Urban power distribution network overcharge load space-time situation prediction method under heavy rainfall weather

Abstract

The invention discloses an urban power distribution network overcharge space-time situation prediction method under heavy rainfall weather. The method comprises the following steps: S1, constructing an electrical performance failure probability model under surface ponding depth, rainfall intensity and time history change; s2, constructing an overcharge load space-time transfer matrix model considering the availability of the overcharge pile and the charging risk avoiding behavior of the user under the driving of the rainfall intensity time history; s3, dividing a charging radiation area by taking the overcharge station as a node, mapping rainfall intensity and time history data to the charging radiation area node, and obtaining an overcharge pile operation state characteristic, a rainfall intensity characteristic and a traffic flow characteristic by combining a user electrical performance failure probability model and an overcharge load space-time transfer matrix model; and constructing an over-charge load dynamic association model based on time-space diagram modeling, and inputting the current over-charge pile operation state characteristics, the rainfall intensity characteristics and the traffic flow characteristics into the over-charge load dynamic association model to obtain a corresponding load prediction amount.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and particularly relates to a method for predicting the spatio-temporal situation of ultra-fast charging load in urban distribution networks under heavy rainfall weather. Background Art

[0002] In a new power system, the wide access of a high proportion of new energy promotes green and low-carbon development while challenging the flexible regulation ability on the power supply side, and the power system's supply-demand balance faces greater uncertainties. With the increasing penetration rate of electric vehicles in urban distribution networks, their charging loads show high randomness and unevenness in the spatio-temporal dimension. As a high-power centralized charging facility, an ultra-fast charging station can effectively meet the demand for rapid energy replenishment, but it also significantly increases the load management and regulation pressure on the distribution system. Ultra-fast charging loads have the characteristics of significant large power, fast change, strong concentration, and high dependence on user selection. Their spatio-temporal distribution is affected by the superposition of multiple factors such as travel behavior, traffic network operation status, and meteorological conditions, showing strong uncertainty and volatility. Especially under heavy rainfall weather conditions, the spatial distribution of ultra-fast charging loads will face more complex disturbing factors, such as charging facilities being unable to operate normally due to waterlogging, the reconstruction of charging paths caused by users' risk avoidance behaviors, and the instantaneous transfer and aggregation of loads in the spatial dimension. At the same time, factors such as the concentration of travel time periods during rainfall, traffic flow delays, and route adjustments further amplify the impact of load peaks on the distribution system, which may cause problems such as local overload, voltage fluctuations, and even over-limit, and may even induce feeder overload or equipment tripping in severe cases, affecting the safe and stable operation of the power grid.

[0003] Most existing research on electric vehicle load prediction focuses on slow charging and fast charging scenarios, and there are obvious technical gaps in the modeling of ultra-fast charging load situations under heavy rainfall conditions. Moreover, existing methods generally ignore the dual disturbances of rainfall type characteristics such as rainfall intensity and time course distribution on the flooding failure of ultra-fast charging piles and users' charging behaviors, and it is difficult to accurately depict complex phenomena such as path interruption, spatial aggregation, and load sudden change under heavy rainfall. There is a lack of collaborative prediction ability for the dynamic changes of ultra-fast charging loads and multi-factor coupling. Intermittent heavy rainfall is characterized by strong suddenness and uncertain duration, which is likely to cause rapid accumulation of surface water in a short time. And when the accumulated water is not completely drained during the intermittent period, it may repeatedly trigger sensor actions, putting the charging piles in a complex environment of alternating flooding and recovery. At the same time, traffic congestion, road closures, and reduced traffic efficiency caused by rainfall will significantly change the spatial accessibility of vehicles, easily triggering a dynamic charging behavior pattern of "rain avoidance - concentration - rain avoidance" for users, further exacerbating the load impact during the rainfall time course intermittent period and amplifying the emergency bearing pressure when the charging piles resume operation. Summary of the Invention

[0004] In view of this, the present invention provides a method for predicting the spatio-temporal situation of the overcharging load of urban distribution networks under heavy rainfall weather, so as to at least solve the problem that the existing methods for predicting the spatio-temporal situation of the overcharging load of urban distribution networks are difficult to be applicable to heavy rainfall weather conditions.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: A method for predicting the spatio-temporal situation of the overcharging load of urban distribution networks under heavy rainfall weather, comprising the following steps: S1. Based on the water accumulation evolution process under heavy rainfall scenarios, considering surface runoff and local drainage capacity, dynamically simulate the relationship between the ground water depth in the area where the overcharging pile is located and the rainfall intensity and duration per unit time, establish a water level response threshold model for the sensors at the bottom of the overcharging pile, and, taking the sensor triggering height as the boundary, combine the triggering delay to issue a control signal or power-off protection when the water level threshold is exceeded, and then construct an electrical performance failure probability model under the ground water depth, rainfall intensity and time course changes; S2. Analyze the dynamic transfer characteristics of the user charging selection space considering the distribution of waterlogged sections of the urban traffic network, obtain the pulsed aggregation characteristics of the overcharging load caused by the superposition of users' concentrated travel and charging behaviors under intermittent rainfall time courses, and construct a spatio-temporal transfer matrix model of the overcharging load considering the availability of overcharging piles and users' charging risk avoidance behaviors driven by the rainfall intensity time course; S3. Divide the charging radiation area with the overcharging station as the node, map the rainfall intensity and time course data to the nodes of the charging radiation area, combine the user electrical performance failure probability model and the spatio-temporal transfer matrix model of the overcharging load to obtain the operating state characteristics of the overcharging pile, rainfall intensity characteristics and traffic flow characteristics, construct a dynamic correlation model of the overcharging load based on spatio-temporal graph modeling, and input the current operating state characteristics of the overcharging pile, rainfall intensity characteristics and traffic flow characteristics into the dynamic correlation model of the overcharging load to obtain the corresponding load prediction value.

[0006] Preferably, the specific content of the electrical performance failure probability model includes: , In the formula, is the electrical performance failure probability of the overcharging pile, is the failure rate of the overcharging pile at time is the time step; is the influence function of insulation deterioration on the performance failure of the overcharging pile after being flooded; Among them, the specific content of the overcharging pile failure rate includes: , In the formula, is the electrical performance attenuation coefficient of the overcharging pile after being flooded; is the damping coefficient; is the accumulated water depth detected by the sensor; is the waterproof efficiency coefficient of the ultra-fast charging pile; is the ultra-fast charging station n the reference waterproof threshold when the protection level of the ultra-fast charging pile in the ultra-fast charging station is the reference waterproof level; is the soaking time coefficient; is the corrected cumulative immersion time detected by the sensor; is the anti-water ingress time threshold of the ultra-fast charging pile; The influence function of insulation degradation on the performance failure of the ultra-fast charging pile after being flooded is related to the insulation resistance, and the specific content includes: , , In the formula, is the failure sensitivity coefficient; is the insulation resistance; is the safety threshold resistance; is the initial insulation resistance; is the water absorption aging coefficient; is the conductivity of water; is the water pressure coupling acceleration coefficient, indicating the insulation degradation rate after the seal failure; is the step function, is the real-time water pressure borne by the seal structure, which is determined by the accumulated water depth in the area where the ultra-fast charging pile is located; is the reference water pressure value.

[0007] Preferably, the specific content of obtaining the accumulated water depth in the area where the ultra-fast charging pile is located includes: evolve the heavy rainfall process into a piecewise function of alternating rainfall periods and intermittent periods: , In the formula, is the rainfall intensity sequence, are respectively the rainfall intensity, start time and duration of the k th rainfall; is the k th rainfall and the k +1th rainfall; The accumulated water depth in the area where the ultra-fast charging pile is located is jointly determined by rainfall input, drainage output and neighborhood overflow. During the time-intermittent period, rainfall pauses but the drainage system continues to work. A continuous rainfall intensity-drainage balance model is constructed: , In the formula, is the accumulated water depth in the area of the ultra-fast charging pile at time t ; is the piecewise indicator function. If t is in the rainfall period Take 1 if inside, otherwise take 0, used to simulate rainfall intermittency; is the drainage rate, assumed to be proportional to the water level, f is the drainage capacity coefficient; is the set of geographical areas adjacent to the supercharging station, y refers to any surrounding area within is the surrounding area y for the current area x the overflow transfer coefficient, determined by the slope between the supercharging pile area and the surrounding area; is the surrounding area y at t the moment of accumulated water depth; The rainfall input is obtained in the form of a piecewise function and the evolution process of the accumulated water is affected by the time-course intermittency disturbance. Based on the continuous rainfall intensity - drainage balance model, discretization is carried out to establish a time-step piecewise discretization model of the accumulated water depth under intermittent heavy rainfall: , In the formula, is the accumulated water depth of the supercharging pile area after discretization at t the moment, is the accumulated water depth of the surrounding area after discretization at y at t the moment; Affected by circuit delay and noise, the detected value of the actually deployed sensor and the corrected cumulative immersion time of the sensor detection are: , , In the formula, is the sensor response delay period; i is an intermediate variable, i = t - t 1 + 1, t 1 is the detection time threshold for the immersion state of the supercharging pile; is the measurement noise, following a Gaussian distribution ; is the cumulative immersion time; is the indicator function of the accumulated water depth of the supercharging pile area at i the moment. When is satisfied, the value is 1, and if not satisfied, the value is 0; is the sensor trigger threshold.

[0008] Preferably, the specific content of the spatio-temporal transfer matrix model of the supercharging load includes: ​ , , wherein, is the selection probability of the supercharger station by users in area ; n Selection probability; is the set of users in area , u represents any one user in; is the probability of users using the supercharger; User u selects the probability of charging at the supercharger station n ; is the probability that user u selects the current path at the current moment, OD refers to the path; is the spatio-temporal transfer matrix model of the supercharger load, is the probability that any user in area R selects the supercharger station n at each time, R is all set.

[0009] Preferably, the specific content of obtaining the probability that user u selects the current path at the current moment includes: Using the traffic network topology to reflect the dynamic changes of the waterlogged area, it is set that the passability in the road network is related to the water depth of the road section. When the water depth of the road section exceeds the set critical threshold, this road section is regarded as impassable in the path selection process of users. At this time, the traffic capacity of this road section is judged to be zero, the path impedance tends to infinity, and users re-plan the path. Then, the passability model of urban roads under heavy rainfall is considered as: , , wherein, is the path impedance of path rs ; represents the length of path rs ; is the passing speed of path rs ; is the water depth of the road section; is the conventional speed when the vehicle is driving; is the traffic capacity coefficient, which changes dynamically with the rainfall intensity, road water depth and traffic state, and reflects the travel efficiency; z is the traffic sensitivity factor; is the water depth reference attenuation parameter; Then the user u The probability of selecting the current path at the current moment is as follows: , , wherein, is the risk perception factor of the user for the path rs , and are the travel choices of the user affected by the weather conditions and historical experience respectively, p is the path rs The total number of

[0010] Preferably, obtaining the probability of the user using the supercharger The specific content includes: When the user travels and the battery level is lower than the threshold, a charging demand is generated. For the overall rainfall time series The solution is a series of rainfall segments and intermittent segments, and all rainfall intermittent periods are extracted , wherein, and are respectively the start time and duration of the k th rainfall. Based on the start and end times, spatial positions, and durations of each rainfall intermittent segment, the kernel density estimation method is used to calculate the charging load spatial agglomeration factor: , , wherein, represents the impact of intermittent rainfall on the concentrated travel and charging of users. The longer the intermittency, the more inclined the user is to concentrated travel; q is the influence parameter; represents t The agglomeration intensity of user charging in the area where the supercharger station n is located at the moment; is the number of traveling users in the area where the supercharger station n is located during the intermittent period; is used to control the intensity of the pulsed influence; represents the pulsed intensity of the charging event during the intermittent period after the k th rainfall, and are respectively the mean and standard deviation of the charging event intervals; Considering the influence of intermittent rainfall, the user dynamically judges whether to preferentially choose to use the supercharger pile for charging and energy replenishment according to the duration of the current rainfall intermittent period: , wherein, is the influence factor of rainfall duration on the user's choice is the maximum reference value during the rainfall intermission period; is the state of charge of the user at time t; is the minimum state of charge that the user needs to charge at time t; is a piecewise indicator function, which takes 1 if the condition is satisfied, otherwise it takes 0.

[0011] Preferably, obtaining the probability that the user u chooses to charge at the supercharger station n specifically includes: Calculating the user charging probability based on the characteristics of user concentrated travel and charging and the availability of supercharger piles under intermittent rainfall time history: , wherein, the probability that the user u chooses to charge at the supercharger station n ; represents t the agglomeration intensity of user charging in the area where the supercharger station n is located at time ; u is the shortest accessible path length from the user n to the supercharger station N , which is infinite when the road is flooded;

[0012] Preferably, the specific content of S3 includes: Taking N supercharger stations as graph nodes to divide the charging radiation area of the urban distribution network, defining the node set as , discretizing time into a set of non-overlapping intervals , defining the graph structure at time t as , represents the feature set of all nodes in the time period ; E represents the set of connection edges between supercharger station nodes, which is used to represent the spatial proximity between regions. When the radiation areas of supercharger station i and supercharger station j are adjacent, the value of the connection edge is defined as 1, otherwise it is 0; Extracting the basic state features of each supercharger station node to form a node state vector, and the feature vector s n,0 of each node includes the operating state feature of the supercharger pile, the rainfall intensity feature and the traffic flow feature ​, construct a node-adaptive dynamic adjacency matrix using Sigmoid: , , In the formula, is the adjacency weight, jointly determined by node feature similarity and spatial proximity; and are learnable parameters, controlling the weights of feature differences and spatial proximity; is the static adjacency relationship between the hypercharger i and the hypercharger j ; Extract high-order spatio-temporal correlation features through a multi-layer graph network. For each hypercharger n extract its spatial correlation with adjacent nodes, and aggregate and update the features of all its adjacent hypercharger nodes using the permutation-invariant principle: , , In the formula, is the aggregated feature of the adjacent nodes of the hypercharger node l at the n th layer; is the set of adjacent hyperchargers of the hypercharger n , is any node in; is the n th l layer adjacent feature transformation matrix; and are the input and output matrix orders; is the l- first layer node feature vector; is the l th layer hypercharger n feature vector; is the n th l layer node feature transformation matrix; L is the number of layers of the graph neural network; all trainable parameters in each layer are shared on each node; Obtain the t TGE embedding vector at time , In the formula, and are the outputs of the first and second hidden layers; and are the weight matrices of each hidden layer; and is the bias vector for each output layer; is the time context embedding vector; is the current state variable, representing the time t sequence information at time Multiply the node feature by the output layer weight matrix and perform a non - linear transformation through an activation function. Multiply the result by the final prediction weight vector and obtain the final predicted supercharging load through the activation function again , after passing through l layers of the network, obtain t the load prediction value of node n at time , , In the formula, is the output feature of the last layer of the graph network, Contact is the process of vector concatenation, is the L layer supercharging station n feature vector; is the supercharging station n at time t the predicted supercharging load value at +1; is the final prediction weight vector;

[0013] According to the above - mentioned technical solutions, compared with the prior art, the present invention discloses a method for predicting the spatio - temporal situation of the supercharging load of urban distribution networks under heavy rainfall weather, and has the following beneficial effects: 1. The present invention analyzes the pulsed aggregation characteristics of the spatio - temporal distribution of the supercharging load of electric vehicles in the distribution network under heavy rainfall weather. Existing models do not consider the dual disturbances of rainfall characteristics such as rainfall intensity and time - course distribution on the flooding failure of supercharging piles and user charging behaviors, and it is difficult to depict the spatio - temporal aggregation characteristics of supercharging load charging behaviors in a heavy rainfall environment. The present invention derives an electrical performance failure probability model for supercharging piles after being flooded based on the water accumulation evolution process and waterproof structure threshold under a heavy rainfall scenario, analyzes the dynamic transfer characteristics of the user charging selection space considering the distribution of flooded sections of the urban traffic network, reveals the pulsed aggregation characteristics of supercharging load caused by the superposition of concentrated user travel and charging behaviors under intermittent rainfall time - courses, and constructs a spatio - temporal transfer matrix model of supercharging load considering the availability of supercharging piles and user charging risk - avoidance behaviors driven by rainfall intensity time - courses.

[0014] 2. The present invention proposes a spatio-temporal situation prediction method for ultra-fast charging load in urban distribution networks based on spatio-temporal graph deep learning. The charging radiation area is divided with ultra-fast charging stations as nodes, and rainfall intensity and time course data are mapped to the nodes of the charging radiation area. Combining the characteristics of user ultra-fast charging aggregation and the spatial dynamic reconstruction process of traffic flow, a dynamic association model of ultra-fast charging load based on spatio-temporal graph modeling is constructed. The graph network and time-guided embedding algorithm are used to encode the periodic fluctuations and mutation response characteristics of ultra-fast charging load, analyze the temporal characteristics of ultra-fast charging behavior under different weather conditions, and adaptively construct the adjacency matrix of ultra-fast charging stations according to the similarity of behavior characteristics to capture the spatial diffusion effect under the influence of weather, so as to realize the spatio-temporal situation prediction of electric vehicle ultra-fast charging load under heavy rainfall weather. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0016] Figure 1 It is a flowchart of a method for predicting the spatio-temporal situation of ultra-fast charging load in urban distribution networks under heavy rainfall weather provided by the present invention; Figure 2 It is a schematic diagram of the spatio-temporal distribution result of electric vehicle ultra-fast charging load provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0018] The present invention provides a method for predicting the spatio-temporal situation of ultra-fast charging load in urban distribution networks under heavy rainfall weather, as Figure 1 shown, including the following steps: S1. Based on the water accumulation evolution process under heavy rainfall scenarios, considering surface runoff and local drainage capacity, dynamically simulate the relationship between the ground water depth in the area where the ultra-fast charging pile is located and the rainfall intensity and duration per unit time, establish a water level response threshold model for the sensor at the bottom of the ultra-fast charging pile, and take the sensor trigger height as the boundary. Combine the trigger delay to send a control signal or power-off protection when the water level threshold is exceeded, and then construct an electrical performance failure probability model under the ground water depth, rainfall intensity and time course changes; S2. Analyze the dynamic transfer characteristics of users' charging selection space considering the distribution of flooded sections in the urban traffic network, obtain the pulsed aggregation characteristics of the supercharging load caused by the superposition of users' concentrated travel and charging behaviors under intermittent rainfall time courses, and construct a spatio-temporal transfer matrix model of the supercharging load considering the availability of supercharging piles and users' charging risk avoidance behaviors driven by the rainfall intensity time course; S3. Divide the charging radiation area with the supercharging station as the node, map the rainfall intensity and time course data to the nodes of the charging radiation area, combine the user electrical performance failure probability model and the spatio-temporal transfer matrix model of the supercharging load to obtain the operating state characteristics of the supercharging piles, the rainfall intensity characteristics and the traffic flow characteristics, construct a dynamic correlation model of the supercharging load based on spatio-temporal graph modeling, and obtain the corresponding load prediction values by inputting the current operating state characteristics of the supercharging piles, the rainfall intensity characteristics and the traffic flow characteristics into the dynamic correlation model of the supercharging load.

[0019] To further implement the above technical solutions, a supercharging station electrical performance failure probability model is constructed based on the influence of water level and flooding time under heavy rainfall on the working state of supercharging piles. This model describes the failure probability of charging piles considering the influence of the immersion failure rate of charging piles and the change of insulation performance with the environment. The specific content of the electrical performance failure probability model includes: , In the formula, is the electrical performance failure probability of the supercharging pile, is the failure rate of the supercharging pile at time is the time step; is the influence function of insulation degradation on the performance failure of the supercharging pile after being flooded; The working state of the supercharging pile is affected by the water level and the flooding time. The rising water level will directly affect the insulation performance of the pile body part of the supercharging pile. If the water accumulation depth exceeds a certain threshold, the supercharging pile may encounter electrical faults such as short circuits, leakage or equipment damage. And the flooding time is closely related to the aging process of electrical equipment. As time goes by, the insulation performance of the supercharging pile will gradually decrease, resulting in an increased risk of failure. When the accumulated water invades the heat dissipation pipeline of the charging pile, the conductivity of the coolant increases, leading to a short circuit risk. Assuming that the water level height of the same supercharging pile is the same, the waterproof performance of the supercharging pile is quantified, and a waterproof efficiency coefficient is established considering the IP protection level of the supercharging pile and the failure rate of the supercharging pile in the flooded state is calculated.

[0020] The failure rate of the supercharging pile The specific content includes: , In the formula, is the electrical performance attenuation coefficient of the supercharging pile after being flooded; is the damping coefficient; is the water accumulation depth detected by the sensor; is the waterproof efficiency coefficient of the supercharger pile, where ; is the reference waterproof threshold when the protection level of the supercharger pile in the supercharger station n is the reference waterproof level. In this embodiment, the reference waterproof level is set to IPV67; is the soaking time coefficient; is the cumulative immersion time detected and corrected by the sensor; is the anti-water ingress time threshold of the supercharger pile; The aging process of the insulating material affects the performance of the supercharger pile. In a humid environment, the insulation resistance of the material will exponentially decay due to water absorption, and the decay rate is accelerated by water pressure triggering, which in turn affects the failure rate of the supercharger pile in the flooded state. Considering the aging process of the material in the humid and hot environment, an insulation failure model is established, and the influence function of the insulation deterioration on the performance failure of the supercharger pile after being flooded includes the following specific contents: , , In the formula, is the failure sensitivity coefficient; is the insulation resistance; is the safety threshold resistance; is the initial insulation resistance; is the water absorption aging coefficient; is the conductivity of water; is the water pressure coupling acceleration coefficient, indicating the insulation degradation rate after the seal failure; is the step function, is the real-time water pressure borne by the seal structure, which is determined by the water depth in the area where the supercharger pile is located; is the water pressure reference value.

[0021] To further implement the above technical solution, the specific content of obtaining the water depth in the area where the supercharger pile is located includes: The heavy rainfall process is evolved into a piecewise function with alternating rainfall periods and intermittent periods: , In the formula, is the rainfall intensity sequence, are respectively the rainfall intensity, start time and duration of the k th rainfall; is the k th rainfall and the k +1th rainfall; The water depth in the area where the supercharger pile is located is jointly determined by rainfall input, drainage output and neighborhood overflow. During the time interval, rainfall pauses but the drainage system continues to work. A continuous rainfall intensity-drainage balance model is constructed: , wherein, is the water depth of the supercharging pile area at time t ; is a piecewise indicator function, which takes 1 if t is in the rainfall period and takes 0 otherwise, used to simulate the intermittency of rainfall; is the drainage rate, assumed to be proportional to the water level, f is the drainage capacity coefficient; is the set of geographical areas adjacent to the supercharging station, y refers to any surrounding area in ; y is the overflow transmission coefficient of the surrounding area x to the current area, determined by the slope between the supercharging pile area and the surrounding area; is the water depth of the surrounding area y at time t ; The rainfall input is obtained in the form of a piecewise function and the water accumulation evolution process is affected by the time-course intermittency disturbance. Based on the continuous rainfall intensity - drainage balance model, discretization is carried out to establish a time-step piecewise discretization model of the water depth under intermittent heavy rainfall: , wherein, is the water depth of the supercharging pile area at time t after discretization, is the water depth of the surrounding area y at time t after discretization; The electrical failure probability of the supercharging pile is positively correlated with the water depth and the soaking time. The continuous operation of the drainage system during the time-course intermittent period causes the water level to drop. If the water depth in the area where the charging pile is located exceeds the waterproof threshold, the failure rate of the charging pile rises rapidly. Affected by circuit delay and noise, there is a dynamic deviation between the detection value of the actually deployed water level sensor and the true water depth, and it is necessary to correct the cumulative time based on the photoelectric water level detection value. The sensor detection value and the sensor detection corrected cumulative soaking time are: , , wherein, is the sensor response delay period; i is an intermediate variable, i = t - t 1 + 1, t1 is the detection time threshold for the water immersion state of the ultra-fast charging pile; is the measurement noise, which follows a Gaussian distribution ; is the cumulative water immersion time; is i the indicator function of the water depth in the ultra-fast charging pile area at time . When it is satisfied, the value is 1. If it is not satisfied, the value is 0; is the sensor trigger threshold.

[0022] To further implement the above technical solution, the specific content of the ultra-fast charging load spatio-temporal transfer matrix model includes: , , In the formula, is the selection probability of users in area for the ultra-fast charging station n ; is the set of users in area , u represents any user in; is the probability of users using ultra-fast charging; User u selects the probability of charging at the ultra-fast charging station n ; is the probability that user u selects the current path at the current moment, OD refers to the path; is the ultra-fast charging load spatio-temporal transfer matrix model, is the probability that any user in area R selects the ultra-fast charging station n at each time, R is all 's set.

[0023] To further implement the above technical solution, the specific content of obtaining the probability u that user selects the current path at the current moment includes: Use the traffic network topology structure to reflect the dynamic changes of the flooded area. It is set that the passability in the road network is related to the water depth of the road section. When the water depth of the road section exceeds the set critical threshold, the road section is regarded as impassable in the user's path selection process. At this time, the traffic capacity of the road section is judged to be zero, the path impedance tends to infinity, and the user re-plans the path. Then, considering the passability model of urban roads under heavy rainfall is: , , In the formula, is the path rs impedance; represents the path rs length; is the path rs travel speed; is the water depth of the road section; is the normal speed when the vehicle is driving; is the traffic capacity coefficient, which changes dynamically with the rainfall intensity, road water depth and traffic state, and reflects the travel efficiency; z is the traffic sensitivity factor; is the attenuation parameter of the water depth reference; The user's path selection is not a one-time decision, but a dynamic adjustment process. Since closed sections are not considered in path search, when facing roads that may be flooded or closed, the user will immediately activate the path replanning mechanism. Users tend to adjust their travel paths according to the principle of minimum impedance, that is, choose a path with the least resistance and the highest efficiency.

[0024] Then the user u The probability of choosing the current path at the current moment is: , , In the formula, is the user's risk perception factor for the path rs , and are the travel choices of the user affected by weather conditions and historical experience respectively, p is the path rs total number.

[0025] To further implement the above technical solution, the specific content of obtaining the probability that the user uses the supercharger includes: When the user travels and the battery level is lower than the threshold, a charging demand is generated. For the overall rainfall time series is solved as a series of rainfall segments and intermittent segments, and all rainfall intermittent segments are extracted, where and are the start time and duration of the k th rainfall respectively. Based on the start and end times, spatial positions and durations of each rainfall intermittent segment, the kernel density estimation method is used to calculate the spatial aggregation factor of the charging load: , , In the formula, Indicates the impact of intermittent rainfall on users' concentrated travel and charging. The longer the intermittency, the more inclined users are to travel concentratedly; q Is the impact parameter; Indicates t The agglomeration intensity of users' charging in the area where the supercharger station is located at n the moment; Is the number of traveling users in the area where the supercharger station is located during the intermittent period; n Is used to control the intensity of the pulsed impact; Indicates the pulsed intensity of the charging event during the intermittent period after the th rainfall, k and and Are the mean and standard deviation of the charging event interval respectively; Considering the impact of intermittent rainfall, users dynamically judge whether to preferentially choose to use the supercharger pile for charging and energy replenishment based on the duration of the current rainfall intermittent period: , In the formula, Is the impact factor of rainfall duration on user selection; Is the maximum reference value of the rainfall intermittent period; Is the state of charge of the user at time t; Is the minimum state of charge value that the user needs to charge at time t; Is a piecewise indicator function, which takes 1 if the condition of is satisfied, otherwise it takes 0.

[0026] To further implement the above technical solution, obtaining the u probability that a user n chooses to charge at the supercharger station specifically includes: Calculating the user charging probability based on the characteristics of users' concentrated travel and charging and the availability of supercharger piles under the intermittent rainfall time course: , In the formula, The probability that the user u chooses to charge at the supercharger station n ; Indicates t the agglomeration intensity of users' charging in the area where the supercharger station is located at n the moment; Is the shortest accessible path length from the user u to the supercharger station n , which is infinite when the road is flooded; N Is the total number of supercharger stations.

[0027] To further implement the above technical solution, the specific content of S3 includes: Taking N supercharging stations as graph nodes to divide the charging radiation area of the urban distribution network, defining the node set as , discretizing time into a set of non-overlapping intervals , defining the graph structure at time t as , representing the set of features of all nodes in the time period ; E representing the set of connection edges between supercharging station nodes to represent the spatial proximity between regions. When the radiation areas of supercharging stations i and supercharging station j are adjacent, defining the value of the connection edge as 1, otherwise 0; extracting the basic state features of each supercharging station node to form a node state vector, and the feature vector of each node s n,0 including the operating state feature of the supercharging pile , the rainfall intensity feature and the traffic flow feature , using Sigmoid to construct a node adaptive dynamic adjacency matrix: , , wherein, is the adjacency weight, jointly determined by the node feature similarity and spatial proximity; and are learnable parameters, controlling the weights of feature differences and spatial proximity; is the static adjacency relationship between supercharging stations i and supercharging station j ; extracting high-order spatio-temporal correlation features through a multi-layer graph network. For each supercharging station n extracting the spatial correlation between it and adjacent nodes, and aggregating and updating the features of all its adjacent supercharging station nodes according to the permutation invariance principle: , , wherein, is the aggregated feature of the adjacent nodes of the supercharging station node l at the n th layer; is the set of adjacent supercharging stations of supercharging station n , is any node in; is the node n at the lLayer adjacency feature transformation matrix; and are the input and output matrix orders; is the l- feature vector of the nodes in the first layer; is the l feature vector of the hypercharger station in the n layer; is the node n in the l layer node feature transformation matrix; L is the number of layers of the graph neural network; all trainable parameters in each layer are shared on each node; The time-guided embedding extracts hidden stationary features by learning the conditional distribution of the time context of the prediction target, and then captures the potential patterns of the user's hypercharging behavior on time scales such as daily and weekly cycles. First, the graph neural network is used to extract the temporal feature information of the nodes, and then these feature information are concatenated with the time-guided embedding vector. At t the +1 moment, the TGE embedding vector realizes the perception of the time evolution trend by fusing information such as rainfall intensity, water accumulation depth, user hypercharging demand, traffic status, and station function status at the current time, so as to provide temporal consistency support for the downstream graph neural network.

[0028] Obtain t the TGE embedding vector at the +1 moment: , wherein, and are the outputs of the first and second hidden layers; and are the weight matrices of each hidden layer; and are the bias vectors of each output layer; is the time context embedding vector; is the current state variable, representing the temporal information of time t +1; Multiply the node feature by the output layer weight matrix , perform a non-linear transformation through the activation function, multiply the result by the final prediction weight vector , and obtain the final predicted hypercharging load again through the activation function. After passing through l layers of the network, obtain t the load prediction value of the node n at the +1 moment: , , In the formula, is the output feature of the last-layer graph network, Contact is the process of vector concatenation, is the L th-layer supercharging station n 's feature vector; is the predicted supercharging load value of the supercharging station n at the t +1 moment; is the final predicted weight vector; is the output layer weight matrix.

[0029] The present invention will be further described below through simulation experiments: To verify the prediction accuracy of the spatio-temporal distribution of the supercharging load of the proposed model under heavy rainfall conditions, 25 supercharging stations in a typical urban area are selected, and the load prediction results of the traditional LSTM time series prediction model, the static graph model under normal weather, and the graph network time-guided embedding TGE model incorporating the impact of heavy rainfall constructed by the present invention are compared respectively in an intermittent heavy rainfall scenario. The historical load data of the past 30 days and the corresponding rainfall and waterlogging conditions are selected as the training set to predict the spatio-temporal distribution of the supercharging load, and the evaluation indicators include mean square error, mean absolute percentage error, and spatial distribution consistency index.

[0030] The spatio-temporal distribution results of the supercharging load of electric vehicles under heavy rainfall are as Figure 2 shown. The supercharging load of electric vehicles shows obvious spatial agglomeration characteristics. Due to waterlogging, the traffic on some roads is restricted, causing vehicles to detour to areas with higher accessibility, resulting in the superposition of local congestion and charging demand. Secondly, the intermittent rainfall makes the charging behavior of users tend to be in the modes of avoiding rain, concentrating, and dispersing. A large number of vehicles pour into available supercharging stations in a short time, exacerbating the load fluctuation. In addition, due to intermittent heavy rainfall, some supercharging stations are out of service in some areas, further restricting the available charging resources and driving the load to gather at a few stable nodes.

[0031]

[0032] The comparison of the prediction results under different methods is shown in Table 1. Under continuous heavy rainfall conditions, the traditional model has obvious lag and prediction deviation at the load mutation points and lacks the ability to identify the spatial aggregation effect. However, the model of the present invention significantly improves the sensitivity to load fluctuations and the ability to capture the spatio-temporal aggregation trend by introducing the rainfall-traffic-load coupling mechanism. It is superior to the comparison models in all three indicators, demonstrating good practicability and adaptability.

[0033] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included within the protection scope of the present application.

Claims

1. A spatio-temporal situation prediction method for the ultra-fast charging load of urban distribution networks under heavy rainfall weather, characterized in that, The following steps are involved: S1. Based on the evolution of water accumulation under heavy rainfall scenarios, the relationship between the depth of ground water accumulation in the area where the supercharging pile is located and the rainfall intensity and duration per unit time is dynamically simulated by considering surface runoff and local drainage capacity. A threshold model for the response of the sensor at the bottom of the supercharging pile to the water level is established. The sensor trigger height is used as the boundary. Combined with the trigger delay, a control signal is issued or power is cut off for protection when the water level threshold is exceeded. Then, a probability model for electrical performance failure under changes in ground water accumulation depth, rainfall intensity and time course is constructed. S2. Analyze the spatial dynamic transfer characteristics of user charging choices considering the distribution of flooded sections in the urban traffic network, obtain the pulse-like agglomeration characteristics of supercharging load caused by the superposition of user concentrated travel and charging behavior under intermittent rainfall schedules, and construct a supercharging load spatiotemporal transfer matrix model driven by rainfall intensity schedules considering the availability of supercharging piles and user charging risk avoidance behavior; S3. Divide the charging radiation area with supercharging stations as nodes, map the rainfall intensity and time series data to the nodes of the charging radiation area, and obtain the operating status characteristics, rainfall intensity characteristics and traffic flow characteristics of the supercharging piles by combining the user electrical performance failure probability model and the supercharging load spatiotemporal transfer matrix model. Construct a supercharging load dynamic association model based on spatiotemporal graph modeling, and obtain the corresponding load forecast by inputting the current supercharging pile operating status characteristics, rainfall intensity characteristics and traffic flow characteristics into the supercharging load dynamic association model.

2. A method for predicting the spatio-temporal situation of the ultra-charge load of urban distribution networks under heavy rainfall weather according to claim 1, characterized in that The specific contents of the electrical performance failure probability model include: ， Wherein, is the electrical performance failure probability of the ultra-fast charging pile, is the failure rate of the ultra-fast charging pile at time is the time step; is the influence function of insulation deterioration on the performance failure of the ultra-fast charging pile after being flooded; Among them, the failure rate of the ultra-fast charging pile The specific content includes: ， Wherein, is the attenuation coefficient of the electrical performance of the ultra-fast charging pile after being flooded; is the damping coefficient; is the water depth detected by the sensor; is the waterproof efficiency coefficient of the ultra-fast charging pile; is the ultra-fast charging station n is the reference waterproof threshold when the protection level of the ultra-fast charging pile in it is the reference waterproof level; is the immersion time coefficient; is the corrected cumulative immersion time detected by the sensor; is the anti-water ingress time threshold of the ultra-fast charging pile; Influence Function of Insulation Deterioration on Performance Failure of Ultra-fast Chargers after Flooding Related to the insulation resistance, the specific content includes: ， ， Wherein, is the failure sensitivity coefficient; is the insulation resistance; is the safety threshold resistance; is the initial insulation resistance; is the water absorption aging coefficient; is the conductivity of water; is the water pressure coupling acceleration coefficient, indicating the insulation degradation rate after seal failure; is the step function, is the real-time water pressure borne by the seal structure, which is determined by the water depth in the area where the overcharging pile is located; is the reference value of water pressure.

3. A method for predicting the spatio-temporal situation of the ultra-charging load of urban distribution networks under heavy rainfall weather according to claim 2, characterized in that, The specific contents of obtaining the water depth in the area where the supercharging pile is located include: The heavy rainfall process is evolved into a piecewise function with alternating rainfall periods and intermittent periods: ， In the formula, is the rainfall intensity sequence, are respectively the rainfall intensity, start time and duration of the k -th rainfall; is the interval time between the k -th rainfall and the k +1-th rainfall; The water depth in the area where the supercharging piles are located is determined by the rainfall input, drainage output and overflow of the neighborhood. During the interval period, the rainfall stops but the drainage system continues to work, and a continuous rainfall intensity-drainage balance model is constructed: ， In the formula, is the water depth of the supercharging pile area at time t ; is a piecewise indicator function. If t is in the rainfall period , it takes 1, otherwise it takes 0, which is used to simulate the intermittency of rainfall; is the drainage rate, which is assumed to be proportional to the water level, f is the drainage capacity coefficient; is the set of geographical areas adjacent to the supercharging station, y refers to any surrounding area in ; y is the overflow transmission coefficient of the surrounding area x to the current area, which is determined by the slope between the supercharging pile area and the surrounding area; is the water depth of the surrounding area y at time t ; The rainfall input is obtained in the form of piecewise function and the evolution process of waterlogging is affected by intermittent disturbances in time history. Discretization is performed on the basis of the continuous rainfall intensity-drainage balance model, and a time-step piecewise discretization model of waterlogging depth under intermittent heavy rainfall is established: ， In the formula, is the accumulated water depth in the ultra-fast charging pile area at the t discretized moment, is the accumulated water depth in the surrounding area at the y discretized t moment. Affected by circuit delay and noise, the detection value of the actually deployed sensor and the corrected cumulative immersion time detected by the sensor are as follows: ， ， In the formula, is the sensor response delay period; i is the intermediate variable, i = t - t 1+1, t 1 is the detection time threshold of the supercharging pile immersion state; To measure noise, it follows a Gaussian distribution ; is the cumulative immersion time; for i The indicator function of the water depth in the supercharging pile area at the moment is satisfied when If it is not satisfied, the value is 0; Trigger threshold for the sensor.

4. The method for predicting the spatiotemporal situation of overload of urban distribution network under heavy rainfall according to claim 1 is characterized in that: The specific contents of the overcharge load space-time transfer matrix model include: ， ， In the formula, For Region of users use supercharging stations n Probability of selection; For Region The collection of internal users, u express Any user in The probability of using supercharging for users; user u Choose a supercharging station n Probability of charging; For users u The probability of choosing the current path at the current moment, OD Refers to the path; is the overcharge space-time transfer matrix model, For Region R Any user in the area can select a supercharging station at any time. n The probability of R For all A collection of .

5. A method for predicting the spatio-temporal situation of the ultra-charge load of an urban distribution network under heavy rainfall weather according to claim 4, characterized in that Get User u The probability of choosing the current path at the current moment The specific contents include: The traffic network topology is used to reflect the dynamic changes of the flooded area. The road network accessibility is set to be related to the depth of waterlogging on the road section. When the waterlogging depth on the road section exceeds the set critical threshold, the road section is considered impassable in the user's path selection process. At this time, the road capacity of the road section is judged to be zero, and the path impedance tends to infinity. The user replans the path. The accessibility model of urban roads under heavy rainfall is: ， ， In the formula, For path rs The path impedance; Indicates the path rs length; For path rs The speed of travel; is the depth of water accumulation on the road section; The normal speed of the vehicle when traveling; is the traffic capacity coefficient, which reflects travel efficiency as rainfall intensity, road water depth and traffic conditions change dynamically; z is the traffic sensitivity factor; is the reference attenuation parameter of water depth; Then the user u The probability of choosing the current path at the current moment for: ， ， In the formula, Path for users rs The risk perception factor and They are respectively the travel choices of users affected by weather conditions and historical experience. p For path rs The total number of .

6. A method for predicting the spatio-temporal situation of the ultra-charge load of urban distribution networks under heavy rainfall weather according to claim 4, characterized in that, Get the probability of users using supercharging The specific contents include: When the user is traveling and the battery level is below the threshold, a charging demand is generated, which affects the overall rainfall sequence. Solve it into a series of rainfall segments and intermittent segments, extract all rainfall intermittent periods ,in, and Respectively k The starting time and duration of each rainfall interval are calculated based on the starting and ending time, spatial location and duration of each rainfall interval, and the kernel density estimation method is used to calculate the spatial clustering factor of the charging load: ， ， In the formula, It indicates the impact of intermittent rainfall on users’ concentrated travel and charging. The longer the intermittent rainfall, the more users tend to travel in a concentrated manner. q To influence the parameters; express t Supercharging station n The concentration intensity of charging users in the area; Supercharging station during the intermittent period n Number of travel users in the area; Used to control the intensity of impulse effects; Indicates k The pulse intensity of charging events during the intermittent period after the rainfall, and are the mean and standard deviation of the charging event intervals, respectively; Taking into account the impact of intermittent rainfall, users can dynamically determine whether to give priority to using supercharging piles for charging and replenishing energy based on the duration of the current rainfall interval: ， In the formula, The factors affecting the user's choice are rainfall duration; It is the maximum reference value during the rainfall interval; is the user's state of charge at time t; The minimum state of charge that the user needs to charge at time t; is a piecewise indicator function, if it satisfies The condition is 1, otherwise it is 0.

7. The method for predicting the spatiotemporal situation of overload of urban distribution network under heavy rainfall according to claim 4 is characterized in that: Get User u Choose a supercharging station n Probability of charging The specific contents include: The user charging probability is calculated based on the user's concentrated travel and charging characteristics and the availability of supercharging piles under intermittent rainfall schedule: ， In the formula, user u Choose a supercharging station n Probability of charging; express t Supercharging station n The concentration intensity of charging users in the area; For users u To the supercharging station n The shortest traversable path length is infinite when the road is flooded; N is the total number of supercharging stations.

8. The method for predicting the spatiotemporal situation of overload of urban distribution network under heavy rainfall according to claim 1 is characterized in that: The specific contents of S3 include: by N The supercharging stations are used as graph nodes to divide the charging radiation area of ​​the urban distribution network, and the node set is defined as , discretize time into a set of non-overlapping intervals , define time t The graph structure at the moment is , Indicates time period The feature set of all nodes in , E The set of connecting edges between supercharging station nodes is used to represent the spatial proximity between regions. i and supercharging stations j When the radiation areas of the nodes are adjacent, define the connecting edge The value of is 1, otherwise it is 0; Extract the basic state features of each supercharging station node to form a node state vector, and the feature vector of each node s n,0 Including super charging pile operation status characteristics , rainfall intensity characteristics and traffic flow characteristics , use Sigmoid to build a node-adaptive dynamic adjacency matrix: ， ， In the formula, is the adjacency weight, which is determined by the node feature similarity and spatial proximity; and is a learnable parameter that controls the weights of feature differences and spatial proximity; For super charging stations i and supercharging stations j Static adjacency between them; Through the multi-layer graph network, high-order spatiotemporal correlation features are extracted for each supercharging station. n The spatial correlation between it and its adjacent nodes is extracted, and the features of all its adjacent supercharging station nodes are aggregated and updated using the permutation invariance principle: ， ， In the formula, For the l Layer Supercharging Station Node n Adjacent node aggregation features; For super charging stations n The set of adjacent supercharging stations, for Any node in ; For Node n No. l Layer adjacency feature transformation matrix; and is the input and output matrix order; For the l- Layer 1 Node The eigenvector of For the l Supercharging station n The eigenvector of For Node n No. l Layer node feature transformation matrix; L is the number of graph neural network layers; all trainable parameters in each layer are shared on each node; Get t +1 moment TGE embedding vector: ， In the formula, and Outputs of the first and second hidden layers; and is the weight matrix of each hidden layer; and is the bias vector of each output layer; Embedding vector for temporal context; is the current state variable, indicating time t +1 for the timing information; Node Features and the output layer weight matrix Multiply, perform nonlinear transformation through activation function, and add the result to the final prediction weight vector Multiply them together and pass the activation function again to get the final predicted overcharge load ,go through l After the layer network, we get t +1 time node n Load forecast: ， ， In the formula, is the output feature of the last layer of graph network, Contact is the process of vector concatenation, For the L Supercharging station n The eigenvector of For super charging stations n exist t +1 predicted supercharge load value at time; is the final prediction weight vector; is the output layer weight matrix.

Images