.

[0074] As a preferred embodiment, step S2, a pre-trained artificial neural network is used to calculate the power flow distribution corresponding to each single fault to obtain the total expected power supply shortage of the power grid, including:

[0075] simulate a single fault of the power grid by using the pre-trained artificial neural network to obtain an optimal power flow under the single fault;

[0076] obtain a node expected power shortage and a number of load shedding nodes of each node of the power grid according to the optimal power flow;

[0077] by calculate a total expected power shortage of the power grid corresponding to each single fault; wherein G i is the node expected power shortage of node i; N s is the total number of nodes of the power grid; D s is the number of load shedding nodes.

[0078] Exemplarily, the pre-trained artificial neural network comprises an input layer, at least one hidden layer and an output layer. The input layer, the hidden layer and the output layer each comprise a plurality of artificial neurons, each neuron being linked to neurons of its adjacent layer through a weighted relationship. That is, in each neuron, the input is first weighted and then summed.

[0079] It also needs to be explained that after a fault occurs at a certain node, the change of network power flow can cause a whole network fault, and the problem of system power flow distribution is not considered in the prior art. In the embodiment of the present application, multiple simulations are performed and multiple optimal power flows are solved within a simulation time T, and each power flow assumes one kind of fault. Generally, the time required to solve the optimal power flow is closely related to the network structure, and the solving time can be shortened by using a corresponding parallel solving strategy. However, the optimization problem cannot be linearized at the same time and needs to be solved multiple times, which is time-consuming. The pre-trained artificial neural network of the embodiment of the present application can effectively shorten the expected calculation time, and can evaluate the reliability of the power grid under extreme weather conditions through multiple simulations and optimal power flow solving.

[0080] As a preferred embodiment, step S3 obtains a fault rate of the power grid according to the fault condition and the weather condition, specifically by performing steps S31 to S34:

[0081] S31, according to the fault condition, uses HPP distribution to model the random probability of fault occurrence under general weather conditions to obtain a first fault rate of the power grid under general weather conditions.

[0082] Since under general weather conditions, the occurrence of power grid faults is usually not closely related to weather conditions, and is generally natural aging of equipment or other natural faults, etc., in the embodiment of the present application, the random probability of fault occurrence under general weather conditions is simulated by using HPP (Homogeneous Poisson Process) distribution.

[0083] It should be noted that the random probability of the occurrence of the fault under the extreme meteorological condition is simulated by a NHPP (Non-Homogeneous Poisson Process) distribution.

[0084] S32, obtaining a critical wind speed from the meteorological condition, and calculating a second fault rate of the power grid under a first extreme meteorological condition in combination with the fault condition.

[0085] It can be understood that, under the typhoon condition, the critical wind speed is inconsistent with that under the general meteorological condition, and generally, the wind speed is higher and has a relatively regular change trend, etc. By obtaining the critical wind speed and the fault condition, the second fault rate of the power grid under the typhoon extreme meteorological condition can be obtained, and subsequently, the fault under the typhoon meteorological condition can be analyzed according to the real-time operation data through the second fault rate.

[0086] S33, obtaining a ground flash density of lightning from the meteorological condition, and calculating a third fault rate of the power grid under a second extreme meteorological condition in combination with the fault condition.

[0087] It can be understood that the lightning has a great influence on the line, and the heavy rain is usually accompanied by lightning. In the embodiment of the present application, the intensity of lightning is represented by the ground flash density of lightning, and subsequently, the fault under the heavy rain or thunderstorm meteorological condition can be analyzed according to the real-time operation data through the third fault rate.

[0088] S34, obtaining a fault rate of the power grid according to the first fault rate, the second fault rate and the third fault rate.

[0089] The level of wind speed can directly or indirectly affect the stability of the equipment, and the lightning activity can directly affect the insulation level of the equipment. The typhoon and the heavy rain accompanied by the thunderstorm condition can cause great safety threat to the power grid line, and in the embodiment of the present application, the fault rate under the extreme meteorological condition of the typhoon and the heavy rain is mainly analyzed.

[0090] Further, in some embodiments, the step S31 comprises:

[0091] obtaining the number of faults per kilometer of line in a preset time period according to the fault condition;

[0092] by modeling the random probability of the occurrence of the fault under the general meteorological condition; wherein C f (t) is the number of faults per kilometer of line in time t; k is the kth fault; ξ n is a first fault rate of the power grid under the general meteorological condition.

[0093] Exemplarily, the occurrence of the extreme meteorological condition is represented by the NHPP distribution, and specifically, the occurrence of the extreme meteorological condition is represented by the NHPP distribution modeling a random probability of occurrence of a failure under an extreme weather condition; wherein k is the kth failure; V e t is a time-independent occurrence rate of the extreme weather condition; V e (t') is a time-dependent occurrence rate of the extreme weather condition.

[0094] Preferably, in some embodiments, step S32 comprises:

[0095] obtaining a critical wind speed from the weather condition, and determining that the first extreme weather condition exists when the critical wind speed is greater than a preset wind speed threshold;

[0096] calculating a wind speed intensity at time t under the first extreme weather condition by W w (t) = W c (t) + Δ w (t).

[0097] calculating a second failure rate of the power grid under the first extreme weather condition by

[0098] wherein ξ n is the first failure rate of the power grid under a general weather condition; W c (t) is a critical wind speed; Δ w (t) is a preset critical wind speed random threshold; W w (t) is the wind speed intensity at time t under the first extreme weather condition; a w is an adjustment coefficient of the second failure rate.

[0099] It should be noted that by adjusting the adjustment coefficient a w , the second failure rate can be more accurately calculated in the case where the wind speed is greater than the critical wind speed W c (t).

[0100] As a preferred embodiment, step S33 comprises:

[0101] obtaining a ground flash density of lightning from the weather condition, and determining that the second extreme weather condition exists when the ground flash density is greater than a preset ground flash density threshold; the ground flash density changes according to a logarithmic distribution;

[0102] calculating a third failure rate of the power grid under the second extreme weather condition by ξ lg (C g (t)) = ξ n β1C g (t). n wherein ξ g ​(t) is the ground flash density.

[0103] The ground flash density is the number of ground strikes in a certain time unit and area, which varies according to a logarithmic distribution. The specific value of the parameter of the logarithmic distribution is obtained according to historical operation data. In the embodiment of the present application, the lightning intensity is represented by the ground flash density.

[0104] Preferably, in some embodiments, step S4, obtaining the rated wind speed and the critical wind speed parameter, in combination with the meteorological condition, obtains the equipment repair speed, including:

[0105] When the meteorological condition is a general meteorological condition and the wind speed intensity is not less than a preset wind speed intensity threshold, the equipment repair speed is calculated by .

[0106] When the meteorological condition is an extreme meteorological condition and the wind speed intensity is less than a preset wind speed intensity threshold, the equipment repair speed is calculated by .

[0107] When the meteorological condition is an extreme meteorological condition and the wind speed intensity is not less than a preset wind speed intensity threshold, the equipment repair speed is calculated by .

[0108] Wherein, v n is a preset rated wind speed; η is a preset first positive parameter; W w (t) is the wind speed intensity; W c (t) is the critical wind speed; ψ is a preset second positive parameter; N g is a preset extreme meteorological condition parameter.

[0109] It should be noted that the extreme meteorological condition parameter can be determined according to the specific parameters of the extreme meteorological condition. For example, in the case of a typhoon, if the wind speed intensity is within a preset first threshold range, it is considered that N g = 0.2; if the wind speed intensity is within a preset second threshold range, it is considered that N g = 0.4.

[0110] It should also be noted that in the embodiment of the present application, when the meteorological condition is a general meteorological condition, it is considered that N g = 0.

[0111] As a preferred implementation, step S5, according to the load demand, represents the total load of each node of the power grid at time t as a normal distribution, and calculates the load demand probability, including:

[0112] According to the load demand, the total load of each node of the power grid at time t is represented as a normal distribution, and the normal distribution parameters are obtained;

[0113] by calculating load demand probability; wherein, μ is the mean of total load; σ is the standard deviation of total load; θ is the parameter of normal distribution.

[0114] It should be noted that the load demand varies with time and space scale, and is a physical quantity associated with the characteristics of two-dimensional space-time, and the random model of load can be used to explain the time correlation.

[0115] As a preferred embodiment, step S6, according to the total expected power shortage, the failure rate, the equipment repair speed and the load demand probability, establishes the risk assessment model of the power grid, comprising:

[0116] calculating the unit output of the power grid by P g = α (E, v, G) + β (ξ) ;

[0117] calculating the load reduction of the power grid by P c = γ (E, v, G) + ε (ξ) ;

[0118] establishing the risk assessment model of the power grid by F = min f (P g , P c ) ;

[0119] wherein, E is the total expected power shortage; v is the equipment repair speed; G is the load demand probability; ξ is the failure rate; α and ε are preset positive parameters; β and γ are preset negative parameters.

[0120] It should be noted that under extreme weather conditions, according to the risk assessment model, when the unit output P g increases, the power grid is more likely to meet the load reduction P c , which can reduce the risk of overload and failure, thereby reducing the failure rate; and when the load reduction P c decreases, the power supply pressure of the power grid is reduced, which can also reduce the failure rate. Those skilled in the art can perform power grid dispatching based on the above idea.

[0121] The power grid safety evaluation method based on weather conditions provided by the embodiment of the present application can quickly and accurately evaluate the risk of the power system under extreme weather conditions, and combines the power flow distribution to ensure the reliability and safety of power supply.

[0122] Please refer to Figure 2The embodiment of the present application provides a kind of based on meteorological condition's power grid safety evaluation system.The based on meteorological condition's power grid safety evaluation system includes historical operation data acquisition module 11, total expected power shortage quantity calculation module 12, failure rate calculation module 13, equipment repair speed calculation module 14, load demand probability calculation module 15, model establishment module 16 and safety evaluation module 17, wherein:

[0123] Historical operation data acquisition module 11 is used to collect the historical operation data of power grid;The historical operation data includes load demand, failure condition and meteorological condition;

[0124] Total expected power shortage quantity calculation module 12 is used to calculate the power flow distribution corresponding to each single failure by using pre-trained artificial neural network, to obtain the total expected power shortage quantity of the power grid;

[0125] Failure rate calculation module 13 is used to obtain the failure rate of the power grid according to the failure condition and the meteorological condition;

[0126] Equipment repair speed calculation module 14 is used to obtain rated wind speed and key wind speed parameters, and obtain equipment repair speed in combination with the meteorological condition;

[0127] Load demand probability calculation module 15 is used to express the total load of each node of power grid at time t as normal distribution according to the load demand, and calculate load demand probability;

[0128] Model establishment module 16 is used to establish the risk assessment model of the power grid according to the total expected power shortage quantity, the failure rate, the equipment repair speed and the load demand probability;

[0129] Safety evaluation module 17 is used to input real-time power grid operation data into the risk assessment model to obtain risk value for evaluating power grid safety.

[0130] As a preferred embodiment, the total expected power shortage quantity calculation module 12 comprises:

[0131] Failure simulation unit is used to simulate single failure of the power grid by using pre-trained artificial neural network to obtain optimal power flow under the single failure;

[0132] Node power flow solving unit is used to obtain node expected power shortage quantity and number of load reduction nodes of each node of power grid according to the optimal power flow;

[0133] Expected calculation unit is used to calculate total expected power shortage quantity of the power grid corresponding to each single failure by Wherein, G i Is the node expected power shortage quantity of node i;N sis the total number of nodes of the power grid; D s is the number of load nodes.

[0134] As a preferred implementation, the failure rate calculation module 13 comprises:

[0135] a first failure rate calculation unit, configured to model a random probability of occurrence of a failure under general weather conditions according to the failure condition by using a HPP distribution, to obtain a first failure rate of the power grid under general weather conditions;

[0136] a second failure rate calculation unit, configured to obtain a critical wind speed from the weather condition, and calculate a second failure rate of the power grid under first extreme weather conditions in combination with the failure condition;

[0137] a third failure rate calculation unit, configured to obtain a lightning ground flash density from the weather condition, and calculate a third failure rate of the power grid under second extreme weather conditions in combination with the failure condition;

[0138] a failure rate calculation unit, configured to obtain a failure rate of the power grid according to the first failure rate, the second failure rate and the third failure rate.

[0139] Further, preferably, the first failure rate calculation unit is specifically configured to:

[0140] obtain a number of failures per kilometer of line in a preset time period according to the failure condition;

[0141] by modeling a random probability of occurrence of a failure under general weather conditions; wherein C f (t) is the number of failures per kilometer of line in time t; k is the kth failure; ξ n is the first failure rate of the power grid under general weather conditions.

[0142] Preferably, the second failure rate calculation unit is specifically configured to:

[0143] obtain a critical wind speed from the weather condition, and determine that it is first extreme weather conditions when the critical wind speed is greater than a preset wind speed threshold;

[0144] by W w (t) = W c (t) + Δ w (t) calculating a wind speed intensity in time t under first extreme weather conditions;

[0145] by calculating a second failure rate of the power grid under first extreme weather conditions;

[0146] wherein ξn is the first failure rate of the power grid under general weather conditions; W c (t) is a critical wind speed; Δ w (t) is a preset critical wind speed random threshold; W w (t) is a wind speed intensity at time t under the first extreme weather condition; a w is an adjustment coefficient of the second failure rate.

[0147] In some preferred embodiments, the third failure rate calculation unit is specifically configured to:

[0148] obtain a ground flash density of lightning from the weather condition, and determine that the weather condition is a second extreme weather condition when the ground flash density is greater than a preset ground flash density threshold; the ground flash density changes in accordance with a logarithmic distribution;

[0149] by ξ lg (C g (t)) = ξ n β1C g (t) calculates a third failure rate of the power grid under the second extreme weather condition; wherein, ξ n is the first failure rate of the power grid under general weather conditions; β1 is a preset parameter; C g (t) is the ground flash density.

[0150] Preferably, the equipment repair speed calculation module 14 comprises:

[0151] a first case calculation unit configured to calculate the equipment repair speed by when the weather condition is a general weather condition and a wind speed intensity is not less than a preset wind speed intensity threshold;

[0152] a second case calculation unit configured to calculate the equipment repair speed by when the weather condition is an extreme weather condition and the wind speed intensity is less than the preset wind speed intensity threshold;

[0153] a third case calculation unit configured to calculate the equipment repair speed by when the weather condition is an extreme weather condition and the wind speed intensity is not less than the preset wind speed intensity threshold;

[0154] wherein, v n is a preset rated wind speed; η is a preset first positive parameter; W w (t) is the wind speed intensity; W c (t) is the critical wind speed; ψ is a preset second positive parameter; N g is a preset extreme weather condition parameter.

[0155] As a preferred implementation, the load demand probability calculation module 15 comprises:

[0156] a normal distribution parameter calculation unit, configured to represent the total load of each node of the power grid at time t as a normal distribution according to the load demand, to obtain a normal distribution parameter;

[0157] a load demand probability calculation unit, configured to calculate a load demand probability by ; wherein, μ is the mean of the total load; σ is the standard deviation of the total load; and θ is the normal distribution parameter.

[0158] Preferably, the model establishment module 16 comprises:

[0159] a unit commitment calculation unit, configured to calculate the unit commitment of the power grid by P g = α (E, v, G) + β (ξ) ;

[0160] a load shedding calculation unit, configured to calculate the load shedding of the power grid by P c = γ (E, v, G) + ε (ξ) ;

[0161] a risk assessment model establishment unit, configured to establish a risk assessment model of the power grid by F = min f (P g , P c ) ;

[0162] ; wherein, E is the total expected power supply shortage; v is the equipment repair speed; G is the load demand probability; ξ is the failure rate; α and ε are preset positive parameters; and β and γ are preset negative parameters.

[0163] The power grid safety assessment system based on meteorological conditions provided by the embodiments of the present application can quickly and accurately assess the risk of the power system under extreme meteorological conditions, and combines the power system flow distribution to ensure the reliability and safety of power supply.

[0164] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by a computer program instructing related hardware, and the program can be stored in a computer readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. The storage medium can be a magnetic disc, an optical disc, a read-only memory (ROM) or a random access memory (RAM) and the like.

[0165] The above is the preferred embodiment of the present application, it should be pointed out that, for those skilled in the art, without departing from the principles of the present application, can also make a number of improvements and refinements, these improvements and refinements are also considered to be within the scope of the present application.

Claims

1. A power grid security assessment method based on meteorological conditions, characterized in that, include: Collect historical operating data of the power grid; the historical operating data includes load demand, fault conditions, and weather conditions. A pre-trained artificial neural network is used to calculate the power flow distribution corresponding to each individual fault, thereby obtaining the total expected power shortage of the power grid. Based on the fault conditions and the meteorological conditions, the failure rate of the power grid is obtained; Obtain the rated wind speed and key wind speed parameters, and combine them with the meteorological conditions to determine the equipment repair speed; Based on the load demand, the total load of each node in the power grid at time t is represented as a normal distribution, and the load demand probability is calculated. A risk assessment model for the power grid is established based on the total expected power shortage, the failure rate, the equipment repair speed, and the load demand probability. Real-time power grid operation data is input into the risk assessment model to obtain risk values ​​used to assess power grid security; The method of using a pre-trained artificial neural network to calculate the power flow distribution corresponding to each individual fault, and obtaining the total expected power shortage of the power grid, includes: A pre-trained artificial neural network is used to simulate a single fault in the power grid to obtain the optimal power flow under the single fault. Based on the optimal power flow, the expected power shortage at each node of the power grid and the number of nodes to reduce load are obtained; pass Calculate the total expected power shortage of the power grid corresponding to each individual fault; where G i Let N be the expected power shortage of node i; s D is the total number of nodes in the power grid; s To reduce the number of load nodes; The step of obtaining the power grid failure rate based on the fault conditions and the weather conditions includes: Based on the aforementioned fault conditions, the HPP distribution is used to model the random probability of fault occurrence under general weather conditions, thereby obtaining the first fault rate of the power grid under general weather conditions. The key wind speed is obtained from the meteorological conditions, and the second failure rate of the power grid under the first extreme meteorological conditions is calculated in combination with the fault conditions. The lightning ground flash density is obtained from the meteorological conditions, and the third failure rate of the power grid under the second extreme meteorological conditions is calculated in combination with the fault conditions. The failure rate of the power grid is obtained based on the first failure rate, the second failure rate, and the third failure rate. Based on the fault conditions, the HPP distribution is used to model the random probability of fault occurrence under general weather conditions to obtain the first fault rate of the power grid under general weather conditions, including: Based on the fault conditions, the number of faults per kilometer of line within a preset time period is obtained; pass Modeling the random probability of fault occurrence under general meteorological conditions; where C f (t) represents the number of faults per kilometer of line within time t; k represents the kth fault; ξ n This represents the first failure rate of the power grid under normal weather conditions. The step of obtaining the key wind speed from the meteorological conditions and calculating the second failure rate of the power grid under the first extreme meteorological conditions, in conjunction with the fault situation, includes: The key wind speed is obtained from the meteorological conditions. When the key wind speed is greater than the preset wind speed threshold, it is determined to be the first extreme meteorological condition. Through W w (t)=W c (t)+Δ w (t) Calculate the wind speed intensity within time t under the first extreme weather conditions; pass Calculate the second failure rate of the power grid under the first extreme weather conditions; Where, ξ n The first failure rate of the power grid under normal meteorological conditions; W c (t) represents the critical wind speed; Δ w (t) represents the preset key wind speed random threshold; W w (t) represents the wind speed intensity within time t under the first extreme weather condition; a w This is the adjustment coefficient for the second failure rate; The step of obtaining the lightning strike density from the meteorological conditions and, in conjunction with the fault situation, calculating the third fault rate of the power grid under the second extreme meteorological conditions includes: The lightning density is obtained from the meteorological conditions. When the lightning density is greater than a preset lightning density threshold, it is determined to be a second extreme meteorological condition. The change in the lightning density follows a logarithmic distribution. Through ξ lg (C g (t))=ξ n β1C g (t) Calculate the third failure rate of the power grid under the second extreme weather conditions; where, ξ n β1 is the first failure rate of the power grid under normal meteorological conditions; C is a preset parameter. g (t) represents the ground flash density; The process of obtaining the rated wind speed and key wind speed parameters, and combining them with the meteorological conditions to determine the equipment repair speed, includes: When the meteorological conditions are general and the wind speed intensity is not less than the preset wind speed intensity threshold, by Calculate the equipment repair speed; When the meteorological conditions are extreme and the wind speed intensity is less than a preset wind speed intensity threshold, by Calculate the equipment repair speed; When the meteorological conditions are extreme and the wind speed intensity is not less than a preset wind speed intensity threshold, by Calculate the equipment repair speed; Among them, v n η is the preset rated wind speed; η is the preset first positive parameter; W w (t) represents wind speed intensity; W c (t) represents the critical wind speed; ψ is the preset second positive parameter; N g These are preset parameters for extreme weather conditions; The step of representing the total load of each node in the power grid at time t as a normal distribution based on the load demand and calculating the load demand probability includes: Based on the load demand, the total load of each node in the power grid at time t is represented as a normal distribution, and the normal distribution parameters are obtained. pass Calculate the load demand probability; where μ is the mean of the total load; σ is the standard deviation of the total load; and θ is the normal distribution parameter. The risk assessment model for the power grid, established based on the total expected power shortage, the failure rate, the equipment repair speed, and the load demand probability, includes: Through P g =α(E,v,G)+β(ξ) calculates the unit output of the power grid; Through P c =γ(E,v,G)+ε(ξ) calculates the load reduction of the power grid; By F = minf(P) g ,P c Establish a risk assessment model for the power grid; Where E is the total expected power shortage; v is the equipment repair speed; G is the load demand probability; ξ is the failure rate; α and ε are preset positive parameters; β and γ are preset negative parameters.

2. A power grid security assessment system based on meteorological conditions, characterized in that, For executing the power grid security assessment method based on meteorological conditions as described in claim 1, the power grid security assessment system based on meteorological conditions comprises: The historical operation data acquisition module is used to collect historical operation data of the power grid; the historical operation data includes load demand, fault conditions and weather conditions. The total expected power shortage calculation module is used to calculate the power flow distribution corresponding to each individual fault using a pre-trained artificial neural network, so as to obtain the total expected power shortage of the power grid. The failure rate calculation module is used to obtain the failure rate of the power grid based on the failure situation and the meteorological conditions. The equipment repair speed calculation module is used to obtain the rated wind speed and key wind speed parameters, and combine them with the meteorological conditions to obtain the equipment repair speed. The load demand probability calculation module is used to calculate the load demand probability by representing the total load of each node of the power grid at time t as a normal distribution based on the load demand. The model building module is used to build a risk assessment model for the power grid based on the total expected power shortage, the failure rate, the equipment repair speed, and the load demand probability. The safety assessment module is used to input real-time power grid operation data into the risk assessment model to obtain risk values ​​for assessing power grid safety.

Images