Intelligent charging scheduling system and resource allocation method

Abstract

The invention belongs to the technical field of charging piles, and provides an intelligent charging scheduling system and a resource distribution method, and the method comprises the steps: data collection, energy distribution model prediction, electric pile transportation, energy supply-demand ratio calculation, electric pile movement scheme determination and electric pile recovery. The energy scheduling scheme is generated through the energy demand data, the weather data, the road condition data and the energy distribution model, energy distribution is designed according to historical data and real-time data, and distribution reasonability and accuracy are improved; through energy supply-demand ratio calculation and electric pile movement scheme determination, energy transfer in an emergency situation is realized, and the error-tolerant rate of the system is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of charging piles, and in particular to an intelligent charging scheduling system and a resource allocation method. Background Art

[0002] Mobile charging pile technology has developed rapidly in recent years, mainly in terms of intelligence, modularization and convenience. With the growth of demand for electric vehicles, mobile charging piles have gradually realized functions such as fast battery charging, remote monitoring, and data analysis. Through the cloud platform and APP, users can view the charging status in real time and make reservations. The new mobile charging pile also has more flexible power scheduling and automatic vehicle identification technology, and supports multiple charging interfaces. In addition, based on the Internet of Vehicles technology, some charging piles can interact intelligently with electric vehicles to optimize the charging process and manage energy. Overall, mobile charging piles have shown greater application potential in scenarios such as urban transportation and long-distance travel.

[0003] However, mobile charging pile technology faces some challenges in energy distribution and scheduling. Due to the uncertainty and suddenness of charging demand, how to reasonably allocate limited power resources in real time is a major problem. Summary of the invention

[0004] In order to overcome the deficiencies of the prior art, the purpose of the present invention is to provide an intelligent charging scheduling system and resource allocation method to achieve optimal scheduling and allocation of mobile charging piles.

[0005] To achieve the above object, the present invention provides the following solutions: An intelligent charging scheduling system, comprising: The data collection module is used to collect the user's order information, the weather information of the target city, and the traffic information of the target road section, and obtain energy demand data, weather data, and road condition data; An energy allocation module, used for inputting the energy demand data, the weather data and the road condition data in a dynamic time window into a pre-trained energy allocation model for prediction to obtain an energy scheduling plan; The charging pile transportation module is used to transport the mobile charging pile to the target charging node using the prepared mobile charging vehicle according to the energy scheduling plan, and place the mobile charging pile at the charging pile position of the target charging node; A real-time statistics module, used to calculate the energy supply-demand ratio of each charging node according to the energy demand data; A fast adjustment module, used for determining a charging pile movement plan according to a preset charging pile screening model when the energy supply-demand ratio is lower than a preset normal power supply threshold, and using the mobile charging vehicle to transfer the mobile charging pile corresponding to the charging pile movement plan to a charging node where the energy supply-demand ratio is lower than the preset normal power supply threshold; The charging pile recovery module is used to use the mobile charging vehicle to transport the mobile charging piles whose power levels in the charging nodes within the target range are lower than the normal power threshold back to the charging station for power replenishment when the mobile charging vehicle returns to the charging station.

[0006] Preferably, a smart charging resource allocation method comprises: The user's order information, the target city's weather information, and the target road section's traffic information are collected respectively to obtain the energy demand data, the weather data, and the road condition data; Inputting the energy demand data, the weather data and the road condition data within the dynamic time window into the pre-trained energy allocation model for prediction to obtain the energy scheduling plan; According to the energy scheduling plan, the mobile charging pile is transported to the target charging node by using the prepared mobile charging vehicle, and the mobile charging pile is placed at the charging pile position of the target charging node; Calculating the energy supply-demand ratio of each charging node according to the energy demand data; When the energy supply-demand ratio is lower than a preset normal power supply threshold, a charging pile movement plan is determined according to the preset charging pile screening model, and the mobile charging vehicle is used to transfer the mobile charging pile corresponding to the charging pile movement plan to a charging node where the energy supply-demand ratio is lower than the preset normal power supply threshold; When the mobile charging vehicle returns to the charging power station, the mobile charging piles whose power levels among charging nodes within the target range are lower than a normal power threshold are transported by the mobile charging vehicle back to the charging power station for power replenishment.

[0007] Preferably, the training process of the energy allocation model includes: Collecting operation data of the research area, and dividing the operation data into historical data of the same period and dynamic window data according to the time sequence; the operation data includes: the energy demand data, the weather data and the road condition data; Determine energy shortage data of the study area according to the dynamic window data, and determine the optimal energy deployment plan of the study area using the energy shortage data; Determine the locations of charging nodes in the study area to obtain static features; Build a TFT network including encoder and decoder; Constructing the loss function of the TFT network based on energy gap and energy redundancy; The historical contemporaneous data, the dynamic window data and the static features are used as network inputs, the optimal energy deployment plan is used as network target output, the TFT network is trained using the loss function according to sliding window sampling and early stopping strategy, and the trained energy allocation model is obtained.

[0008] Preferably, according to the energy scheduling scheme, the mobile charging pile is transported to the target charging node by using a prepared mobile charging vehicle, and the mobile charging pile is placed at the charging pile position of the target charging node, including: According to the image recognition algorithm and the laser sensor on the mobile charging vehicle, the mobile charging vehicle is transported back to the charging station by using a camera and a mechanical arm device, and the mobile charging pile is transferred to a preset guide rail module, and the module battery on the mobile charging pile is transferred to the guide rail module by using the mechanical arm device; The guide rail module is used to transport the spare battery with a power ratio of 100% to the target position, the mechanical arm device is used to install the spare battery on the mobile charging pile, and the mechanical arm device is used to place the mobile charging pile on an empty position on the mobile charging vehicle according to the laser sensor; When the number of mobile charging piles brought back to the charging power station by the mobile charging vehicle is less than the full load, after the batteries of all the brought back mobile charging piles are replaced, the mobile charging piles retained by the charging power station are placed in the vacant positions on the mobile charging vehicle by using the mechanical arm device; Determine the target node according to the energy scheduling scheme; The mobile charging vehicle is controlled to reach the target node using laser navigation technology, and the position sensor on the target node and the mechanical arm device are used to fix the mobile charging pile on the mobile charging vehicle in the charging pile placement area of ​​the target node.

[0009] Preferably, the energy supply-demand ratio is calculated as follows: ; in, is the calculated value of the energy supply-demand ratio; is the available power of the i-th mobile charging pile; is the charging efficiency of the i-th mobile charging pile; is the time attenuation coefficient; The transportation time for the replacement charging pile to arrive at the i-th mobile charging pile; is the available time attenuation coefficient; Predicting the available time of the remaining power of the i-th mobile charging pile; is the original predicted power demand; is the weather weight; is the weather influencing factor; is the traffic weight; is the traffic congestion factor; is the vehicle quantity weight; It is the predicted value of the number of charging vehicles in the future time window.

[0010] Preferably, the calculation formula of the electric pile screening model is: ; in, ; Score the screening; They are time weight, busy weight, and power weight respectively; is the round trip time; is the node busyness; The remaining power of the mobile charging pile; is a fixed value.

[0011] Preferably, the training process of the energy allocation model further includes: Freezing the decoder of the energy distribution model during a preset low-peak charging period; The encoder and attention weight of the energy allocation model are adjusted using the newly collected dynamic window data to obtain the energy allocation model after online update.

[0012] Preferably, the historical contemporaneous data, the dynamic window data and the static features are used as network inputs, the optimal energy deployment scheme is used as network target output, and the TFT network is trained using the loss function according to sliding window sampling and early stopping strategy to obtain the trained energy allocation model, including: Standardizing and concatenating the historical contemporaneous data, the dynamic window data, and the static features to obtain an input sequence; Using the gated recurrent unit of the encoder to extract the temporal features of the input sequence to obtain a coded latent state; Performing multi-head self-attention mechanism calculation, residual connection and normalization processing on the encoded hidden state to obtain an encoded output; Using the self-attention mechanism and cross-attention mechanism of the decoder to locally model and interact with the encoded output to obtain a decoded hidden state; Mapping the decoded hidden state using the fully connected layer of the TFT network to obtain a network prediction matrix; The loss function is calculated according to the network prediction matrix to obtain a loss value, and the network parameters of the TFT network are optimized according to the loss value, and the step of "using the gated recurrent unit of the encoder to extract the timing features of the input sequence to obtain the encoded hidden state" is returned to obtain the trained energy allocation model.

[0013] Preferably, the loss function is expressed as: ; in, ; is the calculated value of the loss function; are the first penalty weight and the second penalty weight respectively; for Regularization coefficient; is the energy gap at the tth time step; is the energy redundancy at the tth time step; is the indicative function; is the time window length; are the model parameters of the TFT network.

[0014] Preferably, the detection implementation process of the laser sensor includes: Fixing the laser sensor in the cargo box of the mobile charging vehicle according to a preset placement space layout; Utilizing the laser sensor to emit a detection laser; When the laser detection device corresponding to the laser sensor detects the detection laser, determining the placement state as not placed; When the laser detection device does not detect the detection laser, the placement state is determined as placed.

[0015] The present invention discloses the following technical effects: The present invention provides an intelligent charging scheduling system and resource allocation method, which generates an energy scheduling plan through energy demand data, weather data, road condition data and an energy allocation model, solves the problem that the prior art has poor effects in energy scheduling and allocation, and realizes the design of energy allocation based on historical data and real-time data; by calculating the energy supply-demand ratio and determining the charging pile movement plan, solves the problem that the prior art has poor ability to deal with emergencies, and realizes energy transfer in emergency situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0017] Figure 1 A schematic diagram of an intelligent charging scheduling system provided by an embodiment of the present invention; Figure 2 A schematic diagram of a smart charging resource allocation process provided by an embodiment of the present invention; Figure 3 A schematic diagram of the energy allocation model training process provided by an embodiment of the present invention; Figure 4 A schematic diagram of the transportation process of the electric pile provided in an embodiment of the present invention; Figure 5 A schematic diagram of a TFT network iteration process provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] The purpose of the present invention is to provide an intelligent charging scheduling system and resource allocation method to achieve optimal scheduling and allocation of mobile charging piles.

[0020] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0021] Figure 1 A schematic diagram of an intelligent charging scheduling system provided by an embodiment of the present invention, such as Figure 1 As shown, the present invention provides an intelligent charging scheduling system, comprising: The data collection module is used to collect the user's order information, the weather information of the target city, and the traffic information of the target road section, and obtain energy demand data, weather data, and road condition data; The energy allocation module is used to input the energy demand data, weather data and road condition data in the dynamic time window into the pre-trained energy allocation model for prediction and obtain the energy scheduling plan; The charging pile transportation module is used to transport the mobile charging pile to the target charging node using the prepared mobile charging vehicle according to the energy scheduling plan, and place the mobile charging pile at the charging pile position of the target charging node; A real-time statistics module is used to calculate the energy supply-demand ratio of each charging node based on energy demand data; A fast adjustment module is used to determine a charging pile movement plan according to a preset charging pile screening model when the energy supply-demand ratio is lower than a preset normal power supply threshold, and use a mobile charging vehicle to transfer the mobile charging pile corresponding to the charging pile movement plan to a charging node where the energy supply-demand ratio is lower than the preset normal power supply threshold; The charging pile recovery module is used to transport the mobile charging piles whose power levels in the charging nodes within the target range are lower than the normal power threshold back to the charging station for power replenishment when the mobile charging vehicle returns to the charging station.

[0022] refer to Figure 2 , a smart charging resource allocation method, comprising: Step 100: Collect the user's order information, the target city's weather information, and the target road section's traffic information to obtain energy demand data, weather data, and road condition data; Step 200: inputting energy demand data, weather data and road condition data within the dynamic time window into a pre-trained energy allocation model for prediction to obtain an energy scheduling plan; Step 300: transporting the mobile charging pile to the target charging node using the prepared mobile charging vehicle according to the energy scheduling plan, and placing the mobile charging pile at the charging pile position of the target charging node; Step 400: Calculate the energy supply-demand ratio of each charging node according to the energy demand data; Step 500: When the energy supply-demand ratio is lower than a preset normal power supply threshold, a charging pile movement plan is determined according to a preset charging pile screening model, and a mobile charging vehicle is used to transfer a mobile charging pile corresponding to the charging pile movement plan to a charging node where the energy supply-demand ratio is lower than a preset normal power supply threshold; Step 600: When the mobile charging vehicle returns to the charging station, the mobile charging vehicle is used to transport the mobile charging piles in the charging nodes within the target range whose power levels are lower than the normal power threshold back to the charging station for power replenishment.

[0023] refer to Figure 3 ,The training process of the energy allocation model includes: Step 201: Collecting operation data of the research area, and dividing the operation data into historical data and dynamic window data according to the time sequence; the operation data includes: energy demand data, weather data and road condition data; Step 202: determining energy shortage data of the study area according to the dynamic window data, and determining the optimal energy deployment plan of the study area using the energy shortage data; Step 203: Determine the locations of charging nodes in the study area and obtain static features; Step 204: construct a TFT network including an encoder and a decoder; Step 205: constructing a loss function of the TFT network based on energy gap and energy redundancy; Step 206: Using historical data from the same period, dynamic window data, and static features as network inputs, and the optimal energy deployment plan as the network target output, the TFT network is trained using a loss function according to sliding window sampling and early stopping strategies to obtain a trained energy allocation model.

[0024] refer to Figure 4 , according to the energy dispatching plan, the mobile charging pile is transported to the target charging node by using the prepared mobile charging vehicle, and the mobile charging pile is placed at the charging pile position of the target charging node, including: Step 301: Using a camera and a robotic arm device according to an image recognition algorithm and a laser sensor on the mobile charging vehicle, the mobile charging vehicle is transported back to the mobile charging pile of the charging power station and transferred to a preset guide rail module, and the modular battery on the mobile charging pile is transferred to the guide rail module using a robotic arm device; Step 302: Use the guide rail module to transport the spare battery with a power ratio of 100% to the target location, use the robotic arm device to install the spare battery on the mobile charging pile, and use the robotic arm device to place the mobile charging pile on an empty position on the mobile charging vehicle according to the laser sensor; Step 303: When the number of mobile charging piles transported back to the charging station by the mobile charging vehicle is less than the full load, after the batteries of all the mobile charging piles transported back are replaced, the mobile charging piles retained in the charging station are placed in the vacant positions on the mobile charging vehicle using a robotic arm device; Step 304: Determine the target node according to the energy scheduling plan; Step 305: Use laser navigation technology to control the mobile charging vehicle to reach the target node, and use the position sensor and mechanical arm device on the target node to fix the mobile charging pile on the mobile charging vehicle in the charging pile placement area of ​​the target node.

[0025] Furthermore, the energy supply-demand ratio is calculated as: ; in, is the calculated value of the energy supply-demand ratio; is the available power of the i-th mobile charging pile; is the charging efficiency of the i-th mobile charging pile; is the time attenuation coefficient; The transportation time for the replacement charging pile to arrive at the i-th mobile charging pile; is the available time attenuation coefficient; Predicting the available time of the remaining power of the i-th mobile charging pile; is the original predicted power demand; is the weather weight; is the weather influencing factor; is the traffic weight; is the traffic congestion factor; is the vehicle quantity weight; It is the predicted value of the number of charging vehicles in the future time window.

[0026] Specifically, the calculation formula of the electric pile screening model is: ; in, ; Score the screening; They are time weight, busy weight, and power weight respectively; is the round trip time; is the node busyness; The remaining power of the mobile charging pile; is a fixed value.

[0027] Preferably, the training process of the energy allocation model further includes: Freeze the decoder of the energy distribution model during the preset low-peak charging period; The encoder and attention weights of the energy allocation model are adjusted using the newly collected dynamic window data to obtain an online updated energy allocation model.

[0028] refer to Figure 5 , using historical data, dynamic window data and static features as network input, and the optimal energy deployment plan as network target output, the TFT network is trained using the loss function according to the sliding window sampling and early stopping strategy to obtain the trained energy allocation model, including: Step 20601: standardize and concatenate historical data of the same period, dynamic window data, and static features to obtain an input sequence; Step 20602: Use the gated recurrent unit of the encoder to extract the temporal features of the input sequence to obtain the encoded latent state; Step 20603: Perform multi-head self-attention mechanism calculation, residual connection and normalization processing on the encoded hidden state to obtain the encoded output; Step 20604: Use the decoder's self-attention mechanism and cross-attention mechanism to locally model and interact with the encoded output to obtain a decoded hidden state; Step 20605: Map the decoded hidden state using the fully connected layer of the TFT network to obtain a network prediction matrix; Step 20606: Calculate the loss function according to the network prediction matrix to obtain the loss value, and optimize the network parameters of the TFT network according to the loss value, and return to the step "Use the encoder's gated recurrent unit to extract the time series features of the input sequence to obtain the encoded hidden state" to obtain the trained energy allocation model.

[0029] Specifically, the loss function is expressed as: ; in, ; is the calculated value of the loss function; are the first penalty weight and the second penalty weight respectively; for Regularization coefficient; is the energy gap at the tth time step; is the energy redundancy at the tth time step; is the indicative function; is the time window length; are the model parameters of the TFT network.

[0030] Preferably, the detection implementation process of the laser sensor includes: Fix the laser sensor in the cargo box of the mobile charging vehicle according to the preset placement space layout; Utilize a laser sensor to emit a detection laser; When the laser detection device corresponding to the laser sensor detects the detection laser, the placement state is determined as not placed; When the laser detection device does not detect the detection laser, the placement state is determined as placed.

[0031] Specifically, historical contemporaneous data: select data from the same time period in the past (such as the same period of the previous month. In order to ensure the stability of the model, the time interval is less than 1 year) to capture periodic patterns; dynamic window data: extract recent (1 hour or 15 minutes) real-time data to reflect current dynamic changes.

[0032] Furthermore, energy gap: demand > supply; energy redundancy: supply > demand.

[0033] Preferably, the loss function includes three items: energy gap item, energy redundancy item, and regularization item; only one of the energy gap item and energy redundancy item is retained, and the specific retention is determined by the indicative function, and the value is 1 when the condition is met, otherwise it is 0. This embodiment takes into account that energy shortage has a more serious impact on the user's experience than energy redundancy. When designing the loss function, a weight greater than the weight of the energy redundancy item is used as the weight of the energy gap item to give priority to reducing power shortages. In addition, the regularization item is used to avoid overfitting of parameters during training.

[0034] Specifically, the charging pile recycling and battery replacement process is as follows: 1) Image recognition and laser detection: After the mobile charging vehicle returns to the charging station, it uses the on-board camera to capture images of the interior of the cargo box and uses image recognition algorithms (such as the YOLO model based on deep learning) to identify the location of the mobile charging pile that needs to replace the battery. The laser sensor installed in the cargo box emits a detection laser beam. If the laser receiving end is not blocked (the laser is detected), it is determined that the charging pile is not in place; conversely, if the laser is blocked, it is determined that the charging pile is fixed.

[0035] 2) Robotic arm operation: Based on the recognition results, the robot arm grabs the unfixed charging pile and transfers it to the preset guide rail module. The guide rail module adopts a slide rail design, which supports horizontal and vertical movement to ensure the precise positioning of the charging pile.

[0036] 3) Battery replacement process: The robot arm removes the modular battery from the charging pile and transports it to the battery recycling area of ​​the charging station through the rail module. The robot arm grabs the new battery and installs it on the charging pile. The laser sensor verifies the installation status in real time to ensure that the battery contact points are fully connected.

[0037] Furthermore, the loading of the charging vehicle is optimized. If the mobile charging vehicle is not fully loaded when it returns, the robotic arm will add the fully charged charging piles reserved in the charging station to the vacant position of the cargo box. The cargo box adopts a honeycomb arrangement design, and the laser sensor monitors the vacant position in real time. The robotic arm completes the loading according to the optimal path planning.

[0038] Optimally, target node navigation and charging pile deployment. Path planning and navigation: Laser navigation technology: The mobile charging vehicle scans the surrounding environment through the on-board LiDAR (laser radar), and generates a navigation path in real time in combination with a high-precision map. Dynamic obstacle avoidance: If an obstacle is detected, the path planning algorithm automatically adjusts the route to ensure that the target charging node is reached on time.

[0039] Furthermore, the charging piles are precisely placed. Position sensor calibration: RFID tags or infrared beacons are embedded in the charging pile placement area of ​​the target charging node, and the mobile charging vehicle identifies the tag location through the on-board sensor. Robotic arm fixed operation: After the robotic arm grabs the charging pile from the cargo box, it adjusts the angle through the six-axis freedom, aligns the charging pile base with the card slot in the node placement area, and detects the embedded state of the card slot through the pressure sensor to ensure that the charging pile is firmly installed. If the charging pile is a movable device, after placing it at the target position, the moving wheels of the charging pile are controlled to retract to increase the contact area between the charging pile and the ground.

[0040] Optionally, if the mobile charging vehicle is delayed due to traffic congestion or mechanical failure, the system automatically triggers priority adjustment and allocates charging pile resources to nodes with urgent needs. If the battery installation fails (such as poor contact), the robotic arm automatically retries 3 times. If it still fails, an alarm is triggered and manual intervention is required.

[0041] The beneficial effects of the present invention are as follows: The present invention generates an energy dispatching plan through energy demand data, weather data, road condition data and an energy distribution model, realizes the design of energy distribution according to historical data and real-time data, and improves the rationality and accuracy of distribution; through the calculation of energy supply-demand ratio and the determination of charging pile movement plan, energy transfer in emergency situations is realized, and the fault tolerance of the system is improved.

[0042] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0043] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. An intelligent charging scheduling system, characterized in that: include: The data collection module is used to collect the user's order information, the weather information of the target city, and the traffic information of the target road section, and obtain energy demand data, weather data, and road condition data; An energy allocation module, used for inputting the energy demand data, the weather data and the road condition data in a dynamic time window into a pre-trained energy allocation model for prediction to obtain an energy scheduling plan; The charging pile transportation module is used to transport the mobile charging pile to the target charging node using the prepared mobile charging vehicle according to the energy scheduling plan, and place the mobile charging pile at the charging pile position of the target charging node; A real-time statistics module, used to calculate the energy supply-demand ratio of each charging node according to the energy demand data; A fast adjustment module, used for determining a charging pile movement plan according to a preset charging pile screening model when the energy supply-demand ratio is lower than a preset normal power supply threshold, and using the mobile charging vehicle to transfer the mobile charging pile corresponding to the charging pile movement plan to a charging node where the energy supply-demand ratio is lower than the preset normal power supply threshold; The charging pile recovery module is used to use the mobile charging vehicle to transport the mobile charging piles whose power levels in the charging nodes within the target range are lower than the normal power threshold back to the charging station for power replenishment when the mobile charging vehicle returns to the charging station.

2. A smart charging resource allocation method, characterized in that: Applied to the intelligent charging scheduling system of claim 1, the method comprising: The user's order information, the target city's weather information, and the target road section's traffic information are collected respectively to obtain the energy demand data, the weather data, and the road condition data; Inputting the energy demand data, the weather data and the road condition data within the dynamic time window into the pre-trained energy allocation model for prediction to obtain the energy scheduling plan; According to the energy scheduling plan, the mobile charging pile is transported to the target charging node by using the prepared mobile charging vehicle, and the mobile charging pile is placed at the charging pile position of the target charging node; Calculating the energy supply-demand ratio of each charging node according to the energy demand data; When the energy supply-demand ratio is lower than a preset normal power supply threshold, a charging pile movement plan is determined according to the preset charging pile screening model, and the mobile charging vehicle is used to transfer the mobile charging pile corresponding to the charging pile movement plan to a charging node where the energy supply-demand ratio is lower than the preset normal power supply threshold; When the mobile charging vehicle returns to the charging power station, the mobile charging piles whose power levels among charging nodes within the target range are lower than a normal power threshold are transported by the mobile charging vehicle back to the charging power station for power replenishment.

3. The intelligent charging resource allocation method according to claim 2, characterized in that: The training process of the energy allocation model includes: Collecting operation data of the research area, and dividing the operation data into historical data of the same period and dynamic window data according to the time sequence; the operation data includes: the energy demand data, the weather data and the road condition data; Determine energy shortage data of the study area according to the dynamic window data, and determine the optimal energy deployment plan of the study area using the energy shortage data; Determine the locations of charging nodes in the study area to obtain static features; Build a TFT network including encoder and decoder; Constructing the loss function of the TFT network based on energy gap and energy redundancy; The historical contemporaneous data, the dynamic window data and the static features are used as network inputs, the optimal energy deployment plan is used as network target output, the TFT network is trained using the loss function according to sliding window sampling and early stopping strategy, and the trained energy allocation model is obtained.

4. The intelligent charging resource allocation method according to claim 2, characterized in that: According to the energy dispatching scheme, a mobile charging pile is transported to a target charging node by using a prepared mobile charging vehicle, and the mobile charging pile is placed at the charging pile position of the target charging node, including: According to the image recognition algorithm and the laser sensor on the mobile charging vehicle, the mobile charging vehicle is transported back to the charging station by using a camera and a mechanical arm device, and the mobile charging pile is transferred to a preset guide rail module, and the module battery on the mobile charging pile is transferred to the guide rail module by using the mechanical arm device; The guide rail module is used to transport the spare battery with a power ratio of 100% to the target position, the mechanical arm device is used to install the spare battery on the mobile charging pile, and the mechanical arm device is used to place the mobile charging pile on an empty position on the mobile charging vehicle according to the laser sensor; When the number of mobile charging piles brought back to the charging power station by the mobile charging vehicle is less than the full load, after the batteries of all the brought back mobile charging piles are replaced, the mobile charging piles retained by the charging power station are placed in the vacant positions on the mobile charging vehicle by using the mechanical arm device; Determine the target node according to the energy scheduling scheme; The mobile charging vehicle is controlled to reach the target node using laser navigation technology, and the position sensor on the target node and the mechanical arm device are used to fix the mobile charging pile on the mobile charging vehicle in the charging pile placement area of ​​the target node.

5. The intelligent charging resource allocation method according to claim 2, characterized in that: The energy supply-demand ratio is calculated as follows: ; in, is the calculated value of the energy supply-demand ratio; is the available power of the i-th mobile charging pile; is the charging efficiency of the i-th mobile charging pile; is the time attenuation coefficient; The transportation time for the replacement charging pile to arrive at the i-th mobile charging pile; is the available time attenuation coefficient; Predicting the available time of the remaining power of the i-th mobile charging pile; is the original predicted power demand; is the weather weight; is the weather influencing factor; is the traffic weight; is the traffic congestion factor; is the vehicle quantity weight; It is the predicted value of the number of charging vehicles in the future time window.

6. The intelligent charging resource allocation method according to claim 2, characterized in that: The calculation formula of the electric pile screening model is: ; in, ; Score the screening; They are time weight, busy weight, and power weight respectively; is the round trip time; is the node busyness; The remaining power of the mobile charging pile; is a fixed value.

7. The intelligent charging resource allocation method according to claim 3, characterized in that: The training process of the energy allocation model further includes: Freezing the decoder of the energy distribution model during a preset low-peak charging period; The encoder and attention weight of the energy allocation model are adjusted using the newly collected dynamic window data to obtain the energy allocation model after online update.

8. The intelligent charging resource allocation method according to claim 3, characterized in that: The historical data of the same period, the dynamic window data and the static features are used as network inputs, the optimal energy deployment scheme is used as network target output, and the TFT network is trained using the loss function according to sliding window sampling and early stopping strategy to obtain the trained energy allocation model, including: Standardizing and concatenating the historical contemporaneous data, the dynamic window data, and the static features to obtain an input sequence; Using the gated recurrent unit of the encoder to extract the temporal features of the input sequence to obtain a coded latent state; Performing multi-head self-attention mechanism calculation, residual connection and normalization processing on the encoded hidden state to obtain an encoded output; Using the self-attention mechanism and cross-attention mechanism of the decoder to locally model and interact with the encoded output to obtain a decoded hidden state; Mapping the decoded hidden state using the fully connected layer of the TFT network to obtain a network prediction matrix; The loss function is calculated according to the network prediction matrix to obtain a loss value, and the network parameters of the TFT network are optimized according to the loss value, and the step of "using the gated recurrent unit of the encoder to extract the time series features of the input sequence to obtain the encoded hidden state" is returned to obtain the trained energy allocation model.

9. The intelligent charging resource allocation method according to claim 3, characterized in that: The expression of the loss function is: ; in, ; is the calculated value of the loss function; are the first penalty weight and the second penalty weight respectively; for Regularization coefficient; is the energy gap at the tth time step; is the energy redundancy at the tth time step; is the indicative function; is the time window length; are the model parameters of the TFT network.

10. The intelligent charging resource allocation method according to claim 4, characterized in that: The detection implementation process of the laser sensor includes: Fixing the laser sensor in the cargo box of the mobile charging vehicle according to a preset placement space layout; Utilizing the laser sensor to emit a detection laser; When the laser detection device corresponding to the laser sensor detects the detection laser, determining the placement state as not placed; When the laser detection device does not detect the detection laser, the placement state is determined as placed.

Images