New energy vehicle charging management method and system based on artificial intelligence

Abstract

The invention provides a new energy vehicle charging management method and system based on artificial intelligence, and the method comprises the steps: obtaining historical vehicle information and driving road network information of a historical new energy vehicle, and determining a vehicle charging total load based on the historical vehicle information and the driving road network information; determining a time load graph based on the total automobile charging load and a preset period, dividing the preset period into a plurality of time zones, and determining a final charging price corresponding to each time zone based on the time load graph; constructing a charging optimization management model based on the final charging price; solving the charging optimization management model by adopting an improved particle swarm optimization algorithm to obtain the final charging power of each to-be-charged new energy vehicle in the corresponding time zone; according to the new energy vehicle charging management method and system, the power supply and demand deviation of different time zones can be reduced, the burden of a charging station and a power grid is reduced, and meanwhile the guiding effect of ordered charging can be improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of charging management, and specifically relates to a new energy vehicle charging management method and system based on artificial intelligence. Background Art

[0002] The charging process of new energy vehicles in the prior art is usually a large-scale disordered charging process, which results in several new grid load peaks in the actual charging process. In addition, for the traditional charging time-sharing pricing process, the time of the charging peak and the charging trough is unchanged, which leads to great limitations in the actual application of charging piles, aggravating the disorder of new energy vehicle charging while also increasing the load on the power grid and charging stations, making it difficult to guide the orderly charging process of new energy vehicle users. Summary of the invention

[0003] In order to solve the above technical problems, the present invention provides a new energy vehicle charging management method and system based on artificial intelligence, which are used to solve the technical problems in the prior art.

[0004] On the one hand, the present invention provides the following technical solution, a new energy vehicle charging management method based on artificial intelligence, comprising: Acquire historical vehicle information and road network information of historical new energy vehicles, and determine the total vehicle charging load based on the historical vehicle information and the road network information; Determine a time load diagram based on the total vehicle charging load and a preset period, divide the preset period into a number of time zones, and determine a final charging price corresponding to each time zone based on the time load diagram; Building a charging optimization management model based on the final charging price; The charging optimization management model is solved by using an improved particle swarm optimization algorithm to obtain the final charging power of each new energy vehicle to be charged in the corresponding time zone; The new energy vehicle to be charged is charged based on the final charging power to realize the charging management process.

[0005] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention first obtains historical vehicle information and driving road network information of historical new energy vehicles, and determines the total charging load of the vehicle based on the historical vehicle information and the driving road network information; then determines the time load diagram based on the total charging load of the vehicle and the preset period, divides the preset period into several time zones, and determines the final charging price corresponding to each time zone based on the time load diagram; then constructs a charging optimization management model based on the final charging price; then uses the improved particle swarm optimization algorithm to solve the charging optimization management model to obtain the final charging power of each new energy vehicle to be charged in the corresponding time zone; finally, the new energy vehicle to be charged is charged based on the final charging power to realize the charging management process. The present invention first determines the total charging load of the vehicle and uses the final charging price corresponding to each time zone according to the total charging load, thereby reducing the deviation of supply and demand electricity in different time zones, reducing the burden on charging stations and power grids, and also improving the guiding effect of orderly charging. Finally, the final charging power is determined, which can further reduce the difference between the charging peak and the charging trough and improve the guiding effect of orderly charging.

[0006] Preferably, the step of determining the total vehicle charging load based on the historical vehicle information and the driving road network information includes: Extracting original vehicle flow data and a set of factors affecting vehicle flow data from the historical vehicle information, and decomposing the original vehicle flow data to obtain a plurality of decomposed components; Performing feature selection and feature integration on the vehicle flow data influencing factor set and the plurality of decomposed components to obtain a selected feature set; Acquire training vehicle flow data, and input the training vehicle flow data into a preset vehicle flow prediction model for prediction to obtain predicted vehicle flow data; Determine the historical driving speed and driving power consumption of new energy vehicles based on the predicted traffic flow data; The vehicle SOC is determined based on the initial power of the historical new energy vehicle and the driving power consumption, and the vehicle probability is calculated based on the vehicle SOC. : ; In the formula, Indicates The SOC of the last trip of a new energy vehicle in history, Indicates The standard deviation of the SOC of historical new energy vehicles, Indicates The expected vehicle SOC of historical new energy vehicles; The historical new energy vehicles with a probability greater than a preset probability are regarded as the main new energy vehicles, and the path planning algorithm is used to determine the driving path of the main new energy vehicles to the target charging station; The path power consumption of the main new energy vehicles on the driving path is determined based on the driving speed of the main new energy vehicles, and the single charging load of the main new energy vehicles is determined based on the path power consumption. The single charging loads of all the main new energy vehicles in the same charging time period are superimposed in turn to obtain the total vehicle charging load.

[0007] Preferably, the step of determining the final charging price corresponding to each time zone based on the time load diagram includes: Identify the maximum total vehicle charging load and the minimum total vehicle charging load in the time load diagram, and use the time zone corresponding to the maximum total vehicle charging load as the peak time zone and the time zone corresponding to the total vehicle charging load as the trough time zone. Total load with minimum vehicle charging Calculate the first standard value With the second standard value : ; ; In the formula, Indicates The total vehicle charging load corresponding to each time zone; Based on the first standard value With the second standard value Calculate similarity matrix : ; In the formula, Represents the similarity matrix Middle Row, No. The elements of the row, is the adjustment coefficient, is the number of time zones; For the similarity matrix Perform several quadratic solutions until , if the matrix Elements in If it is greater than the classification threshold, then the time zone With time zone Belonging to the same category, the time zone belonging to the same category as the peak time zone is taken as the peak time zone, the time zone belonging to the same category as the trough time zone is taken as the trough time zone, and the other time zones are taken as the flat time zones, so as to obtain a set of classified time zones; Performing fitting adjustment on the time load graph based on the set of classified time zones to obtain an adjusted time load graph; A final charging price corresponding to each of the time zones is determined based on the adjusted time load diagram.

[0008] Preferably, the step of determining the final charging price corresponding to each time zone based on the adjusted time load diagram includes: Constructing a price objective function based on the adjustment time load diagram : ; ； ； ； ; In the formula, denote the first, second, third, and fourth function values ​​respectively, , , , Respectively represent The electricity purchase cost price corresponding to each time zone, the charging price to be solved, the lower limit of the price fluctuation range, and the lower limit of the price fluctuation range. , Represents the time load diagram, the adjusted time load diagram, and The load corresponding to each time zone is The time load diagram and the adjusted time load diagram are shown in The difference between the loads corresponding to the time zones, represents the price volatility factor, represents the standard deviation of the charging price to be solved, Indicates The price discount coefficient of each new energy vehicle to be charged is Indicates The ideal charging price for each new energy vehicle to be charged. Indicates the user's sensitivity to charging prices, , Respectively represent New energy vehicles waiting to be charged are Remaining power and ideal power in each time zone, Indicates The response coefficient of the user to the charging power of each new energy vehicle to be charged, They represent the number of time zones and the number of new energy vehicles to be charged respectively; The genetic algorithm is used to solve the objective function The charging price to be solved in A solution is performed to output the final charging price corresponding to each of the time zones.

[0009] Preferably, in the step of constructing a charging optimization management model based on the final charging price, the charging optimization management model is: ; In the formula, , Represent the first and second objective function values ​​respectively, Indicates The load power corresponding to each time zone is: represents the average load power, Indicates New energy vehicles waiting to be charged are Charging power in each time zone, They represent the number of time zones and the number of new energy vehicles to be charged. Indicates the number of charging states, Indicates The final charging price corresponding to each time zone is: Indicates the length of time in a single time zone. Indicates The battery life of a new energy vehicle to be charged, Indicates The maximum total battery capacity of the new energy vehicles to be charged, Represents the linear coefficient between battery life and the number of charge and discharge cycles, Indicates New energy vehicles waiting to be charged are SOC of a time zone.

[0010] Preferably, the step of solving the charging optimization management model by using an improved particle swarm optimization algorithm to obtain the final charging power of each new energy vehicle to be charged in the corresponding time zone includes: Determine a number of particles according to the charging optimization management model, initialize the position and speed of each particle, and calculate the fitness of each particle; Iteratively update the local optimal solution and the global optimal solution according to the fitness of the particles; Calculate and update inertia weight : ; In the formula, Respectively represent the maximum and minimum setting weights, , , They represent the particle fitness of the current iteration, the average particle fitness, and the minimum particle fitness. Respectively represent the current number of iterations and the maximum number of iterations, represents the attenuation constant; Update the inertia weight based on Determine the final charging power of each new energy vehicle to be charged in the corresponding time zone.

[0011] Preferably, the updating inertia weight is based on The steps of determining the final charging power of each new energy vehicle to be charged in the corresponding time zone include: Update the inertia weight based on , the local optimal solution of the current iteration number and the global optimal solution update the position and velocity of the particle: ; ; In the formula, , Respectively represent , The velocity of the particle after iterations, Respectively represent , The position of the particle after iterations, Represent the first and second learning rates respectively, Represent the first and second random numbers respectively, Respectively represent , Local optimal solution and global optimal solution after iterations; Iterate and repeat the process of updating the particle's position and velocity until the stopping condition is met, and output the final global optimal solution; The final global optimal solution is iteratively disturbed and a new solution is accepted by using an annealing algorithm to obtain the final charging power of each new energy vehicle to be charged in the corresponding time zone.

[0012] In a second aspect, the present invention provides the following technical solution, a new energy vehicle charging management system based on artificial intelligence, the system comprising: A load module is used to obtain historical vehicle information and driving road network information of historical new energy vehicles, and determine the total vehicle charging load based on the historical vehicle information and the driving road network information; A price module, used to determine a time load diagram based on the total vehicle charging load and a preset period, divide the preset period into a plurality of time zones, and determine a final charging price corresponding to each of the time zones based on the time load diagram; An optimization module, used for constructing a charging optimization management model based on the final charging price; A solution module, used for solving the charging optimization management model by using an improved particle swarm optimization algorithm to obtain the final charging power of each new energy vehicle to be charged in a corresponding time zone; A management module is used to charge the new energy vehicle to be charged based on the final charging power to realize a charging management process.

[0013] In a third aspect, the present invention provides the following technical solution: a computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor; when the processor executes the computer program, the new energy vehicle charging management method based on artificial intelligence as described above is implemented.

[0014] In a fourth aspect, the present invention provides the following technical solution: a storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the new energy vehicle charging management method based on artificial intelligence as described above is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 A flowchart of a new energy vehicle charging management method based on artificial intelligence provided in Embodiment 1 of the present invention; Figure 2 This is a structural block diagram of a new energy vehicle charging management system based on artificial intelligence provided in Embodiment 2 of the present invention; Figure 3 A schematic diagram of the hardware structure of a computer provided in another embodiment of the present invention.

[0017] The embodiments of the present invention will be further described below with reference to the accompanying drawings. DETAILED DESCRIPTION

[0018] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the embodiments of the present invention, and should not be construed as limiting the present invention.

[0019] In the description of the embodiments of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside" and "outside" etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the embodiments of the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0020] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0021] In the embodiments of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like 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, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the embodiments of the present invention can be understood according to specific circumstances.

[0022] Embodiment 1 In the first embodiment of the present invention, Figure 1 As shown, a new energy vehicle charging management method based on artificial intelligence includes: S1. Obtain historical vehicle information and road network information of historical new energy vehicles, and determine the total vehicle charging load based on the historical vehicle information and the road network information; Specifically, the historical vehicle information here includes the speed distribution and flow changes of traffic flow. The driving road network information specifically determines a preset range with the charging station as the center, and then determines a number of network structures with a topological structure in a grid manner, which includes a number of road network nodes and the connection relationship between the road network nodes.

[0023] Wherein, the step S1 comprises: S11, extracting original vehicle flow data and a set of influencing factors of vehicle flow data from the historical vehicle information, and decomposing the original vehicle flow data to obtain a plurality of decomposition components; Specifically, wavelet decomposition is used here to decompose the original traffic flow data.

[0024] S12, performing feature selection and feature integration on the vehicle flow data influencing factor set and the plurality of decomposed components to obtain a selected feature set; Specifically, the feature information selection algorithm based on mRMR is used here to select the influencing factors and decomposition components that have a great impact on the vehicle flow data.

[0025] S13, obtaining training vehicle flow data, and inputting the training vehicle flow data into a preset vehicle flow prediction model for prediction to obtain predicted vehicle flow data; Specifically, the preset traffic flow prediction model here is the LSTM model.

[0026] S14, determining the historical driving speed and driving power consumption of new energy vehicles based on the predicted vehicle flow data; Specifically, the driving speed here for: ; In the formula, For road segments in the road network The free flow speed, For road segments in the road network of traffic volume, For road segments in the road network The traffic capacity, is the road adjustment factor, which is determined according to different types of road sections; The driving power consumption is determined according to the driving speed, driving time and power consumption per unit distance.

[0027] S15, determining the vehicle SOC based on the initial power of the historical new energy vehicle and the driving power consumption, and calculating the vehicle probability based on the vehicle SOC : ; In the formula, Indicates The SOC of the last trip of a new energy vehicle in history, Indicates The standard deviation of the SOC of historical new energy vehicles, Indicates The expected vehicle SOC of a historical new energy vehicle.

[0028] S16, taking the historical new energy vehicles with a vehicle probability greater than a preset probability as the main new energy vehicles, and using a path planning algorithm to determine the driving path of the main new energy vehicles to the target charging station; Specifically, when the probability of a car is greater than a preset probability, it means that the vehicle is more likely to go to a charging station to perform a charging process. The path planning algorithm here is specifically the Floyd algorithm.

[0029] S17, determining the path power consumption of the main new energy vehicle on the driving path based on the driving speed of the main new energy vehicle, determining the single charging load of the main new energy vehicle based on the path power consumption, and sequentially superimposing the single charging loads of all the main new energy vehicles in the same charging time period to obtain the total vehicle charging load; Specifically, the single charging load can be determined based on the sum of driving power consumption and path power consumption, and then superimposed according to different time periods to obtain the total vehicle charging load.

[0030] S2. Determine a time load diagram based on the total vehicle charging load and a preset period, divide the preset period into a number of time zones, and determine a final charging price corresponding to each time zone based on the time load diagram; Wherein, the step S2 comprises: S21, identifying the maximum total vehicle charging load and the minimum total vehicle charging load in the time load diagram, and using the time zone corresponding to the maximum total vehicle charging load as the peak time zone and the time zone corresponding to the total vehicle charging load as the trough time zone, based on the maximum total vehicle charging load Total load with minimum vehicle charging Calculate the first standard value With the second standard value : ; ; In the formula, Indicates The total vehicle charging load corresponding to each time zone.

[0031] S22, based on the first standard value With the second standard value Calculate similarity matrix : ; In the formula, Represents the similarity matrix Middle Row, No. The elements of the row, is the adjustment coefficient, is the number of time zones.

[0032] S23, the similarity matrix Perform several quadratic solutions until , if the matrix Elements in If it is greater than the classification threshold, then the time zone With time zone Belonging to the same category, the time zone belonging to the same category as the peak time zone is taken as the peak time zone, the time zone belonging to the same category as the trough time zone is taken as the trough time zone, and the other time zones are taken as the flat time zones, so as to obtain a set of classified time zones; Specifically, if the element Greater than the classification threshold, time zone With time zone Belong to the same category, therefore, all time zones are judged with the peak time zone and the trough time zone respectively to see whether they are in the same category, so that several peak time zones and trough time zones can be obtained, and then the remaining time zones are taken as flat time zones to obtain a time zone set.

[0033] S24, performing fitting adjustment on the time load graph based on the classified time zone set to obtain an adjusted time load graph; Specifically, the time load diagram is a continuous curve with certain errors. By determining different types of time zones, the increasing and decreasing relationship in the curve can be adjusted and fitted to obtain an adjusted time load diagram.

[0034] S25. Determine a final charging price corresponding to each of the time zones based on the adjusted time load diagram; Wherein, the step S25 comprises: S251: Constructing a price objective function based on the adjustment time load diagram : ; ； ； ； ; In the formula, denote the first, second, third, and fourth function values ​​respectively, , , , Respectively represent The electricity purchase cost price corresponding to each time zone, the charging price to be solved, the lower limit of the price fluctuation range, and the lower limit of the price fluctuation range. , Respectively represent the time load diagram, the adjustment time load diagram The load corresponding to each time zone is The time load diagram and the adjusted time load diagram are shown in The difference between the loads corresponding to the time zones, represents the price volatility factor, represents the standard deviation of the charging price to be solved, Indicates The price discount coefficient of each new energy vehicle to be charged is Indicates The ideal charging price for each new energy vehicle to be charged. Indicates the user's sensitivity to charging prices, , Respectively represent New energy vehicles waiting to be charged are Remaining power and ideal power in each time zone, Indicates The response coefficient of the user to the charging power of each new energy vehicle to be charged, They represent the number of time zones and the number of new energy vehicles to be charged respectively; Specifically, for the price objective function For charging stations, it fully considers the impact of different prices on users, the cost of purchasing electricity from the power grid, the deviation between supply and demand, and the benefits of users and charging stations.

[0035] S252, using genetic algorithm to solve the objective function The charging price to be solved in Solving to output the final charging price corresponding to each of the time zones; Specifically, the genetic algorithm is a commonly used algorithm in the prior art, and thus will not be described in detail here.

[0036] S3. Constructing a charging optimization management model based on the final charging price; Wherein, the charging optimization management model is: ; In the formula, , Represent the first and second objective function values ​​respectively, Indicates The load power corresponding to each time zone is: represents the average load power, Indicates New energy vehicles waiting to be charged are Charging power in each time zone, They represent the number of time zones and the number of new energy vehicles to be charged. Indicates the number of charging states, Indicates The final charging price corresponding to each time zone is: Indicates the length of time in a single time zone. Indicates The battery life of a new energy vehicle to be charged, Indicates The maximum total battery capacity of the new energy vehicles to be charged, Represents the linear coefficient between battery life and the number of charge and discharge cycles, Indicates New energy vehicles waiting to be charged are SOC of each time zone; Specifically, the goal of the charging optimization management model is to minimize the mean square error of the grid load and minimize the user's charging cost, and consider the impact of charging power on battery life and vehicle efficiency.

[0037] S4. Using an improved particle swarm optimization algorithm to solve the charging optimization management model to obtain the final charging power of each new energy vehicle to be charged in the corresponding time zone; Wherein, the step S4 comprises: S41. Determine a number of particles according to the charging optimization management model, initialize the position and speed of each particle, and calculate the fitness of each particle.

[0038] S42. Iteratively update the local optimal solution and the global optimal solution according to the fitness of the particles.

[0039] S43, calculate and update inertia weight : ; In the formula, Respectively represent the maximum and minimum setting weights, , , They represent the particle fitness of the current iteration, the average particle fitness, and the minimum particle fitness. Respectively represent the current number of iterations and the maximum number of iterations, represents the attenuation constant; Specifically, the above steps are the steps of the particle swarm algorithm in the prior art, but the difference is that in the present application, the inertia weight is adjusted accordingly to achieve an adaptive balance between global search and local search, thereby effectively shortening the number of iterations required for problem solving, thereby improving the calculation speed and convergence speed, and at the same time solving the problem of local optimization of particles. In actual situations, the particles may already be the optimal part of the current local area at the initial iteration. Since the initial value of the inertia weight is the largest and continuously decreases linearly, the local search is continuously strengthened and eventually the particles fall into the local optimum. Therefore, the present invention fully considers the influence of fitness on optimization, and can expand the scope of outward search of particles, thereby avoiding falling into the situation of local optimization.

[0040] S44, based on the updated inertia weight Determine the final charging power of each new energy vehicle to be charged in the corresponding time zone; Wherein, the step S44 comprises: S441, based on the updated inertia weight , the local optimal solution of the current iteration number and the global optimal solution update the position and velocity of the particle: ; ; In the formula, , Respectively represent , The velocity of the particle after iterations, Respectively represent , The position of the particle after iterations, Represent the first and second learning rates respectively, Represent the first and second random numbers respectively, Respectively represent , The local optimal solution and the global optimal solution after iterations.

[0041] S442, iteratively repeat the updating process of the particle position and velocity until the stopping condition is met, and output the final global optimal solution; Specifically, the above process is a common usage of the particle swarm algorithm, but the inertia weights used are different.

[0042] S443, using an annealing algorithm to iteratively perturb the final global optimal solution and accept a new solution to obtain a final charging power of each new energy vehicle to be charged in a corresponding time zone; Specifically, the annealing algorithm, namely the SA algorithm, is a commonly used algorithm in the prior art, so it will not be described in detail here. The efficiency and accuracy of the solution can be enhanced by the annealing algorithm, and the solution sought here is to find the optimal .

[0043] S5. Charging the new energy vehicle to be charged based on the final charging power to implement a charging management process; Specifically, the corresponding final charging power is used to charge the new energy vehicles to realize the charging management process, reduce the deviation of power supply and demand in different time zones, reduce the burden on charging stations and power grids, and also improve the guiding effect of orderly charging.

[0044] The artificial intelligence-based new energy vehicle charging management method provided in the first embodiment of the present invention first obtains historical vehicle information and driving road network information of historical new energy vehicles, and determines the total vehicle charging load based on the historical vehicle information and the driving road network information; then determines the time load diagram based on the total vehicle charging load and the preset period, divides the preset period into several time zones, and determines the final charging price corresponding to each time zone based on the time load diagram; then builds a charging optimization management model based on the final charging price; then uses the improved particle swarm optimization algorithm to solve the charging optimization management model to obtain the final charging power of each new energy vehicle to be charged in the corresponding time zone; finally, based on the final charging power, the new energy vehicle to be charged is charged to realize the charging management process. The present invention first determines the total vehicle charging load and the final charging price corresponding to each time zone according to the total vehicle charging load, thereby reducing the deviation of supply and demand electricity in different time zones, reducing the burden on charging stations and power grids, and also improving the guiding effect of orderly charging. Finally, the final charging power is determined, which can further reduce the difference between the charging peak and the charging valley and improve the guiding effect of orderly charging.

[0045] Embodiment 2 like Figure 2 As shown, in the second embodiment of the present invention, a new energy vehicle charging management system based on artificial intelligence is provided, and the system includes: Load module 1, used to obtain historical vehicle information and driving road network information of historical new energy vehicles, and determine the total vehicle charging load based on the historical vehicle information and the driving road network information; A price module 2 is used to determine a time load diagram based on the total vehicle charging load and a preset period, divide the preset period into a plurality of time zones, and determine a final charging price corresponding to each time zone based on the time load diagram; An optimization module 3, configured to construct a charging optimization management model based on the final charging price; A solution module 4 is used to solve the charging optimization management model by using an improved particle swarm optimization algorithm to obtain the final charging power of each new energy vehicle to be charged in the corresponding time zone; A management module 5, configured to charge the new energy vehicle to be charged based on the final charging power to implement a charging management process; The load module 1 comprises: A decomposition submodule, used to extract original vehicle flow data and a set of influencing factors of vehicle flow data from the historical vehicle information, and to decompose the original vehicle flow data to obtain a plurality of decomposition components; An integration submodule, used for performing feature selection and feature integration on the vehicle flow data influencing factor set and a plurality of the decomposed components to obtain a selected feature set; The prediction submodule is used to obtain training vehicle flow data, input the training vehicle flow data into a preset vehicle flow prediction model for prediction, and obtain predicted vehicle flow data; A power consumption submodule, used to determine the historical driving speed and driving power consumption of new energy vehicles based on the predicted vehicle flow data; The probability submodule is used to determine the vehicle SOC based on the initial power and driving power consumption of the historical new energy vehicle, and calculate the vehicle probability based on the vehicle SOC : ; In the formula, Indicates The SOC of the last trip of a new energy vehicle in history, Indicates The standard deviation of the SOC of historical new energy vehicles, Indicates The expected vehicle SOC of historical new energy vehicles; A path submodule is used to take the historical new energy vehicles with a vehicle probability greater than a preset probability as the main new energy vehicles, and use a path planning algorithm to determine the driving path of the main new energy vehicles to the target charging station; The superposition submodule is used to determine the path power consumption of the main new energy vehicles on the driving path based on the driving speed of the main new energy vehicles, determine the single charging load of the main new energy vehicles based on the path power consumption, and superimpose the single charging loads of all the main new energy vehicles in the same charging time period in turn to obtain the total vehicle charging load.

[0046] The price module 2 includes: The identification submodule is used to identify the maximum total vehicle charging load and the minimum total vehicle charging load in the time load diagram, and use the time zone corresponding to the maximum total vehicle charging load as the peak time zone and the time zone corresponding to the total vehicle charging load as the trough time zone. Total load with minimum vehicle charging Calculate the first standard value With the second standard value : ; ; In the formula, Indicates The total vehicle charging load corresponding to each time zone; Matrix submodule for calculating the value of the first standard With the second standard value Calculate similarity matrix : ; In the formula, Represents the similarity matrix Middle Row, No. The elements of the row, is the adjustment coefficient, is the number of time zones; The classification submodule is used to classify the similarity matrix Perform several quadratic solutions until , if the matrix Elements in If it is greater than the classification threshold, then the time zone With time zone Belonging to the same category, the time zone belonging to the same category as the peak time zone is taken as the peak time zone, the time zone belonging to the same category as the trough time zone is taken as the trough time zone, and the other time zones are taken as the flat time zones, so as to obtain a set of classified time zones; A fitting submodule, used for fitting and adjusting the time load diagram based on the set of classified time zones to obtain an adjusted time load diagram; The price output submodule is used to determine the final charging price corresponding to each of the time zones based on the adjusted time load diagram.

[0047] The price output submodule includes: An objective function unit is used to construct a price objective function based on the adjustment time load diagram : ; ； ； ； ; In the formula, denote the first, second, third, and fourth function values ​​respectively, , , , Respectively represent The electricity purchase cost price corresponding to each time zone, the charging price to be solved, the lower limit of the price fluctuation range, and the lower limit of the price fluctuation range. , Respectively represent the time load diagram, the adjustment time load diagram The load corresponding to each time zone is The time load diagram and the adjusted time load diagram are shown in The difference between the loads corresponding to the time zones, represents the price volatility factor, represents the standard deviation of the charging price to be solved, Indicates The price discount coefficient of each new energy vehicle to be charged is Indicates The ideal charging price for each new energy vehicle to be charged. Indicates the user's sensitivity to charging prices, , Respectively represent New energy vehicles waiting to be charged are Remaining power and ideal power in each time zone, Indicates The response coefficient of the user to the charging power of each new energy vehicle to be charged, They represent the number of time zones and the number of new energy vehicles to be charged respectively; Function solving unit, used to solve the objective function using genetic algorithm The charging price to be solved in A solution is performed to output the final charging price corresponding to each of the time zones.

[0048] Wherein, the charging optimization management model is: ; In the formula, , Represent the first and second objective function values ​​respectively, Indicates The load power corresponding to each time zone is: represents the average load power, Indicates New energy vehicles waiting to be charged are Charging power in each time zone, They represent the number of time zones and the number of new energy vehicles to be charged. Indicates the number of charging states, Indicates The final charging price corresponding to each time zone is: Indicates the length of time in a single time zone. Indicates The battery life of a new energy vehicle to be charged, Indicates The maximum total battery capacity of the new energy vehicles to be charged, Represents the linear coefficient between battery life and the number of charge and discharge cycles, Indicates New energy vehicles waiting to be charged are SOC of a time zone.

[0049] The solution module 4 comprises: A fitness submodule, used to determine a number of particles according to the charging optimization management model, initialize the position and speed of each particle, and calculate the fitness of each particle; The update submodule is used to iteratively update the local optimal solution and the global optimal solution according to the fitness of the particles; Weight submodule, used to calculate and update inertia weight : ; In the formula, Respectively represent the maximum and minimum setting weights, , , They represent the particle fitness of the current iteration, the average particle fitness, and the minimum particle fitness. Respectively represent the current number of iterations and the maximum number of iterations, represents the attenuation constant; A power output submodule is used to update the inertia weight based on the Determine the final charging power of each new energy vehicle to be charged in the corresponding time zone.

[0050] The power output submodule comprises: A position velocity updating unit for updating the inertia weight based on the , the local optimal solution of the current iteration number and the global optimal solution update the position and velocity of the particle: ; ; In the formula, , Respectively represent , The velocity of the particle after iterations, Respectively represent , The position of the particle after iterations, Represent the first and second learning rates respectively, Represent the first and second random numbers respectively, Respectively represent , Local optimal solution and global optimal solution after iterations; The output unit is used to iteratively repeat the updating process of the particle's position and velocity until the stopping condition is met and output the final global optimal solution; The power output unit is used to iteratively perturb the final global optimal solution and accept new solutions using an annealing algorithm to obtain the final charging power of each new energy vehicle to be charged in the corresponding time zone.

[0051] In some other embodiments of the present invention, the embodiments of the present invention provide the following technical solutions: a computer, comprising a memory 102, a processor 101, and a computer program stored in the memory 102 and executable on the processor 101; when the processor 101 executes the computer program, the new energy vehicle charging management method based on artificial intelligence as described above is implemented.

[0052] Specifically, the processor 101 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiment of the present invention.

[0053] Among them, the memory 102 may include a large-capacity memory for data or instructions. By way of example and not limitation, the memory 102 may include a hard disk drive (HDD), a floppy disk drive, a solid state drive (SSD), a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 102 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 102 may be inside or outside the data processing device. In a specific embodiment, the memory 102 is a non-volatile memory. In a specific embodiment, the memory 102 includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM) or a flash memory (FLASH), or a combination of two or more of these. Under appropriate circumstances, the RAM can be a static random access memory (SRAM) or a dynamic random access memory (DRAM), wherein the DRAM can be a fast page mode dynamic random access memory (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0054] The memory 102 may be used to store or cache various data files that need to be processed and / or used for communication, as well as possible computer program instructions executed by the processor 101 .

[0055] The processor 101 implements the above-mentioned artificial intelligence-based new energy vehicle charging management method by reading and executing computer program instructions stored in the memory 102.

[0056] In some embodiments, the computer may further include a communication interface 103 and a bus 100. Figure 3 As shown, the processor 101, the memory 102, and the communication interface 103 are connected via a bus 100 and communicate with each other.

[0057] The communication interface 103 is used to implement communication between the modules, devices, units and / or equipment in the embodiment of the present invention. The communication interface 103 can also implement data communication with other components such as: external devices, image / data acquisition equipment, databases, external storage, and image / data processing workstations.

[0058] The bus 100 includes hardware, software or both, and couples the components of the computer device to each other. The bus 100 includes but is not limited to at least one of the following: a data bus, an address bus, a control bus, an expansion bus, and a local bus. By way of example and not limitation, bus 100 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, bus 100 may include one or more buses. Although embodiments of the present invention describe and illustrate a particular bus, the present invention contemplates any suitable bus or interconnect.

[0059] The computer can execute the new energy vehicle charging management method based on artificial intelligence of the present invention based on the acquisition of the new energy vehicle charging management system based on artificial intelligence, thereby realizing the new energy vehicle charging management based on artificial intelligence.

[0060] In some further embodiments of the present invention, in combination with the above-mentioned artificial intelligence-based new energy vehicle charging management method, the embodiments of the present invention provide the following technical solutions: a storage medium having a computer program stored thereon, and the computer program, when executed by a processor, implements the above-mentioned artificial intelligence-based new energy vehicle charging management method.

[0061] Those skilled in the art will appreciate that the logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For purposes of this specification, "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0062] More specific examples of readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0063] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0064] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0065] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A new energy vehicle charging management method based on artificial intelligence, characterized in that: include: Acquire historical vehicle information and road network information of historical new energy vehicles, and determine the total vehicle charging load based on the historical vehicle information and the road network information; Determine a time load diagram based on the total vehicle charging load and a preset period, divide the preset period into a number of time zones, and determine a final charging price corresponding to each time zone based on the time load diagram; Building a charging optimization management model based on the final charging price; The charging optimization management model is solved by using an improved particle swarm optimization algorithm to obtain the final charging power of each new energy vehicle to be charged in the corresponding time zone; The new energy vehicle to be charged is charged based on the final charging power to realize the charging management process.

2. The artificial intelligence-based new energy vehicle charging management method according to claim 1 is characterized in that: The step of determining the total vehicle charging load based on the historical vehicle information and the driving road network information comprises: Extracting original vehicle flow data and a set of factors affecting vehicle flow data from the historical vehicle information, and decomposing the original vehicle flow data to obtain a plurality of decomposed components; Performing feature selection and feature integration on the vehicle flow data influencing factor set and the plurality of decomposed components to obtain a selected feature set; Acquire training vehicle flow data, and input the training vehicle flow data into a preset vehicle flow prediction model for prediction to obtain predicted vehicle flow data; Determine the historical driving speed and driving power consumption of new energy vehicles based on the predicted traffic flow data; The vehicle SOC is determined based on the initial power of the historical new energy vehicle and the driving power consumption, and the vehicle probability is calculated based on the vehicle SOC. : ； In the formula, Indicates The SOC of the last trip of a new energy vehicle in history, Indicates The standard deviation of the SOC of historical new energy vehicles, Indicates The expected vehicle SOC of historical new energy vehicles; The historical new energy vehicles with a probability greater than a preset probability are regarded as the main new energy vehicles, and the path planning algorithm is used to determine the driving path of the main new energy vehicles to the target charging station; The path power consumption of the main new energy vehicles on the driving path is determined based on the driving speed of the main new energy vehicles, and the single charging load of the main new energy vehicles is determined based on the path power consumption. The single charging loads of all the main new energy vehicles in the same charging time period are superimposed in turn to obtain the total vehicle charging load.

3. The new energy vehicle charging management method based on artificial intelligence according to claim 1 is characterized in that: The step of determining the final charging price corresponding to each time zone based on the time load diagram comprises: Identify the maximum total vehicle charging load and the minimum total vehicle charging load in the time load diagram, and use the time zone corresponding to the maximum total vehicle charging load as the peak time zone and the time zone corresponding to the total vehicle charging load as the trough time zone. Total load with minimum vehicle charging Calculate the first standard value With the second standard value : ； ； In the formula, Indicates The total vehicle charging load corresponding to each time zone; Based on the first standard value With the second standard value Calculate similarity matrix : ； In the formula, Represents the similarity matrix Middle Row, No. The elements of the row, is the adjustment coefficient, is the number of time zones; For the similarity matrix Perform several quadratic solutions until , if the matrix Elements in If it is greater than the classification threshold, then the time zone With time zone Belonging to the same category, the time zone belonging to the same category as the peak time zone is taken as the peak time zone, the time zone belonging to the same category as the trough time zone is taken as the trough time zone, and the other time zones are taken as the flat time zones, so as to obtain a set of classified time zones; Performing fitting adjustment on the time load graph based on the set of classified time zones to obtain an adjusted time load graph; A final charging price corresponding to each of the time zones is determined based on the adjusted time load diagram.

4. The artificial intelligence-based new energy vehicle charging management method according to claim 3 is characterized in that: The step of determining the final charging price corresponding to each time zone based on the adjusted time load diagram comprises: Constructing a price objective function based on the adjustment time load diagram : ； ； ； ； ； In the formula, denote the first, second, third, and fourth function values ​​respectively, , , , Respectively represent The electricity purchase cost price corresponding to each time zone, the charging price to be solved, the lower limit of the price fluctuation range, and the lower limit of the price fluctuation range. , Respectively represent the time load diagram, the adjustment time load diagram The load corresponding to each time zone is The time load diagram and the adjusted time load diagram are shown in The difference between the loads corresponding to the time zones, represents the price volatility factor, represents the standard deviation of the charging price to be solved, Indicates The price discount coefficient of each new energy vehicle to be charged is Indicates The ideal charging price for each new energy vehicle to be charged. Indicates the user's sensitivity to charging prices, , Respectively represent New energy vehicles waiting to be charged are Remaining power and ideal power in each time zone, Indicates The response coefficient of the user to the charging power of each new energy vehicle to be charged, They represent the number of time zones and the number of new energy vehicles to be charged respectively; The genetic algorithm is used to solve the objective function The charging price to be solved in A solution is performed to output the final charging price corresponding to each of the time zones.

5. The new energy vehicle charging management method based on artificial intelligence according to claim 1 is characterized in that: In the step of constructing a charging optimization management model based on the final charging price, the charging optimization management model is: ； In the formula, , Represent the first and second objective function values ​​respectively, Indicates The load power corresponding to each time zone is: represents the average load power, Indicates New energy vehicles waiting to be charged are Charging power in each time zone, They represent the number of time zones and the number of new energy vehicles to be charged. Indicates the number of charging states, Indicates The final charging price corresponding to each time zone is: Indicates the length of time in a single time zone. Indicates The battery life of a new energy vehicle to be charged, Indicates The maximum total battery capacity of the new energy vehicles to be charged, Represents the linear coefficient between battery life and the number of charge and discharge cycles, Indicates New energy vehicles waiting to be charged are SOC of a time zone.

6. The artificial intelligence-based new energy vehicle charging management method according to claim 1 is characterized in that: The step of using the improved particle swarm optimization algorithm to solve the charging optimization management model to obtain the final charging power of each new energy vehicle to be charged in the corresponding time zone includes: Determine a number of particles according to the charging optimization management model, initialize the position and speed of each particle, and calculate the fitness of each particle; Iteratively update the local optimal solution and the global optimal solution according to the fitness of the particles; Calculate and update inertia weight : ； In the formula, Respectively represent the maximum and minimum setting weights, , , They represent the particle fitness of the current iteration, the average particle fitness, and the minimum particle fitness. Respectively represent the current number of iterations and the maximum number of iterations, represents the attenuation constant; Update the inertia weight based on Determine the final charging power of each new energy vehicle to be charged in the corresponding time zone.

7. The artificial intelligence-based new energy vehicle charging management method according to claim 6 is characterized in that: The updating of the inertia weight based on The steps of determining the final charging power of each new energy vehicle to be charged in the corresponding time zone include: Update the inertia weight based on , the local optimal solution of the current iteration number and the global optimal solution update the position and velocity of the particle: ； ； In the formula, , Respectively represent , The velocity of the particle after iterations, Respectively represent , The position of the particle after iterations, Represent the first and second learning rates respectively, Represent the first and second random numbers respectively, Respectively represent , Local optimal solution and global optimal solution after iterations; Iterate and repeat the process of updating the particle's position and velocity until the stopping condition is met, and output the final global optimal solution; The final global optimal solution is iteratively disturbed and a new solution is accepted by using an annealing algorithm to obtain the final charging power of each new energy vehicle to be charged in the corresponding time zone.

8. A new energy vehicle charging management system based on artificial intelligence, characterized in that: The system comprises: A load module is used to obtain historical vehicle information and driving road network information of historical new energy vehicles, and determine the total vehicle charging load based on the historical vehicle information and the driving road network information; A price module, used to determine a time load diagram based on the total vehicle charging load and a preset period, divide the preset period into a plurality of time zones, and determine a final charging price corresponding to each of the time zones based on the time load diagram; An optimization module, used for constructing a charging optimization management model based on the final charging price; A solution module, used for solving the charging optimization management model by using an improved particle swarm optimization algorithm to obtain the final charging power of each new energy vehicle to be charged in a corresponding time zone; A management module is used to charge the new energy vehicle to be charged based on the final charging power to realize a charging management process.

9. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the new energy vehicle charging management method based on artificial intelligence as described in any one of claims 1 to 7 is implemented.

10. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the artificial intelligence-based new energy vehicle charging management method as described in any one of claims 1 to 7 is implemented.

Images