Control method and system of mobile charging pile

Abstract

The invention relates to the technical field of mobile charging piles, in particular to a mobile charging pile control method and system, and the method comprises the following steps: S1, charging pile positioning and user demand receiving: obtaining the real-time position information of a mobile charging pile through a GPS; s2, path planning and charging pile movement: controlling a mobile device to drive the charging pile to move to a position designated by a user; s3, charging preparation: performing charging preparation work; s4, electromagnetic interference suppression: suppressing electromagnetic interference; s5, charging and completion: after the charging is completed, disconnecting the power supply, and notifying the user that the charging is completed through the user terminal; s6, dynamic load balancing: monitoring and adjusting the output power of the charging pile in real time; and S7, charging pile returning and data recording: the mobile charging pile returns to an initial position or moves to a standby position according to an instruction of the charging pile control center. According to the invention, efficient scheduling and management of the mobile charging pile are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of mobile charging piles, and in particular to a control method and system for a mobile charging pile. Background Art

[0002] With the popularity of electric vehicles, the demand for charging infrastructure is increasing. Traditional fixed charging piles may not be able to meet the flexible and changeable charging needs in some cases, especially in remote areas or special scenarios. The installation and maintenance costs of fixed charging piles are high and cannot effectively cover all areas. Therefore, mobile charging piles, as a new charging solution, have gradually received attention and research.

[0003] Existing mobile charging piles lack precision and efficiency in scheduling and management, and are often unable to respond to users' charging needs in a timely manner, resulting in long waiting times and poor service quality. In complex electromagnetic environments, electromagnetic interference has a significant impact on the communication and control signals of charging piles. Existing technologies have limited effects in suppressing electromagnetic interference, resulting in unstable system operation and affecting the reliability of the charging process. Traditional load management methods are difficult to predict and adjust the output power of charging piles in real time and accurately, and are unable to effectively balance the loads between multiple charging piles, resulting in unbalanced grid loads and affecting overall charging efficiency and system stability.

[0004] In view of the above problems, the present invention provides a control method for a mobile charging pile. Through the steps of charging pile positioning and user demand reception, path planning and charging pile movement, charging preparation, electromagnetic interference suppression, charging and completion, dynamic load balancing, and charging pile return and data recording, efficient scheduling and management of mobile charging piles are achieved to ensure the stability and reliability of the charging process, while optimizing the efficiency of charging services and user experience. Summary of the invention

[0005] Based on the above objectives, the present invention provides a control method and system for a mobile charging pile.

[0006] A control method for a mobile charging pile comprises the following steps:

[0007] S1, charging pile positioning and user demand reception: obtain the real-time location information of the mobile charging pile through GPS, and send the location information to the charging pile control center, and receive the user's charging demand through the user terminal, which includes charging time, charging amount and charging location;

[0008] S2, path planning and charging pile movement: according to the user's charging needs and the real-time location information of the charging pile, the path planning algorithm is used to calculate the optimal driving route of the mobile charging pile, and the driving route is sent to the charging pile control center. According to the optimal driving route, the charging pile is driven to move to the user's specified location by controlling the mobile device;

[0009] S3, charging preparation: After the mobile charging pile arrives at the designated location, it will prepare for charging, including automatically connecting to the power supply and checking the status of the charging equipment;

[0010] S4, electromagnetic interference suppression: Use adaptive filtering algorithm to process the communication and control signals of the charging pile to suppress electromagnetic interference;

[0011] S5, charging and completion: after confirming that the charging preparation work is completed, start charging the electric vehicle and monitor the charging status in real time. After charging is completed, disconnect the power supply and notify the user through the user terminal that the charging is completed;

[0012] S6, dynamic load balancing: real-time monitoring and adjustment of the output power of the charging pile, dynamically adjusting the charging power according to the status of the electric vehicle battery and the charging demand, and balancing the load between multiple charging piles;

[0013] S7, Charging pile return and data recording: After charging is completed, the mobile charging pile returns to the initial position or moves to the standby position according to the instruction of the charging pile control center, records the relevant data of each charging, including charging time, charging amount and charging cost, and sends the relevant data to the charging pile control center for analysis.

[0014] Furthermore, the path planning and charging pile movement in S2 include:

[0015] S21, optimal route calculation: combining the user's charging demand and the real-time location information of the charging pile, and using the Dijkstra algorithm to calculate the optimal driving route;

[0016] S22, information sending: sending the calculated optimal driving route to the charging pile control center, and the charging pile control center receives the driving route information;

[0017] S23, charging pile movement: according to the optimal driving route, the charging pile is driven to move to the user-specified position by controlling the mobile device (such as the automatic driving system, the path tracking control module, etc.). The mobile device adjusts the driving path in real time based on the received driving route information and the sensor data (such as the lidar, the camera, etc.).

[0018] Furthermore, the electromagnetic interference suppression in S4 includes:

[0019] S41, electromagnetic interference detection: monitor the communication and control signals of the charging pile in real time through the electromagnetic interference detection mechanism to obtain the characteristic information of the electromagnetic interference, including the interference frequency and amplitude;

[0020] S42, adaptive filter initialization: input the acquired electromagnetic interference characteristic information into the adaptive filter, and the adaptive filter dynamically adjusts the filter parameters according to the input signal to suppress the electromagnetic interference;

[0021] S43, filter weight update: using a recursive least squares (RLS) algorithm to update the weight of the adaptive filter;

[0022] S44, signal processing and application: using the signal processed by the adaptive filter for communication and control of the charging pile.

[0023] Furthermore, the electromagnetic interference detection in S41 includes:

[0024] S411, electromagnetic interference detection device installation: an electromagnetic interference detection device is installed in the communication and control circuit of the charging pile, the electromagnetic interference detection device includes an electromagnetic interference sensor and a signal processing unit, and monitors and processes electromagnetic interference signals in real time;

[0025] S412, signal processing unit analysis: The signal processing unit performs spectrum analysis on the electromagnetic interference signal to extract characteristic information of the interference signal. The calculation formula is:

[0026]

[0027] Among them, X(f) is the frequency domain signal, x(t) is the time domain signal, f is the frequency, and t is the time;

[0028] S413, characteristic information transmission: the acquired electromagnetic interference characteristic information is transmitted to the adaptive filter for electromagnetic interference suppression processing.

[0029] Further, the recursive least squares (RLS) algorithm includes:

[0030] Gain vector calculation:

[0031] Where P(n-1) is the covariance matrix in the n-1th iteration, x(n) is the input signal vector in the nth iteration, and λ is the forgetting factor, (0<λ≤1);

[0032] Weight update: w(n)=w(n-1)+K(n)e(n);

[0033] Where w(n) is the filter weight of the nth iteration, K(n) is the gain vector, and e(n) is the current error;

[0034] Covariance matrix update:

[0035] Furthermore, the dynamic load balancing in S6 includes:

[0036] S61, battery status monitoring: real-time monitoring of electric vehicle battery status information, including battery power, battery health status and charging requirements;

[0037] S62, load prediction: based on the battery status information and charging demand, use the load prediction model to predict the real-time load demand of the charging pile;

[0038] S63, dynamically adjusting the output power of the charging pile: based on the predicted load demand and the real-time monitored battery status, calculating the optimal output power of each charging pile, and adjusting the output power of the charging pile in real time;

[0039] S64, balancing the load between charging piles: by real-time monitoring of the load status of the charging piles, when the load of the charging piles is too high, the load is automatically distributed, and the load balancing algorithm is used to optimize the load distribution.

[0040] Furthermore, the load prediction model in S62 adopts a generative adversarial network (GAN) model, and the generative adversarial network (GAN) model includes:

[0041] S621, data acquisition and feature extraction: obtain electric vehicle battery status information (battery power, battery health status) and charging requirements (charging time, charging amount), and extract time series features, including battery power change rate, historical charging records, and environmental factors;

[0042] S622, initialize the generator and discriminator: initialize the weights and biases of the generator G and the discriminator D;

[0043] S623, conditional input: the battery status and charging requirements of the electric vehicle are used as conditional input c, combined with the random noise z input generator;

[0044] S624, loss function definition:

[0045] Discriminator loss function:

[0046]

[0047] Among them, L D is the loss function of the discriminator, L is the true load demand, c is the conditional input (electric vehicle battery status and charging demand), p data is the real data distribution, D(L|c) is the output of the discriminator for the real load demand L under given condition c, z is the random noise vector, p zis the distribution of the noise vector, G(z,c) is the load demand generated by the generator under the given noise vector z and condition c, and D(G(z,c)|c) is the output of the discriminator for the generated load demand G(z,c) under the given condition c;

[0048] Generator loss function:

[0049]

[0050] Among them, L G is the loss function of the generator, p c is the distribution of the conditional input;

[0051] S625, adaptive learning rate adjustment: dynamically adjust the learning rate according to the loss changes during training. The calculation formula is:

[0052]

[0053] Among them, α(t) is the learning rate of the tth iteration, β is the adjustment coefficient, is the rate of change of the loss function;

[0054] S626, training the producer and discriminator: repeat the training process until the loss function converges. The training process is:

[0055] Update the discriminator:

[0056] Update the generator:

[0057] Among them, θ D is the parameter of the discriminator, α D is the learning rate of the discriminator, is the discriminator loss function L D For parameter θ D The gradient of θ G is the parameter of the generator, α G is the learning rate of the generator, is the generator loss function L G For parameter θ G The gradient of

[0058] S627, load prediction: Use the trained generator G to receive the conditional input c and random noise z to generate the predicted load demand

[0059] Furthermore, the dynamically adjusting the output power of the charging pile in S63 includes:

[0060] S631, Initial Output Power Calculation: Obtaining Forecasted Load Demand And the real-time monitored battery status S, according to the current battery power E and charging demand D, calculate the initial output power P of each charging pile init , the calculation formula is:

[0061]

[0062] Where D is the battery charging demand, E is the current power, and T is the expected charging time;

[0063] S632, optimal output power calculation: According to the predicted load demand and the real-time monitored battery status, the output power is adjusted using the PID control algorithm. The calculation formula is:

[0064]

[0065] Among them, P i (t) is the output power of the i-th charging pile at the t-th time, is the error, K p is the proportional gain, K i is the integral gain, K d is the differential gain;

[0066] S633, real-time adjustment of the output power of the charging pile: according to the output power calculated by the PID control algorithm, the output power of each charging pile is adjusted in real time. The calculation formula is:

[0067]

[0068] in, is the output power of the i-th charging pile at the t-th time calculated by the PID control algorithm, and α is the adjustment coefficient.

[0069] Furthermore, balancing the loads between the charging piles in S64 includes:

[0070] S641, real-time monitoring of the load status of the charging pile: real-time monitoring of the load information of each charging pile, including the current output power and load status, and recording the load status of each charging pile to form historical load data;

[0071] S642, detecting excessive load: analyzing the real-time monitored load information, and triggering the load distribution mechanism when it is detected that the load of the charging pile exceeds a preset threshold;

[0072] S643, automatic load distribution: after detecting that the load is too high, automatically distribute the predetermined load to the charging pile with low load;

[0073] S644, optimize load distribution using load balancing algorithm: Use load balancing algorithm to optimize load distribution between charging piles. The calculation formula is:

[0074]

[0075] in, is the load of the i-th charging pile after redistribution, is the load before allocation, ΔP is the total load to be allocated, and N is the number of charging piles with lower load.

[0076] A control system for a mobile charging pile, used to implement the above-mentioned control method for a mobile charging pile, includes the following modules:

[0077] Charging pile positioning and user demand receiving module: obtain the real-time location information of the mobile charging pile, send the location information to the charging pile control center, and receive the user's charging demand;

[0078] Path planning and charging pile movement module: Calculate the optimal driving route of the mobile charging pile according to the user's charging needs and the real-time location information of the charging pile, and send the driving route to the charging pile control center. According to the optimal driving route, the charging pile is driven to the user's specified location by controlling the mobile device;

[0079] Charging preparation module: After the mobile charging pile arrives at the designated location, it will prepare for charging and check the status of the charging equipment;

[0080] Electromagnetic interference suppression module: processes the communication and control signals of the charging pile to suppress electromagnetic interference;

[0081] Charging and completion module: After confirming that the charging preparation work is completed, start charging the electric vehicle and monitor the charging status in real time. After charging is completed, disconnect the power connection and notify the user through the user terminal that the charging is completed;

[0082] Dynamic load balancing module: monitors and adjusts the output power of charging piles in real time, dynamically adjusts the charging power according to the status of the electric vehicle battery and charging demand, and balances the load between multiple charging piles;

[0083] Charging pile return and data recording module: After charging is completed, the mobile charging pile returns to the initial position or moves to the standby position according to the instructions of the charging pile control center, records the relevant data of each charging, and sends the relevant data to the charging pile control center for analysis.

[0084] Beneficial effects of the present invention:

[0085] The present invention realizes efficient scheduling and management of mobile charging piles through the steps of accurate charging pile positioning and user demand reception, path planning and charging pile movement, etc., and uses the Dijkstra algorithm to calculate the optimal driving route to ensure that the mobile charging pile can quickly and efficiently reach the user's specified location, reduce driving time and energy consumption, and improve the scheduling efficiency and service quality of the charging pile. In addition, the automatic connection power supply and equipment status inspection function of the charging pile ensure the efficiency and safety of charging preparation work, and optimize the overall efficiency of the charging service and user experience.

[0086] The present invention processes the communication and control signals of the charging pile through an adaptive filtering algorithm, effectively suppresses electromagnetic interference, ensures the stability and reliability of the system, and enables the charging pile system to operate normally in a complex electromagnetic environment through real-time electromagnetic interference detection and dynamic adjustment of the adaptive filter, thereby improving the communication quality and control accuracy. At the same time, the dynamic load balancing mechanism balances the loads between multiple charging piles by real-time monitoring and adjusting the output power of the charging pile, thereby ensuring the stability of the power grid and maximizing the charging efficiency, avoiding failures caused by overload, and further improving the reliability of the system.

[0087] The present invention, through the generative adversarial network (GAN) model, accurately predicts the load demand of the mobile charging pile based on the battery status and charging demand information of the electric vehicle. The GAN model can generate high-quality load demand prediction results, improve the response speed and prediction accuracy of the charging pile system, and optimize the stability and reliability of the charging service. In addition, the output power of the charging pile is dynamically adjusted through the PID control algorithm, and the load balancing algorithm is used to optimize the load distribution between the charging piles, ensuring the efficient operation and overall efficiency of the charging network. This mechanism not only improves the quality of the charging service, but also ensures the stable operation of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0088] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0089] Figure 1 A schematic diagram of a control method flow chart of an embodiment of the present invention;

[0090] Figure 2 Schematic diagram of system function modules according to an embodiment of the present invention. DETAILED DESCRIPTION

[0091] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0092] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0093] like Figure 1 As shown, a control method for a mobile charging pile includes the following steps:

[0094] S1, charging pile positioning and user demand reception: obtain the real-time location information of the mobile charging pile through GPS, and send the location information to the charging pile control center, and receive the user's charging demand through the user terminal, which includes charging time, charging amount and charging location;

[0095] S2, path planning and charging pile movement: according to the user's charging needs and the real-time location information of the charging pile, the path planning algorithm is used to calculate the optimal driving route of the mobile charging pile, and the driving route is sent to the charging pile control center. According to the optimal driving route, the charging pile is driven to move to the user's specified location by controlling the mobile device;

[0096] S3, charging preparation: After the mobile charging pile arrives at the designated location, it will prepare for charging, including automatically connecting to the power supply and checking the status of the charging equipment;

[0097] S4, electromagnetic interference suppression: Use adaptive filtering algorithms to process the communication and control signals of the charging pile to suppress electromagnetic interference and ensure the stability and reliability of the system;

[0098] S5, charging and completion: after confirming that the charging preparation work is completed, start charging the electric vehicle and monitor the charging status in real time. After charging is completed, disconnect the power supply and notify the user through the user terminal that the charging is completed;

[0099] S6, dynamic load balancing: real-time monitoring and adjustment of the output power of the charging pile, dynamically adjusting the charging power according to the status of the electric vehicle battery and the charging demand, and balancing the load between multiple charging piles to ensure grid stability and maximize charging efficiency;

[0100] S7, Charging pile return and data recording: After charging is completed, the mobile charging pile returns to the initial position or moves to the standby position according to the instruction of the charging pile control center, records the relevant data of each charging, including charging time, charging amount and charging cost, and sends the relevant data to the charging pile control center for analysis to optimize future charging services;

[0101] Through the above steps, efficient scheduling and management of mobile charging piles are achieved, ensuring the stability and reliability of the charging process, while optimizing the efficiency of charging services and user experience.

[0102] Path planning and charging pile movement in S2 include:

[0103] S21, optimal route calculation: combining the user's charging demand and the real-time location information of the charging pile, and using the Dijkstra algorithm to calculate the optimal driving route;

[0104] Dijkstra's algorithm includes:

[0105] Constructing a graph model: The service area of ​​the mobile charging pile is constructed as a graph model, where nodes represent locations, edges represent paths, and edge weights are path distances or travel time.

[0106] Initialize the distance set: set the distance from the starting node (current location of the charging pile) to itself to 0, the distances of other nodes to ∞, and add all nodes to the unvisited set;

[0107] Select the minimum distance node: Select the node with the minimum distance from the unvisited set as the current node, denoted as u;

[0108] Update the distance of adjacent nodes: For each adjacent node v of the current node u, calculate the distance from the starting point to v. If the distance is less than the currently recorded distance, update the distance. The calculation formula is:

[0109] d(v)=min(d(v),d(u)+w(u,v));

[0110] Where d(v) is the current shortest distance to node v, d(u) is the current shortest distance to node u, and w(u,v) is the path weight (distance or time) from node u to node v.

[0111] Mark node: mark the current node u as visited and remove it from the unvisited set;

[0112] Repeatedly select the minimum distance node: Repeatedly select the minimum distance node to the marked node until the shortest path from the start point to the end point is found or the unvisited set is empty;

[0113] S22, information sending: sending the calculated optimal driving route to the charging pile control center, and the charging pile control center receives the driving route information;

[0114] S23, charging pile movement: according to the optimal driving route, the charging pile is driven to move to the user's designated location by controlling the mobile device (such as the automatic driving system, the path tracking control module, etc.). The mobile device adjusts the driving path in real time based on the received driving route information and the sensor data (such as the laser radar, the camera, etc.) to ensure that it arrives safely at the user's designated location;

[0115] The present invention combines the user's charging needs and the real-time location information of the charging pile, and uses the Dijkstra algorithm to calculate the optimal driving route, ensuring that the mobile charging pile can quickly and efficiently reach the user's specified location. The Dijkstra algorithm optimizes the path selection by accurately calculating the path distance or driving time, reduces the driving time and energy consumption, and improves the scheduling efficiency and service quality of the charging pile. By controlling the mobile device to accurately execute the optimal driving route, the reliable operation of the mobile charging pile in a complex urban environment is guaranteed.

[0116] EMI suppression in S4 includes:

[0117] S41, electromagnetic interference detection: monitor the communication and control signals of the charging pile in real time through the electromagnetic interference detection mechanism to obtain the characteristic information of the electromagnetic interference, including the interference frequency and amplitude;

[0118] S42, adaptive filter initialization: input the acquired electromagnetic interference characteristic information into the adaptive filter, and the adaptive filter dynamically adjusts the filter parameters according to the input signal to suppress the electromagnetic interference;

[0119] S43, filter weight update: using a recursive least squares (RLS) algorithm to update the weight of the adaptive filter;

[0120] S44, signal processing and application: the signal processed by the adaptive filter is used for communication and control of the charging pile to ensure the stability and reliability of the system;

[0121] By using an adaptive filtering algorithm to process the communication and control signals of the charging pile, the present invention can suppress electromagnetic interference in real time and ensure the stability and reliability of the system. The adaptive filter dynamically adjusts the filtering parameters through the LMS or RLS algorithm, and can effectively filter out interference signals in complex electromagnetic environments, thereby improving the communication quality and control accuracy of the charging pile, thereby improving the performance of the entire system and user experience.

[0122] EMI detection in S41 includes:

[0123] S411, electromagnetic interference detection device installation: an electromagnetic interference detection device is installed in the communication and control circuit of the charging pile, the electromagnetic interference detection device includes an electromagnetic interference sensor and a signal processing unit, and monitors and processes electromagnetic interference signals in real time;

[0124] S412, signal processing unit analysis: The signal processing unit performs spectrum analysis on the electromagnetic interference signal to extract characteristic information of the interference signal. The calculation formula is:

[0125]

[0126] Among them, X(f) is the frequency domain signal, x(t) is the time domain signal, f is the frequency, and t is the time;

[0127] S413, characteristic information transmission: transmitting the acquired electromagnetic interference characteristic information to the adaptive filter for electromagnetic interference suppression processing. The characteristic information can help the adaptive filter dynamically adjust the filtering parameters and accurately suppress the electromagnetic interference;

[0128] Through the electromagnetic interference detection device, the communication and control signals of the charging pile are monitored in real time, and the characteristic information of the electromagnetic interference, including the interference frequency and amplitude, is obtained, which can provide accurate input data for the subsequent adaptive filtering processing. This mechanism can effectively identify and analyze the source of electromagnetic interference, thereby more accurately suppressing interference and ensuring the stability and reliability of the charging pile system.

[0129] The recursive least squares (RLS) algorithm includes:

[0130] Gain vector calculation:

[0131] Where P(n-1) is the covariance matrix in the n-1th iteration, x(n) is the input signal vector in the nth iteration, and λ is the forgetting factor, (0<λ≤1);

[0132] Weight update: w(n)=w(n-1)+K(n)e(n);

[0133] Where w(n) is the filter weight of the nth iteration, K(n) is the gain vector, and e(n) is the current error;

[0134] Covariance matrix update:

[0135] The RLS algorithm ensures that the filter can quickly adapt to new signal characteristics, thereby effectively suppressing electromagnetic interference and ensuring the stability and reliability of communication and control signals.

[0136] Dynamic load balancing in S6 includes:

[0137] S61, battery status monitoring: real-time monitoring of electric vehicle battery status information, including battery power, battery health status and charging requirements;

[0138] S62, load prediction: based on the battery status information and charging demand, use the load prediction model to predict the real-time load demand of the charging pile;

[0139] S63, dynamically adjust the output power of the charging pile: based on the predicted load demand and the real-time monitored battery status, calculate the optimal output power of each charging pile, and adjust the output power of the charging pile in real time to ensure the stability and efficiency of the charging process;

[0140] S64, balancing the load between charging piles: by real-time monitoring of the load status of the charging piles, when the load of the charging piles is too high, the load is automatically distributed, and the load balancing algorithm is used to optimize the load distribution, ensuring the stable and efficient operation of the charging network and avoiding failures caused by overload;

[0141] By real-time monitoring of the status and charging needs of electric vehicle batteries, the present invention can dynamically adjust the output power of the charging pile to ensure the stability and efficiency of the charging process. At the same time, through load prediction and balancing algorithms, the load distribution between multiple charging piles is optimized to improve the efficiency and reliability of the entire charging network. This mechanism not only improves the quality of charging services, but also ensures the stable operation of the power grid.

[0142] The load prediction model in S62 adopts the Generative Adversarial Network (GAN) model, which includes:

[0143] S621, data acquisition and feature extraction: obtain electric vehicle battery status information (battery power, battery health status) and charging requirements (charging time, charging amount), and extract time series features, including battery power change rate, historical charging records, and environmental factors;

[0144] S622, initialize the generator and discriminator: initialize the weights and biases of the generator G and the discriminator D;

[0145] S623, conditional input: the battery status and charging requirements of the electric vehicle are used as conditional input c, combined with the random noise z input generator;

[0146] S624, loss function definition:

[0147] Discriminator loss function:

[0148]

[0149] Among them, L D is the loss function of the discriminator, L is the true load demand, c is the conditional input (electric vehicle battery status and charging demand), pdata is the real data distribution, D(L|c) is the output of the discriminator for the real load demand L under given condition c, z is the random noise vector, p z is the distribution of the noise vector, G(z,c) is the load demand generated by the generator under the given noise vector z and condition c, and D(G(z,c)|c) is the output of the discriminator for the generated load demand G(z,c) under the given condition c;

[0150] Generator loss function:

[0151]

[0152] Among them, L G is the loss function of the generator, p c is the distribution of the conditional input;

[0153] S625, adaptive learning rate adjustment: dynamically adjust the learning rate according to the loss changes during training. The calculation formula is:

[0154]

[0155] Among them, α(t) is the learning rate of the tth iteration, β is the adjustment coefficient, is the rate of change of the loss function;

[0156] S626, training the producer and discriminator: repeat the training process until the loss function converges. The training process is:

[0157] Update the discriminator:

[0158] Update the generator:

[0159] Among them, θ D is the parameter of the discriminator, α D is the learning rate of the discriminator, is the discriminator loss function L D For parameter θ D The gradient of θ G is the parameter of the generator, α G is the learning rate of the generator, is the generator loss function L G For parameter θ G The gradient of

[0160] S627, load prediction: Use the trained generator G to receive the conditional input c and random noise z to generate the predicted load demand

[0161] The present invention realizes efficient and accurate prediction of the load demand of mobile charging piles through a generative adversarial network (GAN) model. The GAN model can utilize the battery status and charging demand information of electric vehicles to generate high-quality load demand prediction results, improve the response speed and prediction accuracy of the charging pile system, and thus optimize the stability and reliability of the charging service.

[0162] The dynamic adjustment of charging pile output power in S63 includes:

[0163] S631, Initial Output Power Calculation: Obtaining Forecasted Load Demand And the real-time monitored battery status S, according to the current battery power E and charging demand D, calculate the initial output power P of each charging pile init , the calculation formula is:

[0164]

[0165] Where D is the battery charging demand, E is the current power, and T is the expected charging time;

[0166] S632, optimal output power calculation: According to the predicted load demand and the real-time monitored battery status, the output power is adjusted using the PID control algorithm. The calculation formula is:

[0167]

[0168] Among them, P i (t) is the output power of the i-th charging pile at the t-th time, is the error, K p is the proportional gain, K i is the integral gain, K d is the differential gain;

[0169] S633, real-time adjustment of the output power of the charging pile: According to the output power calculated by the PID control algorithm, the output power of each charging pile is adjusted in real time to ensure that the real-time load demand is met. The calculation formula is:

[0170]

[0171] in, is the output power of the i-th charging pile at the t-th time calculated by the PID control algorithm, and α is the adjustment coefficient;

[0172] Through the above steps, the present invention can realize dynamic adjustment of the output power of the charging pile, ensuring that the charging pile system provides efficient and reliable charging services under complex and changeable load demands and battery conditions.

[0173] The loads between the charging piles in S64 are balanced as follows:

[0174] S641, real-time monitoring of the load status of the charging pile: real-time monitoring of the load information of each charging pile, including the current output power and load status, and recording the load status of each charging pile to form historical load data for analysis and prediction;

[0175] S642, detecting excessive load: analyzing the real-time monitored load information, and triggering the load distribution mechanism when it is detected that the load of the charging pile exceeds a preset threshold, where the preset threshold is set according to the rated power of the charging pile and the safety operation requirements;

[0176] S643, automatic load distribution: after detecting that the load is too high, automatically distribute the predetermined load to the charging pile with low load;

[0177] S644, optimize load distribution using load balancing algorithm: Use load balancing algorithm to optimize load distribution between charging piles. The calculation formula is:

[0178]

[0179] in, is the load of the i-th charging pile after redistribution, is the load before allocation, ΔP is the total load to be allocated, and N is the number of charging piles with lower load;

[0180] Through the above steps, the present invention can achieve load balancing between charging piles, avoid failure of a charging pile due to overload, and improve the overall efficiency and reliability of the charging pile system.

[0181] like Figure 2 As shown, a control system of a mobile charging pile is used to implement the above-mentioned control method of a mobile charging pile, including the following modules:

[0182] Charging pile positioning and user demand receiving module: obtain the real-time location information of the mobile charging pile, send the location information to the charging pile control center, and receive the user's charging demand;

[0183] Path planning and charging pile movement module: Calculate the optimal driving route of the mobile charging pile according to the user's charging needs and the real-time location information of the charging pile, and send the driving route to the charging pile control center. According to the optimal driving route, the charging pile is driven to the user's specified location by controlling the mobile device;

[0184] Charging preparation module: After the mobile charging pile arrives at the designated location, it will prepare for charging and check the status of the charging equipment;

[0185] Electromagnetic interference suppression module: processes the communication and control signals of the charging pile to suppress electromagnetic interference;

[0186] Charging and completion module: After confirming that the charging preparation work is completed, start charging the electric vehicle and monitor the charging status in real time. After charging is completed, disconnect the power connection and notify the user through the user terminal that the charging is completed;

[0187] Dynamic load balancing module: monitors and adjusts the output power of charging piles in real time, dynamically adjusts the charging power according to the status of the electric vehicle battery and charging demand, and balances the load between multiple charging piles;

[0188] Charging pile return and data recording module: After charging is completed, the mobile charging pile returns to the initial position or moves to the standby position according to the instructions of the charging pile control center, records the relevant data of each charging, and sends the relevant data to the charging pile control center for analysis.

[0189] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present invention is limited to these examples. Under the concept of the present invention, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the present invention as described above, which are not provided in detail for the sake of simplicity.

[0190] The present invention is intended to cover all such substitutions, modifications and variations that fall within the broad scope of the claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A control method for a mobile charging pile, characterized in that: The following steps are involved: S1, charging pile positioning and user demand reception: obtain the real-time location information of the mobile charging pile through GPS, and send the location information to the charging pile control center, and receive the user's charging demand through the user terminal, which includes charging time, charging amount and charging location; S2, path planning and charging pile movement: according to the user's charging needs and the real-time location information of the charging pile, the path planning algorithm is used to calculate the optimal driving route of the mobile charging pile, and the driving route is sent to the charging pile control center. According to the optimal driving route, the charging pile is driven to move to the user's specified location by controlling the mobile device; S3, charging preparation: After the mobile charging pile arrives at the designated location, it will prepare for charging, including automatically connecting to the power supply and checking the status of the charging equipment; S4, electromagnetic interference suppression: Use adaptive filtering algorithm to process the communication and control signals of the charging pile to suppress electromagnetic interference; S5, charging and completion: after confirming that the charging preparation work is completed, start charging the electric vehicle and monitor the charging status in real time. After charging is completed, disconnect the power supply and notify the user through the user terminal that the charging is completed; S6, dynamic load balancing: real-time monitoring and adjustment of the output power of the charging pile, dynamically adjusting the charging power according to the status of the electric vehicle battery and the charging demand, and balancing the load between multiple charging piles; S7, Charging pile return and data recording: After charging is completed, the mobile charging pile returns to the initial position or moves to the standby position according to the instruction of the charging pile control center, records the relevant data of each charging, including charging time, charging amount and charging cost, and sends the relevant data to the charging pile control center for analysis.

2. A control method for a mobile charging pile according to claim 1, characterized in that: The path planning and charging pile movement in S2 include: S21, optimal route calculation: combining the user's charging demand and the real-time location information of the charging pile, and using the Dijkstra algorithm to calculate the optimal driving route; S22, information sending: sending the calculated optimal driving route to the charging pile control center, and the charging pile control center receives the driving route information; S23, charging pile movement: according to the optimal driving route, the charging pile is driven to move to the user-specified position by controlling the mobile device. The mobile device adjusts the driving path in real time based on the received driving route information and combined with the sensor data.

3. The control method of a mobile charging pile according to claim 1, characterized in that: The electromagnetic interference suppression in S4 includes: S41, electromagnetic interference detection: monitor the communication and control signals of the charging pile in real time through the electromagnetic interference detection mechanism to obtain the characteristic information of the electromagnetic interference, including the interference frequency and amplitude; S42, adaptive filter initialization: input the acquired electromagnetic interference characteristic information into the adaptive filter, and the adaptive filter dynamically adjusts the filter parameters according to the input signal to suppress the electromagnetic interference; S43, filter weight update: using a recursive least squares algorithm to update the weight of the adaptive filter; S44, signal processing and application: using the signal processed by the adaptive filter for communication and control of the charging pile.

4. A control method for a mobile charging pile according to claim 3, characterized in that: The electromagnetic interference detection in S41 includes: S411, electromagnetic interference detection device installation: an electromagnetic interference detection device is installed in the communication and control circuit of the charging pile, the electromagnetic interference detection device includes an electromagnetic interference sensor and a signal processing unit, and monitors and processes electromagnetic interference signals in real time; S412, signal processing unit analysis: The signal processing unit performs spectrum analysis on the electromagnetic interference signal to extract characteristic information of the interference signal. The calculation formula is: Among them, X(f) is the frequency domain signal, x(t) is the time domain signal, f is the frequency, and t is the time; S413, characteristic information transmission: the acquired electromagnetic interference characteristic information is transmitted to the adaptive filter for electromagnetic interference suppression processing.

5. A control method for a mobile charging pile according to claim 4, characterized in that: The recursive least squares algorithm includes: Gain vector calculation: Where P(n-1) is the covariance matrix at the n-1th iteration, x(n) is the input signal vector at the nth iteration, and λ is the forgetting factor; Weight update: w(n)=w(n-1)+K(n)e(n); Where w(n) is the filter weight of the nth iteration, K(n) is the gain vector, and e(n) is the current error; Covariance matrix update:

6. The control method of a mobile charging pile according to claim 1, characterized in that: The dynamic load balancing in S6 includes: S61, battery status monitoring: real-time monitoring of electric vehicle battery status information, including battery power, battery health status and charging requirements; S62, load prediction: based on the battery status information and charging demand, use the load prediction model to predict the real-time load demand of the charging pile; S63, dynamically adjusting the output power of the charging pile: based on the predicted load demand and the real-time monitored battery status, calculating the optimal output power of each charging pile, and adjusting the output power of the charging pile in real time; S64, balancing the load between charging piles: by real-time monitoring of the load status of the charging piles, when the load of the charging piles is too high, the load is automatically distributed, and the load balancing algorithm is used to optimize the load distribution.

7. A control method for a mobile charging pile according to claim 6, characterized in that: The load prediction model in S62 adopts a generative adversarial network model, and the generative adversarial network model includes: S621, data acquisition and feature extraction: obtain electric vehicle battery status information and charging requirements, and extract time series features, including battery power change rate, historical charging records, and environmental factors; S622, initialize the generator and discriminator: initialize the weights and biases of the generator G and the discriminator D; S623, conditional input: the battery status and charging requirements of the electric vehicle are used as conditional input c, combined with the random noise z input generator; S624, loss function definition: Discriminator loss function: Among them, L D is the loss function of the discriminator, L is the actual load demand, c is the conditional input, and p data is the real data distribution, D(L|c) is the output of the discriminator for the real load demand L under given condition c, z is the random noise vector, p z is the distribution of the noise vector, G(z,c) is the load demand generated by the generator under the given noise vector z and condition c, and D(G(z,c)|c) is the output of the discriminator for the generated load demand G(z,c) under the given condition c; Generator loss function: Among them, L G is the loss function of the generator, p c is the distribution of the conditional input; S625, adaptive learning rate adjustment: dynamically adjust the learning rate according to the loss changes during training. The calculation formula is: Among them, α(t) is the learning rate of the tth iteration, β is the adjustment coefficient, is the rate of change of the loss function; S626, training the producer and discriminator: repeat the training process until the loss function converges. The training process is: Update the discriminator: Update the generator: Among them, θ D is the parameter of the discriminator, α D is the learning rate of the discriminator, is the discriminator loss function L D For parameter θ D The gradient of θ G is the parameter of the generator, α G is the learning rate of the generator, is the generator loss function L G For parameter θ G The gradient of S627, load prediction: Use the trained generator G to receive the conditional input c and random noise z to generate the predicted load demand 8. A control method for a mobile charging pile according to claim 7, characterized in that: The dynamic adjustment of the charging pile output power in S63 includes: S631, Initial Output Power Calculation: Obtaining Forecasted Load Demand And the real-time monitored battery status S, according to the current battery power E and charging demand D, calculate the initial output power P of each charging pile init , the calculation formula is: Where D is the battery charging demand, E is the current power, and T is the expected charging time; S632, optimal output power calculation: According to the predicted load demand and the real-time monitored battery status, the output power is adjusted using the PID control algorithm. The calculation formula is: Among them, P i (t) is the output power of the i-th charging pile at the t-th time, is the error, K p is the proportional gain, K i is the integral gain, K d is the differential gain; S633, real-time adjustment of the output power of the charging pile: according to the output power calculated by the PID control algorithm, the output power of each charging pile is adjusted in real time. The calculation formula is: in, is the output power of the i-th charging pile at the t-th time calculated by the PID control algorithm, and α is the adjustment coefficient.

9. A control method for a mobile charging pile according to claim 8, characterized in that: The load balancing between the charging piles in S64 includes: S641, real-time monitoring of the load status of the charging pile: real-time monitoring of the load information of each charging pile, including the current output power and load status, and recording the load status of each charging pile to form historical load data; S642, detecting excessive load: analyzing the real-time monitored load information, and triggering the load distribution mechanism when it is detected that the load of the charging pile exceeds a preset threshold; S643, automatic load distribution: after detecting that the load is too high, automatically distribute the predetermined load to the charging pile with low load; S644, optimize load distribution using load balancing algorithm: Use load balancing algorithm to optimize load distribution between charging piles. The calculation formula is: in, is the load of the i-th charging pile after redistribution, is the load before allocation, ΔP is the total load to be allocated, and N is the number of charging piles with lower load.

10. A control system for a mobile charging pile, used to implement a control method for a mobile charging pile as claimed in any one of claims 1 to 9, characterized in that: Includes the following modules: Charging pile positioning and user demand receiving module: obtain the real-time location information of the mobile charging pile, send the location information to the charging pile control center, and receive the user's charging demand; Path planning and charging pile movement module: Calculate the optimal driving route of the mobile charging pile according to the user's charging needs and the real-time location information of the charging pile, and send the driving route to the charging pile control center. According to the optimal driving route, the charging pile is driven to the user's specified location by controlling the mobile device; Charging preparation module: After the mobile charging pile arrives at the designated location, it will prepare for charging and check the status of the charging equipment; Electromagnetic interference suppression module: processes the communication and control signals of the charging pile to suppress electromagnetic interference; Charging and completion module: After confirming that the charging preparation work is completed, start charging the electric vehicle and monitor the charging status in real time. After charging is completed, disconnect the power connection and notify the user through the user terminal that the charging is completed; Dynamic load balancing module: monitors and adjusts the output power of charging piles in real time, dynamically adjusts the charging power according to the status of electric vehicle batteries and charging needs, and balances the load between multiple charging piles; Charging pile return and data recording module: After charging is completed, the mobile charging pile returns to the initial position or moves to the standby position according to the instructions of the charging pile control center, records the relevant data of each charging, and sends the relevant data to the charging pile control center for analysis.

Images