Intelligent electricity utilization information acquisition optimization system based on AI algorithm

Abstract

The invention discloses an intelligent electricity utilization information acquisition optimization system based on an AI algorithm, which relates to the technical field of data analysis and comprises an acquisition module I, a judgment module I, a regulation and control module I, a calculation module, an acquisition module II, a judgment module II, a statistics module I, a regulation and control module II, a maintenance module, a judgment module III, a statistics module II, a regulation and control module III and a meteorological regulation and control module. According to the invention, the electricity utilization information of the charging station can be collected, and the electricity utilization power is optimized and regulated according to the electricity utilization condition of the automobile, so that the electricity utilization power load of the charging station does not exceed the bearing capacity, and the accuracy of electricity utilization load regulation is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and particularly to an intelligent power consumption information acquisition and optimization system based on an AI algorithm. Background Art

[0002] With the innovation and popularization of new energy technologies, electric vehicles are widely used, and the demand and energy consumption of public charging stations are also continuously increasing. The charging piles in charging stations usually share the same power distribution network with other buildings. Therefore, the carrying capacity of a charging station usually depends on its fixed upper limit of power consumption load.

[0003] Since new energy vehicles usually have a relatively high charging power and power consumption, the difference between the peak and valley values of the power consumption of the charging station is relatively large. For example, in a charging station near a residential building, users mostly choose to charge their cars at night, causing the power consumption of the charging station to rise rapidly within a short period of time, while the situation is opposite in a charging station near an office building.

[0004] Taking the charging station near a residential building as an example, during the period from after work to night, a large number of new energy vehicles use electricity simultaneously, which easily causes the instantaneous power consumption to exceed the upper limit of the power consumption load of the charging station, thereby leading to power outages. At midnight, the power consumption demand of the charging station drops significantly, resulting in redundant power consumption.

[0005] For the above technical solutions, it is necessary to collect the power consumption information of the charging station and optimize and control the power consumption according to the power consumption status of the vehicles, so that the power consumption load of the charging station does not exceed the carrying capacity and improve the accuracy of the power consumption load control. Summary of the Invention

[0006] The purpose of the present invention is to provide an intelligent power consumption information acquisition and optimization system based on an AI algorithm to solve the problems raised in the above background art.

[0007] The intelligent power consumption information acquisition and optimization system based on an AI algorithm includes the following modules:

[0008] Acquisition Module I: Acquire the battery capacity C, rated charging power P, average charging duration, average power-off duration, and power consumption load P of the charging station of the nth vehicle among N vehicles from historical data n , rated charging power P n , average charging duration average power-off duration and the power consumption load P of the charging station m ;

[0009] Judgment Module I: Judge whether the sum of the rated charging powers of the currently charging vehicles in the qth detection period exceeds P. If it exceeds, execute Regulation Module I; if not, let the vehicles charge at P and execute Calculation Module. m , if it exceeds, execute Regulation Module I; if not, let the vehicles charge at P n and execute Calculation Module.

[0010] Regulation Module I: Allocate the charging power of the vehicle in sequence according to the average charging duration, enabling the vehicle with a shorter average charging duration to preferentially charge at the rated charging power. When the remaining power of the vehicle reaches αC n reduce its charging power and allocate the redundant power to other vehicles. α is the first dynamic coefficient, and α ∈ (0, 1];

[0011] Calculation Module: Obtain the remaining power of the nth vehicle to be charged in the qth detection period and calculate its estimated power consumption duration as:

[0012] Acquisition Module II: Obtain the actual charging duration of the nth vehicle in the qth detection period and the actual power-off duration and calculate its actual power consumption duration as:

[0013] Judgment Module II: Set the maximum stay duration A. If it is determined that the stay is timed out, execute Statistics Module I. Otherwise, it is determined that the stay is not timed out;

[0014] Statistics Module I: Let the first statistical value of the nth vehicle in the qth detection period be If execute Regulation Module II. Q is the number of detection periods, and Z 0 is a positive integer;

[0015] Regulation Module II: Reduce the actual charging power of the nth vehicle in the (Q + 1)th detection period.

[0016] By adopting the above technical solution, Acquisition Module I obtains the historical data of N vehicles in the charging station. The power-off duration refers to the total duration from when the vehicle finishes charging to when the user arrives at the charging station and completes the power-off state. Judgment Module I determines whether the sum of the rated charging powers of the currently charging vehicles exceeds the power consumption load. If it is determined to exceed, Regulation Module I allocates the charging power in sequence according to the average charging duration of each vehicle during charging, enabling the vehicle with a shorter average charging duration to preferentially charge at the rated charging power, thereby preferentially exiting the charging state. When the remaining power of the vehicle reaches αC n reduce the charging power and allocate the redundant power to other vehicles. With such a setting, since the actual power utilization rate of the battery of new energy vehicles is usually relatively high before reaching the 80% - 90% stage, and after this stage, to reduce energy loss, extend the battery life, and prevent overcharging, the battery management system of the vehicle usually actively reduces the actual charging power and adopts trickle charging to protect the battery. Therefore, allocate the charging power in sequence according to the average charging duration of the vehicles during charging, and when charging to the dynamic threshold αCn When the power is actively reduced, the power load of the charging station does not exceed the bearing capacity, reducing the probability of grid collapse caused by overcrowding during peak hours, which is beneficial to improving resource utilization and the accuracy of power load regulation; if it is judged that it has not exceeded, the cars being charged are charged at the rated charging power. The calculation module calculates the estimated power consumption duration of the nth car, and the acquisition module II calculates the actual power consumption duration. If the judgment module II determines that the stay is overtime, the statistics module I records the first statistical value If it is recognized that Then, in the (Q + 1)th detection cycle, the regulation module II reduces the actual charging power of the nth car below the rated charging power. By setting the maximum stay duration in this way, the behavior of users occupying the charging pile overtime is identified, and vehicles with multiple overtimes are recorded. In subsequent cycles, their charging power is restricted, effectively suppressing the problem of resource waste, facilitating the reasonable allocation of charging pile resources, reducing the grid load fluctuation caused by vehicle detention at the same time, restricting user behavior, improving the turnover rate of charging piles, and thus improving the accuracy of power load regulation.

[0017] Optionally, when the judgment module II determines that the stay is not overtime, the judgment module III is also executed;

[0018] Judgment module III: Set the warning stay duration B of the nth car n , B n The calculation model of is: If Then it is judged that the stay time is long, and the statistics module II is executed. If Then it is judged that the stay time is reasonable;

[0019] Statistics module II: Let the second statistical value of the nth car in the qth detection cycle be X 0 is a positive integer greater than or equal to one. If Then the regulation module III is executed;

[0020] Regulation module III: In the (Q + 1)th detection cycle, let the nth car be charged at the rated charging power. When the remaining power of the car reaches αC n Reduce its charging power.

[0021] By adopting the above technical solution, when the judgment module II determines that the stay is not overtime, the judgment module III sets the warning stay duration B of the nth car n , if it is judged that the stay time is long, the statistics module II records the second statistical value as If it is recognized that Then, in the (Q + 1)-th detection cycle, the regulation module III commands the n-th vehicle to charge at the rated charging power. When the remaining battery charge of the vehicle reaches αC n , the charging power is reduced. With such a setting, through the warning stay duration B n , the differences in users' electricity consumption habits are judged. If the electricity consumption duration of a user is recorded as long for many times, the regulation module causes the vehicle of this user to reduce the power when charging to the dynamic threshold, instead of setting a limit from the initial charging state. This is beneficial to meeting the basic needs of users, while reducing resource waste. Through the method of classified statistics, general overtime and long-term violation behaviors can be distinguished, reducing the probability that a user is stranded due to an emergency and triggering power restrictions, improving the accuracy and fairness of electricity load regulation, facilitating the reasonable allocation of charging pile resources, and reducing the probability of power grid fluctuations.

[0022] Optionally, in the judgment module III, according to the first sensitivity constant D, the calculation model of B n is corrected, and the updated calculation model is: where D ∈ (0, 1].

[0023] By adopting the above technical solution, the proportion of the average electricity consumption duration in the warning stay duration is dynamically adjusted through the first sensitivity constant. As the number of detection cycles increases, the calculation of the warning stay duration depends more on the user's behavior of recently completing the exit from electricity consumption. With such a setting, it is beneficial to adapt to the dynamic changes of user habits, be closer to the current needs of users, further improve the reasonable allocation of charging pile resources, and thus improve the accuracy of electricity load regulation.

[0024] Optionally, in the acquisition module I, the battery usage duration R of the n-th vehicle is also acquired n and the upper limit of the battery life

[0025] In the judgment module III, according to R n and , the value of the first sensitivity constant D is determined. The specific calculation model for the value of D is: where is the time constant,

[0026] By adopting the above technical solution, the battery of a vehicle with aging phenomenon is prone to charging delay due to the decline in battery performance, increasing the expected charging duration. By introducing the battery service life to dynamically adjust the first sensitivity constant D, the warning stay duration is actively increased, while the battery with a shorter usage time has smaller performance changes and the warning stay duration is not changed. Thus, it can intelligently adapt to the usage situation of the vehicle, is beneficial to real-time observation of the battery health status, is beneficial to the reasonable allocation of charging pile resources, reduces the power grid load fluctuation, and thus improves the accuracy of electricity load regulation.

[0027] Optionally, in the judgment module III, according to the second sensitivity constant E, the calculation model of B n is corrected, and the updated calculation model after correction is: where E ∈ (0, 1].

[0028] By adopting the above technical solution, the proportion of the power-off duration in the warning stay duration is dynamically adjusted through the second sensitivity constant E. As the detection period increases, the actual charging duration of each period fluctuates less, and the calculation of the warning stay duration depends more on the user's recent behavior of completing power-off. Such a setting is beneficial to adapting to the dynamic changes of user habits, getting closer to the current needs of users, further improving the reasonable allocation of charging pile resources, and thus improving the accuracy of power load regulation.

[0029] Optionally, in the acquisition module II, the actual ambient temperature of the nth vehicle in the qth detection period and the average temperature U of the geographical location where the charging station is located are also acquired ; g ;

[0030] In the judgment module III, according to U and U g the value of the second sensitivity constant E is determined, and the specific calculation model of the value of E is: where U 0 is a temperature constant, 2°C ≤ U 0 < 10°C.

[0031] By adopting the above technical solution, the second sensitivity constant E is dynamically adjusted by introducing the ambient temperature data of the charging station. When in extreme high or low temperature, resulting in a large deviation between the actual ambient temperature and the average ambient temperature, the power-off duration of the user is dynamically adjusted according to the degree of temperature deviation, thereby reasonably increasing the warning stay duration, reducing the probability of misjudging the user when the environment interferes with the user's travel, improving the accuracy and fairness of power load regulation, being beneficial to the reasonable allocation of charging pile resources, reducing the probability of power grid fluctuations, and improving the practicality and reliability of the system.

[0032] Optionally, in the regulation module I, when the remaining power of the vehicle reaches αC n , its charging power is reduced, specifically, the charging power is reduced to βP n , where β is the second dynamic coefficient, and the calculation model of β is: where γ is the third dynamic coefficient, γ ∈ [0, 1).

[0033] By adopting the above technical solution, the value of the second dynamic coefficient β is calculated according to the third dynamic coefficient γ, so that the trickle slow charging time is extended When the user is able to perform the operation of exiting the charging process at the charging pile, the vehicle can still complete the charging within the average power-off duration, reducing the impact on the normal use of the user, which is beneficial to improving the resource utilization rate, reducing the battery energy loss, reducing the probability of grid load fluctuations, and improving the accuracy of power load regulation.

[0034] Optionally, in the regulation module III, when the remaining power of the vehicle is charged to αC n , the charging power is reduced, specifically, the charging power is reduced to βP n , where β is the second dynamic coefficient, and the calculation model of β is: where γ is the third dynamic coefficient, and γ ∈ [0, 1).

[0035] By adopting the above technical solution, the value of the second dynamic coefficient β is calculated according to the third dynamic coefficient γ, so that the trickle slow charging time is extended When the user is able to perform the operation of exiting the charging process at the charging pile, the vehicle can still complete the charging within the average power-off duration, reducing the impact on the normal use of the user, which is beneficial to improving the resource utilization rate, reducing the battery energy loss, reducing the probability of grid load fluctuations, and improving the accuracy of power load regulation.

[0036] Optionally, it further includes a maintenance module: setting the warning statistical value as Z max , Z max is an integer greater than Z 0 , when it is recognized that , a maintenance warning for the nth vehicle is sent to the management terminal.

[0037] By adopting the above technical solution, if the total value of the first statistical value recorded by the maintenance module is too high, a maintenance warning for the vehicle is sent to the management terminal to actively identify the vehicle that needs maintenance. The management terminal can actively push warning information to the user or propose behaviors such as replacing service content, reducing the maintenance cost and potential safety hazards, and improving the practicability and reliability of the system.

[0038] Optionally, it further includes a meteorological regulation module: obtaining the future 24-hour environmental temperature change trend and the user's power consumption demand at the geographical location where the charging station is located. When there is extremely cold weather, the charging station implements a preheating strategy, transfers the load of redundant lines to the charging pile for preheating, and applies for capacity expansion of the power load in advance. When there is extremely hot weather, the charging station implements a dynamic derating charging strategy, reduces the charging power of the charging pile with a higher working temperature, and automatically resumes after the temperature drops to the safety threshold.

[0039] By adopting the above technical solutions, when there is extremely cold weather, the charging station implements a preheating strategy, transferring the load of redundant lines to the charging piles for preheating to reduce start-up delay and reduce additional loss of battery energy; when there is extremely hot weather, the charging station implements a dynamic derating charging strategy to increase the heat dissipation and transfer the load, which is beneficial to improving the safety of equipment use, increasing the charging efficiency, further enhancing the rational allocation of charging pile resources, and thus improving the accuracy of power load regulation.

[0040] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0041] 1. Since the actual power utilization rate of the battery of new energy vehicles is usually relatively high before the charging stage reaches 80% - 90%, and after this stage, in order to reduce energy loss, extend the battery life and prevent overcharging, the battery management system of the vehicle usually actively reduces the actual charging power and adopts trickle charging to protect the battery. Therefore, the charging power is allocated in turn according to the average charging duration of the vehicles during charging, and when charging reaches the dynamic threshold αC n actively derates, so that the power load of the charging station does not exceed the bearing capacity, reducing the probability of grid collapse caused by overcrowding during peak periods, which is beneficial to improving resource utilization rate and the accuracy of power load regulation; by setting the maximum stay duration, identifying the behavior of users occupying the charging piles for overtime, recording the vehicles with multiple overtimes, and restricting their charging power in subsequent cycles, thus effectively suppressing the problem of resource waste, which is beneficial to the rational allocation of charging pile resources, while reducing the grid load fluctuation caused by vehicle detention, restricting user behavior, increasing the turnover rate of charging piles, and thus improving the accuracy of power load regulation.

[0042] 2. After the judgment module II determines that the stay is not overtime, the judgment module III sets the warning stay duration B n for the nth vehicle. If it is judged that the stay time is long, the statistics module II records the second statistical value as If it is recognized that then in the (Q + 1)th detection cycle, the regulation module III makes the nth vehicle charge at the rated charging power. When the remaining power of the vehicle reaches αC n the charging power is reduced. With such settings, by the warning stay duration B n the difference in users' electricity consumption habits is judged. If the electricity consumption duration of the user is recorded as long for many times, the regulation module makes the vehicle of this user derate when charging reaches the dynamic threshold, rather than limiting the power from the initial charging state, which is beneficial to meeting the basic needs of users, while reducing resource waste. By the method of classified statistics, general overtime and long-term violation behaviors can be distinguished, reducing the probability of power limit triggered by users' detention due to emergencies, improving the accuracy and fairness of power load regulation, being beneficial to the rational allocation of charging pile resources, and reducing the probability of grid fluctuation.

[0043] 3. For automotive batteries with aging problems, due to the decline in battery performance, charging delays are likely to occur, increasing the estimated charging duration. By introducing the first sensitivity constant D for dynamic adjustment of battery service life, the warning stay duration is actively increased. For batteries with shorter usage times, the performance change is smaller, and the warning stay duration is not changed, thus intelligently adapting to the usage conditions of the vehicle, facilitating real-time observation of the battery health status, facilitating the rational allocation of charging pile resources, reducing grid load fluctuations, and thus improving the accuracy of power consumption load regulation.

[0044] 4. By introducing environmental temperature data of the charging station to dynamically adjust the second sensitivity constant E, when in extreme high or low temperatures, resulting in a large deviation between the actual environmental temperature and the average environmental temperature, the user's power-off duration is dynamically adjusted according to the degree of temperature deviation, thereby reasonably increasing the warning stay duration, reducing the probability of misjudging users when the environment interferes with users' travel, improving the accuracy and fairness of power consumption load regulation, facilitating the rational allocation of charging pile resources, reducing the probability of grid fluctuations, and improving the practicality and reliability of the system.

[0045] 5. Calculate the value of the second dynamic coefficient β according to the third dynamic coefficient γ, so as to extend the trickle slow charging time When the user arrives at the charging pile and executes the power-off charging operation, the vehicle can still complete charging within the average power-off duration, reducing the impact on the normal use of the user, facilitating the improvement of resource utilization rate, reducing battery energy loss, reducing the probability of grid load fluctuations, and improving the accuracy of power consumption load regulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] To more clearly illustrate the solutions in the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following described drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0047] Figure 1 It is a module block diagram of the intelligent power consumption information acquisition optimization system based on the AI algorithm in the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0048] The following will combine the Figure 1 in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0049] This embodiment discloses an intelligent power consumption information acquisition optimization system based on an AI algorithm. Referring to Figure 1 , it includes the following modules:

[0050] Acquisition Module I: Acquire the battery capacity C of the nth vehicle among the historical data of N vehicles in the charging station n , the rated charging power P n , the average charging duration The average power-off duration The battery usage duration R n , the upper limit of battery life and the power load P of the charging station, m where N is a positive integer greater than or equal to 2, and n = 1, 2,..., N.

[0051] Judgment Module I: Judge whether the sum of the rated charging powers of the currently charging vehicles in the charging station in the qth detection period exceeds the power load P m . If it exceeds, execute Regulation Module I. If it does not exceed, let the charging vehicles charge at the rated charging power P n and execute the calculation module, where q is a positive integer greater than or equal to 2.

[0052] Regulation Module I: Allocate the charging power of the vehicles in sequence according to the average charging duration, so that the vehicles with shorter average charging durations charge at the rated charging power first. When the remaining power of a vehicle reaches αC n , reduce the charging power to βP n , and allocate the redundant power to other vehicles. Among them, α is the first dynamic coefficient, α ∈ (0, 1], and β is the second dynamic coefficient. The calculation model of β is: γ is the third dynamic coefficient, γ ∈ [0, 1).

[0053] Calculation Module: Acquire the remaining power of the nth vehicle to be charged in the qth detection period Calculate the estimated power consumption duration of the nth vehicle The calculation model of which is:

[0054] Acquisition Module II: Acquire the actual charging duration of the nth vehicle in the qth detection period and the actual power-off duration Calculate the actual power consumption duration of the nth vehicle as Acquire the actual ambient temperature of the nth vehicle in the qth detection period and the average temperature U of the geographical location where the charging station is located g , and execute Judgment Module II and Meteorological Regulation Module.

[0055] Judgment Module II: Set the maximum residence duration A. If then it is determined that the residence is timed out, and Statistics Module I is executed. If then it is determined that the residence is not timed out, and Judgment Module III is executed.

[0056] Statistics Module I: Let the first statistical value of the nth vehicle in the qth detection cycle be Q is the fixed number of detection cycles, and Z 0 is a positive integer greater than or equal to one. If then Regulation Module II is executed.

[0057] Regulation Module II: In the (Q + 1)th detection cycle, reduce the actual charging power of the nth vehicle below the rated charging power, and execute the Maintenance Module.

[0058] Maintenance Module: Set the warning statistical value as Z max , Z max is an integer greater than Z 0 When is recognized, a maintenance warning for the nth vehicle is sent to the management terminal.

[0059] Judgment Module III: Set the warning residence duration B for the nth vehicle n , B n The calculation model is:

[0060] Among them, D is the first sensitivity constant, and the calculation model for the value of D is:

[0061] Among them, is the time constant,

[0062] E is the second sensitivity constant, and the calculation model for the value of E is:

[0063] Among them, U 0 is the temperature constant, 2°C ≤ U 0 < 10°C;

[0064] If then it is determined that the residence time is long, and Statistics Module II is executed. If then it is determined that the residence time is reasonable.

[0065] Statistics Module II: Let the second statistical value of the nth vehicle in the qth detection cycle be X 0 is a positive integer greater than or equal to one. If then Regulation Module III is executed.

[0066] Regulation Module III: In the (Q + 1)-th detection cycle, let the n-th vehicle charge at the rated charging power. When the remaining battery charge of the vehicle reaches αC n reduce the charging power to βP n .

[0067] Meteorological Regulation Module: Obtain the environmental temperature change trend and user electricity demand in the next 24 hours at the geographical location where the charging station is located. When there is extremely cold weather, the charging station implements a preheating strategy, transfers the load of redundant lines to the charging piles for preheating, and submits an application for power capacity expansion in advance for the electricity power load. When there is extremely hot weather, the charging station implements a dynamic derating charging strategy, reduces the charging power of the charging piles with higher working temperatures, and automatically resumes after the temperature drops to the safety threshold.

[0068] The implementation principle of the intelligent electricity consumption information acquisition and optimization system based on the AI algorithm in this embodiment is as follows:

[0069] Obtain the battery capacity C, rated charging power P n , average charging duration n , average exit electricity consumption duration average battery usage duration R , upper limit of battery life n , and the electricity power load P of the charging station from the historical data of N vehicles in the charging station through Acquisition Module I. Among them, the exit electricity consumption duration refers to the total duration from when the vehicle finishes charging to when the user arrives at the charging station and completes the exit from the electricity consumption state. Judgment Module I judges whether the sum of the rated charging powers of the currently charging vehicles in the charging station in the q-th detection cycle exceeds the electricity power load P m . If the judgment is that it exceeds, then execute Regulation Module I. If the judgment is that it does not exceed, then let the charging vehicles charge at the rated charging power and execute Calculation Module. m When Judgment Module I judges that it exceeds, Regulation Module I distributes the charging power of the vehicles in sequence according to the average charging duration of each charging vehicle, so that the vehicles with shorter average charging duration charge at the rated charging power first, so that the vehicles with faster charging speed exit the charging state first. When the remaining battery charge of the vehicle reaches αC

[0070] reduce the charging power to βP n , and distribute the redundant power to other vehicles. Among them, α is the first dynamic coefficient, α ∈ (0, 1], β is the second dynamic coefficient, and the calculation model of β is: n γ is the third dynamic coefficient, γ ∈ [0, 1).

[0071] ​Since the actual power utilization rate of the battery of new energy vehicles is usually relatively high before the charging stage reaches 80% - 90%, and after this stage, in order to reduce energy loss, extend the battery life and prevent overcharging, the vehicle's battery management system usually actively reduces the actual charging power and adopts trickle charging to protect the battery. Therefore, the charging power is intelligently allocated according to the average charging duration of the vehicle during charging, and when charging reaches the dynamic threshold αC n actively performs AI intelligent dynamic derating, so that the power load of the charging station does not exceed the carrying capacity, reducing the probability of grid collapse caused by overcrowding during peak periods, which is beneficial to improving resource utilization rate and enhancing the accuracy of power load regulation.

[0072] Calculate the value of the second dynamic coefficient β according to the third dynamic coefficient γ, so as to extend the trickle slow charging time During the process that the user can execute the charging exit operation when arriving at the charging pile, the vehicle can still complete charging within the average exit power consumption duration, reducing the impact on the normal use of the user, which is beneficial to improving resource utilization rate, reducing battery energy loss, reducing the probability of grid load fluctuation, and enhancing the accuracy of power load regulation.

[0073] When the judgment module I judges that it has not exceeded, the calculation module obtains the remaining power of the nth vehicle to be charged in the qth detection cycle Calculate the estimated power consumption duration of the nth vehicle The acquisition module II obtains the actual charging duration of the nth vehicle in the qth detection cycle and the actual exit power consumption duration Calculate the actual power consumption duration and obtain the actual ambient temperature of the nth vehicle in the qth detection cycle and the average temperature U of the geographical location where the charging station is located g , the judgment module II sets the maximum stay duration A. If then it is judged that the stay is overtime, and the statistics module I is executed. If then it is judged that the stay is not overtime, and the judgment module III is executed.

[0074] When the judgment module II judges that the stay is overtime, the statistics module I records the first statistical value of the nth vehicle in the qth detection cycle as Q is the number of fixed detection cycles, Z 0 is a positive integer greater than or equal to one. If it is recognized that then the regulation module II reduces the actual charging power of the nth vehicle below the rated charging power in the (Q + 1)th detection cycle. The maintenance module sets the warning statistical value Z max , Z max is an integer greater than Z 0 If the maintenance module recognizes that When it is time, send a maintenance warning for the nth vehicle to the management terminal.

[0075] With such settings, by setting the maximum stay duration, identify the behavior of users occupying the charging pile for over time, record the vehicles with multiple overtimes, and limit their charging power in subsequent cycles, thus effectively suppressing the problem of resource waste, facilitating the reasonable allocation of charging pile resources, and reducing the power grid load fluctuations caused by vehicle detention. Using the AI algorithm to intelligently restrict user behavior, improve the turnover rate of the charging pile, and thus improve the accuracy of power load regulation.

[0076] If the total value of the first statistical value recorded by the maintenance module is too high, send a maintenance warning for this vehicle to the management terminal, actively identify the vehicle that needs maintenance. The management terminal can actively push warning information to the user or propose actions such as changing service content, reducing maintenance costs and potential safety hazards, and enhancing the practicality and reliability of the system.

[0077] After the judgment module II determines that the stay is not overtime, the judgment module III sets the warning stay duration for the nth vehicle Among them, the first sensitivity constant Time constant The second sensitivity constant Temperature constant U 0 The value range is 2°C ≤ U 0 < 10°C. If Then it is judged that the stay time is long, and the statistical module II is executed. If Then it is judged that the stay time is reasonable.

[0078] The statistical module II makes the second statistical value of the nth vehicle in the qth detection cycle be X 0 Is a positive integer greater than or equal to one. If it is recognized that Then the regulation module III in the (Q + 1)th detection cycle makes the nth vehicle charge at the rated charging power. When the remaining power of the vehicle reaches αC n At this time, reduce the charging power to βP n .

[0079] With such settings, through the warning stay duration B nIntelligently judge the differences in users' electricity consumption habits. If the electricity consumption duration of a user is recorded as long for multiple times, the regulation module will derate the user's vehicle when it is charged to the dynamic threshold, rather than setting a limit from the initial charging state. This is beneficial to meeting the basic needs of users while reducing resource waste. The method of classification and statistics through AI algorithms can distinguish general overtime and long-term violations, reduce the probability that users are triggered to limit power due to being stranded in case of emergencies, improve the accuracy and fairness of electricity load regulation, facilitate the reasonable allocation of charging pile resources, and reduce the probability of power grid fluctuations.

[0080] Due to the decline in battery performance, the aging vehicle battery is prone to charging delay, resulting in an increase in the expected charging duration. By introducing the dynamic adjustment of the first sensitivity constant D for the battery service life, the warning stay duration is actively increased. While for the battery with a shorter usage time, the performance change is smaller, and the warning stay duration is not changed, thus intelligently adapting to the usage situation of the vehicle, which is beneficial to the real-time observation of the battery health status, the reasonable allocation of charging pile resources, and the reduction of power grid load fluctuations, thereby improving the accuracy of electricity load regulation.

[0081] Dynamically adjust the proportion of the exit electricity consumption duration in the warning stay duration through the second sensitivity constant E. As the detection period increases, the actual charging duration fluctuations in each period are smaller, and the calculation of the warning stay duration depends more on the user's recent behavior of completing the exit electricity consumption. With such settings, it is beneficial to adapt to the dynamic changes of users' habits, be closer to the current needs of users, further improve the reasonable allocation of charging pile resources, and thus improve the accuracy of electricity load regulation.

[0082] Dynamically adjust the second sensitivity constant E by introducing the environmental temperature data of the charging station. When in extreme high or low temperatures, resulting in a large deviation between the actual environmental temperature and the average environmental temperature, dynamically adjust the user's exit electricity consumption duration according to the degree of temperature deviation, thereby reasonably increasing the warning stay duration, reducing the probability of misjudging users when the environment interferes with users' travel, improving the accuracy and fairness of electricity load regulation, facilitating the reasonable allocation of charging pile resources, reducing the probability of power grid fluctuations, and improving the practicability and reliability of the system.

[0083] The meteorological warning module obtains the future 24-hour ambient temperature change trend and user electricity demand at the geographical location where the charging station is located in real time. When there is extremely cold weather, the charging station implements a preheating strategy, transfers the load of redundant lines to the charging piles for preheating, and makes an application for capacity expansion of the electricity power load in advance to reduce startup delay and reduce additional loss of battery energy. When there is extremely hot weather, the charging station implements a dynamic derating charging strategy, reduces the charging power of the charging piles with higher working temperatures, and automatically resumes after the temperature drops to the safety threshold, so as to increase the heat dissipation and transfer the load, which is beneficial to improving the safety of equipment use, improving the charging efficiency, further improving the rational allocation of charging pile resources, and thus improving the accuracy of electricity load regulation.

[0084] Obviously, the embodiments described above are only a part of the embodiments of the present invention, rather than all embodiments. The preferred embodiments of the present invention are given in the drawings, but do not limit the patent scope of the present invention. The present invention can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosed content of the present invention more thorough and comprehensive. Although the present invention has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions recorded in the foregoing specific embodiments, or perform equivalent replacements for some of the technical features. Any equivalent structure directly or indirectly using the content of the specification and drawings of the present invention in other related technical fields is similarly within the scope of the patent protection of the present invention.

Claims

1. An intelligent power consumption information acquisition optimization system based on AI algorithms, characterized in that, It includes the following modules: Acquisition Module I: Obtain the battery capacity C, the rated charging power P, the average charging duration, the average power-off duration, and the power load P of the charging station of the nth vehicle among N historical vehicles n , the rated charging power P n , the average charging duration The average power-off duration and the power load P of the charging station m ; Judgment module I: Determine whether the sum of the rated charging powers of the currently charging vehicles in the qth detection period exceeds P m , if it exceeds, execute the regulation module I, if it does not exceed, let the vehicle charge at P n , and execute the calculation module; Regulation Module I: Allocate the charging power of the vehicle according to the average charging duration in sequence, so that the vehicle with a shorter average charging duration is preferentially charged at the rated charging power. When the remaining battery power of the vehicle reaches αC n , reduce its charging power and allocate the redundant power to other vehicles. α is the first dynamic coefficient, and α ∈ (0, 1]; Calculation module: Obtain the remaining power of the nth vehicle to be charged in the qth detection cycle Calculate its estimated power consumption duration as follows: Acquisition Module II: Obtain the actual charging duration of the nth vehicle in the qth detection cycle and the actual power-off duration Calculate its actual power consumption duration as follows: Judgment Module II: Set the maximum stay duration A. If it is determined that the stay is timed out, execute Statistics Module I. Otherwise, it is determined that the stay is not timed out; Statistical module I: Let the first statistical value of the nth vehicle in the qth detection period be If Then execute regulation module II, Q is the number of detection periods, and Z 0 is a positive integer; Regulation Module II: Reduce the actual charging power of the nth vehicle in the (Q + 1)th detection cycle.

2. The intelligent power consumption information acquisition optimization system based on the AI algorithm according to claim 1, wherein: It also includes a Statistics Module II and a Regulation Module III. When the Judgment Module II determines that the stay is not timed out, the Judgment Module III is also executed. Judgment Module III: Set the warning stay duration B of the nth vehicle n , B n The calculation model of is as follows: If Then it is judged that the stay time is long, and the statistical module II is executed. If Then it is judged that the stay time is reasonable; Statistical Module II: Let the second statistical value of the nth vehicle in the qth detection period be X 0 be a positive integer greater than or equal to 1. If then execute Regulation Module III; Regulation Module III: In the (Q + 1)-th detection cycle, let the n-th vehicle charge at the rated charging power. When the remaining power of the vehicle reaches αC n , reduce its charging power.

3. The intelligent power consumption information acquisition optimization system based on the AI algorithm according to claim 2, wherein: In the judgment module III, the calculation model of B is corrected according to the first sensitivity constant D n and the updated calculation model after correction is: where D ∈ (0, 1].

4. The intelligent power consumption information acquisition optimization system based on the AI algorithm according to claim 3, wherein: In the acquisition module I, the battery usage duration R of the nth vehicle is also acquired n and the upper limit of the battery life In the determination module III, according to R n and the value of the first sensitivity constant D is determined. The specific calculation model for the value of D is as follows: Wherein, is the time constant, 5. The intelligent power consumption information acquisition optimization system based on the AI algorithm according to claim 2, characterized in that: In the judgment module III, the calculation model of B is corrected according to the second sensitivity constant E, and the corrected calculation model is updated to: n wherein, E ∈ (0, 1]. ​ 6. The intelligent power consumption information acquisition optimization system based on the AI algorithm according to claim 5, characterized in that: In the acquisition module II, the actual ambient temperature of the nth vehicle in the qth detection period is also acquired and the average temperature U of the geographical location where the charging station is located g ; In the judgment module III, according to U and U g the value of the second sensitivity constant E is determined. The value calculation model of E is specifically: where U 0 is the temperature constant, 2°C ≤ U 0 < 10°C.

7. The intelligent power consumption information acquisition optimization system based on the AI algorithm according to any one of claims 1-6, characterized in that: In regulation module I, when the remaining power of the vehicle reaches αC n the charging power is reduced, specifically, the charging power is reduced to βP n , where β is the second dynamic coefficient, and the calculation model of β is: where γ is the third dynamic coefficient and γ ∈ [0, 1).

8. The intelligent power consumption information acquisition optimization system based on the AI algorithm according to any one of claims 2, characterized in that: In the regulation module III, when the remaining power of the vehicle battery reaches αC n the charging power is reduced, specifically, it is reduced to βP n , where β is the second dynamic coefficient, and the calculation model of β is: where γ is the third dynamic coefficient, and γ ∈ [0, 1).

9. The intelligent power consumption information acquisition optimization system based on the AI algorithm according to any one of claims 1-6, characterized in that: It further includes a maintenance module: setting the warning statistical value as Z max , Z max is an integer greater than Z 0 , and when it is recognized that , a maintenance warning for the nth vehicle is sent to the management terminal.

10. The intelligent power consumption information acquisition optimization system based on the AI algorithm according to any one of claims 1-6, characterized in that: It also includes a Meteorological Regulation Module: Obtain the ambient temperature change trend and user power consumption demand in the next 24 hours at the geographical location where the charging station is located. When there is extremely cold weather, the charging station implements a preheating strategy, transfers the load of redundant lines to the charging piles for preheating, and submits an application for increasing the power load in advance. When there is extremely hot weather, the charging station implements a dynamic derating charging strategy, reduces the charging power of the charging piles with higher working temperatures, and automatically resumes after the temperature drops to the safety threshold.

Images