Charging pile management method and system

Abstract

The invention discloses a charging pile management method and system, and the method comprises the steps: carrying out the data collection operation according to a current sensor and a temperature sensor of a charging pile, obtaining current data and temperature data, carrying out the data preprocessing, and obtaining the real-time data of the charging pile; according to the real-time data of the charging pile, performing feature extraction operation to obtain a charging pile operation feature vector; according to the charging pile operation feature vector, generating a target energy management model, and obtaining a charging pile energy management strategy; according to the charging pile energy management strategy, strategy optimization updating is carried out, and an optimized charging pile management strategy is obtained; according to charging pile real-time data and the charging pile management strategy, performing anomaly detection to obtain an anomaly score; and when the abnormal score is judged to be greater than a preset abnormal threshold value, generating an early warning signal and sending the early warning signal to a user side. According to the method, the response speed and the early warning capability of charging pile management can be improved.

Description

Technical Field

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

[0002] With the popularity of electric vehicles, the demand for charging piles continues to increase. As the infrastructure for charging electric vehicles, the efficient and stable operation of charging piles is of great significance to the popularization of electric vehicles and green travel. The operation and management of charging piles face multiple challenges, including real-time monitoring of the working status of charging piles, energy management, and ensuring safety and energy saving. As the use environment and load conditions of charging piles become increasingly complex, how to improve the intelligent management level of charging piles, reduce failure rates, and improve energy efficiency and user experience has become an urgent problem to be solved in the industry.

[0003] At present, the management system of charging piles generally adopts traditional monitoring and scheduling strategies, and performs basic operation management through data collection, current and temperature monitoring, etc. The existing technology collects real-time data of charging piles through hardware devices such as current sensors and temperature sensors, and performs preprocessing and feature extraction on the data to generate energy management models and implement scheduling strategies.

[0004] In summary, the existing solutions rely on traditional data analysis methods. Faced with complex operating environments, the response speed and early warning capabilities of charging pile management are insufficient. Summary of the invention

[0005] The present invention provides a charging pile management method and system to improve the response speed and early warning capability of charging pile management.

[0006] In a first aspect, in order to solve the above technical problems, the present invention provides a charging pile management method, comprising:

[0007] According to the current sensor and temperature sensor of the charging pile, data collection operation is performed to obtain current data and temperature data;

[0008] Perform data preprocessing according to the current data and the temperature data to obtain real-time data of the charging pile;

[0009] Performing feature extraction operations according to the real-time data of the charging pile to obtain a charging pile operation feature vector;

[0010] According to the charging pile operation feature vector, multi-dimensional data fusion and optimization modeling are performed to generate a target energy management model and obtain a charging pile energy management strategy;

[0011] According to the charging pile energy management strategy, the strategy is optimized and updated to obtain an optimized charging pile management strategy;

[0012] Perform anomaly detection according to the real-time data of the charging pile and the management strategy of the charging pile to obtain an anomaly score;

[0013] When it is determined that the abnormality score is greater than a preset abnormality threshold, a warning signal is generated and sent to the user end.

[0014] As an optional implementation manner, performing data preprocessing according to the current data and the temperature data to obtain real-time data of the charging pile includes:

[0015] Performing filtering processing on the current data to obtain smoothed current data;

[0016] Performing standardization processing on the temperature data to obtain standard temperature data;

[0017] According to the smoothed current data and the standard temperature data, fusion processing is performed to obtain the real-time data of the charging pile.

[0018] As an optional implementation manner, performing a feature extraction operation according to the real-time data of the charging pile to obtain a charging pile operation feature vector includes:

[0019] According to the real-time data of the charging pile, the load change of the charging pile is calculated to obtain the load fluctuation characteristics of the charging pile;

[0020] Calculate the temperature change of the charging pile according to the real-time data of the charging pile to obtain the temperature fluctuation characteristics of the charging pile;

[0021] Calculating the comprehensive operation state characteristics of the charging pile according to the load fluctuation characteristics of the charging pile and the temperature fluctuation characteristics of the charging pile to obtain the operation characteristic data of the charging pile;

[0022] Vectorization processing is performed based on the charging pile operation characteristic data to obtain a charging pile operation characteristic vector.

[0023] As an optional implementation manner, the calculation of the charging pile operation characteristic vector includes:

[0024] The calculation formula for the load change of the charging pile is as follows:

[0025] ΔP=P(t+Δt)-P(t)+β·P(t)·e -λ ·Δt

[0026] The calculation formula for the temperature change of the charging pile is as follows:

[0027] ΔT=T(t+Δt)-T(t)+γ·ΔT·e -λ ·Δt

[0028] The calculation formula of the comprehensive operating status characteristics of the charging pile is as follows:

[0029]

[0030] Among them, ΔP is the load change; P(t) is the charging pile load at time t; P(t+Δt) is the charging pile load at time t+Δt; β is the adjustment coefficient of the load change; λ is the attenuation factor; Δt is the time interval; e is the base of the natural logarithm; ΔT is the temperature change; T(t) is the charging pile temperature at time t; T(t+Δt) is the charging pile temperature at time t+Δt; γ is the adjustment coefficient of temperature change; R is the comprehensive operating status characteristics of the charging pile; α is the weighting coefficient of the load change; is the weighting coefficient of temperature change; δ is the weighting coefficient of the relationship between load change and temperature change.

[0031] As an optional implementation, performing multi-dimensional data fusion and optimization modeling according to the charging pile operation feature vector, generating a target energy management model, and obtaining a charging pile energy management strategy includes:

[0032] According to the charging pile operation characteristic vector, multi-dimensional data fusion processing is performed to obtain the comprehensive energy demand characteristics of the charging pile;

[0033] According to the comprehensive energy demand characteristics, an energy management optimization model is established, and an optimization method based on a prediction algorithm is used to generate an optimal load scheduling strategy for charging piles;

[0034] According to the optimal load scheduling strategy, multi-objective optimization processing is performed to obtain a charging pile energy management strategy.

[0035] As an optional implementation, the energy management optimization model is established according to the comprehensive energy demand characteristics, and the optimal load scheduling strategy of the charging pile is generated using an optimization method based on a prediction algorithm, including:

[0036] According to the comprehensive energy demand characteristics, a time-space correlation prediction model is used to perform prediction to obtain charging demand prediction data of the charging pile;

[0037] According to the charging demand forecast data, an adaptive learning algorithm is used for optimization to obtain an optimal load dispatching strategy;

[0038] The comprehensive energy demand characteristics include a historical charging data characteristic vector and a traffic demand characteristic vector.

[0039] As an optional implementation, the spatiotemporal correlation prediction model performs prediction and strategy optimization, including:

[0040] The calculation formula of the spatiotemporal correlation prediction model is as follows:

[0041]

[0042] The calculation formula of the strategy optimization process of the adaptive learning algorithm is as follows:

[0043]

[0044] Among them, C s,t represents the predicted value of charging demand in region s at time t; β1, β2 and β3 represent the influence weights of historical charging data characteristics, traffic demand characteristics and charging demand in adjacent regions respectively; H s,t represents the historical charging data feature vector of region s at time t; T s,t represents the traffic demand characteristic vector of area s at time t; α s',t-Δt represents the spatiotemporal correlation factor; C s',t-Δt represents the charging demand of the adjacent area s' at time t-Δt; Δt represents the time interval; β j represents the jth weight coefficient after the model is updated; β j ' represents the jth weight coefficient before the model is updated; η represents the learning rate; ∈ represents the prediction error; Represents the prediction error ∈ relative to the weight coefficient β j ' rate of change.

[0045] As an optional implementation, performing strategy optimization and updating according to the charging pile energy management strategy to obtain an optimized charging pile management strategy includes:

[0046] According to the charging pile energy management strategy, a reinforcement learning model is constructed to obtain a reinforcement learning model;

[0047] According to the reinforcement learning model, load scheduling optimization operation is performed, and reward calculation is performed according to the charging pile operation feature vector and operation target to obtain a reward signal;

[0048] According to the reward signal, real-time dynamic adjustment and strategy optimization and update are performed to obtain an optimized charging pile management strategy.

[0049] As an optional implementation manner, performing anomaly detection according to the real-time data of the charging pile and the management strategy of the charging pile to obtain anomaly scores includes:

[0050] According to the real-time data of the charging pile and the management strategy of the charging pile, a multi-dimensional anomaly detection model is constructed to obtain a multi-dimensional anomaly detection model;

[0051] According to the real-time data of the charging pile and the multi-dimensional anomaly detection model, dynamically calculate the real-time change range of each data dimension to obtain an anomaly detection threshold;

[0052] Perform joint anomaly detection according to the anomaly detection threshold, and calculate the anomaly score for each data dimension;

[0053] According to the anomaly score, a comprehensive calculation of the anomaly score is performed to obtain the anomaly score.

[0054] In a second aspect, the present invention provides a management system for charging piles, including:

[0055] The data acquisition module is used to perform data acquisition operations according to the current sensor and temperature sensor of the charging pile to obtain current data and temperature data;

[0056] A data preprocessing module, used to perform data preprocessing according to the current data and temperature data to obtain real-time data of the charging pile;

[0057] A feature extraction module, used to perform a feature extraction operation based on the real-time data of the charging pile to obtain a charging pile operation feature vector;

[0058] A model building module, used to perform multi-dimensional data fusion and optimization modeling according to the charging pile operation feature vector, generate a target energy management model, and obtain a charging pile energy management strategy;

[0059] A strategy optimization module, used to optimize and update the strategy according to the charging pile energy management strategy to obtain an optimized charging pile management strategy;

[0060] An anomaly detection module, used to perform anomaly detection according to the real-time data of the charging pile and the management strategy of the charging pile, and obtain an anomaly score;

[0061] The abnormality warning module is used to generate a warning signal and send it to the user end when it is determined that the abnormality score is greater than a preset abnormality threshold.

[0062] Compared with the prior art, the present invention has the following beneficial effects:

[0063] The present invention provides a charging pile management method, comprising: performing data acquisition operations according to a current sensor and a temperature sensor of the charging pile to obtain current data and temperature data; performing data preprocessing according to the current data and the temperature data to obtain real-time data of the charging pile; performing feature extraction operations according to the real-time data of the charging pile to obtain a charging pile operation feature vector; performing multi-dimensional data fusion and optimization modeling according to the charging pile operation feature vector to generate a target energy management model to obtain a charging pile energy management strategy; performing strategy optimization and updating according to the charging pile energy management strategy to obtain an optimized charging pile management strategy; performing anomaly detection according to the real-time data of the charging pile and the charging pile management strategy to obtain an anomaly score; when it is determined that the anomaly score is greater than a preset anomaly threshold, generating an early warning signal and sending it to a user end.

[0064] In the present invention, by combining the current and temperature data collected in real time by the charging pile, preprocessing, feature extraction, energy management strategy generation and optimization are performed to form an intelligent management system. The system can adapt to the changes in the operating state of the charging pile in real time, and perform anomaly detection according to the preset abnormal threshold, effectively ensuring the stability and safety of the charging pile. At the same time, the strategy optimization and update uses a reinforcement learning model, which can adaptively adjust the operating strategy of the charging pile to ensure the best operating effect under various environments and load conditions. In addition, the present invention uses an abnormal detection module, combined with the operating feature vector and management strategy of the charging pile, to perform data analysis in real time, generate anomaly scores and trigger early warning signals. This method greatly improves the level of intelligent management of charging piles, avoids equipment failures or safety accidents caused by abnormal situations not being discovered in time, and provides users with a more stable and safe charging experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 It is a schematic diagram of a charging pile management method provided by an embodiment of the present invention;

[0066] Figure 2 It is a schematic diagram of the structure of a charging pile management system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0067] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0068] Reference Figure 1 The first embodiment of the present invention provides a charging pile management method, comprising the following steps:

[0069] S11, performing data collection operations according to the current sensor and temperature sensor of the charging pile to obtain current data and temperature data;

[0070] S12, performing data preprocessing according to the current data and the temperature data to obtain real-time data of the charging pile;

[0071] S13, performing a feature extraction operation according to the real-time data of the charging pile to obtain a charging pile operation feature vector;

[0072] S14, performing multi-dimensional data fusion and optimization modeling according to the charging pile operation feature vector, generating a target energy management model, and obtaining a charging pile energy management strategy;

[0073] S15, performing strategy optimization and updating according to the charging pile energy management strategy to obtain an optimized charging pile management strategy;

[0074] S16, performing anomaly detection according to the real-time data of the charging pile and the management strategy of the charging pile to obtain an anomaly score;

[0075] S17: When it is determined that the abnormality score is greater than a preset abnormality threshold, a warning signal is generated and sent to the user terminal.

[0076] In step S11, data collection operation is performed according to the current sensor and temperature sensor of the charging pile to obtain current data and temperature data.

[0077] It should be noted that the data acquisition operation refers to real-time acquisition of current data and temperature data through the current sensor and temperature sensor of the charging pile. This operation plays an important role in the operation monitoring of the charging pile, and can provide key real-time data support for subsequent energy management, abnormality detection and fault warning. In an embodiment of the present invention, the data acquisition operation is based on the current sensor and temperature sensor in the charging pile. Among them, the current data acquisition operation refers to real-time monitoring of the current of the charging pile load through the current sensor to obtain the current data of the charging pile under various working states. The current sensor can accurately capture the fluctuation of the charging pile load and provide accurate input data for subsequent energy management and load scheduling. The temperature data acquisition operation refers to real-time monitoring of the working temperature of the charging pile through the temperature sensor to obtain the temperature data of the charging pile under different operating conditions. The temperature sensor can accurately sense the temperature rise of the charging pile, ensure that the charging pile operates within a safe temperature range, and provide a basis for temperature fluctuation detection and fault warning. The dual monitoring of current and temperature data can effectively identify potential abnormal conditions and ensure the stability and safety of the charging pile.

[0078] In step S12, data preprocessing is performed according to the current data and the temperature data to obtain real-time data of the charging pile, including:

[0079] Performing filtering processing on the current data to obtain smoothed current data;

[0080] Performing standardization processing on the temperature data to obtain standard temperature data;

[0081] According to the smoothed current data and the standard temperature data, fusion processing is performed to obtain the real-time data of the charging pile.

[0082] It should be noted that the data preprocessing operation refers to processing the current data and temperature data of the charging pile through filtering and standardization to obtain clear and stable real-time data of the charging pile. This operation plays an important role in the charging pile management system and can provide key high-quality data support for subsequent feature extraction, energy management and anomaly detection. In an embodiment of the present invention, the data preprocessing operation is based on the current data and temperature data of the charging pile, and is implemented through steps such as filtering, standardization and fusion. Data preprocessing can significantly improve data quality and ensure the accuracy of subsequent processing.

[0083] Among them, the current data filtering operation refers to the use of a filtering algorithm to process the current data collected by the charging pile, remove the noise and instantaneous fluctuations therein, and obtain smooth current data. In the embodiment of the present invention, the filtering operation is performed by a low-pass filter or other suitable filtering methods, which is not limited by the present invention. The filtering operation can remove high-frequency noise, retain the effective signal of the current data, and provide stable current information for subsequent energy management and abnormality detection. The temperature data standardization operation refers to the standardization of the temperature data of the charging pile, converting the temperature data from different sources into a unified numerical range. Through standardization, the distribution of temperature data is unified, so that the data collected by different sensors are consistent and comparable, which is helpful for subsequent analysis and decision-making. The current data and temperature data fusion operation refers to the fusion of the filtered current data and the standardized temperature data to obtain the real-time operation data of the charging pile. In the embodiment of the present invention, the fusion operation adopts the principal component analysis (PCA) method. Of course, according to the actual application scenario and user needs, the fusion operation can also adopt weighted average and other methods, which is not limited by the present invention. The fusion operation combines the key information of the current data and the temperature data to generate comprehensive real-time data of the charging pile for subsequent feature extraction and management strategy optimization. Data preprocessing operations can clean and integrate the current and temperature data of the charging piles to ensure high data quality and stability, suitable for further intelligent processing. These processes provide a solid foundation for abnormal detection, energy management and strategy optimization of charging piles, ensuring the efficiency and accuracy of the entire charging pile management system.

[0084] In step S13, the feature extraction operation is performed according to the real-time data of the charging pile to obtain the charging pile operation feature vector, including:

[0085] According to the real-time data of the charging pile, the load change of the charging pile is calculated to obtain the load fluctuation characteristics of the charging pile;

[0086] Calculate the temperature change of the charging pile according to the real-time data of the charging pile to obtain the temperature fluctuation characteristics of the charging pile;

[0087] Calculating the comprehensive operation state characteristics of the charging pile according to the load fluctuation characteristics of the charging pile and the temperature fluctuation characteristics of the charging pile to obtain the operation characteristic data of the charging pile;

[0088] Vectorization processing is performed based on the charging pile operation characteristic data to obtain a charging pile operation characteristic vector.

[0089] It should be noted that the feature extraction operation refers to extracting the key operating characteristics of the charging pile by analyzing the real-time data of the charging pile. This operation plays an important role in the management system of the charging pile and can provide key information for subsequent energy management, strategy optimization and anomaly detection. In an embodiment of the present invention, the feature extraction operation is implemented by calculating the load change, temperature change and comprehensive operating status characteristics of the charging pile. The feature extraction process can significantly improve the accuracy and stability of the charging pile status analysis and ensure the effectiveness of subsequent processing.

[0090] Among them, the load change calculation operation refers to calculating the load change according to the real-time data of the charging pile to obtain the load fluctuation characteristics of the charging pile. The load change can effectively reflect the load fluctuation of the charging pile during operation by calculating the difference between the load data of the charging pile at different time points, and provide a key basis for subsequent energy management and load scheduling. The temperature change calculation operation refers to calculating the temperature change of the charging pile according to the real-time temperature data of the charging pile to obtain the temperature fluctuation characteristics of the charging pile. The temperature change can determine whether the charging pile is overheated by calculating the temperature changes of each component of the charging pile, and provide effective information for temperature control and fault warning. The comprehensive operation status characteristic calculation operation refers to calculating the comprehensive operation status characteristics of the charging pile by combining the load fluctuation characteristics and the temperature fluctuation characteristics. This operation obtains a comprehensive operation characteristic by weighted synthesis of the load change and the temperature change, which can comprehensively reflect the state changes of the charging pile during operation and provide basic data for subsequent feature vector generation and strategy optimization. The feature vectorization processing operation refers to converting the calculated comprehensive operation status characteristics into feature vectors to facilitate subsequent model training, anomaly detection and strategy optimization. By converting feature data into vector form, it can be efficiently processed in machine learning and optimization algorithms, providing standardized data input for the intelligent management system of charging piles.

[0091] It is worth noting that the calculation of the charging pile operation characteristic vector includes:

[0092] The calculation formula for the load change of the charging pile is as follows:

[0093] ΔP=P(t+Δt)-P(t)+β·P(t)·e -λ ·Δt

[0094] The calculation formula for the temperature change of the charging pile is as follows:

[0095] ΔT=T(t+Δt)-T(t)+γ·ΔT·e -λ ·Δt

[0096] The calculation formula of the comprehensive operating status characteristics of the charging pile is as follows:

[0097]

[0098] Among them, ΔP is the load change; P(t) is the charging pile load at time t, which is obtained from the current sensor data at time t; P(t+Δt) is the charging pile load at time t+Δt, which is obtained from the current sensor data at time t+Δt; β is the adjustment coefficient of the load change, which is adjusted by experimental data or system demand to control the influence of load change on the comprehensive operating state characteristics; λ is the attenuation factor, which represents the attenuation effect of time correlation in the system on previous data, which is obtained by fitting experimental data and is used to reduce the influence of distant time data on the current state; Δt is the time interval interval, which indicates the time difference between the current and next time steps, is the time step of system sampling; e is the base of the natural logarithm; ΔT is the temperature change; T(t) is the temperature of the charging pile at time t, obtained from the temperature sensor data at time t; T(t+Δt) is the temperature of the charging pile at time t+Δt, obtained from the temperature sensor data at time t+Δt; γ is the adjustment coefficient of temperature change, which is adjusted by experimental data or system requirements; R is the comprehensive operating status feature of the charging pile; α is the weighting coefficient of load change, which is used to adjust the weight of the impact of load change on the comprehensive operating status; is the weighting coefficient of temperature change, which is used to adjust the weight of the impact of temperature change on the comprehensive operating state; δ is the weighting coefficient of the relationship between load change and temperature change, which is used to adjust the relative importance of load and temperature in the comprehensive operating state characteristics.

[0099] In step S14, multi-dimensional data fusion and optimization modeling are performed according to the charging pile operation feature vector to generate a target energy management model and obtain a charging pile energy management strategy, including:

[0100] According to the charging pile operation characteristic vector, multi-dimensional data fusion processing is performed to obtain the comprehensive energy demand characteristics of the charging pile;

[0101] According to the comprehensive energy demand characteristics, an energy management optimization model is established, and an optimization method based on a prediction algorithm is used to generate an optimal load scheduling strategy for charging piles;

[0102] According to the optimal load scheduling strategy, multi-objective optimization processing is performed to obtain a charging pile energy management strategy.

[0103] It should be noted that the energy management model generation operation refers to generating an energy management strategy for a charging pile based on the operating characteristic vector of the charging pile through multi-dimensional data fusion and optimization algorithm. This operation plays an important role in the intelligent management system of the charging pile, and can effectively realize the load scheduling and energy efficiency optimization of the charging pile, and provide support for the stable operation of the charging pile under different load conditions. In an embodiment of the present invention, the energy management model generation operation is implemented through steps such as multi-dimensional data fusion, optimization model establishment, and multi-objective optimization. Through this operation, the accuracy and flexibility of the energy management of the charging pile can be significantly improved, ensuring the efficiency of the subsequent charging strategy.

[0104] Among them, the multi-dimensional data fusion processing operation refers to fusing data of different dimensions according to the operating characteristic vector of the charging pile to obtain the comprehensive energy demand characteristics of the charging pile. By fusing multiple data dimensions such as current, temperature, and load change, the energy demand of the charging pile can be fully reflected, providing accurate basic data for subsequent energy management optimization. The energy management optimization model establishment operation refers to establishing an energy management optimization model based on the comprehensive energy demand characteristics. The model uses an optimization method based on a prediction algorithm to predict energy demand and then generate an optimal load scheduling strategy for the charging pile. Through this prediction method, the energy demand of the charging pile can be predicted in advance, providing a scientific basis for the formulation of the scheduling strategy. The multi-objective optimization processing operation refers to performing multi-objective optimization on the basis of the generated optimal load scheduling strategy. The optimization process aims to balance multiple objectives such as energy efficiency, load balance, and response time of the charging pile, and finally obtain the energy management strategy of the charging pile. Through multi-objective optimization, the charging pile management system can be flexibly scheduled in different usage scenarios to ensure that energy consumption during charging is minimized, while avoiding problems such as excessive load and system instability. Through the above steps, the energy management model generation operation can effectively generate accurate energy management strategies based on the real-time data and needs of the charging pile. These strategies can help charging piles achieve optimal load scheduling and energy efficiency management under different load and environmental conditions, improve the intelligence level of charging piles, and ensure stable and efficient operation of the system.

[0105] It is worth noting that according to the comprehensive energy demand characteristics, an energy management optimization model is established, and an optimization method based on a prediction algorithm is used to generate an optimal load scheduling strategy for charging piles, including:

[0106] According to the comprehensive energy demand characteristics, a time-space correlation prediction model is used to perform prediction to obtain charging demand prediction data of the charging pile;

[0107] According to the charging demand forecast data, an adaptive learning algorithm is used for optimization to obtain an optimal load dispatching strategy;

[0108] The comprehensive energy demand characteristics include a historical charging data characteristic vector and a traffic demand characteristic vector.

[0109] It should be noted that the energy management optimization model is established according to the comprehensive energy demand characteristics, and the optimal load scheduling strategy of the charging pile is generated using an optimization method based on a prediction algorithm. This operation plays an important role in the charging pile management system. It can flexibly adjust the load scheduling of the charging pile according to the changes in charging demand to ensure efficient use of energy during the charging process. In an embodiment of the present invention, the generation of the optimal load scheduling strategy is achieved through steps such as a spatiotemporal correlation prediction model and an adaptive learning algorithm. Through this optimization method, the load scheduling efficiency of the charging pile can be significantly improved, energy waste can be avoided, and the stability of the system can be ensured.

[0110] Among them, the prediction operation of the spatiotemporal correlation prediction model refers to predicting the charging demand of the charging pile using the spatiotemporal correlation prediction model according to the comprehensive energy demand characteristics. The spatiotemporal correlation prediction model can capture the spatiotemporal variation law of charging demand by analyzing historical data and regional traffic demand characteristics, and accurately predict the future charging demand data of the charging pile, providing data support for subsequent load scheduling. The adaptive learning algorithm optimization operation refers to using the adaptive learning algorithm to optimize the load scheduling according to the charging demand prediction data. By dynamically learning and adjusting the charging demand prediction data, the adaptive algorithm can autonomously optimize the load scheduling strategy of the charging pile according to the changes in real-time charging demand, ensure the maximization of resource allocation during the charging process, and meet the charging demand in different time periods and different regions. The comprehensive energy demand feature processing operation refers to using the historical charging data feature vector and the traffic demand feature vector as input features in the spatiotemporal correlation prediction model and the adaptive learning algorithm. The historical charging data feature vector can reflect the past load of the charging pile, and the traffic demand feature vector can capture the changes in traffic flow in the region, providing a more comprehensive prediction basis for the load scheduling of the charging pile.

[0111] It is worth noting that the spatiotemporal correlation prediction model performs prediction and strategy optimization, including:

[0112] The calculation formula of the spatiotemporal correlation prediction model is as follows:

[0113]

[0114] The calculation formula of the strategy optimization process of the adaptive learning algorithm is as follows:

[0115]

[0116] Among them, C s,trepresents the predicted value of charging demand in region s at time t; β1, β2 and β3 represent the influence weights of historical charging data characteristics, traffic demand characteristics and charging demand in adjacent regions respectively; H s,t represents the historical charging data feature vector of region s at time t; T s,t represents the traffic demand characteristic vector of area s at time t; α s',t-Δt represents the spatiotemporal correlation factor; C s',t-Δt represents the charging demand of the adjacent area s' at time t-Δt; Δt represents the time interval; β j represents the jth weight coefficient after the model is updated; β j ' represents the jth weight coefficient before the model is updated; η represents the learning rate; ∈ represents the prediction error; Represents the prediction error ∈ relative to the weight coefficient β j ' rate of change.

[0117] In step S15, the strategy optimization and updating is performed according to the charging pile energy management strategy to obtain an optimized charging pile management strategy, including:

[0118] According to the charging pile energy management strategy, a reinforcement learning model is constructed to obtain a reinforcement learning model;

[0119] According to the reinforcement learning model, load scheduling optimization operation is performed, and reward calculation is performed according to the charging pile operation feature vector and operation target to obtain a reward signal;

[0120] According to the reward signal, real-time dynamic adjustment and strategy optimization and update are performed to obtain an optimized charging pile management strategy.

[0121] It should be noted that the strategy optimization and update according to the energy management strategy of the charging pile refers to adjusting the management strategy of the charging pile in real time through the construction and optimization of the reinforcement learning model. This operation can automatically update and optimize the management strategy according to the real-time operating status of the charging pile and changes in the external environment, ensuring the efficient operation of the charging pile under different loads and working conditions. In an embodiment of the present invention, the strategy optimization and update is achieved through the steps of training the reinforcement learning model, calculating the reward signal, and dynamically adjusting. Through this optimization method, the intelligence level and adaptability of the charging pile management can be significantly improved, ensuring the flexibility and stability of the system.

[0122] Among them, the reinforcement learning model construction operation refers to building a reinforcement learning model according to the energy management strategy of the charging pile. The model can simulate the behavior and reaction of the charging pile in different environments and working conditions through the design of state space, action space and reward function. The reinforcement learning model continuously learns how to select the optimal management strategy through interaction with the environment, thereby optimizing the energy management and load scheduling of the charging pile in actual operation. The reward signal calculation operation refers to calculating the corresponding reward signal according to the action performed by the reinforcement learning model. The reward signal reflects the effect of the charging pile after performing a certain action, such as the efficiency of the energy consumption of the charging pile, the balance of the load scheduling, etc. According to the operation goals of the charging pile (including energy saving, cost reduction or load optimization), the reward signal provides feedback for the learning of the model, thereby helping the model to gradually adjust the strategy in subsequent decisions and develop towards the optimal state. The real-time dynamic adjustment and strategy optimization operation refers to the real-time dynamic adjustment and optimization update of the strategy according to the calculated reward signal. The reinforcement learning model continuously adjusts the strategy parameters so that the charging pile management strategy can automatically adapt to different operating states and external environmental changes. This operation enables the management strategy of the charging pile to be adaptive, and to make the best response under different load, temperature and other changing conditions, ensuring the efficient and stable operation of the charging pile. The strategy optimization update operation can be dynamically adjusted according to the feedback of the reinforcement learning model to ensure the optimization of the charging pile management strategy in different situations. This process enables the charging pile management system to have the ability of real-time learning and self-optimization, improving the overall management efficiency and intelligence level of the charging pile.

[0123] In step S16, performing anomaly detection according to the real-time data of the charging pile and the management strategy of the charging pile to obtain anomaly scores includes:

[0124] According to the real-time data of the charging pile and the management strategy of the charging pile, a multi-dimensional anomaly detection model is constructed to obtain a multi-dimensional anomaly detection model;

[0125] According to the real-time data of the charging pile and the multi-dimensional anomaly detection model, dynamically calculate the real-time change range of each data dimension to obtain an anomaly detection threshold;

[0126] Perform joint anomaly detection according to the anomaly detection threshold, and calculate the anomaly score for each data dimension;

[0127] According to the anomaly score, a comprehensive calculation of the anomaly score is performed to obtain the anomaly score.

[0128] It should be noted that the anomaly detection based on the real-time data of the charging pile and the charging pile management strategy refers to the construction and optimization of a multidimensional anomaly detection model, real-time monitoring of the operating status of the charging pile, and calculation of the anomaly score. This operation can identify potential abnormal conditions in a timely manner to ensure the safe and efficient operation of the charging pile. In an embodiment of the present invention, anomaly detection is achieved through the steps of constructing a multidimensional anomaly detection model, calculating the real-time change range, and integrating the anomaly score. Through this method, the anomaly detection capability and response speed of the charging pile management system can be significantly improved, ensuring the stability and safety of the system.

[0129] Among them, the multidimensional anomaly detection model construction operation refers to building a multidimensional anomaly detection model based on the real-time data and management strategy of the charging pile. The model can handle the complex relationship between multiple data dimensions of the charging pile (including current, temperature, load, etc.), accurately identify abnormal patterns through comprehensive analysis of data of different dimensions, and provide strong support for subsequent anomaly detection. The real-time change range calculation operation refers to dynamically calculating the real-time change range of each data dimension based on the real-time data of the charging pile and the multidimensional anomaly detection model, and then obtaining the threshold of anomaly detection. Through real-time monitoring of each data dimension, the system can adaptively adjust the detection threshold to adapt to the normal fluctuations of the charging pile under different load and environmental conditions, ensuring the flexibility and accuracy of anomaly detection. The joint anomaly detection operation refers to performing joint anomaly detection based on the obtained anomaly detection threshold. This step calculates the anomaly score of each data dimension by comprehensively analyzing the changes in each data dimension of the charging pile. By jointly analyzing multiple data dimensions, the accuracy of anomaly detection can be improved, avoiding misjudgment or missed judgment caused by a single data source. The anomaly score comprehensive calculation operation refers to comprehensively calculating the anomaly scores of each data dimension to obtain the final anomaly score. This step obtains a comprehensive anomaly score by weighting or otherwise integrating the anomaly scores of multiple data dimensions to determine the overall abnormal state of the charging pile. The level of the anomaly score directly affects the subsequent early warning and processing mechanism, ensuring that the charging pile takes appropriate response measures in a timely manner when an abnormality occurs. Through the above steps, the anomaly detection operation can monitor the operating status of the charging pile in real time, accurately identify potential abnormal situations, and make judgments through comprehensive anomaly scores, thereby ensuring the safe and stable operation of the charging pile under various operating conditions.

[0130] In step S17, when it is determined that the abnormality score is greater than the preset abnormality threshold, a warning signal is generated and sent to the user terminal.

[0131] It should be noted that when the abnormal score is determined to be greater than the preset abnormal threshold, a warning signal is generated and sent to the user end, which means that through real-time monitoring and comparison of the abnormal score, it is determined whether there is an abnormal situation in the charging pile, and a warning signal is issued in time. This operation can notify the user and take countermeasures as soon as possible when the charging pile has a potential fault or unstable state, thereby avoiding accidents and ensuring the normal operation of the charging pile. In an embodiment of the present invention, the generation and sending of the warning signal is achieved through steps such as comparing the abnormal score with the threshold and triggering the warning mechanism. Through this method, the fault warning capability of the charging pile can be significantly improved, ensuring the stability and safety of the system.

[0132] Among them, the abnormal score and threshold comparison operation refers to comparing the abnormal score of the charging pile with the preset abnormal threshold to determine whether the charging pile is in an abnormal state. When the abnormal score exceeds the set threshold, it indicates that the charging pile may have a fault or operate abnormally, and it is necessary to pay attention and take corresponding measures. In the embodiment of the present invention, the abnormal threshold is set to 80. Of course, according to the actual application scenario and user needs, the abnormal threshold can also be set to other values ​​such as 75, 85, etc., and the present invention is not limited to this. The warning signal generation operation refers to the system generating a warning signal when the abnormal score exceeds the preset threshold. The signal can reflect the type and severity of the abnormality of the charging pile and provide guidance for subsequent response operations. The content of the warning signal includes information such as the abnormal state description of the charging pile, the abnormal score, and the possible fault type. The warning signal sending operation refers to sending the generated warning signal to the user end. This operation can inform the user of the abnormal state of the charging pile, so that the user can understand the working condition of the charging pile in time, and take corresponding measures according to the warning signal, such as deactivating the charging pile and troubleshooting.

[0133] Reference Figure 2 The second embodiment of the present invention provides a management system for charging piles, including:

[0134] The data acquisition module is used to perform data acquisition operations according to the current sensor and temperature sensor of the charging pile to obtain current data and temperature data;

[0135] A data preprocessing module, used to perform data preprocessing according to the current data and temperature data to obtain real-time data of the charging pile;

[0136] A feature extraction module, used to perform a feature extraction operation based on the real-time data of the charging pile to obtain a charging pile operation feature vector;

[0137] A model building module, used to perform multi-dimensional data fusion and optimization modeling according to the charging pile operation feature vector, generate a target energy management model, and obtain a charging pile energy management strategy;

[0138] A strategy optimization module, used to optimize and update the strategy according to the charging pile energy management strategy to obtain an optimized charging pile management strategy;

[0139] An anomaly detection module, used to perform anomaly detection according to the real-time data of the charging pile and the management strategy of the charging pile, and obtain an anomaly score;

[0140] The abnormality warning module is used to generate a warning signal and send it to the user end when it is determined that the abnormality score is greater than a preset abnormality threshold.

[0141] It should be noted that a charging pile management system provided in an embodiment of the present invention is used to execute all process steps of a charging pile management method in the above embodiment, and the working principles and beneficial effects of the two correspond one to one, so they will not be repeated here.

[0142] In summary, in the present invention, by combining the current and temperature data collected in real time by the charging pile, preprocessing, feature extraction, energy management strategy generation and optimization are performed to form an intelligent management system. The system can adapt to the changes in the operating state of the charging pile in real time, and perform anomaly detection according to the preset abnormal threshold, effectively ensuring the stability and safety of the charging pile. At the same time, the strategy optimization and update uses a reinforcement learning model, which can adaptively adjust the operating strategy of the charging pile to ensure the best operating effect under various environments and load conditions. In addition, the present invention uses an abnormal detection module, combined with the operating feature vector and management strategy of the charging pile, to perform data analysis in real time, generate anomaly scores and trigger early warning signals. This method greatly improves the level of intelligent management of charging piles, avoids equipment failures or safety accidents caused by abnormal situations not being discovered in time, and provides users with a more stable and safe charging experience.

[0143] The embodiment of the present invention further provides a terminal device. The terminal device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a charging pile management program. When the processor executes the computer program, the steps in the above-mentioned various charging pile management method embodiments are implemented, such as Figure 1 Alternatively, the processor implements the functions of each module / unit in the above-mentioned system embodiments when executing the computer program.

[0144] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the terminal device.

[0145] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of terminal devices and do not constitute a limitation on the terminal device. The terminal device may include more or fewer components than the above components, or may combine certain components, or different components. For example, the terminal device may also include input and output devices, network access devices, buses, etc.

[0146] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0147] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the terminal device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0148] Wherein, if the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or system capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0149] It should be noted that the system embodiment described above is merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the system embodiment provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0150] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A charging pile management method, characterized in that: include: According to the current sensor and temperature sensor of the charging pile, data collection operation is performed to obtain current data and temperature data; Perform data preprocessing according to the current data and the temperature data to obtain real-time data of the charging pile; Performing feature extraction operations according to the real-time data of the charging pile to obtain a charging pile operation feature vector; According to the charging pile operation feature vector, multi-dimensional data fusion and optimization modeling are performed to generate a target energy management model and obtain a charging pile energy management strategy; According to the charging pile energy management strategy, the strategy is optimized and updated to obtain an optimized charging pile management strategy; Perform anomaly detection according to the real-time data of the charging pile and the management strategy of the charging pile to obtain an anomaly score; When it is determined that the abnormality score is greater than a preset abnormality threshold, a warning signal is generated and sent to the user end.

2. The charging pile management method according to claim 1, characterized in that: The method of performing data preprocessing according to the current data and the temperature data to obtain real-time data of the charging pile includes: Performing filtering processing on the current data to obtain smoothed current data; Performing standardization processing on the temperature data to obtain standard temperature data; According to the smoothed current data and the standard temperature data, fusion processing is performed to obtain the real-time data of the charging pile.

3. The charging pile management method according to claim 1, characterized in that: The step of performing a feature extraction operation according to the real-time data of the charging pile to obtain a charging pile operation feature vector includes: According to the real-time data of the charging pile, the load change of the charging pile is calculated to obtain the load fluctuation characteristics of the charging pile; Calculate the temperature change of the charging pile according to the real-time data of the charging pile to obtain the temperature fluctuation characteristics of the charging pile; Calculating the comprehensive operation state characteristics of the charging pile according to the load fluctuation characteristics of the charging pile and the temperature fluctuation characteristics of the charging pile to obtain the operation characteristic data of the charging pile; Vectorization processing is performed based on the charging pile operation characteristic data to obtain a charging pile operation characteristic vector.

4. The charging pile management method according to claim 3, characterized in that: The calculation of the charging pile operation characteristic vector includes: The calculation formula for the load change of the charging pile is as follows: ΔP=P(t+Δt)-P(t)+β·P(t)·e -λ ·Δt The calculation formula for the temperature change of the charging pile is as follows: ΔT=T(t+Δt)-T(t)+γ·ΔT·e -λ ·Δt The calculation formula of the comprehensive operating status characteristics of the charging pile is as follows: Among them, ΔP is the load change; P(t) is the charging pile load at time t; P(t+Δt) is the charging pile load at time t+Δt; β is the adjustment coefficient of the load change; λ is the attenuation factor; Δt is the time interval; e is the base of the natural logarithm; ΔT is the temperature change; T(t) is the charging pile temperature at time t; T(t+Δt) is the charging pile temperature at time t+Δt; γ is the adjustment coefficient of temperature change; R is the comprehensive operating status characteristics of the charging pile; α is the weighting coefficient of the load change; is the weighting coefficient of temperature change; δ is the weighting coefficient of the relationship between load change and temperature change.

5. The charging pile management method according to claim 1, characterized in that: The method of performing multi-dimensional data fusion and optimization modeling according to the charging pile operation feature vector, generating a target energy management model, and obtaining a charging pile energy management strategy includes: According to the charging pile operation characteristic vector, multi-dimensional data fusion processing is performed to obtain the comprehensive energy demand characteristics of the charging pile; According to the comprehensive energy demand characteristics, an energy management optimization model is established, and an optimization method based on a prediction algorithm is used to generate an optimal load scheduling strategy for charging piles; According to the optimal load scheduling strategy, multi-objective optimization processing is performed to obtain a charging pile energy management strategy.

6. The charging pile management method according to claim 5, characterized in that: According to the comprehensive energy demand characteristics, Establish an energy management optimization model and use the optimization method based on the prediction algorithm to generate the optimal load scheduling strategy for charging piles, including: According to the comprehensive energy demand characteristics, a time-space correlation prediction model is used to perform prediction to obtain charging demand prediction data of the charging pile; According to the charging demand forecast data, an adaptive learning algorithm is used for optimization to obtain an optimal load dispatching strategy; The comprehensive energy demand characteristics include a historical charging data characteristic vector and a traffic demand characteristic vector.

7. The charging pile management method according to claim 6, characterized in that: The spatiotemporal correlation prediction model performs prediction and strategy optimization, including: The calculation formula of the spatiotemporal correlation prediction model is as follows: The calculation formula of the strategy optimization process of the adaptive learning algorithm is as follows: Among them, C s,t represents the predicted value of charging demand in region s at time t; β1, β2 and β3 represent the influence weights of historical charging data characteristics, traffic demand characteristics and charging demand in adjacent regions respectively; H s,t represents the historical charging data feature vector of region s at time t; T s,t represents the traffic demand characteristic vector of area s at time t; α s',t-Δt represents the spatiotemporal correlation factor; C s',t-Δt represents the charging demand of the adjacent area s' at time t-Δt; Δt represents the time interval; β j represents the jth weight coefficient after the model is updated; β j ' represents the jth weight coefficient before the model is updated; η represents the learning rate; ∈ represents the prediction error; Represents the prediction error ∈ relative to the weight coefficient β j ' rate of change.

8. The charging pile management method according to claim 1, characterized in that: The step of optimizing and updating the charging pile energy management strategy to obtain an optimized charging pile management strategy includes: According to the charging pile energy management strategy, a reinforcement learning model is constructed to obtain a reinforcement learning model; According to the reinforcement learning model, load scheduling optimization operation is performed, and reward calculation is performed according to the charging pile operation feature vector and operation target to obtain a reward signal; According to the reward signal, real-time dynamic adjustment and strategy optimization and update are performed to obtain an optimized charging pile management strategy.

9. The charging pile management method according to claim 1, characterized in that: The performing anomaly detection according to the real-time data of the charging pile and the management strategy of the charging pile to obtain an anomaly score includes: According to the real-time data of the charging pile and the management strategy of the charging pile, a multi-dimensional anomaly detection model is constructed to obtain a multi-dimensional anomaly detection model; According to the real-time data of the charging pile and the multi-dimensional anomaly detection model, dynamically calculate the real-time change range of each data dimension to obtain an anomaly detection threshold; Perform joint anomaly detection according to the anomaly detection threshold, and calculate the anomaly score for each data dimension; According to the anomaly score, a comprehensive calculation of the anomaly score is performed to obtain the anomaly score.

10. A charging pile management system, characterized in that: include: The data acquisition module is used to perform data acquisition operations according to the current sensor and temperature sensor of the charging pile to obtain current data and temperature data; A data preprocessing module, used to perform data preprocessing according to the current data and temperature data to obtain real-time data of the charging pile; A feature extraction module, used to perform a feature extraction operation based on the real-time data of the charging pile to obtain a charging pile operation feature vector; A model building module, used to perform multi-dimensional data fusion and optimization modeling according to the charging pile operation feature vector, generate a target energy management model, and obtain a charging pile energy management strategy; A strategy optimization module, used to optimize and update the strategy according to the charging pile energy management strategy to obtain an optimized charging pile management strategy; An anomaly detection module, used to perform anomaly detection according to the real-time data of the charging pile and the management strategy of the charging pile, and obtain an anomaly score; The abnormality warning module is used to generate a warning signal and send it to the user end when it is determined that the abnormality score is greater than a preset abnormality threshold.

Images