Charging cost analysis method and system for liquid cooling over-charging terminal

Abstract

The embodiment of the invention discloses a charging cost analysis method and system for a liquid cooling over-charging terminal, and belongs to the technical field of data analysis. According to the method, through multi-dimensional data acquisition and deep behavior analysis, accurate description of user charging behavior characteristics can be realized, the accuracy of charging demand prediction and resource scheduling is effectively improved, and the user behavior characteristics are converted into quantifiable parameters, so that the user experience is improved. According to the invention, the formulation of differentiated service strategies can be realized to enhance the personalized adaptation capability of the charging service. Besides, the generation and execution mechanism of the cross-terminal dynamic scheduling strategy can optimize the distribution efficiency of the power resources in the space-time dimension and relieve the local overload problem in the peak period, and the cooperative adjustment function of the real-time power supply parameters and the cost calculation logic can guarantee the charging efficiency and balance the operation stability of the power grid at the same time. In conclusion, the method can significantly improve the resource utilization efficiency of the charging facility.

Description

Technical Field

[0001] The embodiments of the present invention belong to the field of data analysis technology, and specifically relate to a cost analysis method and system for charging a liquid-cooled supercharging terminal. Background Art

[0002] Liquid-cooled supercharging terminal is an advanced charging device of great significance in the field of electric vehicle charging. It uses liquid cooling technology to solve the heat dissipation problem during the charging process. During the supercharging process, due to the high charging power, the traditional air cooling method often cannot meet the heat dissipation requirements. Liquid cooling technology can efficiently remove heat through the circulation of coolant inside the charging device, thereby ensuring the stability and safety of the charging device during high-power charging.

[0003] Liquid-cooled supercharging terminals can achieve charging power far exceeding that of ordinary charging equipment, greatly shortening the charging time of electric vehicles, which plays a key role in improving the convenience of electric vehicles. For example, some liquid-cooled supercharging terminals can replenish a large amount of electricity for electric vehicles in a short period of time, meeting users' urgent charging needs, making scenarios such as long-distance travel of electric vehicles more feasible.

[0004] However, with the widespread use of liquid-cooled supercharging terminals, some problems have also been exposed. Specifically, existing technical solutions often find it difficult to maintain stable operation of the power grid while ensuring charging efficiency, and thus it is difficult to ensure the resource utilization efficiency of charging facilities. Summary of the invention

[0005] The embodiments of the present invention provide a method and system for analyzing the cost of charging a liquid-cooled supercharging terminal, which can solve or partially solve the technical problems involved in the above-mentioned background technology.

[0006] An embodiment of the present invention provides a cost analysis method for charging a liquid-cooled supercharging terminal, which is applied to a liquid-cooled supercharging terminal charging middle station system, and the method includes: collecting operating status data sets of multiple groups of liquid-cooled supercharging terminals, the operating status data sets including charging power time series change records, user charging cycle distribution and corresponding segmented cost settlement results; performing multi-dimensional charging behavior analysis on the operating status data sets to generate a user behavior feature set including charging time period preference mode, power adjustment rules and cost response intensity; constructing a charging preference label for an on-board charging terminal based on the user behavior feature set, the charging preference label including a time period priority weight, a power stability threshold and a cost tolerance interval; generating a dynamic scheduling strategy across liquid-cooled supercharging terminals according to the charging preference label, the dynamic scheduling strategy including a power redistribution path and a cost compensation rule; optimizing the real-time power supply parameters and cost calculation logic of the target liquid-cooled supercharging terminal according to the dynamic scheduling strategy, so as to achieve a coordinated improvement in charging efficiency and resource utilization.

[0007] An embodiment of the present invention provides a liquid-cooled supercharging terminal charging middle station system, comprising at least one processor and a memory; the memory stores computer-executable instructions; the at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the above method.

[0008] An embodiment of the present invention provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the above method are implemented.

[0009] The embodiments of the present invention can accurately characterize the characteristics of user charging behavior through multi-dimensional data collection and in-depth behavior analysis, effectively improve the accuracy of charging demand prediction and resource scheduling, and can realize the formulation of differentiated service strategies by converting user behavior characteristics into quantifiable parameters to enhance the personalized adaptation capabilities of charging services. In addition, the generation and execution mechanism of cross-terminal dynamic scheduling strategies can optimize the allocation efficiency of power resources in the time and space dimensions and alleviate the problem of local overload during peak hours, while the coordinated adjustment function of real-time power supply parameters and cost calculation logic can balance the stability of power grid operation while ensuring charging efficiency. In summary, the embodiments of the present invention can significantly improve the resource utilization efficiency of charging facilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A flow chart of a method for analyzing charging costs of a liquid-cooled supercharging terminal provided in an embodiment of the present invention.

[0011] Figure 2 A schematic diagram of the structure of a liquid-cooled supercharging terminal charging middle station system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0012] 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 part of the embodiments of the present invention, not all of them. Based on the embodiments in 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 embodiments of the present invention.

[0013] The terms "first", "second", etc. in the embodiments of the present invention are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the embodiments of the present invention can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more. In addition, in the embodiments of the present invention, "and / or" means at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0014] Figure 1 A cost analysis method for charging a liquid-cooled supercharging terminal is shown, which is applied to a liquid-cooled supercharging terminal charging middle station system. The method includes the following steps 110-150.

[0015] Step 110: Collecting operation status data sets of multiple groups of liquid-cooled supercharging terminals, wherein the operation status data sets include charging power time series change records, user charging cycle distribution, and corresponding segment fee settlement results.

[0016] In the embodiment of the present invention, the operating status data set refers to a multidimensional data set of the charging process recorded in real time by the liquid-cooled supercharging terminal sensor network, including the charging power time series change record, the user charging cycle distribution and the segmented fee settlement results. Among them, the charging power time series change record stores the instantaneous power value in the form of a time series (such as the 150kW to 200kW fluctuation data collected every second), reflecting the dynamic changes of the power load during the charging process; the user charging cycle distribution records the start time, duration and charging amount of each charging of the user (such as the user's charging behavior from 19:00 to 21:00 every day), which is used to analyze charging habits; the segmented fee settlement results are related to the electricity price policy and the user's actual payment data (such as the segmented records of users paying 1.2 yuan / kWh and 0.8 yuan / kWh under the peak and valley electricity prices), and the segmented fee settlement results can be used for fee sensitivity analysis.

[0017] Specifically, the liquid-cooled supercharging terminal charging middle station system captures the charging power time series change records in real time through the multi-channel sensor network deployed on the terminal, including the instantaneous power value, fluctuation amplitude and duration in seconds. For example, a terminal records the process of power value gradually decreasing from the initial peak value of 200kW to 150kW during a continuous 30-minute charging cycle, forming a time series curve containing 600 data points.

[0018] In addition, the user charging cycle distribution data is collected through the terminal operation interface, covering the start timestamp, end timestamp and charging amount of each charging. For example, user A starts charging from 19:00 to 21:00 every day for a week, and the charging amount is stable in the range of 80kWh to 85kWh.

[0019] Furthermore, the segmented fee settlement results are generated by the billing module, which records the step changes in electricity prices in different time periods and the actual amount paid by users. For example, under the policy of a peak electricity price of 1.5 yuan / kWh and a valley electricity price of 0.8 yuan / kWh, user B generates a segmented billing record during a certain charging due to crossing the peak and valley periods. The above data is synchronized to the central data storage node through an encrypted transmission protocol, and a timestamp alignment algorithm is used to eliminate the time deviation of multi-terminal data to ensure the time consistency of the data set. For abnormal data (such as invalid records where the power suddenly drops to zero), the liquid-cooled supercharging terminal charging middle station system uses a sliding window mean filtering algorithm for cleaning. For example, it interpolates and repairs abnormal points where the power value deviates from the mean by more than 30% for 5 consecutive seconds.

[0020] Step 120: Perform multi-dimensional charging behavior analysis on the operating status data set to generate a user behavior feature set including charging time period preference mode, power adjustment rule and cost response intensity.

[0021] In the embodiment of the present invention, multi-dimensional charging behavior analysis is a process of extracting user behavior characteristics through an algorithm model based on the operating status data set. The charging period preference pattern refers to the distribution of charging frequency and duration of users in different time periods (such as the proportion of charging in the evening peak period of a certain user group exceeds 40%), and the high-frequency time interval is identified through the density clustering algorithm; the power adjustment law describes the behavioral characteristics of users actively or passively adjusting the charging power (such as the average response time when the power drops from 200kW to 150kW), and the typical power curve is matched through the dynamic time warping algorithm; the cost response intensity quantifies the user's sensitivity to cost changes (such as the probability of power reduction increases by 25% when the electricity price increases by 0.1 yuan), combined with the behavior trigger rate and delay time calculation.

[0022] In detail, the liquid-cooled supercharging terminal charging middleware system performs multi-dimensional analysis on the pre-processed data set, and first uses the density-based DBSCAN clustering algorithm to perform time period preference analysis on the charging start timestamp. For example, after dividing 100,000 charging records by hourly granularity, it is identified that the charging records in the 19:00-21:00 period account for 45%, which is significantly higher than other periods, and is defined as a high-frequency charging period group.

[0023] The extraction of power adjustment rules relies on the morphological analysis of the power timing curve. The liquid-cooled supercharging terminal charging middleware system matches the typical power change pattern through the dynamic time warping algorithm (DTW). For example, it is detected that a certain type of user is accustomed to manually reducing the power from 200kW to 150kW within 10 minutes after charging starts. The repetition rate of this behavior in historical data is 72%.

[0024] Furthermore, the calculation of cost response intensity combines segmented cost data with user behavior adjustment records. For example, statistics show that when the real-time electricity price exceeds 1.2 yuan / kWh, 65% of users will trigger a power reduction operation, and the average response delay is 3.2 seconds. The liquid-cooled supercharging terminal charging middle station system generates a user behavior feature set by constructing a three-dimensional feature space (time distribution density, power adjustment frequency, and cost response speed), and each feature dimension is normalized to eliminate the impact of the dimension.

[0025] Step 130: Construct a charging preference label for the vehicle charger based on the user behavior feature set, wherein the charging preference label includes a time period priority weight, a power stability threshold, and a cost tolerance interval.

[0026] In the embodiment of the present invention, the charging preference label is an aggregated expression of user behavior characteristics, including time period priority weight, power stability threshold and cost tolerance interval. The time period priority weight is calculated by weighting the time period coverage frequency and power density (for example, a certain time period is given a weight of 0.7 due to high frequency use and high power demand); the power stability threshold defines the user's acceptable power fluctuation range (for example, fluctuations within ±5% are considered to be a stable state), which is determined based on historical adjustment behavior statistics; the cost tolerance interval defines the user's acceptance boundary for cost changes (for example, 1.0 yuan to 1.2 yuan is a tolerable range), which is generated through the correlation analysis of cost distribution and behavior feedback.

[0027] For example, based on the user behavior feature set, the liquid-cooled supercharging terminal charging middleware system can construct a charging preference label through a weighted fusion algorithm.

[0028] (1) The calculation of time period priority weights takes into account the frequency of time period coverage and the average power density within the time period. For example, a user's charging frequency during the 19:00-21:00 period accounts for 38% and the average power density reaches 180kW. After linear weighting, the weight of this period is set to 0.62.

[0029] (2) The power stability threshold is determined by statistically analyzing the acceptable power fluctuation range for users. For example, analysis shows that the adjustment probability of a certain user group increases to 85% when the power fluctuation exceeds ±8%, so the threshold is set to ±7.5%.

[0030] (3) The cost tolerance interval is generated using a sliding window dynamic calibration algorithm. For example, after dividing the cost data into three sub-intervals of 0.6-0.8 yuan, 0.8-1.0 yuan, and 1.0-1.2 yuan, the proportion of users terminating charging in each interval is 5%, 12%, and 28%, respectively. Based on this, 1.1 yuan is defined as the high tolerance boundary. The label parameters are dynamically updated through an incremental learning mechanism. For example, when it is detected that a user continues to charge at high power for three consecutive times when the electricity price is 1.15 yuan, the system adjusts the upper limit of the cost tolerance interval from 1.2 yuan to 1.25 yuan.

[0031] Step 140: Generate a dynamic scheduling strategy across liquid-cooled supercharging terminals based on the charging preference tag, wherein the dynamic scheduling strategy includes a power redistribution path and cost compensation rules.

[0032] In an embodiment of the present invention, the dynamic scheduling strategy is a resource allocation and cost control rule generated by the liquid-cooled supercharging terminal charging middle station system according to the charging preference tag. The power redistribution path refers to a topological structure that optimizes power distribution among multiple terminals (such as diverting 20% ​​of the power of an overloaded terminal to an adjacent idle terminal), which is dynamically generated based on the load forecasting model and grid constraints; the cost compensation rule is a compensation mechanism designed to balance the cost differences caused by power adjustment (such as compensating users whose costs are overspent due to diversion at 20% of the deviation value), combined with the cost tolerance interval and user priority classification trigger.

[0033] In this step, the liquid-cooled supercharger terminal charging middle station system generates a dynamic scheduling strategy across terminals based on the charging preference label. The formulation of the power redistribution path relies on the load forecasting model. For example, it is predicted that the total regional demand power will reach 15MW during the period of 19:00-21:00 the next day, and the grid supply capacity is 12MW. The system automatically generates a path plan to divert 3MW demand to adjacent terminals. The cost compensation rule adopts a hierarchical response mechanism. For example, for users whose costs increase due to power diversion, when the deviation value is within the tolerance range (within 0.5 yuan), a fixed proportion compensation (20% of the deviation value) is used. When it exceeds the range, the dynamic compensation algorithm (30% of the deviation value + basic compensation) is started. The strategy generation process introduces a multi-objective optimization algorithm, while weighing indicators such as terminal load balance (target value>0.85), user satisfaction (predicted value>4.2 / 5) and grid stability (volatility<5%), and selecting the optimal strategy through Pareto frontier analysis.

[0034] Step 150: Optimize the real-time power supply parameters and cost calculation logic of the target liquid-cooled supercharging terminal according to the dynamic scheduling strategy to achieve a coordinated improvement in charging efficiency and resource utilization.

[0035] In an embodiment of the present invention, real-time power supply parameters are a set of operating parameters used when the liquid-cooled supercharging terminal executes a dynamic scheduling strategy, including power caps, priority queues, and response delays. For example, during peak hours, a 220kW power cap is set for high-priority users, and low-priority users are limited to 180kW. The cost calculation logic refers to the algorithm process for generating user fees based on real-time electricity prices and compensation rules (such as superimposing basic electricity prices, diversion compensation, and peak-valley discounts), which must meet the requirements of real-time calculation and accuracy (such as millisecond response and ±0.5% error control).

[0036] Charging efficiency and resource utilization are the core indicators for measuring system performance. Charging efficiency is calculated by the ratio of the amount of electric energy transmitted per unit time to the theoretical maximum value (such as the actual transmission efficiency increased from 85% to 92%); resource utilization comprehensively evaluates the level of coordinated utilization of power facilities, terminal equipment and grid load (such as the regional grid load rate optimized from 75% to 88%). The two are coordinated and improved through the continuous optimization of dynamic scheduling strategies, such as reducing the peak load of the grid while ensuring the charging speed of users.

[0037] In actual application, the dynamic scheduling strategy can be sent to the liquid-cooled supercharging terminal for execution through control instructions. The power supply parameter optimization adopts a fuzzy control algorithm. For example, when it is detected that the real-time load of a terminal reaches 90%, the initial power of the newly connected user is automatically limited from 200kW to 180kW, and the difference of 20kW is dynamically allocated to high-priority users. The cost calculation logic integrates a real-time electricity price prediction module. For example, when the photovoltaic power generation of the next day is predicted to increase suddenly in combination with weather forecast data, a price reduction strategy is generated 6 hours in advance to adjust the valley electricity price from 0.8 yuan to 0.75 yuan. The system performs a global status scan every 5 minutes. When the actual resource utilization rate is monitored to deviate from the predicted value by more than 8%, the strategy regeneration process is triggered. The execution effect evaluation adopts an A / B test mechanism. For example, 10% of the terminals are classified as the control group to maintain the original strategy. After the experimental group adopts the new strategy, the resource utilization rate increases by 12% and the user complaint rate decreases by 18%. After verifying the effectiveness of the strategy, the full amount is pushed.

[0038] Based on the above content, the technical solution recorded in steps 110 to 150 is implemented through an application scenario example.

[0039] In a liquid-cooled supercharging demonstration area in a city with a high penetration rate of new energy vehicles, the charging peak came at 19:00 on a weekday evening, and the liquid-cooled supercharging terminal charging middle-station system started full-link intelligent regulation. At this time, the 12 liquid-cooled supercharging terminals in the area showed a real-time load rate of 92%. The system first collected the operating status data set from the terminal sensor array: the power time series record showed that the power value of terminal 3 fluctuated from 200kW to 165kW during 18:55 to 19:10, corresponding to a charging capacity of 28kWh; user charging cycle data showed that user C charged 5 times in the 19:00-20:30 period in the past 7 days, with an average single charging capacity of 72kWh; the segmented cost record showed that the user's last charging cost increased by 19.6 yuan due to crossing the 19:00 peak electricity price node (from 0.8 yuan to 1.2 yuan / kWh).

[0040] When the system performs multi-dimensional analysis on massive data, it identifies three typical charging period groups in the area through the improved OPTICS clustering algorithm: morning commuting group (07:30-09:00, accounting for 18%), lunchtime charging group (12:00-13:30, accounting for 23%), and evening peak group (19:00-21:30, accounting for 59%). For the power fluctuation curve of user C, dynamic time regularization matching found that it has a regular behavior of actively reducing power to 80% of the rated value after charging for 10 minutes, triggering the labeling as "high cost sensitive user". The cost response intensity calculation module detects that the probability of power reduction for this user is 83% when the electricity price exceeds 1.1 yuan, and the average response delay is 2.8 seconds, which is significantly higher than the regional average of 65% and 4.5 seconds.

[0041] Based on the above characteristics, the system constructs the charging preference label of user C: the evening peak period is weighted 0.68 in the time period priority weight (the time period frequency accounts for 40% and the power density contributes 60% in the calculation formula); the power stability threshold is set to ±6% (because the probability of interrupting charging increases sharply when the power fluctuation exceeds 7% in its historical data); the cost tolerance range is dynamically calibrated to 0.9-1.15 yuan (originally 0.8-1.2 yuan, and the upper limit was expanded due to the recent two continuous charging at 1.18 yuan). At the same time, the regional heat map shows that there are 4 terminals in an idle state within 500 meters around Terminal 3, and the load rate is only 35%.

[0042] The dynamic scheduling strategy engine immediately generates an optimization plan: 35kW of the current 200kW power allocation of Terminal 3 is diverted to Terminal 5 (idle rate 65%) through the topology network, and a critical fee warning of 1.15 yuan is set for user C. The fee compensation rule module calculates that the charging time is extended by 8 minutes due to the diversion, and automatically compensates the user account with 25% of the deviation value of 0.7 yuan (predicted fee difference). The real-time power supply parameter control unit synchronously updates the maximum output power of Terminal 3 to 165kW, and reserves 10kW of elastic capacity for high-priority users.

[0043] After executing this strategy, the system monitored that the overall load balance in the region increased from 0.62 to 0.79, the actual charging cost of user C was 11.3% lower than expected, and the charging completion time was only extended by 6 minutes (originally predicted to be 8 minutes). During the valley period at 1:00 a.m. the next day, the system automatically started the reverse optimization of the compensation strategy: the diversion power of Terminal 5 was called back to Terminal 3, and the remaining 12kWh of charging demand was completed using the valley electricity price (0.6 yuan), achieving the optimal allocation of resources across time periods. After 30 days of operation verification, the peak utilization rate of charging piles in the area dropped from 88% to 76%, the average user satisfaction score increased from 4.1 to 4.7, and the peak-to-valley difference rate of the power grid decreased by 14.6%, fully demonstrating the technical value from data perception to strategy closed loop.

[0044] In an optional embodiment, the multi-dimensional charging behavior analysis of the operating status data set is performed to generate a user behavior feature set including a charging time period preference mode, a power adjustment rule, and a cost response intensity, including: Filtering a selected charging record subset that meets a preset integrity condition from the operating status data set, wherein the selected charging record subset includes a power fluctuation trajectory within a complete charging cycle and corresponding cost segmentation data; Performing charging period distribution analysis on the selected charging record subset to identify high-frequency charging period groups and corresponding power peak densities; Extracting trigger condition parameters of the power sudden drop event in the power fluctuation trajectory, and generating a dynamic event sequence including a sudden drop time point and a sudden drop amplitude; Performing spatiotemporal correlation analysis on the high-frequency charging period group and the dynamic event sequence to determine the response relationship between the cost segmentation data and the power adjustment behavior; Based on the response relationship and the power peak density, a time period preference pattern, a power adjustment rule and a cost response intensity of a user behavior feature set are generated.

[0045] In this embodiment, the technical solution for the liquid-cooled supercharging terminal charging middle-station system to perform multi-dimensional charging behavior analysis on the operating status data set specifically involves the steps of constructing a user behavior feature set through data screening, feature extraction and correlation analysis. The liquid-cooled supercharging terminal charging middle-station system first screens the charging record subset according to the preset integrity conditions, specifically including charging cycle integrity verification and data continuity verification. The charging cycle integrity verification requires that a single charging record must contain a start timestamp, an end timestamp and a complete power fluctuation trajectory, excluding fragmented records caused by equipment failure or communication interruption; the data continuity verification uses a timestamp continuity detection algorithm to ensure that the interval between adjacent data points in the power fluctuation trajectory does not exceed the set threshold (such as 1 second). The selected charging record subset after screening contains charging cycle data with clear start and end boundaries and complete fluctuation characteristics. For example, a charging process lasting 45 minutes contains 2700 continuous power sampling points and corresponding 24 segmented billing records.

[0046] When analyzing the charging period distribution of the selected charging record subset, the liquid-cooled supercharging terminal charging middle station system divides the charging start time into time slots according to the preset time granularity (such as 15 minutes), and uses an improved density-based clustering algorithm to identify high-frequency charging period groups. The specific process includes: calculating the distribution density of the number of charging records in each time slot, setting a density threshold (such as more than 2 times the standard deviation of the mean) to filter out candidate time slots; performing time window expansion processing on adjacent candidate time slots to generate continuous high-frequency charging time intervals (such as 19:00-21:30). The power peak density calculation module then counts the peak frequency and duration of the power fluctuation trajectory in each high-frequency time interval. For example, an average of 3.2 power peaks per minute are detected in a certain time interval, and the peak duration accounts for 68% of the total duration.

[0047] During the power sag event detection phase, the liquid-cooled supercharging terminal charging middle station system performs morphological analysis on the power fluctuation trajectory and defines a power sag event as a continuous power value drop exceeding a preset threshold (such as 15%) and lasting less than a set window (such as 30 seconds). The trigger condition parameter extraction module records the start time point, end time point and absolute value of the power difference of each sag event. For example, it detects that the power drops from 180kW to 145kW at 19:12:35 during a certain charging process, with a sag of 19.4%. The dynamic event sequence generation unit sorts the sag events by timestamp and constructs an event chain structure containing spatiotemporal attributes, such as generating a structured sequence containing event numbers, sag amplitudes, and intervals between adjacent events.

[0048] In the spatiotemporal correlation analysis phase, the liquid-cooled supercharging terminal charging middle station system maps the high-frequency charging period group with the dynamic event sequence in multiple dimensions: establish the first analysis dimension with the high-frequency period interval as the time baseline, and the second analysis dimension with the sudden drop time point as the event base point. The cost segmentation data is mapped to the corresponding dimension through the timestamp alignment algorithm to generate a thermal distribution diagram of cost changes. For example, when the electricity price is detected to rise from 0.8 yuan to 1.2 yuan during the 19:00-20:00 period, the frequency of sudden drop events in this period increases by 42%. The response relationship calculation engine analyzes the correlation between the sudden drop amplitude and the cost fluctuation value. For example, when the cost increases by 0.1 yuan, the average sudden drop amplitude increases by 5.3%, and the response delay is shortened by 1.8 seconds. Based on this, the cost response intensity index is constructed (such as defining the response coefficient as the rate of change of the power adjustment amplitude caused by the cost change unit).

[0049] The generation process of the user behavior feature set integrates the above multi-dimensional analysis results: the time period preference pattern is calculated by weighting the high-frequency charging time interval and its power peak density. For example, the time period weight coefficient of a certain user group in the 19:00-21:00 period is 0.72. The power adjustment law is characterized by the statistical distribution of the frequency and amplitude of the sudden drop event (such as defining the adjustment intensity as the ratio of the mean and standard deviation of the sudden drop amplitude). The cost response intensity is a three-dimensional feature vector generated by combining the cost-related response coefficient and the delay time attenuation factor. The feature set uses standardization to eliminate dimensional differences, and the principal component analysis is used to reduce the dimension to form an interpretable feature space. For example, the original 12-dimensional data is compressed to 3 principal component dimensions, retaining more than 85% of the information.

[0050] In this way, through multi-dimensional data correlation analysis, deep feature extraction of user charging behavior is achieved, which improves the accuracy of charging demand prediction and resource scheduling. The spatiotemporal correlation model based on dynamic event sequences enhances the quantitative evaluation capability of the impact of fee policies. The standardized feature set generation mechanism provides a unified decision-making input benchmark for cross-terminal collaborative scheduling, effectively supporting the coordinated optimization of charging efficiency and resource utilization.

[0051] In a preferred technical solution, the charging time period distribution analysis is performed on the selected charging record subset to identify the high-frequency charging time period group and the corresponding power peak density, including: density clustering the charging start time in the selected charging record subset according to a preset time granularity to form a plurality of time period distribution clusters; Calculate the time period coverage frequency of each time period distribution cluster, where the time period coverage frequency is determined by the ratio of the number of charging records in the cluster to the total number of records; Filter the time period distribution clusters whose time period coverage frequency exceeds the preset frequency threshold as candidate thermal time period groups; Expand the time window of the charging start time in the candidate thermal time period group to generate a continuous active charging time period interval; The peak occurrence frequency and duration ratio of the power fluctuation trajectory within the active charging period are counted to generate a corresponding power peak density matrix.

[0052] Furthermore, the extracting of trigger condition parameters of the power sudden drop event in the power fluctuation trajectory to generate a dynamic event sequence including a sudden drop time point and a sudden drop amplitude includes: Detecting a section in the power fluctuation trajectory where the continuous power value drops by more than a preset sudden drop threshold as a candidate sudden drop event; Record the starting time point, ending time point and absolute value of power difference of each candidate sudden drop event; Calculate the ratio of the absolute value of the power difference to the initial power value as the sudden drop amplitude; Sorting the candidate sudden drop events in time series according to the starting time point to generate a dynamic event sequence; Analyze the interval duration distribution of adjacent events in the dynamic event sequence to determine the triggering frequency and correlation characteristics of sudden drop events.

[0053] In the above technical solution, the liquid-cooled supercharging terminal charging middle station system analyzes the charging period distribution of the selected charging record subset and extracts the power sudden drop event parameter technical solution, and realizes the deep feature mining of user behavior through data clustering and dynamic event modeling. When the system performs density clustering of the charging start time according to the preset time granularity, it uses the density estimation algorithm based on the Gaussian kernel function to divide the period distribution cluster. The preset time granularity is set as a configurable parameter, and the typical value is 15 minutes to ensure that the period division has sufficient time resolution. For example, after dividing the charging records of 30 consecutive days into 2880 time slots at 15-minute intervals, the system calculates the probability density distribution of the number of charging records in each time slot and identifies the time cluster whose density exceeds the preset frequency threshold. The calculation formula for the time period coverage frequency is the ratio of the number of charging records in the cluster to the total number of records. For example, if a time period cluster contains 1200 records and the total number of records is 10,000, the time period coverage frequency is 12%. The screening of candidate thermal time period groups is dynamically adjusted based on the preset frequency threshold. When a change in regional charging load is detected, the system automatically increases the threshold from the initial value of 8% to 10% to focus on the core time period.

[0054] When the time window of the candidate thermal time period group is expanded, the system uses a sliding window merging algorithm to eliminate the gaps between discrete clusters. For example, a candidate thermal time period group contains two adjacent time period clusters of 19:15-19:30 and 19:30-19:45, which are merged to generate a continuous active charging time period interval of 19:15-19:45. The power peak density calculation module then counts the peak attributes of the power fluctuation trajectory in this interval: the peak frequency is based on the number of power extreme values ​​detected in the statistical cycle per minute (for example, 3.2 peaks are detected per minute in a certain period), and the duration ratio is calculated by calculating the ratio of the peak maintenance time to the total duration (for example, the peak maintenance time is 68%). The construction of the power peak density matrix adopts a two-dimensional coordinate system, with the horizontal axis being the time dimension (such as divided by 5-minute slices), the vertical axis being the power level (such as layered by 50kW intervals), and the matrix element value being the peak density index of the corresponding time-space unit (for example, a unit index of 0.85 indicates the density of the power level at that time).

[0055] The detection of power sag events is based on the first-order derivative analysis of the power fluctuation trajectory. The system defines the sag threshold as the percentage of the power continuous decline exceeding the rated value (such as 15%) and the duration is less than the set window (such as 30 seconds). The identification process of candidate sag events adopts a sliding window difference algorithm: the power change rate of adjacent data points is calculated with a step size of 1 second, and the event start time point is marked when the cumulative decline exceeds the threshold, and the end time point is recorded until the power tends to stabilize or the decline ends. For example, if it is detected that the power drops continuously from 180kW to 153kW (a drop of 15%) within 5 seconds during a certain charging process, it is marked as a valid sag event. The extraction of trigger condition parameters includes recording the start time point, the end time point and the absolute value of the power difference (such as the difference of 27kW in this example), and the sag amplitude is calculated as the ratio of the power difference to the start power value (27 / 180=15%).

[0056] The generation of dynamic event sequences is achieved through a timestamp sorting algorithm, which arranges candidate sudden drop events in ascending order according to the starting time point to form an ordered event chain. For example, three sudden drop events are detected in a charging cycle, and the timestamps are {19:12:35}, {19:18:20}, and {19:25:44}, respectively. Then, an event sequence containing the time sequence position and the sudden drop amplitude is generated. The statistics of the trigger frequency are based on the distribution characteristics of the event interval duration. The system uses the kernel density estimation method to calculate the probability density of the interval time of adjacent events. For example, the probability of detecting an interval time in the range of 3-5 minutes is 65%. The correlation feature analysis module identifies multi-event correlation patterns through event co-occurrence detection. For example, it is found that the probability of a certain type of user triggering power reduction again within 10 minutes after a sudden drop event increases by 40%.

[0057] By applying the above embodiments, high-frequency charging periods can be accurately identified through density clustering and time window expansion, providing spatiotemporal hotspot positioning capabilities for resource scheduling; dynamic event sequence modeling is used to reveal the triggering rules of power sag behaviors, thereby enhancing the system's prediction accuracy for user cost-sensitive behaviors; the construction of a power peak density matrix can achieve quantitative characterization of charging load distribution, thereby supporting the coordinated optimization of power grid stability analysis and terminal power allocation strategies.

[0058] In another preferred technical solution, the high-frequency charging period group is subjected to spatiotemporal correlation analysis with a dynamic event sequence to determine the response relationship of the cost segmentation data to the power adjustment behavior, including: Establish the first analysis layer with the active charging period interval as the time dimension; Establish the second analysis layer with the sudden drop time point in the dynamic event sequence as the event dimension; Mapping the cost segmentation data to the first analysis layer according to the timestamp to generate a cost change thermal distribution map; Matching and associating the sudden drop amplitude with the cost fluctuation value in the cost segmentation data to generate a cost response intensity index; A spatiotemporal correlation response relationship matrix is ​​constructed based on the cost change heat distribution map and the cost response intensity index.

[0059] In this technical solution, the liquid-cooled supercharging terminal charging middle station system constructs a cost response relationship model through the spatiotemporal correlation analysis of the high-frequency charging period group and the dynamic event sequence, forming a multi-dimensional decision support framework. The system first establishes the first analysis layer with the active charging period interval as the time dimension, which divides the continuous time axis into analysis units matching the high-frequency charging period. For example, for the identified active period interval of 19:00-21:00, the system subdivides it into 24 time slices with 5 minutes as the basic unit, and each slice is embedded with charging power, cost data and user behavior labels. The granularity of the time dimension is dynamically adjusted according to the activity of the time period. In high-density periods (such as 19:30-20:30), a finer 2-minute slice is used, while in low-density periods (such as 21:00-21:30), a 10-minute slice is used to optimize the allocation of computing resources. Multi-dimensional data features are integrated in each time slice, including average power value, cost change gradient and user group distribution density, forming the basic structure of the spatiotemporal data cube.

[0060] The second analysis layer constructs discrete analysis nodes based on the sudden drop time point in the dynamic event sequence as the event dimension. The system performs spatiotemporal encoding on the sudden drop events, maps the sudden drop time point of each event to the corresponding time slice, and associates event attribute parameters (such as a sudden drop of 15% and an interval of 5 minutes). The analysis nodes of the event dimension express the correlation between events through a directed graph structure. For example, if the interval between event A (sudden drop of 12%) and event B (sudden drop of 18%) is less than a preset threshold (such as 8 minutes), a causal relationship edge is established and a weight coefficient (such as 0.65) is assigned. The node attributes in the event graph structure include the sudden drop, the triggering user type, and the associated cost segmentation identifier, forming an event-driven analysis network.

[0061] The cost segmentation data is mapped to the time slice unit of the first analysis layer through the timestamp alignment algorithm to generate a heat map of cost changes. The heat map uses color depth encoding technology to express the intensity of cost fluctuations. For example, when the electricity price jumps from 0.8 yuan to 1.2 yuan at the 19:30 time slice, the corresponding unit is displayed as a dark red mark, and the cost stability interval is displayed as light blue. The generation process of the heat map introduces a sliding window smoothing algorithm to eliminate instantaneous fluctuation interference. For example, the cost gradient values ​​of three adjacent time slices are weighted averaged (weight coefficient 0.5-0.3-0.2) to ensure that the visual expression of the cost trend is in line with the actual policy adjustment rhythm.

[0062] The matching association between the sudden drop amplitude and the cost fluctuation value is realized by a two-way mapping mechanism. The forward mapping process extracts the cost fluctuation value at the time of the sudden drop event (such as the cost increase of 0.15 yuan corresponding to the event time point 19:12:35), and calculates the linear proportional relationship between the sudden drop amplitude and the cost change (such as every 0.1 yuan increase in cost triggers an average power reduction of 6.2%). The reverse mapping analyzes the user behavior feedback delay after the cost adjustment (such as after the cost drops by 0.1 yuan, the average response time for users to restore the original power is 4.3 seconds). The system quantifies the incentive effect of different cost ranges on power adjustment behavior by constructing a cost-power response surface model. For example, the cost response sensitivity in the 1.0-1.2 yuan range is increased to 1.8 times the normal level.

[0063] The construction of the spatiotemporal correlation response relationship matrix integrates the heat distribution map and the response intensity index to form a three-dimensional data structure: the first dimension is the time slice sequence, the second dimension is the event type code, and the third dimension is the response intensity level. The filling rule of the matrix elements is determined by the product of the event density and the response intensity in the time slice. For example, if a time slice detects three sudden drop events during 19:15-19:20 and the average response intensity is 0.75, the corresponding matrix unit value is 2.25. The matrix supports a dynamic update mechanism. When a new charging record or a fee policy change is detected, the matrix weight coefficient is adjusted through an incremental learning algorithm (such as a new event updates a unit value from 2.25 to 2.38), ensuring that the model continues to adapt to the evolution of behavioral patterns.

[0064] It can be seen that the dynamic impact of fee policies on user behavior can be accurately portrayed through the dual-dimensional space-time correlation model, providing data support for the formulation of differentiated charging strategies; the constructed multi-dimensional response relationship matrix realizes the quantitative expression of complex behavior patterns, and enhances the system's ability to predict and respond to sudden load fluctuations; the two-way mapping mechanism reveals the interaction mechanism between fee and power adjustment, improves the economy and user acceptance of resource scheduling strategies, and ultimately achieves the coordinated optimization of intelligent charging services and grid stability.

[0065] In an exemplary embodiment, the step of constructing a charging preference label for the vehicle charging terminal based on the user behavior feature set includes: Extracting a charging period preference pattern from the user behavior feature set, wherein the charging period preference pattern is determined by the period weight and power peak density distribution of the active charging period interval; Analyze the user adjustment behavior records in different fee ranges of the fee segmentation data to generate a fee tolerance range; Determining a power stability threshold according to a trigger frequency of a sudden drop event in the dynamic event sequence and a cost response intensity index; The time period weight, power stability threshold and cost tolerance interval are integrated in multiple dimensions to generate a charging preference label for the on-board charging terminal; The parameter weights in the charging preference tag are dynamically adjusted through a real-time charging data stream update mechanism, and the parameter weights are synchronously updated based on the load fluctuation of the liquid-cooled supercharging terminal and the grid cost strategy.

[0066] In detail, the analyzing the user adjustment behavior records of the fee segmentation data in different fee intervals to generate the fee tolerance interval includes: Dividing the expense segmentation data into a plurality of continuous sub-expense intervals according to the expense amount; Count the number of charging behavior adjustments and the corresponding adjustment types within each sub-cost interval, where the adjustment types include active power reduction, charging suspension, and terminal switching operations; Calculating an adjustment trigger rate for each sub-cost interval, wherein the adjustment trigger rate is determined by a ratio of the number of adjustments to the number of charging times; generating a cost tolerance interval according to the adjustment trigger rate and the sub-cost interval span, wherein the cost tolerance interval includes a first tolerance boundary and a second tolerance boundary; The cost tolerance interval is dynamically calibrated through a sliding window algorithm to eliminate the interference of abnormal data on the interval range.

[0067] In an embodiment of the present invention, the step of constructing a charging preference label for the on-board charging terminal by the liquid-cooled supercharging terminal charging middle station system realizes the accurate characterization of the user's charging preference through the multi-dimensional behavior feature fusion and dynamic parameter adjustment mechanism. In detail, when the liquid-cooled supercharging terminal charging middle station system extracts the charging period preference mode from the user behavior feature set, it comprehensively calculates the period weight and the power peak density distribution of the active charging period interval. The determination of the period weight is based on the contribution ratio of the period coverage frequency to the power peak. For example, a period is assigned a weight value of 0.72 because the coverage frequency accounts for 38% and the power peak density index is 0.85. The power peak density distribution is calculated by counting the extreme value distribution characteristics of the power fluctuation trajectory in the active period interval. For example, 3.2 power peak fluctuations per minute are detected in the 19:00-20:00 period, and its density level is marked as a high-density level. The quantitative expression of the period preference mode adopts the form of a three-dimensional feature vector, which includes the period start time offset, the duration coefficient and the power density attenuation factor to ensure the distinguishability and comparability of different period modes.

[0068] Furthermore, the generation of cost tolerance intervals relies on the hierarchical analysis of cost segmentation data. The system divides the cost segmentation data into continuous sub-cost intervals according to the preset amount interval (such as 0.2 yuan), such as 0.6-0.8 yuan, 0.8-1.0 yuan, and 1.0-1.2 yuan. The user adjustment behavior records in each sub-cost interval are extracted through the event log analysis module, including active power reduction events (such as from 200kW to 180kW), charging suspension events (such as suspension time exceeding 5 minutes) and terminal switching operations (such as switching to adjacent low-rate terminals). The adjustment trigger rate is calculated using the sliding window statistics method. For example, if 36 adjustment events occur in 120 charging behaviors detected in the 0.8-1.0 yuan interval, the adjustment trigger rate is 30%. The trigger rate threshold is dynamically set based on historical data. When the adjustment trigger rate of a sub-interval exceeds 1.5 times the standard deviation of the mean, it is marked as a high-sensitivity interval.

[0069] It is understandable that the determination of the first tolerance boundary and the second tolerance boundary adopts a dual threshold determination mechanism. The first tolerance boundary is defined as the critical point of the fee adjustment trigger rate that exceeds the preset threshold for the first time. For example, if the trigger rate is detected to jump from 15% to 32% in the 0.8-1.0 yuan range, 0.8 yuan is set as the first boundary; the second tolerance boundary is the critical point where the trigger rate continues to be higher than the threshold and presents a monotonically increasing trend. For example, in the 1.0-1.2 yuan range, the trigger rate increases linearly from 40% to 55%, and 1.1 yuan is taken as the second boundary. The sliding window dynamic calibration algorithm weights the historical data by the time decay factor, for example, using the exponential weighted moving average method, giving the recent data a weight of 0.7 and the historical data a weight of 0.3, eliminating the interference of abnormal fluctuations (such as special rate policies for holidays) on the interval range. During the calibration process, when it is detected that the boundary point offset exceeds the preset tolerance (such as ±0.05 yuan), the boundary redrawing is triggered. For example, when the user adjustment behavior at the 1.05 yuan fee point is detected to surge for three consecutive billing cycles, the system adjusts the second boundary from 1.1 yuan to 1.05 yuan.

[0070] In addition, the power stability threshold is determined by integrating the trigger frequency of sudden drop events and the cost response intensity index of the dynamic event sequence. The calculation of the trigger frequency is based on the number of sudden drop events in the unit time window. For example, 0.8 sudden drop events are detected per minute during peak hours, and its frequency level is marked as a high frequency level. The cost response intensity index is determined by the correlation coefficient between the sudden drop amplitude and the cost fluctuation value. For example, when the cost increases by 0.1 yuan, the average sudden drop amplitude increases by 7.2%, and the correlation coefficient reaches 0.78. The system uses fuzzy logic rules to map the trigger frequency and response intensity to the power stability threshold. For example, the trigger threshold of the high-frequency and high-response combination is tightened to ±5%, and the low-frequency and low-response combination is relaxed to ±10%. The dynamic adjustment mechanism of the threshold is linked to the power grid stability index. When it is detected that the regional power grid load rate exceeds 85%, the threshold is automatically shrunk by 20% to suppress power fluctuations.

[0071] Specifically, the multi-dimensional fusion process of charging preference labels adopts a feature weighted splicing algorithm. After the time period weight, power stability threshold and cost tolerance interval are normalized to the [0,1] interval value, a dynamic weight coefficient is assigned according to the real-time load status (for example, the time period weight coefficient is increased to 0.6 during peak hours, and the power stability coefficient is reduced to 0.3). The label generation engine encodes three types of parameters into structured data objects, such as a time period weight of 0.72, a power stability threshold of ±7%, and a cost tolerance interval of 0.8-1.1 yuan to form a label instance. The real-time charging data stream update mechanism adjusts the parameter weights through an incremental learning model. For example, when a user is detected to frequently switch terminals at a cost point of 1.05 yuan, the system increases the update frequency of its cost tolerance interval to once a minute, and at the same time reduces the time period weight coefficient by 0.1 to reflect changes in behavior patterns.

[0072] With this design, accurate modeling of charging preference labels is achieved through multi-dimensional parameter fusion and dynamic calibration mechanism, thereby improving the matching degree between charging strategies and user needs; the tolerance interval generation method based on cost behavior correlation analysis enhances the system's adaptability to market policy changes; the dynamic adjustment function of the power stability threshold effectively balances user behavior freedom and grid stability requirements, providing a core decision-making basis for intelligent charging scheduling, and ultimately achieving the dual goals of personalized charging services and optimized power resources.

[0073] In an alternative embodiment, generating a dynamic scheduling strategy across liquid-cooled supercharging terminals according to the charging preference tag includes: Parsing the time period weight, power stability threshold and cost tolerance range in the charging preference tag; Obtain real-time operating load data and grid power supply constraints of multiple liquid-cooled supercharging terminals; Predicting charging demand distribution and power demand peak within a target time window based on the time period weights; generating a power distribution path between terminals according to the power demand peak and the real-time operating load data; The cost compensation coefficient in the power split path is adjusted in combination with the cost tolerance interval to generate a dynamic scheduling strategy across terminals.

[0074] In the next step, the charging demand distribution and the power demand peak within the target time window are predicted based on the time period weights, including: Extracting the active charging time interval and the time period coverage frequency in the time period weight; Construct a forecast input sequence with the period coverage frequency as the time axis and the power peak density as the intensity axis; Analyzing the periodic characteristics in the input sequence through a time series pattern recognition algorithm to generate a charging demand prediction curve within a target time window; Identifying a local extreme point in the charging demand prediction curve as a power demand peak; The charging demand distribution is determined according to the timestamp corresponding to the local extreme point and the terminal location information.

[0075] In addition, after generating the cross-terminal dynamic scheduling strategy, the method further includes: Real-time monitoring of the execution effect data of the dynamic scheduling strategy, wherein the execution effect data includes resource utilization improvement rate and user satisfaction index; Compare the difference between the execution effect data and the preset optimization target to generate strategy adjustment parameters; Feeding back the strategy adjustment parameters to the updating mechanism of the charging preference tag to form a closed-loop optimization link; Through multiple rounds of iterative optimization, the optimal scheduling strategy is gradually converged to achieve adaptive matching of charging resource allocation and user needs.

[0076] In this embodiment, the liquid-cooled supercharger terminal charging middle station system generates a technical solution for cross-terminal dynamic scheduling strategies, and realizes efficient allocation of charging resources through multi-dimensional parameter integration and closed-loop optimization mechanism. When the system parses the charging preference label, it extracts the active charging time interval and the time period coverage frequency from the time period weight. For example, it identifies that the weight coefficient of the 19:00-21:00 time period is 0.75, and the time period coverage frequency is 45%. The power stability threshold is determined based on the trigger frequency of sudden drop events in the dynamic event sequence (such as 0.6 times per minute) and the cost response intensity index (such as every 0.1 yuan increase in cost triggers a power reduction of 8.2%). For example, the threshold is set to ±7% to balance the user's behavior freedom and the grid stability requirements. The cost tolerance interval determines the boundary value (such as setting the first tolerance boundary to 1.05 yuan and the second boundary to 1.15 yuan) by analyzing the adjustment trigger rate distribution of the sub-cost interval (such as 38% trigger rate in the 1.0-1.2 yuan interval), and dynamically calibrates the interval range in combination with the sliding window algorithm to eliminate abnormal data interference (such as boundary offset caused by sudden changes in charging behavior during holidays).

[0077] When obtaining real-time operating load data, the system collects the instantaneous power value, temperature status and queue length of each node through the terminal sensor network. For example, it monitors that the load rate of terminal No. 3 is 95%, and the load rate of the adjacent terminal No. 5 is only 58%. The power supply constraint analysis module synchronously obtains the real-time power supply capacity of the regional power grid (such as the maximum output power of 12MW), the line transmission loss rate (such as 3.2%) and the stability index (such as the voltage fluctuation threshold ±5%) to form a multi-dimensional constraint matrix. The demand forecasting model based on time period weights constructs an input sequence with the time period coverage frequency as the time axis and the power peak density as the intensity axis. For example, the 19:00-21:00 time period data of the past 30 days is sliced ​​into 15 minutes to generate an input sequence containing 96 data points. The time series pattern recognition algorithm uses the long short-term memory network (LSTM) to mine the periodic features in the sequence (such as a 23% increase in power demand during the daily peak period) to generate a charging demand forecast curve for the target time window (such as 19:00-21:00 the next day). The curve local extreme point detection module identifies the power demand peak through derivative analysis (such as predicting a peak demand of 15.2MW at 19:45), and generates a spatial distribution heat map (such as the commercial area accounts for 62%) based on the terminal geographic location information (such as Terminal 3 is located in the center of the commercial district).

[0078] The generation of power diversion paths is based on graph optimization algorithms, with terminal nodes modeled as weighted vertices and power grid lines modeled as edges. The system calculates the optimal diversion path based on the peak power demand (e.g., 15.2MW) and real-time load data (e.g., the available power margin of terminal 3 is 200kW). For example, the 180kW load of terminal 3 is distributed to terminal 5 through a low-loss path (transmission loss rate of 1.8%) in the topological network. The adjustment of the cost compensation coefficient is dynamically set according to the cost tolerance interval. For example, when the diversion causes the user's cost to increase by 0.8 yuan (exceeding the compensation trigger point of the second tolerance boundary of 1.15 yuan), the hierarchical compensation mechanism (basic compensation rate of 20% + dynamic adjustment rate of 5%) is activated. The output of the dynamic scheduling strategy includes a power allocation instruction set (e.g., the power upper limit of terminal A is adjusted to 200kW, and the power upper limit of terminal B is increased to 180kW) and a cost compensation parameter table (e.g., the compensation coefficient of user group C is 0.25), which is sent to each terminal execution unit through an encrypted control channel.

[0079] The execution effect monitoring module collects resource utilization improvement rate (such as the average regional load rate optimized from 85% to 78%) and user satisfaction index (such as the satisfaction score increased from 4.1 to 4.6) in real time. The difference value calculation engine compares the actual data with the preset optimization target (such as the load balance target of 0.8 and the satisfaction threshold of 4.5) to generate strategy adjustment parameters (such as the time period weight coefficient is reduced by 0.1 and the compensation rate is increased by 3%). When the parameters are fed back to the charging preference label update mechanism, the incremental learning algorithm is used to adjust the label parameters. For example, when it is detected that the boundary offset of the cost tolerance interval exceeds the tolerance (such as 0.05 yuan), the interval recalibration process is triggered. During multiple rounds of iterative optimization, the system saves the historical strategy set (such as V1.2 to V1.5 versions) through the strategy version management module, and selects the optimal strategy based on the convergence condition (such as the difference value of three consecutive rounds of optimization is less than 2%). The adaptive matching mechanism finally formed can dynamically adjust the power allocation granularity (such as from 50kW to 10kW) and compensation rules to achieve high-precision adaptation of resource allocation and user needs.

[0080] Therefore, through multi-dimensional data fusion and closed-loop feedback mechanism, the dynamic scheduling strategy can be accurately generated and continuously optimized, thereby improving the global allocation efficiency of charging resources; the prediction model based on spatiotemporal feature analysis enhances the adaptability to complex demand fluctuations and ensures the stability of grid operation; the synergy between the hierarchical compensation mechanism and the dynamic parameter adjustment function balances the economic benefits of users and the operating costs of the system, and promotes the coordinated development of intelligent charging services and sustainable grid operations.

[0081] In an optional technical approach, the real-time power supply parameters and cost calculation logic of the target liquid-cooled supercharging terminal are optimized according to the dynamic scheduling strategy, including: Determine a threshold allocatable power value of the target terminal according to the power split path in the dynamic scheduling strategy; Adjust the cost ladder calculation rule of the target terminal in combination with the cost tolerance interval in the charging preference tag; Real-time monitoring of the target terminal's power usage and user behavior feedback signals; Dynamically optimize the priority allocation mechanism in the power supply parameters to ensure power supply priority for users with active time period weights; The cost balance algorithm is used to eliminate the cost differences caused by power diversion and maintain the stability of user cost expenditure within the cost tolerance range.

[0082] Wherein, the cost balancing algorithm is used to eliminate the cost difference caused by power splitting, including: Identify user groups whose cost deviation due to power diversion exceeds a preset threshold; Extracting a cost tolerance interval boundary value in the charging preference tag of the user group; Calculate the degree of deviation of the cost deviation from the cost tolerance interval boundary; generating a dynamic compensation coefficient according to the degree of deviation, wherein the compensation coefficient is positively correlated with the degree of deviation; The dynamic compensation coefficient is embedded in the cost calculation logic to achieve real-time correction of cost deviation.

[0083] Based on this design idea, the cold super-charging terminal charging middle station system optimizes the real-time power supply parameters and cost calculation logic according to the dynamic scheduling strategy, and realizes the efficient use of charging resources and precise control of user costs through multi-dimensional parameter dynamic adaptation and real-time feedback mechanism. When the system determines the threshold allocatable power value of the target terminal according to the power diversion path in the dynamic scheduling strategy, it adopts a joint optimization algorithm based on load balancing and grid constraints. For example, when it is detected that the total load demand in the area where the target terminal is located is 15.2MW and the upper limit of the power supply of the power grid is 13.8MW, the system calculates the optimal diversion ratio through the topological path loss model (such as the line loss rate of 1.8%), and allocates the over-limit 1.4MW load to the available capacity of the adjacent terminal according to priority. The setting of the threshold allocatable power value takes into account the maximum carrying capacity of the terminal equipment (such as the rated power of a single terminal of 250kW) and the real-time temperature status (such as automatically lowering the power upper limit by 10% when the heat dissipation efficiency decreases), forming a dynamically adjusted safe operation boundary.

[0084] The adjustment of the cost ladder calculation rules deeply integrates the cost tolerance interval parameters in the charging preference label. The system maps the boundary values ​​of the cost tolerance interval (such as 0.8-1.1 yuan) to the ladder rate calculation engine, and automatically triggers the rate smoothing algorithm when the real-time electricity price approaches or exceeds the boundary. For example, when the cost approaches the upper limit of 1.1 yuan, the system uses piecewise linear interpolation to adjust the rate growth gradient from the conventional 0.05 yuan / level to 0.03 yuan / level, slowing down the speed at which user costs reach the tolerance boundary. The dynamic adjustment module of the ladder rule synchronously monitors user behavior feedback signals. For example, when it is detected that the power reduction frequency of a certain user group increases by 15% after the rate adjustment, the rate ladder interval is automatically reduced (such as from 0.1 yuan to 0.08 yuan) to enhance the response sensitivity of the strategy.

[0085] The real-time monitoring module collects power utilization indicators through the distributed sensor network deployed on the terminal, including instantaneous power value, cumulative energy consumption and power fluctuation variance. For example, if the power utilization rate of a terminal is continuously higher than 90% during the period of 19:30-20:00, the system automatically generates a load warning signal. The analysis of user behavior feedback signals uses natural language processing and pattern recognition technology to analyze the satisfaction ratings (such as 1-5 stars) and text feedback (such as "charging speed is too slow") submitted by users through the terminal interface, and quantify them into behavior feedback indexes (such as satisfaction index 4.2 corresponds to behavior parameter 0.85). The priority allocation mechanism of power supply parameters is dynamically adjusted according to the time period weight and user level. For example, for the VIP user group with a high time period weight (0.75), an additional 15% of power elastic capacity is allocated during peak hours to ensure that its charging efficiency is not affected by load fluctuations.

[0086] The core of the cost balance algorithm is to identify and eliminate the cost deviation caused by power diversion. The system calculates the absolute value of the deviation by comparing the user's original charging plan cost with the actual cost after diversion (for example, user A's planned cost is 58 yuan, the actual cost is 63 yuan, and the deviation is 5 yuan). The setting of the preset threshold is dynamically adjusted according to the width of the cost tolerance interval (for example, when the interval width is 0.3 yuan, the threshold is set to 1.5 yuan). When the deviation exceeds the threshold, the multi-level compensation process is started. For example, for the user group with a deviation of 5 yuan, the second boundary value of its cost tolerance interval (such as 1.1 yuan) is extracted, and the degree of deviation is calculated as (5-1.1) / 1.1=3.55 times, and a dynamic compensation coefficient of 0.35 is generated (the coefficient is positively correlated with the degree of deviation but the upper limit is limited by the saturation function). When the compensation logic is embedded in the cost calculation engine, a layered superposition mechanism is adopted, such as superimposing the compensation amount on the basic rate (such as 5 yuan deviation × 0.35 coefficient = 1.75 yuan compensation), and returning it in real time through user account points or electricity fee deductions.

[0087] The generation process of the dynamic compensation coefficient introduces a time decay factor and a behavior feedback weight. For example, for users whose charging costs exceed the standard three times in a row due to diversion, the system gradually increases the compensation coefficient (from 0.2 to 0.4), and adjusts the weight according to the user's historical satisfaction score (such as the weight of users with a score of 4.5 is set to 0.8, and the weight of users with a score of 3.0 is set to 0.5). The cost correction data is synchronized to the billing database in real time to ensure the accuracy and traceability of the bill data. The system performs a global cost balance status scan every 5 minutes. When it detects that the overall deviation rate of the region exceeds 2%, it triggers the compensation rule to optimize the process, such as adjusting the compensation coefficient baseline value from 0.3 to 0.35.

[0088] In this way, through the synergy of dynamic threshold power allocation and intelligent cost compensation mechanism, the problem of out-of-control user costs caused by power diversion can be effectively solved, ensuring the fairness and economy of charging services; the priority allocation mechanism based on real-time monitoring data significantly improves the charging experience of high-demand users and enhances the system's service differentiation capabilities; the adaptive compensation strategy of the cost balance algorithm achieves accurate matching of user cost expenditure and psychological expectations while maintaining controllable operating costs. The closed-loop optimization mechanism promotes the evolution of charging resource allocation from static preset to dynamic intelligence by continuously calibrating power supply parameters and cost rules, providing core technical support for building a flexible and scalable intelligent charging network, and ultimately achieving the dual goals of efficient use of power resources and improved user satisfaction.

[0089] In an extended embodiment, the step of gradually converging to the optimal scheduling strategy through multiple rounds of iterative optimization to achieve adaptive matching of charging resource allocation with user needs includes: Monitor the real-time execution effect data set generated during the execution of the current dynamic scheduling strategy, wherein the real-time execution effect data set includes a resource utilization fluctuation curve of each terminal and a user satisfaction feedback sequence; Compare the real-time execution effect data set with the preset optimization target layer by layer to identify the resource utilization deviation and satisfaction difference value; Generate a multi-dimensional strategy adjustment parameter set based on the resource utilization deviation and satisfaction difference value, wherein the parameter set includes a time period weight correction coefficient, a power diversion compensation factor, and a cost tolerance calibration amount; Injecting the multi-dimensional strategy adjustment parameter set into the update link of the charging preference label, triggering dynamic calibration of the label parameters, and generating an optimized charging preference label version; Re-parse the time period priority weight, power stability threshold and cost tolerance interval based on the optimized charging preference label version, and reconstruct the input conditions of the dynamic scheduling strategy; Based on the reconstructed input conditions, the power redistribution path and cost compensation rules are parameterized and adjusted to generate an updated scheduling strategy that adapts to the current resource status and user needs; Execute the updated scheduling strategy and start a new round of execution effect monitoring to form a closed-loop feedback optimization link; The preset convergence conditions are used to determine whether the current updated scheduling strategy has reached the optimal balance between resource allocation and user needs: if not, the next round of iterative optimization is triggered; if reached, the optimization process is terminated and the optimal scheduling strategy is locked.

[0090] In detail, the liquid-cooled supercharging terminal charging middle-station system realizes the technical solution of adaptive matching of charging resource allocation and user demand through multiple rounds of iterative optimization, and builds a dynamic closed-loop intelligent scheduling system. The system collects and integrates the resource utilization fluctuation curves and user satisfaction feedback sequences of each terminal in real time, forming a full-dimensional execution effect data set covering the equipment operation status and user behavior response. The resource utilization fluctuation curve is generated based on the instantaneous power value, load rate and temperature data uploaded by the terminal sensor network. The instantaneous fluctuation is smoothed by the sliding window mean algorithm (such as calculating the mean with a 5-minute window) to generate a smooth curve reflecting the load trend. The construction of the user satisfaction feedback sequence adopts multi-source data fusion technology, integrating terminal interface rating data (such as 1-5 star rating), voice feedback semantic analysis results (such as "charging speed satisfaction" is mapped to a satisfaction index of 0.8) and behavior pattern derivation parameters (such as the inverse correlation coefficient between charging interruption rate and power adjustment frequency) to form a normalized satisfaction index.

[0091] The difference comparison engine matches the real-time data set with the preset optimization target layer by layer. The standard deviation weighted model is used to calculate the resource utilization deviation. For example, when the regional target load balance is 0.8 and the actual value is 0.65, the deviation is quantified as (0.8-0.65) / 0.8×100%=18.75%. The satisfaction difference value is calculated by comparing the square of the difference between the actual satisfaction index and the target threshold (such as 4.2 / 5.0). For example, when the actual value is 3.9, the difference value is (4.2-3.9)²=0.09. The generation module of the multi-dimensional strategy adjustment parameter set dynamically generates the time period weight correction coefficient (such as a 0.1 decrease in the weight for every 5% increase in load deviation), the power diversion compensation factor (such as a 2% increase in the compensation rate for every 0.1 increase in the satisfaction difference value) and the cost tolerance calibration amount (such as a 10% decrease in the user behavior feedback index triggers a 0.05 yuan expansion of the tolerance interval).

[0092] The dynamic calibration process of the charging preference label adopts an incremental parameter injection mechanism. The system weights and fuses the time period weight correction coefficient with the original label parameter. For example, the original time period weight of 0.75 is updated to 0.675 after the correction coefficient of -0.1 is superimposed. The adjustment of the power stability threshold is dynamically scaled according to the compensation factor. For example, when it is detected that power diversion has caused a decrease in satisfaction, the threshold is relaxed from ±7% to ±10% to reduce the frequency of user behavior intervention. The application of the cost tolerance calibration amount is achieved by shifting the interval boundary. For example, when the calibration amount is +0.05 yuan, the original interval of 0.8-1.1 yuan is expanded to 0.8-1.15 yuan. The label update link adopts a version control mechanism to retain historical parameter snapshots (such as versions V2.1 to V2.3) to support rollback operations, ensuring that the system can quickly recover to a stable state when the parameter adjustment is abnormal.

[0093] When reconstructing the dynamic scheduling strategy input conditions, the system re-parses the optimized label parameters: the calculation of time period priority weights introduces a load deviation compensation factor, for example, the inverse of the deviation (1 / deviation) is added to the peak period weight calculation formula to give the high-load area an additional boost in time period weights; the determination of power stability thresholds integrates real-time grid fluctuation data. For example, when it is detected that the regional voltage fluctuation rate exceeds 2%, the threshold is automatically shrunk by 20% to enhance grid stability; the boundary calibration of the cost tolerance interval is combined with the historical strategy execution effect. For example, for intervals where there are still differences in satisfaction after three consecutive calibrations, an exponential decay algorithm is used to reduce the calibration step size to increase the convergence speed.

[0094] The optimization of the power redistribution path adopts an adaptive graph network model, superimposing a real-time load thermal layer on the original topology. For example, when the load rate of a terminal jumps from 75% to 92%, the system adds virtual nodes to its associated path to expand the diversion path selection space. The parameterized adjustment of the cost compensation rule introduces satisfaction feedback weights. For example, a double compensation coefficient is given to the high satisfaction user group (score>4.5), while the low satisfaction group (score<3.0) uses the basic compensation rate. The output of the updated scheduling strategy includes a dynamic power allocation matrix and a hierarchical compensation rule table, which are synchronized to each terminal execution unit through an encrypted control channel, and a version compatibility verification mechanism (such as verification protocol hash value matching) is enabled to ensure the safe deployment of the strategy.

[0095] The closed-loop feedback optimization link is operated in an event-driven mode. A new round of optimization iteration is triggered when the new strategy executes for a full preset period (such as 30 minutes) or a sudden change in key indicators (such as a 15% drop in the satisfaction index) is detected. The convergence condition judgment module comprehensively evaluates the results of multiple rounds of optimization: the resource utilization deviation must be reduced by less than 1% for three consecutive iterations, the satisfaction difference value must be stable within the ±5% range of the target threshold, and the cost tolerance calibration amount change rate must be less than 0.5%. When the above conditions are met, the system locks the current strategy version as the optimal solution, starts the persistent storage process, solidifies the strategy parameters into the distributed database, and releases the computing resources occupied by the optimization process.

[0096] It can be seen that the continuous self-improvement of charging resource allocation strategy is achieved through closed-loop feedback and multi-round iterative optimization mechanism, which significantly improves the system's adaptability to dynamic environments; the intelligent generation and injection mechanism of multi-dimensional strategy adjustment parameters ensures the deep coupling of user behavior characteristics and grid operation status, and enhances the accuracy and robustness of the dispatching strategy; the adaptive convergence judgment model effectively balances the optimization efficiency and result stability to avoid falling into the local optimal solution; version control and rollback functions improve the system's fault tolerance and ensure continuous and reliable services. Finally, an intelligent charging management platform with autonomous evolution capabilities is constructed to achieve a high degree of unity between the global optimization configuration of power resources and the satisfaction of users' personalized needs, providing core technical support for the operation of large-scale charging facilities under the new power system.

[0097] In a further scalable embodiment, the power redistribution path and the cost compensation rule are parameterized based on the reconstructed input conditions to generate an updated scheduling strategy adapted to the current resource status and user needs, including: Obtaining the updated value of the time period priority weight, the power stability threshold adjustment amount, and the cost tolerance calibration amount in the reconstructed input conditions; Analyze the matching relationship between the priority weight update value of the time period and the current terminal load distribution, and determine the priority allocation coefficient in the power redistribution path; Dynamically expand or shrink the power fluctuation tolerance range in the power redistribution path according to the power stability threshold adjustment amount to generate a path constraint condition adapted to the current grid stability state; Performing gradient correction on the compensation coefficient in the cost compensation rule in combination with the cost tolerance calibration amount to generate a compensation rule adjustment parameter that matches the user's cost sensitivity; Inputting the priority allocation coefficient, path constraint condition and compensation rule adjustment parameter into a strategy generation engine to generate a candidate scheduling strategy set including an updated power diversion ratio and a cost compensation mechanism; Based on the candidate scheduling strategy set, a multi-objective trade-off evaluation is performed on the terminal load balance, cost deviation tolerance and user satisfaction prediction value, and the candidate strategy with the highest comprehensive score is selected as the updated scheduling strategy; Verify the compatibility of the updated scheduling strategy with historical execution effect data to ensure that the adjustment range of the strategy parameters is within the preset safety threshold; The verified updated scheduling strategy is output and embedded in the real-time control system of the liquid-cooled supercharging terminal for execution.

[0098] In this embodiment, the liquid-cooled supercharge terminal charging middle station system performs parameterized adjustment on the power redistribution path and cost compensation rules after reconstructing the input conditions, and realizes the dynamic adaptation of the scheduling strategy through multi-dimensional parameter collaborative optimization and multi-objective decision-making mechanism. When the system obtains the updated value of the priority weight of the reconstructed time period, it uses the time-space matching algorithm to analyze its correlation with the current terminal load distribution. For example, when it is detected that the weight of a certain time period is updated from 0.75 to 0.68, the system determines the load density change in the corresponding area of ​​the time period (such as from 85% to 72%) through the load thermal layer matching algorithm, and then calculates the priority allocation coefficient in the power redistribution path. The priority allocation coefficient is generated by using a weighted attenuation model, combining the time period weight value (0.68), the load density difference (13%) and the historical strategy execution effect (such as the success rate of the past three optimizations in this time period is 92%), to generate a dynamic coefficient (such as 0.65) for controlling the resource acquisition priority of different terminals during the power diversion process.

[0099] The application of power stability threshold adjustment is realized through a dynamic constraint generator. The system adjusts the power fluctuation tolerance range according to the direction of the threshold change (expansion or contraction). For example, when the threshold is expanded from ±7% to ±10%, the maximum allowable fluctuation range in the path constraint condition is increased synchronously, allowing the terminal to maintain operation within a larger power fluctuation range (such as allowing instantaneous power to fluctuate from 180kW to 198kW without triggering adjustment); conversely, when the threshold is shrunk to ±5%, the system automatically tightens the path selection criteria and only selects terminals with load fluctuation rates below 5% as diversion nodes. The dynamic adjustment of constraints is deeply coupled with power grid stability indicators. For example, when the regional power grid frequency fluctuates by more than 0.5Hz, the threshold contraction mechanism is triggered to reduce the fluctuation tolerance range by 30% to prioritize power grid security.

[0100] The gradient correction process of the cost compensation rule combines the cost tolerance calibration amount with user behavior feedback data. The system maps the calibration amount (such as the interval boundary expanding from 1.1 yuan to 1.15 yuan) to the compensation coefficient adjustment gradient, for example, setting a compensation coefficient increment curve in the 1.1-1.15 yuan interval (the compensation rate increases by 0.5% for every 0.01 yuan interval). The gradient correction engine simultaneously analyzes the user's historical behavior data and gives higher compensation sensitivity (such as the coefficient weighting factor increased to 1.2) to high-frequency adjustment users (such as users with an average of more than 15 power adjustments per month). The compensation rule adjustment parameters are generated through a nonlinear interpolation algorithm to ensure a smooth transition of the compensation rate at the tolerance interval boundary and avoid abnormal user perception caused by rate jumps.

[0101] After receiving the priority allocation coefficient, path constraints and compensation rule adjustment parameters, the strategy generation engine uses a multi-objective optimization algorithm to generate a candidate scheduling strategy set. The power diversion ratio is determined based on a mixed integer programming model to maximize the load balancing index while satisfying the path constraints. For example, for a regional network containing 12 terminals, the engine may generate three candidate solutions: Solution A has a diversion ratio of 18% and a load balancing degree of 0.82, Solution B has a diversion ratio of 25% and a balancing degree of 0.78, and Solution C has a diversion ratio of 15% and a balancing degree of 0.85. The construction of the cost compensation mechanism adopts a hybrid architecture of a rule engine and a machine learning model. For example, a reinforcement learning model is used to predict the optimal compensation strategy for high-cost-sensitive user groups (compensation coefficient>0.3), while a rule-based static compensation table is used for ordinary user groups.

[0102] The multi-objective trade-off evaluation module jointly scores the terminal load balance, cost deviation tolerance, and user satisfaction prediction value of the candidate strategy set. The load balance is quantified by calculating the deviation of the regional terminal load variance from the ideal value (for example, when the variance decreases from 120 to 95, the balance increases by 15%); the cost deviation tolerance is evaluated based on the expected cost excess ratio after the strategy is implemented (for example, the predicted proportion of users exceeding the standard decreases from 8% to 3%); the user satisfaction prediction value is derived through the behavioral feedback model, integrating the historical scoring data and the correlation between the strategy parameters (for example, an increase of 0.1 in the compensation coefficient corresponds to an increase of 0.2 in the predicted satisfaction). The evaluation process uses the Pareto optimal frontier analysis method to screen out candidate strategies that are non-inferior solutions in all three target dimensions, such as selecting the comprehensive optimal strategy with a load balance of 0.83, a cost deviation tolerance of 4%, and a satisfaction prediction value of 4.3.

[0103] During the strategy compatibility verification phase, the system will perform a matching analysis between the updated scheduling strategy and the historical execution effect database. Verification indicators include parameter adjustment range safety thresholds (such as a single adjustment of the time period weight not exceeding ±0.15), load mutation rate limits (such as the power diversion ratio change rate not exceeding 20% ​​per hour), and compensation rule continuity (such as the difference in compensation coefficients between adjacent strategy versions is less than 0.05). When it is detected that the power diversion ratio of a candidate strategy is 28% higher than the historical maximum value (exceeding the preset 25% safety threshold), the system automatically triggers the strategy correction process to ensure a smooth transition by reducing the diversion gradient (such as adjusting from 5% / minute to 3% / minute). After verification, the updated scheduling strategy is encrypted with a digital signature and sent to the terminal control system through a low-latency communication protocol. The embedded execution module uses a real-time priority preemption mechanism to ensure timely response to strategy instructions.

[0104] With this design, the precise adaptation of the dispatching strategy is achieved through dynamic parameter injection and multi-objective optimization mechanism, which significantly improves the flexibility and adaptability of charging resource allocation; the intelligent adjustment function of the power fluctuation tolerance range effectively balances the stability of the power grid and the freedom of user behavior, and enhances the robustness of system operation; the combination of the gradient compensation model and the compatibility verification mechanism ensures that the cost regulation process is smooth and reliable, and avoids the degradation of user experience caused by sudden changes in the strategy; the low-latency response characteristics of the embedded real-time control system ensure the timeliness of strategy execution, and provide core technical support for the dynamic allocation of resources in complex charging scenarios. The overall solution builds a complete technical closed loop from strategy generation to execution verification, and promotes the continuous evolution of charging services towards intelligence and adaptability.

[0105] In summary, the embodiments of the present invention achieve accurate characterization of user charging behavior characteristics through multi-dimensional data collection and in-depth behavior analysis, effectively improving the accuracy of charging demand prediction and resource scheduling. The constructed charging preference label system converts user behavior characteristics into quantifiable parameters, provides a core basis for the formulation of differentiated service strategies, and enhances the personalized adaptation capabilities of charging services. The generation and execution mechanism of cross-terminal dynamic scheduling strategies optimizes the allocation efficiency of power resources in the time and space dimensions and alleviates the problem of local overload during peak hours. The coordinated adjustment function of real-time power supply parameters and cost calculation logic balances the stability of power grid operation while ensuring charging efficiency, thereby reducing operating costs. The overall solution forms a closed-loop optimization link from data perception to strategy execution, significantly improving the resource utilization efficiency of charging facilities.

[0106] Further, Figure 2 Schematic diagram of a liquid-cooled supercharger terminal charging mid-station system 200 provided in an embodiment of the present invention. Figure 2 The liquid-cooled supercharging terminal charging station system 200 shown includes a processor 210, which can call and run a computer program from a memory to implement the method in the embodiment of the present invention.

[0107] Alternatively, if Figure 2 As shown, the liquid-cooled supercharging terminal charging mid-station system 200 may also include a memory 230. Among them, the processor 210 can call and run a computer program from the memory 230 to implement the method in the embodiment of the present invention.

[0108] The memory 230 may be a separate device independent of the processor 210 , or may be integrated into the processor 210 .

[0109] Alternatively, if Figure 2 As shown, the liquid-cooled supercharging terminal charging station system 200 may also include a transceiver 220, and the processor 210 may control the transceiver 220 to interact with other devices. Specifically, it may send information or data to other devices, or receive information or data sent by other devices.

[0110] Optionally, the liquid-cooled supercharging terminal charging middle station system 200 can implement the corresponding processes corresponding to the storage engine or components in the storage engine (such as a processing module) or a device deployed with a storage engine in each method of the embodiments of the present invention. For the sake of brevity, they will not be repeated here.

[0111] It should be understood that the processor of the embodiment of the present invention may be an integrated circuit chip with signal processing capability.

[0112] It is understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory. It should be noted that the memory of the systems and methods described herein is intended to include but is not limited to suitable types of memory.

[0113] Based on the above, a readable storage medium is provided, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the above method are implemented.

[0114] It should be noted that, in this article, the term "comprises", "includes" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the method and device in the embodiment of the present invention is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0115] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned implementation methods can be implemented by means of software plus a necessary general hardware platform, and of course, by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the embodiment of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the embodiment of the present invention.

[0116] The embodiments of the embodiments of the present invention are described above in conjunction with the accompanying drawings, but the embodiments of the present invention are not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the embodiments of the present invention, ordinary technicians in this field can also make many forms without departing from the purpose of the embodiments of the present invention and the scope of protection of the embodiments of the present invention, all of which are within the protection of the embodiments of the present invention.

Claims

1. A method for analyzing the cost of charging a liquid-cooled supercharging terminal, characterized in that: The method comprises: Collecting multiple sets of operating status data sets of liquid-cooled supercharging terminals, wherein the operating status data sets include charging power time series change records, user charging cycle distribution, and corresponding segment fee settlement results; Perform multi-dimensional charging behavior analysis on the operating status data set to generate a user behavior feature set including charging time period preference mode, power adjustment rule and cost response intensity; Constructing a charging preference label for the vehicle charger based on the user behavior feature set, wherein the charging preference label includes a time period priority weight, a power stability threshold, and a cost tolerance interval; Generate a dynamic scheduling strategy across liquid-cooled supercharging terminals according to the charging preference tag, wherein the dynamic scheduling strategy includes a power redistribution path and a cost compensation rule; The real-time power supply parameters and cost calculation logic of the target liquid-cooled supercharging terminal are optimized according to the dynamic scheduling strategy to achieve a coordinated improvement in charging efficiency and resource utilization.

2. The method according to claim 1, characterized in that The multi-dimensional charging behavior analysis of the operating status data set is performed to generate a user behavior feature set including a charging time period preference mode, a power adjustment rule, and a cost response intensity, including: Filtering a selected charging record subset that meets a preset integrity condition from the operating status data set, wherein the selected charging record subset includes a power fluctuation trajectory within a complete charging cycle and corresponding cost segmentation data; Performing charging period distribution analysis on the selected charging record subset to identify high-frequency charging period groups and corresponding power peak densities; Extracting trigger condition parameters of the power sudden drop event in the power fluctuation trajectory, and generating a dynamic event sequence including a sudden drop time point and a sudden drop amplitude; Performing spatiotemporal correlation analysis on the high-frequency charging period group and the dynamic event sequence to determine the response relationship between the cost segmentation data and the power adjustment behavior; Based on the response relationship and the power peak density, a time period preference pattern, a power adjustment rule and a cost response intensity of a user behavior feature set are generated.

3. The method according to claim 2, characterized in that The performing charging period distribution analysis on the selected charging record subset to identify high-frequency charging period groups and corresponding power peak densities includes: Density clustering of the charging start time in the selected charging record subset according to a preset time granularity to form a plurality of time period distribution clusters; Calculate the time period coverage frequency of each time period distribution cluster, where the time period coverage frequency is determined by the ratio of the number of charging records in the cluster to the total number of records; Filter the time period distribution clusters whose time period coverage frequency exceeds the preset frequency threshold as candidate thermal time period groups; Expand the time window of the charging start time in the candidate thermal time period group to generate a continuous active charging time period interval; Counting the peak occurrence frequency and duration ratio of the power fluctuation trajectory within the active charging period, and generating a corresponding power peak density matrix; The extracting the trigger condition parameters of the power sudden drop event in the power fluctuation trajectory to generate a dynamic event sequence including a sudden drop time point and a sudden drop amplitude includes: Detecting a section in the power fluctuation trajectory where the continuous power value drops by more than a preset sudden drop threshold as a candidate sudden drop event; Record the starting time point, ending time point and absolute value of power difference of each candidate sudden drop event; Calculate the ratio of the absolute value of the power difference to the initial power value as the sudden drop amplitude; Sorting the candidate sudden drop events in time series according to the starting time point to generate a dynamic event sequence; Analyze the interval duration distribution of adjacent events in the dynamic event sequence to determine the triggering frequency and correlation characteristics of sudden drop events.

4. The method according to claim 2, characterized in that: The step of performing spatiotemporal correlation analysis on the high-frequency charging time period group and the dynamic event sequence to determine the response relationship between the cost segmentation data and the power adjustment behavior includes: Establish the first analysis layer with the active charging period interval as the time dimension; Establish the second analysis layer with the sudden drop time point in the dynamic event sequence as the event dimension; Mapping the cost segmentation data to the first analysis layer according to the timestamp to generate a cost change thermal distribution map; Matching and associating the sudden drop amplitude with the cost fluctuation value in the cost segmentation data to generate a cost response intensity index; A spatiotemporal correlation response relationship matrix is ​​constructed based on the cost change heat distribution map and the cost response intensity index.

5. The method according to claim 2, characterized in that: The step of constructing a charging preference label for the vehicle charging terminal based on the user behavior feature set includes: Extracting a charging period preference pattern from the user behavior feature set, wherein the charging period preference pattern is determined by the period weight and power peak density distribution of the active charging period interval; Analyze the user adjustment behavior records in different fee ranges of the fee segmentation data to generate a fee tolerance range; Determining a power stability threshold according to a trigger frequency of a sudden drop event in the dynamic event sequence and a cost response intensity index; The time period weight, power stability threshold and cost tolerance interval are integrated in multiple dimensions to generate a charging preference label for the on-board charging terminal; Dynamically adjust the parameter weights in the charging preference tag through a real-time charging data stream update mechanism, where the parameter weights are synchronously updated based on the load fluctuations of the liquid-cooled supercharging terminal and the grid cost strategy; The step of analyzing the user adjustment behavior records of the fee segmentation data in different fee intervals to generate a fee tolerance interval includes: Dividing the expense segmentation data into a plurality of continuous sub-expense intervals according to the expense amount; Count the number of charging behavior adjustments and the corresponding adjustment types within each sub-cost interval, where the adjustment types include active power reduction, charging suspension, and terminal switching operations; Calculating an adjustment trigger rate for each sub-cost interval, wherein the adjustment trigger rate is determined by a ratio of the number of adjustments to the number of charging times; generating a cost tolerance interval according to the adjustment trigger rate and the sub-cost interval span, wherein the cost tolerance interval includes a first tolerance boundary and a second tolerance boundary; The cost tolerance interval is dynamically calibrated through a sliding window algorithm to eliminate the interference of abnormal data on the interval range.

6. The method according to claim 1, characterized in that The generating a dynamic scheduling strategy across liquid-cooled supercharging terminals according to the charging preference tag includes: Parsing the time period weight, power stability threshold and cost tolerance range in the charging preference tag; Obtain real-time operating load data and grid power supply constraints of multiple liquid-cooled supercharging terminals; Predicting charging demand distribution and power demand peak within a target time window based on the time period weights; generating a power distribution path between terminals according to the power demand peak and the real-time operating load data; The cost compensation coefficient in the power split path is adjusted in combination with the cost tolerance interval to generate a dynamic scheduling strategy across terminals.

7. The method according to claim 6, characterized in that The predicting of charging demand distribution and power demand peak within the target time window based on the time period weights includes: Extracting the active charging time interval and the time period coverage frequency in the time period weight; Construct a forecast input sequence with the period coverage frequency as the time axis and the power peak density as the intensity axis; Analyzing the periodic characteristics in the input sequence through a time series pattern recognition algorithm to generate a charging demand prediction curve within a target time window; Identifying a local extreme point in the charging demand prediction curve as a power demand peak; The charging demand distribution is determined according to the timestamp corresponding to the local extreme point and the terminal location information.

8. The method according to claim 1, characterized in that The real-time power supply parameters and cost calculation logic of the target liquid-cooled supercharging terminal are optimized according to the dynamic scheduling strategy, including: Determine a threshold allocatable power value of the target terminal according to the power split path in the dynamic scheduling strategy; Adjust the cost ladder calculation rule of the target terminal in combination with the cost tolerance interval in the charging preference tag; Real-time monitoring of the target terminal's power usage and user behavior feedback signals; Dynamically optimize the priority allocation mechanism in the power supply parameters to ensure power supply priority for users with active time period weights; Eliminate the cost differences caused by power diversion through the cost balance algorithm, and maintain the stability of user cost expenditure within the cost tolerance range; The cost balancing algorithm is used to eliminate the cost difference caused by power splitting, including: Identify user groups whose cost deviation due to power diversion exceeds a preset threshold; Extracting a cost tolerance interval boundary value in the charging preference tag of the user group; Calculate the degree of deviation of the cost deviation from the cost tolerance interval boundary; generating a dynamic compensation coefficient according to the degree of deviation, wherein the compensation coefficient is positively correlated with the degree of deviation; The dynamic compensation coefficient is embedded in the cost calculation logic to achieve real-time correction of cost deviation.

9. The method according to claim 6, characterized in that After generating the cross-terminal dynamic scheduling strategy, the method further includes: Real-time monitoring of the execution effect data of the dynamic scheduling strategy, wherein the execution effect data includes resource utilization improvement rate and user satisfaction index; Compare the difference between the execution effect data and the preset optimization target to generate strategy adjustment parameters; Feeding back the strategy adjustment parameters to the updating mechanism of the charging preference tag to form a closed-loop optimization link; Through multiple rounds of iterative optimization, the optimal scheduling strategy is gradually converged to achieve adaptive matching of charging resource allocation and user needs.

10. A liquid-cooled supercharging terminal charging middle station system, characterized in that: The method comprises at least one processor and a memory; the memory stores computer-executable instructions; the at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the method according to any one of claims 1 to 9.

Images