Charging station energy management method

Abstract

The invention belongs to the technical field of power station energy management, and provides a charging station energy management method, which comprises the steps of electric pile data acquisition, to-be-distributed request data acquisition, electric pile distribution scheme generation, energy supply and demand state determination, user guidance, mobile charging pile recovery, common charging of a photovoltaic panel and a power grid, independent charging of the power grid and battery replacement in a peak period. Through the energy management model, the optimal mobile charging pile is allocated to the user, the utilization rate of the charging pile is improved, and the waiting time of the user is shortened; the charging modes under different working conditions are realized through the energy supply and demand state and the environment illumination intensity, and the operation cost is reduced; and the battery is replaced in the peak period of power utilization, so that the energy supplement efficiency of the mobile charging pile is further improved, and the power shortage pressure of the charging station in the peak period is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of power station energy management, and in particular to a charging station energy management method. Background Art

[0002] Charging station energy management technology has developed rapidly with the large-scale application of electric vehicles and the low-carbon transformation of energy systems. It aims to solve the contradiction between the surge in charging demand and the stability, economy and sustainability of the power grid through multi-dimensional collaborative optimization. Its core background technology covers three aspects: First, the collaborative challenges of infrastructure and power grid, including local power grid overload caused by large-scale centralized charging, peak-to-valley electricity price-guided peak-shifting charging mechanism, and charging stations participating in power grid demand response as flexible loads; second, distributed energy integration, by configuring renewable energy such as photovoltaics and wind power and energy storage systems, building an integrated "light storage and charging" microgrid to improve green electricity absorption capacity and power supply reliability; third, intelligent management and control system, relying on the Internet of Things, 5G communication and AI algorithms to achieve dynamic scheduling, such as orderly charging based on user behavior prediction, V2G bidirectional charging and discharging to adjust the power grid frequency, and using optimization models such as reinforcement learning to balance costs, carbon emissions and user experience. In addition, power electronics technology has improved energy conversion efficiency, and the policy side has promoted the implementation of technology through grid connection regulations and carbon trading mechanisms.

[0003] However, existing charging station energy management technologies generally have problems such as delayed dynamic response, fragmented multi-objective optimization, and low automation levels. Specifically, they are unable to adapt to real-time changing queue situations and dynamic user needs; real-time data does not effectively drive dynamic scheduling and still relies on manual intervention. There is a lack of time series analysis and pattern mining of historical data, and future load trends cannot be predicted; battery replacement efficiency is slow, and other problems. Summary of the invention

[0004] In order to overcome the deficiencies of the prior art, an object of the present invention is to provide a charging station energy management method to shorten the user's waiting time and improve the utilization efficiency of mobile charging piles.

[0005] To achieve the above object, the present invention provides the following solutions: A charging station energy management method, comprising: Collect the power information of each mobile charging pile in all charging stations to obtain the charging pile data; Collect users' electricity applications and reservations to obtain request data to be allocated; Inputting the electric pile data and the request data to be allocated into a pre-trained energy management model to generate a plan, thereby obtaining an electric pile allocation plan; According to the electric pile data, statistics are made on the proportion of the mobile charging piles in use in each of the charging piles to obtain the energy supply and demand status; Determine the mobile charging pile in the charging pile allocation plan as the charging pile to be operated, and guide the user to the charging pile to be operated for charging or provide the target charging pile location information of the charging pile to be operated to the user through the mobile terminal; Using a mobile charging vehicle to transport the mobile charging piles in all the charging stations whose power levels are lower than a normal power threshold back to the charging base; When the ambient light intensity exceeds a preset intensity benchmark and the energy supply and demand state is in a low-peak period, the mobile charging pile is charged by using the power grid and the photovoltaic panels in the charging base; When the ambient light intensity is lower than a preset intensity benchmark or the energy supply and demand state is at a peak period, the mobile charging pile is charged using the power grid; When the energy supply and demand status is during the peak period of electricity consumption, if the proportion of the mobile charging piles in the charging station with power below the normal power threshold exceeds the warning ratio, the spare batteries with 100% power in the charging base are transported to the charging station by the mobile charging vehicle, and the battery replacement equipment on the mobile charging vehicle is used to replace the spare batteries with the mobile charging piles with power below the normal power threshold.

[0006] Preferably, the charging pile data includes: power data, estimated power consumption of current vehicle charging, number of vehicles in queue, scheduled power consumption of vehicles in queue, charging pile location data, charging type data, real-time status, rates and historical utilization.

[0007] Preferably, the battery replacement device comprises: a mechanical claw, a mechanical screwdriver, a camera, an upper guide rail, a lower guide rail and a magnetic suction plate; The upper guide rail is arranged on the roof of the mobile charging vehicle; the mechanical claw and the mechanical screwdriver are respectively arranged on the upper guide rail; the lower guide rail is arranged on the bottom side of the cargo box of the mobile charging vehicle; and the camera is fixed on the top inner side of the cargo box.

[0008] Preferably, when the mobile charging pile adopts a ternary lithium battery, the normal power threshold is 20% to 80%; when the mobile charging pile adopts a lithium iron phosphate battery, the normal power threshold is 20% to 90%.

[0009] Preferably, the calculation formula of the preset strength reference is: ; in, is the preset strength reference; is the rated charging power of a single mobile charging pile; is the energy conversion efficiency of the photovoltaic panel; is the effective lighting area of ​​the photovoltaic panel; is the loss coefficient.

[0010] Preferably, the request data to be allocated includes: reservation time, reservation power consumption, user location data, charging type requirement, battery capacity, priority data and waiting tolerance data.

[0011] Preferably, when the energy supply and demand state is at a peak period of electricity consumption, if the proportion of the mobile charging piles in the charging station whose power is lower than the normal power threshold exceeds the warning ratio, the spare batteries with a power ratio of 100% in the charging base are transported to the charging station by the mobile charging vehicle, and the spare batteries are replaced with the mobile charging piles whose power is lower than the normal power threshold by the battery replacement equipment on the mobile charging vehicle, including: Using the camera to collect image data, and using an object recognition algorithm to identify the image data, to obtain spatial position information of the mobile charging pile whose battery is to be replaced; Moving the mechanical claw to a position where the upper guide rail is closest to the mobile charging pile of the battery to be replaced according to the spatial position information; Using a laser sensor to locate the grooves on both sides of the mobile charging pile, and using the mechanical claw to transfer the mobile charging pile to the replacement station of the lower guide rail through the grooves; Using an object recognition algorithm to detect the fixing screws on the back cover of the mobile charging pile to obtain screw placement information; Remove the fixing screws on the back cover using a mechanical screwdriver according to the screw placement information; Using the magnetic plate to transfer the back cover to a temporary storage area; The camera uses an object recognition algorithm to detect the battery to be replaced in the mobile charging pile to obtain battery placement information; Using the mechanical claw to transfer the battery to be replaced to the recovery area of ​​the lower rail according to the battery placement information, and installing the prepared spare battery into the mobile charging pile; After the backup battery is installed, the rear cover is installed on the mobile charging pile using the mechanical screwdriver, and the mobile charging pile is transferred to its original position using the mechanical claw.

[0012] Preferably, the training process of the energy management model includes: Collect the electric pile data and the request data to be allocated of the target research power station, and reversely formulate an electric pile allocation plan that meets each stage based on the electric pile data and the request data to be allocated; The charging pile data is standardized using a Z-Score formula; Performing one-hot encoding on the charging type data and the real-time status to obtain category features; Performing Euclidean distance calculation based on the electric pile location data and the user location data to obtain location features; Standardizing the request data to be allocated by using Min-Max; Build an original model with a dual-tower encoder and criss-cross attention mechanism; Construct loss function; Encoding the standardized electric pile data, the category features, and the position features using the electric pile encoding tower of the original model to obtain an electric pile embedding vector; Encoding the standardized request data to be allocated using the request encoding tower of the original model to obtain a request embedding vector; Taking the request embedding vector as Query and the electric pile embedding vector as Key and Value, the attention weight is calculated through the cross attention mechanism to obtain the context vector; Using the mask layer of the original model to perform hard constraints and dynamic masking on the context vector to obtain a mask output; Mapping and probability distribution calculation of the mask output are performed using the fully connected layer and Softmax of the original model to obtain a distribution matrix; Calculating the loss function according to the allocation matrix and the established electric pile allocation plan to obtain a predicted loss value; The original model is optimized using an optimizer according to the predicted loss value, and the process returns to the step of "using the electric pile encoding tower of the original model to encode the standardized electric pile data, the category features and the position features to obtain an electric pile embedding vector" to obtain the trained energy management model.

[0013] Preferably, the mobile charging pile in the charging pile allocation scheme is determined as the charging pile to be operated, and the user is guided to the charging pile to be operated for charging or the target charging pile location information of the charging pile to be operated is provided to the user through the mobile terminal, including: The user location data and the target electric pole location information are input into the navigation software to obtain a travel route, and the travel route is updated on the user's mobile terminal.

[0014] Preferably, the loss function is expressed as: ; in, is the calculated value of the loss function; is the number of requests; is the number of charging piles; is the priority weight; is a dynamically generated mask; is the true label; To predict the probability of success; is the balance coefficient; is the historical utilization variance.

[0015] The present invention discloses the following technical effects: The present invention provides a charging station energy management method. Through the energy management model, the problem of unreasonable plan formulation in the prior art when responding to dynamic user needs is solved, and the optimal mobile charging pile is allocated to the user; through the energy supply and demand status and the ambient light intensity, the problem of low charging efficiency caused by the single energy replenishment source of conventional charging stations and the simple insertion of photovoltaic panels is solved, and the charging method under different working conditions is realized; by replacing the battery during the peak power consumption period, the problem of long waiting time for users during the peak power consumption period is solved, and the rapid energy replenishment of the mobile charging pile is realized. 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 the energy management process of a charging station provided by an embodiment of the present invention; Figure 2 A schematic diagram of a battery replacement process provided by an embodiment of the present invention; Figure 3 A schematic diagram of the energy management model training process provided by 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 a charging station energy management method to shorten the waiting time of users and improve the utilization efficiency 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 the energy management process of a charging station provided by an embodiment of the present invention is shown in FIG. Figure 1 As shown, the present invention provides a charging station energy management method, comprising: Step 100: Collecting the power information of each mobile charging pile in all charging stations to obtain charging pile data; Step 200: Collect the user's electricity application and electricity reservation to obtain the request data to be allocated; Step 300: inputting the electric pile data and the request data to be allocated into a pre-trained energy management model to generate a plan, thereby obtaining an electric pile allocation plan; Step 400: Count the proportion of mobile charging piles in use in each charging pile according to the charging pile data to obtain the energy supply and demand status; Step 500: determining a mobile charging pile in the charging pile allocation plan as a waiting charging pile, and guiding the user to the waiting charging pile for charging or providing the user with target charging pile location information of the waiting charging pile through a mobile terminal; Step 600: Use a mobile charging vehicle to transport the mobile charging piles in all charging stations whose power levels are lower than the normal power threshold back to the charging base; Step 700: When the ambient light intensity exceeds the preset intensity benchmark and the energy supply and demand state is in the low-peak period, the mobile charging pile is charged by using the power grid and the photovoltaic panels in the charging base; Step 800: When the ambient light intensity is lower than a preset intensity benchmark or the energy supply and demand state is at a peak period, the mobile charging pile is charged using the power grid; Step 900: When the energy supply and demand state is at the peak of electricity consumption, if the proportion of mobile charging piles with power below the normal power threshold in the charging station exceeds the warning ratio, the spare batteries with 100% power ratio in the charging base are transported to the charging station by a mobile charging vehicle, and the battery replacement equipment on the mobile charging vehicle is used to replace the spare batteries with the mobile charging piles with power below the normal power threshold.

[0022] Furthermore, the charging pile data includes: power data, estimated power consumption of current vehicle charging, number of vehicles in queue, scheduled power consumption of vehicles in queue, charging pile location data, charging type data, real-time status, rates and historical utilization.

[0023] Specifically, the battery replacement equipment includes: a mechanical claw, a mechanical screwdriver, a camera, an upper guide rail, a lower guide rail, and a magnetic suction plate; The upper guide rail is arranged on the roof of the mobile charging vehicle; the mechanical claw and the mechanical screwdriver are respectively arranged on the upper guide rail; the lower guide rail is arranged on the bottom side of the cargo box of the mobile charging vehicle; and the camera is fixed on the top inner side of the cargo box.

[0024] Preferably, when the mobile charging pile adopts a ternary lithium battery, the normal power threshold is 20% to 80%; when the mobile charging pile adopts a lithium iron phosphate battery, the normal power threshold is 20% to 90%.

[0025] Furthermore, the calculation formula of the preset strength benchmark is: ; in, is the preset strength reference; is the rated charging power of a single mobile charging pile; is the energy conversion efficiency of the photovoltaic panel; is the effective lighting area of ​​the photovoltaic panel; is the loss coefficient.

[0026] Specifically, the request data to be allocated includes: reservation time, reservation power consumption, user location data, charging type requirements, battery capacity, priority data and waiting tolerance data.

[0027] Furthermore, when the energy supply and demand state is at the peak of electricity consumption, if the proportion of mobile charging piles with power below the normal power threshold in the charging station exceeds the warning ratio, the spare batteries with 100% power in the charging base are transported to the charging station by a mobile charging vehicle, and the spare batteries are replaced with the mobile charging piles with power below the normal power threshold by using the battery replacement equipment on the mobile charging vehicle, including: Step 901: using a camera to collect image data, and using an object recognition algorithm to identify the image data, to obtain spatial position information of a mobile charging pile whose battery is to be replaced; Step 902: Move the mechanical claw to a position where the upper guide rail is closest to the mobile charging pile of the battery to be replaced according to the spatial position information; Step 903: Use a laser sensor to locate the grooves on both sides of the mobile charging pile, and use a mechanical claw to transfer the mobile charging pile to the replacement station of the lower guide rail through the grooves; Step 904: using an object recognition algorithm to detect the fixing screws on the back cover of the mobile charging pile to obtain screw placement information; Step 905: Remove the fixing screws on the back cover using a mechanical screwdriver according to the screw placement information; Step 906: Using a magnetic plate to transfer the back cover to a temporary storage area; Step 907: Using a camera and an object recognition algorithm to detect the battery to be replaced in the mobile charging pile, and obtaining battery placement information; Step 908: Using a mechanical claw to transfer the battery to be replaced to the recovery area of ​​the lower rail according to the battery placement information, and installing the prepared spare battery into the mobile charging pile; Step 909: After the backup battery is installed, use a mechanical screwdriver to install the back cover onto the mobile charging pile, and use a mechanical claw to move the mobile charging pile to its original position.

[0028] Specifically, the training process of the energy management model includes: Step 301: Collect the electric pile data and the request data to be allocated of the target research power station, and reversely formulate the electric pile allocation plan that meets each stage according to the electric pile data and the request data to be allocated; Step 302: Standardize the charging pile data using the Z-Score formula; Step 303: Perform one-hot encoding on the charging type data and the real-time status to obtain category features; Step 304: performing Euclidean distance calculation based on the electric pole location data and the user location data to obtain location features; Step 305: Standardize the request data to be allocated using Min-Max; Step 306: Build an original model with a dual-tower encoder and a cross-attention mechanism; Step 307: construct a loss function; Step 308: Encode the standardized electric pile data, category features, and position features using the electric pile encoding tower of the original model to obtain an electric pile embedding vector; Step 309: Encode the standardized request data to be allocated using the request encoding tower of the original model to obtain a request embedding vector; Step 310: Using the request embedding vector as the query and the electric pile embedding vector as the key and value, the attention weight is calculated through the cross attention mechanism to obtain the context vector; Step 311: Use the mask layer of the original model to perform hard constraints and dynamic masking on the context vector to obtain a mask output; Step 312: Use the fully connected layer and Softmax of the original model to map the mask output and calculate the probability distribution to obtain a distribution matrix; Step 313: Calculate the loss function according to the allocation matrix and the established charging pile allocation plan to obtain a predicted loss value; Step 314: Optimize the original model using the optimizer according to the predicted loss value, and return to the step of "encoding the standardized electric pile data, category features, and position features using the electric pile encoding tower of the original model to obtain an electric pile embedding vector" to obtain a trained energy management model.

[0029] Preferably, the mobile charging pile in the charging pile allocation scheme is determined as the waiting charging pile, and the user is guided to the waiting charging pile for charging or the target charging pile location information of the waiting charging pile is provided to the user through the mobile terminal, including: The user's location data and the target charging station location information are input into the navigation software to obtain the travel route, and the travel route is updated on the user's mobile terminal.

[0030] Specifically, the loss function is expressed as: ; in, is the calculated value of the loss function; is the number of requests; is the number of charging piles; is the priority weight; is a dynamically generated mask; is the true label; To predict the probability of success; is the balance coefficient; is the historical utilization variance.

[0031] Preferably, the charging pile data is preprocessed. Standardization of numerical features: For continuous values ​​such as power, number of queues, rates, and historical utilization, Z-Score standardization (subtracting the mean and dividing by the standard deviation) is used to eliminate dimensional differences. For historical utilization, the time dimension is added: the sliding window mean of the past hour is calculated to capture dynamic changes.

[0032] Furthermore, the category features are encoded. The charging type (such as fast charging / slow charging) and real-time status (idle / occupied / faulty) are encoded using One-Hot to generate a sparse binary vector. The status field is supplemented with "estimated idle time": dynamically calculated based on the current vehicle charging time.

[0033] Optionally, position data processing: combine the longitude and latitude of the charging pile with the longitude and latitude requested by the user, calculate the Euclidean distance or spherical distance (Haversine formula) as a feature, cluster the locations into regions (such as 500-meter grids), and convert them into Embedding codes of region IDs.

[0034] Specifically, request data preprocessing. Time feature processing: split the appointment time into time series features such as hours, days of the week, whether it is a holiday, etc., and use sine / cosine to encode periodicity. Calculate the "difference between the current time and the appointment time" as the urgency indicator.

[0035] Furthermore, the numerical features are normalized: the scheduled power consumption and battery capacity are normalized using Min-Max and scaled to the interval [0, 1]. The waiting tolerance is converted to a numerical type, such as "the longest waiting time acceptable to the user (minutes)".

[0036] Optionally, priority processing: map priorities (such as VIP / ordinary user) to weight values ​​(such as 1.5 and 1.0) for subsequent loss function weighting.

[0037] Specifically, the neural network architecture is implemented. Dual-tower encoder design: 1) Electric pile coding tower: Input layer: receives the preprocessed electric pile feature vector (including standardized values, One-Hot categories, distances, etc.); Hidden layer: Use 3 layers of full connection (e.g. 256, 128, 64 nodes), each layer is followed by ReLU activation and BatchNormalization; Output layer: Generates a 64-dimensional charging pile embedding vector to characterize the static properties and dynamic state of the charging pile.

[0038] 2) Request encoding tower: Input layer: receives request feature vector (time, location, power demand, etc.); Hidden layer: Symmetrical structure with the charging tower (256, 128, 64 nodes), outputting a 64-dimensional request embedding vector.

[0039] Specifically, the cross-attention mechanism: uses the request embedding vector as the query, and the charging pile embedding vector as the key and value; calculates the attention weight: measures the matching degree between the request and each charging pile through dot product or additive attention; outputs the context vector: weighted aggregate charging pile features to enhance the perception of the global charging pile status.

[0040] Optionally, the mask layer is implemented. Hard constraint filtering: Charging type matching: If the request requires fast charging, then the charging piles that do not support fast charging are blocked; Status filtering: exclude charging piles that are "faulty" or "current utilization exceeds 90%"; Waiting time limit: If the total time taken by the vehicles queuing for the charging pile is greater than the user's tolerance time, block the charging pile. Dynamic mask generation: During each batch of inference, a Boolean mask matrix is ​​generated based on the real-time charging pile status to block invalid options.

[0041] Furthermore, the output layer and decision-making: the attention output is mapped to the charging pile matching score through the fully connected layer; Softmax is applied to generate the probability distribution, and the charging pile with the highest probability is selected as the allocation result.

[0042] Specifically, the model training is implemented as follows: input data organization; batch construction: each training sample contains a set of charging pile data and a request to be allocated; positive sample: the charging pile actually allocated to the request is marked as 1, and the others are marked as 0; negative sample: random sampling of unallocated charging piles (a mask needs to be applied to filter invalid items); loss function design. The loss item of high-priority requests is multiplied by a weight (such as 1.5 times) to enhance the accuracy of the model's allocation.

[0043] Furthermore, the optimization strategy is as follows: Optimizer: Use AdamW (Adam with weight decay), and the initial learning rate is set to 0.0003; Learning rate scheduling: Use the cosine annealing strategy to reset the learning rate every 50 epochs to avoid local optimality.

[0044] Optionally, regularization: L2 weight decay (coefficient 0.0001) is used to prevent overfitting. Dropout (probability 0.3) is applied to the embedding and fully connected layers.

[0045] Furthermore, the training process: load the preprocessed charging pile and request datasets, and divide them into training set and verification set in an 8:2 ratio; randomly sample 100 requests and their associated charging pile data in each batch; forward propagate to calculate the matching score, and calculate the loss after applying the dynamic mask; back propagate to update the parameters, and verify the model performance every 100 batches.

[0046] Optionally, lightweight the model: use TensorRT or ONNX to convert the model to a high-performance inference format. Pre-calculate the embedding vectors (features that do not change in real time) for the electric pile encoding tower to reduce the amount of online calculations. Real-time data processing: receive the electric pile status stream data (such as updates every second) through Kafka or RabbitMQ. Request data is stored in Redis cache to ensure low-latency reading. Online inference service: deploy Flask / FastAPI service, receive electric pile and request data, and return the allocation plan. Use GPU to accelerate batch inference and support processing of thousands of requests per second.

[0047] Specifically, the coordinated operation of the robot arm and the guide rail. Integrated design of the robot arm and the guide rail: The upper guide rail and the robot arm of the mobile charging vehicle adopt an integrated structure. The base of the robot arm is driven by a servo motor and can slide horizontally along the upper guide rail. The upper guide rail has a built-in encoder to provide real-time feedback on the position of the robot arm (accuracy ±1mm), ensuring that the movement of the robot arm is synchronized with the positioning of the charging pile.

[0048] Furthermore, the charging pile grabbing process: the robot arm slides along the guide rail to the target charging pile position, locates the grooves on both sides of the charging pile through the laser sensor (accuracy ±2mm), and moves the charging pile as a whole along the guide rail to the battery replacement station after clamping. The upper guide rail only carries the movement and positioning of the charging pile, and the robot arm is responsible for clamping, disassembly, replacement and other operations. The two work together through the central controller to avoid positioning deviation caused by separation.

[0049] Optionally, the adsorption distance between the magnetic plate and the back cover is fixed at 1 cm (calibrated in real time by a laser rangefinder). After adsorption, it is translated along the guide rail to the temporary storage area to avoid collision with the electric pile body.

[0050] Specifically, the battery replacement process: Electric pile fixation and rear cover removal: The mechanical arm clamps the electric pile to the guide rail station, and the bottom buckle automatically locks the electric pile position. The mechanical screwdriver removes the rear cover screws, and after completion, the electromagnet is triggered to absorb the rear cover and remove it.

[0051] Battery replacement operation: The mechanical claw reaches into the charging pile, locates the battery slot through 3D vision, clamps the old battery and pulls it out along the guide rail, and places it in the recycling bin. The spare battery compartment of the mobile charging vehicle pops out a fully charged battery, and the mechanical arm clamps the new battery and aligns it with the slot, inserting the fully charged battery into the charging pile.

[0052] Reset the back cover and return the charging pile to its original position: the magnetic suction plate moves the back cover back to the top of the charging pile, the robotic arm helps to align the screw holes, and the screwdriver tightens the screws.

[0053] The charging pile releases the rail lock, and the robotic arm pushes it back to its original position, and the return accuracy is confirmed through visual inspection of markers.

[0054] Optionally, the object recognition algorithm uses the YOLOv8 network, which takes into account both real-time performance and accuracy, and is suitable for the recognition of objects such as mobile charging piles, screws, and batteries in dynamic environments. Use CSPDarknet53 to extract image features, and combine with PANet for multi-scale feature fusion to improve the detection ability of small objects (such as screws). Use the labeled data to pre-train the YOLOv8 network. In order to ensure the recognition accuracy of the screws, the labeled data contains a large number of images of the screw head shape to enhance the recognition accuracy of the drive slot orientation of the screws on the mobile charging pile, ensuring that the mechanical screwdriver can accurately fit the drive slot.

[0055] The beneficial effects of the present invention are as follows: The present invention realizes the allocation of the best mobile charging pile for users through the energy management model, improves the utilization rate of the charging pile, and reduces the waiting time of users; through the energy supply and demand status and the ambient light intensity, the charging method under different working conditions is realized, and the operating cost is reduced; by replacing the battery during the peak period of electricity consumption, the energy replenishment efficiency of the mobile charging pile is further improved, and the power shortage pressure of the charging station during the peak period is reduced.

[0056] 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.

[0057] 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. A charging station energy management method, characterized in that: include: Collect the power information of each mobile charging pile in all charging stations to obtain the charging pile data; Collect users' electricity applications and reservations to obtain request data to be allocated; Inputting the electric pile data and the request data to be allocated into a pre-trained energy management model to generate a plan, thereby obtaining an electric pile allocation plan; According to the electric pile data, statistics are made on the proportion of the mobile charging piles in use in each of the charging piles to obtain the energy supply and demand status; Determine the mobile charging pile in the charging pile allocation plan as the charging pile to be operated, and guide the user to the charging pile to be operated for charging or provide the target charging pile location information of the charging pile to be operated to the user through the mobile terminal; Using a mobile charging vehicle to transport the mobile charging piles in all the charging stations whose power levels are lower than a normal power threshold back to the charging base; When the ambient light intensity exceeds a preset intensity benchmark and the energy supply and demand state is in a low-peak period, the mobile charging pile is charged by using the power grid and the photovoltaic panels in the charging base; When the ambient light intensity is lower than a preset intensity benchmark or the energy supply and demand state is at a peak period, the mobile charging pile is charged using the power grid; When the energy supply and demand status is during the peak period of electricity consumption, if the proportion of the mobile charging piles in the charging station with power below the normal power threshold exceeds the warning ratio, the spare batteries with 100% power in the charging base are transported to the charging station by the mobile charging vehicle, and the battery replacement equipment on the mobile charging vehicle is used to replace the spare batteries with the mobile charging piles with power below the normal power threshold.

2. A charging station energy management method according to claim 1, characterized in that: The charging pile data includes: power data, estimated power consumption of current vehicle charging, number of vehicles in queue, scheduled power consumption of vehicles in queue, charging pile location data, charging type data, real-time status, rates and historical utilization.

3. A charging station energy management method according to claim 1, characterized in that: The battery replacement equipment includes: a mechanical claw, a mechanical screwdriver, a camera, an upper guide rail, a lower guide rail and a magnetic suction plate; The upper guide rail is arranged on the roof of the mobile charging vehicle; the mechanical claw and the mechanical screwdriver are respectively arranged on the upper guide rail; the lower guide rail is arranged on the bottom side of the cargo box of the mobile charging vehicle; and the camera is fixed on the top inner side of the cargo box.

4. A charging station energy management method according to claim 1, characterized in that: When the mobile charging pile adopts a ternary lithium battery, the normal power threshold is 20% to 80%; when the mobile charging pile adopts a lithium iron phosphate battery, the normal power threshold is 20% to 90%.

5. A charging station energy management method according to claim 1, characterized in that: The calculation formula of the preset strength reference is: ; in, is the preset strength reference; is the rated charging power of a single mobile charging pile; is the energy conversion efficiency of the photovoltaic panel; is the effective lighting area of ​​the photovoltaic panel; is the loss coefficient.

6. A charging station energy management method according to claim 2, characterized in that: The request data to be allocated includes: reservation time, reservation power consumption, user location data, charging type requirement, battery capacity, priority data and waiting tolerance data.

7. A charging station energy management method according to claim 3, characterized in that: When the energy supply and demand state is at a peak period of electricity consumption, if the proportion of the mobile charging piles in the charging station whose power is lower than the normal power threshold exceeds the warning ratio, the spare batteries with a power ratio of 100% in the charging base are transported to the charging station by the mobile charging vehicle, and the spare batteries are replaced with the mobile charging piles whose power is lower than the normal power threshold by the battery replacement equipment on the mobile charging vehicle, including: Using the camera to collect image data, and using an object recognition algorithm to identify the image data, to obtain spatial position information of the mobile charging pile whose battery is to be replaced; Moving the mechanical claw to a position where the upper guide rail is closest to the mobile charging pile of the battery to be replaced according to the spatial position information; Using a laser sensor to locate the grooves on both sides of the mobile charging pile, and using the mechanical claw to transfer the mobile charging pile to the replacement station of the lower guide rail through the grooves; Using an object recognition algorithm to detect the fixing screws on the back cover of the mobile charging pile to obtain screw placement information; Remove the fixing screws on the back cover using a mechanical screwdriver according to the screw placement information; Using the magnetic plate to transfer the back cover to a temporary storage area; The camera uses an object recognition algorithm to detect the battery to be replaced in the mobile charging pile to obtain battery placement information; Using the mechanical claw to transfer the battery to be replaced to the recovery area of ​​the lower rail according to the battery placement information, and installing the prepared spare battery into the mobile charging pile; After the backup battery is installed, the rear cover is installed on the mobile charging pile using the mechanical screwdriver, and the mobile charging pile is transferred to its original position using the mechanical claw.

8. A charging station energy management method according to claim 6, characterized in that: The training process of the energy management model includes: Collect the electric pile data and the request data to be allocated of the target research power station, and reversely formulate an electric pile allocation plan that meets each stage based on the electric pile data and the request data to be allocated; The charging pile data is standardized using a Z-Score formula; Performing one-hot encoding on the charging type data and the real-time status to obtain category features; Performing Euclidean distance calculation based on the electric pile location data and the user location data to obtain location features; Standardizing the request data to be allocated by using Min-Max; Build an original model with a dual-tower encoder and criss-cross attention mechanism; Construct loss function; Encoding the standardized electric pile data, the category features, and the position features using the electric pile encoding tower of the original model to obtain an electric pile embedding vector; Encoding the standardized request data to be allocated using the request encoding tower of the original model to obtain a request embedding vector; Taking the request embedding vector as Query and the electric pile embedding vector as Key and Value, the attention weight is calculated through the cross attention mechanism to obtain the context vector; Using the mask layer of the original model to perform hard constraints and dynamic masking on the context vector to obtain a mask output; Mapping and probability distribution calculation of the mask output are performed using the fully connected layer and Softmax of the original model to obtain a distribution matrix; Calculating the loss function according to the allocation matrix and the established electric pile allocation plan to obtain a predicted loss value; The original model is optimized using an optimizer according to the predicted loss value, and the process returns to step "using the electric pile encoding tower of the original model to encode the standardized electric pile data, the category features and the position features to obtain an electric pile embedding vector" to obtain the trained energy management model.

9. A charging station energy management method according to claim 6, characterized in that: Determining the mobile charging pile in the charging pile allocation plan as the charging pile to be operated, and guiding the user to the charging pile to be operated for charging or providing the target charging pile location information of the charging pile to be operated to the user through the mobile terminal, including: The user location data and the target electric pole location information are input into the navigation software to obtain a travel route, and the travel route is updated on the user's mobile terminal.

10. A charging station energy management method according to claim 8, characterized in that: The expression of the loss function is: ; in, is the calculated value of the loss function; is the number of requests; is the number of charging piles; is the priority weight; is a dynamically generated mask; is the true label; To predict the probability of success; is the balance coefficient; is the historical utilization variance.

Images