Optical storage and charging V2G-based user behavior perception hierarchical group control method and system

Abstract

The invention discloses a hierarchical group control method and system based on optical storage and charging V2G user behavior perception, and relates to the technical field of data processing, and the main technical scheme comprises the steps: determining at least one piece of first simulation state data from at least two pieces of first simulation state data as clustering center data; performing relevancy calculation on the at least one piece of clustering center data and second simulation state data to obtain a first relevancy between each piece of clustering center data and the second simulation state data; determining the second simulation state data of which the first relevancy is greater than a first preset threshold value as target simulation state data for each piece of clustering center data; and distributing the target to-be-scheduled resources corresponding to the target simulation state data to the clustering groups corresponding to the clustering center data. Compared with the prior art, the scheduling resources with similar state data are allocated to the same cluster group, and the scheduling accuracy of the to-be-scheduled resources is improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of data processing, and in particular, to a hierarchical group control method and system for optical storage charging V2G user behavior perception. Background Art

[0002] Vehicle-to-grid (V2G) technology refers to the technology that electric vehicles and the power grid can charge and discharge each other. V2G technology can convert electric vehicles into distributed energy storage units for power grid dispatching, that is, electric vehicles are used as a dispatching resource. Each dispatching resource includes an energy boundary and a power boundary. The power grid schedules energy according to the energy boundary and power boundary of the dispatching resource. Due to the large number of dispatching resources, calculating the energy boundary and power boundary of each dispatching resource separately consumes a large amount of computing resources. In order to reduce the consumption of computing resources, it is necessary to aggregate the dispatching resources.

[0003] The existing method is to aggregate all dispatching resources into a total dispatching resource, and directly add the energy boundaries and power boundaries of all dispatching resources as the energy boundary and power boundary of the total dispatching resource.

[0004] Since the actual usage status of each dispatching resource is different, directly adding the energy boundaries and power boundaries of all dispatching resources cannot reflect the actual dispatching demand, resulting in a large error between the energy for resource scheduling and the energy of the actual demand. Summary of the Invention

[0005] The present disclosure provides a hierarchical group control method and system for optical storage charging V2G user behavior perception. Its main purpose is to solve the problem that since the actual usage status of each dispatching resource is different, directly adding the energy boundaries and power boundaries of all dispatching resources cannot reflect the actual dispatching demand, resulting in a large error between the energy for resource scheduling and the energy of the actual demand.

[0006] According to the first aspect of the present disclosure, a hierarchical group control method for optical storage charging V2G user behavior perception is provided, which includes: Determine at least one first simulation state data as clustering center data from at least two first simulation state data, and each clustering center data serves as the center data for generating a clustering group; wherein, the first simulation state data is the first simulation state data corresponding to the resource to be dispatched; Calculate the correlation between each of the at least one clustering center data and the second simulation state data to obtain a first correlation between each clustering center data and the second simulation state data; the second simulation state data is any first simulation state data other than the clustering center data in the first simulation state data; For each cluster center data, determine the second simulated state data with the first correlation degree greater than the first preset threshold as the target simulated state data; Allocate the target to-be-scheduled resources corresponding to the target simulated state data to the cluster groups corresponding to each cluster center data, so as to schedule the to-be-scheduled resources in the cluster groups.

[0007] Optionally, the determining at least one first simulated state data as the cluster center data from at least two first simulated state data includes: Select a preset number of first simulated state data as the to-be-cluster-center data to obtain the to-be-cluster-center data of the preset number; the correlation degree between the to-be-cluster-center data is greater than the second preset threshold, and the preset number is less than the total number of the at least two to-be-scheduled resources; Regarding each cluster center data as the center data for generating a cluster group includes: Regarding each to-be-cluster-center data as the center data for generating a cluster group; Call a preset cluster center calculation algorithm to calculate the to-be-cluster-center data of the preset number to obtain the cluster center data of the preset number.

[0008] Optionally, the calling a preset cluster center calculation algorithm to calculate the to-be-cluster-center data of the preset number to obtain the cluster center data of the preset number includes: Calculate the correlation degree between the to-be-cluster-center data of the preset number and the third simulated state data respectively to obtain the second correlation degree between at least one to-be-cluster-center data and the third simulated state data; the third simulated state data is any first simulated state data other than the to-be-cluster-center data in the first simulated state data; Determine the cluster center data of the preset number according to the second correlation degree between at least one to-be-cluster-center data and the third simulated state data.

[0009] Optionally, the determining the cluster center data of the preset number according to the second correlation degree between at least one to-be-cluster-center data and the third simulated state data includes: For each to-be-cluster-center data, update the third simulated state data with the second correlation degree greater than the first preset threshold into the cluster groups corresponding to each to-be-cluster-center data; Calculate the average value of the to-be-cluster-center data and the third simulated state data in the cluster groups corresponding to each to-be-cluster-center data respectively to obtain the to-be-cluster-center data of the preset number after update; Calculate the correlation between each of the updated data of the to-be-clustered centers with the preset number and the third simulated state data until the data of the to-be-clustered centers stops updating, to obtain the data of the clustered centers with the preset number.

[0010] Optionally, the calculating the correlation between each of the at least one data of the clustered centers and the second simulated state data to obtain the first correlation between each data of the clustered centers and the second simulated state data includes: Obtain the first simulated position, the first simulated arrival time, the first simulated departure time, the first simulated remaining power upon arrival, and the first simulated remaining power upon departure in the data of the clustered centers; Obtain the second simulated position, the second simulated arrival time, the second simulated departure time, the second simulated remaining power upon arrival, and the second simulated remaining power upon departure in the second simulated state data; Obtain the first weight parameter corresponding to the first simulated position and the second simulated position, obtain the second weight parameter corresponding to the first simulated arrival time, the first simulated departure time, the second simulated arrival time, and the second simulated departure time, and obtain the third weight parameter corresponding to the first simulated remaining power upon arrival, the first simulated remaining power upon departure, the second simulated remaining power upon arrival, and the second simulated remaining power upon departure; Call a preset correlation algorithm to calculate the first simulated position, the first simulated arrival time, the first simulated departure time, the first simulated remaining power upon arrival, the first simulated remaining power upon departure, the second simulated position, the second simulated arrival time, the second simulated departure time, the second simulated remaining power upon arrival, the second simulated remaining power upon departure, the first weight parameter, the second weight parameter, and the third weight parameter to obtain the first correlation.

[0011] Optionally, the calling a preset correlation algorithm to calculate the first simulated position, the first simulated arrival time, the first simulated departure time, the first simulated remaining power upon arrival, the first simulated remaining power upon departure, the second simulated position, the second simulated arrival time, the second simulated departure time, the second simulated remaining power upon arrival, the second simulated remaining power upon departure, the first weight parameter, the second weight parameter, and the third weight parameter to obtain the first correlation includes: Calculate the difference between the first simulated position and the second simulated position, calculate the difference between the first simulated arrival time and the second simulated arrival time, calculate the difference between the first simulated departure time and the second simulated departure time, calculate the difference between the first simulated remaining power upon arrival and the second simulated remaining power upon arrival, calculate the difference between the first simulated remaining power upon departure and the second simulated remaining power upon departure, and obtain the corresponding difference results; Calculate the square of each of the corresponding difference results respectively to obtain the square results corresponding to the respective difference results; Perform a product calculation of the first weight parameter, the second weight parameter, and the third weight parameter with the corresponding square results respectively to obtain the corresponding product value results; Calculate the first correlation degree according to the corresponding product value results.

[0012] Optionally, the calculating the first correlation degree according to the corresponding product value results includes: Perform a summation calculation on the corresponding product value results to obtain a summation result; there is a corresponding summation result between each second simulated state data and each cluster center data; Determine the maximum value among all the summation results as the target summation result; Perform a calculation of the target summation result with each summation result to obtain the first correlation degree.

[0013] Optionally, after allocating the target to-be-scheduled resource corresponding to the target simulated state data to the cluster groups corresponding to each cluster center data, the method further includes: Obtain the energy upper bound and energy lower bound of each to-be-scheduled resource in the cluster group, and obtain the power upper bound and power lower bound of each to-be-scheduled resource in the cluster group; Perform a summation calculation on the energy upper bounds of all the to-be-scheduled resources in the cluster group to obtain the total energy upper bound of the cluster group; Perform a summation calculation on the energy lower bounds of all the to-be-scheduled resources in the cluster group to obtain the total energy lower bound of the cluster group; Perform a summation calculation on the power upper bounds of all the to-be-scheduled resources in the cluster group to obtain the total power upper bound of the target cluster group; Perform a summation calculation on the power lower bounds of all the to-be-scheduled resources to obtain the total power lower bound of the target cluster group, so as to schedule all the to-be-scheduled resources based on the total energy upper bound, the total energy lower bound, the total power upper bound, and the power lower bound.

[0014] According to a second aspect of the present disclosure, there is provided a hierarchical group control system for perceiving user behavior based on optical storage charging V2G, including: A first determination unit configured to determine at least one first analog state data from at least two first analog state data as clustering center data, and each clustering center data serves as the center data for generating a clustering group; wherein, the first analog state data is the first analog state data corresponding to the resource to be scheduled; A first calculation unit configured to calculate the correlation between each of the at least one clustering center data and second analog state data, to obtain a first correlation between each clustering center data and the second analog state data; the second analog state data is any first analog state data other than the clustering center data in the first analog state data; A second determination unit configured to, for each clustering center data, determine the second analog state data with the first correlation greater than a first preset threshold as target analog state data; An allocation unit configured to allocate the target resources to be scheduled corresponding to the target analog state data to the clustering groups corresponding to each clustering center data, so as to schedule the resources to be scheduled in the clustering groups.

[0015] Optionally, the first determination unit includes: A selection module configured to select a preset number of first analog state data as data to be clustering centers, to obtain the preset number of data to be clustering centers; the correlation between the data to be clustering centers is greater than a second preset threshold, and the preset number is less than the total number of the at least two resources to be scheduled; The statement that each clustering center data serves as the center data for generating a clustering group includes: Each data to be clustering center serves as the center data for generating a clustering group; A first calculation module configured to call a preset clustering center calculation algorithm to calculate the preset number of data to be clustering centers, to obtain the preset number of the clustering center data.

[0016] Optionally, the first calculation module is further configured to calculate the correlation between the preset number of data to be clustering centers and third analog state data, to obtain a second correlation between at least one data to be clustering center and the third analog state data; the third analog state data is any first analog state data other than the data to be clustering centers in the first analog state data; determine the preset number of the clustering center data according to the second correlation between the at least one data to be clustering center and the third analog state data.

[0017] Optionally, the first calculation module is further configured to update the third simulated state data with the second relevance greater than the first preset threshold for each data to be clustered center into the clustering group corresponding to each data to be clustered center; calculate the average value of the data to be clustered center and the third simulated state data in the clustering group corresponding to each data to be clustered center, and obtain the preset number of updated data to be clustered center; calculate the relevance between the preset number of updated data to be clustered center and the third simulated state data respectively until the data to be clustered center is no longer updated, and obtain the preset number of the clustering center data.

[0018] Optionally, the first calculation unit includes: an acquisition module, configured to acquire the first simulated position, the first simulated arrival time, the first simulated departure time, the first simulated remaining power upon arrival, and the first simulated remaining power upon departure in the clustering center data; The acquisition module is further configured to acquire the second simulated position, the second simulated arrival time, the second simulated departure time, the second simulated remaining power upon arrival, and the second simulated remaining power upon departure in the second simulated state data; The acquisition module is further configured to acquire the first weight parameter corresponding to the first simulated position and the second simulated position, acquire the second weight parameter corresponding to the first simulated arrival time, the first simulated departure time, the second simulated arrival time, and the second simulated departure time, and acquire the third weight parameter corresponding to the first simulated remaining power upon arrival, the first simulated remaining power upon departure, the second simulated remaining power upon arrival, and the second simulated remaining power upon departure; a second calculation module, configured to call a preset relevance algorithm to calculate the first simulated position, the first simulated arrival time, the first simulated departure time, the first simulated remaining power upon arrival, the first simulated remaining power upon departure, the second simulated position, the second simulated arrival time, the second simulated departure time, the second simulated remaining power upon arrival, the second simulated remaining power upon departure, the first weight parameter, the second weight parameter, and the third weight parameter, and obtain the first relevance.

[0019] Optionally, the second calculation module is further configured to Calculate the difference between the first simulated position and the second simulated position, calculate the difference between the first simulated arrival time and the second simulated arrival time, calculate the difference between the first simulated departure time and the second simulated departure time, calculate the difference between the first simulated remaining power upon arrival and the second simulated remaining power upon arrival, calculate the difference between the first simulated remaining power upon departure and the second simulated remaining power upon departure, and obtain the corresponding difference results; Perform square calculations on the respective corresponding difference results to obtain the square results corresponding to the respective corresponding difference results; Perform product calculations on the first weight parameter, the second weight parameter, and the third weight parameter with the corresponding square results respectively to obtain the respective corresponding product results; Calculate the first correlation degree according to the respective corresponding product results.

[0020] Optionally, the second calculation module is further configured to, Perform summation calculations on the respective corresponding product results to obtain a summation result; there is a corresponding summation result between each second simulated state data and each cluster center data; Determine the maximum value among all the summation results as the target summation result; Perform calculations on the target summation result and each summation result respectively to obtain the first correlation degree.

[0021] Optionally, the device further includes: An acquisition unit, configured to, after allocating the target to-be-scheduled resource corresponding to the target simulated state data to the cluster groups corresponding to each cluster center data, acquire the energy upper boundary and energy lower boundary of each to-be-scheduled resource in the cluster group, and acquire the power upper boundary and power lower boundary of each to-be-scheduled resource in the cluster group; A second calculation unit, configured to perform summation calculations on the energy upper boundaries of all to-be-scheduled resources in the cluster group to obtain the total energy upper boundary of the cluster group; The second calculation unit is further configured to perform summation calculations on the energy lower boundaries of all to-be-scheduled resources in the cluster group to obtain the total energy lower boundary of the cluster group; The second calculation unit is further configured to perform summation calculations on the power upper boundaries of all to-be-scheduled resources in the cluster group to obtain the total power upper boundary of the target cluster group; The second calculation unit is further configured to perform summation calculations on the power lower boundaries of all to-be-scheduled resources to obtain the total power lower boundary of the target cluster group, so as to schedule all to-be-scheduled resources based on the total energy upper boundary, the total energy lower boundary, the total power upper boundary, and the power lower boundary.

[0022] According to a third aspect of the present disclosure, there is provided an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in the foregoing first aspect.

[0023] According to a fourth aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to execute the method described in the foregoing first aspect.

[0024] According to a fifth aspect of the present disclosure, there is provided a computer program product including a computer program, and the computer program, when executed by a processor, implements the method described in the foregoing first aspect.

[0025] For the hierarchical group control method for optical storage charging V2G user behavior perception provided by the present disclosure, at least one first analog state data is determined from at least two first analog state data as clustering center data, and each clustering center data is used as the center data for generating a clustering group; wherein, the first analog state data is the first analog state data corresponding to the resource to be scheduled; the at least one clustering center data is respectively calculated for correlation with the second analog state data to obtain a first correlation between each clustering center data and the second analog state data; the second analog state data is any first analog state data other than the clustering center data in the first analog state data; for each clustering center data, the second analog state data with the first correlation greater than a first preset threshold is determined as the target analog state data; the target resources to be scheduled corresponding to the target analog state data are allocated to the clustering groups corresponding to the respective clustering center data, so as to schedule the resources to be scheduled in the clustering groups. Compared with the related art, in the embodiment of the present disclosure, at least one first analog state data is determined from at least two first analog state data as clustering center data, the first correlation between the second analog state data and the clustering center data is calculated, and the resources to be scheduled corresponding to the analog state data with a higher first correlation are allocated to one clustering group, so that the resources to be scheduled with similar state data are allocated to the same clustering group, and the scheduling accuracy of the resources to be scheduled is improved.

[0026] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The drawings are used to better understand the present solution and do not constitute a limitation to the present disclosure. Among them: Figure 1 FIG. is a schematic flowchart of a hierarchical group control method for optical storage charging V2G user behavior perception provided by an embodiment of the present disclosure; Figure 2 FIG. is a schematic flowchart of a process of transferring travel locations provided by an embodiment of the present disclosure; Figure 3 FIG. is a schematic flowchart of a simulation method for status data of resources to be scheduled provided by an embodiment of the present disclosure; Figure 4 FIG. is a flowchart example of a method for determining clustering center data provided by an embodiment of the present disclosure; Figure 5 FIG. is a schematic flowchart of a preset clustering center calculation algorithm provided by an embodiment of the present disclosure; Figure 6 FIG. is a schematic diagram of an aggregation feasible region between different resources to be scheduled provided by an embodiment of the present disclosure; Figure 7 FIG. is an effect diagram of using the direct aggregation method for peak shaving and valley filling provided by an embodiment of the present disclosure; Figure 8 FIG. is an effect diagram of using the aggregation method of the present invention for peak shaving and valley filling provided by an embodiment of the present disclosure; Figure 9 FIG. is a schematic structural diagram of a hierarchical group control system for optical storage charging V2G user behavior perception provided by an embodiment of the present disclosure; Figure 10 FIG. is a schematic structural diagram of a hierarchical group control system for optical storage charging V2G user behavior perception provided by an embodiment of the present disclosure; Figure 11 FIG. is a schematic block diagram of an exemplary electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] The following describes exemplary embodiments of the present disclosure with reference to the drawings. Various details of the embodiments of the present disclosure are included to assist in understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for clarity and conciseness, descriptions of well-known functions and structures are omitted below.

[0029] The following describes the hierarchical group control method and system for optical storage charging V2G user behavior perception according to embodiments of the present disclosure with reference to the drawings.

[0030] Figure 1A flowchart of a hierarchical group control method for V2G user behavior perception based on optical storage and charging provided by an embodiment of the present disclosure.

[0031] As Figure 1 shown, this method is applied to a server, and the method includes the following steps: Step 101: Determine at least one first simulated state data from at least two first simulated state data as cluster center data, and each cluster center data serves as the center data for generating a cluster group; wherein, the first simulated state data is the first simulated state data corresponding to the resource to be scheduled.

[0032] The scheduling resource is some power sources and loads in the power grid that can have their power controlled. For example, when arranging for electric vehicles participating in V2G to charge and discharge, the electric vehicle is a scheduling resource. However, it should be clear that this statement is not intended to limit the scheduling resource to only electric vehicles, and it can also be some power sources and loads in the power grid that can have their power controlled; the simulated state data is the state data when simulating the use of the resource to be scheduled. The simulated state data includes, but is not limited to, the simulated location when the resource to be scheduled is used, the simulated arrival time when the resource to be scheduled arrives at the simulated location, the simulated departure time when the resource to be scheduled leaves the simulated location, the simulated remaining power when the resource to be scheduled arrives at the simulated location, and the simulated remaining power when the resource to be scheduled leaves the simulated location. The simulated location can be longitude and latitude, and the specific form of expression of the simulated location in the embodiment of the present disclosure is not limited; the cluster center data is the center data in the cluster group. A cluster group contains multiple simulated state data, and the cluster center data can be the average or median of multiple simulated state data in a cluster group.

[0033] The simulated state data of the resource to be scheduled is obtained by simulating through a preset state data simulation model. Among them, the preset state data simulation model is a model obtained by training an initial state data model using a preset training state data set, and the preset training state data is the historical state data of the resource to be scheduled.

[0034] The trip chains of the resources to be scheduled are divided into 9 types: home - home, home - locations other than home and workplace, home - workplace, workplace - home, locations other than home and workplace - locations other than home and workplace, locations other than home and workplace - workplace, workplace - home, workplace - locations other than home and workplace, and workplace - workplace. The training state dataset contains a large amount of historical state data of the resources to be scheduled. The training dataset is a very large dataset. Using the historical state data in the training dataset as input, a preset state data simulation model is constructed. The preset state data simulation model is divided into 4 parts: the first departure time of the resources to be scheduled, the transfer of the trip locations of the resources to be scheduled, the residence time of the resources to be scheduled, the trip simulation of the resources to be scheduled, and the total trip end condition.

[0035] Among them, the probability distributions of the trip time and the residence time are the gamma distribution and the mixture Gaussian distribution respectively, which can be directly fitted using the trip data. The probability density functions of the trip time and the residence time can be realized through Formula (1) and Formula (2):

[0036]

[0037] Among them, α, β, K, ρ, μ, σ are all undetermined parameters, which can be obtained by fitting the historical state data. Xi (i = 1, 2, 3) is the user's residence location, where i taking values 1, 2, 3 respectively represents home, locations other than home and workplace, and workplace.

[0038] The transfer of the trip locations can be described by a Markov process. For better understanding of the transfer of the trip locations, as Figure 2 shown, Figure 2 is a schematic flow diagram of the transfer of a trip location provided by an embodiment of the present disclosure. Denote the set of trip locations as X = {X1, X2, X3}, and use the set X as the value range of the state quantity Si (i = 1, 2,..., n) of the Markov process. The initial state is approximately calculated by the frequencies of the types of each location at the first departure in the statistical data, and the process state probability can also be approximately calculated by the frequencies. Specifically, count the number of resources to be scheduled for home - home, home - locations other than home and workplace, home - workplace, workplace - home, locations other than home and workplace - locations other than home and workplace, locations other than home and workplace - workplace, workplace - home, workplace - locations other than home and workplace, and workplace - workplace in each time period in the training state dataset (C = 1, 2, …, 9), where C = 1, 2, …, 9 respectively represent home - home, home - location other than home and workplace, home - workplace, workplace - home, location other than home and workplace - location other than home and workplace, location other than home and workplace - workplace, workplace - home, workplace - location other than home and workplace, and workplace - workplace. Then, the probability of the travel type with respect to time can be achieved through formula (3): (3) where, is the travel mode of the resource to be scheduled at time t, is any one of the travel modes of the resource to be scheduled among home - workplace, workplace - home, location other than home and workplace - location other than home and workplace, location other than home and workplace - workplace, workplace - home, workplace - location other than home and workplace, and workplace - workplace; Therefore, the state transition matrix A(t) of the resource to be scheduled can be achieved through formula (4): (4) where, is the probability that the resource to be scheduled travels from one travel location to another at time t.

[0039] The single - day itinerary simulation of the resource to be scheduled adopts Monte Carlo simulation. The simulation time uses discrete time, with minutes as the minimum time scale. The end condition of the total itinerary is that the travel state of the resource to be scheduled is home again or the current time is later than 23:59 on the same day. For better understanding of the simulation of the state data of the resource to be scheduled, as Figure 3 shown, Figure 3 is a schematic flow chart of a method for simulating the state data of a resource to be scheduled provided by an embodiment of the present disclosure. After N simulations (N is the total number of resources to be scheduled in a specific area), a simulation state data set of the arrival simulation time when the resource to be scheduled in the resource cluster to be scheduled in a specific area arrives at the simulation location, the departure simulation time when the resource to be scheduled leaves the simulation location, the remaining power at the simulation arrival when the resource to be scheduled reaches the simulation location, and the remaining power at the simulation departure when the resource to be scheduled leaves the simulation location can be obtained. This data set can depict the schedulable power boundary and energy boundary of each resource to be scheduled throughout the day.

[0040] To calculate the correlation between different simulated state data, two simulated state data are required. Calculating the correlation between each simulated state data and all other simulated state data separately would result in a large amount of data. By determining at least one first simulated state data from at least two first simulated state data as the clustering center data and calculating the correlation between the clustering center data and all other simulated state data separately, the amount of data for correlation calculation can be reduced, the consumption of computing resources can be lowered, and the computing efficiency can be improved.

[0041] Step 102: Calculate the correlation between each of the at least one clustering center data and the second simulated state data to obtain the first correlation between each clustering center data and the second simulated state data; the second simulated state data is any first simulated state data other than the clustering center data among the first simulated state data.

[0042] The correlation is used to measure the correlation between two simulated state data. The greater the correlation, the higher the correlation between the two simulated state data.

[0043] To better understand the calculation of the first correlation between each of the at least one clustering center data and the second simulated state data, an example is provided. Suppose there are two clustering center data, namely a and b, and there are four second simulated state data, namely c, d, e, and f. Calculate the first correlations between a and c, a and d, a and e, a and f, b and c, b and d, b and e, and b and f respectively.

[0044] The calculation method of the correlation between two simulated state data can be obtained by calculating the two simulated state data through a preset correlation algorithm. The calculation formula of the preset correlation algorithm can be implemented by formula (5): (5) Among them, The definitions of and γ can be implemented by formula (6) and formula (7) respectively: (6) (7) Among them, is a preset second weight parameter, is a preset first weight parameter, is a preset third weight parameter, is the simulated arrival time of a simulated state data, is the simulated arrival time of another simulated state data, is the simulated departure time of a simulated state data, is the simulated departure time of another piece of simulated state data, and is the simulated position of a piece of simulated state data, and is the simulated position of another piece of simulated state data, is the simulated remaining battery power upon arrival of a piece of simulated state data, is the simulated remaining battery power upon arrival of another piece of simulated state data, is the simulated remaining battery power upon departure of a piece of simulated state data, is the simulated remaining battery power upon departure of another piece of simulated state data.

[0045] By calculating the first correlation degree between the clustering center data and the second simulated state data, it can help determine which second simulated state data are more suitable to be assigned to the clustering group where the specific clustering center data is located, thereby achieving more effective resource scheduling and management.

[0046] Step 103: For each piece of clustering center data, determine the second simulated state data with the first correlation degree greater than the first preset threshold as the target simulated state data.

[0047] There is a corresponding first correlation degree between different clustering center data and different second simulated state data. By setting the first correlation degree to be greater than the first preset threshold, the second simulated state data highly correlated with the clustering center data can be screened out. These data can be considered as data having a strong connection with the clustering center data, and thus are determined as the target simulated state data. In this way, more accurate matching of appropriate data and resources can be achieved in subsequent resource allocation and scheduling.

[0048] For ease of understanding, an example is provided. Suppose there are two pieces of clustering center data, namely a and b, and there are four pieces of second simulated state data, namely c, d, e, and f. The first correlation degrees between a and c, a and d, a and e, a and f, b and c, b and d, b and e, and b and f are 8, 7, 9, 3, 4, 2, 5, and 8 respectively, and the first preset threshold is 6. Since the first correlation degrees between a and c, a and d, and a and e are greater than the first preset threshold, so c, d, and e are the target simulated state data of a, and the first correlation degree between b and f is greater than the first preset threshold, so f is the target simulated state data of b.

[0049] Step 104: Allocate the target resources to be scheduled corresponding to the target simulated state data to the clustering groups corresponding to each piece of clustering center data, so as to schedule the resources to be scheduled in the clustering groups.

[0050] By allocating the to-be-scheduled resources corresponding to the target simulation state data to the clustering groups corresponding to each clustering center data, more refined management and scheduling of the to-be-scheduled resources can be achieved. This can better optimize the utilization efficiency of the to-be-scheduled resources and improve the usage rate of the to-be-scheduled resources.

[0051] For the sake of easy understanding, an example is provided. Suppose there are two clustering center data, namely a and b, and there are four second simulation state data, namely c, d, e, and f. The clustering group corresponding to a is g, the clustering group corresponding to b is h, the target simulation state data of a are c, d, and e, and the target simulation state data of b is f. The to-be-scheduled resources corresponding to c, d, and e are respectively allocated to g, and the to-be-scheduled resources of f are allocated to h.

[0052] The hierarchical group control method for user behavior perception based on photovoltaic-storage-charging V2G provided by the present disclosure determines at least one first simulation state data as clustering center data from at least two first simulation state data, and each clustering center data serves as the center data for generating a clustering group; wherein, the first simulation state data is the first simulation state data corresponding to the to-be-scheduled resources; calculating the correlation degree between each clustering center data and the second simulation state data respectively to obtain the first correlation degree between each clustering center data and the second simulation state data; the second simulation state data is any first simulation state data other than the clustering center data in the first simulation state data; for each clustering center data, determining the second simulation state data with the first correlation degree greater than the first preset threshold as the target simulation state data; allocating the target to-be-scheduled resources corresponding to the target simulation state data to the clustering groups corresponding to each clustering center data so as to schedule the to-be-scheduled resources in the clustering groups. Compared with the related technology, in the embodiment of the present disclosure, by determining at least one first simulation state data as clustering center data from at least two first simulation state data, calculating the first correlation degree between the second simulation state data and the clustering center data, and allocating the to-be-scheduled resources corresponding to the simulation state data with a higher first correlation degree to a clustering group, it is realized that the scheduling resources with similar state data are allocated to the same clustering group, and the scheduling accuracy of the to-be-scheduled resources is improved.

[0053] As a refinement of step 101, when performing the step of determining at least one first simulation state data as clustering center data from at least two first simulation state data, it can be implemented in but not limited to the following ways, such as Figure 4 shown Figure 4 is a flow example diagram of a method for determining clustering center data provided by an embodiment of the present disclosure, including: Step 201: Select a preset number of first simulated state data as the data to be clustered centers, obtaining the preset number of data to be clustered centers; the correlation between the data to be clustered centers is greater than a second preset threshold, and the preset number is less than the total number of the at least two resources to be scheduled.

[0054] The number of the data of the clustering centers is preset in advance, that is, the preset number, and the preset number can be any value, which is not limited in the embodiments of the present disclosure; the data to be clustered centers are randomly selected from all the first simulated state data, but the correlation between the data to be clustered centers needs to be greater than the second preset threshold, which can prevent the correlation between the randomly selected data to be clustered centers from being too close, affecting the selection of the data of the clustering centers. Among them, the second preset threshold can be the same as or different from the first preset threshold, and the specific values of the second preset threshold and the first preset threshold are not limited in the embodiments of the present disclosure.

[0055] For the convenience of understanding, an example is provided. Assume that there are 6 pieces of first simulated state data, namely a, b, c, d, e, f, the preset number is 2, and if the randomly selected data to be clustered centers are c and f, and the correlation between c and f is greater than the second preset threshold, then c and f are determined as the data to be clustered centers.

[0056] Step 202: Each data of the clustering centers being used as the center data for generating a clustering group includes: Each data to be clustered center is used as the center data for generating a clustering group.

[0057] Each data to be clustered center is assigned to the corresponding clustering group, and there is only one data to be clustered in a clustering group. By using each data to be clustered center as the center of a clustering group, the characteristics and attributes of the clustering group can be more intuitively understood.

[0058] Step 203: Invoke a preset clustering center calculation algorithm to calculate the preset number of data to be clustered centers, obtaining the preset number of the data of the clustering centers.

[0059] For the convenience of better understanding the determination process of the data of the clustering centers, as Figure 5 shown, Figure 5It is a schematic flowchart of a preset clustering center calculation algorithm provided by an embodiment of the present disclosure. The relevance between each data to be clustered center is calculated respectively with each third simulated state data, and the third simulated state data with a relatively high relevance to the data to be clustered center is assigned to the clustering group corresponding to the data to be clustered center. The average value of all the simulated state data in the clustering group is calculated, and the average value is updated as the new data to be clustered center, and all the simulated state data in the clustering group except the new data to be clustered center are deleted. The relevance between the new data to be clustered center and each third simulated state data is calculated, and the third simulated state data with a relatively high relevance to the new data to be clustered center is assigned to the clustering group corresponding to the new data to be clustered center. The average value of all the simulated state data in the clustering group is calculated until the average value no longer changes, and the final average value is determined as the clustering center data, so that the clustering center data can reflect the differences between all the simulated state data.

[0060] Exemplarily, the third simulated state data is any first simulated state data in the first simulated state data except the data to be clustered center.

[0061] As a refinement of step 203, when performing the call to the preset clustering center calculation algorithm to calculate the preset number of data of the clustering center for the preset number of data to be clustered center, it can be implemented but not limited to the following method. The relevance between the preset number of data to be clustered center and the third simulated state data is calculated respectively to obtain at least one second relevance between the data to be clustered center and the third simulated state data. The third simulated state data is any first simulated state data in the first simulated state data except the data to be clustered center. By calculating the relevance between the data to be clustered center and the third simulated state data, it can help to determine which data to be clustered center is more suitable as the clustering center. According to the at least one second relevance between the data to be clustered center and the third simulated state data, determining the preset number of data of the clustering center can ensure that the final clustering center data can better reflect the internal structure and characteristics of all the simulated state data.

[0062] As a refinement of the above embodiments, when determining the preset number of the cluster center data according to the second correlation between the at least one data of the to-be-clustered center and the third simulation state data, the following implementation manners can be adopted but are not limited thereto. For each data of the to-be-clustered center, the third simulation state data with the second correlation greater than the first preset threshold is updated into the cluster group corresponding to each data of the to-be-clustered center; the average value is calculated respectively for the data of the to-be-clustered center and the third simulation state data in the cluster group corresponding to each data of the to-be-clustered center, so as to obtain the preset number of updated data of the to-be-clustered center; the correlation between the preset number of updated data of the to-be-clustered center and the third simulation state data is calculated respectively until the data of the to-be-clustered center is no longer updated, so as to obtain the preset number of the cluster center data; by iteratively updating the data of the to-be-clustered center and calculating the correlation, the quality of the data of the to-be-clustered center can be effectively improved, so that the finally obtained cluster center data is more accurate and stable.

[0063] As a refinement of step 102, when performing the calculation of the correlation between the at least one cluster center data and the second simulation state data respectively to obtain the first correlation between each cluster center data and the second simulation state data, the following implementation manners can be adopted but are not limited thereto: obtaining the first simulation position, the first simulation arrival time, the first simulation departure time, the first simulation remaining power upon arrival, and the first simulation remaining power upon departure in the cluster center data; obtaining the second simulation position, the second simulation arrival time, the second simulation departure time, the second simulation remaining power upon arrival, and the second simulation remaining power upon departure in the second simulation state data; obtaining the first weight parameter corresponding to the first simulation position and the second simulation position, obtaining the second weight parameter corresponding to the first simulation arrival time, the first simulation departure time, the second simulation arrival time, and the second simulation departure time, and obtaining the third weight parameter corresponding to the first simulation remaining power upon arrival, the first simulation remaining power upon departure, the second simulation remaining power upon arrival, and the second simulation remaining power upon departure; calling a preset correlation algorithm, and putting the first simulation position, the first simulation arrival time, the first simulation departure time, the first simulation remaining power upon arrival, the first simulation remaining power upon departure, the second simulation position, the second simulation arrival time, the second simulation departure time, the second simulation remaining power upon arrival, the second simulation remaining power upon departure, the first weight parameter, the second weight parameter, and the third weight parameter into formula (6) for calculation to obtain , and putting all into formula 7 to obtain γ, and putting and γ into formula (5) for calculation to obtain the first correlation.

[0064] As a refinement of the above embodiments, when performing the call to the preset correlation algorithm to calculate the first correlation degree for the first simulated position, the first simulated arrival time, the first simulated departure time, the first simulated remaining battery power at arrival, the first simulated remaining battery power at departure, the second simulated position, the second simulated arrival time, the second simulated departure time, the second simulated remaining battery power at arrival, the second simulated remaining battery power at departure, the first weight parameter, the second weight parameter, and the third weight parameter, the following implementation manners may be adopted but are not limited thereto. Calculate the difference between the first simulated position and the second simulated position, calculate the difference between the first simulated arrival time and the second simulated arrival time, calculate the difference between the first simulated departure time and the second simulated departure time, calculate the difference between the first simulated remaining battery power at arrival and the second simulated remaining battery power at arrival, calculate the difference between the first simulated remaining battery power at departure and the second simulated remaining battery power at departure, to obtain the corresponding difference results respectively; perform square calculations on the respective corresponding difference results to obtain the square results corresponding to the respective corresponding difference results respectively; perform product calculations on the first weight parameter, the second weight parameter, and the third weight parameter with the corresponding square results respectively to obtain the respective corresponding product results; calculate the first correlation degree according to the respective corresponding product results; the embodiments of the present disclosure are the literal descriptions of formula (6).

[0065] As a refinement of the above embodiments, when performing the calculation of the first correlation degree according to the respective corresponding product results, the following implementation manners may be adopted but are not limited thereto. Perform summation calculations on the respective corresponding product results to obtain a summation result; there is a corresponding summation result between each second simulated state data and each cluster center data; determine the maximum value among all the summation results as the target summation result; perform calculations on the target summation result with each summation result respectively to obtain the first correlation degree; the embodiments of the present disclosure are the literal descriptions of formula (5) and formula (6).

[0066] In practical applications, after allocating the target to-be-scheduled resources corresponding to the target simulated state data to the cluster groups corresponding to each cluster center data, it is necessary to perform summation processing on the energy boundaries and power boundaries of the target to-be-scheduled resources in the same cluster group. The following implementation manners may be adopted but are not limited thereto. Obtain the upper energy boundary and the lower energy boundary of each to-be-scheduled resource in the cluster group, and obtain the upper power boundary and the lower power boundary of each to-be-scheduled resource in the cluster group; perform summation calculations on the upper energy boundaries of all the to-be-scheduled resources in the cluster group to obtain the total upper energy boundary of the cluster group, and the total upper energy boundary can be implemented through formula (8): (8) Among them, is the upper energy boundary of the resource to be scheduled, is the upper boundary of the total power during charging or discharging of the resource to be scheduled, is the current time of charging or discharging of the resource to be scheduled, is the start time of charging or discharging of the resource to be scheduled, is and the difference.

[0067] Sum up the lower energy boundaries of all resources to be scheduled in the clustering group to obtain the total lower energy boundary of the clustering group. The total lower energy boundary can be achieved through formula (9): (9) Among them, is the lower energy boundary of the resource to be scheduled, is the lower boundary of the total power during charging or discharging of the resource to be scheduled, is the current time of charging or discharging of the resource to be scheduled, is the start time of charging or discharging of the resource to be scheduled, is and the difference.

[0068] Sum up the upper power boundaries of all resources to be scheduled in the clustering group to obtain the total upper power boundary of the target clustering group. The total upper power boundary can be achieved through formula (10): (10) Among them, is the upper power boundary of the resource to be scheduled, is the current time of charging or discharging of the resource to be scheduled, is the start time of charging or discharging of the resource to be scheduled, is and the difference.

[0069] Sum up the lower power boundaries of all resources to be scheduled to obtain the total lower power boundary of the target clustering group. The total lower power boundary can be achieved through formula (11): (11) Among them, is the lower power boundary of the resource to be scheduled, is the current time of charging or discharging of the resource to be scheduled, is the start time of charging or discharging of the resource to be scheduled, is The difference from is

[0070] Based on the upper bound of the total energy, the lower bound of the total energy, the upper bound of the total power, and the lower bound of the power, schedule all the resources to be scheduled, and use the upper bound of the total energy, the lower bound of the total energy, the upper bound of the total power, and the lower bound of the power as the constraint conditions for resource scheduling. In the actual resource scheduling process, it is necessary to consider the limitations in aspects such as energy consumption and power to ensure that the resource scheduling scheme meets the energy and power requirements of the system, and at the same time avoid exceeding the carrying capacity of the resources.

[0071] In an implementable manner of the embodiments of the present disclosure, clustering is performed on the similarity between the analog state data of the resources to be scheduled. The advantages are reflected in that the obtained feasible region of the aggregated resources is very accurate, and at the same time, the requirement for the amount of calculation is significantly reduced compared with non-aggregation. As Figure 6 shown Figure 6 FIG. is a schematic diagram of the feasible region of aggregation between different resources to be scheduled provided by the embodiments of the present disclosure. The positive direction of the vertical axis E represents the absorbed energy. ta1 and ta2 are the times when the first resource to be scheduled and the second resource to be scheduled access the charging pile respectively, and td1 and td2 are the times when the first resource to be scheduled and the second resource to be scheduled leave the charging pile respectively; e1max and e2max are the maximum power of the two resources to be scheduled respectively, and e1exp and e2exp are the expected power when the two resources to be scheduled leave. After adding the power constraint, the energy feasible region of the charging piles accessed by the two resources to be scheduled can be obtained, and this feasible region includes the energy constraint and the power constraint.

[0072] In a V2G peak shaving and valley filling example, the traditional direct aggregation method and the scheduling resource aggregation method of the embodiments of the present disclosure are respectively used. In this example, 1000 resources to be scheduled participate in V2G, and the time interval for intraday scheduling is 1 hour. The results are as Figure 7 and Figure 8 shown Figure 7 FIG. is an effect diagram of the direct aggregation method provided by the embodiments of the present disclosure for peak shaving and valley filling. Figure 8The figure shows the effect of the polymerization method of the present invention for peak shaving and valley filling provided by the embodiments of the present disclosure. Assuming that the number of clusters NA is set to 8, it can be seen that direct aggregation will cause a large deviation between the actual power of the resources to be scheduled and the day-ahead scheduling plan, while the method proposed by the embodiments of the present disclosure will not show a large deviation. In addition, through calculation, it can be known that the variance of the base load is 3.0556×106, and the peak-valley difference rate is 0.4879; the total load variance of the electric vehicle load superimposed on the base load after being scheduled by the direct polymerization method is 1.9056×106, and the peak-valley difference rate is 0.3882; the total load variance of the electric vehicle load superimposed on the base load after being scheduled by the polymerization method of this patent is 1.7813×106, and the peak-valley difference rate is 0.3544. It can be seen that the scheduling resource aggregation method proposed by the embodiments of the present disclosure is better.

[0073] In summary, the embodiments of the present disclosure can achieve the following effects: In the embodiments of the present disclosure, at least one first simulated state data is determined from at least two first simulated state data as the clustering center data, the first correlation between the second simulated state data and the clustering center data is calculated, and the resources to be scheduled corresponding to the first simulated state data with a higher first correlation are assigned to a clustering group, so as to achieve the assignment of scheduling resources with similar state data to the same clustering group, and improve the scheduling accuracy of the resources to be scheduled.

[0074] Corresponding to the above-mentioned hierarchical group control method based on the perception of the behavior of V2G users in the integrated energy storage and charging system, the present invention also proposes a hierarchical group control system based on the perception of the behavior of V2G users in the integrated energy storage and charging system. Since the device embodiments of the present invention correspond to the above-mentioned method embodiments, for the details not disclosed in the device embodiments, reference may be made to the above-mentioned method embodiments, and the present invention will not be elaborated herein.

[0075] Figure 9 The figure shows the structural schematic diagram of a hierarchical group control system based on the perception of the behavior of V2G users provided by the embodiments of the present disclosure. The device is applied to a server, as Figure 9 shown, and includes: A first determination unit 31, configured to determine at least one first simulated state data from at least two first simulated state data as the clustering center data, and each clustering center data serves as the center data for generating a clustering group; wherein, the first simulated state data is the first simulated state data corresponding to the resources to be scheduled; A first calculation unit 32, configured to calculate the correlation between each of the at least one clustering center data and the second simulated state data to obtain the first correlation between each clustering center data and the second simulated state data; the second simulated state data is any first simulated state data other than the clustering center data in the first simulated state data; A second determination unit 33, configured to determine, for each cluster center data, the second simulated state data whose first relevance is greater than a first preset threshold as target simulated state data; An allocation unit 34, configured to allocate the target to-be-scheduled resources corresponding to the target simulated state data to the cluster groups corresponding to the respective cluster center data, so as to schedule the to-be-scheduled resources in the cluster groups.

[0076] The hierarchical group control system for optical storage charging V2G user behavior perception provided by the present disclosure determines at least one first simulated state data as cluster center data from at least two first simulated state data, and each cluster center data serves as the center data for generating a cluster group; wherein, the first simulated state data is the first simulated state data corresponding to the to-be-scheduled resources; calculating the relevance between the at least one cluster center data and the second simulated state data respectively to obtain a first relevance between each cluster center data and the second simulated state data; the second simulated state data is any first simulated state data other than the cluster center data in the first simulated state data; determining, for each cluster center data, the second simulated state data whose first relevance is greater than a first preset threshold as target simulated state data; and allocating the target to-be-scheduled resources corresponding to the target simulated state data to the cluster groups corresponding to the respective cluster center data, so as to schedule the to-be-scheduled resources in the cluster groups. Compared with the related art, in the embodiment of the present disclosure, by determining at least one first simulated state data as cluster center data from at least two first simulated state data, calculating the first relevance between the second simulated state data and the cluster center data, and allocating the to-be-scheduled resources corresponding to the simulated state data with a higher first relevance to a cluster group, the to-be-scheduled resources with similar state data are allocated to the same cluster group, thereby improving the scheduling accuracy of the to-be-scheduled resources.

[0077] Further, in a possible implementation manner of the embodiment of the present disclosure, as Figure 10 shown, the first determination unit 31 includes: A selection module 311, configured to select a preset number of first simulated state data as to-be-cluster center data, to obtain the preset number of to-be-cluster center data; the relevance between the to-be-cluster center data is greater than a second preset threshold, and the preset number is less than the total number of the at least two to-be-scheduled resources; The statement that each cluster center data serves as the center data for generating a cluster group includes: Each to-be-cluster center data serves as the center data for generating a cluster group; The first calculation module 312 is configured to call a preset clustering center calculation algorithm to calculate the preset number of data to be clustered centers, and obtain the preset number of the clustering center data.

[0078] Further, in a possible implementation manner of the embodiment of the present disclosure, as Figure 10 shown, the first calculation module 312 is further configured to, calculate the correlation between the preset number of data to be clustered centers and the third simulation state data respectively, to obtain a second correlation between at least one data to be clustered center and the third simulation state data; the third simulation state data is any first simulation state data other than the data to be clustered centers in the first simulation state data; determine the preset number of the clustering center data according to the second correlation between at least one data to be clustered center and the third simulation state data.

[0079] Further, in a possible implementation manner of the embodiment of the present disclosure, as Figure 10 shown, the first calculation module 312 is further configured to, for each data to be clustered center, update the third simulation state data with the second correlation greater than the first preset threshold into the clustering group corresponding to each data to be clustered center; calculate the average value of the data to be clustered center and the third simulation state data in the clustering group corresponding to each data to be clustered center respectively, to obtain the preset number of updated data to be clustered centers; calculate the correlation between the preset number of updated data to be clustered centers and the third simulation state data respectively until the data to be clustered centers are no longer updated, to obtain the preset number of the clustering center data.

[0080] Further, in a possible implementation manner of the embodiment of the present disclosure, as Figure 10 shown, the first calculation unit 32 includes: an acquisition module 321, configured to acquire a first simulation position, a first simulation arrival time, a first simulation departure time, a first simulation remaining battery power upon arrival, and a first simulation remaining battery power upon departure in the clustering center data; the acquisition module 321 is further configured to acquire a second simulation position, a second simulation arrival time, a second simulation departure time, a second simulation remaining battery power upon arrival, and a second simulation remaining battery power upon departure in the second simulation state data; The obtaining module 321 is further configured to obtain a first weight parameter corresponding to the first simulated position and the second simulated position, obtain a second weight parameter corresponding to the first simulated arrival time, the first simulated departure time, the second simulated arrival time, and the second simulated departure time, and obtain a third weight parameter corresponding to the first simulated remaining power upon arrival, the first simulated remaining power upon departure, the second simulated power upon arrival, and the second simulated remaining power upon departure; The second calculation module 322 is configured to call a preset relevance algorithm to calculate the first simulated position, the first simulated arrival time, the first simulated departure time, the first simulated remaining power upon arrival, the first simulated remaining power upon departure, the second simulated position, the second simulated arrival time, the second simulated departure time, the second simulated remaining power upon arrival, the second simulated remaining power upon departure, the first weight parameter, the second weight parameter, and the third weight parameter to obtain the first relevance.

[0081] Further, in a possible implementation manner of the embodiments of the present disclosure, as Figure 10 shown, the second calculation module 324 is further configured to calculate the difference between the first simulated position and the second simulated position, calculate the difference between the first simulated arrival time and the second simulated arrival time, calculate the difference between the first simulated departure time and the second simulated departure time, calculate the difference between the first simulated remaining power upon arrival and the second simulated remaining power upon arrival, and calculate the difference between the first simulated remaining power upon departure and the second simulated remaining power upon departure to obtain respective difference results; perform a square calculation on each of the respective difference results to obtain respective square results corresponding to the respective difference results; perform a product calculation on the first weight parameter, the second weight parameter, and the third weight parameter respectively with the corresponding square results to obtain respective product results; calculate the first relevance according to the respective product results.

[0082] Further, in a possible implementation manner of the embodiments of the present disclosure, as Figure 10 shown, the second calculation module 324 is further configured to perform a summation calculation on the respective product results to obtain a summation result; there is a corresponding summation result between each second simulated state data and each cluster center data; determine the maximum value among all the summation results as the target summation result; calculate the first relevance by calculating the target summation result with each summation result respectively.

[0083] Further, in a possible implementation manner of the embodiments of the present disclosure, as Figure 10 shown, the apparatus further includes: An obtaining unit 35, configured to obtain the upper energy boundary and the lower energy boundary of each to-be-scheduled resource in the clustering group, and obtain the upper power boundary and the lower power boundary of each to-be-scheduled resource in the clustering group after allocating the target to-be-scheduled resources corresponding to the target simulation state data to the clustering groups corresponding to the respective clustering center data; A second calculation unit 36, configured to perform a summation calculation on the upper energy boundaries of all the to-be-scheduled resources in the clustering group to obtain the total upper energy boundary of the clustering group; The second calculation unit 36 is further configured to perform a summation calculation on the lower energy boundaries of all the to-be-scheduled resources in the clustering group to obtain the total lower energy boundary of the clustering group; The second calculation unit 36 is further configured to perform a summation calculation on the upper power boundaries of all the to-be-scheduled resources in the clustering group to obtain the total upper power boundary of the target clustering group; The second calculation unit 36 is further configured to perform a summation calculation on the lower power boundaries of all the to-be-scheduled resources to obtain the total lower power boundary of the target clustering group, so as to schedule all the to-be-scheduled resources based on the total upper energy boundary, the total lower energy boundary, the total upper power boundary, and the lower power boundary.

[0084] It should be noted that the foregoing explanations of the method embodiments are also applicable to the apparatus of the embodiments of the present disclosure, with the same principle, and are not further limited in the embodiments of the present disclosure.

[0085] According to the embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0086] Figure 11 FIG. shows a schematic block diagram of an exemplary electronic device 400 that can be used to implement the embodiments of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, a personal digital processing, a cellular phone, a smart phone, a wearable device, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described herein and / or claimed.

[0087] As Figure 11As shown, device 400 includes a computing unit 401, which can perform various appropriate actions and processes according to a computer program stored in a ROM (Read-Only Memory) 402 or a computer program loaded from a storage unit 408 into a RAM (Random Access Memory) 403. In the RAM 403, various programs and data required for the operation of the device 400 can also be stored. The computing unit 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An I / O (Input / Output) interface 405 is also connected to the bus 404.

[0088] Multiple components in the device 400 are connected to the I / O interface 405, including: an input unit 406, such as a keyboard, a mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 408, such as a magnetic disk, an optical disc, etc.; and a communication unit 409, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 409 allows the device 400 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0089] The computing unit 401 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 include but are not limited to a CPU (Central Processing Unit), a GPU (Graphic Processing Units), various dedicated AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, a DSP (Digital Signal Processor), and any appropriate processor, controller, microcontroller, etc. The computing unit 401 executes the various methods and processes described above, such as the hierarchical group control method based on the perception of user behavior of photovoltaic-storage-charging V2G. For example, in some embodiments, the hierarchical group control method based on the perception of user behavior of photovoltaic-storage-charging V2G can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as the storage unit 408. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 400 via the ROM 402 and / or the communication unit 409. When the computer program is loaded into the RAM 403 and executed by the computing unit 401, one or more steps of the methods described above can be executed. Alternatively, in other embodiments, the computing unit 401 can be configured to execute the aforementioned hierarchical group control method based on the perception of user behavior of photovoltaic-storage-charging V2G in any other appropriate way (e.g., by means of firmware).

[0090] The various embodiments of the systems and techniques described above in this specification can be implemented in digital electronic circuitry, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application Specific Standard Products), SoCs (System On Chip), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which may be a special-purpose or general-purpose programmable processor that receives data and instructions from, and transmits data and instructions to, a storage system, at least one input device, and at least one output device.

[0091] The program code for implementing the methods of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that the program codes, when executed by the processor or controller, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0092] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a RAM, a ROM, an EPROM (Electrically Programmable Read-Only-Memory), or flash memory, an optical fiber, a CD-ROM (Compact Disc Read-Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0093] In order to provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor); and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, speech input, or tactile input).

[0094] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a LAN (Local Area Network), a WAN (Wide Area Network), the Internet, and a blockchain network.

[0095] A computer system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The relationship between the client and the server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services ("Virtual Private Server", or simply "VPS"). The server may also be a server of a distributed system or a server combined with a blockchain.

[0096] Among them, it should be noted that artificial intelligence is a discipline that studies enabling a computer to simulate certain thinking processes and intelligent behaviors of humans (such as learning, reasoning, thinking, planning, etc.), and there are both hardware-level technologies and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include several major directions such as computer vision technology, speech recognition technology, natural language processing technology, and machine learning / deep learning, big data processing technology, and knowledge graph technology.

[0097] It should be understood that various forms of processes shown above can be used, steps can be reordered, added, or deleted. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and no limitations are imposed herein.

[0098] The above specific embodiments do not constitute a limitation on the protection scope of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the protection scope of this disclosure.

Claims

1. A hierarchical group control method based on V2G user behavior perception based on photovoltaic storage and charging, characterized in that: include: Determine at least one first simulation state data from at least two first simulation state data as cluster center data, and each cluster center data is used as the center data for generating a cluster group; wherein the first simulation state data is the first simulation state data corresponding to the resource to be scheduled; Calculating the correlation between the at least one cluster center data and the second simulation state data respectively, to obtain a first correlation between each cluster center data and the second simulation state data; the second simulation state data is any first simulation state data except the cluster center data in the first simulation state data; For each cluster center data, determining the second simulation state data whose first correlation is greater than a first preset threshold as target simulation state data; The target resources to be scheduled corresponding to the target simulation state data are allocated to the cluster groups corresponding to the cluster center data, so as to schedule the resources to be scheduled in the cluster groups.

2. The method according to claim 1, characterized in that The determining at least one first simulation state data as cluster center data from at least two first simulation state data comprises: A preset number of first simulation state data are selected as center data to be clustered, and the preset number of center data to be clustered is obtained; the correlation between the center data to be clustered is greater than a second preset threshold, and the preset number is less than the total number of the at least two resources to be scheduled; Each cluster center data as the center data for generating a cluster group includes: Each of the center data to be clustered is used as the center data for generating a cluster group; A preset cluster center calculation algorithm is called to calculate the preset number of to-be-clustered center data to obtain a preset number of cluster center data.

3. The method according to claim 2, characterized in that The calling of a preset cluster center calculation algorithm to calculate the preset number of to-be-clustered center data to obtain the preset number of cluster center data includes: Calculating the correlation between the preset number of center data to be clustered and the third simulation state data respectively, and obtaining a second correlation between at least one center data to be clustered and the third simulation state data; the third simulation state data is any first simulation state data except the center data to be clustered in the first simulation state data; The preset number of cluster center data is determined according to a second correlation between the at least one to-be-clustered center data and the third simulation state data.

4. The method according to claim 3, characterized in that Determining the preset number of cluster center data according to the second correlation between the at least one to-be-clustered center data and the third simulation state data comprises: For each center data to be clustered, the third simulation state data whose second correlation is greater than the first preset threshold is updated in the clustering group corresponding to each center data to be clustered; Calculating the average values ​​of the center data to be clustered and the third simulation state data in the cluster groups corresponding to each center data to be clustered, respectively, to obtain the preset number of updated center data to be clustered; The preset number of updated center data to be clustered are respectively correlated with the third simulation state data until the center data to be clustered is no longer updated, thereby obtaining the preset number of cluster center data.

5. The method according to claim 1, characterized in that The step of calculating the correlation between the at least one cluster center data and the second simulation state data respectively to obtain a first correlation between each cluster center data and the second simulation state data comprises: Obtaining the first simulated position, the first simulated arrival time, the first simulated departure time, the first simulated arrival remaining power, and the first simulated departure remaining power in the cluster center data; Obtaining a second simulated position, a second simulated arrival time, a second simulated departure time, a second simulated arrival remaining power, and a second simulated departure remaining power in the second simulated state data; Obtain a first weight parameter corresponding to the first simulated position and the second simulated position, obtain a second weight parameter corresponding to the first simulated arrival time, the first simulated departure time, the second simulated arrival time, and the second simulated departure time, and obtain a third weight parameter corresponding to the first simulated arrival remaining power, the first simulated departure remaining power, the second simulated arrival power, and the second simulated departure remaining power; Call a preset correlation algorithm to calculate the first simulated position, the first simulated arrival time, the first simulated departure time, the first simulated arrival remaining power, the first simulated departure remaining power, the second simulated position, the second simulated arrival time, the second simulated departure time, the second simulated arrival remaining power, the second simulated departure remaining power, the first weight parameter, the second weight parameter, and the third weight parameter to obtain the first correlation.

6. The method according to claim 5, characterized in that The calling of a preset correlation algorithm to calculate the first simulated position, the first simulated arrival time, the first simulated departure time, the first simulated arrival remaining power, the first simulated departure remaining power, the second simulated position, the second simulated arrival time, the second simulated departure time, the second simulated arrival remaining power, the second simulated departure remaining power, the first weight parameter, the second weight parameter, and the third weight parameter to obtain the first correlation includes: performing a difference calculation between the first simulated position and the second simulated position, performing a difference calculation between the first simulated arrival time and the second simulated arrival time, performing a difference calculation between the first simulated departure time and the second simulated departure time, performing a difference calculation between the first simulated arrival remaining power and the second simulated arrival remaining power, performing a difference calculation between the first simulated departure remaining power and the second simulated departure remaining power, and obtaining respective corresponding difference results; Performing square calculations on the respective corresponding difference results respectively to obtain square results corresponding to the respective corresponding difference results respectively; Calculate the product of the first weight parameter, the second weight parameter, and the third weight parameter with the corresponding square results to obtain the corresponding product value results; The first correlation is calculated according to the corresponding product value results.

7. The method according to claim 6, characterized in that The calculating the first correlation according to the corresponding product value results includes: The corresponding product value results are added and calculated to obtain a sum result; there is a corresponding sum result between each second simulation state data and each cluster center data; The maximum value among all the summation results is determined as the target summation result; The target sum result is calculated separately with each sum result to obtain the first correlation.

8. The method according to claim 1, characterized in that After allocating the target resources to be scheduled corresponding to the target simulation state data to the cluster groups corresponding to the cluster center data, the method further includes: Obtaining an upper energy boundary and a lower energy boundary of each resource to be scheduled in the cluster group, and obtaining an upper power boundary and a lower power boundary of each resource to be scheduled in the cluster group; Adding and calculating the energy upper bounds of all resources to be scheduled in the cluster group to obtain the total energy upper bound of the cluster group; The energy lower bounds of all resources to be scheduled in the cluster group are summed up to obtain the total energy lower bound of the cluster group; The power upper bounds of all resources to be scheduled in the cluster group are summed up to obtain the total power upper bound of the target cluster group; The power lower boundaries of all the resources to be scheduled are added and calculated to obtain the total power lower boundary of the target cluster group, so as to schedule all the resources to be scheduled based on the total energy upper boundary, the total energy lower boundary, the total power upper boundary and the power lower boundary.

9. A hierarchical group control system based on V2G user behavior perception based on solar storage and charging, characterized in that: include: A first determination unit, used to determine at least one first simulation state data from at least two first simulation state data as cluster center data, each cluster center data as center data for generating a cluster group; wherein the first simulation state data is the first simulation state data corresponding to the resource to be scheduled; a first calculation unit, configured to calculate the correlation between the at least one cluster center data and the second simulation state data respectively, to obtain a first correlation between each cluster center data and the second simulation state data; the second simulation state data is any first simulation state data other than the cluster center data in the first simulation state data; A second determining unit, configured to determine, for each cluster center data, the second simulation state data having the first correlation greater than a first preset threshold as target simulation state data; An allocating unit is used to allocate the target resources to be scheduled corresponding to the target simulation state data to the cluster groups corresponding to the cluster center data, so as to schedule the resources to be scheduled in the cluster groups.

10. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 8.

Images