Charging pile reservation scheduling and path planning cooperation system and method

Abstract

The invention relates to the technical field of charging infrastructure management, and particularly discloses a charging pile appointment scheduling and path planning cooperation system and a charging pile appointment scheduling and path planning cooperation method. According to the method, continuous wavelet transform and fast Fourier transform are adopted to extract a charging rate fluctuation characteristic value and a power grid power supply stability characteristic value for quantitatively evaluating the service stability of a charging pile and the power supply reliability of a regional power grid, and the system fuses the characteristic values into a comprehensive characteristic vector as the input of a gradient boosting tree model so as to obtain a gradient boosting tree model; and training the prediction model to output a charging planning score so as to judge whether the user can smoothly complete the charging task, and if a prediction result does not meet a set threshold value, dynamically adjusting a reservation scheduling strategy and re-planning an optimal charging path.

Description

Technical Field

[0001] The present invention relates to the technical field of charging infrastructure management, and particularly relates to a collaborative system and method for charging pile reservation scheduling and path planning. Background Art

[0002] With the popularization of electric vehicles, the intelligent management of charging infrastructure has become a key link to improve user experience and traffic system efficiency. At present, charging pile reservation scheduling and path planning are mostly based on static information (such as the location of charging piles and whether they are idle) for decision-making, lacking the dynamic perception ability of the operating state of charging piles and the external power supply environment. Existing scheduling systems usually regard charging piles as idealized nodes, and do not fully consider problems such as performance fluctuations and service interruptions that may occur during actual operation, resulting in the situation that users may still be unable to complete the charging task due to equipment abnormalities, grid disturbances, etc. after arriving at the target charging pile, affecting travel continuity and user satisfaction.

[0003] The existing technology has the following deficiencies: The current mainstream charging pile scheduling and path planning methods have the following technical bottlenecks: First, most systems only rely on static indicators such as whether the charging pile is idle or historical average efficiency for recommendation, ignoring the real-time performance changes and service stability of charging piles; second, there is a lack of a dynamic evaluation mechanism for the power supply quality of the regional power grid, and it is difficult to make timely scheduling responses in the face of situations such as grid fluctuations and unstable power supply; third, it fails to effectively integrate the operating data of charging piles and user trip information to construct an intelligent prediction model, resulting in lagging scheduling strategies and inaccurate path planning, and easily causing some high-risk or inefficient charging piles to be frequently reserved, thus leading to problems such as unbalanced resource allocation and increased service failure rate. Therefore, there is an urgent need for a collaborative system and method that can comprehensively perceive the operating state of charging piles and the power grid power supply environment and implement dynamic scheduling and path optimization accordingly. Summary of the Invention

[0004] The purpose of the present invention is to provide a collaborative system and method for charging pile reservation scheduling and path planning to solve the problems in the above background.

[0005] The purpose of the present invention can be achieved through the following technical solutions: A collaborative method for charging pile reservation scheduling and path planning includes the following steps: S1: During the collaborative process of charging pile reservation scheduling and path planning, collect and monitor the charging rate changes and grid power supply fluctuations of each charging pile in real time; S2: Calculate the charging rate fluctuation characteristic value according to the amplitude of the charging rate change monitored in real time, and use it to evaluate the risk of service interruption of the charging pile in the current usage environment; S3: Calculate the power grid power supply stability characteristic value based on the power grid power supply fluctuation degree obtained in real time, which is used to determine whether there is an unstable power supply problem in the area where the charging pile is located; S4: Conduct a comprehensive analysis of the charging rate fluctuation characteristic value and the power grid power supply stability characteristic value, and construct a prediction model according to the analysis result to determine whether the user can successfully complete the charging task; S5: If the user cannot successfully complete the charging task, dynamically adjust the charging pile reservation scheduling strategy.

[0006] As a further solution of the present invention: The evaluation of the risk of service interruption of the charging pile in the current usage environment specifically includes: During the coordination process of charging pile reservation scheduling and path planning, collect the charging rate data of each charging pile in real time. According to the change range of the charging rate, calculate the charging rate fluctuation characteristic value, and determine whether the charging rate fluctuation characteristic value is greater than or equal to the preset threshold. If so, there is a risk of service interruption of the charging pile in the current usage environment; if not, there is no risk of service interruption of the charging pile in the current usage environment.

[0007] As a further solution of the present invention: The process of obtaining the charging rate fluctuation characteristic value is as follows: Collect the charging rate time series data of each charging pile in real time, perform continuous wavelet transform on the charging rate time series data to obtain wavelet coefficients, and calculate the energy distribution at each scale based on the wavelet coefficients; Calculate the average value of the energy distributions of all scales as the reference energy, calculate the sum of the absolute values of the differences between the reference energy and the energies at all scales, and calculate the ratio of the sum of the absolute values to the total energy of all scales to obtain the charging rate fluctuation characteristic value.

[0008] As a further solution of the present invention: The determination of whether there is an unstable power supply problem in the area where the charging pile is located specifically includes: During the coordination process of charging pile reservation scheduling and path planning, collect the power grid power supply fluctuation data of each charging pile in real time. According to the power grid power supply fluctuation degree, calculate the power grid power supply stability characteristic value, and determine whether the power grid power supply stability characteristic value is greater than or equal to the preset threshold. If so, there is an unstable power supply problem in the area where the charging pile is located; if not, there is no unstable power supply problem in the area where the charging pile is located.

[0009] As a further solution of the present invention: The process of obtaining the power grid power supply stability characteristic value is as follows: Collect the power grid power supply voltage data of the area where each charging pile is located as the power grid power supply fluctuation data, perform fast Fourier transform on the power grid power supply fluctuation data to convert it from a time-domain signal to a frequency-domain signal, and obtain the corresponding spectrum function; Calculate the power spectral density based on the squared modulus of the spectral function; Set a reference frequency set, including the fundamental frequency of the power grid and the main harmonic frequency components, as the reference frequency range for evaluating the stability of the power grid; Obtain the power grid power supply stability eigenvalue according to the energy ratio of the power spectral density within the entire frequency range and the reference frequency range.

[0010] As a further solution of the present invention: comprehensively analyze the charging rate fluctuation eigenvalue and the power grid power supply stability eigenvalue, and construct a prediction model according to the analysis results, specifically including: During the collaborative process of charging pile reservation scheduling and path planning, obtain the charging rate fluctuation eigenvalue and the power grid power supply stability eigenvalue, construct the charging rate fluctuation eigenvalue and the power grid power supply stability eigenvalue into a comprehensive feature vector as the input of the prediction model, minimize the error between the predicted charging plan score and the actual charging plan score as the training objective of the model, and output the charging plan score according to the trained prediction model. The prediction model is the gradient boosting tree algorithm.

[0011] As a further solution of the present invention: the training process of the prediction model is as follows: Obtain the historical comprehensive feature vector and the charging plan score as the training data set, use the training data set to train the gradient boosting tree algorithm. During the training process, use multiple decision trees to sequentially fit the residuals between the current model prediction result and the true charging plan score, and gradually correct and optimize the overall prediction accuracy. In each iteration, the model calculates the loss between the current predicted value and the actual label, and generates a new decision tree accordingly to make up for the error. Finally, the outputs of all weak learners are superimposed to obtain an accurate prediction result. The training objective is to minimize the overall error between the predicted charging plan score and the actual charging plan score.

[0012] As a further solution of the present invention: the judgment of whether the user can successfully complete the charging task specifically includes: During the collaborative process of charging pile reservation scheduling and path planning, judge whether the charging plan score is greater than or equal to a preset threshold. If so, the user can successfully complete the charging task; if not, the user cannot successfully complete the charging task.

[0013] As a further solution of the present invention: if the user cannot successfully complete the charging task, then dynamically adjust the charging pile reservation scheduling strategy, specifically including: If it is determined that the user cannot successfully complete the charging task, the system automatically activates a multi-dimensional dynamic scheduling strategy: identify sudden load fluctuations based on the changing trend of the charging rate, downgrade the priority of the charging piles with a tendency to fail, and limit the number of reserved openings during high-load periods; judge the reliability of regional power supply based on the degree of grid power supply fluctuations. If it is detected that the grid instability persists, implement power grading control for the charging piles within the region to preferentially ensure the stable charging of low-power consumption vehicles.

[0014] A collaborative system for charging pile reservation scheduling and path planning, comprising: A data acquisition module that, during the collaborative process of charging pile reservation scheduling and path planning, collects and monitors the charging rate changes and the degree of grid power supply fluctuations of each charging pile in real time; A charging rate evaluation module that calculates the charging rate fluctuation characteristic value according to the amplitude of the charging rate change monitored in real time, and is used to evaluate the risk of service interruption of the charging pile in the current usage environment; A grid power supply fluctuation evaluation module that calculates the grid power supply stability characteristic value based on the degree of grid power supply fluctuations obtained in real time, and is used to judge whether there are problems with unstable power supply in the area where the charging pile is located; A charging prediction module that comprehensively analyzes the charging rate fluctuation characteristic value and the grid power supply stability characteristic value, constructs a prediction model according to the analysis results, and judges whether the user can successfully complete the charging task; A dynamic adjustment module that dynamically adjusts the charging pile reservation scheduling strategy if the user cannot successfully complete the charging task.

[0015] Advantages of the present invention: (1) By introducing the charging rate fluctuation eigenvalue based on continuous wavelet transform and the power grid power supply stability eigenvalue based on fast Fourier transform, the present invention constructs a multi-dimensional and dynamic evaluation system for the operating state of charging piles, realizing real-time perception and accurate quantification of the performance stability of charging facilities and the quality of regional power supply. Different from the traditional path planning and scheduling system that only relies on static indicators such as the idle state of charging piles or historical average efficiency for decision-making, the present invention starts from both the time domain and the frequency domain, deeply excavates the hidden abnormal fluctuations caused by factors such as equipment aging, load mutation, and power grid interference during the actual operation of charging piles, can identify potential service interruption risks in advance, and significantly improves the early warning ability of the system for sudden charging failure events. On this basis, the system fuses the above eigenvalues into a comprehensive evaluation index, inputs it into the prediction model constructed based on the gradient boosting tree algorithm, generates a quantitative score reflecting the charging success rate, and dynamically adjusts the reservation strategy and path recommendation plan accordingly, preferentially guiding users to choose charging piles with stable service and reliable power supply, thereby effectively avoiding high-risk sites, greatly increasing the probability of users successfully completing the charging task, ensuring the travel continuity and experience satisfaction of electric vehicle users, and promoting the development of the charging network towards the direction of intelligence, refinement, and high availability.

[0016] (2) The present invention constructs an efficient and accurate prediction mechanism based on the gradient boosting tree, fully integrating multi-dimensional operation data of charging piles and real-time travel information of users, including key parameters such as charging rate fluctuation eigenvalue, power grid power supply stability eigenvalue, current load state of charging piles, historical service score, user's current location, remaining battery power, destination distance, and estimated arrival time, forming a dynamic comprehensive evaluation feature vector as the model input. Through the combination of offline training and online learning, the model can output a quantitative charging plan score reflecting the service reliability of charging piles, and judge the success probability of users completing the charging task at the target charging pile accordingly. When the prediction result is lower than the set threshold, the system automatically triggers the path re-planning and scheduling strategy adjustment mechanism, and intelligently recommends alternative charging piles with higher stability and accessibility, avoiding the risk of charging failure caused by equipment abnormalities or power grid fluctuations. This mechanism not only significantly improves the intelligence, adaptability, and forward-looking performance of the scheduling system, but also realizes the optimal allocation of charging pile resources in the time and space dimensions, effectively alleviates congestion during peak hours, avoids over-concentration in areas with unstable power supply, and comprehensively improves the service throughput capacity and resource utilization efficiency of the charging network, providing a solid technical support and systematic solution for constructing an efficient, stable, safe, and user-experience-centered electric vehicle charging service system. Brief Description of the Drawings

[0017] The present invention will be further described below with reference to the accompanying drawings.

[0018] Figure 1It is a flowchart of a collaborative method for charging pile reservation scheduling and path planning according to the present invention; Figure 2 It is a flowchart of a collaborative system for charging pile reservation scheduling and path planning in the present invention. Specific embodiments

[0019] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0020] Please refer to Figure 1 As shown, the present invention is a collaborative method for charging pile reservation scheduling and path planning, including the following steps: S1: During the collaborative process of charging pile reservation scheduling and path planning, the charging rate changes and grid power supply fluctuation degrees of each charging pile are collected and monitored in real time; S2: According to the amplitude of the charging rate change monitored in real time, the charging rate fluctuation characteristic value is calculated to evaluate the risk of service interruption of the charging pile in the current usage environment; S3: Based on the grid power supply fluctuation degree obtained in real time, the grid power supply stability characteristic value is calculated to determine whether there is an unstable power supply problem in the area where the charging pile is located; S4: The charging rate fluctuation characteristic value and the grid power supply stability characteristic value are comprehensively analyzed, and a prediction model is constructed according to the analysis result to judge whether the user can successfully complete the charging task; S5: If the user cannot successfully complete the charging task, the charging pile reservation scheduling strategy is dynamically adjusted.

[0021] In S1, during the collaborative process of charging pile reservation scheduling and path planning, the charging rate changes and grid power supply fluctuation degrees of each charging pile are collected and monitored in real time, specifically including: During the collaborative process of charging pile reservation scheduling and path planning, the system high-frequency collects parameters such as current, voltage, and power during the charging process through the sensor modules deployed inside each charging pile, and calculates the change in the power output per unit time to obtain the real-time charging rate data of the charging pile; the charging rate data is uploaded to the cloud scheduling platform at a preset time interval, and the platform performs a sliding window process on the multi-period data to extract the charging rate difference between adjacent time points, forming a charging rate change sequence for subsequent analysis of the performance stability of the charging pile during actual operation.

[0022] Meanwhile, the system accesses the grid distribution unit or smart meter to obtain the grid voltage fluctuation data in the area where the charging pile is located in real time, with a sampling frequency of not less than once per second, ensuring that abnormal phenomena such as short-term voltage dips, surges, or harmonic disturbances can be captured; the collected voltage data is filtered and then further converted into a standard voltage deviation index, which is compared and analyzed in combination with the historical voltage baseline to identify whether there is an abnormal fluctuation trend in the grid power supply; the above two types of data are jointly used as important dynamic inputs for path planning and scheduling decisions to achieve refined perception and response to the operating environment of the charging pile.

[0023] In S2, according to the change range of the charging rate monitored in real time, the charging rate fluctuation characteristic value is calculated to evaluate the risk of service interruption of the charging pile in the current usage environment. During the collaborative process of charging pile reservation scheduling and path planning, the charging rate data of each charging pile is collected in real time. According to the change range of the charging rate, the charging rate fluctuation characteristic value is calculated, and it is judged whether the charging rate fluctuation characteristic value is greater than or equal to the preset threshold. If so, there is a risk of service interruption of the charging pile in the current usage environment; if not, there is no risk of service interruption of the charging pile in the current usage environment.

[0024] The process of obtaining the charging rate fluctuation characteristic value is as follows: The charging rate time series data of each charging pile is collected in real time, and continuous wavelet transform is performed on the charging rate time series data to obtain wavelet coefficients. Based on the wavelet coefficients, the energy distribution at each scale is calculated, and the calculation expression is: ; In the formula, represents the number of scales, represents the th scale energy distribution, represents the translation parameter, represents the th scale position of the wavelet coefficient; Calculate the average value of the energy distributions of all scales as the reference energy, and calculate the charging rate fluctuation characteristic value according to the reference energy. The calculation expression is: ; In the formula, represents the charging rate fluctuation characteristic value, represents the reference energy.

[0025] It should be noted that: by collecting the real-time charging rate data of the charging pile and using the continuous wavelet transform technology to perform multi-scale analysis on the charging rate time series, the energy distribution characteristics at each scale are extracted. Furthermore, the average value of the energy distributions at all scales is used as the reference energy to construct the charging rate fluctuation eigenvalue. The charging rate fluctuation eigenvalue can effectively reflect the abnormal fluctuation conditions of the charging pile during actual operation caused by factors such as external load changes, equipment aging, or grid interference, thereby accurately evaluating its service interruption risk. The present invention utilizes wavelet transform to capture the local mutation characteristics of the signal in the time-frequency domain, with higher sensitivity and robustness, capable of identifying early potential fault trends, providing a reliable basis for dynamic scheduling and path planning, significantly enhancing the system's perception ability of the charging pile operation status and the intelligent decision-making level, and possessing outstanding technological progressiveness and practicality.

[0026] In S3, according to the power supply fluctuation degree of the power grid obtained in real time, calculate the power grid power supply stability eigenvalue, which is used to determine whether there is an unstable power supply problem in the area where the charging pile is located. Specifically, it includes: During the collaborative process of charging pile reservation scheduling and path planning, the power grid power supply fluctuation data of each charging pile is collected in real time. According to the power grid power supply fluctuation degree, calculate the power grid power supply stability eigenvalue, and determine whether the power grid power supply stability eigenvalue is greater than or equal to the preset threshold. If so, there is an unstable power supply problem in the area where the charging pile is located. If not, there is no unstable power supply problem in the area where the charging pile is located.

[0027] The process of obtaining the power grid power supply stability eigenvalue is as follows: Collect the power grid power supply voltage data of the area where each charging pile is located in real time as the power grid power supply fluctuation data, and perform fast Fourier transform on the power grid power supply fluctuation data to convert it from a time-domain signal to a frequency-domain signal, obtaining the corresponding spectrum function; Based on the spectrum function, calculate the power spectral density. The calculation expression is: ; In the formula, represents the frequency variable, represents the power spectral density of the th frequency variable, represents the spectrum function of the th frequency variable; Set a reference frequency set, which includes the power grid fundamental frequency and the main harmonic frequency components, as the reference frequency range for evaluating the power grid stability; According to the energy ratio of the power spectral density within the entire frequency range and within the reference frequency range, obtain the power grid power supply stability eigenvalue. The calculation expression is: ; In the formula, represents the reference frequency range, Represents the characteristic value of the power grid power supply stability.

[0028] It should be noted that: by collecting the power grid power supply voltage data in real time in the area where the charging pile is located, using the fast Fourier transform to convert the time-domain fluctuation signal into a frequency-domain signal, then calculating the power spectral density, and extracting the energy distribution characteristics of the power grid at different frequencies. On this basis, a reference frequency set including the fundamental frequency of the power grid and its main harmonic components is set as the ideal frequency band for evaluating the stable operation of the power grid, and by calculating the energy ratio between the non-reference frequency components and the reference frequency components, the characteristic value of the power grid power supply stability is constructed. The characteristic value of the power grid power supply stability can effectively reflect the power supply quality and stability level of the regional power grid, identify hidden abnormal phenomena such as voltage harmonic distortion and frequency offset, so as to accurately judge whether the charging pile is in an area with unstable power supply. Starting from the frequency domain perspective, the present invention introduces a frequency component analysis mechanism, which has higher sensitivity and anti-interference ability, can realize the refined perception of the power grid state, provides a scientific and reliable dynamic input basis for path planning and scheduling decision-making, and has significant technical innovation and engineering application value.

[0029] In S4, a comprehensive analysis is carried out on the charging rate fluctuation characteristic value and the power grid power supply stability characteristic value, and a prediction model is constructed according to the analysis result to judge whether the user can successfully complete the charging task, specifically including: In the process of coordinating the charging pile reservation scheduling and path planning, the charging rate fluctuation characteristic value and the power grid power supply stability characteristic value are obtained, and the charging rate fluctuation characteristic value and the power grid power supply stability characteristic value are constructed into a comprehensive feature vector as the input of the prediction model. Taking the minimization of the error between the predicted charging plan score and the actual charging plan score as the training objective of the model, according to the trained prediction model, the charging plan score is output, and the prediction model is the gradient boosting tree algorithm.

[0030] The training process of the prediction model is as follows: The historical comprehensive feature vector and the charging plan score are obtained as the training data set, and the gradient boosting tree algorithm is trained using the training data set. During the training process, multiple decision trees are used to sequentially fit the residual between the current model prediction result and the true charging plan score, and the overall prediction accuracy is gradually corrected and optimized. In each iteration, the model calculates the loss between the current predicted value and the actual label, and generates a new decision tree accordingly to make up for the error. Finally, the outputs of all weak learners are superimposed to obtain an accurate prediction result. The training goal is to minimize the overall error between the predicted charging plan score and the actual charging plan score.

[0031] After the model training is completed, the system can input the feature vectors of the charging piles collected in real time into the trained gradient boosting tree model, and output the corresponding charging plan scores, which are used to evaluate the reliability and service quality of the charging piles in the current operating state. These scores can be used to dynamically adjust the path planning suggestions for users and the reservation priorities of charging piles, thereby improving the response ability and service level of the overall system.

[0032] The judgment on whether the user can successfully complete the charging task specifically includes: During the collaborative process of charging pile reservation scheduling and path planning, it is judged whether the charging plan score is greater than or equal to a preset threshold. If so, the user can successfully complete the charging task; if not, the user cannot successfully complete the charging task.

[0033] In S5, if the user cannot successfully complete the charging task, the charging pile reservation scheduling strategy is dynamically adjusted, which specifically includes: If it is determined that the user cannot successfully complete the charging task, the system automatically activates a multi-dimensional dynamic scheduling strategy: on the one hand, it identifies sudden load fluctuations according to the changing trend of the charging rate, downgrades the priority of the charging piles with a tendency to fail, and restricts the number of reservation openings during high-load periods; on the other hand, it judges the reliability of regional power supply based on the degree of power grid supply fluctuations. If it is detected that the power grid instability continues to occur, power grading control is implemented for the charging piles in this area, giving priority to ensuring the stable charging of low-power consumption vehicles, re-planning a new charging path, generating a new reservation recommendation plan and actively pushing it to the user terminal; in addition, the system also synchronously uploads the abnormal data to the cloud operation and maintenance platform to provide data support for subsequent equipment maintenance and scheduling optimization.

[0034] Please refer to Figure 2 As shown, a collaborative system for charging pile reservation scheduling and path planning includes: A data collection module that, during the collaborative process of charging pile reservation scheduling and path planning, collects and monitors the charging rate changes and the degree of power grid supply fluctuations of each charging pile in real time; A charging rate evaluation module that calculates the charging rate fluctuation eigenvalue according to the amplitude of the charging rate changes monitored in real time, and is used to evaluate the risk of service interruption of the charging pile in the current usage environment; A power grid supply fluctuation evaluation module that calculates the power grid supply stability eigenvalue based on the degree of power grid supply fluctuations obtained in real time, and is used to judge whether there are problems with unstable power supply in the area where the charging pile is located; A charging prediction module that comprehensively analyzes the charging rate fluctuation eigenvalue and the power grid supply stability eigenvalue, and constructs a prediction model according to the analysis results to judge whether the user can successfully complete the charging task; A dynamic adjustment module, which dynamically adjusts the reservation scheduling strategy of the charging pile if the user fails to complete the charging task smoothly.

[0035] The working principle of the present invention: By collecting the charging rate data of the charging pile and the grid power supply voltage data in real time, and respectively using the continuous wavelet transform and the fast Fourier transform technology, the charging rate fluctuation eigenvalue and the grid power supply stability eigenvalue are extracted, so as to realize the accurate evaluation of the performance state of the charging pile and the stability of the regional power grid. Among them, the charging rate fluctuation eigenvalue can effectively identify the potential service interruption risk caused by factors such as load mutation and equipment aging by analyzing the energy distribution at multiple scales; while the grid power supply stability eigenvalue is based on frequency domain analysis, and judges whether there is abnormal disturbance in the regional power grid by referring to the energy ratio of the reference frequency component and the non-reference frequency component, improving the perception ability of hidden power faults. Further, the system constructs the above two eigenvalues into a comprehensive feature vector, which is used as the input of the gradient boosting tree model, trains the prediction model based on historical data, outputs the charging plan score reflecting the overall service quality of the charging pile, and judges whether the user can complete the charging task smoothly based on this. When the prediction result does not meet the set threshold, the system automatically triggers the dynamic scheduling strategy, re-plans the optimal path in combination with the current charging pile status, alternative site information and user driving conditions, and pushes a new reservation plan to the user terminal, while uploading the abnormal data to the cloud platform for subsequent operation and maintenance optimization. This technical solution realizes the closed-loop control from operation state perception to scheduling response, significantly improves the service quality and scheduling intelligence level of the charging network, and has good practical value and promotion prospects.

[0036] The above formulas are all dimensionless and take their numerical calculations. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0037] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired or wireless (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that contains one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, or magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0038] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. Additionally, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood with reference to the context.

[0039] It should be understood that in various embodiments of the present application, the magnitudes of the sequence numbers of the above processes do not indicate the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0040] The above has described in detail one embodiment of the present invention, but the content described is only a preferred embodiment of the present invention and cannot be considered as limiting the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the application of the present invention should still fall within the scope covered by the patent of the present invention.

Claims

1. A charging pile reservation scheduling and path planning collaborative method, characterized in that: The following steps are involved: S1: In the process of coordination between charging pile reservation scheduling and route planning, the charging rate changes of each charging pile and the fluctuation degree of power grid power supply are collected and monitored in real time; S2: Calculate the charging rate fluctuation characteristic value based on the real-time monitored charging rate change range to assess the risk of service interruption of the charging pile in the current usage environment; S3: Calculate the grid power supply stability characteristic value based on the real-time grid power supply fluctuation degree to determine whether there is a problem of unstable power supply in the area where the charging pile is located; S4: Comprehensively analyze the charging rate fluctuation characteristic values ​​and the grid power supply stability characteristic values, and build a prediction model based on the analysis results to determine whether the user can successfully complete the charging task; S5: If the user cannot successfully complete the charging task, the charging pile reservation scheduling strategy is dynamically adjusted.

2. A charging pile reservation scheduling and path planning collaborative method according to claim 1, characterized in that: The assessment of the risk of service interruption of the charging pile in the current use environment specifically includes: During the coordinated process of charging pile reservation scheduling and route planning, the charging rate data of each charging pile is collected in real time. According to the charging rate change amplitude, the charging rate fluctuation characteristic value is calculated to determine whether the charging rate fluctuation characteristic value is greater than or equal to the preset threshold. If so, the charging pile is at risk of service interruption under the current usage environment. If not, the charging pile is not at risk of service interruption under the current usage environment.

3. A charging pile reservation scheduling and path planning collaborative method according to claim 2, characterized in that: The process of obtaining the charging rate fluctuation characteristic value is as follows: Collect the charging rate time series data of each charging pile in real time, perform continuous wavelet transform on the charging rate time series data to obtain wavelet coefficients, and calculate the energy distribution at each scale based on the wavelet coefficients; The average value of the energy distribution at all scales is calculated as the reference energy, the sum of the absolute values ​​of the reference energy and the energy difference at all scales is calculated, and the sum of the absolute values ​​is ratioed to the total energy of all scales to obtain the charging rate fluctuation characteristic value.

4. A charging pile reservation scheduling and path planning collaborative method according to claim 1, characterized in that: The determining whether there is an unstable power supply problem in the area where the charging pile is located specifically includes: During the coordinated process of charging pile reservation scheduling and route planning, the power supply fluctuation data of each charging pile is collected in real time. According to the degree of power supply fluctuation, the power supply stability characteristic value of the power grid is calculated to determine whether the power supply stability characteristic value is greater than or equal to the preset threshold. If so, there is an unstable power supply problem in the area where the charging pile is located. If not, there is no unstable power supply problem in the area where the charging pile is located.

5. A charging pile reservation scheduling and path planning collaborative method according to claim 2, characterized in that: The process of obtaining the characteristic value of power supply stability of the power grid is as follows: The grid power supply voltage data of the area where each charging pile is located is collected in real time as grid power supply fluctuation data, and the grid power supply fluctuation data is converted from a time domain signal to a frequency domain signal by fast Fourier transform to obtain the corresponding spectrum function; Calculate the power spectral density based on the square of the modulus value of the spectrum function; Setting a reference frequency set, including the fundamental frequency of the power grid and the main harmonic frequency components, as a reference frequency range for evaluating the stability of the power grid; According to the energy ratio of the power spectrum density in the whole frequency range and the reference frequency range, the characteristic value of the power supply stability of the power grid is obtained.

6. A charging pile reservation scheduling and path planning collaborative method according to claim 1, characterized in that: The comprehensive analysis of the charging rate fluctuation characteristic value and the power grid power supply stability characteristic value, and the construction of a prediction model based on the analysis results, specifically includes: In the coordinated process of charging pile reservation scheduling and path planning, the charging rate fluctuation characteristic value and the power supply stability characteristic value are obtained, and the charging rate fluctuation characteristic value and the power supply stability characteristic value are constructed into a comprehensive characteristic vector as the input of the prediction model to minimize the error between the predicted charging planning score and the actual charging planning score as the training target of the model. According to the trained prediction model, the charging planning score is output, and the prediction model is a gradient boosting tree algorithm.

7. A charging pile reservation scheduling and path planning collaborative method according to claim 1, characterized in that: The training process of the prediction model is: The historical comprehensive feature vectors and charging planning scores are obtained as training data sets, and the gradient boosting tree algorithm is trained using the training data sets. During the training process, multiple decision trees are used to fit the residual between the current model prediction results and the actual charging planning scores in turn, and the overall prediction accuracy is optimized by gradual correction. In each iteration, the model calculates the loss between the current prediction value and the actual label, and generates a new decision tree to make up for the error. Finally, the outputs of all weak learners are superimposed to obtain accurate prediction results. The training goal is to minimize the overall error between the predicted charging planning score and the actual charging planning score.

8. A charging pile reservation scheduling and path planning collaborative method according to claim 1, characterized in that: The determining whether the user can successfully complete the charging task specifically includes: In the process of coordination between charging pile reservation scheduling and route planning, it is determined whether the charging planning score is greater than or equal to the preset threshold. If so, the user can successfully complete the charging task; if not, the user cannot successfully complete the charging task.

9. A charging pile reservation scheduling and path planning collaborative method according to claim 1, characterized in that: If the user cannot successfully complete the charging task, the charging pile reservation scheduling strategy is dynamically adjusted, specifically including: If it is determined that the user cannot successfully complete the charging task, the system automatically initiates a multi-dimensional dynamic scheduling strategy: it identifies sudden load fluctuations based on the charging rate change trend, downgrades the priority of fault-prone charging piles, and limits the number of reservations open during high-load periods; it determines the regional power supply reliability based on the degree of grid power supply fluctuation. If it is detected that the grid is continuously unstable, it implements power classification control for the charging piles in the area, giving priority to ensuring the stable charging of low-power vehicles.

10. A charging pile reservation scheduling and route planning collaborative system, characterized in that: A charging pile reservation scheduling and path planning collaborative method as claimed in any one of claims 1 to 9, comprising: A data acquisition module, which collects and monitors the charging rate changes of each charging pile and the fluctuation degree of power supply of the power grid in real time during the coordination of charging pile reservation scheduling and route planning; A charging rate assessment module, which calculates a charging rate fluctuation characteristic value according to the charging rate variation amplitude monitored in real time, and is used to assess the risk of service interruption of the charging pile in the current use environment; A power grid power supply fluctuation assessment module, which calculates a power grid power supply stability characteristic value based on the power grid power supply fluctuation degree obtained in real time, and is used to determine whether there is an unstable power supply problem in the area where the charging pile is located; A charging prediction module, which performs a comprehensive analysis on the charging rate fluctuation characteristic value and the grid power supply stability characteristic value, and builds a prediction model based on the analysis results to determine whether the user can successfully complete the charging task; A dynamic adjustment module is used to dynamically adjust the charging pile reservation scheduling strategy if the user cannot successfully complete the charging task.

Images