New energy vehicle charging station power supply optimization regulation and control system in power supply peak period

Abstract

The invention relates to the technical field of new energy vehicle charging, and discloses a new energy vehicle charging station power supply optimization regulation and control system in a power supply peak period, and the system comprises a processor, a charging demand prediction module, a power supply load distribution module, a real-time regulation and control module, and a power supply performance monitoring module. The charging demand prediction module predicts a charging demand based on historical data and user behaviors; the power supply load distribution module distributes power supply priority and power upper limit according to the prediction result and the power grid state; the real-time regulation and control module adjusts power supply parameters according to the real-time data The power supply performance monitoring module records the regulation response time and the deviation value. In addition, the system is further provided with an energy storage coordination module, a user priority evaluation module and a power grid interaction module which are respectively used for optimizing energy storage management, evaluating user priority and coordinating power grid power supply. The system can accurately predict the charging demand, reasonably distribute power supply resources, regulate and control power supply parameters in real time, and improve the power supply efficiency and stability of the charging station.

Description

Technical Field

[0001] The present invention relates to the technical field of new energy vehicle charging, and in particular to a power supply optimization and control system for a new energy vehicle charging station during power supply peak period. Background Art

[0002] With the global emphasis on environmental protection and the rapid development of new energy technologies, the market share of new energy vehicles has exploded. With its clean and efficient features, new energy vehicles have gradually become a powerful substitute for traditional fuel vehicles, playing an important role in alleviating the energy crisis and reducing environmental pollution. However, this has also brought huge challenges to the charging infrastructure of new energy vehicles, especially during peak power supply periods, when the power supply problem of charging stations has become increasingly prominent.

[0003] During the peak power supply period, multiple factors are intertwined, resulting in many difficulties in the power supply of charging stations. On the one hand, the demand for charging new energy vehicles is highly concentrated in a specific time period, showing obvious peak-to-valley differences. For example, after get off work on weekday evenings, a large number of users go to charging stations to charge their vehicles, causing a sudden surge in charging demand, far exceeding the conventional power supply capacity of charging stations. If this centralized charging demand is not properly regulated, it is very easy to cause local overload of charging stations, seriously affecting the normal operation and service life of charging piles.

[0004] On the other hand, the grid load is already at a high level during peak hours. At this time, a large number of new energy vehicles connected for charging will undoubtedly further increase the burden on the grid, and may even cause problems such as grid voltage fluctuations and unstable frequency. These problems will not only affect the charging efficiency of charging stations, but may also pose a threat to the safe and stable operation of the entire grid. If the grid voltage is too low, the charging speed of new energy vehicles will drop significantly, and the user's waiting time will be extended; if the voltage is too high, it may damage the vehicle battery and charging equipment.

[0005] The existing power supply control methods for new energy vehicle charging stations have many shortcomings. Many charging stations lack the ability to accurately predict charging demand and cannot know the distribution of charging demand in different periods in advance, resulting in unreasonable allocation of power supply resources. Without accurate predictions, charging stations may over-allocate power supply resources during the low charging demand period, resulting in resource waste; and during peak periods, due to insufficient resources, they cannot meet user charging needs.

[0006] At the same time, traditional power supply load allocation strategies often only consider a single factor, such as allocating power according to the principle of first-come, first-served, without comprehensively considering multiple factors such as grid load balance, charging pile utilization, and user waiting time. This single allocation method cannot maximize the overall benefits of charging stations, and it is easy for some charging piles to be idle while some users have to wait for a long time to charge.

[0007] In addition, the existing control system has a slow response speed to power grid fluctuations and real-time changes, and cannot adjust the power supply parameters of charging piles in time. When the power grid electricity price fluctuates, the charging station cannot adjust the charging strategy according to the change in electricity price in time, resulting in increased charging costs for users; when the power grid is partially overloaded, it is also difficult to quickly take effective load transfer or restriction measures, affecting the stable operation of the power grid and charging stations.

[0008] With the continuous development of the new energy vehicle industry, it is urgent to solve the problem of power supply at charging stations during peak hours. This is not only related to the user experience of new energy vehicles, but also has important significance for the sustainable development of the new energy vehicle industry and the safe and stable operation of the power grid. Therefore, the development of an efficient and intelligent power supply optimization and control system for new energy vehicle charging stations during peak hours has become a key issue in this field. Summary of the invention

[0009] The purpose of the present invention is to provide a power supply optimization and control system for a new energy vehicle charging station during power supply peak period to solve the problems raised in the above background technology.

[0010] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a power supply optimization and control system for new energy vehicle charging stations during power supply peak period, the system comprising: a processor, a charging demand prediction module, a power supply load distribution module, a real-time control module and a power supply performance monitoring module; The charging demand prediction module predicts the charging demand distribution in the future period based on the historical charging data and user behavior characteristics, and sends the prediction result to the power supply load distribution module; The power supply load distribution module dynamically allocates the power supply priority and power upper limit of each charging pile according to the prediction results and the current grid load status; The real-time control module dynamically adjusts the power supply priority and power limit based on the real-time operation data of the charging pile and the power grid fluctuation information; The power supply performance monitoring module records the response time and deviation value of the regulation process and generates a regulation abnormality signal.

[0011] Preferably, the specific operation process of the charging demand prediction module is as follows: The timestamp, charging power, user stay time and charging period distribution characteristics in the historical charging data are extracted, and the periodic component and trend component are generated through the time series decomposition algorithm; the reservation preference, charging frequency and emergency charging mark in the user behavior data are collected, and the user behavior characteristics are classified and weighted using the random forest model to output the charging demand prediction value; if the deviation between the predicted value and the actual charging demand exceeds the preset threshold, the prediction calibration signal is triggered and the model parameters are updated.

[0012] Preferably, the power supply load distribution module adopts a multi-objective optimization algorithm, specifically including: A nonlinear constraint model is constructed with the grid load balance, charging pile utilization and user waiting time as optimization objectives. The Lagrangian relaxation method is introduced to relax the constraints, and the initial power supply priority and power allocation plan of each charging pile are generated in combination with the dynamic programming algorithm. When grid electricity price fluctuations or local overloads are detected, the dynamic priority adjustment strategy is activated to reduce the power allocation weight of non-emergency charging piles.

[0013] Preferably, the specific operation process of the real-time control module is as follows: The real-time power, battery health status and user charging urgency level of the charging pile are collected to generate a dynamic control coefficient. Based on the control coefficient and the real-time electricity price data of the power grid, a reinforcement learning algorithm is used to calculate the power adjustment range of each charging pile. If the adjustment range exceeds the preset safety threshold, the power limit instruction is triggered and a control abnormality signal is sent to the power supply performance monitoring module.

[0014] Preferably, the specific analysis process of the power supply performance monitoring module includes: Record the start and end time of each regulation operation, and calculate the regulation response time; collect the power deviation value and grid load fluctuation rate of the charging pile after regulation, perform normalized weighted calculation on the deviation value and fluctuation rate, and generate a regulation efficiency evaluation value; if the evaluation value exceeds the preset threshold, the current regulation process is judged to be abnormal and marked as an unqualified regulation record.

[0015] Preferably, the processor is communicatively connected with the energy storage coordination module, and the energy storage coordination module dynamically switches the charging and discharging mode of the energy storage system according to the regulation efficiency evaluation value and the grid load status; when the regulation unqualified records are continuously triggered, the energy storage coordination module starts the emergency power supply strategy and preferentially calls the energy storage system to power the high-priority charging piles.

[0016] Preferably, the specific strategy generation process of the energy storage coordination module is as follows: The remaining capacity, charging and discharging efficiency and life attenuation parameters of the energy storage system are collected to construct an energy storage state matrix. Based on the matrix eigenvalues ​​and the real-time electricity price gradient, a greedy algorithm is used to select the optimal charging and discharging period. When the peak load of the power grid is detected, the discharge power of the energy storage system is matched with the demand of the charging pile to generate a power supply compensation plan.

[0017] Preferably, the processor is communicatively connected with a user priority assessment module, and the user priority assessment module calculates the user priority weight according to the user's charging urgency level, historical credit score and remaining vehicle range; the power supply load distribution module uses the weight value as a constraint to adjust the power distribution ratio of the charging pile.

[0018] Preferably, the specific calculation process of the user priority evaluation module includes: The user's urgency level is divided into three levels: high, medium and low, and each is assigned a different weight coefficient. The user's credit score data is collected and a credit correction factor is generated through normalization. The range urgency is calculated based on the ratio of the vehicle's remaining range to the distance to the charging station. The weight coefficient, credit correction factor and range urgency are linearly combined to output the final user priority weight.

[0019] Preferably, the processor is communicatively connected to the power grid interaction module, and the power grid interaction module obtains the load distribution, electricity price fluctuations and renewable energy output data of the regional power grid in real time; the power supply load distribution module combines the data of the power grid interaction module and adopts a game theory model to optimize the coordinated power supply strategy of the charging station and the power grid, and dynamically adjusts the power supply upper limit and time period allocation of the charging pile.

[0020] Compared with the prior art, the present invention has the following beneficial effects: In terms of charging demand prediction, by extracting the timestamp, charging power, user stay time and charging period distribution characteristics from the historical charging data, the time series decomposition algorithm is used to generate periodic components and trend components. At the same time, the user behavior data is combined with the reservation preference, charging frequency and emergency charging mark, and the random forest model is used for classification weighted prediction. This precise prediction method greatly improves the accuracy of the prediction of charging demand distribution in future time periods. Compared with traditional prediction methods, it can know the charging demand in different time periods more accurately in advance, so that charging stations can reasonably plan power supply resources in advance, avoid excessive allocation of resources during the low charging demand period, and cause waste. It can also increase power supply in a targeted manner during peak periods, reduce user waiting time, and improve user charging experience.

[0021] The power supply load distribution module adopts a multi-objective optimization algorithm, builds a nonlinear constraint model with the grid load balance, charging pile utilization and user waiting time as optimization targets, and generates the initial power supply priority and power distribution plan through Lagrangian relaxation method and dynamic programming algorithm. When the grid electricity price fluctuates or there is a local overload, the dynamic priority adjustment strategy is activated. This method effectively balances the interests of the grid, charging piles and users.

[0022] The real-time control module collects real-time power, battery health status and user charging emergency level based on the real-time operation data of the charging pile and the grid fluctuation information to generate a dynamic control coefficient, and then combines the real-time electricity price data of the grid to calculate the power adjustment range using the reinforcement learning algorithm. If the adjustment range exceeds the preset safety threshold, the power limit instruction is triggered and the control abnormality signal is sent. This enables the charging pile power supply to respond quickly according to the real-time situation and optimize the power supply cost while ensuring charging safety. For example, when the grid electricity price is low, the charging power is automatically increased to reduce the user's charging cost; when the grid load fluctuates greatly, the power is adjusted in time to prevent damage to the grid and charging equipment and extend the service life of the equipment.

[0023] The power supply performance monitoring module records the response time and deviation value of the regulation process, and comprehensively monitors the regulation process by calculating the regulation response time and regulation efficiency evaluation value. If the evaluation value exceeds the preset threshold, the regulation is judged to be abnormal and marked. This provides a strong basis for system optimization and troubleshooting, and can promptly discover problems in the regulation process, make targeted improvements, and improve the overall performance of the system. For example, by monitoring the response time, the slow response links in the system can be discovered in time, and optimization and upgrade can be carried out to increase the system response speed.

[0024] In addition, the processor is connected to the energy storage coordination module, the user priority evaluation module, and the grid interaction module. The energy storage coordination module dynamically switches the charging and discharging mode of the energy storage system according to the control efficiency evaluation value and the grid load status, and activates the emergency power supply strategy when the control failure record is continuously triggered to ensure the power supply of high-priority charging piles and improve the reliability of power supply; the user priority evaluation module calculates the user priority weight according to the user's charging urgency level, historical credit score and the remaining range of the vehicle, and the power supply load distribution module adjusts the power distribution ratio accordingly to reflect fairness and rationality; the grid interaction module obtains regional grid data in real time, and the power supply load distribution module uses the game theory model to optimize the collaborative power supply strategy based on the data, so as to achieve efficient coordination between the charging station and the grid, and further improve the efficiency of grid resource utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present disclosure, and together with the specification, are used to explain the principles of the present disclosure. Obviously, the drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings: Figure 1 It is a working flow chart of the system of the present invention; Figure 2 A detailed workflow diagram for the charging demand prediction module; Figure 3 Workflow diagram for dynamically adjusting power supply parameters for real-time control module; Figure 4 The flowchart shows the coordinated control of the processor and energy storage coordination module. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solutions and advantages of the present disclosure clearer, the present disclosure will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0027] The terms used in the embodiments of the present disclosure are only for the purpose of describing specific embodiments, and are not intended to limit the present disclosure. The singular forms "a", "said" and "the" used in the embodiments of the present disclosure and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings, and "multiple" generally includes at least two, and other quantifiers are similar.

[0028] It should be understood that, although the terms first, second, third, etc. may be used to describe in the disclosed embodiments, these descriptions should not be limited to these terms. These terms are only used to distinguish the described objects. For example, without departing from the scope of the disclosed embodiments, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. In addition, the terms "first", "second", "third", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0029] In the description of the present disclosure, it should be noted that, unless otherwise clearly specified and limited, the terms "connected" and "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0030] It should also be noted that the term "includes", "comprising" or any other variation thereof is intended to cover non-exclusive inclusion, so that a commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprising a ..." do not exclude the existence of other identical elements in the commodity or device including the elements.

[0031] The optional embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0032] See also Figure 1-4 The present invention provides a technical solution: a power supply optimization and control system for new energy vehicle charging stations during power supply peak period, the system comprising: Charging demand prediction module: This module predicts the charging demand distribution in future time periods based on historical charging data and user behavior characteristics. It extracts the timestamp, charging power, user stay time and charging period distribution characteristics from the historical charging data, and generates periodic components and trend components through the time series decomposition algorithm; at the same time, it collects the reservation preference, charging frequency and emergency charging mark in the user behavior data, and uses the random forest model to classify and weight the user behavior characteristics to output the charging demand prediction value. If the deviation between the predicted value and the actual charging demand exceeds the preset threshold, the prediction calibration signal is triggered and the model parameters are updated. After that, the prediction result will be sent to the power supply load distribution module.

[0033] Power supply load allocation module: This module dynamically allocates the power supply priority and power limit of each charging pile according to the prediction results of the charging demand prediction module and the current grid load status. It adopts a multi-objective optimization algorithm, takes the grid load balance, charging pile utilization rate and user waiting time as optimization objectives, and constructs a nonlinear constraint model. The Lagrangian relaxation method is introduced to relax the constraints, and the initial power supply priority and power allocation plan of each charging pile are generated in combination with the dynamic programming algorithm. When the grid electricity price fluctuation or local overload is detected, the dynamic priority adjustment strategy is activated to reduce the power allocation weight of non-emergency charging piles.

[0034] Real-time control module: Based on the real-time operation data of the charging pile and the grid fluctuation information, the real-time control module dynamically adjusts the power supply priority and power limit. This module collects the real-time power of the charging pile, the battery health status and the user's charging urgency level to generate a dynamic control coefficient; based on the control coefficient and the real-time electricity price data of the grid, the reinforcement learning algorithm is used to calculate the power adjustment range of each charging pile. If the adjustment range exceeds the preset safety threshold, the power limit instruction is triggered and a control abnormality signal is sent to the power supply performance monitoring module.

[0035] Power supply performance monitoring module: responsible for recording the response time and deviation value of the regulation process, and generating regulation abnormality signals. The specific analysis process is to record the start and end time of each regulation operation, calculate the regulation response time; collect the power deviation value and grid load fluctuation rate of the charging pile after regulation, normalize the deviation value and fluctuation rate, and perform weighted calculation to generate the regulation efficiency evaluation value. If the evaluation value exceeds the preset threshold, the current regulation process is judged to be abnormal and marked as an unqualified regulation record.

[0036] Processor: As the core of the entire system, the processor is responsible for coordinating the data interaction and workflow between modules to ensure stable and efficient operation of the system.

[0037] The present invention will be further described below in conjunction with Examples 1 to 5: Embodiment 1: In this embodiment, the charging demand prediction module extracts historical charging data from the database of the charging station. The database stores a large number of charging records in the past period of time, and each record contains information such as timestamp, charging power, user stay time, and charging period distribution characteristics. For example, the timestamp accurately records the specific time when the user starts and ends charging, the charging power reflects the power size when the vehicle is charged, the user stay time reflects the user's stay time at the charging station, and the charging period distribution characteristics can help analyze the charging demand rules in different time periods.

[0038] The extracted historical charging data is processed using the time series decomposition algorithm. The time series decomposition algorithm can decompose the time series data into periodic components and trend components. Assume that the time series of historical charging data is , the periodic component can be obtained by this algorithm and trend component ,Right now . Periodic component It reflects the periodic change of charging demand over time, such as high charging demand during fixed time periods every day; trend component It reflects the long-term changing trend of charging demand. For example, with the increase in the number of new energy vehicles, the overall charging demand is on an upward trend.

[0039] In terms of collecting user behavior data, the user's operation records on the charging platform are used to obtain information such as appointment preferences, charging frequency, and emergency charging marks. Appointment preferences record the user's habit of making advance appointments for charging and time choices; charging frequency reflects how frequently the user uses the charging station; and the emergency charging mark indicates whether the user has an urgent need for charging.

[0040] The collected user behavior data is input into the random forest model. The random forest model is an ensemble learning algorithm based on decision trees. It classifies and weights user behavior features by training and integrating a large number of decision trees. During the training process, the model learns the degree of influence of different behavior features on charging demand and assigns corresponding weights to each feature. Finally, the model outputs the predicted value of charging demand.

[0041] To ensure the accuracy of the prediction, a preset threshold is set. The predicted value is compared with the actual charging demand regularly. If the deviation exceeds the preset threshold, it means that the prediction result is not accurate enough, and the prediction calibration signal is triggered. The prediction calibration signal will start the model parameter update program, retrain the model with the latest historical charging data and user behavior data, and adjust the model parameters to improve the accuracy of the prediction.

[0042] Embodiment 2: This embodiment focuses on the multi-objective optimization algorithm adopted by the power supply load distribution module. By reasonably constructing models and strategies, it balances multiple factors such as grid load, charging pile utilization, and user waiting time to achieve more scientific and efficient power supply distribution and improve the overall operating efficiency of the charging station.

[0043] The power supply load distribution module constructs a nonlinear constraint model with the grid load balance, charging pile utilization and user waiting time as optimization targets. The grid load balance is used to measure the uniformity of the load in each part of the grid to avoid the situation where the load in some areas is too high and the load in other areas is too low. Its calculation can be measured by the proportional relationship between the power allocated to each charging pile and the total capacity of the grid. Assume that the total capacity of the grid is , No. The power allocated to each charging pile is , then the grid load balance index can be expressed as ,in is the total number of charging piles, The smaller the value, the more balanced the grid load is.

[0044] The charging pile utilization rate reflects the actual use efficiency of the charging pile, which is calculated as the ratio of the actual charging time to the total charging time. For example, the total charging time of a charging pile in a day is , the actual charging time is , then the utilization rate of the charging pile .

[0045] User waiting time is an important indicator for measuring user experience. It is calculated by counting the average time users wait for charging at charging stations. Users are waiting for charging at the charging station, and the waiting time for each user is , then the average waiting time of users is .

[0046] The Lagrangian relaxation method is introduced to relax the constraints of the constructed nonlinear constraint model. The Lagrangian relaxation method converts the constraints into part of the objective function by introducing Lagrangian multipliers, thereby simplifying the problem solving. In this embodiment, the constraints are combined with the objective function to construct a Lagrangian function. .

[0047] Combined with the dynamic programming algorithm, the initial power supply priority and power allocation plan of each charging pile are generated. The dynamic programming algorithm is a method to solve complex problems by decomposing the original problem into relatively simple sub-problems and saving the solutions of the sub-problems to avoid repeated calculations. In this module, according to different charging demand scenarios and grid load conditions, the problem is divided into multiple sub-problems, and the initial power supply priority and power allocation plan of each charging pile are obtained by solving the sub-problems.

[0048] When power grid price fluctuations or local overloads are detected, the dynamic priority adjustment strategy is activated. Power grid price fluctuations will affect the operating costs of charging stations, and local overloads will threaten the safe and stable operation of the power grid. In this case, the power allocation weight of non-emergency charging piles is reduced. For example, by real-time monitoring of power grid price data and regional power grid load conditions, when it is found that the power grid price in a certain area has risen or a local overload has occurred, the power allocation weight of non-emergency charging piles in the area is adjusted to give priority to the power supply of emergency charging piles and charging piles that have less impact on the power grid load.

[0049] Embodiment 3: The real-time control module collects data such as the real-time power of the charging pile, the battery health status, and the user charging emergency level. The real-time power of the charging pile is obtained through the power monitoring device installed inside the charging pile, which can monitor the power output of the charging pile in real time. The battery health status can be obtained through the communication between the vehicle battery management system and the charging station, such as the remaining battery power, battery internal resistance and other parameters, which can reflect the health of the battery. The user charging emergency level is selected by the user on the charging platform or determined according to the system preset rules. For example, when the remaining mileage of the vehicle is extremely low, it is automatically determined to be a high emergency level.

[0050] Generate a dynamic control coefficient based on the collected data. Assume that the dynamic control coefficient is , the calculation formula can be ,in is the real-time power of the charging pile, is the battery health status parameter (normalized), Provides charging urgency level for users (high, medium, and low correspond to different values). , , is the weight coefficient, which is set according to the actual situation.

[0051] Based on the control coefficient and the real-time electricity price data of the power grid, the reinforcement learning algorithm is used to calculate the power adjustment range of each charging pile. The reinforcement learning algorithm is an algorithm that learns the optimal strategy based on the reward signal fed back by the environment through the interaction between the intelligent agent and the environment. In this embodiment, the intelligent agent is a real-time control module, the environment is the power grid and charging pile system of the charging station, and the reward signal can be set as an indicator that comprehensively considers factors such as power supply cost and charging efficiency. Through continuous interaction and learning with the environment, the algorithm calculates the power adjustment range of each charging pile.

[0052] If the adjustment range exceeds the preset safety threshold, the power limit instruction is triggered and a control abnormality signal is sent to the power supply performance monitoring module. The preset safety threshold is determined based on factors such as the rated power of the charging pile and the safe operating range of the power grid. When the calculated power adjustment range exceeds the threshold, in order to protect the safety of the charging pile and power grid equipment, the power limit instruction is immediately triggered to limit the power adjustment of the charging pile, and a control abnormality signal is sent to the power supply performance monitoring module for subsequent analysis and processing of the abnormal situation.

[0053] Embodiment 4: This embodiment describes the collaborative working mechanism of the power supply performance monitoring module and the energy storage coordination module. By monitoring the regulation process and rationally using the energy storage system, the stability and reliability of the power supply of the charging station are improved, and the power supply of high-priority charging piles is guaranteed when regulation anomalies occur.

[0054] The power supply performance monitoring module records the start time of each regulation operation and end time , by calculating The control response time is obtained. This time reflects the system's response speed to the control command and is one of the important indicators for measuring system performance.

[0055] Collect the power deviation value of the charging pile after regulation The grid load fluctuation rate The power deviation value is the difference between the actual output power of the charging pile after regulation and the expected power. The grid load fluctuation rate is obtained by calculating the change rate of the grid load before and after regulation. The deviation value and the fluctuation rate are normalized and weighted to generate the regulation efficiency evaluation value. Assume that the regulation efficiency evaluation value is , the calculation formula can be ,in is the rated power of the charging pile, , is the weight coefficient, which is set according to the actual situation.

[0056] If the evaluation value If it exceeds the preset threshold, the current regulation process is judged to be abnormal and marked as a regulation failure record. The preset threshold is determined based on the actual operating requirements and empirical data of the charging station. When a regulation failure record appears, it means that there is a problem with the current power supply regulation and measures need to be taken to optimize it. The processor is connected to the energy storage coordination module, which dynamically switches the charging and discharging mode of the energy storage system based on the regulation efficiency evaluation value and the grid load status. The remaining capacity, charging and discharging efficiency, and life attenuation parameters of the energy storage system will be collected to construct the energy storage state matrix. For example, the energy storage state matrix can be expressed as ,in is the remaining capacity of the energy storage system, For charging efficiency, is the discharge efficiency, is the depth of discharge parameter.

[0057] Based on the matrix eigenvalue and the real-time electricity price gradient, a greedy algorithm is used to select the optimal charging and discharging period. A greedy algorithm is an algorithm that takes the optimal decision under the current state in each step. In this embodiment, according to the real-time electricity price gradient and the state of the energy storage system, charging is selected when the electricity price is low and discharging is selected when the electricity price is high to reduce the charging cost.

[0058] When the control failure record is triggered continuously, the energy storage coordination module starts the emergency power supply strategy and preferentially calls the energy storage system to supply power to the high-priority charging piles. When the first unqualified record is recorded ( is the preset value), the energy storage coordination module matches the discharge power of the energy storage system with the demand of the high-priority charging pile according to the power supply priority of the charging pile, generates a power supply compensation plan, and ensures the normal power supply of the high-priority charging pile.

[0059] Embodiment 5: This embodiment illustrates the specific application of the user priority evaluation module and the power grid interaction module. It optimizes power supply distribution by reasonably evaluating user priorities and optimizes the coordinated power supply of charging stations and power grids by using the data of the power grid interaction module, thereby improving user satisfaction and power grid resource utilization efficiency.

[0060] The processor is in communication with the user priority assessment module, which calculates the user priority weight based on the user's charging urgency level, historical credit score, and vehicle remaining range. The user's urgency level is divided into three levels: high, medium, and low, and different weight coefficients are assigned to each level. For example, the weight coefficient for high urgency level is , the weight coefficient of the medium emergency level is , the low emergency level weight coefficient is ,and .

[0061] Collect user credit score data and generate credit correction factors through normalization. Assume that the user credit score is , the maximum credit score is , the minimum value is , then the credit correction factor .

[0062] Based on the vehicle's remaining range Distance to charging station The ratio of , calculates the endurance urgency The range urgency reflects how difficult it is for the vehicle to reach other charging stations with the current remaining power.

[0063] Linearly combine the weight coefficient, credit correction factor and endurance urgency to output the final user priority weight ,in The value corresponding to the user's charging urgency level (high, medium, and low correspond to different values). The power supply load distribution module uses the weight value as a constraint condition to adjust the power distribution ratio of the charging pile and give priority to powering high-priority users.

[0064] The processor is connected to the grid interaction module, which obtains the load distribution, electricity price fluctuation and renewable energy output data of the regional grid in real time. The load distribution data of the regional grid is obtained through the grid monitoring system, which can accurately reflect the power load situation in different regions. The electricity price fluctuation data is released by the grid company or obtained through the relevant data interface, and the renewable energy output data comes from the renewable energy power generation equipment connected to the grid, such as solar panels, wind turbines, etc.

[0065] The power supply load distribution module combines the data from the power grid interaction module and uses a game theory model to optimize the coordinated power supply strategy between the charging station and the power grid. The game theory model takes into account the interests and decisions of both the charging station and the power grid, and dynamically adjusts the power supply upper limit and time allocation of the charging pile by analyzing the benefits and costs under different strategies. For example, when the power grid load is low and the renewable energy generation is sufficient, the power supply upper limit of the charging station is increased to encourage users to charge during this period; when the power grid load is peak, the power supply upper limit is appropriately lowered to guide users to charge during off-peak hours, so as to achieve coordinated optimization of power supply between the charging station and the power grid.

[0066] The above embodiments are only used to illustrate the technical solutions of the present disclosure, rather than to limit them. Although the present disclosure has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present disclosure.

Claims

1. A power supply optimization and control system for new energy vehicle charging stations during power supply peak period, characterized in that: It includes a processor, a charging demand prediction module, a power supply load distribution module, a real-time control module and a power supply performance monitoring module; The charging demand prediction module predicts the charging demand distribution in the future period based on the historical charging data and user behavior characteristics, and sends the prediction result to the power supply load distribution module; The power supply load distribution module dynamically allocates the power supply priority and power upper limit of each charging pile according to the prediction results and the current grid load status; The real-time control module dynamically adjusts the power supply priority and power limit based on the real-time operation data of the charging pile and the power grid fluctuation information; The power supply performance monitoring module records the response time and deviation value of the regulation process and generates a regulation abnormality signal.

2. The power supply optimization and control system according to claim 1, characterized in that: The specific operation process of the charging demand prediction module is as follows: The timestamp, charging power, user stay time and charging period distribution characteristics in the historical charging data are extracted, and the periodic component and trend component are generated through the time series decomposition algorithm; the reservation preference, charging frequency and emergency charging mark in the user behavior data are collected, and the user behavior characteristics are classified and weighted using the random forest model to output the charging demand prediction value; if the deviation between the predicted value and the actual charging demand exceeds the preset threshold, the prediction calibration signal is triggered and the model parameters are updated.

3. The power supply optimization and control system according to claim 1, characterized in that: The power supply load distribution module adopts a multi-objective optimization algorithm, which specifically includes: A nonlinear constraint model is constructed with the grid load balance, charging pile utilization and user waiting time as optimization objectives. The Lagrangian relaxation method is introduced to relax the constraints, and the initial power supply priority and power allocation plan of each charging pile are generated in combination with the dynamic programming algorithm. When grid electricity price fluctuations or local overloads are detected, the dynamic priority adjustment strategy is activated to reduce the power allocation weight of non-emergency charging piles.

4. The power supply optimization and control system according to claim 3, characterized in that: The specific operation process of the real-time control module is as follows: The real-time power, battery health status and user charging urgency level of the charging pile are collected to generate a dynamic control coefficient. Based on the control coefficient and the real-time electricity price data of the power grid, a reinforcement learning algorithm is used to calculate the power adjustment range of each charging pile. If the adjustment range exceeds the preset safety threshold, the power limit instruction is triggered and a control abnormality signal is sent to the power supply performance monitoring module.

5. The power supply optimization and control system according to claim 1, characterized in that: The specific analysis process of the power supply performance monitoring module includes: Record the start and end time of each regulation operation, and calculate the regulation response time; collect the power deviation value and grid load fluctuation rate of the charging pile after regulation, perform normalized weighted calculation on the deviation value and fluctuation rate, and generate a regulation efficiency evaluation value; if the evaluation value exceeds the preset threshold, the current regulation process is judged to be abnormal and marked as an unqualified regulation record.

6. The power supply optimization and control system according to claim 5, characterized in that: The processor is communicatively connected to the energy storage coordination module, and the energy storage coordination module dynamically switches the charging and discharging mode of the energy storage system according to the regulation efficiency evaluation value and the grid load status; when the regulation unqualified records are continuously triggered, the energy storage coordination module starts the emergency power supply strategy and preferentially calls the energy storage system to power the high-priority charging piles.

7. The power supply optimization and control system according to claim 6, characterized in that: The specific strategy generation process of the energy storage coordination module is as follows: The remaining capacity, charging and discharging efficiency and life attenuation parameters of the energy storage system are collected to construct an energy storage state matrix. Based on the matrix eigenvalues ​​and the real-time electricity price gradient, a greedy algorithm is used to select the optimal charging and discharging period. When the peak load of the power grid is detected, the discharge power of the energy storage system is matched with the demand of the charging pile to generate a power supply compensation plan.

8. The power supply optimization and control system according to claim 1, characterized in that: The processor is in communication with a user priority assessment module, which calculates a user priority weight based on the user's charging urgency level, historical credit score, and remaining vehicle range; the power supply load distribution module uses the weight value as a constraint to adjust the power distribution ratio of the charging pile.

9. The power supply optimization and control system according to claim 8, characterized in that: The specific calculation process of the user priority evaluation module includes: The user's urgency level is divided into three levels: high, medium and low, and each is assigned a different weight coefficient. The user's credit score data is collected and a credit correction factor is generated through normalization. The range urgency is calculated based on the ratio of the vehicle's remaining range to the distance to the charging station. The weight coefficient, credit correction factor and range urgency are linearly combined to output the final user priority weight.

10. The power supply optimization and control system according to claim 1, characterized in that: The processor is communicatively connected to the power grid interaction module, and the power grid interaction module obtains the load distribution, electricity price fluctuations and renewable energy output data of the regional power grid in real time; the power supply load distribution module combines the data of the power grid interaction module, adopts the game theory model to optimize the coordinated power supply strategy of the charging station and the power grid, and dynamically adjusts the power supply upper limit and time period allocation of the charging pile.

Images