Scheduling Method, Device and Equipment for Split-Shared Hanging-Rail Charging Robot

Abstract

The present application relates to a scheduling method, device and equipment for a split shared hanging rail type charging robot. The method includes: obtaining the operating states of a plurality of charging robots deployed inside a charging station, the operating states of a plurality of chargers, and at least one charging request; determining a plurality of candidate charging scheduling strategies according to the operating states of the plurality of charging robots, the operating states of the plurality of chargers, and the at least one charging request; determining a target charging scheduling strategy from the plurality of candidate charging scheduling strategies based on a preset objective function and preset constraint conditions; and when the current moment matches any scheduling moment, controlling the target charging robot at the corresponding scheduling moment to move the charger at the corresponding target charger position to the charging point position indicated by the corresponding target charging request, and charging the vehicle at the charging point position. Using this method can improve the charging efficiency of the charging station.

Description

Technical Field

[0001] The present application relates to the technical field of power system automation, and particularly to a scheduling method, device, and equipment for a split shared hanging rail type charging robot. Background Art

[0002] With the popularization of electric vehicles and the rapid development of industrial automation, the split shared hanging rail type charging robot, as a new type of charging equipment, has gradually played an important role in places such as factories and parking lots. Traditional charging equipment relies on manual operation, with low efficiency and being easily restricted by human factors. The split shared hanging rail type charging robot realizes autonomous operation and charging through autonomous navigation and intelligent charging technology, and has the advantages of high-efficiency charging and flexible operation. Different from the traditional method of using a robotic arm to complete automatic plugging and unplugging of the charging gun, the split shared hanging rail type charging robot system reserves charging gun lines at each point, and adopts a connection design that supports hot plugging at the incoming and outgoing power ports of the pile body, realizing a low-cost and reliable decoupling of the pile body and the high-voltage power line. The split shared hanging rail type charging robot constructs a new paradigm of electric vehicle charging and discharging service ecosystem based on the flexible plugging and unplugging design of the system's heavy pile body. However, how to reasonably schedule and manage charging robots to meet the charging needs of diverse scenarios in this service ecosystem and improve the charging efficiency of charging stations has become one of the current research focuses. Summary of the Invention

[0003] Based on this, in view of the above technical problems, it is necessary to provide a scheduling method, device, and equipment for a split shared hanging rail type charging robot that can improve the charging efficiency of charging stations.

[0004] In a first aspect, the present application provides a scheduling method for a split shared hanging rail type charging robot, including:

[0005] Obtaining the operating states of multiple charging robots deployed in a charging station, the operating states of multiple chargers, and at least one charging request; the charging request is used to indicate charging a vehicle at a charging point location;

[0006] Determining multiple candidate charging scheduling strategies according to the operating states of multiple charging robots, the operating states of multiple chargers, and at least one charging request;

[0007] Based on a preset objective function and preset constraint conditions, determining a target charging scheduling strategy among multiple candidate charging scheduling strategies; the target charging scheduling strategy includes the target charging robot, the target charger location, and the target charging request to be processed at multiple scheduling times;

[0008] When the current moment matches any scheduling moment, control the target charging robot at the corresponding scheduling moment to move the charger at the corresponding target charger position to the charging point position indicated by the corresponding target charging request, and charge the vehicle at the charging point position.

[0009] In one embodiment, determining a target charging scheduling strategy from multiple candidate charging scheduling strategies based on a preset objective function and preset constraint conditions includes:

[0010] Determine multiple reference charging scheduling strategies that meet the preset constraint conditions from multiple candidate charging scheduling strategies;

[0011] Based on the preset objective function, determine the target charging scheduling strategy from multiple reference charging scheduling strategies.

[0012] In one embodiment, the preset constraint conditions include charge state dynamic constraints, charging power constraints, charger charging condition constraints, conditional risk constraints, and charging robot scheduling related constraints.

[0013] In one embodiment, the preset objective function includes a remaining battery charge deviation function, a charging cost function under dynamic electricity prices, a charging robot moving distance function, and a charging power function; at least one charging request includes the number of vehicles, the real-time charge state of each vehicle, and the desired charge state; based on the preset objective function, determining the target charging scheduling strategy from multiple reference charging scheduling strategies includes:

[0014] For each reference charging scheduling strategy, according to the remaining battery charge deviation function, the number of vehicles at the scheduling moment corresponding to the reference charging scheduling strategy, the real-time charge state of each vehicle, and the desired charge state, determine the remaining battery charge deviation corresponding to the reference charging scheduling strategy; according to the charging cost function under dynamic electricity prices, the electricity price at the scheduling moment corresponding to the reference charging scheduling strategy, and the charging power of each charger, determine the charging cost under dynamic electricity prices corresponding to the reference charging scheduling strategy; according to the charging robot moving distance function, the parking positions of each vehicle, the positions of each charging robot, and the positions of each charger at the scheduling moment corresponding to the reference charging scheduling strategy, determine the charging robot moving distance corresponding to the reference charging scheduling strategy; according to the charging power function, the predicted departure time of each vehicle and the charging power of each charger at the scheduling moment corresponding to the reference charging scheduling strategy, determine the reference charging power corresponding to the reference charging scheduling strategy; weight the remaining battery charge deviation, the charging cost under dynamic electricity prices, the charging robot moving distance, and the reference charging power to obtain the target value corresponding to the reference charging scheduling strategy;

[0015] Determine the target charging scheduling strategy whose target value meets the preset conditions from multiple reference charging scheduling strategies.

[0016] In one embodiment, the multiple charging requests include the charging power and the charging start time of multiple vehicles; according to the operating states of multiple charging robots, the operating states of multiple chargers, and at least one charging request, multiple candidate charging scheduling strategies are determined, including:

[0017] Obtain real-time environmental information and historical charging data of multiple charging robots;

[0018] According to the real-time environmental information and the historical charging data of multiple charging robots, determine the predicted departure times of multiple vehicles;

[0019] According to the operating states of multiple charging robots, the operating states of multiple chargers, the predicted departure times of multiple vehicles, the charging power, and the charging start time, determine multiple candidate charging scheduling strategies.

[0020] In one embodiment, according to the real-time environmental information and the historical charging data of multiple charging robots, determining the predicted departure times of multiple vehicles includes:

[0021] Input the real-time environmental information and the historical charging data of multiple charging robots into a pre-trained charging demand prediction model. The pre-trained charging demand prediction model is composed of a long short-term memory network module, an attention mechanism processing module, a multi-channel neural network module, a squeeze-and-excitation network module, and an output module;

[0022] The long short-term memory network module extracts temporal features from the historical charging data to obtain temporal features. The attention mechanism processing module performs weighted processing on the temporal features of different time steps to obtain attention features. The multi-channel neural network module performs multi-channel processing on the attention features to obtain multi-channel features. The squeeze-and-excitation network module performs enhancement processing on the multi-channel features to obtain enhanced features. The output module performs fully connected processing on the enhanced features to obtain the predicted departure times of the vehicles charged by multiple charging robots.

[0023] In a second aspect, the present application also provides a scheduling device for a split shared rail-mounted charging robot, including:

[0024] An acquisition module, configured to acquire the operating states of multiple charging robots deployed in a charging station, the operating states of multiple chargers, and at least one charging request; the charging request is used to indicate charging of a vehicle at a charging point location;

[0025] A first determination module, configured to determine multiple candidate charging scheduling strategies according to the operating states of multiple charging robots, the operating states of multiple chargers, and at least one charging request;

[0026] A second determination module, configured to determine a target charging scheduling policy from multiple candidate charging scheduling policies based on a preset objective function and preset constraint conditions; the target charging scheduling policy includes target charging robots, target charger positions, and target charging requests to be processed at multiple scheduling times;

[0027] A control module, configured to, when the current time matches any one of the scheduling times, control the target charging robot at the corresponding scheduling time to move the charger at the corresponding target charger position to the charging point position indicated by the corresponding target charging request, and charge the vehicle at the charging point position.

[0028] In a third aspect, the present application further provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0029] Obtain the operating states of multiple charging robots deployed in a charging yard, the operating states of multiple chargers, and at least one charging request; the charging request is used to indicate charging a vehicle at a charging point position;

[0030] Determine multiple candidate charging scheduling policies according to the operating states of multiple charging robots, the operating states of multiple chargers, and at least one charging request;

[0031] Determine a target charging scheduling policy from multiple candidate charging scheduling policies based on a preset objective function and preset constraint conditions; the target charging scheduling policy includes target charging robots, target charger positions, and target charging requests to be processed at multiple scheduling times;

[0032] When the current time matches any one of the scheduling times, control the target charging robot at the corresponding scheduling time to move the charger at the corresponding target charger position to the charging point position indicated by the corresponding target charging request, and charge the vehicle at the charging point position.

[0033] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0034] Obtain the operating states of multiple charging robots deployed in a charging yard, the operating states of multiple chargers, and at least one charging request; the charging request is used to indicate charging a vehicle at a charging point position;

[0035] Determine multiple candidate charging scheduling policies according to the operating states of multiple charging robots, the operating states of multiple chargers, and at least one charging request;

[0036] Determine a target charging scheduling strategy among multiple candidate charging scheduling strategies based on a preset objective function and preset constraint conditions; the target charging scheduling strategy includes target charging robots, target charger positions, and target charging requests to be processed at multiple scheduling times;

[0037] When the current time matches any one of the scheduling times, control the target charging robot at the corresponding scheduling time to move the charger at the corresponding target charger position to the charging point position indicated by the corresponding target charging request, and charge the vehicle at the charging point position.

[0038] In a fifth aspect, the present application also provides a computer program product, including a computer program, which when executed by a processor implements the following steps:

[0039] Obtain the operating states of multiple charging robots deployed in a charging yard, the operating states of multiple chargers, and at least one charging request; the charging request is used to indicate charging of the vehicle at the charging point position;

[0040] Determine multiple candidate charging scheduling strategies based on the operating states of multiple charging robots, the operating states of multiple chargers, and at least one charging request;

[0041] Determine a target charging scheduling strategy among multiple candidate charging scheduling strategies based on a preset objective function and preset constraint conditions; the target charging scheduling strategy includes target charging robots, target charger positions, and target charging requests to be processed at multiple scheduling times;

[0042] When the current time matches any one of the scheduling times, control the target charging robot at the corresponding scheduling time to move the charger at the corresponding target charger position to the charging point position indicated by the corresponding target charging request, and charge the vehicle at the charging point position.

[0043] The scheduling method, device, computer equipment, computer-readable storage medium and computer program product of the above-mentioned split shared rail-mounted charging robot obtain the operating states of multiple charging robots deployed inside a charging station, the operating states of multiple chargers, and at least one charging request; the charging request is used to indicate charging a vehicle at a charging point location; combining the operating states of multiple charging robots, the operating states of multiple chargers, and at least one charging request to determine multiple candidate charging scheduling strategies, and the determined multiple candidate charging scheduling strategies can simultaneously meet the charging requirements of the charging robots, chargers, and vehicles; based on a preset objective function and preset constraint conditions, determine a target charging scheduling strategy among the multiple candidate charging scheduling strategies, and the target charging scheduling strategy includes the target charging robot, the target charger location, and the target charging request to be processed at multiple scheduling times. This method of using the objective function and constraint conditions to screen the target charging scheduling strategy is beneficial to optimizing power management and reducing energy consumption. Automatically scheduling the charging robot based on the target charging scheduling strategy improves the scheduling efficiency of the charging robot, thereby facilitating the improvement of the overall charging efficiency of the charging station. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] To more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0045] Figure 1 It is an application environment diagram of the scheduling method of the split shared rail-mounted charging robot in an embodiment;

[0046] Figure 2 It is a flowchart of the scheduling method of the split shared rail-mounted charging robot in an embodiment;

[0047] Figure 3 It is a flowchart of charging scheduling based on the target charging scheduling strategy in an embodiment;

[0048] Figure 4 It is a structural block diagram of the scheduling device of the split shared rail-mounted charging robot in an embodiment;

[0049] Figure 5 It is an internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0050] In order to make the objectives, technical solutions and advantages of the present application more clear and understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0051] The scheduling method for the split shared rail-mounted charging robot provided by the embodiment of the present application can be applied to an application environment as Figure 1 shown. Among them, the terminal 102 communicates with the server 104 through a network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed in the cloud or other network servers. This embodiment takes the application of this method to the terminal as an example for illustration. It can be understood that this method can also be applied to the server, and can also be applied to a system including the terminal and the server, and is realized through the interaction between the terminal and the server. The terminal 102 obtains the operating status of multiple charging robots deployed inside the charging station, the operating status of multiple chargers, and at least one charging request; the charging request is used to indicate charging of the vehicle at the charging point location; according to the operating status of multiple charging robots, the operating status of multiple chargers, and at least one charging request, determine multiple candidate charging scheduling strategies; based on a preset objective function and preset constraint conditions, determine the target charging scheduling strategy among the multiple candidate charging scheduling strategies; the target charging scheduling strategy includes the target charging robot, the target charger location, and the target charging request to be processed at multiple scheduling times; when the current time matches any scheduling time, control the target charging robot at the corresponding scheduling time to move the charger at the corresponding target charger location to the charging point location indicated by the corresponding target charging request, and charge the vehicle at the charging point location. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, projection devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, a smart glasses, etc. The server 104 can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0052] In an exemplary embodiment, as Figure 2 shown, a scheduling method for the split shared rail-mounted charging robot is provided. Taking the application of this method to the Figure 1 terminal 102 as an example for illustration, it includes the following steps 202 to step 208. Among them:

[0053] Step 202: Obtain the operating statuses of multiple charging robots deployed within the charging station, the operating statuses of multiple chargers, and at least one charging request; the charging request is used to indicate charging of a vehicle at a charging point location.

[0054] Among them, a charging station refers to a site that provides electrical energy replenishment for vehicles. Multiple charging robots and chargers are deployed at the charging station. Among them, the charging robot is a split-type shared rail-mounted charging robot. Both the charging robot and the charger are set on the track, and a site module is also set on the track. The site module is a power-taking device for the charger. When a vehicle in a certain parking space needs to be charged, the charging robot can move along the track, carry the charger to the site module, and dock the charger with the site module to charge the vehicle.

[0055] The operating status of the charging robot includes a working status, an idle status, and a charging status. The operating status of the charger includes a working status and an idle status.

[0056] A charging request refers to a request initiated by a vehicle for charging, and is used to indicate charging of a vehicle at a charging point location.

[0057] The charging point location refers to the location of the site module on the track. The site module reserves a charging gun cable and a hot-swappable connection port. One end of the charging gun cable is connected to the vehicle, and the other end is connected to the power supply line. When the site module is connected to the charger through the hot-swappable connection port, the power supply line can charge the vehicle at the charging point location. When the site module is disconnected from the charger, the power supply line stops charging the vehicle.

[0058] Step 204: Determine multiple candidate charging scheduling strategies based on the operating statuses of multiple charging robots, the operating statuses of multiple chargers, and at least one charging request.

[0059] Among them, a candidate charging scheduling strategy refers to a strategy for scheduling charging robots to meet charging requirements. The candidate charging scheduling strategy includes charging robots, charger positions, and charging requests to be processed at multiple scheduling times. By fully considering the operating statuses of each charging robot and each charger in the actual working scenario, as well as each charging requirement, the determined candidate charging scheduling strategy can simultaneously meet the charging requirements of the charging robot, the charger, and the vehicle, improving the scheduling efficiency.

[0060] In some embodiments, the terminal sorts at least one charging request by priority. For example, the sorting can be based on the time when the vehicle initiates the charging request, the level information of the vehicle, etc. The scheduling time can be determined according to the priorities of the charging requests.

[0061] In some embodiments, the determination of the candidate charging scheduling strategy may also consider factors such as the number of charging robots, working hours, types and frequencies of charging demands, and may also consider the charging demand situations of charging robots at different time periods and locations. By fully understanding the characteristics of charging demands, necessary data support can be provided for subsequent determination of the candidate charging scheduling strategy.

[0062] In some embodiments, the candidate charging scheduling strategy further includes important parameters such as the task attributes of charging robots, task spatio-temporal distribution characteristics, task quantity, and task priorities. By determining the candidate charging scheduling strategy, basic data and guidance can be provided for subsequent scheduling optimization.

[0063] Step 206: Based on a preset objective function and preset constraint conditions, determine a target charging scheduling strategy among multiple candidate charging scheduling strategies; the target charging scheduling strategy includes target charging robots, target charger positions, and target charging requests to be processed at multiple scheduling times.

[0064] Among them, to improve the scheduling efficiency of charging robots and the charging efficiency of the charging station, the embodiment of the present application proposes to determine a target charging scheduling strategy among multiple candidate charging scheduling strategies based on a preset objective function and preset constraint conditions. The target charging scheduling strategy includes target charging robots, target charger positions, and target charging requests to be processed at multiple scheduling times.

[0065] The preset objective function is used to evaluate at least one of the remaining power deviation, charging cost, moving distance of the charging robot, and charging power. The preset constraint conditions are used for at least one of the charge state, charging power, charger charging conditions, conditional risk, and charging robot scheduling.

[0066] Step 208: When the current time matches any scheduling time, control the target charging robot at the corresponding scheduling time to move the charger at the corresponding target charger position to the charging point position indicated by the corresponding target charging request, and charge the vehicle at the charging point position.

[0067] Among them, the terminal schedules the charging robot according to the target charging scheduling strategy. Specifically, when the current time matches any scheduling time in the target charging scheduling strategy, control the target charging robot at the corresponding scheduling time to move the charger at the corresponding target charger position to the charging point position indicated by the corresponding target charging request. At the charging point position, connect the charger to the station module, so as to charge the vehicle parked near the charging point position through the charging gun line of the station module.

[0068] In the scheduling method of the above-mentioned split-type shared hanging-rail charging robot, the operating states of multiple charging robots deployed inside the charging station, the operating states of multiple chargers, and at least one charging request are obtained; the charging request is used to indicate charging a vehicle at a charging point location; multiple candidate charging scheduling strategies are determined in combination with the operating states of multiple charging robots, the operating states of multiple chargers, and at least one charging request, and the determined multiple candidate charging scheduling strategies can simultaneously meet the charging requirements of the charging robots, chargers, and vehicles; based on a preset objective function and preset constraint conditions, a target charging scheduling strategy is determined among the multiple candidate charging scheduling strategies, and the target charging scheduling strategy includes the target charging robot, the target charger location, and the target charging request to be processed at multiple scheduling times. This method of using the objective function and constraint conditions to screen the target charging scheduling strategy is beneficial to optimizing power management, reducing energy consumption, automatically scheduling the charging robot based on the target charging scheduling strategy, improving the scheduling efficiency of the charging robot, and thus being beneficial to improving the overall charging efficiency of the charging station.

[0069] In an exemplary embodiment, based on a preset objective function and preset constraint conditions, determining a target charging scheduling strategy among multiple candidate charging scheduling strategies includes: determining multiple reference charging scheduling strategies that meet the preset constraint conditions among the multiple candidate charging scheduling strategies; determining a target charging scheduling strategy among the multiple reference charging scheduling strategies based on the preset objective function.

[0070] Among them, in the process of determining the target charging scheduling strategy, first, multiple reference charging scheduling strategies that meet the preset constraint conditions are screened out from multiple candidates, and then, based on the preset objective function, the target charging scheduling strategy is screened out from the multiple reference charging scheduling strategies.

[0071] In this embodiment, through the dual constraints of the preset constraint conditions and the preset objective function, the target charging scheduling strategy is screened out from multiple candidate charging scheduling strategies, and the selected target charging scheduling strategy is used to schedule the charging robot, which can improve the scheduling efficiency and the charging efficiency of the charging station.

[0072] In one of the embodiments, the preset constraint conditions include charge state dynamic constraint, charging power constraint, charger charging condition constraint, conditional risk constraint, and charging robot scheduling-related constraint.

[0073] Among them, the charge state dynamic constraint is used to constrain the charge state of the vehicle. The charge state dynamic constraint can be expressed as follows:

[0074]

[0075] Among them, represents the battery capacity of the i-th vehicle. Indicates the desired SOC (State of Charge of the battery) level. Indicates that the desired SOC level needs to be met when the vehicle departs. Is a robust SOC constraint, that is, the desired SOC level of the vehicle can be not met under a certain deviation.

[0076] The charging power constraint is used to restrict the charging power for charging the vehicle. The charging power constraint can be expressed as follows:

[0077]

[0078] Where, Is the maximum charging power when the k-th charger charges the i-th vehicle, and its value is the maximum of the charging power upper limit of the charger and the charging power upper limit of the vehicle.

[0079] The charger charging condition constraint is used to restrict that a charger can serve at most one vehicle's charging demand. The charger charging condition constraint can be expressed as follows:

[0080]

[0081] The conditional risk constraint is used to handle the uncertainty in the charging process. The conditional risk constraint can adopt the CVaR (Conditional Value at Risk) model. The conditional risk constraint can be expressed as follows:

[0082]

[0083] To handle uncertainties, such as the uncertainty of the actual departure time of the vehicle, the conditional value at risk model can be used to ensure that the SOC of the vehicle meets the requirements at a certain confidence level.

[0084] The charging robot scheduling related constraints are used to restrict the moving speed and moving position of the charging robot, etc. The charging robot scheduling related constraints can be expressed as follows:

[0085] Robot scheduling constraint:

[0086]

[0087] Robot moving speed constraint:

[0088]

[0089] Real-time position and target position constraint:

[0090]

[0091] Where, Represents the moving speed of the robot. Represents the target location of this task.

[0092] In this embodiment, by constructing multiple constraint conditions, the screening of the target charging scheduling strategy is constrained from multiple perspectives, which is beneficial to ensuring that the target charging scheduling strategy meets the constraints such as the charge state of the vehicle, the charging power for charging the vehicle, the charging conditions of the charger, the conditional risk, and the charging robot scheduling.

[0093] In one of the embodiments, the preset objective function includes a remaining power deviation function, a charging cost function under dynamic electricity prices, a charging robot moving distance function, and a charging power function; at least one charging request includes the number of vehicles, the real-time charge state of each vehicle, and the desired charge state; based on the preset objective function, determining the target charging scheduling strategy among multiple reference charging scheduling strategies includes: for each reference charging scheduling strategy, according to the remaining power deviation function, the number of vehicles at the scheduling moment corresponding to the reference charging scheduling strategy, the real-time charge state of each vehicle, and the desired charge state, determining the remaining power deviation corresponding to the reference charging scheduling strategy; according to the charging cost function under dynamic electricity prices, the electricity price at the scheduling moment corresponding to the reference charging scheduling strategy, and the charging power of each charger, determining the charging cost under dynamic electricity prices corresponding to the reference charging scheduling strategy; according to the charging robot moving distance function, the parking positions of each vehicle at the scheduling moment corresponding to the reference charging scheduling strategy, the positions of each charging robot, and the positions of each charger, determining the charging robot moving distance corresponding to the reference charging scheduling strategy; according to the charging power function, the predicted departure time of each vehicle at the scheduling moment corresponding to the reference charging scheduling strategy, and the charging power of each charger, determining the reference charging power corresponding to the reference charging scheduling strategy; weighting the remaining power deviation, the charging cost under dynamic electricity prices, the charging robot moving distance, and the reference charging power to obtain the target value corresponding to the reference charging scheduling strategy; determining the target charging scheduling strategy whose target value meets the preset conditions from multiple reference charging scheduling strategies.

[0094] Among them, in order to further optimize the power management, multiple target values are calculated based on the preset objective function, which is beneficial to screening out the ideal target charging scheduling strategy.

[0095] Among them, the remaining power deviation function is used to evaluate the remaining power deviation of the vehicle, and the remaining power deviation function can be expressed as follows:

[0096]

[0097] Among them, i represents the i-th vehicle, N represents the total number of vehicles, Represents the SOC of the i-th vehicle at time t, Represents the desired SOC level of the i-th vehicle.

[0098] The charging cost function under dynamic electricity price is used to evaluate the charging cost of vehicles, and the charging cost function under dynamic electricity price can be expressed as follows:

[0099]

[0100] where, represents the electricity price at time t; represents the charging power of the k-th charger at the i-th charging point at time t; is a binary variable indicating whether the j-th charging robot places the k-th charger at the i-th charging point for charging at time t ( =1 means placed, 0 means not placed).

[0101] The charging robot moving distance function is used to evaluate the moving distance of the charging robot, and the charging robot moving distance function can be expressed as follows:

[0102]

[0103] where, d(u,v) represents the distance from node u to node v; represents the parking space number where the i-th vehicle stays at time t; represents the position number of the j-th charging robot at time t; represents the position number of the k-th charger at time t.

[0104] The charging power function is used to evaluate the charging power of all vehicles, and the charging power function can be expressed as follows:

[0105]

[0106] where, represents the charging priority of the i-th vehicle. In some practical situations, the charging priority of the vehicle may change dynamically with time. For example, as the departure time of the vehicle approaches, the priority may increase. At this time, the priority can be expressed as a function of time . where, is the planned departure time of vehicle i. As time t increases, the priority gradually rises, so as to obtain more charging resources before departure.

[0107] In some embodiments, for each reference charging scheduling strategy, the remaining power deviation, charging cost, charging robot moving distance, and reference charging power corresponding to each preset objective function are calculated respectively, and the terminal performs weighted summation on the above calculation results to obtain the objective value corresponding to the reference charging scheduling strategy.

[0108] For example, the total objective function is: , where are the weight variables corresponding to each preset objective function respectively.

[0109] The terminal determines a target charging scheduling strategy whose target value meets the preset conditions from multiple reference charging scheduling strategies. In some embodiments, the preset condition may be that the reference charging scheduling strategy with the minimum target value is used as the target charging scheduling strategy, or the reference charging scheduling strategy whose target value is less than the preset target value may be used as the target charging scheduling strategy, etc.

[0110] In this embodiment, by constructing multiple preset objective functions and screening the target charging scheduling strategies whose target values meet the preset conditions from multiple perspectives, it is beneficial to ensure that the target charging scheduling strategy has a small remaining power deviation, charging cost, charging robot moving distance, and charging power, which is beneficial to optimizing power management.

[0111] In one of the embodiments, the multiple charging requests include the charging power and charging start time of multiple vehicles; according to the operating states of multiple charging robots, the operating states of multiple chargers, and at least one charging request, multiple candidate charging scheduling strategies are determined, including: obtaining real-time environment information and historical charging data of multiple charging robots; according to the real-time environment information and historical charging data of multiple charging robots, determining the predicted departure times of multiple vehicles; according to the operating states of multiple charging robots, the operating states of multiple chargers, the predicted departure times of multiple vehicles, the charging power, and the charging start time, determining multiple candidate charging scheduling strategies.

[0112] Among them, the historical charging data refers to the charging information in the charging station within the historical time period before the current moment, including the number of vehicles charging at each moment, the utilization of charging points, the charging power, the working conditions of chargers, and the working conditions of charging robots, etc. The real-time environment information refers to the external environment information that may affect charging scheduling, such as weather information, holiday information, etc.

[0113] Since the departure times of the vehicles staying in the charging station cannot be accurately known, therefore, the embodiments of the present application propose to use the real-time environment information and the historical charging data of multiple charging robots to determine the predicted departure times of multiple vehicles. For example, a pre-trained charging demand prediction model can be used for prediction.

[0114] Based on the predicted departure times of multiple vehicles, combined with the operating states of multiple charging robots, the operating states of multiple chargers, the charging power, and the charging start time, the terminal can determine multiple candidate charging scheduling strategies.

[0115] In this embodiment, the predicted departure times of multiple vehicles are predicted by using real-time environment information and historical charging data of multiple charging robots. Then, in combination with the operating states of multiple charging robots, the operating states of multiple chargers, the charging power, and the charging start time, multiple candidate charging scheduling strategies are determined. Adopting the candidate charging scheduling strategies for charging scheduling is beneficial to improving the scheduling efficiency and charging efficiency.

[0116] In one of the embodiments, determining the predicted departure times of multiple vehicles according to real-time environment information and historical charging data of multiple charging robots includes: inputting the real-time environment information and historical charging data of multiple charging robots into a pre-trained charging demand prediction model. The pre-trained charging demand prediction model includes a long short-term memory network module, an attention mechanism processing module, a multi-channel neural network module, a squeeze-and-excitation network module, and an output module. The long short-term memory network module extracts temporal features from the historical charging data to obtain temporal features. The attention mechanism processing module performs weighted processing on the temporal features of different time steps to obtain attention features. The multi-channel neural network module performs multi-channel processing on the attention features to obtain multi-channel features. The squeeze-and-excitation network module performs enhancement processing on the multi-channel features to obtain enhanced features. The output module performs fully connected processing on the enhanced features to obtain the predicted departure times of the vehicles charged by multiple charging robots.

[0117] Among them, the real-time environment information and historical charging data of multiple charging robots are input into the pre-trained charging demand prediction model, and sequentially pass through the long short-term memory network module for temporal feature extraction, the attention mechanism processing module for weighted processing, the multi-channel neural network module for multi-channel processing, the squeeze-and-excitation network module for enhancement processing, and finally pass through the output module for fully connected processing to obtain the predicted departure times of the vehicles charged by multiple charging robots.

[0118] The core of the long short-term memory network module (LSTM network) is capable of capturing the long-term and short-term dependencies of data. To improve the prediction ability of the model, the LSTM networks are stacked into a multi-layer structure to extract deep features in the time series layer by layer. Each layer of the LSTM network will output a hidden state, and the next layer of the LSTM network will continue to learn based on the hidden state of the previous layer. For multiple layers of LSTM, it can be expressed as follows:

[0119]

[0120] Among them, represents the hidden state of the L-th layer of the LSTM network at time step t, is the input data, and L represents the number of layers of the LSTM network.

[0121] The attention mechanism processing module first calculates the attention weights and then performs weighted processing. Calculating the attention weights :

[0122]

[0123] Among them, , are learnable parameters, is the attention vector.

[0124] The weighted processing can be expressed as: .

[0125] In this structure, the output of each LSTM network layer will be fed into the attention mechanism processing module (Attention layer), and through weighted summation, is obtained. Different from the traditional LSTM network that only uses the output at the last moment for subsequent calculations, the introduction of the attention mechanism can effectively reduce the loss of input information, and at the same time make the model more focused on the key parts in the long sequence, thereby improving the overall training effect.

[0126] The multi-channel neural network module can perform multi-scale spatial feature extraction. To better extract local features from time-series data, a multi-channel convolutional neural network is introduced. The idea of the multi-channel convolutional neural network CNN is to use convolutional kernels (filters) of different sizes to capture local features of different scales. Assuming that N convolutional kernels are used, and each convolutional kernel has sizes of respectively, the convolutional operation can be expressed as:

[0127]

[0128] Among them, represents the convolutional kernel, represents the convolutional operation, is the output of the LSTM, is the bias term, is the th output feature map of the channel, and ReLU is the activation function.

[0129] The overall output of the multi-channel CNN is the concatenation of the feature maps of different convolutional kernels:

[0130]

[0131] Among them, is the set of all feature maps obtained through multi-channel convolutional operations.

[0132] The enhancement process of the squeeze-and-excitation network module includes a squeeze step, an excitation step, and a scale step.

[0133] Squeeze step: Perform global average pooling on each convolutional channel:

[0134]

[0135] where represents the eigenvalue of the i-th channel at position , and are the height and width of the feature map.

[0136] Excitation step: recalibrate the weights of the channels through a fully connected layer and an activation function: . where and are the weight matrices of the fully connected layer, is the Sigmoid activation function.

[0137] Scale step: Apply the weight to the feature map of each channel: , so that the model can pay more attention to important feature channels, thereby enhancing the expression ability of the model.

[0138] The output module flattens the feature map processed by the squeeze-and-excitation network module and performs a fully connected process, and finally generates the final prediction result through the output layer:

[0139]

[0140] where is the output of the fully connected layer, is the output weight matrix, is the bias vector of the output layer.

[0141] In this embodiment, the real-time environment information and the historical charging data of multiple charging robots are input into the pre-trained charging demand prediction model. Through the sequential processing of multiple modules in the pre-trained charging demand prediction model, the predicted departure times of the vehicles charged by multiple charging robots are obtained, realizing the prediction of the departure times of vehicles based on real-time environment information and historical charging data, which is beneficial to improving the scheduling efficiency of charging robots.

[0142] To illustrate the effect of the scheduling method of the split shared rail-mounted charging robot in this solution in detail, the following is an illustration with a most detailed embodiment:

[0143] Taking the scenario of scheduling multiple split shared rail-mounted charging robots in a charging station as an example for illustration. The terminal obtains the operating states of multiple charging robots deployed inside the charging station, the operating states of multiple chargers, and at least one charging request; the charging request is used to indicate charging a vehicle at a charging point location; based on the operating states of the multiple charging robots, the operating states of the multiple chargers, and the at least one charging request, determine multiple candidate charging scheduling strategies; based on a preset objective function and preset constraint conditions, determine a target charging scheduling strategy among the multiple candidate charging scheduling strategies; the target charging scheduling strategy includes the target charging robot, the target charger location, and the target charging request to be processed at multiple scheduling times; when the current time matches any scheduling time, control the target charging robot at the corresponding scheduling time to move the charger at the corresponding target charger location to the charging point location indicated by the corresponding target charging request, and charge the vehicle at the charging point location.

[0144] As Figure 3 shown is a schematic flowchart of charging scheduling based on the target charging scheduling strategy in some embodiments. Among them, after determining the target charging scheduling strategy, the terminal sends a charger location instruction 1 and a charging point location instruction 2 to the charging robot, controls the charging robot to move to the charger location 1, extend the forklift, and fork the charger at the charger location 1, and fork the charger to the central position of the charging robot. Control the charging robot to move the charger to the charging point location 2, extend the forklift, push and fork the charger, and then retract the forklift. In some embodiments, the charging robot can judge according to its own battery level. If the battery level is lower than the lowest set value, the charging robot will move to the charging position for charging, or, if the charging robot does not receive the next charging requirement, after a preset duration of stopping operation, such as 5 minutes, the charging robot will move to the charging position for charging.

[0145] In some embodiments, when the vehicle charging is completed, the terminal sends a charging end signal to the charging robot. When the charging robot receives the charging end at the S i position, move the jth charging robot closest to the S i position to move to the S i position to execute the gun unplugging instruction, and then carry the charger to the next target position.

[0146] The scheduling method of the above-mentioned split and shared rail-mounted charging robot obtains the operating states of multiple charging robots deployed in a charging station, the operating states of multiple chargers, and at least one charging request; the charging request is used to indicate charging a vehicle at a charging point location; determining multiple candidate charging scheduling strategies by combining the operating states of multiple charging robots, the operating states of multiple chargers, and at least one charging request, and the determined multiple candidate charging scheduling strategies can simultaneously meet the charging requirements of the charging robots, chargers, and vehicles; based on a preset objective function and preset constraint conditions, determining a target charging scheduling strategy among multiple candidate charging scheduling strategies, the target charging scheduling strategy includes the target charging robot, the target charger location, and the target charging request to be processed at multiple scheduling times. This method of using the objective function and constraint conditions to screen the target charging scheduling strategy is beneficial to optimizing power management and reducing energy consumption. Automatically scheduling the charging robot based on the target charging scheduling strategy improves the scheduling efficiency of the charging robot, thereby facilitating the improvement of the overall charging efficiency of the charging station. In addition, through a pre-trained charging demand prediction model, combined with historical charging data and real-time environmental information, accurately predicting the predicted departure times of multiple vehicles, so as to more effectively arrange the scheduling of the charging robot. Determining candidate charging scheduling strategies by combining the operating states of the charging robot, the operating states of the chargers, the predicted departure times of multiple vehicles, etc., and screening out the target charging scheduling strategy for operating the charging robot and the charger based on the preset objective function and preset constraint conditions to optimize power management and reduce energy consumption. Through the self-optimizing scheduling method, the scheduling efficiency of the split and shared rail-mounted charging robot is improved, thereby improving the overall service quality and charging efficiency of the charging station.

[0147] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps does not have a strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed 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 executed alternately or alternately with at least a part of other steps or steps or stages in other steps.

[0148] Based on the same inventive concept, an embodiment of the present application further provides a scheduling device for a split shared rail-mounted charging robot for implementing the scheduling method of the split shared rail-mounted charging robot involved above. The implementation solution provided by this device for solving problems is similar to the implementation solution recorded in the above method. Therefore, the specific limitations in one or more embodiments of the scheduling device for the split shared rail-mounted charging robot provided below can refer to the limitations on the scheduling method of the split shared rail-mounted charging robot in the above text, and will not be repeated here.

[0149] In an exemplary embodiment, as Figure 4 shown, a scheduling device 400 for a split shared rail-mounted charging robot is provided, including: an acquisition module 420, a first determination module 440, a second determination module 460, and a control module 480, where:

[0150] The acquisition module 420 is configured to acquire the operating states of a plurality of charging robots deployed in a charging station, the operating states of a plurality of chargers, and at least one charging request; the charging request is used to indicate charging a vehicle at a charging point location;

[0151] The first determination module 440 is configured to determine a plurality of candidate charging scheduling strategies according to the operating states of a plurality of charging robots, the operating states of a plurality of chargers, and at least one charging request;

[0152] The second determination module 460 is configured to determine a target charging scheduling strategy from a plurality of candidate charging scheduling strategies based on a preset objective function and preset constraint conditions; the target charging scheduling strategy includes target charging robots, target charger positions, and target charging requests to be processed at a plurality of scheduling times;

[0153] The control module 480 is configured to, when the current time matches any scheduling time, control the target charging robot at the corresponding scheduling time to move the charger at the corresponding target charger position to the charging point position indicated by the corresponding target charging request, and charge the vehicle at the charging point position.

[0154] The scheduling device of the above-mentioned split and shared hanging-rail type charging robot obtains the operating states of a plurality of charging robots deployed inside a charging station, the operating states of a plurality of chargers, and at least one charging request; the charging request is used to indicate charging a vehicle at a charging point location; determines a plurality of candidate charging scheduling strategies by combining the operating states of the plurality of charging robots, the operating states of the plurality of chargers, and the at least one charging request, and the determined plurality of candidate charging scheduling strategies can simultaneously meet the charging requirements of the charging robots, chargers, and vehicles; based on a preset objective function and preset constraint conditions, determines a target charging scheduling strategy among the plurality of candidate charging scheduling strategies, and the target charging scheduling strategy includes target charging robots, target charger positions, and target charging requests to be processed at multiple scheduling times. This method of using the objective function and constraint conditions to screen the target charging scheduling strategy is beneficial to optimizing power management, reducing energy consumption, automatically scheduling the charging robots based on the target charging scheduling strategy, improving the scheduling efficiency of the charging robots, and thus being beneficial to improving the overall charging efficiency of the charging station.

[0155] In one embodiment, when determining the target charging scheduling strategy based on the preset objective function and preset constraint conditions among the plurality of candidate charging scheduling strategies, the second determination module 460 is further configured to: determine a plurality of reference charging scheduling strategies that meet the preset constraint conditions among the plurality of candidate charging scheduling strategies; and determine the target charging scheduling strategy among the plurality of reference charging scheduling strategies based on the preset objective function.

[0156] In one embodiment, the preset constraint conditions include charge state dynamic constraints, charging power constraints, charger charging condition constraints, conditional risk constraints, and charging robot scheduling-related constraints.

[0157] In one embodiment, the preset objective function includes a remaining battery charge deviation function, a charging cost function under dynamic electricity prices, a charging robot moving distance function, and a charging power function; at least one charging request includes the number of vehicles, the real-time charge state of each vehicle, and the desired charge state; based on the preset objective function, a target charging scheduling strategy is determined from multiple reference charging scheduling strategies. The second determination module 460 is further configured to: for each reference charging scheduling strategy, determine the remaining battery charge deviation corresponding to the reference charging scheduling strategy according to the remaining battery charge deviation function, the number of vehicles at the scheduling time corresponding to the reference charging scheduling strategy, the real-time charge state of each vehicle, and the desired charge state; determine the charging cost under dynamic electricity prices corresponding to the reference charging scheduling strategy according to the charging cost function under dynamic electricity prices, the electricity price at the scheduling time corresponding to the reference charging scheduling strategy, and the charging power of each charger; determine the moving distance of the charging robot corresponding to the reference charging scheduling strategy according to the charging robot moving distance function, the parking positions of each vehicle at the scheduling time corresponding to the reference charging scheduling strategy, the positions of each charging robot, and the positions of each charger; determine the reference charging power corresponding to the reference charging scheduling strategy according to the charging power function, the predicted departure time of each vehicle at the scheduling time corresponding to the reference charging scheduling strategy, and the charging power of each charger; weight the remaining battery charge deviation, the charging cost under dynamic electricity prices, the moving distance of the charging robot, and the reference charging power to obtain the target value corresponding to the reference charging scheduling strategy; and determine the target charging scheduling strategy whose target value meets the preset conditions from multiple reference charging scheduling strategies.

[0158] In one embodiment, multiple charging requests include the charging power and the charging start time of multiple vehicles; according to the operating states of multiple charging robots, the operating states of multiple chargers, and at least one charging request, multiple candidate charging scheduling strategies are determined. The first determination module 440 is further configured to: obtain real-time environmental information and historical charging data of multiple charging robots; determine the predicted departure time of multiple vehicles according to the real-time environmental information and the historical charging data of multiple charging robots; and determine multiple candidate charging scheduling strategies according to the operating states of multiple charging robots, the operating states of multiple chargers, the predicted departure time of multiple vehicles, the charging power, and the charging start time.

[0159] In one embodiment, according to the real-time environment information and the historical charging data of multiple charging robots, the predicted departure times of multiple vehicles are determined. The first determination module 440 is further configured to: input the real-time environment information and the historical charging data of multiple charging robots into a pre-trained charging demand prediction model. The pre-trained charging demand prediction model includes a long short-term memory network module, an attention mechanism processing module, a multi-channel neural network module, a squeeze-and-excitation network module, and an output module. The long short-term memory network module extracts temporal features from the historical charging data to obtain temporal features. The attention mechanism processing module performs weighted processing on the temporal features of different time steps to obtain attention features. The multi-channel neural network module performs multi-channel processing on the attention features to obtain multi-channel features. The squeeze-and-excitation network module performs enhancement processing on the multi-channel features to obtain enhanced features. The output module performs fully connected processing on the enhanced features to obtain the predicted departure times of the vehicles charged by multiple charging robots.

[0160] Each module in the above scheduling device of the split shared rail-mounted charging robot can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above respective modules.

[0161] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as Figure 5As shown in the figure. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, near field communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a scheduling method for a split shared hanging rail charging robot. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0162] Those skilled in the art can understand that Figure 5 the structure shown in the figure is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0163] In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0164] In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0165] In an embodiment, a computer program product is provided, including a computer program. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0166] 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 for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0167] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile memory 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), magnetoresistive 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 be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., without limitation.

[0168] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, 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, it should be considered as the scope recorded in this application.

[0169] The above-described embodiments merely represent several implementation manners of this application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of this application. It should be noted that for those of ordinary skill in the art, without departing from the concept of this application, several modifications and improvements can still be made, and these all belong to the protection scope of this application. Therefore, the protection scope of this application shall be subject to the appended claims.

Claims

1. A scheduling method for a split shared hanging rail type charging robot, characterized in that, The method includes: Obtaining the operating states of multiple charging robots deployed within a charging station, the operating states of multiple chargers, and at least one charging request; the charging request is used to indicate charging a vehicle at a charging point location; the at least one charging request includes the number of vehicles, the real-time charge state of each vehicle, the desired charge state, the charging power of multiple vehicles, and the charging start time; Obtaining real-time environmental information and historical charging data of multiple charging robots; determining the predicted departure times of multiple vehicles according to the real-time environmental information and the historical charging data of multiple charging robots; determining multiple candidate charging scheduling strategies according to the operating states of multiple charging robots, the operating states of multiple chargers, the predicted departure times of multiple vehicles, the charging power, and the charging start time; Determining multiple reference charging scheduling strategies that meet preset constraint conditions among the multiple candidate charging scheduling strategies; for each reference charging scheduling strategy, determining the remaining power deviation corresponding to the reference charging scheduling strategy according to the remaining power deviation function, the number of vehicles at the scheduling time corresponding to the reference charging scheduling strategy, the real-time charge state and the desired charge state of each vehicle; determining the charging cost under dynamic electricity prices corresponding to the reference charging scheduling strategy according to the charging cost function under dynamic electricity prices, the electricity price at the scheduling time corresponding to the reference charging scheduling strategy, and the charging power of each charger; determining the moving distance of the charging robot corresponding to the reference charging scheduling strategy according to the charging robot moving distance function, the parking positions of each vehicle at the scheduling time corresponding to the reference charging scheduling strategy, the positions of each charging robot, and the positions of each charger; determining the reference charging power corresponding to the reference charging scheduling strategy according to the charging power function, the predicted departure times of each vehicle at the scheduling time corresponding to the reference charging scheduling strategy, and the charging power of each charger; weighting the remaining power deviation, the charging cost under dynamic electricity prices, the moving distance of the charging robot, and the reference charging power to obtain the target value corresponding to the reference charging scheduling strategy; determining the target charging scheduling strategy whose target value meets the preset conditions from the multiple reference charging scheduling strategies; the target charging scheduling strategy includes the target charging robot, the target charger position, and the target charging request to be processed at multiple scheduling times; When the current time matches any scheduling time, controlling the target charging robot at the corresponding scheduling time to move the charger at the corresponding target charger position to the charging point position indicated by the corresponding target charging request, and charging the vehicle at the charging point position.

2. The method according to claim 1, characterized in that, The preset constraint conditions include charge state dynamic constraints, charging power constraints, charger charging condition constraints, conditional risk constraints, and charging robot scheduling related constraints.

3. The method according to claim 1, wherein The determining the predicted departure times of multiple vehicles according to the real-time environmental information and the historical charging data of multiple charging robots includes: Input the real-time environment information and the historical charging data of multiple charging robots into a pre-trained charging demand prediction model, where the pre-trained charging demand prediction model consists of a long short-term memory network module, an attention mechanism processing module, a multi-channel neural network module, a squeeze-and-excitation network module, and an output module; The long short-term memory network module extracts temporal features from the historical charging data to obtain temporal features. The attention mechanism processing module performs weighted processing on the temporal features of different time steps to obtain attention features. The multi-channel neural network module performs multi-channel processing on the attention features to obtain multi-channel features. The squeeze-and-excitation network module performs enhancement processing on the multi-channel features to obtain enhanced features. The output module performs fully connected processing on the enhanced features to obtain the predicted departure times of the vehicles charged by multiple charging robots.

4. A scheduling device for a split-type shared hanging-rail charging robot, characterized in that, The device includes: An acquisition module, configured to acquire the operating states of multiple charging robots deployed in a charging station, the operating states of multiple chargers, and at least one charging request; the charging request is used to indicate charging of a vehicle at a charging point location; the at least one charging request includes the number of vehicles, the real-time charge state of each vehicle, the desired charge state, the charging power of multiple vehicles, and the charging start time; A first determination module, configured to acquire real-time environment information and historical charging data of multiple charging robots; determine the predicted departure times of multiple vehicles according to the real-time environment information and the historical charging data of multiple charging robots; determine multiple candidate charging scheduling strategies according to the operating states of multiple charging robots, the operating states of multiple chargers, the predicted departure times of multiple vehicles, the charging power, and the charging start time; A second determination module, configured to determine multiple reference charging scheduling policies that meet preset constraint conditions from multiple candidate charging scheduling policies; for each reference charging scheduling policy, determine the remaining power deviation corresponding to the reference charging scheduling policy according to the remaining power deviation function, the number of vehicles at the scheduling moment corresponding to the reference charging scheduling policy, the real-time charge state and the desired charge state of each vehicle; determine the charging cost under dynamic electricity prices corresponding to the reference charging scheduling policy according to the charging cost function under dynamic electricity prices, the electricity price at the scheduling moment corresponding to the reference charging scheduling policy, and the charging power of each charger; determine the moving distance of the charging robot corresponding to the reference charging scheduling policy according to the charging robot moving distance function, the parking positions of each vehicle, the positions of each charging robot, and the positions of each charger at the scheduling moment corresponding to the reference charging scheduling policy; determine the reference charging power corresponding to the reference charging scheduling policy according to the charging power function, the predicted departure moments of each vehicle at the scheduling moment corresponding to the reference charging scheduling policy, and the charging power of each charger; weight the remaining power deviation, the charging cost under dynamic electricity prices, the moving distance of the charging robot, and the reference charging power to obtain the target value corresponding to the reference charging scheduling policy; determine the target charging scheduling policy whose target value meets the preset conditions from multiple reference charging scheduling policies; the target charging scheduling policy includes the target charging robot, the target charger position, and the target charging requests to be processed at multiple scheduling moments; A control module, configured to, when the current moment matches any scheduling moment, control the target charging robot at the corresponding scheduling moment to move the charger at the corresponding target charger position to the charging point position indicated by the corresponding target charging request, and charge the vehicle at the charging point position.

5. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 3 are implemented.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 3 are implemented.

7. A computer program product comprising a computer program, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 3 are implemented.

Images