Charging device scheduling method, electronic device, storage medium and program product

Abstract

Embodiments of the present application provide a charging device scheduling method, an electronic device, a storage medium and a program product. The method comprises: predicting a charging demand of a target area based on historical charging data of the target area; matching, among mobile charging devices located within a set area range corresponding to the target area, a candidate mobile charging device capable of providing an electric quantity corresponding to the charging demand; determining, according to path information of the candidate mobile charging device moving to the target area, a target mobile charging device scheduled to the target area among the candidate mobile charging devices; and controlling the target mobile charging device to move to the target area. The method can accurately predict the charging demand of the target area by predicting the historical data, effectively allocate mobile charging devices to the target area, and meet the charging demand of users in the target area.

Description

Technical Field

[0001] This application relates to the field of charging scheduling technology, and in particular to a charging equipment scheduling method, electronic device, storage medium and program product. Background Technology

[0002] With the development of new energy vehicles, mobile charging piles are more flexible than fixed charging piles, and the demand for mobile charging piles is increasing.

[0003] Currently, mobile charging stations are generally dispatched manually. Staff members dispatch the mobile charging stations to designated areas in advance. However, in some densely populated areas, the number of mobile charging stations is less than the demand from users, while in some remote areas, the number of mobile charging stations exceeds the demand from users. This results in an uneven distribution of charging resources and makes it difficult to meet users' charging needs. Summary of the Invention

[0004] This application provides a charging equipment scheduling method, electronic device, storage medium, and program product to solve the technical problem of uneven distribution of charging resources and difficulty in meeting users' charging needs.

[0005] In a first aspect, embodiments of this application provide a charging device scheduling method, including:

[0006] Based on historical charging data of the target area, predict the charging demand of the target area;

[0007] Among the mobile charging devices located within a set area corresponding to the target area, a candidate mobile charging device is matched that can provide the power corresponding to the charging demand;

[0008] Based on the path information of the candidate mobile charging devices moving to the target area, a target mobile charging device is determined from the candidate mobile charging devices and scheduled to be dispatched to the target area.

[0009] Control the target mobile charging device to move to the target area.

[0010] In one possible implementation, predicting the charging demand of the target area based on historical charging data of the target area includes:

[0011] The historical charging demand and historical charging supply data are input into the prediction model, and the charging demand of the target area is output. The charging demand includes the charging demand of each area in the target area and the peak demand period.

[0012] The historical charging demand is determined by the number of charging users, the charging frequency of each user, the time of peak hours, and the number of peak hours; the historical charging supply is determined based on the number of historical mobile charging devices and the charging capacity of each mobile charging device.

[0013] In one possible implementation, it also includes:

[0014] When a preset time remains before the peak demand period, a preset number of mobile charging devices located in the area with the lowest charging demand in the target area are moved to the area with the highest charging demand in the target area. The areas with the highest and lowest charging demand are determined based on the charging demand of each area in the target area.

[0015] In one possible implementation, matching alternative mobile charging devices that can provide the power required for the charging demand from among the mobile charging devices located within a defined area corresponding to the target area includes:

[0016] In the mobile charging devices within the set area corresponding to the target area, the remaining power of the currently unused mobile charging devices is obtained, and the remaining power of the currently unused mobile charging devices is compared with the preset power.

[0017] Mobile charging devices with remaining battery power greater than the preset battery power are considered as alternative mobile charging devices that can provide the battery power corresponding to the charging demand.

[0018] In one possible implementation, determining the target mobile charging device to be scheduled to the target area based on the path information of the candidate mobile charging devices moving to the target area includes:

[0019] The path length in the path information of the candidate mobile charging device to the target area is compared with the preset path length, and the candidate mobile charging device whose path length is less than the preset path length is determined and scheduled to be the target mobile charging device in the target area.

[0020] In one possible implementation, controlling the target mobile charging device to move to the target area includes:

[0021] A control command is sent to the target mobile charging device, the control command including path information, so that the target mobile charging device can move to the target area based on the path information.

[0022] In one possible implementation, the path information is determined in the following way:

[0023] A reinforcement learning-based scheduling algorithm is used to determine the path information of each mobile charging device based on the number of charging users, the charging frequency of each user, the time of peak hours, the number of peak hours, and the starting location of the mobile charging device in the historical charging data.

[0024] In one possible implementation, it also includes:

[0025] For each scheduling, obtain the expected revenue and the actual revenue corresponding to the scheduling;

[0026] A difference analysis was performed between the expected return and the actual return to obtain the difference analysis results.

[0027] Secondly, embodiments of this application provide a charging equipment scheduling device, comprising:

[0028] The processing unit is used to predict the charging demand of the target area based on historical charging data of the target area;

[0029] The processing unit is also configured to match, among the mobile charging devices located within a set area corresponding to the target area, a candidate mobile charging device that can provide the power corresponding to the charging demand;

[0030] The processing unit is further configured to determine, based on the path information of the alternative mobile charging devices moving to the target area, a target mobile charging device to be scheduled to the target area from the alternative mobile charging devices;

[0031] A control unit is used to control the target mobile charging device to move to the target area.

[0032] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0033] The memory stores computer-executed instructions;

[0034] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0035] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0036] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0037] The charging device scheduling method, electronic device, storage medium, and program product provided in this application's embodiments predict the charging demand of a target area by analyzing historical charging data. Furthermore, among mobile charging devices located within a designated area corresponding to the target area, alternative mobile charging devices that can provide the corresponding amount of electricity to meet the charging demand are matched. A target mobile charging device is determined from the alternatives based on path information, and the target mobile charging device is controlled to travel to the target area to provide charging services. By predicting historical data, the charging demand of the target area can be accurately predicted, effectively allocating mobile charging devices to the target area and meeting the charging needs of users in the target area. Attached Figure Description

[0038] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0039] Figure 1 A schematic diagram illustrating a scenario for the charging equipment scheduling method provided in this application;

[0040] Figure 2 Flowchart of the charging equipment scheduling method provided in this application Figure 1 ;

[0041] Figure 3 Flowchart of the charging equipment scheduling method provided in this application Figure 2 ;

[0042] Figure 4 A diagram illustrating the changes in charging demand and supply;

[0043] Figure 5 A thermal imaging diagram illustrating charging demand;

[0044] Figure 6 Flowchart of the charging equipment scheduling method provided in this application Figure 3 ;

[0045] Figure 7 A schematic diagram of the charging equipment scheduling device provided in this application;

[0046] Figure 8 A schematic diagram of the structure of the electronic device provided in this application.

[0047] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0048] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0049] Figure 1 This is a schematic diagram illustrating a scenario for the charging equipment scheduling method provided in this application, such as... Figure 1 As shown, the system includes a server 101 and multiple mobile charging piles 102. The server 101 is communicatively connected to the multiple mobile charging piles 102. The server 101 uses historical charging data of the target area to predict the charging demand of the target area. The server 101 matches candidate mobile charging devices that can provide the corresponding amount of electricity to the charging demand among the mobile charging devices located within a set area corresponding to the target area. The server 101 determines the target mobile charging device to be dispatched to the target area based on the path information of the candidate mobile charging devices moving to the target area. The server 101 controls the target mobile charging device to move to the target area.

[0050] Based on the above scenarios, it is clear that existing technologies suffer from uneven distribution of charging resources, making it difficult to meet users' charging needs.

[0051] The charging equipment scheduling method provided in this application predicts the charging demand of a target area using historical charging data. It then matches candidate mobile charging devices that can provide the required charging capacity from among the mobile charging devices located within a designated area corresponding to the target area. Based on path information, it determines a target mobile charging device from the candidate devices and controls the target mobile charging device to travel to the target area to provide charging services. By predicting from historical data, the method can accurately predict the charging demand of the target area, effectively allocate mobile charging devices to the target area, and meet the charging needs of users in the target area.

[0052] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0053] Figure 2 Flowchart of the charging equipment scheduling method provided in this application Figure 1 ,like Figure 2 As shown, the method includes:

[0054] Step 201: Based on historical charging data of the target area, predict the charging demand of the target area.

[0055] In this embodiment, the executing entity is an electronic device, which can be a digital computer in various forms, such as a laptop computer, desktop computer, workbench, server, blade server, mainframe computer, and other suitable computers.

[0056] Specifically, when scheduling conditions are met, historical charging data for the target area is acquired. These scheduling conditions can be pre-set based on time, such as a 30-minute interval. If the difference between the current time and the last scheduling time is 30 minutes, the scheduling conditions are considered met, historical charging data for the target area is acquired, and the charging demand for that area is predicted. Alternatively, scheduling personnel can trigger a scheduling request via a terminal. The electronic device receives and parses the request, obtains an area identifier, identifies the area corresponding to the identifier as the target area, acquires historical charging data for the target area, and thus predicts the charging demand for that target area.

[0057] Step 202: Among the mobile charging devices located within the set area corresponding to the target area, match alternative mobile charging devices that can provide the power required for charging.

[0058] In this embodiment, among the mobile charging devices located within a set area corresponding to the target area, alternative mobile charging devices that can provide the power corresponding to the charging demand are matched. The alternative mobile charging devices are mobile charging devices that are not currently in use and have sufficient power, so as to exclude mobile charging devices that are currently in use and / or mobile charging devices with insufficient power.

[0059] Step 203: Based on the path information of the candidate mobile charging devices moving to the target area, determine the target mobile charging device to be dispatched to the target area from among the candidate mobile charging devices.

[0060] In this embodiment, the path information of the candidate mobile charging devices moving to the target area is obtained. Based on the path information of the candidate mobile charging devices moving to the target area, the target mobile charging device that can be dispatched to the target area is selected from the candidate mobile charging devices, such as selecting the mobile charging device with the shortest path distance.

[0061] Step 204: Control the target mobile charging device to move to the target area.

[0062] In this embodiment, the electronic device sends a control command to the target mobile charging device to control the target mobile device. After receiving the control command, the target mobile charging device moves to the target area.

[0063] The charging device scheduling method provided in this application predicts the charging demand of a target area by analyzing historical charging data. It then matches candidate mobile charging devices that can provide the required charging capacity from among the mobile charging devices located within a designated area corresponding to the target area. Based on path information, a target mobile charging device is selected from the candidate devices and directed to the target area to provide charging services. By predicting historical data, the charging demand of the target area can be accurately predicted, effectively allocating mobile charging devices to the target area and meeting the charging needs of users in the target area.

[0064] Figure 3 Flowchart of the charging equipment scheduling method provided in this application Figure 2 ,like Figure 3 As shown, in this embodiment... Figure 2 Based on the embodiments, the charging equipment scheduling method is described in detail, which includes:

[0065] Step 301: Based on the historical charging data of the target area, predict the charging demand of the target area.

[0066] In this embodiment, the executing entity is an electronic device, which can be a digital computer in various forms, such as a laptop computer, desktop computer, workbench, server, blade server, mainframe computer, and other suitable computers.

[0067] Specifically, when scheduling conditions are met, historical charging data for the target area is acquired. These scheduling conditions can be pre-set based on time, such as a 30-minute interval. If the difference between the current time and the last scheduling time is 30 minutes, the scheduling conditions are considered met, historical charging data for the target area is acquired, and the charging demand for that area is predicted. Alternatively, scheduling personnel can trigger a scheduling request via a terminal. The electronic device receives and parses the request, obtains an area identifier, identifies the area corresponding to the identifier as the target area, acquires historical charging data for the target area, and thus predicts the charging demand for that target area.

[0068] In one possible implementation, the charging demand of the target area is predicted based on historical charging data of the target area, including:

[0069] The historical charging demand and supply data are input into the prediction model to output the charging demand of the target area. The charging demand includes the charging demand of each area in the target area and the peak demand period. The historical charging demand is determined by the number of charging users, the charging frequency of each user, the time of the peak period, and the number of peak periods. The historical charging supply is determined based on the number of mobile charging devices and the charging capacity of each mobile charging device.

[0070] In this embodiment, the prediction model can be a Long Short-Term Memory (LSTM) neural network or a time series analysis model (ARIMA model). The ARIMA model is an autoregressive statistical model primarily used for modeling and predicting time series data. Historical charging demand and supply data from historical charging data are input into the prediction model, and the model outputs the charging demand for the target area. This charging demand includes the charging volume and peak demand periods for each region within the target area.

[0071] Specifically, historical charging demand is determined by the number of charging users, the charging frequency of each user, the time of peak hours, and the number of peak hours. The number of charging users, the charging frequency of each user, the time of peak hours, and the number of peak hours are substituted into formula (1) to calculate historical charging demand. Formula (1) is expressed as:

[0072]

[0073] Where D(t) represents the charging demand at time t, N represents the number of users, F represents the charging frequency per user, and k represents the number of peak periods. Let be the time of the i-th peak period.

[0074] Specifically, the historical charging supply is determined based on the number of historical mobile charging devices and the charging capacity of each device. Substituting the number of historical mobile charging devices and the charging capacity of each device into formula (2) calculates the historical charging supply. Formula (2) is expressed as:

[0075] S(t)=U×C Formula (2)

[0076] Where S(t) is the charging supply at time t, U is the number of mobile charging units, and C is the charging capacity of each unit.

[0077] See Figure 4 , Figure 4 This diagram illustrates the changes in charging demand and supply. The solid blue line shows the total charging demand of users at different times of the day. Demand peaks around 8:00 AM and 6:00 PM, while it is lowest around 2:00 PM and 3:00 PM. The dashed red line represents the available charging capacity. It can be observed that charging demand increases significantly during peak hours and decreases significantly during off-peak hours.

[0078] Optionally, the method further includes:

[0079] When there is a preset time remaining before the peak demand period, a preset number of mobile charging devices located in the area with the lowest charging demand in the target area are moved to the area with the highest charging demand in the target area. The areas with the highest and lowest charging demand are determined based on the charging demand of each area in the target area.

[0080] In this embodiment, a prediction model is used to obtain the charging demand during peak demand periods and in each area of ​​the target region. Based on the charging demand in each area of ​​the target region, the areas with the highest and lowest charging demand are determined. The areas are then sorted from highest to lowest charging demand, and the area with the highest charging demand is designated as the area with the lowest charging demand. When a preset amount of time remains before the peak demand period, a preset number of mobile charging devices located in the area with the lowest charging demand are moved to the area with the highest charging demand. This allows for the pre-deployment of more mobile charging devices in high-demand areas and a reduction in the number of mobile charging devices in low-demand areas, ensuring optimal resource allocation and utilization. Increasing the number of mobile charging devices in high-demand areas and decreasing their number in low-demand areas reduces waiting time for mobile charging devices during peak periods, effectively improving charging services.

[0081] Optionally, the method further includes:

[0082] The charging demand density of the target area is determined by the charging demand of each area and the area of ​​each area.

[0083] In this embodiment, the charging demand of each region in the target area and the area of ​​each region are substituted into formula (3) to calculate the charging demand density. Formula (3) is expressed as:

[0084]

[0085] Among them, D density For demand density, Q i For the charging demand of region i in the target area, A i Let be the area of ​​the i-th region in the target region.

[0086] Optionally, to help dispatch staff gain a more intuitive understanding of the charging demand in each area, a charging demand thermal imaging map can be generated based on the charging demand density. (See [link]). Figure 5 , Figure 5 A thermal imaging diagram illustrating charging demand. Figure 5The "dots" in the diagram represent different locations within the target area. The horizontal and vertical axes represent longitude and latitude, respectively. The target area mainly includes four zones: the city center, commercial district, residential area, and remote areas relatively far from the city center. The density of charging demand in each zone is represented by the shade of color, with the color gradually changing from black to red to yellow, representing a change from low demand to high demand. Figure 5 As can be seen, the charging demand density is highest in city centers, represented by numerous red and yellow dots, indicating a need for focused deployment of mobile charging equipment in this area. Commercial areas also have relatively high charging demand density, shown by many orange and yellow dots, suggesting that coverage can be increased to meet high traffic demands. Residential areas have moderate charging demand density, represented by yellow and light yellow dots, indicating a need for service optimization and rational distribution of mobile charging equipment. Remote areas have low charging demand density, shown by many dark red and black dots, but basic services still need to be ensured to provide charging support in emergencies. The charging demand density provides a clear view of the distribution of charging demand in different areas, which is helpful for the deployment and scheduling of mobile charging equipment, improving overall service quality and economic efficiency.

[0087] Step 302: Among the mobile charging devices located within the set area corresponding to the target area, match alternative mobile charging devices that can provide the power required for charging.

[0088] In this embodiment, among the mobile charging devices located within a set area corresponding to the target area, alternative mobile charging devices that can provide the power corresponding to the charging demand are matched. The alternative mobile charging devices are mobile charging devices that are not currently in use and have sufficient power, so as to exclude mobile charging devices that are currently in use and / or mobile charging devices with insufficient power.

[0089] In one possible implementation, among the mobile charging devices located within a designated area corresponding to the target area, alternative mobile charging devices that can provide the power required for charging are matched, including:

[0090] Within the designated area corresponding to the target area, obtain the remaining power of currently unused mobile charging devices, compare the remaining power of the currently unused mobile charging devices with a preset power level, and select mobile charging devices with remaining power levels greater than the preset power level as candidate mobile charging devices that can provide the power level corresponding to the charging needs.

[0091] In this embodiment, among the mobile charging devices within the set area corresponding to the target area, currently unused mobile charging devices are selected, the remaining power of the currently unused mobile charging devices is obtained, and the remaining power of the currently unused mobile charging devices is compared with a preset power. The preset power is set according to the actual situation. If the remaining power is too low, the mobile charging device cannot move to the corresponding position. Mobile charging devices with remaining power greater than the preset power are selected as candidate mobile charging devices that can provide the power corresponding to the charging needs.

[0092] Step 303: Based on the path information of the candidate mobile charging devices moving to the target area, determine the target mobile charging device to be dispatched to the target area from the candidate mobile charging devices.

[0093] In this embodiment, the path information of the candidate mobile charging devices moving to the target area is obtained. Based on the path information of the candidate mobile charging devices moving to the target area, the target mobile charging device that can be dispatched to the target area is selected from the candidate mobile charging devices, such as selecting the mobile charging device with the shortest path distance.

[0094] In one possible implementation, based on the path information of the candidate mobile charging devices moving to the target area, the target mobile charging device is determined from the candidate mobile charging devices and scheduled to be dispatched to the target area, including:

[0095] The path length in the path information of the candidate mobile charging device to the target area is compared with the preset path length. The candidate mobile charging device with the path length less than the preset path length is determined and dispatched to the target mobile charging device in the target area.

[0096] In this embodiment, the path length in the path information of the candidate mobile charging device to the target area is compared with the preset path length. The preset path can be set according to needs, such as revenue. If the distance is too far, the scheduling cost will be relatively high from a cost perspective. The candidate mobile charging device with a path length less than the preset path length is determined as the target mobile charging device to be scheduled to the target area.

[0097] In one possible implementation, the path information is determined in the following way:

[0098] A reinforcement learning-based scheduling algorithm is used to determine the path information of each mobile charging device based on the number of charging users, the charging frequency of each user, the time of peak hours, the number of peak hours, and the starting location of the mobile charging device in the historical charging data.

[0099] In this embodiment, the number of charging users, the charging frequency of each user, the time of peak hours, the number of peak hours, and the starting position of the mobile charging device are obtained from the historical charging data. A scheduling algorithm based on reinforcement learning is adopted to obtain the path information of each mobile charging device based on the number of charging users, the charging frequency of each user, the time of peak hours, the number of peak hours, and the starting position of the mobile charging device. Each mobile charging device travels to the target area based on the path information, thereby providing charging services to users in the target area.

[0100] Step 304: Control the target mobile charging device to move to the target area.

[0101] In this embodiment, the electronic device sends a control command to the target mobile charging device to control the target mobile device. After receiving the control command, the target mobile charging device moves to the target area.

[0102] In one possible implementation, controlling the target mobile charging device to move to the target area includes:

[0103] Send control commands to the target mobile charging device. The control commands include path information so that the target mobile charging device can move to the target area based on the path information.

[0104] In this embodiment, a control command is sent to the target mobile charging device. The control command includes path information. The target mobile charging device receives the control command, parses the control command, obtains the path information, and moves to the target area based on the path information, thereby completing the scheduling of the mobile charging device.

[0105] Step 305: For each scheduling, obtain the expected revenue and the actual revenue corresponding to the scheduling.

[0106] In this embodiment, for each scheduling, the expected benefit and the actual benefit corresponding to the scheduling are calculated.

[0107] The expected return is determined in the following way:

[0108] Obtain the projected total revenue from charging services, the projected total revenue from differences in charging speeds, the projected advertising revenue, and the projected total revenue from value-added services. Based on these projected total revenues, the projected total revenue from differences in charging speeds, the projected advertising revenue, and the projected total revenue from value-added services, calculate the expected revenue.

[0109] In this embodiment, the charging standards for different charging periods are analyzed. In order to accurately calculate the total charging service revenue, the charging volume and charging standards are substituted into the formula to calculate the expected total charging service revenue. Formula (4) is expressed as:

[0110]

[0111] Among them, R charging For the projected total revenue from charging services, Q i Let P be the charging amount in the i-th time period. i Let $n$ represent the charging standard for the $i$-th time period, and $n$ represent the number of time periods. A time-based charging strategy is adopted, which improves adaptability to charging demand during different time periods and solves the problem of unreasonable charging standards during peak and off-peak hours.

[0112] Furthermore, the total revenue generated from the difference in charging speed is projected as follows:

[0113] To meet diverse user needs, the price difference between fast charging and slow charging was also considered. Specifically, a speed-based pricing formula was adopted, as follows:

[0114]

[0115] Among them, R speed Q represents the total revenue generated from the projected difference in charging speed. fast,j and Q alow,j P represents the fast charging and slow charging amounts for user j, respectively. fast and P slow The prices are for fast charging and slow charging, respectively, where m represents the number of users. A speed-based pricing strategy is adopted, improving responsiveness to different user needs and resolving the issue of unreasonable pricing between fast and slow charging.

[0116] Furthermore, advertising revenue can be projected through the following methods:

[0117] Regarding additional service revenue, advertising revenue from mobile charging devices was considered. The specific advertising revenue formula used is as follows:

[0118] R ads =A×P ads Formula (6)

[0119] Among them, R ads Let A be the projected advertising revenue, and P be the advertising area or number of advertisements. ads The price per unit of advertising. An advertising placement strategy was adopted, increasing additional revenue streams and addressing the issue of relying on a single revenue source.

[0120] Furthermore, the total revenue from value-added services is projected in the following ways:

[0121] In addition, value-added services such as vehicle cleaning and basic maintenance are provided, specifically using a value-added service revenue formula, as follows:

[0122]

[0123] Among them, R value_added S represents the projected total revenue from value-added services. k P represents the quantity of the k-th value-added service. service,k Let p be the price of the k-th value-added service, and p be the number of different value-added services. By employing multiple value-added service strategies, service diversity and revenue streams are increased, thus addressing the issue of limited service offerings.

[0124] Furthermore, by substituting the expected total revenue from charging services, the expected total revenue from differences in charging speeds, the expected advertising revenue, and the expected total revenue from value-added services into formula (8), the expected revenue is calculated. Formula (8) is expressed as:

[0125] R total =R charging +R speed +R ads +R value_added Formula (8)

[0126] Among them, R total For the expected return, R charging For the projected total revenue from charging services, R speed R represents the total revenue generated from the projected difference in charging speed. ads For the projected advertising revenue, R value_added This represents the projected total revenue from value-added services. By comprehensively considering multiple revenue streams, the diversity and stability of revenue are improved, thus solving the problem of relying on a single revenue source.

[0127] Furthermore, the actual benefit is determined in the following way:

[0128] The system obtains the total revenue from actual charging services, the total revenue generated from the difference in actual charging speed, the actual advertising revenue, and the actual value-added service revenue. Based on these, the system calculates the actual profit.

[0129] In this embodiment, the total revenue from actual charging services, the total revenue generated from the difference in actual charging speed, the actual advertising revenue, and the actual value-added service revenue are obtained. These are then substituted into formula (9) to calculate the actual revenue. Formula (9) is expressed as:

[0130] R actual =R1+R2+R3+R4 Formula (9)

[0131] Among them, R actualFor actual revenue, R1 is the total revenue from actual charging services, R2 is the total revenue generated from the difference in actual charging speed, R3 is the actual advertising revenue, and R4 is the actual value-added service revenue.

[0132] Step 306: Perform a difference analysis between expected and actual returns to obtain the results of the difference analysis.

[0133] In this embodiment, a difference analysis is performed between actual and expected revenue. This analysis uses regression analysis, correlation analysis, decision tree analysis, or feature importance analysis to obtain the difference analysis results, assess the impact of each factor on total revenue, and identify and select key features that significantly affect revenue. Users then adjust and optimize based on the results of the difference analysis, such as optimizing scheduling paths, adjusting the deployment of mobile charging devices, and improving charging and value-added services. This continuous iteration and improvement of the scheduling strategy ensures that the scheduling algorithm can adapt to dynamically changing charging demands and improve overall revenue.

[0134] The charging equipment scheduling method provided in this application can accurately predict the charging demand of a target area, effectively allocate mobile charging equipment to the target area, and meet the charging needs of users in the target area.

[0135] Figure 6 Flowchart of the charging equipment scheduling method provided in this application Figure 3 ,like Figure 6 As shown, the charging equipment scheduling method is described in detail, and the method includes:

[0136] Step 601: Obtain basic data on factors affecting the revenue of mobile charging devices.

[0137] In this embodiment, basic data on factors affecting the revenue of mobile charging devices are obtained. The basic data includes: charging demand and supply, predicted operating costs, revenue, energy management and energy storage efficiency, geographical location and coverage.

[0138] Specifically, the number of charging users per day, the charging frequency of each user, the time of peak hours, and the number of peak hours are obtained, and then substituted into formula (10) to calculate the charging demand. Formula (10) is expressed as:

[0139]

[0140] Where D(t) represents the charging demand at time t, N represents the number of users, F represents the charging frequency per user, and k represents the number of peak periods. Let be the time of the i-th peak period.

[0141] Specifically, the number of mobile charging devices and the charging capacity of each mobile charging device are obtained. The number of mobile charging devices and the charging capacity of each mobile charging device are substituted into formula (11) to calculate the charging supply. Formula (11) is expressed as:

[0142] S(t)=U×C Formula (11)

[0143] Where S(t) is the charging supply at time t, U is the number of mobile charging units, and C is the charging capacity of each unit.

[0144] Specifically, the data collection includes the purchase cost, maintenance and upkeep costs of mobile charging equipment, electricity prices and charging volume for each time period, and labor costs for management and maintenance personnel. Time features (e.g., hour, day of the week, month), electricity price features (e.g., peak and off-peak prices), charging volume features (e.g., charging volume for each time period), and labor cost features (e.g., number of management and maintenance personnel) are extracted, and the data is preprocessed.

[0145] Specifically, the total cost of the equipment is calculated as follows:

[0146] C e =N e ×(P e +M e ×T) Formula (12)

[0147] Among them, C e N represents the total cost of the equipment. e For the number of mobile charging devices, P e The purchase cost of each mobile charging device, M e The monthly maintenance and upkeep cost for each mobile charging device, where T represents usage time (in months). This improves the accuracy of device cost calculations and solves the problem of inaccurate long-term cost forecasting.

[0148] The total energy cost is calculated as follows:

[0149]

[0150] Among them, C energy For the total energy cost, Q i Let P be the charging amount in the i-th time period. i Let be the electricity price for the i-th time period, and n be the number of time periods. This improves adaptability to energy cost fluctuations and solves the cost calculation problem caused by differences in electricity prices across different time periods.

[0151] Specifically, the total labor cost is calculated as follows:

[0152]

[0153] Among them, C h For total labor costs, N mj Let W be the number of managers in category j. mj The salary of managerial staff in category j includes basic salary and other compensation, N tj W represents the number of scheduling and maintenance personnel of type j. tj Let m be the salary of the j-th type of dispatching and maintenance personnel, and m be the number of personnel in each category. This method improves the accuracy of labor cost calculation and solves the cost allocation problem in human resource management.

[0154] Furthermore, the forecast of operating costs is calculated in the following manner:

[0155] C total =C e +C energy +C h Formula (15)

[0156] Among them, C total For the predicted operating costs, C e For the total cost of equipment, C energy For the total energy cost, C h This represents the total labor cost.

[0157] Specifically, the revenue is calculated as follows:

[0158] R actual =R1+R2+R3+R4 Formula (16)

[0159] Among them, R actual For actual revenue, R1 is the total revenue from actual charging services, R2 is the total revenue generated from the difference in actual charging speed, R3 is the actual advertising revenue, and R4 is the actual value-added service revenue.

[0160] Furthermore, energy management and energy storage efficiency are achieved through the following methods:

[0161] In this embodiment, the charge-discharge efficiency of the energy storage battery is one of the key indicators of energy storage system efficiency. The charge-discharge efficiency formula is calculated in the following way:

[0162]

[0163] Where, η charge / discharge For charge and discharge efficiency, E out E is the energy output when the battery discharges. in The energy input during battery charging. Taking into account energy losses during actual charging and discharging processes improves the accuracy of efficiency calculations and solves the problem of dynamic charge / discharge efficiency evaluation.

[0164] Meanwhile, energy loss in the energy storage system is also a significant factor affecting system efficiency. Energy loss is calculated in the following way:

[0165] L storage =E in -E out Formula (18)

[0166] Among them, L storage For energy loss, E in For the input energy, E out Compared to traditional single-loss estimation methods, this method improves the accuracy of loss calculation by taking into account the difference between actual energy input and output, thus solving the problem of inaccurate energy loss assessment.

[0167] Regarding energy management strategies, an efficient energy management system was adopted. To optimize energy use and storage strategies, effective energy utilization is calculated using the following formula:

[0168]

[0169] Among them, E managed For efficient energy utilization, T represents the time period, and E... lost,t Let be the energy loss during time period t. This can improve energy utilization efficiency and solve the problem of slow response speed in energy management systems.

[0170] Furthermore, a dynamically adjusted charge / discharge strategy was introduced to maximize benefits. To achieve this, adjustments were made in the following manner:

[0171]

[0172] Among them, E dynamic For the optimal energy utilization after dynamic adjustment, P t Let E be the electricity price for time period t. out,t Let C be the discharge amount in time period t. t Let E be the charging cost for time period t. in,t Let be the charging amount in time period t. A dynamic adjustment strategy can improve economic efficiency and solve the optimization problem under the influence of electricity price changes over different time periods.

[0173] By combining the above energy storage system efficiency and energy management strategies, efficient energy management and maximum energy storage efficiency can be achieved. The optimized effective energy utilization is calculated in the following way:

[0174]

[0175] Among them, Emanaged For efficient energy utilization after management system optimization, E dynamic To achieve optimal energy utilization through dynamic adjustment, and through charge and discharge efficiency Adjustments should be made to reflect the efficiency of actual utilization. storage Energy loss needs to be deducted from total energy utilization. This not only effectively improves the efficiency of energy storage systems, but also allows for dynamic adjustment of charging and discharging strategies through efficient energy management to cope with different demands and price changes, significantly improving dispatch efficiency and overall economic benefits.

[0176] Specifically, in terms of geographical location, the deployment location of mobile charging devices is a key factor. By analyzing the demand and coverage in city centers, commercial areas, residential areas, and remote areas, we can ensure that each area has appropriate charging facilities. For example, city centers, as high-demand areas, will focus on deploying mobile charging devices; commercial areas, as high-traffic areas, need increased coverage; residential areas, as areas with concentrated household users, need optimized service; and remote areas have less coverage but need to ensure basic service. To achieve this goal, the demand density formula is used, specifically:

[0177]

[0178] Among them, D density For demand density, Q i For the charging demand of region i in the target area, A i Let be the area of ​​region i in the target region. Demand density analysis was employed, which improves the accuracy of demand assessment in different regions and solves the problem of demand imbalance.

[0179] Secondly, regarding coverage, the breadth and density of the service area are determined. By increasing the service density in high-demand areas, the utilization rate of mobile charging devices can be improved. Simultaneously, high-demand areas are identified, and the distribution of mobile charging devices is dynamically adjusted to optimize scheduling paths, meeting maximum demand in the shortest time and improving overall service efficiency. Coverage density is calculated using the following method:

[0180]

[0181] Among them, C coverage For coverage density, N i For the mobile charging device in region i, A i Let be the area of ​​region i. Coverage density analysis was employed, which effectively improved the accuracy of service range assessment and solved the problem of uneven coverage.

[0182] Meanwhile, in order to optimize coverage and scheduling in high-demand areas, a scheduling optimization formula was used, specifically:

[0183]

[0184] Among them, S opt For the scheduling optimization objective, P j For the demand priority of region j, T avail,j Let C be the available time for region j. j Let T be the scheduling cost for region j. travel,j Let be the travel time to region j, which refers to the time required for a mobile charging device to move from one location to region j. Dynamic optimization improves scheduling efficiency and solves the problem of slow scheduling response.

[0185] Step 602: Process the basic data and construct the dataset, which will be used for training.

[0186] In this embodiment, the acquired basic data is processed, including normalization and outlier removal. The data requiring normalization and outlier removal includes: charging demand data, charging supply data, operating cost data, revenue data, energy management and energy storage efficiency data, and geographical location and coverage data. Processing this data ensures consistency and accuracy in subsequent processing and analysis, and a dataset is constructed based on this basic data for training purposes.

[0187] Furthermore, the data is mapped:

[0188] (1) Action attribute mapping:

[0189] {Charging demand and supply: 1, Operating costs: 2, Revenue model: 3, Energy management and energy storage efficiency: 4, Geographic location and coverage: 5}

[0190] (2) Factor mapping in action attributes:

[0191] The charging demand and supply relationship involves two factors: charging demand and charging supply. These factors need to be mapped as follows:

[0192] {Charging demand: a, Charging supply: b}

[0193] Operating costs include three factors: equipment costs, energy costs, and labor costs, which need to be mapped as follows:

[0194] {Equipment cost: c, Energy cost: d, Labor cost: e}

[0195] Revenue includes two factors: charging service fees and additional service revenue, which need to be mapped as follows:

[0196] {Charging service fee: f, Additional service revenue: g}

[0197] Energy management and energy storage efficiency include two factors: energy storage system efficiency and energy management strategy, which need to be mapped as follows:

[0198] {Energy storage system efficiency: h, energy management strategy: i}

[0199] The relationship between geographic location and coverage area includes two factors: geographic location and coverage area. These need to be mapped as follows:

[0200] {Geographic location: j, Coverage area: k}.

[0201] Step 603: Construct and train the reinforcement learning algorithm and the global optimization network.

[0202] In this embodiment, a reinforcement learning algorithm is used to dynamically adjust the scheduling strategy of mobile charging devices based on historical and real-time data, optimizing the path and charging task allocation of mobile charging devices. By establishing a revenue maximization model, considering factors such as charging demand and supply, operating costs, revenue, energy management and storage efficiency, geographical location, and coverage, the expected revenue of each scheduling scheme is calculated. A multi-objective optimization algorithm is used to balance revenue maximization and charging service quality, ensuring that a high level of service quality is maintained while increasing revenue.

[0203] Specifically, reinforcement learning algorithms are used to dynamically adjust the scheduling strategy of mobile charging devices based on historical and real-time data, optimizing the path and charging task allocation of mobile charging devices. In particular, the scheduling problem can be modeled as a Markov Decision Process (MDP), where the state represents the current charging demand and supply distribution, the action represents the scheduling and path selection of mobile charging devices, and the reward function reflects scheduling efficiency and service quality.

[0204] The scheduling strategy optimization utilizes a reinforcement learning algorithm, specifically:

[0205] Q(s,a)<-Q(s,a)+α(r+γmax a′ Formula (25) - Q(s,a)

[0206] Here, Q(s,a) represents the value of taking action a in state s, α is the learning rate, r is the reward, γ is the discount factor, s′ is the next state, and a′ is the optimal action to take in the next state. The process involves initializing the Q-table and setting all Q values ​​to zero. Observing the current state s, an action a is selected and executed. The reward r from action a and the next state s′ are recorded, and the Q-values ​​are updated using the update rule described above. The current state is then updated to the next state. These steps are repeated until the termination condition is met.

[0207] Through repeated iterations and learning, reinforcement learning algorithms can gradually optimize the scheduling strategy of mobile charging devices, finding the optimal path and task allocation scheme under different demand and supply conditions, thereby improving the scheduling efficiency and overall service quality of mobile charging devices. The adoption of a dynamic adjustment strategy effectively improves scheduling efficiency and solves the problem of slow scheduling response.

[0208] Furthermore, a revenue maximization model is established, considering factors such as charging demand and supply, operating costs, revenue, energy management and energy storage efficiency, geographical location and coverage, to calculate the expected revenue of each scheduling scheme. The revenue maximization model uses a comprehensive revenue calculation formula, specifically:

[0209] R total =R charging +R speed +R ads +R value_added -(C e +C energy +C h )

[0210] Formula (25)

[0211] Among them, R total For total revenue, R charging For total revenue from charging services, R speed R represents the total revenue generated from differences in charging speed. ads For advertising revenue, R value_added For total revenue from value-added services, C e For the total equipment cost, C energy For the total energy cost, C h This represents the total labor cost. By comprehensively considering various revenue and cost factors, the accuracy of revenue calculation is improved, and the problem of inaccurate revenue estimation is solved.

[0212] Furthermore, a multi-objective optimization algorithm is used to balance revenue maximization and charging service quality, ensuring that a high level of service quality is maintained while increasing revenue. The multi-objective optimization is performed in the following manner:

[0213] Minimize(f1(x),f2(x),…,f k Formula (26) (x)

[0214] Among them, f i (x) represents the i-th objective function, and k represents the number of objectives. A multi-objective optimization strategy is adopted, which improves the balance among multiple optimization objectives and resolves the conflict problem in multi-objective optimization.

[0215] Furthermore, through feature importance analysis, key features are identified and selected. These features refer to the aforementioned basic data, thereby improving the interpretability and accuracy of the model. Feature importance analysis uses a feature importance score calculation formula, specifically:

[0216]

[0217] Among them, I j The importance score for feature j, where T is the number of decision trees. The importance score of feature j in the t-th tree is calculated. Multi-decision tree analysis is employed, which improves the accuracy of feature selection and addresses the instability problem in feature selection.

[0218] Furthermore, by employing a model ensemble strategy, the prediction results of multiple sub-models are combined to reduce the error of a single model, thereby improving the overall model's performance and reliability. The model ensemble strategy utilizes a model prediction averaging formula, specifically:

[0219]

[0220] in, The final prediction result is given, where T is the number of models. Let t represent the prediction result of the t-th model. Employing a multi-model ensemble strategy improves the stability and accuracy of predictions, addressing the problem of inaccurate predictions from a single model.

[0221] Furthermore, by constructing and training QDL and global optimization networks, the scheduling strategy for mobile charging devices can be optimized, thereby improving operational efficiency and service quality.

[0222] Step 604: Based on the optimized scheduling algorithm, schedule the mobile charging devices, evaluate the actual benefits of each scheduling, perform a difference analysis between the expected benefits and the actual benefits, and obtain the difference analysis results.

[0223] In this embodiment, a predictive model is used to analyze historical data and current charging conditions to estimate charging demand trends for the next few hours or days, and to formulate a scheduling plan in advance. The predictive model is an LSTM neural network or an ARIMA model. The input data includes historical charging demand data and current real-time charging demand data. The predictive model is trained to identify patterns of changing charging demand. Furthermore, the trained predictive model is used to make predictions, and the prediction results include charging demand volume and peak demand periods. Based on the prediction results, more mobile charging devices are deployed in high-demand areas in advance, and the number of mobile charging devices in low-demand areas is reduced.

[0224] Step 605: For each scheduling, perform a difference analysis between the expected revenue and the actual revenue to obtain the difference analysis results.

[0225] In this embodiment, the total revenue from actual charging services, the total revenue generated from differences in actual charging speeds, the actual advertising revenue, and the actual value-added service revenue are obtained. The actual revenue is then summed to obtain the total revenue from actual charging services, the total revenue generated from differences in actual charging speeds, the actual advertising revenue, and the actual value-added service revenue. A difference analysis is performed between the actual revenue and the expected revenue to analyze the discrepancy. Regression analysis, correlation analysis, decision tree analysis, or feature importance analysis are used to obtain the difference analysis results, assess the impact of each factor on the total revenue, and identify and select key features that have a significant impact on revenue. Users adjust and optimize based on the results of the difference analysis, such as optimizing scheduling paths, adjusting the deployment of mobile charging devices, and improving charging services and value-added services. The scheduling strategy is continuously iterated and improved to ensure that the scheduling algorithm can adapt to dynamically changing charging demands and improve overall revenue.

[0226] In this embodiment, after optimization and adjustment, the deployment strategy of mobile charging devices is adjusted, the number of mobile charging devices is increased in high-demand areas and decreased in low-demand areas, the scheduling path is optimized, the waiting time of mobile charging devices during peak hours is reduced, the charging service is improved, and more value-added services are provided to increase revenue.

[0227] Figure 7 This is a schematic diagram of the structure of the charging equipment scheduling device provided in this application, as shown below. Figure 7 As shown, the charging equipment scheduling device 70 provided in this embodiment includes:

[0228] The processing unit 701 is used to predict the charging demand of the target area based on historical charging data of the target area. The processing unit 701 is also used to match alternative mobile charging devices that can provide the corresponding amount of electricity to the charging demand among mobile charging devices located within a set area corresponding to the target area. The processing unit 701 is also used to determine the target mobile charging device to be scheduled to the target area based on the path information of the alternative mobile charging devices moving to the target area. The control unit 702 is used to control the target mobile charging device to move to the target area.

[0229] In one possible implementation, the processing unit 701 is further configured to input the historical charging demand and historical charging supply from the historical charging data into the prediction model, and output the charging demand of the target area. The charging demand includes: the charging demand amount and peak demand periods of each area in the target area; wherein, the historical charging demand is determined by the number of charging users, the charging frequency of each user, and the time and number of peak periods; the historical charging supply is determined based on the number of historical mobile charging devices and the charging capacity of each mobile charging device.

[0230] In one possible implementation, the processing unit 701 is further configured to control a preset number of mobile charging devices located in the lowest charging demand area of ​​the target area to move to the highest charging demand area of ​​the target area when there is a preset time remaining before the peak demand period. The highest charging demand area and the lowest charging demand area are determined based on the charging demand of each area of ​​the target area.

[0231] In one possible implementation, the processing unit 701 is further configured to: obtain the remaining power of currently unused mobile charging devices within a set area range corresponding to the target area; compare the remaining power of currently unused mobile charging devices with a preset power level; and select mobile charging devices with remaining power levels greater than the preset power level as alternative mobile charging devices that can provide the power level corresponding to the charging demand.

[0232] In one possible implementation, the processing unit 701 is further configured to compare the path length in the path information of the candidate mobile charging device moving to the target area with a preset path length, and determine the candidate mobile charging device whose path length is less than the preset path length as the target mobile charging device to be scheduled to the target area.

[0233] In one possible implementation, the control unit 702 is further configured to send control commands to the target mobile charging device, the control commands including path information, so that the target mobile charging device can move to the target area based on the path information.

[0234] In one possible implementation, the processing unit 701 is further configured to employ a reinforcement learning-based scheduling algorithm to determine the path information of each mobile charging device based on the number of charging users in the historical charging demand in the historical charging data, the charging frequency of each user, the time of peak hours, the number of peak hours, and the starting location of the mobile charging device.

[0235] In one possible implementation, the processing unit 701 is further configured to, for each scheduling, obtain the expected revenue and the actual revenue corresponding to the scheduling; perform a difference analysis on the expected revenue and the actual revenue, and obtain the difference analysis results.

[0236] The charging equipment scheduling device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0237] Figure 8 A schematic diagram of the structure of the electronic device provided in this application. Figure 8As shown, the electronic device 80 provided in this embodiment includes at least one processor 801 and a memory 802. Optionally, the device 80 further includes a communication component 803. The processor 801, memory 802, and communication component 803 are connected via a bus 804.

[0238] In a specific implementation, at least one processor 801 executes computer execution instructions stored in memory 802, causing at least one processor 801 to perform the above-described method.

[0239] The specific implementation process of processor 801 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0240] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0241] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0242] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0243] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0244] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0245] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0246] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0247] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0248] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0249] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0250] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0251] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0252] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for scheduling charging equipment, characterized in that, include: Based on historical charging data of the target area, predict the charging demand of the target area; Among the mobile charging devices located within a set area corresponding to the target area, a candidate mobile charging device is matched that can provide the power corresponding to the charging demand; the candidate mobile charging device is currently not in use and has a remaining power greater than a preset power. Based on the path information of the candidate mobile charging devices moving to the target area, a target mobile charging device is determined from the candidate mobile charging devices and scheduled to be dispatched to the target area. The path information includes: path length; the path length of the target mobile charging device is less than a preset path length; Control the target mobile charging device to move to the target area; For the aforementioned scheduling, the expected revenue and the actual revenue corresponding to the scheduling are obtained; the expected revenue is determined based on the expected total revenue of charging services, the expected total revenue generated by the difference in charging speed, the expected advertising revenue, and the expected total revenue of value-added services; the actual revenue is determined based on the actual total revenue of charging services, the actual total revenue generated by the difference in charging speed, the actual advertising revenue, and the actual revenue of value-added services. A difference analysis is performed between the expected revenue and the actual revenue to obtain the difference analysis results; the difference analysis results are used to optimize the scheduling of mobile charging devices.

2. The method according to claim 1, characterized in that, The prediction of charging demand in the target area based on historical charging data of the target area includes: The historical charging demand and historical charging supply data are input into the prediction model, and the charging demand of the target area is output. The charging demand includes the charging demand of each area in the target area and the peak demand period. The historical charging demand is determined by the number of charging users, the charging frequency of each user, the time of peak hours, and the number of peak hours; the historical charging supply is determined based on the number of historical mobile charging devices and the charging capacity of each mobile charging device.

3. The method according to claim 2, characterized in that, Also includes: When a preset time remains before the peak demand period, a preset number of mobile charging devices located in the area with the lowest charging demand in the target area are moved to the area with the highest charging demand in the target area. The areas with the highest and lowest charging demand are determined based on the charging demand of each area in the target area.

4. The method according to claim 1, characterized in that, Among the mobile charging devices located within a designated area corresponding to the target area, the alternative mobile charging devices that can provide the power required for the charging demand include: In the mobile charging devices within the set area corresponding to the target area, the remaining power of the currently unused mobile charging devices is obtained, and the remaining power of the currently unused mobile charging devices is compared with the preset power. Mobile charging devices with remaining battery power greater than the preset battery power are considered as alternative mobile charging devices that can provide the battery power corresponding to the charging demand.

5. The method according to claim 1, characterized in that, The step of determining the target mobile charging device to be dispatched to the target area based on the path information of the candidate mobile charging devices moving to the target area includes: The path length in the path information of the candidate mobile charging device to the target area is compared with the preset path length, and the candidate mobile charging device whose path length is less than the preset path length is determined and scheduled to be the target mobile charging device in the target area.

6. The method according to claim 1, characterized in that, The control of the target mobile charging device to move to the target area includes: A control command is sent to the target mobile charging device, the control command including path information, so that the target mobile charging device can move to the target area based on the path information.

7. The method according to any one of claims 1 to 6, characterized in that, The path information is determined in the following way: A reinforcement learning-based scheduling algorithm is used to determine the path information of each mobile charging device based on the number of charging users, the charging frequency of each user, the time of peak hours, the number of peak hours, and the starting location of the mobile charging device in the historical charging data.

8. A charging equipment scheduling device, characterized in that, include: The processing unit is used to predict the charging demand of the target area based on historical charging data of the target area; The processing unit is further configured to match, among the mobile charging devices located within a set area corresponding to the target area, a candidate mobile charging device that can provide the power corresponding to the charging demand; the candidate mobile charging device is currently not in use and has a remaining power greater than a preset power. The processing unit is further configured to determine, based on the path information of the alternative mobile charging devices moving to the target area, a target mobile charging device to be scheduled to the target area from the alternative mobile charging devices; The path information includes: path length; the path length of the target mobile charging device is less than a preset path length; A control unit is used to control the target mobile charging device to move to the target area; The processing unit is further configured to, for the scheduling, obtain the expected revenue and the actual revenue corresponding to the scheduling; the expected revenue is determined based on the expected total revenue of charging services, the expected total revenue generated by the difference in charging speed, the expected advertising revenue, and the expected total revenue of value-added services; the actual revenue is determined based on the actual total revenue of charging services, the actual total revenue generated by the difference in charging speed, the actual advertising revenue, and the actual revenue of value-added services; perform a difference analysis on the expected revenue and the actual revenue to obtain the difference analysis results; the difference analysis results are used to optimize the scheduling of mobile charging devices.

9. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 7.

11. A computer program product comprising a computer program that, when executed by a processor, implements the method of any one of claims 1 to 7.

Images