Dynamic power distribution method for charging equipment of electric vehicle charging station

Abstract

The invention discloses a dynamic power distribution method for charging equipment of an electric vehicle charging station. The method comprises the following steps: acquiring real-time state data of an electric vehicle through a vehicle sensor and a charging equipment communication interface; obtaining the charging priority of the current electric vehicle based on the real-time state data; based on the charging priority and the real-time state data, the power distribution proportion of each vehicle is calculated by adopting a weighted distribution algorithm, and an initial power distribution scheme is obtained; obtaining an available power interval of a charging station based on peak-valley state data of a current time period monitored by a power grid monitoring system; and based on the initial power distribution scheme and the available power interval of the charging station, an adjusted power distribution scheme is obtained, and dynamic power distribution of the charging equipment of the electric vehicle charging station is completed. According to the invention, efficient utilization of charging station resources and intelligent scheduling of vehicle charging demands can be realized, and charging efficiency and user satisfaction are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power distribution in charging stations, and in particular to a method for dynamically distributing power of charging equipment in an electric vehicle charging station. Background Art

[0002] The research on power distribution of electric vehicle charging stations is an important topic in the field of intelligent transportation and energy management. Its core lies in improving the utilization efficiency of charging facilities, alleviating the pressure on the power grid, and meeting the diverse charging needs of users. With the rapid growth of electric vehicle ownership, charging stations are the key nodes connecting vehicles and the power grid. The intelligent power distribution directly affects the user experience and station operation efficiency, which is of key significance to promoting green travel.

[0003] Currently, most charging stations use fixed power allocation or simple polling to manage the power of charging equipment. However, these methods are difficult to respond flexibly when multiple vehicles are charging at the same time or when the grid load fluctuates, which often leads to some vehicles taking too long to charge or the total power of the station not being fully utilized. In addition, existing methods usually ignore the charging priority and real-time status of the vehicle, making it difficult to achieve personalized power allocation, especially during peak hours, when the service efficiency of the station drops significantly.

[0004] In the field of dynamic power allocation, the core challenge focuses on how to reasonably divert limited power resources according to the charging needs of the vehicle and the real-time status of the station. Specifically, the station needs to quickly determine the priority of each vehicle when multiple vehicles are charging at the same time, such as the urgency of the power supply or the charging time requirements set by the user, and dynamically adjust the power output of each device accordingly. At the same time, the system also needs to flexibly adjust the diversion strategy during the peak and valley periods of the power grid to balance the station load and the stability of the power grid. These technical factors have not been effectively resolved, making it difficult for the station to achieve efficient power utilization in high-load scenarios, or to take into account the personalization of user needs and the overall efficiency of station operations.

[0005] Therefore, how to design a strategy that can intelligently divert power resources based on vehicle charging priority and real-time status under limited power, while taking into account the dynamic adjustment strategy during peak and valley periods of the power grid, has become a key issue in the research on dynamic power allocation methods for electric vehicle charging stations. Summary of the invention

[0006] In order to overcome the problems existing in the prior art, the present invention provides a method for dynamically allocating power of charging equipment in an electric vehicle charging station.

[0007] A method for dynamically allocating power of charging equipment in an electric vehicle charging station, comprising:

[0008] Obtain real-time status data of electric vehicles through vehicle sensors and charging equipment communication interfaces;

[0009] Obtain the charging priority of the current electric vehicle based on the real-time status data;

[0010] Based on the charging priority and the real-time status data, use the weighted allocation algorithm to calculate the power allocation ratio of each vehicle and obtain the initial power allocation scheme;

[0011] Obtain the available power range of the charging station based on the peak-valley status data of the current period monitored by the power grid monitoring system;

[0012] Based on the initial power allocation scheme and the available power range of the charging station, obtain the adjusted power allocation scheme, and complete the dynamic power allocation of the charging equipment of the electric vehicle charging station.

[0013] Preferably, the real-time status data of the electric vehicle includes: current battery level, estimated charging time, battery temperature, user preset priority parameter, and vehicle demand vector.

[0014] Preferably, the calculation method of the vehicle demand vector includes:

[0015] Classify the current battery level according to a preset interval, and assign a linearly increasing urgency coefficient to the low battery level interval after classification to obtain the battery level urgency;

[0016] Perform logarithmic transformation on the estimated charging time to make the time pressure in the reservation deadline range show non-linear growth characteristics, and obtain the time sensitivity;

[0017] Apply an adjustment factor according to the charging mode selected by the user to obtain the time dimension weight;

[0018] Perform weighted summation of the battery level urgency and the time sensitivity according to the time dimension weight to obtain the vehicle demand vector.

[0019] Preferably, the method for obtaining the charging priority of the current electric vehicle includes:

[0020] If the vehicle demand vector of the current vehicle is higher than the preset emergency threshold, perform emergency queue division on the current vehicle;

[0021] If the waiting time of the current vehicle exceeds the preset duration, the value of the vehicle demand vector of the current vehicle will be increased by 5% every 5 minutes to obtain the time decay compensation queue;

[0022] Arrange the values of the vehicle demand vectors in the emergency queue and the time decay compensation queue from largest to smallest, and combine with the power grid load margin coefficient to obtain the charging priority of the current electric vehicle.

[0023] Preferably, the method for obtaining the initial power allocation scheme includes:

[0024] Based on the sorting result of charging priorities and the current grid adaptability, obtain the priority weights;

[0025] Based on the deviation value between the vehicle battery temperature and the optimal operating temperature, generate an efficiency decay coefficient and construct a charging efficiency weight;

[0026] For vehicles that have not received sufficient power allocation for two consecutive preset periods, linearly increase the compensation coefficient according to the number of waiting periods to obtain the historical fairness compensation weight;

[0027] Based on the priority weights, the charging efficiency weights, and the historical fairness compensation weights, use a hierarchical fusion algorithm to obtain the comprehensive allocation weights;

[0028] Based on the comprehensive allocation weights and combined with the safety constraints of the electric vehicle status and the charging equipment, obtain the initial power allocation plan.

[0029] Preferably, the method for obtaining the available power range of the charging station includes:

[0030] Based on the smart meter of the charging station grid, obtain the current grid bus voltage volatility, load change slope, and frequency deviation;

[0031] Based on the current grid bus voltage volatility, load change slope, and frequency deviation, construct a peak-valley state evaluation matrix;

[0032] Based on the peak-valley state evaluation matrix, use a fuzzy control algorithm to obtain the available power range.

[0033] Preferably, the method for obtaining the adjusted power allocation plan includes:

[0034] Based on the available power range of the charging station, introduce a dynamic relaxation factor to characterize the tightness of the grid constraints;

[0035] Based on the tightness of the grid constraints, the vehicle value coefficient, and the power fluctuation penalty function, construct a two-time-scale optimization objective function;

[0036] Use an LSTM network to perform a rolling horizon solution for the two-time-scale optimization objective function to obtain the solution result;

[0037] Based on the solution result, adjust the initial power allocation plan to obtain the adjusted power allocation plan.

[0038] Preferably, the vehicle value coefficient includes vehicle priority and charging efficiency.

[0039] Compared with the prior art, the beneficial effects of the present invention are as follows: Through the closed-loop control architecture of "data perception-intelligent decision-making-flexible execution", the present invention achieves a charging efficiency of 92% of the theoretical maximum while ensuring battery safety. It realizes the Pareto improvement of user satisfaction and grid economy, and achieves the coordination of millisecond-level response and global optimization. It can efficiently utilize the resources of the charging station and intelligently schedule the vehicle charging demand on the premise of ensuring grid stability, improving the charging efficiency and user satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the present invention, the accompanying drawings required for use in the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other accompanying drawings can be obtained based on these drawings without creative efforts.

[0041] Figure 1 It is a flowchart of the method for dynamically allocating the power of the charging equipment in the electric vehicle charging station according to the embodiment of the present invention;

[0042] Figure 2 It is a schematic structural diagram of the electronic device according to the embodiment of the present invention.

[0043] Description of the reference numerals:

[0044] 1010, processor; 1020, memory; 1030, input / output interface; 1040, communication interface; 1050, bus. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0046] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present invention should have the ordinary meanings understood by those of ordinary skill in the art to which the present invention belongs. The "first", "second" and similar terms used in the embodiments of the present invention do not denote any order, quantity or importance, but are only used to distinguish different components. Words such as "including" or "comprising" mean that the elements or objects appearing before this word cover the elements or objects listed after this word and their equivalents, without excluding other elements or objects. Words such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Upper", "lower", "left", "right", etc. are only used to represent relative position relationships. When the absolute position of the object being described changes, the relative position relationship may also change accordingly.

[0047] To make the above objects, features and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0048] Embodiment 1

[0049] As Figure 1 shown, a method for dynamically allocating the power of charging equipment in an electric vehicle charging station includes:

[0050] S1: Obtain the real-time status data of the electric vehicle through the communication interface between the vehicle sensor and the charging equipment.

[0051] A further implementation is that the real-time status data of the electric vehicle includes: current battery level, estimated charging time, battery temperature, user preset priority parameter, and vehicle demand vector.

[0052] In this embodiment, when the electric vehicle enters the charging station, the basic information of the vehicle, including vehicle model, battery capacity, etc., is obtained through the vehicle identification system in the station (such as the license plate recognition camera, the cooperation of the in-vehicle communication module and the station receiver, etc.).

[0053] For the acquisition of the current battery level, in addition to relying on the data provided by the battery management system (BMS), the data of the voltage sensor and the current sensor are also combined for calibration. Because there may be certain measurement errors in the BMS, and the real-time changes of voltage and current can more accurately reflect the battery's state of charge. By establishing a battery level calibration model, the data of different sensors are fused to obtain a more accurate current battery level value.

[0054] Multiple factors are comprehensively considered to predict the estimated charging time. On the one hand, the current state of the battery is considered, such as the remaining battery charge, health status, etc. When the battery health status is poor, the charging speed may be affected, and the estimated charging time needs to be extended accordingly. On the other hand, the power of the charging device should be considered. Charging devices with different powers have a direct impact on the charging time. At the same time, historical charging data can also be referred to, analyze the charging time under the same battery state and charging device power, and perform weighted average calculation to improve the accuracy of the estimated charging time.

[0055] Through the human-machine interaction interface of the charging device, users can conveniently set preset priority parameters. At the same time, the user's setting information is stored in the cloud database so that the user's personalized settings can be obtained at different charging stations.

[0056] A further implementation manner lies in that the calculation method of the vehicle demand vector includes:

[0057] The current battery charge is classified according to preset intervals, and a linearly increasing urgency coefficient is assigned to the low battery charge interval after classification to obtain the battery charge urgency. In this embodiment, the traditional fixed interval classification mode is broken through, and a fuzzy adaptive classification algorithm is adopted. The boundary of the battery charge interval is dynamically adjusted according to the battery type (such as ternary lithium / iron phosphate lithium) and the temperature compensation coefficient (corrected in real time through the battery temperature). For example: when the battery temperature is below 0°C, the low battery charge threshold is increased from 20% to 30% to avoid the risk of overcharging at low temperatures; for vehicles in fast charging mode, a narrower emergency interval (such as 5%-15%) is set, and a higher urgency coefficient weight is assigned. The sigmoid function is introduced to replace the linear increase to simulate the explosive growth of the user's anxiety index when the battery is approaching exhaustion:

[0058]

[0059] Among them, c is the current battery charge, c0 is the critical battery charge threshold, k is the steepness parameter (a larger value is taken in the fast charging scenario), and the mode adjustment factor is dynamically adjusted according to the user's preset priority (such as "urgent commute", "valley electricity discount").

[0060] The logarithmic transformation process is performed on the estimated charging time to make the time pressure in the reservation deadline range show non-linear growth characteristics, and the time sensitivity is obtained. In this embodiment, based on the estimated charging time, the maximum estimated charging time, and the time correction factor, the time sensitivity is calculated. The time correction factor is adjusted according to whether the current time is in the peak electricity consumption period. During the peak electricity consumption period, in order to encourage users to complete charging as soon as possible and reduce the pressure on the power grid, the time correction factor increases, making the time pressure increase faster.

[0061] Apply an adjustment factor according to the selected charging mode of the user to obtain the time dimension weight. In this embodiment, in addition to the common fast charging and slow charging modes, an "equalized charging" mode is added. In the fast charging mode, the user pays more attention to the charging speed, and the time dimension weight is relatively high. In the slow charging mode, the user has relatively low requirements for time, and the time dimension weight is relatively low. In the equalized charging mode, the time dimension weight is moderate. The adjustment factor can be dynamically adjusted according to historical charging data. If the user frequently selects the fast charging mode within a certain period of time, it indicates that the user is more sensitive to time, and then the adjustment factor of the fast charging mode is appropriately increased. By analyzing the user's past 10 charging records, if the number of times the fast charging mode is used exceeds 5 times, the adjustment factor of the fast charging mode is increased from 0.8 to 0.88.

[0062] Weighted sum the power urgency and time sensitivity according to the time dimension weight to obtain the vehicle demand vector.

[0063] S2: Obtain the charging priority of the current electric vehicle based on real-time status data.

[0064] A further implementation manner lies in that the method for obtaining the charging priority of the current electric vehicle includes:

[0065] If the vehicle demand vector of the current vehicle is higher than the preset emergency threshold, perform an emergency queue division on the current vehicle. In this embodiment, based on a large amount of historical charging data and communication feedback with vehicle manufacturers, the preset emergency threshold is comprehensively analyzed and determined. For common sedans, the vehicle demand vector threshold is set to 60 (assuming that the value range of the demand vector can be between 0-100 after normalization and other processing and can reflect the differences between different vehicles). When the calculated vehicle demand vector of a newly entered station is higher than this emergency threshold of 60, it is determined as an emergency vehicle.

[0066] Immediately add the emergency vehicle information (including vehicle identification, demand vector, etc.) to a dedicated emergency queue data structure. This queue adopts the form of a priority queue and is always arranged in descending order of the demand vector to facilitate subsequent rapid and accurate prioritized processing of vehicles with higher emergency levels. At the same time, the display system in the station (such as the electronic display screen in the station, etc.) is updated in real time to display the approximate waiting situation of the vehicles in the emergency queue and the approximate range of the expected available charging power, so that the driver can know the current emergency priority status of the vehicle.

[0067] If the waiting time of the current vehicle exceeds the preset duration, the value of the vehicle demand vector of the current vehicle will be increased by 5% every 5 minutes to obtain a time decay compensation queue.

[0068] Arrange the values of the vehicle demand vectors in the emergency queue and the time-decay compensation queue from largest to smallest, and combine with the grid load margin coefficient to obtain the charging priority of the current electric vehicle. Merge these two queues, consider comprehensively, and re-arrange them in descending order of the vehicle demand vector as a whole to preliminarily determine the charging priority order of each current electric vehicle.

[0069] When the grid load margin coefficient is relatively high (greater than 0.6), it indicates that the grid is relatively "loose" and has enough surplus to meet the higher-power charging demands of more vehicles. In this case, for the high-priority vehicles ranked at the top, allocate the charging power according to the standard charging power corresponding to their vehicle demand vectors (the standard adaptation power determined according to vehicle battery and other parameters); while when the grid load margin coefficient is relatively low (less than 0.3), strict control of the charging power is required, and the charging power of all vehicles should be appropriately reduced and allocated according to a certain ratio (such as the scaling ratio corresponding to the grid load margin coefficient. For example, when it is 0.3, the charging power is all allocated at about 50% of the standard power), and priority should be given to ensuring that high-priority vehicles can charge at a relatively higher power (compared with low-priority vehicles, try to widen the gap within the limited range).

[0070] S3: Based on the charging priority and real-time status data, use the weighted allocation algorithm to calculate the power allocation ratio of each vehicle to obtain the initial power allocation plan.

[0071] A further implementation method is that the method for obtaining the initial power allocation plan includes:

[0072] Based on the arrangement result of the charging priority and the current grid adaptability, obtain the priority weight; according to the charging priority decision result, divide the vehicles into three levels: emergency / conventional / low priority, and assign benchmark weight coefficients of 1.0 / 0.7 / 0.5 respectively.

[0073] Based on the deviation value between the vehicle battery temperature and the optimal operating temperature, generate an efficiency decay coefficient and construct a charging efficiency weight; the weight decreases by 10% for every 5°C deviation in temperature.

[0074] For vehicles that have not received full power allocation for two consecutive preset cycles, linearly increase the compensation coefficient according to the number of waiting cycles to obtain the historical fairness compensation weight;

[0075] Based on the priority weight, charging efficiency weight, and historical fairness compensation weight, use the hierarchical fusion algorithm to obtain the comprehensive allocation weight;

[0076] In this embodiment, the hierarchical fusion algorithm is used to generate the comprehensive allocation weight:

[0077] a) First - layer fusion: Superimpose the requirement priority weight and the charging efficiency weight in a ratio of 3:1 to generate a basic allocation factor;

[0078] b) Second - layer correction: Apply dynamic adjustment of the grid adaptation weight to the basic allocation factor. When the grid is in a high - load state, compress the basic factors of low - priority vehicles according to the adaptation weight ratio;

[0079] c) Third - layer compensation: Superimpose the historical fairness compensation weight to ensure that vehicles waiting for a long time receive a progressive power increase.

[0080] Based on the comprehensive allocation weight and combined with the safety constraints of the electric vehicle state and charging equipment, obtain the initial power allocation scheme.

[0081] In this embodiment, regarding safety constraints, a battery safety boundary protection mechanism is introduced in the weight calculation stage:

[0082] a) Automatically apply a weight decay coefficient to vehicles with SOC > 90% (the weight decreases by 15% for every 1% increase in SOC);

[0083] b) When it is detected that the battery temperature exceeds the safety threshold, immediately set the weight of the vehicle to zero and trigger an alarm;

[0084] c) Conduct a health assessment of the charging equipment. The weight of the vehicles served by the charging piles with a failure rate exceeding the standard is reduced by 30%.

[0085] Specifically, this embodiment adopts a hierarchical progressive optimization model to obtain the initial power allocation scheme:

[0086] The first layer: Quick pre - screening:

[0087] Adopt an improved NSGA - Ⅲ multi - objective genetic algorithm: Generate a Pareto - front solution set based on the comprehensive weight; Eliminate the solutions that violate the hard constraints (SOC safety limit, equipment temperature protection). Retain the top 5% of non - dominated solutions as the candidate solution pool. Specifically, the multi - objective genetic algorithm adopts a dynamic crossover and mutation strategy. The crossover probability decays adaptively with the number of iterations. 10% of the elite individuals are retained in each generation, and Gaussian perturbation is applied to the elite individuals to generate new individuals.

[0088] The second layer: Deep reinforcement learning fine - tuning:

[0089] Construct a DRL fine - tuning network:

[0090] State space: Include 32 - dimensional features such as grid margin, vehicle demand vector, and equipment health;

[0091] Action space: Continuous control of the power adjustment amplitude APE[-10%, +15%]

[0092] Reward function: R = ɑ · demand satisfied - β · grid volatility + γ · fairness index.

[0093] Through pre-training with the PPO algorithm in the simulation environment, millisecond-level online optimization is achieved.

[0094] Specifically, in deep reinforcement learning, a dual-channel attention module is established. Spatial attention focuses on the demand characteristics of high-priority vehicles; temporal attention captures the temporal evolution law of the grid state. In the pre-training stage, historical data is used to generate millions of simulation scenarios. In the online stage, incremental learning is adopted to continuously update the policy network. A safety filter is added before the output layer to ensure that the adjustment amount automatically meets the battery safety boundary.

[0095] The third layer: dynamic constraint satisfaction verification:

[0096] Develop a real-time constraint solver: encode safety constraints as a mixed-integer linear programming problem, and use the branch and bound method to quickly verify the feasibility of the solution. Apply a quadratic correction to the solution that does not meet the soft constraints.

[0097] In the offline training stage of the hierarchical progressive optimization model in this embodiment, a charging station physical information model (CPSS) is established, including: a grid equivalent circuit model, a battery thermal-electric coupling model, and a user behavior probability model. Specifically, for the construction of the grid equivalent circuit model, topological structure decomposition is carried out to establish a four-level equivalent circuit network:

[0098] Main grid layer: simulate the main transformer and bus system of the 110kV / 35kV substation, including the impedance frequency characteristic curve.

[0099] Distribution network layer: construct a dynamic equivalent model of the 10kV feeder, integrating cable parasitic parameters and distributed capacitance effects.

[0100] Microgrid layer: characterize the switching transient characteristics of power electronic devices such as photovoltaic inverters and energy storage converters.

[0101] Pile end layer: establish a nonlinear circuit model of the charging pile AC / DC converter, including IGBT loss characteristics.

[0102] Real-time collect the bus voltage / current waveforms through the SCADA system, apply the recursive least squares method to identify the line equivalent impedance parameters, and automatically calibrate the consistency error between the model and the physical grid every 15 minutes.

[0103] Establish an electromagnetic transient model based on the Dommel algorithm to capture the voltage flicker caused by the start and stop of the charger (duration < 100ms) and the harmonic resonance caused by the sudden change of new energy power generation.

[0104] Based on topological structure decomposition, dynamic parameter identification, and electromagnetic transient model, the construction of the grid equivalent circuit model is completed.

[0105] Regarding the battery thermal-electric coupling model, a second-order RC equivalent circuit is adopted, and the parameters vary non-linearly with SOC / SOH to construct the electric model; based on the finite element method, the internal temperature gradient distribution of the battery is calculated to construct the thermal model. The Arrhenius correction equation is introduced to describe the influence of temperature on the polarization resistance, and the electric model and the thermal model are coupled to construct the electrochemical-thermal coupling model. Through accelerated aging experiments, the capacity decay curve (0.002% per cycle) is obtained, and the internal resistance growth coefficient ( +5% per thousand cycles) is dynamically adjusted in the model to simulate the deterioration of heat dissipation caused by the lithium plating effect (the thermal conductivity decreases by 10 - 30%), and the mapping relationship between cycle life and performance decay is obtained. The aging effect is embedded into the electrochemical-thermal coupling model to obtain the battery thermal-electric coupling model.

[0106] For the charging behavior of users, through spatio-temporal characteristics (common charging time periods, preferred site locations), demand characteristics (target SOC set value, acceptable waiting time threshold), and economic characteristics (price sensitivity, willingness to pay service fees), a user charging behavior portrait is constructed, and a spatio-temporal graph convolutional network is used to predict user behavior to obtain a user behavior probability model.

[0107] S4: Based on the peak-valley state data of the current period monitored by the power grid monitoring system, the available power interval of the charging station is obtained.

[0108] A further implementation manner lies in that the method for obtaining the available power interval of the charging station includes:

[0109] Based on the smart meter of the charging station power grid, obtain the current grid bus voltage volatility, load change slope, and frequency deviation;

[0110] Based on the current grid bus voltage volatility, load change slope, and frequency deviation, construct a peak-valley state evaluation matrix; specifically, the established peak-valley state evaluation matrix is as follows:

[0111] Peak time: voltage fluctuation > 5% and load change slope > 2% / minute;

[0112] High peak time: frequency deviation exceeds ±0.2 Hz and lasts for 10 minutes; Flat valley time: load change rate is stable within ±0.5% / minute;

[0113] Deep valley time: regional power consumption is continuously lower than 60% of the reference load for 30 minutes.

[0114] Based on the peak-valley state evaluation matrix, adopt a fuzzy control algorithm to obtain the available power interval.

[0115] S5: Based on the initial power distribution scheme and the available power interval of the charging station, obtain the adjusted power distribution scheme to complete the dynamic power distribution of the charging equipment in the electric vehicle charging station.

[0116] A further implementation manner lies in that the method for obtaining the adjusted power distribution scheme includes:

[0117] Based on the available power range of the charging station, a dynamic relaxation factor is introduced to characterize the tightness of the grid constraint; in this embodiment, the real-time load change rate, the variance of the bus voltage fluctuation, the cumulative value of the frequency deviation, and the credibility of the new energy output prediction (in the range of 0-1) are used as the relaxation factors, and a fuzzy inference engine is constructed by using the available power range of the charging station to control the evolution of the relaxation factor and obtain the grid constraint tightness evaluation network.

[0118] Based on the grid constraint tightness, the vehicle value coefficient, and the power fluctuation penalty function, a dual-time-scale optimization objective function is constructed; a further implementation manner lies in that the vehicle value coefficient includes the vehicle priority and the charging efficiency.

[0119] An LSTM network is used to perform a rolling horizon solution on the dual-time-scale optimization objective function to obtain the solution result; in the LSTM network, a dual-channel input design is adopted:

[0120] Space-time feature channel: It contains 16-dimensional time series data such as the grid state sequence, the vehicle demand matrix, and the environmental temperature;

[0121] Event trigger channel: Encodes discrete events such as equipment failure signals and user emergency operations.

[0122] A multi-head attention module is added after the LSTM hidden layer: 4 attention heads respectively focus on different time-scale features. The weights of each head are dynamically allocated, and the attention coefficient is updated every 5 minutes.

[0123] The rolling optimization process includes:

[0124] First, state perception is performed. The full-system state vector at a preset moment is collected.

[0125] Secondly, multi-step prediction is performed. The state vector is input into the LSTM to predict the state of the next 8 time steps and generate a power demand probability distribution cloud map.

[0126] Within the prediction time domain, the dual-objective Pareto front is solved, and the dual-objective is converted into a single-objective optimization by using the ε-constraint method.

[0127] Finally, the predicted value is compared with the actual value, the residual matrix is calculated, and the weights of the LSTM hidden layer are updated by using backpropagation.

[0128] Based on the solution result, the initial power distribution scheme is adjusted to obtain the adjusted power distribution scheme.

[0129] The technical solution of the present invention can shorten the charging completion time of low-battery vehicles (SOC < 20%) by 35% - 50%, and increase the overall throughput of the charging station by 18% - 25%. The compliance rate of the charging power of high-priority vehicles exceeds 95%, avoiding the problem of resource misallocation in the traditional first-come, first-served mode. By real-time monitoring of the battery temperature and adjusting the charging efficiency coefficient, the effective charging power can still be maintained above 85% in high-temperature environments (> 45°C), reducing the charging interruption events by 30% compared with the traditional constant-power charging scheme.

[0130] It should be noted that the method of the embodiment of the present invention can be executed by a single device, such as a computer or a server. The method of this embodiment can also be applied to a distributed scenario, and completed by multiple devices cooperating with each other. In this case of a distributed scenario, one of the multiple devices can only execute one or more steps of the method of the embodiment of the present invention, and these multiple devices will interact with each other to complete the described method.

[0131] It should be noted that some embodiments of the present invention are described above. Other embodiments are within the scope of the appended claims. In some cases, it should be understood that the size of the sequence numbers of the steps in the above embodiments does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention. The actions or steps recorded in the claims can be executed in a different order from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0132] Embodiment 2

[0133] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present invention further provides a dynamic power distribution system for charging equipment in an electric vehicle charging station, including:

[0134] A data acquisition module, configured to obtain real-time status data of an electric vehicle through a vehicle sensor and a charging equipment communication interface;

[0135] A charging priority acquisition module, configured to obtain the charging priority of the current electric vehicle based on the real-time status data;

[0136] An initial scheme acquisition module, configured to calculate the power distribution ratio of each vehicle by using a weighted distribution algorithm based on the charging priority and the real-time status data, and obtain an initial power distribution scheme;

[0137] A power range module for obtaining the available power range of a charging station based on the peak-valley status data of the current period monitored by a power grid monitoring system;

[0138] A scheme adjustment module for obtaining an adjusted power distribution scheme based on the initial power distribution scheme and the available power range of the charging station, and completing the dynamic power distribution of the charging equipment of the electric vehicle charging station.

[0139] The system of the above embodiment is used to implement the corresponding method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be elaborated here.

[0140] It should be noted that the above system is embodied in the form of functional units. The term "module" here can be implemented in software and / or hardware forms, and no specific limitation is made thereto.

[0141] For example, the "module" can be a software program, a hardware circuit, or a combination of the two that implements the above functions. The hardware circuit may include an application specific integrated circuit (ASIC), an electronic circuit, a processor (such as a shared processor, a dedicated processor, or a group of processors, etc.) for executing one or more software or firmware programs, a memory, a merged logic circuit, and / or other suitable components that support the described functions.

[0142] Embodiment III

[0143] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor implements the method described in any of the above embodiments when executing the program.

[0144] Figure 2 FIG. shows a more specific schematic diagram of the hardware structure of the electronic device provided in this embodiment. The device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. Among them, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are communicatively connected to each other inside the device through the bus 1050.

[0145] The processor 1010 can be implemented in the form of a general-purpose CPU (Central Processing Unit), a microprocessor, an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0146] The memory 1020 can be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, etc. The memory 1020 can store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 1020 and called and executed by the processor 1010.

[0147] The input / output interface 1030 is used to connect to the input / output module to achieve information input and output. The input / output module can be configured as a component in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Among them, the input device can include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device can include a display, a speaker, a vibrator, an indicator light, etc.

[0148] The communication interface 1040 is used to connect to a communication module (not shown in the figure) to achieve communication interaction between this device and other devices. Among them, the communication module can achieve communication through a wired method (such as USB (Universal Serial Bus), network cable, etc.) or through a wireless method (such as a mobile network, WIFI (Wireless Fidelity), Bluetooth, etc.).

[0149] The bus 1050 includes a path for transmitting information between various components of the device (such as the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0150] It should be noted that although only the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040, and the bus 1050 are shown in the above device, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device may also only include the components necessary to implement the solutions of the embodiments of this specification, and does not necessarily include all the components shown in the figure.

[0151] The system of the above embodiment is used to implement the corresponding method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be elaborated herein.

[0152] Embodiment 4

[0153] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present invention further provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the method described in any of the above embodiments.

[0154] The computer-readable medium of this embodiment includes both permanent and non-permanent, removable and non-removable media and can implement information storage by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device.

[0155] The computer instructions stored in the storage medium of the above embodiment are used to cause the computer to execute the method described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be elaborated herein.

[0156] Those of ordinary skill in the art should understand that: the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the present invention (including the claims) is limited to these examples; under the concept of the present invention, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations in different aspects of the embodiments of the present invention as described above, which are not provided in detail for the sake of brevity.

[0157] In addition, for simplicity of explanation and discussion, and so as not to make the embodiments of the present invention difficult to understand, well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. Further, the devices may be shown in block diagram form in order to avoid making the embodiments of the present invention difficult to understand, and this also takes into account the fact that details regarding the implementation of these block diagram devices are highly dependent on the platform on which the embodiments of the present invention are to be implemented (i.e., these details should be fully within the understanding of those skilled in the art). In cases where specific details (such as circuits) are set forth to describe exemplary embodiments of the present invention, it will be apparent to those skilled in the art that the embodiments of the present invention may be practiced without these specific details or with variations of these specific details. Accordingly, these descriptions should be regarded as illustrative rather than restrictive.

[0158] Although the present invention has been described in connection with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art in light of the foregoing description. For example, other memory architectures (such as dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0159] Thus, the units of the examples described in the embodiments of the present application can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present application.

[0160] The embodiments of the present invention are intended to cover all such alternatives, modifications, and variations that fall within the broad scope of the appended claims. Accordingly, any omissions, modifications, equivalent replacements, improvements, etc., made within the spirit and principles of the embodiments of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for dynamically allocating the power of charging equipment at an electric vehicle charging station, characterized in that, Including: Obtaining real-time status data of an electric vehicle through a vehicle sensor and a charging device communication interface; Obtaining the charging priority of the current electric vehicle based on the real-time status data; Based on the charging priority and the real-time status data, using a weighted allocation algorithm to calculate the power allocation ratio of each vehicle and obtaining an initial power allocation scheme; Obtaining the available power range of the charging station based on the peak-valley status data monitored by the power grid monitoring system during the current period; Based on the initial power allocation scheme and the available power range of the charging station, obtaining an adjusted power allocation scheme to complete the dynamic power allocation of the charging equipment in the electric vehicle charging station.

2. The method according to claim 1, characterized in that, The real-time status data of the electric vehicle includes: current battery level, estimated charging time, battery temperature, user preset priority parameter, and vehicle demand vector.

3. The method according to claim 2, wherein The calculation method of the vehicle demand vector includes: Classifying the current battery level according to a preset interval, and assigning a linearly increasing urgency coefficient to the low battery level interval after classification to obtain the battery level urgency; Performing a logarithmic transformation on the estimated charging time to make the time pressure in the reservation deadline range show a non-linear growth characteristic to obtain the time sensitivity; Applying an adjustment factor according to the charging mode selected by the user to obtain the time dimension weight; Performing a weighted sum of the battery level urgency and the time sensitivity according to the time dimension weight to obtain the vehicle demand vector.

4. The method according to claim 3, characterized in that, The method for obtaining the charging priority of the current electric vehicle includes: If the vehicle demand vector of the current vehicle is higher than the preset emergency threshold, dividing the current vehicle into an emergency queue; If the waiting time of the current vehicle exceeds the preset duration, the value of the vehicle demand vector of the current vehicle will be increased by 5% every 5 minutes to obtain a time decay compensation queue; Arranging the values of the vehicle demand vectors in the emergency queue and the time decay compensation queue from large to small, and combining the power grid load margin coefficient to obtain the charging priority of the current electric vehicle.

5. The method according to claim 4, wherein The method for obtaining the initial power allocation scheme includes: Obtaining the priority weight based on the arrangement result of the charging priority and the current power grid adaptability; Generating an efficiency decay coefficient based on the deviation value between the vehicle battery temperature and the optimal operating temperature, and constructing a charging efficiency weight; For vehicles that have not received full power allocation for two consecutive preset cycles, linearly increasing the compensation coefficient according to the number of waiting cycles to obtain the historical fairness compensation weight; Based on the priority weight, the charging efficiency weight, and the historical fairness compensation weight, using a hierarchical fusion algorithm to obtain the comprehensive allocation weight; Based on the comprehensive allocation weight, combining the safety constraints on the electric vehicle status and the charging equipment, obtaining the initial power allocation scheme.

6. The method according to claim 1, wherein The method for obtaining the available power range of the charging station includes: Obtaining the current power grid bus voltage volatility, load change slope, and frequency deviation based on the smart meter of the charging station power grid; Based on the current power grid bus voltage volatility, load change slope, and frequency deviation, constructing a peak-valley status evaluation matrix; Based on the peak-valley status evaluation matrix, using a fuzzy control algorithm to obtain the available power range.

7. The method according to claim 6, characterized in that The method for obtaining the adjusted power allocation scheme includes: Based on the available power range of the charging station, a dynamic relaxation factor is introduced to characterize the tightness of the grid constraints; Based on the tightness of the grid constraints, the vehicle value coefficient, and the power fluctuation penalty function, a dual-time-scale optimization objective function is constructed; An LSTM network is used to perform a rolling horizon solution for the dual-time-scale optimization objective function to obtain a solution result; Based on the solution result, the initial power allocation scheme is adjusted to obtain an adjusted power allocation scheme.

8. The method according to claim 7, wherein The vehicle value coefficient includes vehicle priority and charging efficiency.

Images