Power distribution area emergency supply insurance method and system based on vehicle network space-time matching, and medium

Abstract

The invention discloses a power distribution area emergency supply insurance method and system based on vehicle network space-time matching, and a medium. Relates to the technical field of emergency supply insurance. According to the scheme, on the basis of a traditional power distribution area emergency supply guarantee technology, the method is improved, environmental meteorological data and power distribution area electrical operation characteristics under different types of extreme weather are analyzed, and the emergency supply guarantee demand of a power distribution area is calculated; according to the method, multi-view portraying is carried out in combination with characteristics of tracks, discharging and the like of the electric vehicles, space-time matching analysis of discharging of the electric vehicles and emergency insurance and supply of the power distribution area is carried out, emergency insurance and supply regulation and control of the power distribution area are realized under the limitation of discharging constraint conditions of the electric vehicles, and meanwhile, through vehicle-network interaction access points widely distributed in the electric vehicles, emergency insurance and supply control of the power distribution area is realized. The power guarantee requirement of any position of the power distribution area is met, and reasonable planning and effective utilization of electric vehicle resources are achieved.

Description

Technical Field

[0001] The present invention relates to the field of emergency power supply technology, and in particular to a distribution station area emergency power supply method, system and medium based on vehicle-grid time-space matching. Background Art

[0002] The current emergency power supply mode usually uses power generation vehicles, flywheel energy storage vehicles, battery energy storage vehicles and other equipment to provide emergency power supply for distribution station areas (DSA), which has problems such as high power generation cost and high power generation noise pollution. At the same time, since the installation of emergency power generation vehicle quick access boxes in distribution station areas is easily restricted by geographical conditions, the existing emergency power supply resources are difficult to meet the power supply needs at any location in the distribution station area. Therefore, it is of positive significance to explore the emergency power supply for distribution station areas.

[0003] At present, there are a lot of research on emergency power supply for distribution substations, which are mainly divided into two categories: emergency power supply of standby generators and emergency power supply of distributed generators (DG). The standby generator supply method mainly involves installing a self-provided high-power generator at the distribution transformer. When the external power supply of the distribution substation is limited or stopped in extreme weather, the high-power generator is used to provide power for emergency power supply of the distribution substation. The distributed power supply emergency supply method uses distributed photovoltaic, fixed energy storage devices and other equipment to provide emergency power supply for the distribution substation.

[0004] For emergency supply of backup generators, the existing technologies include networking and power distribution control of self-provided generators to achieve emergency supply in distribution substations; and mixed integer linear programming of self-provided fuel generators to achieve emergency supply in distribution substations. However, the purchase and installation costs of self-provided generators in distribution substations are high, and the equipment utilization rate is low, which is not suitable for large-scale promotion in emergency supply of distribution substations.

[0005] For emergency supply of distributed power sources, existing technologies include merging the topology of the distribution network through the access of distributed power sources to the distribution area to provide emergency supply of the distribution area within the range of the distribution network topology reduction; or optimizing the discharge power of distributed power sources through the particle swarm optimization algorithm to achieve emergency power supply guarantee of the distribution area; and conducting distributed power response evaluation and distributed power economic scheduling before and after the disaster to achieve emergency supply of the distribution area. There are various methods for emergency supply of distributed power sources, but distributed photovoltaics are limited by solar radiation and cannot provide emergency supply power for the distribution area when extreme weather occurs at night; fixed energy storage equipment can only provide power at the access point of the distribution area, which is difficult to meet the power supply needs of any location in the distribution area.

[0006] New energy electric vehicles (EVs) are a type of distributed large-scale energy storage resource. The vehicle-to-grid (V2G) access points of new energy electric vehicles are widely distributed, enabling access to any location in the distribution area, providing support for emergency supply in the distribution area. However, in extreme weather conditions, new energy electric vehicles are scattered, and how to match new energy electric vehicle resources with emergency supply resources in the distribution area has become an urgent problem that needs to be solved. Summary of the invention

[0007] The technical problem to be solved by the present invention is: in extreme weather, new energy electric vehicles are scattered, making it difficult to achieve resource matching between new energy electric vehicle resources and emergency supply of distribution stations; the purpose of the present invention is to provide a distribution station emergency supply method, system and medium based on vehicle-grid spatiotemporal matching, and to improve the method on the basis of traditional distribution station emergency supply technology, analyze environmental meteorological data and electrical operation characteristics of distribution stations under different types of extreme weather, and calculate the emergency supply demand of distribution stations; combine the trajectory, discharge and other characteristics of electric vehicles to perform multi-perspective profiling, conduct spatiotemporal matching analysis between electric vehicle discharge and emergency supply of distribution stations, and realize emergency supply regulation of distribution stations under the limitation of electric vehicle discharge constraints, meet the power supply demand of any position in the distribution station, and realize reasonable planning and effective utilization of various electric vehicle resources.

[0008] The present invention is achieved through the following technical solutions: This solution provides an emergency power supply guarantee method for distribution area based on vehicle-grid time-space matching, including: Obtain environmental meteorological data and electrical operation data of distribution substations under extreme weather conditions; Analyze the operation characteristics of the distribution area based on the environmental meteorological data and the electrical operation data of the distribution area, and evaluate the emergency supply demand of the distribution area based on the analysis results of the operation characteristics of the distribution area; Construct a multi-view feature portrait of electric vehicles; Combining multi-perspective feature portraits and emergency supply demand assessment results, a spatiotemporal matching analysis of electric vehicle discharge and emergency supply in distribution stations is conducted, and emergency supply regulation in distribution stations is achieved under the constraints of electric vehicle discharge.

[0009] A further optimization scheme is that the environmental meteorological data includes: temperature, ground pressure, wind speed, wind direction, relative humidity, precipitation and solar radiation in the target area; the sampling frequency of environmental meteorological data is F1 times per day; The electrical operation data of the distribution substation area includes: current, voltage, power and power factor on the distribution transformer side; the sampling frequency of the electrical operation data of the distribution substation area is F2 times per day; F2>F1.

[0010] A further optimization scheme is to perform an operation characteristic analysis of the distribution substation area based on the environmental meteorological data and the electrical operation data of the distribution substation area, and to conduct an emergency supply demand assessment of the distribution substation area according to the analysis results of the operation characteristic analysis of the distribution substation area; including methods: Analyze the electrical operation characteristics and impact types of the distribution area affected by extreme weather: when the electrical operation characteristics of the distribution area equipment caused by extreme weather are line disconnection, short circuit or grounding fault, configure it as a direct impact type; when the electrical operation characteristics of the distribution area equipment caused by extreme weather are insufficient power supply capacity or line overload, configure it as an indirect impact type; Taking the electrical operation characteristics as variables, quantifying the variable distribution of the distribution station area based on the Gaussian mixture model, and estimating the impact type of each variable; The variables with power supply demand are used as demand variable access points. The impact type of each demand variable access point is matched with the preset emergency power supply rules to evaluate the emergency power supply demand power of each demand variable access point.

[0011] A further optimization scheme is to quantify the variable distribution of the distribution station area based on the Gaussian mixture model and estimate the impact type of each variable; including the process: Probability density function of each electrical operation feature cluster at the yth point using the Gaussian mixture model p DSA ( y )for: ; Where: It means the sum of all electrical operation characteristics, and Z represents the total number of electrical operation characteristics; a z The mixing coefficient representing the Gaussian distribution electrical operating characteristic z; represents the sum of the covariances of all electrical operating characteristics; m z Indicates the typical characteristic value of the electrical operating characteristic z; is the Gaussian distribution density function of the electrical operation characteristic z; When classifying the electrical operating characteristics z, the Gaussian distribution density function is decomposed into: ; Where: d The number of dimensions that characterize electrical operation; m Represents the mean value of electrical operating characteristics; represents the covariance of electrical operating characteristics; Determinant representing the covariance of the electrical operating characteristics.

[0012] A further optimization scheme is to match the impact type of each demand variable access point with the preset emergency power supply rule to evaluate the emergency power supply demand power of each demand variable access point; including the method: Obtain the power supply level table of the State Grid Corporation, and search for the power supply level that matches each demand variable access point in the power supply level table of the State Grid Corporation: for the demand variable access point of the direct impact type, match the first power supply level; for the demand variable access point of the indirect impact type, match the second power supply level; The emergency power supply of the distribution area corresponding to the power supply level is used as the emergency power supply demand power of the access point matching the demand variable.

[0013] A further optimization scheme is that the method of constructing a multi-view feature portrait of an electric vehicle includes: Acquiring characteristic indicators of the electric vehicle; the characteristic indicators include time characteristics, space characteristics and charge and discharge characteristics; The conflicts among time features, space features and charge-discharge features are compared based on the relative entropy identification method, and the weight of each feature index is determined based on the conflict comparison results.

[0014] A further optimization scheme is to combine the multi-perspective feature portrait and the emergency supply demand assessment results to conduct a spatiotemporal matching analysis of electric vehicle discharge and emergency supply in distribution stations, and realize emergency supply control in distribution stations under the constraints of electric vehicle discharge; including methods: Build a list of available electric vehicles based on multi-view feature portraits of electric vehicles; Based on the improved weighted bipartite graph optimal matching method, the vehicle-grid spatiotemporal matching calculation is performed in combination with the emergency supply demand assessment results and the list of available electric vehicles, and the distribution area emergency supply dispatch instructions are generated and distributed to each available electric vehicle; If the available electric vehicles accept the emergency supply and deployment instructions of the distribution station area, each available electric vehicle will be deployed to the matching demand variable access point; otherwise, the vehicle-grid time-space matching calculation is performed again until all available electric vehicles accept the emergency supply and deployment instructions of the distribution station area.

[0015] A further optimization scheme is that the method for calculating the vehicle-grid spatiotemporal matching includes: The vehicle-network spatiotemporal matching result is calculated according to the following formula g ST : ;

[0016] Where: n C is the total number of available electric vehicles; n D The total number of access points for the demand variables in the distribution area; For distribution area to j The traffic time of the access point of the demand variable; For the i A characteristic value that can be used to ensure emergency supply of electric vehicles to the distribution station area; Electric vehicle discharge constraints include: ; Where: represents the load power of the j-th output electric vehicle; n E Indicates the total number of electric vehicles with output; t IN Time for emergency power supply to distribution stations; Ensure power supply to meet the needs of the distribution station area.

[0017] This solution also provides a distribution substation emergency supply system based on vehicle-grid time-space matching, which is used to implement the above-mentioned distribution substation emergency supply method based on vehicle-grid time-space matching. The system includes: The acquisition module is used to obtain environmental meteorological data and electrical operation data of the distribution station area under extreme weather conditions; The analysis and estimation module is used to analyze the operation characteristics of the distribution area based on the environmental meteorological data and the electrical operation data of the distribution area, and to evaluate the emergency supply demand of the distribution area according to the analysis results of the operation characteristics of the distribution area; A building block for constructing multi-view feature portraits of electric vehicles; The control module is used to combine multi-perspective feature portraits and emergency supply demand assessment results to conduct spatiotemporal matching analysis of electric vehicle discharge and emergency supply in distribution stations, and to achieve emergency supply control in distribution stations under the constraints of electric vehicle discharge.

[0018] The present solution also provides a computer-readable medium on which a computer program is stored. The computer program is executed by a processor to implement the above-mentioned method for emergency power supply in a distribution station area based on time-space matching of the vehicle network.

[0019] Compared with the prior art, the present invention has the following advantages and beneficial effects: The present invention provides a method, system and medium for emergency power supply of distribution stations based on spatiotemporal matching of vehicle-grid. On the basis of traditional emergency power supply technology of distribution stations, the method is improved to analyze environmental meteorological data and electrical operation characteristics of distribution stations under different types of extreme weather, and calculate the emergency power supply demand of distribution stations. Multi-perspective profiling is performed in combination with the trajectory, discharge and other characteristics of electric vehicles, and spatiotemporal matching analysis of electric vehicle discharge and emergency power supply of distribution stations is performed. Under the limitation of electric vehicle discharge constraints, emergency power supply regulation of distribution stations is realized. At the same time, through the widely distributed vehicle-grid interactive access points of electric vehicles, the power supply demand of any position in the distribution station area is realized, and the reasonable planning and effective utilization of various electric vehicle resources are realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without creative work. In the drawings: Figure 1 This is a flow chart of the method for emergency power supply in distribution area based on time-space matching of vehicle network; Figure 2 This is a schematic diagram of the structure of the distribution station area emergency power supply system based on vehicle-grid time-space matching. DETAILED DESCRIPTION

[0021] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.

[0022] In extreme weather conditions, new energy electric vehicles are scattered, making it difficult to match new energy electric vehicle resources with emergency supply resources in distribution stations. In view of this, this solution provides the following embodiments to solve this technical problem.

[0023] Embodiment 1: This embodiment provides a method for emergency power supply in a distribution area based on time-space matching of a vehicle network, such as Figure 1 As shown, including: Step 1: Obtain environmental meteorological data and electrical operation data of the distribution station area under extreme weather conditions; the environmental meteorological data in this step include: temperature, ground pressure, wind speed, wind direction, relative humidity, precipitation and solar radiation in the target area; the sampling frequency of environmental meteorological data is F1 times per day; environmental meteorological data can be derived from meteorological data within the corresponding area of ​​the distribution station area in the numerical weather forecast, as well as historical meteorological measured data provided by local meteorological bureaus. Obtain environmental meteorological data from each meteorological bureau through the application programming interface (API interface); The electrical operation data of the distribution substation includes: current, voltage, power and power factor on the distribution transformer side; the sampling frequency of the electrical operation data of the distribution substation is F2 times per day; F2>F1. The electrical operation data of the distribution substation is collected by the intelligent fusion terminal installed in the distribution substation, such as meters, switches, DG and other equipment; after the intelligent fusion terminal collects the data, it transmits the electrical operation data to the power grid company through the access point name (APN) channel, and finally obtains the electrical operation data of the distribution substation from the power grid company.

[0024] Environmental meteorological data collected d ME ( t ) and distribution area electrical operation data d ELEC ( t ) are: ; ; Where: m is the number of types of environmental meteorological data; n The number of electrical operation data for the distribution station area; t is the sampling time; It is the sampling sequence of environmental meteorological data; It is the sampling sequence of electrical operation data of distribution station area.

[0025] Step 2: Analyze the operation characteristics of the distribution substation area based on the environmental meteorological data and the electrical operation data of the distribution substation area, and evaluate the emergency supply demand of the distribution substation area according to the analysis results of the operation characteristics of the distribution substation area; this step specifically includes the following methods: S21. Analyze the electrical operation characteristics and impact types of extreme weather affecting distribution substations: when the electrical operation characteristics of distribution substation equipment caused by extreme weather are line break, short circuit or ground fault, it is configured as a direct impact type; when the electrical operation characteristics of distribution substation equipment caused by extreme weather are insufficient power supply capacity or line overload, it is configured as an indirect impact type; extreme weather mainly includes typhoons, heavy rains, lightning strikes, extreme high temperatures and extreme cold waves. When a distribution substation encounters a direct impact type fault due to extreme weather, the damaged electrical equipment needs to be isolated, and electric vehicles are required to provide emergency power supply to the undamaged areas of the distribution substation; when a distribution substation encounters an indirect impact type fault due to extreme weather, electric vehicles are also required to provide backup power to ensure reliable power supply to the distribution substation.

[0026] In the case of climate warming, extreme weather has the characteristics of strong randomness in the time of occurrence and wide impact range, which will seriously affect the operation status of power equipment such as distribution transformers, low-voltage lines, and power generation equipment in the distribution substation area. Therefore, when conducting emergency supply demand analysis in the distribution substation area, the electrical operation characteristics and impact types of extreme weather in the distribution substation area should be analyzed first.

[0027] S22, taking the electrical operation characteristics as variables, quantifying the variable distribution of the distribution area based on the Gaussian mixture model, and estimating the impact type of each variable; quantifying the variable distribution of the distribution area based on the Gaussian mixture model, and estimating the impact type of each variable; including the process: The Gaussian mixture model clusters the electrical operation characteristics in the first y Probability density function of a point p DSA ( y )for: ; Where: It means the sum of all electrical operation characteristics, and Z represents the total number of electrical operation characteristics; a z The mixing coefficient representing the Gaussian distribution electrical operating characteristic z; represents the sum of the covariances of all electrical operating characteristics; m z Indicates the typical characteristic value of the electrical operating characteristic z; is the Gaussian distribution density function of the electrical operation characteristic z; When classifying the electrical operating characteristics z, the Gaussian distribution density function is decomposed into: ; Where: d The number of dimensions that characterize electrical operation; m Represents the mean value of electrical operating characteristics; represents the covariance of electrical operating characteristics; Determinant representing the covariance of the electrical operating characteristics.

[0028] The Gaussian mixture model (GMM) is a probability-based clustering method that belongs to the category of generative models. The Gaussian mixture model uses the Gaussian probability density function of multiple normal distribution curves to quantify the variable distribution of data in the distribution area, and uses the expectation maximization (EM) algorithm to estimate the influence type of each variable. The Gaussian mixture model does not need to specify the number of clusters, has the characteristics of accurate clustering and fast clustering speed, and can be used to model and fit the complex data of extreme weather in the distribution area, solving the problem of inaccurate clustering caused by the lack of typical scenes in the distribution area under extreme weather.

[0029] S32, using variables with power supply demand as demand variable access points, matching the impact type of each demand variable access point with the preset emergency power supply rules, and evaluating the emergency power supply demand power of each demand variable access point.

[0030] The preset emergency power supply rules of this plan are mainly the power supply level table of the State Grid Corporation of China. As shown in Table 1, the power supply level of the State Grid Corporation of China is divided into four levels from high to low.

[0031] Table 1 State Grid Corporation of China power reporting level table

[0032] Step S23 specifically includes the following method: S231, obtaining the power supply level table of the State Grid Corporation, and searching the power supply level matching each demand variable access point in the power supply level table of the State Grid Corporation: for a demand variable access point of a direct impact type, matching the first power supply level; for a demand variable access point of an indirect impact type, matching the second power supply level; As can be seen from Table 1, the direct and indirect impact types under extreme weather conditions are mainly for the first and second power protection levels; the first power protection level is the power protection for power distribution area failures caused by extreme weather; the second level is the power protection for power shortage caused by extreme temperature weather. The duration of the first and second power protection levels is respectively t FST and t SEC , the emergency power supply of the first and second power supply levels of the distribution station area p LFST and p LSEC They are:

[0033] Where: p MA1 and p MA2 They are the power requirements for the first and second power protection levels under extreme weather conditions. The power required for the first power protection level is the power required by the distribution equipment after eliminating the faulty equipment in the distribution area. The power required for the second power protection level is the backup power, that is, the overall power of the distribution area. p MASUM Subtract the power provided by the grid p OU ; e EFST and e ESEC The capacities provided for electric vehicles under the first power supply level and the second power supply level respectively; p EFST and p ESEC The power provided by the electric vehicle at the first power protection level and the second power protection level respectively; ϖ The discharge efficiency of electric vehicle batteries.

[0034] S232 uses the emergency supply power of the distribution area corresponding to the power supply level as the emergency supply demand power of the matching demand variable access point; specifically, the emergency supply power of the distribution station area corresponding to the first power supply level is used as the emergency supply demand power of the demand variable access point of the direct impact type; the emergency supply power of the distribution station area corresponding to the second power supply level is used as the emergency supply demand power of the demand variable access point of the indirect impact type.

[0035] Step 3: Construct a multi-view feature portrait of electric vehicles; The adjustable power of electric vehicles participating in the emergency supply of distribution stations is closely related to the travel and charging and discharging habits of electric vehicle users. The travel and charging and discharging characteristics of electric vehicle users are affected by the traffic status of urban and rural transportation networks. Therefore, under the condition of the integration of distribution network and transportation network, the multi-perspective portrait of electric vehicle users is the basis for calculating the adjustable power of emergency supply in distribution stations. The travel and charging and discharging characteristic indicators of electric vehicle users include time characteristics, spatial characteristics and charging and discharging characteristics. The characteristic indicators corresponding to the time characteristics of electric vehicle users include the start time of electric vehicles, the parking time of electric vehicles, the driving time with traffic congestion, the parking time of electric vehicles, and the charging and discharging time of electric vehicles; the characteristic indicators corresponding to the spatial characteristics of electric vehicle users include: the starting and parking locations of electric vehicle travel, and the driving routes; the characteristic indicators corresponding to the charging and discharging of electric vehicles include: the charging and discharging power of electric vehicles, the starting and ending power of charging, the power consumption of driving mileage, and the charging and discharging efficiency.

[0036] The specific method of step three includes: obtaining characteristic indicators of the electric vehicle; the characteristic indicators include time characteristics, space characteristics and charge and discharge characteristics; Based on the relative entropy identification method, the conflicts among time features, space features and charge-discharge features are compared, and the weight of each feature index is determined based on the conflict comparison results. This step specifically includes: Calculate characteristic index j The amount of information that affects the emergency supply of distribution stations h j : ; Where: n A Indicates the total number of feature indicators; s j Characteristic index j The standard deviation of l jk Characteristic index k To feature index j Pearson correlation coefficient between ; when h j The larger the characteristic index is, j The greater the amount of information contained, the more important it is for the characteristic index. j Empowerment, empowerment weight w j for:

[0037] Superimpose the aggregated eigenvalues ​​on the weights of each eigenvalue r EV , get the weight of each characteristic index; the summary characteristic value r EVge According to the following formula:

[0038] Where: r SEV j Characteristic index j The characteristic value of .

[0039] The relative entropy identification method (criteria importance through intercriteria correlation, CRITIC) is a decision analysis method with multiple attributes, which is usually used to solve the problem of describing multiple rules. The relative entropy identification method is used to compare the conflicts between time features, spatial features and charge and discharge features. The conflict results are used as the objective weight basis for determining each feature index, realizing the accurate characterization of the multi-perspective features of electric vehicles.

[0040] Step 4: Combine the multi-perspective feature portraits and emergency supply demand assessment results to conduct a spatiotemporal matching analysis of electric vehicle discharge and emergency supply in distribution stations, and implement emergency supply regulation in distribution stations under the constraints of electric vehicle discharge.

[0041] Step 4 specifically includes the following methods: S41, constructing a callable electric vehicle list based on the multi-view feature portrait of the electric vehicle; When the distribution area is in emergency, the spatial characteristics of electric vehicles determine the spatial distribution of electric vehicles in the urban and rural transportation network. The time characteristics of electric vehicles are the time dimensions of electric vehicles superimposed on the spatial dimensions of electric vehicles, thus forming the spatiotemporal distribution characteristics of electric vehicles. The charging and discharging characteristics of electric vehicles add the electric energy dimension information to the spatiotemporal distribution characteristics of electric vehicles. The electric power information of electric vehicles affects the charging and discharging time, driving path and other spatiotemporal distribution characteristics of electric vehicles. Therefore, in the case of vehicle-grid coupling, the time, space, and charging and discharging characteristics of electric vehicles affect each other and jointly determine the adjustable power of electric vehicles participating in the emergency supply of distribution areas.

[0042] Therefore, this solution builds a callable electric vehicle list based on all characteristic indicators, transportation network, electric vehicle power and other data: the electric vehicle deployment threshold Electric vehicles with a value greater than the preset deployment threshold are considered as available electric vehicles; the electric vehicle deployment threshold Calculated according to the following formula:

[0043] Where: n B is the number of electric vehicles; c i For the i The characteristic values ​​of electric vehicles; s j For the j The characteristic value of a characteristic indicator.

[0044] S42, based on the improved weighted bipartite graph optimal matching method, combined with the emergency supply demand assessment results and the list of available electric vehicles, the vehicle-grid time-space matching calculation is performed, and the distribution station area emergency supply deployment instructions are generated and distributed to each available electric vehicle; The time-space matching of the vehicle network refers to the time-space correspondence between electric vehicles and the emergency supply demand of the distribution station area by matching the power and duration of the emergency supply of the distribution station area with electric vehicles with suitable geographical locations, driving trajectories, and power. The driving trajectory of electric vehicles is the basis for the distribution station area to carry out emergency supply. By monitoring the current location of electric vehicles and the traffic network of power, the driving status, discharge demand, power, etc. of electric vehicles can be analyzed. Based on the running trajectory of electric vehicles, the deployment analysis of electric vehicles participating in the emergency supply of the distribution station area is carried out.

[0045] Improved weighted bipartite graph optimal matching method (karnik-mendel, KM) is a data allocation method suitable for vehicle-grid spatiotemporal matching. Improved weighted bipartite graph optimal matching method is improved from the traditional Hungarian algorithm; this method configures weights on the bipartite graph, thereby converting the vehicle-grid spatiotemporal matching calculation into a labeled matching calculation on the bipartite graph. In the improved weighted bipartite graph optimal matching method, the optimal bipartite graph matching is the best vehicle-grid spatiotemporal matching method. Improved weighted bipartite graph optimal matching method has the characteristics of accurate matching and high data analysis efficiency, and can effectively solve the optimization problem of vehicle-grid spatiotemporal matching.

[0046] Specifically, the vehicle-network time-space matching result is calculated according to the following formula: g ST :

[0047] Where: n C is the total number of available electric vehicles; n D The total number of access points for the demand variables in the distribution area; For distribution area to j The traffic time of the access point of the demand variable; For the i A characteristic value that can be used to ensure emergency supply of electric vehicles to the distribution station area; Electric vehicle discharge constraints include: ; Where: represents the load power of the j-th output electric vehicle; n E Indicates the total number of electric vehicles with output; t IN Time for emergency power supply to distribution stations; Ensure power supply to meet the needs of the distribution station area.

[0048] S43, if the available electric vehicles accept the emergency supply and deployment instructions of the distribution station area, each available electric vehicle is deployed to the matching demand variable access point; otherwise, the vehicle-grid time-space matching calculation is re-performed until all available electric vehicles accept the emergency supply and deployment instructions of the distribution station area.

[0049] Embodiment 2: This embodiment provides a distribution network area emergency supply system based on vehicle-grid time-space matching, which is used to implement the distribution network area emergency supply method based on vehicle-grid time-space matching described in Embodiment 1, such as Figure 2 As shown, the system comprises: The acquisition module is used to obtain environmental meteorological data and electrical operation data of the distribution station area under extreme weather conditions; The analysis and estimation module is used to analyze the operation characteristics of the distribution area based on the environmental meteorological data and the electrical operation data of the distribution area, and to evaluate the emergency supply demand of the distribution area according to the analysis results of the operation characteristics of the distribution area; A building block for constructing multi-view feature portraits of electric vehicles; The control module is used to combine multi-perspective feature portraits and emergency supply demand assessment results to conduct spatiotemporal matching analysis of electric vehicle discharge and emergency supply in distribution stations, and to achieve emergency supply control in distribution stations under the constraints of electric vehicle discharge.

[0050] Embodiment 3: This embodiment provides a computer-readable medium on which a computer program is stored. The computer program is executed by a processor to implement the method for emergency power supply in a distribution station area based on time-space matching of a vehicle network as described in Embodiment 1. Specifically, the following steps are performed: Step 1: Obtain environmental meteorological data and electrical operation data of distribution substation areas under extreme weather conditions; Step 2: Analyze the operation characteristics of the distribution substation area based on the environmental meteorological data and the electrical operation data of the distribution substation area, and evaluate the emergency supply demand of the distribution substation area according to the analysis results of the operation characteristics of the distribution substation area; Step 3: Construct a multi-view feature portrait of electric vehicles; Step 4: Combine the multi-perspective feature portraits and emergency supply demand assessment results to conduct a spatiotemporal matching analysis of electric vehicle discharge and emergency supply in distribution stations, and implement emergency supply regulation in distribution stations under the constraints of electric vehicle discharge.

[0051] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. The method for emergency power supply in distribution area based on time-space matching of vehicle network is characterized by: include: Obtain environmental meteorological data and electrical operation data of distribution substations under extreme weather conditions; Analyze the operation characteristics of the distribution area based on the environmental meteorological data and the electrical operation data of the distribution area, and evaluate the emergency supply demand of the distribution area based on the analysis results of the operation characteristics of the distribution area; Construct a multi-view feature portrait of electric vehicles; Combining multi-perspective feature portraits and emergency supply demand assessment results, a spatiotemporal matching analysis of electric vehicle discharge and emergency supply in distribution stations is conducted, and emergency supply regulation in distribution stations is achieved under the constraints of electric vehicle discharge.

2. The method for emergency power supply in distribution area based on vehicle-grid time-space matching according to claim 1 is characterized in that: The environmental meteorological data include: temperature, ground pressure, wind speed, wind direction, relative humidity, precipitation and solar radiation in the target area; the sampling frequency of environmental meteorological data is F1 times per day; The electrical operation data of the distribution substation area includes: current, voltage, power and power factor on the distribution transformer side; the sampling frequency of the electrical operation data of the distribution substation area is F2 times per day; F2>F1.

3. The method for emergency power supply in distribution area based on vehicle-grid time-space matching according to claim 1 is characterized in that: The analysis of the operation characteristics of the distribution station area is performed based on the environmental meteorological data and the electrical operation data of the distribution station area, and the emergency supply demand assessment of the distribution station area is performed according to the analysis results of the operation characteristics of the distribution station area; including method: Analyze the electrical operation characteristics and impact types of the distribution area affected by extreme weather: When the electrical operation characteristics of the distribution area equipment caused by extreme weather are disconnection faults, short circuit faults or grounding faults, configure it as a direct impact type; When the electrical operation characteristics of the distribution substation area caused by extreme weather are insufficient power supply capacity or line overload, it is configured as an indirect impact type; Taking the electrical operation characteristics as variables, quantifying the variable distribution of the distribution station area based on the Gaussian mixture model, and estimating the impact type of each variable; The variables with power supply demand are used as demand variable access points. The impact type of each demand variable access point is matched with the preset emergency power supply rules to evaluate the emergency power supply demand power of each demand variable access point.

4. The method for emergency power supply in distribution area based on vehicle-grid time-space matching according to claim 3 is characterized in that: The Gaussian mixture model is used to quantify the distribution of variables in the distribution area and estimate the impact type of each variable; including: process: Probability density function of each electrical operation feature cluster at the yth point using the Gaussian mixture model p DSA ( y )for: ； Where: It means the sum of all electrical operation characteristics, and Z represents the total number of electrical operation characteristics; a z The mixing coefficient representing the Gaussian distribution electrical operating characteristic z; represents the sum of the covariances of all electrical operating characteristics; μ z Represents the typical characteristic value of the electrical operating characteristic z; is the Gaussian distribution density function of the electrical operation characteristic z; When classifying the electrical operating characteristics z, the Gaussian distribution density function is decomposed into: ； Where: d The number of dimensions that characterize electrical operation; μ Represents the mean value of electrical operating characteristics; represents the covariance of electrical operating characteristics; Determinant representing the covariance of the electrical operating characteristics.

5. The method for emergency power supply in distribution area based on vehicle-grid time-space matching according to claim 3 is characterized in that: The method includes matching the impact type of each demand variable access point with the preset emergency power supply rule to evaluate the emergency power supply demand power of each demand variable access point; Obtain the power supply level table of the State Grid Corporation, and search for the power supply level that matches each demand variable access point in the power supply level table of the State Grid Corporation: for the demand variable access point of the direct impact type, match the first power supply level; for the demand variable access point of the indirect impact type, match the second power supply level; The emergency power supply of the distribution area corresponding to the power supply level is used as the emergency power supply demand power of the access point matching the demand variable.

6. The method for emergency power supply in distribution area based on vehicle-grid time-space matching according to claim 1 is characterized in that: The method of constructing a multi-view feature portrait of an electric vehicle includes: Acquiring characteristic indicators of the electric vehicle; the characteristic indicators include time characteristics, space characteristics and charge and discharge characteristics; The conflicts among time features, space features and charge-discharge features are compared based on the relative entropy identification method, and the weight of each feature index is determined based on the conflict comparison results.

7. The method for emergency power supply in distribution area based on vehicle-grid time-space matching according to claim 3 is characterized in that: The multi-perspective feature portrait and emergency supply demand assessment results are combined to conduct a spatiotemporal matching analysis between electric vehicle discharge and emergency supply in distribution stations, and to achieve emergency supply control in distribution stations under the constraints of electric vehicle discharge. Included methods: Build a list of available electric vehicles based on multi-view feature portraits of electric vehicles; Based on the improved weighted bipartite graph optimal matching method, the vehicle-grid spatiotemporal matching calculation is performed in combination with the emergency supply demand assessment results and the list of available electric vehicles, and the distribution area emergency supply dispatch instructions are generated and distributed to each available electric vehicle; If the available electric vehicles accept the emergency supply and deployment instructions of the distribution station area, each available electric vehicle will be deployed to the matching demand variable access point; otherwise, the vehicle-grid time-space matching calculation is performed again until all available electric vehicles accept the emergency supply and deployment instructions of the distribution station area.

8. The method for emergency power supply in distribution area based on vehicle-grid time-space matching according to claim 7 is characterized in that: The method for calculating the vehicle-grid spatiotemporal matching includes: The vehicle-network spatiotemporal matching result is calculated according to the following formula g ST : ; Where: n C is the total number of available electric vehicles; n D The total number of access points for the demand variables in the distribution area; For distribution area to j The traffic time of the access point of the demand variable; For the i A characteristic value that can be used to ensure emergency supply of electric vehicles to the distribution station area; Electric vehicle discharge constraints include: ; In the formula: In the formula: represents the load power of the j-th output electric vehicle; n E Indicates the total number of electric vehicles with output; t IN Time for emergency power supply to distribution stations; Ensure power supply to meet the needs of the distribution station area.

9. The distribution area emergency supply system based on vehicle-grid time-space matching is characterized by: The system for implementing the method for ensuring emergency power supply in a distribution area based on vehicle-grid time-space matching according to any one of claims 1 to 8 comprises: The acquisition module is used to obtain environmental meteorological data and electrical operation data of the distribution station area under extreme weather conditions; The analysis and estimation module is used to analyze the operation characteristics of the distribution area based on the environmental meteorological data and the electrical operation data of the distribution area, and to evaluate the emergency supply demand of the distribution area according to the analysis results of the operation characteristics of the distribution area; A building block for constructing multi-view feature portraits of electric vehicles; The control module is used to combine multi-perspective feature portraits and emergency supply demand assessment results to conduct spatiotemporal matching analysis of electric vehicle discharge and emergency supply in distribution stations, and to achieve emergency supply control in distribution stations under the constraints of electric vehicle discharge.

10. A computer readable medium having a computer program stored thereon, characterized in that: The computer program is executed by a processor to implement the distribution station area emergency power supply method based on vehicle-grid time-space matching as described in any one of claims 1-8.

Images