Energy storage type charging station charging scheduling method and device, computer device and storage medium

Abstract

The application relates to an energy storage type charging station charging scheduling method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring charging demand information of a vehicle and current operation data of each charging pile of a charging station, and screening initial charging piles meeting the charging demand information of the vehicle; collecting electric quantity information of each initial charging pile and battery information of the vehicle, so as to screen a target charging pile corresponding to the vehicle through a charging pile scheduling strategy; collecting current environment information, and predicting a charging strategy of the vehicle through a charging prediction model; collecting current battery information of the vehicle and environment change information, so as to adjust the charging strategy of the vehicle, obtain a new charging strategy, replace the charging strategy with the new charging strategy, and return to execute the above steps until the current battery information of the vehicle is saturated electric quantity. The method can improve the charging efficiency of the charging station for the electric vehicle.

Description

Technical Field

[0001] This application relates to the fields of artificial intelligence and resource scheduling technology, and in particular to a charging scheduling method, apparatus, computer equipment and storage medium for energy storage charging stations. Background Technology

[0002] Electric vehicles have received considerable attention in recent years as an environmentally friendly mode of transportation. However, problems such as the difficulty of charging for electric vehicle users and the uneven distribution of charging infrastructure resources hinder their friendly development. In particular, the phenomenon of electric vehicles not charging immediately after arriving at a charging station and occupying charging piles even after the battery is fully charged is common, known as "overstaying." To address the mismatch between user charging demand and energy storage charging station resources, an intelligent scheduling method for energy storage charging stations is needed to solve these problems.

[0003] Existing charging scheduling methods for energy storage charging stations involve randomly assigning idle charging piles. This method allocates charging piles by randomly assigning idle charging piles to electric vehicles. However, the remaining power of energy storage charging piles and the power demand of electric vehicles often do not match, resulting in low charging efficiency of charging stations for electric vehicles. Summary of the Invention

[0004] Therefore, it is necessary to provide a charging scheduling method, device, computer equipment, computer-readable storage medium, and computer program product for energy storage charging stations to address the above-mentioned technical problems.

[0005] Firstly, this application provides a charging scheduling method for an energy storage charging station. The method includes:

[0006] The system obtains the charging demand information of the vehicle and the current operating data of each charging pile in the charging station, and based on the current operating data of each charging pile, selects the initial charging pile that meets the charging demand information of the vehicle.

[0007] Collect the power information of each initial charging pile and the battery information of the vehicle, and based on the power information of each initial charging pile and the battery information of the vehicle, filter the target charging pile corresponding to the vehicle through a charging pile scheduling strategy.

[0008] Collect current environmental information, and based on the current environmental information, the power information of the target charging pile, and the battery information of the vehicle, predict the charging strategy of the vehicle through a charging prediction model;

[0009] Collect the vehicle's current battery information and environmental change information to adjust the vehicle's charging strategy, obtain a new charging strategy, replace the existing charging strategy with the new charging strategy, and return to execute the step of collecting the vehicle's current battery information and environmental change information to adjust the vehicle's charging strategy and obtain a new charging strategy, until the vehicle's current battery information is at saturation.

[0010] Optionally, the step of selecting initial charging piles that meet the charging needs of the vehicle based on the current operating data of each charging pile includes:

[0011] Among the charging piles, those whose current working status is idle in the current operating data are selected as the first charging pile;

[0012] Based on the remaining power in the current operating data of each of the first charging piles and the required power in the charging demand information of the vehicle, the first charging pile with a remaining power greater than the required power is selected as the initial charging pile for the vehicle.

[0013] Optionally, the step of filtering the target charging station corresponding to the vehicle based on the power information of each initial charging station and the battery information of the vehicle, through a charging station scheduling strategy, includes:

[0014] For each initial charging station, based on the charging station's power information and the vehicle's battery information, the power correspondence between the initial charging station and the vehicle is calculated, and historical operating data of the initial charging station is collected.

[0015] Based on the fault alarm information in the historical operation data of the initial charging pile, the fault frequency level of the initial charging pile is identified, and based on the historical operation data of the initial charging pile, the health status information of the initial charging pile is identified.

[0016] The battery level correspondence, the fault frequency level, and the health status information are input into the charging pile scoring model to obtain the initial charging pile score. Among the initial charging piles, the initial charging pile with the highest score is selected as the target charging pile for the vehicle.

[0017] Optionally, the collection of current environmental information includes:

[0018] Obtain the current working status, weather information, date information, and business change information of each charging pile in the charging station;

[0019] Based on the current operating status of each charging pile, the operating segment characteristics of the charging station are identified, and the weather characteristics corresponding to the weather information and the date characteristics corresponding to the date information are queried in the cloud interconnected database.

[0020] Based on the information on changes in businesses around the charging station, the electricity price level characteristics of the charging station are identified, and the operating time characteristics, weather characteristics, date characteristics, and electricity price level characteristics of the charging station are used as current environmental information.

[0021] Optionally, the step of predicting the vehicle's charging strategy based on the current environmental information, the target charging pile's power information, and the vehicle's battery information using a charging prediction model includes:

[0022] Based on the operating time characteristics of the charging station, the weather characteristics, the date characteristics, and the electricity price level characteristics, the electricity price change trend information of the charging station is predicted through a charging prediction model.

[0023] Based on the vehicle's battery information, the vehicle's charging urgency and predicted charging time are identified, and based on the vehicle's charging urgency, the charging time limit range of the vehicle is determined.

[0024] Based on the electricity price change trend information, the charging time limit range of the vehicle, and the predicted charging time of the vehicle, the target charging time periods of the vehicle are selected, and the target charging time periods of the vehicle are used as the charging strategy of the vehicle.

[0025] Optionally, the step of collecting the vehicle's current battery information and environmental change information to adjust the vehicle's charging strategy and obtain a new charging strategy includes:

[0026] Based on the environmental change information, the charging prediction model is used to re-predict the new electricity price change trend information of the charging station, and based on the current battery information of the vehicle, the new predicted charging time of the vehicle is identified.

[0027] Based on the new electricity price change trend information and the new predicted charging time, the new target charging time periods for the vehicle are re-selected to obtain the new charging strategy for the vehicle.

[0028] Optionally, when all charging piles are currently in charging mode, before collecting the current environmental information, the process further includes:

[0029] The current charging strategy of each vehicle charged by each charging pile is obtained, and based on the current charging strategy of each vehicle, the predicted remaining power of each charging pile and the predicted end time of each charging pile are identified.

[0030] Based on the power demand information in the vehicle's charging demand information, among the charging piles, the first charging pile corresponding to the predicted remaining power that is greater than the vehicle's power demand information is selected, and among the first charging piles, the first charging pile corresponding to the earliest predicted end time is selected as the target charging pile for the vehicle.

[0031] Secondly, this application also provides a charging scheduling device for an energy storage charging station. The device includes:

[0032] The acquisition module is used to acquire the charging demand information of the vehicle and the current operating data of each charging pile in the charging station, and based on the current operating data of each charging pile, to select an initial charging pile that meets the charging demand information of the vehicle.

[0033] The filtering module is used to collect the power information of each initial charging pile and the battery information of the vehicle, and based on the power information of each initial charging pile and the battery information of the vehicle, filter the target charging pile corresponding to the vehicle through a charging pile scheduling strategy.

[0034] The prediction module is used to collect current environmental information and, based on the current environmental information, the power information of the target charging pile, and the battery information of the vehicle, predict the charging strategy of the vehicle through a charging prediction model.

[0035] The adjustment module is used to collect the vehicle's current battery information and environmental change information to adjust the vehicle's charging strategy, obtain a new charging strategy, replace the existing charging strategy with the new charging strategy, and return to execute the step of collecting the vehicle's current battery information and environmental change information to adjust the vehicle's charging strategy and obtain a new charging strategy, until the vehicle's current battery information is at saturation.

[0036] Optionally, the acquisition module is specifically used for:

[0037] Among the charging piles, those whose current working state is idle in the current operating data are selected as the first charging pile;

[0038] Based on the remaining power in the current operating data of each of the first charging piles and the required power in the charging demand information of the vehicle, the first charging pile with a remaining power greater than the required power is selected as the initial charging pile for the vehicle.

[0039] Optionally, the filtering module is specifically used for:

[0040] For each initial charging station, based on the charging station's power information and the vehicle's battery information, the power correspondence between the initial charging station and the vehicle is calculated, and historical operating data of the initial charging station is collected.

[0041] Based on the fault alarm information in the historical operation data of the initial charging pile, the fault frequency level of the initial charging pile is identified, and based on the historical operation data of the initial charging pile, the health status information of the initial charging pile is identified.

[0042] The battery level correspondence, the fault frequency level, and the health status information are input into the charging pile scoring model to obtain the initial charging pile score. Among the initial charging piles, the initial charging pile with the highest score is selected as the target charging pile for the vehicle.

[0043] Optionally, the prediction module is specifically used for:

[0044] Obtain the current working status, weather information, date information, and business change information of each charging pile in the charging station;

[0045] Based on the current operating status of each charging pile, the operating segment characteristics of the charging station are identified, and the weather characteristics corresponding to the weather information and the date characteristics corresponding to the date information are queried in the cloud interconnected database.

[0046] Based on the information on changes in businesses around the charging station, the electricity price level characteristics of the charging station are identified, and the operating time characteristics, weather characteristics, date characteristics, and electricity price level characteristics of the charging station are used as current environmental information.

[0047] Optionally, the prediction module is specifically used for:

[0048] Based on the operating time characteristics of the charging station, the weather characteristics, the date characteristics, and the electricity price level characteristics, the electricity price change trend information of the charging station is predicted through a charging prediction model.

[0049] Based on the vehicle's battery information, the vehicle's charging urgency and predicted charging time are identified, and based on the vehicle's charging urgency, the charging time limit range of the vehicle is determined.

[0050] Based on the electricity price change trend information, the charging time limit range of the vehicle, and the predicted charging time of the vehicle, the target charging time periods of the vehicle are selected, and the target charging time periods of the vehicle are used as the charging strategy of the vehicle.

[0051] Optionally, the adjustment module is specifically used for:

[0052] Based on the environmental change information, the charging prediction model is used to re-predict the new electricity price change trend information of the charging station, and based on the current battery information of the vehicle, the new predicted charging time of the vehicle is identified.

[0053] Based on the new electricity price change trend information and the new predicted charging time, the new target charging time periods for the vehicle are re-selected to obtain the new charging strategy for the vehicle.

[0054] Optionally, the device further includes:

[0055] The identification module is used to obtain the current charging strategy of the vehicles charged by each of the charging piles, and based on the current charging strategy of each vehicle, to identify the predicted remaining power of each of the charging piles and the predicted end time of each of the charging piles.

[0056] The determination module is used to, based on the power demand information in the charging demand information of the vehicle, select the first charging pile corresponding to the predicted remaining power that is greater than the power demand information of the vehicle among the charging piles, and select the first charging pile corresponding to the earliest predicted end time point among the first charging piles as the target charging pile of the vehicle.

[0057] Thirdly, this application provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method described in any one of the first aspects.

[0058] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0059] Fifthly, this application provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0060] The aforementioned energy storage charging station charging scheduling method, apparatus, computer equipment, and storage medium acquire vehicle charging demand information and current operating data of each charging pile in the charging station. Based on the current operating data of each charging pile, they select initial charging piles that meet the vehicle's charging demand information. They collect the power information of each initial charging pile and the vehicle's battery information, and based on this information, select target charging piles corresponding to the vehicle using a charging pile scheduling strategy. They collect current environmental information and, based on this information, the power information of the target charging pile, and the vehicle's battery information, predict the vehicle's charging strategy using a charging prediction model. They collect the vehicle's current battery information and environmental change information to adjust the vehicle's charging strategy, obtaining a new charging strategy. This new strategy replaces the previous charging strategy, and the process returns to the previous steps of collecting the vehicle's current battery information and environmental change information to adjust the vehicle's charging strategy and obtain a new charging strategy, until the vehicle's current battery information reaches saturation. This solution selects suitable initial charging stations by comprehensively considering the vehicle's charging needs and the current operating data of the charging piles. Then, by combining the initial charging pile's power information and the vehicle's battery information, it selects the optimal charging station for the vehicle, improving the accuracy of charging station allocation during vehicle charging. This avoids problems such as low charging pile resource utilization leading to a mismatch between charging demand and supply, and "overdue waiting." Furthermore, by comprehensively considering environmental information and using a charging prediction model, it predicts the vehicle's charging strategy and adjusts this strategy based on real-time environmental change information and the vehicle's current battery information to complete vehicle charging. This improves resource optimization during vehicle charging, avoids high charging resource costs, and increases the fault tolerance of the charging strategy by adjusting the charging strategy in real time, ensuring that the utilization rate of vehicle charging resources remains optimal at all times. Therefore, it comprehensively improves the charging efficiency of charging stations for electric vehicles. Attached Figure Description

[0061] Figure 1 This is a flowchart illustrating a charging scheduling method for an energy storage charging station in one embodiment.

[0062] Figure 2 This is a flowchart illustrating a charging scheduling example for an energy storage charging station in one embodiment.

[0063] Figure 3 This is a structural block diagram of a charging scheduling device for an energy storage charging station in one embodiment;

[0064] Figure 4 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0065] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0066] The charging scheduling method for energy storage charging stations provided in this application can be applied to intelligent scheduling environments for energy storage charging stations. This method can be applied to terminals, servers, or systems including both terminals and servers, and is implemented through interaction between the terminals and servers. The terminals can be, but are not limited to, various personal computers, laptops, smartphones, tablets, etc. The terminal selects the initial charging pile suitable for the vehicle by comprehensively considering the vehicle's charging needs and the current operating data of the charging pile. Then, by combining the initial charging pile's power information and the vehicle's battery information, it selects the optimal charging pile suitable for the vehicle. This improves the accuracy of charging station allocation during vehicle charging, avoiding problems such as mismatch between charging demand and supply and "overdue stays" caused by low utilization of charging pile resources. Then, by comprehensively considering environmental information and using a charging prediction model, it predicts the vehicle's charging strategy and adjusts the charging strategy based on real-time collected environmental change information and the vehicle's current battery information to complete vehicle charging. This improves the resource optimization effect during vehicle charging, avoids the problem of high vehicle charging resource costs, and improves the fault tolerance rate of the charging strategy during vehicle charging by adjusting the vehicle charging strategy in real time, ensuring that the utilization rate of vehicle charging resources is always at its optimal level, thereby comprehensively improving the charging efficiency of charging stations for electric vehicles.

[0067] In one embodiment, such as Figure 1 As shown, a charging scheduling method for energy storage charging stations is provided. Taking the application of this method to a terminal as an example, the method includes the following steps:

[0068] Step S101: Obtain the vehicle's charging demand information and the current operating data of each charging pile in the charging station, and based on the current operating data of each charging pile, select the initial charging pile that meets the vehicle's charging demand information from among the charging piles.

[0069] In this embodiment, the terminal collects the charging demand information of each vehicle, input by the driver, through an information collection device installed at the entrance of the charging station. This charging demand information includes the vehicle's current battery level, vehicle model, charging urgency level, and battery status information (actual full-load capacity). Then, the terminal obtains the current operating data of each charging pile through detection devices installed at each energy storage charging pile. This current operating data includes the charging pile's operating status and remaining battery power. The energy storage charging piles are those that fully charge during off-peak hours at night and then charge the vehicle during peak hours during the day using the stored energy. During off-peak hours at night, the charging piles directly charge the vehicle from the power grid. Based on the current operating data of each charging pile, the terminal selects initial charging piles that meet the vehicle's charging demand. These initial charging piles are those with remaining battery power greater than the vehicle's required battery power and currently in an idle state. The specific selection process will be explained in detail later.

[0070] Step S102: Collect the power information of each initial charging pile and the battery information of the vehicle, and based on the power information of each initial charging pile and the battery information of the vehicle, select the target charging pile corresponding to the vehicle through the charging pile scheduling strategy.

[0071] In this embodiment, the terminal collects the power information of each initial charging pile and the vehicle's battery information. Based on this power information, and using a charging pile scheduling strategy, it selects the target charging pile corresponding to the vehicle. The power information includes the remaining power of the initial charging pile, the health status of its energy storage cabinet, and the frequency of fault alarms. The specific selection process will be explained in detail later.

[0072] Step S103: Collect current environmental information, and based on the current environmental information, the power information of the target charging pile, and the vehicle's battery information, predict the vehicle's charging strategy through a charging prediction model.

[0073] In this embodiment, the terminal collects current environmental information and, based on this information, the target charging pile's power information, and the vehicle's battery information, predicts the vehicle's charging strategy using a charging prediction model. The current environmental information includes the charging station's operating time characteristics, weather characteristics, date characteristics, and electricity price level characteristics. Operating time characteristics include off-peak hours, peak hours, and sluggish hours. Weather characteristics include sunny days, rainy days, snowy days, hail days, and typhoon days. Specifically, charging prices are higher on sunny days, moderate on rainy or snowy days, and lower on hail or typhoon days. Date characteristics include weekdays, weekends, and holidays. Electricity price level characteristics include weekday prices, off-peak prices, peak prices, and sluggish prices. The charging strategy refers to the vehicle's charging time periods. The specific prediction process will be explained in detail later.

[0074] Step S104: Collect the vehicle's current battery information and environmental change information to adjust the vehicle's charging strategy, obtain a new charging strategy, replace the old charging strategy with the new charging strategy, and return to execute the steps of collecting the vehicle's current battery information and environmental change information to adjust the vehicle's charging strategy and obtain a new charging strategy until the vehicle's current battery information is at full charge.

[0075] In this embodiment, the terminal collects the vehicle's current battery information and environmental change information to adjust the vehicle's charging strategy, obtains a new charging strategy, replaces the existing charging strategy with the new one, and returns to execute the steps of collecting the vehicle's current battery information and environmental change information to adjust the vehicle's charging strategy and obtain the new charging strategy, until the vehicle's current battery information indicates that the battery is at full charge. The specific adjustment process will be described in detail later.

[0076] Based on the above scheme, the initial charging piles suitable for the vehicle are selected by comprehensively considering the vehicle's charging needs and the current operating data of the charging piles. Then, by combining the power information of the initial charging piles and the vehicle's battery information, the optimal charging pile suitable for the vehicle is selected. This improves the accuracy of charging station allocation during vehicle charging, avoiding the problems of mismatch between charging demand and supply and "overdue stay" caused by low utilization of charging pile resources. Then, by comprehensively considering environmental information and using a charging prediction model, the charging strategy of the vehicle is predicted. Based on real-time collected environmental change information and the vehicle's current battery information, the charging strategy is adjusted to complete the vehicle charging, improving the resource optimization effect during vehicle charging and avoiding the problem of high vehicle charging resource costs. At the same time, by adjusting the vehicle charging strategy in real time, the fault tolerance rate of the charging strategy during vehicle charging is improved, ensuring that the utilization rate of vehicle charging resources is always at its optimal level, thereby comprehensively improving the charging efficiency of charging stations for electric vehicles.

[0077] Optionally, based on the current operating data of each charging pile, the initial charging pile that meets the charging needs of the vehicle is selected from among the charging piles, including: selecting the charging piles whose current working state is idle in the current operating data as the first charging piles; and selecting the first charging piles with remaining power greater than the required power in the current operating data of each first charging pile as the initial charging piles of the vehicle, based on the remaining power in the current operating data of each first charging pile and the required power in the charging needs of the vehicle.

[0078] In this embodiment, the terminal selects charging piles whose current operating status is idle from the current operating data, and designates them as the first charging piles. Then, based on the remaining battery power in the current operating data of each first charging pile and the required battery power in the vehicle's charging demand information, the terminal selects the first charging pile with a remaining battery power greater than the required battery power, and designates it as the vehicle's initial charging pile. The required battery power for the vehicle is the difference between the vehicle's current remaining battery power and its full charge power under the vehicle's current battery state.

[0079] Based on the above scheme, by selecting available charging stations with remaining power greater than the required power, the situation where vehicles cannot be fully charged is avoided, thus improving the rationality of charging station allocation.

[0080] Optionally, based on the power information of each initial charging pile and the vehicle's battery information, a target charging pile corresponding to the vehicle is selected through a charging pile scheduling strategy. This includes: for each initial charging pile, calculating the power correspondence between the initial charging pile and the vehicle based on the power information of the initial charging pile and the vehicle's battery information, and collecting historical operating data of the initial charging pile; identifying the fault frequency level of the initial charging pile based on the fault alarm information in the historical operating data of the initial charging pile, and identifying the health status information of the initial charging pile based on the historical operating data of the initial charging pile; inputting the power correspondence, fault frequency level, and health status information into the charging pile scoring model to obtain the score value of the initial charging pile, and selecting the initial charging pile with the highest score value from among the initial charging piles as the target charging pile corresponding to the vehicle.

[0081] In this embodiment, for each initial charging station, the terminal calculates the correspondence between the initial charging station's battery level and the vehicle's battery level based on the initial charging station's battery information and the vehicle's battery information, and collects historical operating data of the initial charging station. The correspondence between the vehicle's battery information and the charging station's battery level information includes, but is not limited to, the following:

[0082] The remaining power in the energy storage cabinet exceeds the power demand of new energy vehicles by 5% — A1

[0083] The remaining power in the energy storage cabinet exceeds the power demand of new energy vehicles by 10% — A2

[0084] The remaining power in the energy storage cabinet exceeds the power demand of new energy vehicles by 20% — A3

[0085] The remaining power in the energy storage cabinet exceeds the power demand of new energy vehicles by 30% — A4

[0086] The remaining power in the energy storage cabinet exceeds 50% of the power demand of new energy vehicles. —A5

[0087] The electricity demand of new energy vehicles exceeds the remaining capacity of energy storage cabinets by 5% — A6

[0088] The electricity demand of new energy vehicles exceeds the remaining capacity of energy storage cabinets by 10% — A7

[0089] The electricity demand of new energy vehicles exceeds the remaining capacity of energy storage cabinets by 20% — A8

[0090] The electricity demand of new energy vehicles exceeds the remaining capacity of energy storage cabinets by 40% — A9

[0091] Then, based on the fault alarm information in the historical operation data of the initial charging pile, the terminal identifies the fault frequency level of the initial charging pile, and based on the historical operation data of the initial charging pile, identifies the health status information of the initial charging pile.

[0092] Specifically, the health status information of charging piles is represented by the state of health (SOH) of the energy storage cabinet. Each energy storage cabinet's SOH corresponds to a coded information, for example:

[0093] The coding relationship of the SOH (Sort of Energy) cabinet:

[0094] SOH100——B100

[0095] SOH99 ——B99

[0096] SOH98 ——B98

[0097] Secondly, the relationship between fault frequency level and fault alarm frequency is as follows:

[0098] The monthly fault alarm frequency is 0 C0

[0099] Monthly fault alarm frequency is 1-5 C1

[0100] The monthly fault alarm frequency is 6-10 C2

[0101] The monthly fault alarm frequency is 11-15 C3

[0102] The monthly fault alarm frequency is 16-20 C4

[0103] C5 with a monthly fault alarm frequency of 20 or more

[0104] Finally, the terminal inputs the battery level correspondence, fault frequency level, and health status information into the charging pile scoring model to obtain the initial charging pile score. From these initial charging piles, the one with the highest score is selected as the target charging pile for the vehicle. This charging pile scoring model is the XGBOOST (eXtreme GradientBoosting) model.

[0105] Specifically, the terminal uses the overall economic benefit of the charging station as the objective function. The remaining capacity of the energy storage cabinets and the power demand of new energy vehicles are directly related to economic benefits; prioritizing the use of the energy storage cabinets will improve economic efficiency. The State of Charge (SOH) of the energy storage cabinets is also directly related to the economic benefits of the charging station; high SOH energy storage cabinets have higher charging and discharging efficiency, so prioritizing the use of high SOH energy storage cabinets improves the economic benefits of the station and also improves the overall SOH balance of the charging station's energy storage cabinets, thus enhancing system safety. The frequency of fault alarms is indirectly related to economic benefits; the monthly frequency of fault alarms affects the owner's experience, reduces charging demand, and also affects charging and discharging efficiency.

[0106] Then, the terminal takes all the historical data of the entire charging station over the past two months, filters out the relationship between the remaining power of the energy storage cabinet and the power demand of new energy vehicles, the SOH of the energy storage cabinet, the frequency of fault alarms, and the total economic benefits of the charging station on that day, and inputs them into the XGBOOST model to obtain the importance score KA1, KA2, KA3... for each event. The final charging pile score K is equal to the sum of the importance scores of each event of the charging pile, for example, K=KA1+KB99+KC0.

[0107] The terminal will recommend the charging station with the highest score to the user for charging.

[0108] Based on the above scheme, by combining the historical information of the charging piles and the correspondence between the power information, the target charging piles of users can be screened, thereby improving the accuracy of the target charging pile screening.

[0109] Optionally, current environmental information is collected, including: obtaining the current operating status of each charging pile in the charging station, weather information, date information, and information on changes in businesses around the charging station; based on the current operating status of each charging pile, identifying the operating period characteristics of the charging station, and querying the weather characteristics corresponding to the weather information and the date characteristics corresponding to the date information in the cloud-connected database; based on the information on changes in businesses around the charging station, identifying the electricity price level characteristics of the charging station, and using the operating period characteristics, weather characteristics, date characteristics, and electricity price level characteristics of the charging station as current environmental information.

[0110] In this embodiment, the terminal acquires the current operating status of each charging pile in the charging station, weather information, date information, and information on changes in businesses around the charging station. Then, based on the current operating status of each charging pile, the terminal identifies the operating characteristics of the charging station and queries the cloud-connected database for the weather characteristics corresponding to the weather information and the date characteristics corresponding to the date information. The cloud-connected database is a real-time updated database of each terminal, including but not limited to meteorological bureau terminals, online time terminals, and terminals of the park where the charging station is located. Finally, based on the information on changes in businesses around the charging station, the terminal identifies the electricity price level characteristics of the charging station and uses the operating characteristics, weather characteristics, date characteristics, and electricity price level characteristics of the charging station as the current environmental information.

[0111] Based on the above scheme, by identifying the multi-factor and multi-angle environmental characteristics of charging stations, the practicality and accuracy of predicting vehicle charging strategies are improved.

[0112] Optionally, based on current environmental information, the power information of the target charging pile, and the vehicle's battery information, a charging prediction model is used to predict the vehicle's charging strategy. This includes: predicting the charging station's electricity price change trend based on the charging station's operating time characteristics, weather characteristics, date characteristics, and electricity price level characteristics; identifying the vehicle's charging urgency and predicted charging duration based on the vehicle's battery information, and determining the vehicle's charging time limit range based on the vehicle's charging urgency; and filtering the vehicle's target charging time periods based on the electricity price change trend information, the vehicle's charging time limit range, and the vehicle's predicted charging duration, and using each target charging time period as the vehicle's charging strategy.

[0113] In this embodiment, the terminal predicts the electricity price change trend of the charging station based on the station's operating time characteristics, weather characteristics, date characteristics, and electricity price level characteristics using a charging prediction model. The charging prediction model is the XGBOOST (eXtreme Gradient Boosting) model. The terminal inputs the operating time characteristics, weather characteristics, date characteristics, and electricity price level characteristics into the XGBOOST model to predict the current charging station's normal electricity price, peak electricity price, and off-peak electricity price. Then, the terminal distributes the normal electricity price, peak electricity price, and off-peak electricity price according to the different time periods corresponding to each price, thus obtaining the charging station's electricity price change trend information.

[0114] Then, based on the vehicle's battery information, the terminal identifies the vehicle's charging urgency and predicted charging time, and determines the vehicle's charging time limit range based on the charging urgency. Here, the charging urgency is the vehicle's allowed charging waiting time, and the allowed charging usage time is the duration information input by the user into the terminal. The terminal determines the charging urgency corresponding to the duration range to which this waiting time belongs.

[0115] Then, based on electricity price change trend information, vehicle charging time range, and vehicle predicted charging time, the terminal filters the target charging time periods for the vehicle and uses each target charging time period as the vehicle's charging strategy.

[0116] Based on the above scheme, by predicting the trend of electricity price changes, the charging time of vehicles can be determined, thereby improving the resource utilization rate during vehicle charging and reducing charging costs.

[0117] Optionally, the vehicle's current battery information and environmental change information are collected to adjust the vehicle's charging strategy and obtain a new charging strategy, including: based on environmental change information, using a charging prediction model to re-predict the new electricity price change trend information of the charging station, and based on the vehicle's current battery information, identifying the vehicle's new predicted charging duration; and based on the new electricity price change trend information and the new predicted charging duration, re-selecting each new target charging period of the vehicle to obtain the vehicle's new charging strategy.

[0118] In this embodiment, the terminal, based on environmental change information, uses a charging prediction model to re-predict the new electricity price change trend of the charging station, and identifies the new predicted charging duration of the vehicle based on the vehicle's current battery information. Then, based on the new electricity price change trend and the new predicted charging duration, the terminal re-selects the new target charging periods for the vehicle to obtain a new charging strategy for the vehicle.

[0119] Based on the above scheme, by adjusting the charging periods of each new target through environmental change information, the intelligent adjustment of vehicle charging strategy is improved, avoiding the problem of charging strategy not conforming to the actual situation, improving the intelligent charging effect, and minimizing vehicle charging costs.

[0120] Optionally, when all charging piles are currently in charging mode, before collecting the current environmental information, the method further includes: obtaining the current charging strategy of the vehicle being charged by each charging pile, and based on the current charging strategy of each vehicle, identifying the predicted remaining power of each charging pile and the predicted end time of each charging pile; based on the power demand information in the vehicle's charging demand information, selecting the first charging pile with a predicted remaining power greater than the vehicle's power demand information, and selecting the first charging pile with the earliest predicted end time as the target charging pile for the vehicle.

[0121] In this embodiment, the terminal obtains the current charging strategy of the vehicles being charged at each charging pile, and based on the current charging strategy of each vehicle, identifies the predicted remaining battery power and the predicted end time of each charging pile. Then, based on the battery demand information in the vehicle's charging demand information, the terminal selects the first charging pile with a predicted remaining battery power greater than the vehicle's battery demand information, and then selects the first charging pile with the earliest predicted end time as the vehicle's target charging pile.

[0122] Based on the above scheme, when there are no available charging piles, the target charging pile for each vehicle is allocated in real time according to the status of each charging pile, avoiding the situation of charging piles being idle and vehicles queuing, thus improving the charging efficiency of waiting vehicles and the charging pile allocation efficiency of waiting vehicles.

[0123] This application also provides an example of charging scheduling for energy storage charging stations, such as... Figure 2 As shown, the specific processing procedure includes the following steps:

[0124] Step S201: Obtain the vehicle's charging demand information and the current operating data of each charging pile in the charging station.

[0125] Step S202: Among all charging piles, select the charging piles whose current working state is idle from the current operating data and designate them as the first charging piles.

[0126] Step S203: Based on the remaining power in the current operating data of each first charging pile and the required power in the vehicle's charging demand information, select the first charging pile with remaining power greater than the required power as the vehicle's initial charging pile.

[0127] Step S204: Collect the power information of each initial charging station and the battery information of the vehicle.

[0128] Step S205: For each initial charging pile, calculate the correspondence between the initial charging pile and the vehicle's battery capacity based on the initial charging pile's power information and the vehicle's battery information, and collect the historical operating data of the initial charging pile.

[0129] Step S206: Based on the fault alarm information in the historical operation data of the initial charging pile, identify the fault frequency level of the initial charging pile, and based on the historical operation data of the initial charging pile, identify the health status information of the initial charging pile.

[0130] Step S207: Input the power correspondence, fault frequency level, and health status information into the charging pile scoring model to obtain the initial charging pile score. Then, select the initial charging pile with the highest score from each initial charging pile as the target charging pile for the vehicle.

[0131] Step S208: Obtain the current working status of each charging pile in the charging station, weather information, date information, and information on changes in enterprises around the charging station.

[0132] Step S209: Based on the current working status of each charging pile, identify the operating segment characteristics of the charging station, and query the weather characteristics corresponding to the weather information and the date characteristics corresponding to the date information in the cloud interconnected database.

[0133] Step S210: Based on the information on changes in enterprises around the charging station, identify the electricity price level characteristics of the charging station, and use the charging station's operating time characteristics, weather characteristics, date characteristics, and electricity price level characteristics as current environmental information.

[0134] Step S211: Based on the charging station's operating time characteristics, weather characteristics, date characteristics, and electricity price level characteristics, the charging prediction model is used to predict the electricity price change trend information of the charging station.

[0135] Step S212: Based on the vehicle's battery information, identify the vehicle's charging urgency and the vehicle's predicted charging time, and determine the vehicle's charging time limit range based on the vehicle's charging urgency.

[0136] Step S213: Based on the electricity price change trend information, the vehicle's charging time limit range, and the vehicle's predicted charging time, filter the vehicle's target charging time periods and use each target charging time period as the vehicle's charging strategy.

[0137] Step S214: Based on environmental change information, the charging prediction model is used to re-predict the new electricity price change trend information of the charging station, and based on the vehicle's current battery information, the new predicted charging time of the vehicle is identified.

[0138] Step S215: Based on the new electricity price change trend information and the new predicted charging time, re-select the new target charging time periods for the vehicle to obtain the new charging strategy for the vehicle.

[0139] Step S216: Replace the charging strategy with the new charging strategy, and return to collect the vehicle's current battery information and environmental change information to adjust the vehicle's charging strategy and obtain the new charging strategy, until the vehicle's current battery information is at saturation.

[0140] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0141] Based on the same inventive concept, this application also provides an energy storage charging station charging scheduling device for implementing the above-mentioned energy storage charging station charging scheduling method. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more energy storage charging station charging scheduling device embodiments provided below can be found in the limitations of the energy storage charging station charging scheduling method above, and will not be repeated here.

[0142] In one embodiment, such as Figure 3 As shown, a charging scheduling device for an energy storage charging station is provided, comprising: an acquisition module 310, a screening module 320, a prediction module 330, and an adjustment module 340, wherein:

[0143] The acquisition module 310 is used to acquire the charging demand information of the vehicle and the current operating data of each charging pile of the charging station, and based on the current operating data of each charging pile, to select an initial charging pile that meets the charging demand information of the vehicle.

[0144] The filtering module 320 is used to collect the power information of each of the initial charging piles and the battery information of the vehicle, and based on the power information of each of the initial charging piles and the battery information of the vehicle, filter the target charging pile corresponding to the vehicle through a charging pile scheduling strategy.

[0145] The prediction module 330 is used to collect current environmental information and, based on the current environmental information, the power information of the target charging pile, and the battery information of the vehicle, predict the charging strategy of the vehicle through a charging prediction model.

[0146] The adjustment module 340 is used to collect the current battery information and environmental change information of the vehicle to adjust the charging strategy of the vehicle, obtain a new charging strategy, replace the charging strategy with the new charging strategy, and return to execute the step of collecting the current battery information and environmental change information of the vehicle to adjust the charging strategy of the vehicle and obtain a new charging strategy, until the current battery information of the vehicle is saturated.

[0147] Optionally, the acquisition module 310 is specifically used for:

[0148] Among the charging piles, those whose current working state is idle in the current operating data are selected as the first charging pile;

[0149] Based on the remaining power in the current operating data of each of the first charging piles and the required power in the charging demand information of the vehicle, the first charging pile with a remaining power greater than the required power is selected as the initial charging pile for the vehicle.

[0150] Optionally, the filtering module 320 is specifically used for:

[0151] For each initial charging station, based on the charging station's power information and the vehicle's battery information, the power correspondence between the initial charging station and the vehicle is calculated, and historical operating data of the initial charging station is collected.

[0152] Based on the fault alarm information in the historical operation data of the initial charging pile, the fault frequency level of the initial charging pile is identified, and based on the historical operation data of the initial charging pile, the health status information of the initial charging pile is identified.

[0153] The battery level correspondence, the fault frequency level, and the health status information are input into the charging pile scoring model to obtain the initial charging pile score. Among the initial charging piles, the initial charging pile with the highest score is selected as the target charging pile for the vehicle.

[0154] Optionally, the prediction module 330 is specifically used for:

[0155] Obtain the current working status, weather information, date information, and business change information of each charging pile in the charging station;

[0156] Based on the current operating status of each charging pile, the operating segment characteristics of the charging station are identified, and the weather characteristics corresponding to the weather information and the date characteristics corresponding to the date information are queried in the cloud interconnected database.

[0157] Based on the information on changes in businesses around the charging station, the electricity price level characteristics of the charging station are identified, and the operating time characteristics, weather characteristics, date characteristics, and electricity price level characteristics of the charging station are used as current environmental information.

[0158] Optionally, the prediction module 330 is specifically used for:

[0159] Based on the operating time characteristics of the charging station, the weather characteristics, the date characteristics, and the electricity price level characteristics, the electricity price change trend information of the charging station is predicted through a charging prediction model.

[0160] Based on the vehicle's battery information, the vehicle's charging urgency and predicted charging time are identified, and based on the vehicle's charging urgency, the charging time limit range of the vehicle is determined.

[0161] Based on the electricity price change trend information, the charging time limit range of the vehicle, and the predicted charging time of the vehicle, the target charging time periods of the vehicle are selected, and the target charging time periods of the vehicle are used as the charging strategy of the vehicle.

[0162] Optionally, the adjustment module 340 is specifically used for:

[0163] Based on the environmental change information, the charging prediction model is used to re-predict the new electricity price change trend information of the charging station, and based on the current battery information of the vehicle, the new predicted charging time of the vehicle is identified.

[0164] Based on the new electricity price change trend information and the new predicted charging time, the new target charging time periods for the vehicle are re-selected to obtain the new charging strategy for the vehicle.

[0165] Optionally, the device further includes:

[0166] The identification module is used to obtain the current charging strategy of the vehicles charged by each of the charging piles, and based on the current charging strategy of each vehicle, to identify the predicted remaining power of each of the charging piles and the predicted end time of each of the charging piles.

[0167] The determination module is used to, based on the power demand information in the charging demand information of the vehicle, select the first charging pile corresponding to the predicted remaining power that is greater than the power demand information of the vehicle among the charging piles, and select the first charging pile corresponding to the earliest predicted end time point among the first charging piles as the target charging pile of the vehicle.

[0168] Each module in the aforementioned energy storage charging station charging dispatching device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0169] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 4 As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a charging scheduling method for an energy storage charging station. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0170] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0171] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described in any one of the first aspects.

[0172] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0173] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0174] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0175] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0176] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0177] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A charging scheduling method for an energy storage charging station, characterized in that, The method includes: The system obtains the charging demand information of the vehicle and the current operating data of each charging pile in the charging station, and based on the current operating data of each charging pile, selects the initial charging pile that meets the charging demand information of the vehicle. Collect the power information of each of the initial charging piles and the battery information of the vehicle; For each initial charging station, based on the charging station's power information and the vehicle's battery information, the power correspondence between the initial charging station and the vehicle is calculated, and historical operating data of the initial charging station is collected. Based on the fault alarm information in the historical operation data of the initial charging pile, the fault frequency level of the initial charging pile is identified, and based on the historical operation data of the initial charging pile, the health status information of the initial charging pile is identified. The power correspondence, the fault frequency level, and the health status information are input into the charging pile scoring model to obtain the initial charging pile score. Among the initial charging piles, the initial charging pile with the highest score is selected as the target charging pile for the vehicle. Collect current environmental information; Based on the charging station's operating time characteristics, weather characteristics, date characteristics, and electricity price level characteristics, a charging prediction model is used to predict the electricity price change trend information of the charging station. Based on the vehicle's battery information, the vehicle's charging urgency and predicted charging time are identified, and based on the vehicle's charging urgency, the charging time limit range of the vehicle is determined. Based on the electricity price change trend information, the charging time limit range of the vehicle, and the predicted charging time of the vehicle, the target charging time periods of the vehicle are selected, and the target charging time periods of the vehicle are used as the charging strategy of the vehicle. Collect the vehicle's current battery information and environmental change information to adjust the vehicle's charging strategy, obtain a new charging strategy, replace the existing charging strategy with the new charging strategy, and return to execute the step of collecting the vehicle's current battery information and environmental change information to adjust the vehicle's charging strategy and obtain a new charging strategy, until the vehicle's current battery information is at saturation.

2. The method according to claim 1, characterized in that, The step of selecting an initial charging station that meets the vehicle's charging needs based on the current operating data of each charging station includes: Among the charging piles, those whose current working status is idle in the current operating data are selected as the first charging pile; Based on the remaining power in the current operating data of each of the first charging piles and the required power in the charging demand information of the vehicle, the first charging pile with a remaining power greater than the required power is selected as the initial charging pile for the vehicle.

3. The method according to claim 1, characterized in that, The collection of current environmental information includes: Obtain the current working status, weather information, date information, and business change information of each charging pile in the charging station; Based on the current operating status of each charging pile, the operating segment characteristics of the charging station are identified, and the weather characteristics corresponding to the weather information and the date characteristics corresponding to the date information are queried in the cloud interconnected database. Based on the information on changes in businesses around the charging station, the electricity price level characteristics of the charging station are identified, and the operating time characteristics, weather characteristics, date characteristics, and electricity price level characteristics of the charging station are used as current environmental information.

4. The method according to claim 1, characterized in that, The process of collecting the vehicle's current battery information and environmental change information to adjust the vehicle's charging strategy and obtain a new charging strategy includes: Based on the environmental change information, the charging prediction model is used to re-predict the new electricity price change trend information of the charging station, and based on the current battery information of the vehicle, the new predicted charging time of the vehicle is identified. Based on the new electricity price change trend information and the new predicted charging time, the new target charging time periods for the vehicle are re-selected to obtain the new charging strategy for the vehicle.

5. The method according to claim 2, characterized in that, When all charging stations are currently in charging mode, before collecting the current environmental information, the process also includes: The current charging strategy of each vehicle charged by each charging pile is obtained, and based on the current charging strategy of each vehicle, the predicted remaining power of each charging pile and the predicted end time of each charging pile are identified. Based on the power demand information in the vehicle's charging demand information, among the charging piles, the first charging pile corresponding to the predicted remaining power that is greater than the vehicle's power demand information is selected, and among the first charging piles, the first charging pile corresponding to the earliest predicted end time is selected as the target charging pile for the vehicle.

6. A charging dispatching device for an energy storage charging station, characterized in that, The device includes: The acquisition module is used to acquire the charging demand information of the vehicle and the current operating data of each charging pile in the charging station, and based on the current operating data of each charging pile, to select an initial charging pile that meets the charging demand information of the vehicle. A filtering module is used to collect the power information of each initial charging pile and the battery information of the vehicle; for each initial charging pile, based on the power information of the initial charging pile and the battery information of the vehicle, calculate the power correspondence between the initial charging pile and the vehicle, and collect the historical operating data of the initial charging pile; based on the fault alarm information in the historical operating data of the initial charging pile, identify the fault frequency level of the initial charging pile, and based on the historical operating data of the initial charging pile, identify the health status information of the initial charging pile; input the power correspondence, the fault frequency level, and the health status information into the charging pile scoring model to obtain the score value of the initial charging pile, and filter out the initial charging pile with the highest score value from among the initial charging piles as the target charging pile corresponding to the vehicle; The prediction module is used to collect current environmental information; based on the charging station's operating time characteristics, weather characteristics, date characteristics, and electricity price level characteristics, it predicts the electricity price change trend of the charging station using a charging prediction model; based on the vehicle's battery information, it identifies the vehicle's charging urgency and predicted charging duration, and determines the vehicle's charging time limit range based on the vehicle's charging urgency; based on the electricity price change trend information, the vehicle's charging time limit range, and the vehicle's predicted charging duration, it filters each target charging period of the vehicle, and uses each target charging period of the vehicle as the vehicle's charging strategy; The adjustment module is used to collect the vehicle's current battery information and environmental change information to adjust the vehicle's charging strategy, obtain a new charging strategy, replace the existing charging strategy with the new charging strategy, and return to execute the step of collecting the vehicle's current battery information and environmental change information to adjust the vehicle's charging strategy and obtain a new charging strategy, until the vehicle's current battery information is at saturation.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images