V2G charging and discharging behavior identification method and system based on Internet of Vehicles big data

Abstract

The invention relates to a V2G charging and discharging behavior identification method and system based on Internet of Vehicles big data, and the method comprises the steps: obtaining the total data of a vehicle, screening the data of a parking vehicle state as vehicle data, and calibrating the vehicle state of each frame of vehicle data; according to the vehicle state of each frame, vehicle data merging is carried out according to a first merging rule, a plurality of basic secondary rows are obtained, and secondary row information of each basic secondary row is extracted; based on the secondary row information, each basic secondary row is judged, if the judgment result is that the secondary row is effective, the secondary row is reserved, and otherwise, the secondary row is removed; and according to a second merging rule, performing effective sub-row merging to obtain a complete sub-row, and based on the complete sub-row, determining the charging and discharging behavior of the vehicle in the Internet of Vehicles, the system is used for implementing the method. Compared with the prior art, the method provided by the invention can avoid the misrecognition of the charging and discharging behaviors caused by no unified discharging state identifier.

Description

Technical Field

[0001] This invention relates to the field of vehicle-to-everything (V2G) big data technology, and in particular to a method and system for identifying V2G charging and discharging behavior based on V2G big data. Background Technology

[0002] Vehicle-to-Grid (V2G) technology refers to the technology of electric vehicles supplying electricity to the power grid. Its core idea is to utilize the energy storage of a large number of electric vehicles as a buffer between the power grid and renewable energy sources. V2G technology is receiving widespread attention because it can significantly alleviate the problems of low grid efficiency and renewable energy fluctuations, while also generating revenue for electric vehicle users. With the acceleration of the global energy transition, major cities such as Shanghai and Beijing have successively launched large-scale V2G pilot projects. V2G technology endows electric vehicles with the attributes of mobile energy storage units, and its enormous potential is reflected in two main aspects: First, at the macro-grid level, large-scale electric vehicles can discharge electricity to the grid during peak electricity consumption periods via V2G, forming an extremely flexible distributed energy storage network. This can effectively smooth peak and valley loads, supporting the consumption of a high proportion of renewable energy, which is of strategic significance for building a new power system and ensuring energy security. Second, at the micro-economic level, V2G creates a new model for car owners to participate in grid peak shaving and obtain revenue, which is expected to significantly reduce the total life cycle cost of vehicles, while providing new business opportunities for market players such as charging operators and aggregators.

[0003] However, current monitoring of V2G charging and discharging behavior mainly relies on data from smart charging piles, lacking complete behavioral data from vehicle-side users. Specifically, the vehicle-to-everything (V2G) big data sent by automakers to third parties every 10 seconds, based on the national standard GB / T32960, includes vehicle information such as driving and charging, charging current and voltage information, and corresponding spatiotemporal information such as time and latitude / longitude. Existing technologies often directly acquire information such as the charging and discharging status of vehicles in the V2G network for vehicle behavior recognition. For example, Chinese patent application CN111538752A directly obtains the vehicle's charging and discharging status from the V2G database in its technical solution. However, the current vehicle data in GBT32960 does not directly indicate the vehicle's V2G discharge status. In the existing vehicle status and charging fields, different states have corresponding unified identifiers. However, during the discharge process, the output of the charging field in the national standard GBT32960 is inconsistent across different vehicle models. Some models output 0x01 parking and charging status, while others output 0x03 not charging status. Moreover, the output of the charging field remains consistent throughout a single discharge process.

[0004] It is evident that automakers lack a unified standard for reflecting vehicle V2G discharge behavior, resulting in a deficiency in discharge status identification. This leads to misclassification of V2G charging and discharging activities and further complicates identification due to inconsistencies among automakers. Additionally, the limited effective timeframe for detecting SOC changes fails to provide sufficient information for assessing the vehicle's charging and discharging status. Therefore, providing a method to avoid misidentification of charging and discharging behavior caused by the lack of a unified discharge status identifier is a crucial technical challenge. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of the existing technology and provide a V2G charging and discharging behavior identification method and system based on vehicle-to-everything (V2G) big data. By comprehensively judging data from different dimensions of the vehicle, it can identify V2G discharging behavior even without V2G discharging identifiers. It has the characteristics of low cost and wide range and is applicable to scenarios such as dynamic assessment of urban energy infrastructure, assessment of V2G commercialization potential, and power system load monitoring.

[0006] The objective of this invention can be achieved through the following technical solutions: According to a first aspect of the present invention, a method for identifying V2G charging and discharging behavior based on vehicle-to-everything (V2G) big data is provided, comprising: Acquire total vehicle data, filter data where the vehicle status is "parked" as vehicle data, and label the vehicle status of each frame of vehicle data. Based on the vehicle status described in each frame, vehicle data is merged according to the first merging rule to obtain multiple basic sub-rows, and sub-row information of each basic sub-row is extracted. Based on the aforementioned secondary row information, each basic secondary row is judged. If the judgment result is a valid secondary row, it is retained; otherwise, it is discarded. The effective sub-rows are merged according to the second merging rule to obtain the complete sub-row. The charging and discharging behavior of vehicles in the Internet of Vehicles is determined based on the complete sub-row.

[0007] As a preferred technical solution, the vehicle data includes vehicle ID, vehicle data upload time, SOC, vehicle current value, vehicle voltage value, vehicle speed, and charging status bit.

[0008] As a preferred technical solution, the charging status bits include parking charging, driving charging, not charging, charging complete, abnormal, and invalid.

[0009] As a preferred technical solution, the method for calibrating the vehicle state is as follows: Based on the vehicle data, extract the SOC of each frame of the vehicle, select the SOC data of several frames before the current frame, and calculate the SOC change rate in the selected time period. If the SOC change rate increases, the vehicle state of the current frame is marked as a state of increasing battery power. If the SOC change rate decreases, the vehicle state of the current frame is marked as a power depletion state, which includes a discharge state or an idling power consumption state. If the SOC change rate is less than a preset change value, the vehicle state of the current frame is marked as a stable power state, which includes charging state, discharging state, or idling power consumption state.

[0010] As a preferred technical solution, the first merging rule includes: Based on the vehicle data, the vehicle upload time is extracted, and the vehicle data within the frame time interval in the first preset time period is selected as the candidate vehicle data in the same group according to the vehicle upload time. Obtain the vehicle status and charging status bit of each candidate vehicle data, and merge the candidate vehicle data with the same vehicle status and charging status bit as the basic second row.

[0011] As a preferred technical solution, the secondary row information includes vehicle status, charging status bit, start and end time, duration, initial SOC, end SOC, SOC change, average power, and the number of data points included in the corresponding basic secondary row.

[0012] As a preferred technical solution, the method for determining each basic sub-row includes: Based on the aforementioned second-row information, the number of data points included in the basic second-row to be determined is obtained. The determination of valid and interfering second-rows is performed only if the number of data points is greater than a preset number. Based on the aforementioned secondary information, the vehicle status and duration of the basic secondary line to be determined are obtained. If the vehicle status is a stable battery state and the duration is less than a second preset time, it is determined to be an interfering secondary line; otherwise, it is a valid secondary line.

[0013] As a preferred technical solution, the second merging rule includes: Obtain the start and end times of each valid row, and select the valid rows whose interval between the end time of the previous valid row and the start time of the next valid row is less than a third preset time as candidate valid rows in the same group. For each candidate valid row, the vehicle status and charging status bits are obtained based on the row information. Candidate valid rows with the same vehicle status and charging status bits are merged into a complete row.

[0014] As a preferred technical solution, the second merging rule further includes: for valid second rows that cannot be merged according to the second merging rule, obtaining the corresponding duration and SOC change, and removing valid second rows whose duration is less than the minimum time threshold and whose SOC change is less than the maximum change value.

[0015] According to a second aspect of the present invention, a V2G charging and discharging behavior recognition system based on vehicle network big data is provided to implement the above-described method.

[0016] Compared with existing technologies, this invention provides a method to avoid incorrect identification of charging and discharging behavior caused by the lack of a unified discharge state identifier. It utilizes a first merging rule to retain effective information for vehicle charging and discharging state identification, and then uses a second merging rule to filter this effective information to distinguish between charging / discharging states and idling power consumption states. It retains vehicle sub-line information with significant SOC changes, achieving accurate differentiation between charging / discharging states and idling power consumption states, which are easily confused when the battery level is decreasing or stable. Furthermore, for sub-lines showing short-duration battery level changes, this invention concatenates them into a complete sub-line, solving the problem of insufficient duration for judging charging and discharging behavior, thus achieving more accurate charging and discharging behavior identification. Attached Figure Description

[0017] Figure 1 This is a flowchart of the method of the present invention; Figure 2 This is a schematic diagram showing the changes in SOC during charging / discharging and idling power consumption states according to the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0019] Unless otherwise defined, the technical or scientific terms used in this application shall have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms “a,” “an,” “an,” “the,” and similar words used in this application do not indicate quantity limitation and may indicate singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units not listed, or may include other steps or units inherent to these processes, methods, products, or devices. The terms “connected,” “linked,” “coupled,” and similar words used in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. “Multiple” used in this application refers to two or more. “And / or” describes the relationship between related objects, indicating that three relationships may exist; for example, “A and / or B” can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following objects are in an "or" relationship. The terms "first," "second," and "third" used in this application are merely to distinguish similar objects and do not represent a specific ordering of the objects.

[0020] Example 1 In the current GBT32960 vehicle data, the existing vehicle status field includes five statuses and identifiers: vehicle start (0x01), engine off (0x02), other statuses (0x03), abnormal (0xFE), and invalid (0xFF). The charging status field includes six statuses and identifiers: parking charging (0x01), driving charging (0x02), not charging (0x03), charging complete (0x04), abnormal (0xFE), and invalid (0xFF). However, there is no unified identifier for the discharging status. This could lead to misclassification of V2G discharging behavior, and the different identifiers used by different automakers further complicate the identification of V2G discharging behavior.

[0021] Furthermore, it is known that V2G discharge behavior in vehicle-to-everything (V2G) networks has the following characteristics: 1) During the discharge process, the vehicle is stationary and its speed is 0. 2) During the discharge process, the vehicle's SOC continues to decrease. Due to the differences in configuration between different vehicles, it can discharge in real time from either the DC charging port or the AC charging port. If it is DC discharge, the discharge power is generally higher, with the peak power of some models reaching 80kW in actual measurements. However, the AC discharge power is lower, and the power is limited by the on-board charger, with limits of 3.3kW, 6.6kW, 11kW, etc. 3) During the discharge process, the output of the charging field in the national standard GBT32960 is inconsistent on different vehicle models. Some models output 0x01 parking charging status, while others output 0x03: not charging status. However, the output of the charging field remains consistent during a single discharge process. 4) Compared with the vehicle idling, when the vehicle participates in V2G discharge, the output power is higher, the SOC change is greater, and an effective discharge behavior can be considered to last more than 3 minutes, with an average discharge power of more than 2.5kW, an SOC change of more than 3, and no change in the charging field status during the process.

[0022] As described above, this invention provides a V2G charging and discharging behavior recognition method based on vehicle-to-everything (V2G) big data to solve the problems existing in the prior art. The process is as follows: Figure 1 As shown, it includes: S1. Obtain total vehicle data, filter data where the vehicle status is "parked" as vehicle data, and label the vehicle status of each frame of vehicle data.

[0023] To identify vehicle charging and discharging behavior, the vehicle data to be collected includes vehicle ID, vehicle data upload time, SOC, vehicle current value, vehicle voltage value, vehicle speed, and charging status bit. The effective range of the vehicle's SOC is [0, 100]. The vehicle's power can be obtained from the current and voltage values. Furthermore, since different automakers assign different values ​​to the current direction, the vehicle power is expressed as an absolute value. The aforementioned charging status includes six states: parking charging (0x01), driving charging (0x02), not charging (0x03), charging complete (0x04), abnormal (0xFE), and invalid (0xFF).

[0024] Different automakers employ different data collection frequencies, with the mainstream distribution being one data point every 10 seconds and one every 30 seconds. Data loss may occur during actual transmission. Therefore, when determining the vehicle status reflected in each data point, the main reference is the rate of change of SOC over time at that specific point and several points preceding it. Based on the current vehicle data collection frequency, the current frame and the vehicle data from the six frames preceding it are used for judgment. Specifically, the vehicle status of the current frame is determined by using either one minute or three minutes of continuous vehicle data. Specifically, the SOC of each frame of the vehicle is extracted based on the vehicle data. For the current frame, the SOC data from the six frames preceding it is selected, and the rate of change of SOC within the selected time period is calculated.

[0025] If the SOC change rate increases, the vehicle state in the current frame is marked as the battery level increasing. At this point, it can be determined without a doubt that the vehicle is in a charging state.

[0026] If the SOC change rate decreases, the vehicle state of the current frame is marked as a power depletion state, which includes either a discharge state or an idling power consumption state.

[0027] If the SOC change rate is less than the preset change value (in this embodiment, the preset change value is set to 1), then the vehicle state of the current frame is marked as a stable power state. The stable power state includes charging state, discharging state, or idling power consumption state.

[0028] In this invention, considering that there is a period of constant SOC reading regardless of whether it is in the charging / discharging state or the idling power consumption state, such as... Figure 2 As shown, specifically, in the charging and discharging state, although stages one and three can capture changes in SOC, their durations are relatively short. Stage two, because the SOC reading remains unchanged, is marked as a stable charge state and cannot be used to identify the specific charging and discharging state. Furthermore, it is clear that the power of charging and discharging is greater than that of idling power consumption; therefore, compared to the idling power consumption state, the duration of stage two in the charging and discharging state is shorter. To identify the complete charging or discharging process, stage two needs to be removed, and stages one and three need to be further combined to extend the time, thus facilitating the identification of the charging and discharging state. Specifically, steps S2-S4 are executed to remove the stable charge state and filter out the idling power consumption state.

[0029] S2. Based on the vehicle status of each frame, merge the vehicle data according to the first merging rule to obtain multiple basic sub-rows, and extract the sub-row information of each basic sub-row.

[0030] Specifically, the first merger rule mentioned above includes: S21. Extract the vehicle upload time based on vehicle data, and select vehicle data within the frame time interval of the vehicle upload time as candidate vehicle data in the same group according to the vehicle upload time.

[0031] S22. Obtain the vehicle status and charging status bit of each candidate vehicle data. Merge the candidate vehicle data with the same vehicle status and charging status bit as a basic sub-row. The sub-row information of each basic sub-row includes vehicle status, charging status bit, start and end time, duration, initial SOC, end SOC, SOC change, average power, and the number of data points included in the corresponding basic sub-row.

[0032] S3. Based on the information of each basic row, determine the row. If the determination result is a valid row, keep it; otherwise, discard it.

[0033] First, based on the secondary row information, the number of data points included in the basic secondary row to be judged is obtained. If and only if the number of data points is greater than a preset number (set to 5 in this invention), the valid and interfering secondary rows are judged, as follows: Based on the information of the next line, the vehicle status and duration of the basic next line to be judged are obtained. If the vehicle status is a stable battery state and the duration is less than the second preset time (set to 10 minutes in this embodiment), it is judged as an interfering next line; otherwise, it is a valid next line.

[0034] S4. Merge the valid sub-rows according to the second merging rule to obtain the complete sub-row, and determine the charging and discharging behavior of the vehicle in the Internet of Vehicles based on the complete sub-row.

[0035] Specifically, the second merger rule includes: S41. Obtain the start and end times of each valid row, and select the valid rows whose interval between the end time of the previous valid row and the start time of the next valid row is less than a third preset time (set to 10 minutes in this embodiment) as candidate valid rows in the same group.

[0036] S42. For each candidate valid row, obtain the vehicle status and charging status bit based on the row information, and merge the candidate valid rows with the same vehicle status and charging status bit as a complete row.

[0037] S43. Since the second stage of the charging or discharging process has been deleted through steps S2 to S3, the first and second stages of the charging and discharging state can be merged to generate a complete next row. However, for the idling power consumption state, the second stage cannot be deleted through the aforementioned steps, and because of the existence of the second stage, the first and third stages cannot be merged. For this type of valid next row that cannot be merged according to the second merging rule, the corresponding duration and SOC change are obtained, and valid next rows with a duration less than the minimum time threshold (set to 3 minutes in this embodiment) and an SOC change less than the maximum change value (set to 3 in this embodiment) are removed. This process ensures that idling power consumption behavior that is not easily distinguishable from V2G discharge behavior will not generate a next row.

[0038] Ultimately, the charging and discharging behavior is determined based on the SOC changes in the complete sub-row information.

[0039] Example 2 This embodiment provides a V2G charging and discharging behavior recognition system based on vehicle-to-everything (V2G) big data, used to implement the above method, including: 1) Data acquisition and calibration module.

[0040] This module is used to acquire total vehicle data, filter data where the vehicle status is "parked" as vehicle data, and label the vehicle status of each frame of vehicle data.

[0041] For identifying vehicle charging and discharging behavior, the data acquisition and calibration module needs to collect vehicle data including vehicle ID, vehicle data upload time, SOC, vehicle current value, vehicle voltage value, vehicle speed, and charging status bit. The effective range of the vehicle's SOC is [0, 100]. The vehicle's power can be obtained from the current and voltage values. Furthermore, since different automakers assign different values ​​to the current direction, the vehicle power is expressed as an absolute value. The aforementioned charging status includes six states: parking charging (0x01), driving charging (0x02), not charging (0x03), charging complete (0x04), abnormal (0xFE), and invalid (0xFF).

[0042] Different automakers employ different data collection frequencies, with the mainstream distribution being one data point every 10 seconds and one every 30 seconds. Data loss may occur during actual transmission. Therefore, when determining the vehicle status reflected in each data point, the main reference is the rate of change of SOC over time at that specific point and several points preceding it. Based on the current vehicle data collection frequency, the current frame and the vehicle data from the six frames preceding it are used for judgment. Specifically, the vehicle status of the current frame is determined by using either one minute or three minutes of continuous vehicle data. Specifically, the SOC of each frame of the vehicle is extracted based on the vehicle data. For the current frame, the SOC data from the six frames preceding it is selected, and the rate of change of SOC within the selected time period is calculated.

[0043] If the SOC change rate increases, the vehicle state in the current frame is marked as the battery level increasing. At this point, it can be determined without a doubt that the vehicle is in a charging state.

[0044] If the SOC change rate decreases, the vehicle state of the current frame is marked as a power depletion state, which includes either a discharge state or an idling power consumption state.

[0045] If the SOC change rate is less than the preset change value (in this embodiment, the preset change value is set to 1), then the vehicle state of the current frame is marked as a stable power state. The stable power state includes charging state, discharging state, or idling power consumption state.

[0046] 2) Basic sub-line generation module.

[0047] Based on the vehicle status of each frame, the module merges vehicle data according to the first merging rule to obtain multiple basic sub-rows, and extracts the sub-row information of each basic sub-row.

[0048] Specifically, the steps of the basic sub-row generation model to generate basic sub-rows according to the first merging rule include: Based on the vehicle data, the vehicle upload time is extracted, and the vehicle data within the frame time interval of the vehicle upload time is selected as the candidate vehicle data in the same group according to the vehicle upload time.

[0049] The system acquires the vehicle status and charging status bit of each candidate vehicle data. Candidate vehicle data with the same vehicle status and charging status bit are merged into a basic sub-row. The sub-row information of each basic sub-row includes vehicle status, charging status bit, start and end time, duration, initial SOC, end SOC, SOC change, average power, and the number of data points included in the corresponding basic sub-row.

[0050] 3) Second row determination module.

[0051] This module determines each basic second row based on the second row information. If the determination result is a valid second row, it is retained; otherwise, it is discarded.

[0052] First, the secondary row determination module obtains the number of data points included in the basic secondary row to be determined based on the secondary row information. If and only if the number of data points is greater than a preset number (set to 5 in this invention), the valid and interfering secondary rows are determined, as follows: Based on the information of the next line, the vehicle status and duration of the basic next line to be judged are obtained. If the vehicle status is a stable battery state and the duration is less than the second preset time (set to 10 minutes in this embodiment), it is judged as an interfering next line; otherwise, it is a valid next line.

[0053] 4) Complete sub-line generation module.

[0054] This module merges valid second rows according to the second merging rule to obtain a complete second row. When the complete second row generation module merges valid second rows according to the second merging rule, it performs the following steps: Obtain the start and end times of each valid row, and select the valid rows whose interval between the end time of the previous valid row and the start time of the next valid row is less than a third preset time (set to 10 minutes in this embodiment) as candidate valid rows in the same group.

[0055] For each candidate valid row, the vehicle status and charging status bits are obtained based on the row information. Candidate valid rows with the same vehicle status and charging status bits are merged into a complete row.

[0056] In the sub-line determination module and the complete sub-line generation module, the second stage of the charging or discharging process has been deleted. Therefore, the first and second stages in the charging and discharging state can be merged to generate a complete sub-line. However, for the idling power consumption state, the second stage cannot be deleted by the aforementioned steps. Furthermore, due to the existence of the second stage, the first and third stages cannot be merged. For this type of valid sub-line that cannot be merged according to the second merging rule, the corresponding duration and SOC change are obtained. Valid sub-lines with a duration less than the minimum time threshold (set to 3 minutes in this embodiment) and an SOC change less than the maximum change value (set to 3 in this embodiment) are removed. This process ensures that idling power consumption behavior that is not easily distinguishable from V2G discharge behavior will not generate a sub-line.

[0057] 5) Charge / discharge determination module.

[0058] Finally, the charge / discharge determination module obtains the SOC change from the complete second row information in the complete second row generation module to determine the charge / discharge behavior.

[0059] Example 3 The present invention also provides an electronic device including a central processing unit (CPU) that can perform various appropriate actions and processes according to computer program instructions stored in read-only memory (ROM) or loaded from a storage unit into random access memory (RAM). The RAM may also store various programs and data required for device operation. The CPU, ROM, and RAM are interconnected via a bus. Input / output (I / O) interfaces are also connected to the bus.

[0060] Multiple components in the device are connected to the I / O interface, including: input units such as keyboards and mice; output units such as various types of displays and speakers; storage units such as disks and optical discs; and communication units such as network interface cards (NICs), modems, and wireless transceivers. The communication unit allows the device to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0061] The processing unit executes the various methods and processes described above, such as methods S1 to S4. For example, in some embodiments, methods S1 to S4 may be implemented as computer software programs tangibly contained in a machine-readable medium, such as a storage unit. In some embodiments, part or all of the computer program may be loaded and / or installed on the device via ROM and / or a communication unit. When the computer program is loaded into RAM and executed by the CPU, one or more steps of methods S1 to S4 described above may be performed. Alternatively, in other embodiments, the CPU may be configured to execute methods S1 to S4 by any other suitable means (e.g., by means of firmware).

[0062] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0063] The program code used to implement the methods of the present invention can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0064] In the context of this invention, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction 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. Machine-readable media can include, but are 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 machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0065] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for recognizing V2G charging and discharging behavior based on vehicle-to-everything (V2G) big data, characterized in that, include: Acquire total vehicle data, filter data where the vehicle status is "parked" as vehicle data, and label the vehicle status of each frame of vehicle data. Based on the vehicle status described in each frame, vehicle data is merged according to the first merging rule to obtain multiple basic sub-rows, and sub-row information of each basic sub-row is extracted. Based on the aforementioned secondary row information, each basic secondary row is judged. If the judgment result is a valid secondary row, it is retained; otherwise, it is discarded. The effective sub-rows are merged according to the second merging rule to obtain the complete sub-row. The charging and discharging behavior of vehicles in the Internet of Vehicles is determined based on the complete sub-row.

2. The V2G charging and discharging behavior recognition method based on vehicle-to-everything (V2G) big data according to claim 1, characterized in that, The vehicle data includes vehicle ID, vehicle data upload time, SOC, vehicle current value, vehicle voltage value, vehicle speed, and charging status bit.

3. The V2G charging and discharging behavior recognition method based on vehicle-to-everything (V2G) big data according to claim 2, characterized in that, The charging status bits include charging while parked, charging while driving, not charging, charging complete, abnormal, and invalid.

4. The V2G charging and discharging behavior recognition method based on vehicle-to-everything (V2G) big data according to claim 1, characterized in that, The method for calibrating the vehicle status is as follows: Based on the vehicle data, extract the SOC of each frame of the vehicle, select the SOC data of several frames before the current frame, and calculate the SOC change rate in the selected time period. If the SOC change rate increases, the vehicle state of the current frame is marked as a state of increasing battery power. If the SOC change rate decreases, the vehicle state of the current frame is marked as a power depletion state, which includes a discharge state or an idling power consumption state. If the SOC change rate is less than a preset change value, the vehicle state of the current frame is marked as a stable power state, which includes charging state, discharging state, or idling power consumption state.

5. The V2G charging and discharging behavior recognition method based on vehicle-to-everything (V2G) big data according to claim 1, characterized in that, The first merging rule includes: Based on the vehicle data, the vehicle upload time is extracted, and the vehicle data within the frame time interval in the first preset time period is selected as the candidate vehicle data in the same group according to the vehicle upload time. Obtain the vehicle status and charging status bit of each candidate vehicle data, and merge the candidate vehicle data with the same vehicle status and charging status bit as the basic second row.

6. The V2G charging and discharging behavior recognition method based on vehicle-to-everything (V2G) big data according to claim 1, characterized in that, The secondary row information includes vehicle status, charging status bit, start and end time, duration, initial SOC, end SOC, SOC change, average power, and the number of data points included in the corresponding basic secondary row.

7. The V2G charging and discharging behavior recognition method based on vehicle-to-everything (V2G) big data according to claim 1, characterized in that, The methods for determining each basic sub-row include: Based on the aforementioned second-row information, the number of data points included in the basic second-row to be determined is obtained. The determination of valid and interfering second-rows is performed only if the number of data points is greater than a preset number. Based on the aforementioned secondary information, the vehicle status and duration of the basic secondary line to be determined are obtained. If the vehicle status is a stable battery state and the duration is less than a second preset time, it is determined to be an interfering secondary line; otherwise, it is a valid secondary line.

8. The V2G charging and discharging behavior recognition method based on vehicle-to-everything (V2G) big data according to claim 1, characterized in that, The second merging rule includes: Obtain the start and end times of each valid row, and select the valid rows whose interval between the end time of the previous valid row and the start time of the next valid row is less than a third preset time as candidate valid rows in the same group. For each candidate valid row, the vehicle status and charging status bits are obtained based on the row information. Candidate valid rows with the same vehicle status and charging status bits are merged into a complete row.

9. The V2G charging and discharging behavior recognition method based on vehicle-to-everything (V2G) big data according to claim 8, characterized in that, The second merging rule further includes: for valid rows that cannot be merged according to the second merging rule, obtaining the corresponding duration and SOC change, and removing valid rows whose duration is less than the minimum time threshold and whose SOC change is less than the maximum change value.

10. A V2G charging and discharging behavior recognition system based on vehicle-to-everything (V2G) big data, characterized in that, The system is used to implement the method as described in any one of claims 1 to 9.

Images