Intelligent dispatching system for new energy charging piles based on big data

Abstract

The present invention relates to the field of intelligent scheduling technology, specifically to an intelligent scheduling system for new energy charging piles based on big data, comprising: an information acquisition module, used to obtain the scheduling cycle of the charging piles, and collect the charging amount, power consumption and charging time of the charging piles in each scheduling cycle; a scheduling identification module, used to identify the scheduling target and scheduling pricing in each scheduling cycle, and check the power consumption distribution in each scheduling cycle to obtain a consumption evaluation factor; a scheduling adjustment module, used to obtain multiple incentive clusters corresponding to the scheduling target according to the scheduling target and scheduling pricing in each scheduling cycle; each incentive cluster contains the scheduling target, scheduling pricing and incentive effect; the multiple incentive clusters are clustered according to the scheduling pricing to obtain the incentive factor under each scheduling cycle, and the target set of charging pile scheduling is determined based on the obtained incentive factor; the utilization rate and efficiency of the charging piles are improved, and the intelligent scheduling of the charging piles is realized.

Description

Technical Field

[0001] The present invention relates to the field of intelligent scheduling technology, and in particular to a new energy charging pile intelligent scheduling system based on big data. Background Art

[0002] At present, with the popularization of new energy vehicles, the demand for charging piles has increased dramatically. In order to meet the demand for large-scale charging piles, the charging pile management system needs to realize effective management and monitoring of charging piles, including status monitoring, fault diagnosis, real-time scheduling and other functions of charging piles to ensure the normal operation and service quality of the charging pile network.

[0003] Medium and large charging stations are often composed of multiple charging piles. Charging pile self-organizing network refers to the establishment of a communication network between each charging pile so that each charging pile can realize data exchange and collaborative work with each other. During the operation of the entire charging station, all charging piles complete real-time interaction of node load, equipment status and other information through the self-organizing network, so that the scheduling server can intelligently schedule each charging pile in the charging station based on this real-time information.

[0004] For example, Chinese patent publication number CN117077872A discloses an intelligent scheduling and management system for new energy electric vehicle charging piles, which includes an information collection module, an information collation module, a data analysis module, a data comparison module and an execution module. Through the information collection, collation module, data analysis module and data comparison module, the system can record and feedback the real-time data of the charging piles, so that managers can better understand the status and needs of the charging piles to optimize the use of the charging piles, improve the efficiency of the charging piles, and reduce the working pressure of the charging piles. The system can intelligently adjust the use of the charging piles to ensure that the charging piles are reasonably utilized during peak and off-peak periods. The system can dynamically dispatch the charging piles according to the actual power pressure conditions to ensure the normal operation of the charging station and the charging needs of the vehicles.

[0005] However, when scheduling charging piles, the existing technology does not consider how to adjust the scheduling according to the changes in the current goals when the scheduling content and goals change. As a result, the charging piles are prone to ignore the priorities between different scheduling goals in the scenario of multi-target scheduling, resulting in a chaotic scheduling order and a reduced user experience. Summary of the Invention

[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is: an intelligent scheduling system for new energy charging piles based on big data, including: an information collection module for obtaining the scheduling cycle of the charging piles, and collecting the charging amount, power consumption and charging time of the charging piles in each scheduling cycle.

[0007] The scheduling identification module is used to identify the scheduling target and scheduling pricing in each scheduling cycle, and to check the power consumption distribution in each scheduling cycle to obtain the consumption assessment factor.

[0008] The scheduling adjustment module is used to obtain multiple incentive clusters corresponding to the scheduling targets and scheduling pricing within each scheduling cycle; each incentive cluster contains the scheduling target, scheduling pricing and incentive effect; multiple incentive clusters are clustered according to the scheduling pricing to obtain the incentive factors under each scheduling cycle, and based on the obtained incentive factors, the target set of charging pile scheduling is determined.

[0009] The scheduling parallel module is used to determine the scheduling order coefficient of the charging piles in multi-objective scheduling according to the target set of the charging pile scheduling, and obtain the evaluation result of the scheduling order.

[0010] The scheduling evaluation module is used to evaluate the current scheduling mode according to the output results of the scheduling identification module, the scheduling adjustment module and the scheduling parallel module, and obtain a comprehensive evaluation result of the charging pile scheduling.

[0011] The beneficial effects of this invention are as follows: 1. Through an intelligent scheduling system, this invention can monitor the operating status and power consumption distribution of charging piles in real time, dynamically adjust charging power and charging time, and improve charging efficiency. The system can also be flexibly adjusted according to user needs, ensuring the rational allocation of charging resources and reducing user waiting time.

[0012] 2. The present invention can identify peak and off-peak charging periods, and through an orderly charging management strategy, achieve peak shaving and valley filling, thereby optimizing energy utilization; charging when the grid load is low and reducing charging when the load is high can reduce charging costs and improve the economic benefits of charging stations; it also reduces the waiting time of users and improves the user experience.

[0013] 3. The present invention reduces users' charging costs and promotes their willingness to charge through dynamic pricing strategies and incentive mechanisms; and effectively balances the grid load and reduces pressure during peak periods by adjusting scheduling strategies in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The present invention will be further described below with reference to the accompanying drawings and examples.

[0015] Figure 1 This is the system framework diagram of the new energy charging pile intelligent scheduling system based on big data.

[0016] Figure 2 This is a system diagram of the intelligent scheduling system for new energy charging piles based on big data.

[0017] Figure 3This is a flow chart of the scheduling target in the scheduling identification module of the new energy charging pile intelligent scheduling system based on big data. DETAILED DESCRIPTION

[0018] The following embodiments of the present invention are described in detail. The embodiments described below are exemplary and are only used to explain the present invention, and are not to be construed as limiting the present invention. Where specific techniques or conditions are not specified in the embodiments, the techniques or conditions described in the literature in the art or in the product specifications shall be followed.

[0019] See Figure 1 、 Figure 2 The intelligent dispatching system of new energy charging piles based on big data includes: an information collection module, a dispatching identification module, a dispatching adjustment module, a dispatching parallel module, and a dispatching evaluation module; the information collection module inputs data into the dispatching identification module, the output end of the dispatching identification module is connected to the dispatching adjustment module and the dispatching evaluation module respectively, the output end of the dispatching adjustment module is connected to the dispatching parallel module and the dispatching evaluation module respectively, and the output end of the dispatching parallel module is connected to the dispatching evaluation module. After receiving the outputs of the dispatching identification module, the dispatching adjustment module, and the dispatching parallel module, the dispatching evaluation module completes the evaluation of the dispatch.

[0020] The information collection module is used to obtain the scheduling cycle of the charging pile and collect the charging amount, power consumption and charging time of the charging pile in each scheduling cycle.

[0021] The scheduling identification module is used to identify the scheduling target and scheduling pricing in each scheduling cycle, and to check the power consumption distribution in each scheduling cycle to obtain the consumption assessment factor.

[0022] The scheduling adjustment module is used to obtain multiple incentive clusters corresponding to the scheduling targets and scheduling pricing within each scheduling cycle; each incentive cluster contains the scheduling target, scheduling pricing and incentive effect; multiple incentive clusters are clustered according to the scheduling pricing to obtain the incentive factors under each scheduling cycle, and based on the obtained incentive factors, the target set of charging pile scheduling is determined.

[0023] The scheduling parallel module is used to determine the scheduling order coefficient of the charging piles in multi-objective scheduling according to the target set of the charging pile scheduling, and obtain the evaluation result of the scheduling order.

[0024] The scheduling evaluation module is used to evaluate the current scheduling mode according to the output results of the scheduling identification module, the scheduling adjustment module and the scheduling parallel module, and obtain a comprehensive evaluation result of the charging pile scheduling.

[0025] The present invention identifies the specific circumstances of each scheduling of the charging pile, determines whether losses are generated during each scheduling, and clusters the corresponding targets during scheduling to obtain the power used by the corresponding targets at this time, so as to judge whether the scheduling is reasonable; at the same time, it will jointly identify multiple scheduling targets and determine the processing order when multi-target scheduling occurs, ensuring that the charging pile can be adjusted in real time to meet user needs.

[0026] The scheduling cycle is obtained according to the time interval of each intelligent scheduling of the charging pile. For example, the use of the charging pile is arranged every half hour, one hour or one day. At this time, the scheduling cycle is to obtain data within a time period of corresponding size, and determine how to schedule at this time based on the situation of this part of the data.

[0027] The charging capacity of the charging pile is to determine the total cumulative consumption of the charging pile during the scheduling period, and the obtained power consumption is the instantaneous power consumption at the acquisition moment or the corresponding time, so that the currently scheduled power can be accurately identified.

[0028] When identifying the distribution of power consumption, the scheduling target and scheduling pricing within the scheduling cycle will be determined first. The scheduling target refers to the need to schedule user vehicles and the current tasks that need to be scheduled, such as maximizing the utilization rate of charging piles, reducing user waiting time, reducing charging costs, balancing the grid load, reducing queuing time, etc.; the scheduling target at this time needs to clarify the content that needs to be processed at this time; the scheduling pricing represents the current grid electricity price in each scheduling cycle and the charging price that the scheduling strategy needs to determine during scheduling, so that the charging cost can be adjusted in combination with the scheduling target, and the charging standard can be adjusted according to the power supply and demand situation, thereby improving the charging experience for different users; the final power consumption distribution is to understand the load situation of the power grid at different times, so as to adjust the scheduling strategy of the charging pile at this time.

[0029] The method for obtaining the scheduling target and scheduling pricing of the scheduling identification module at this time is shown below.

[0030] like Figure 3 As shown, the method for obtaining the scheduling target is: A1, obtaining the usage data within the scheduling period, the usage data including the number of charging times, charging amount, and charging time of the charging pile.

[0031] A2, based on usage data within the scheduling cycle, analyzes user charging habits and identifies peak and off-peak periods for charging pile usage.

[0032] The usage data obtained at this time will calculate the average number of charging times, charging power and charging time within the scheduling cycle. This average value refers to the average value of adjacent scheduling cycles. The usage data will be input into the array according to the number and position of each charging pile, and a charging curve corresponding to the usage data will be generated according to the order of time points. The charging area will be compared with the data of the current scheduling cycle to identify the charging habits preferred by the user at this time, and according to the peak and valley time periods of actual use of the charging pile at this time, the preliminary scheduling goals that need to meet the user habits at this time will be selected, and these scheduling goals will be sorted to find the scheduling goals with different priorities for achieving the effect at this time. This scheduling goal can be data for only one goal, or it can be data containing multiple goals. For example, the scheduling goal can only be to maximize the utilization rate of the charging pile; the scheduling goal can also be to maximize the utilization rate of the charging pile, reduce user waiting time, and other goals in order of priority, thereby completing the scheduling goal output at this time.

[0033] A3 calculates the average number of charging times, charging amount, and charging time for each user; categorizes users based on the average number of charging times, charging amount, and charging time, and assigns behavior labels to each user, such as morning peak charging and evening peak charging.

[0034] A4 calculates the user's habit coefficient for charging times, charging amount, and charging time under each behavior tag, and uses the habit coefficient, charging times, charging amount, and charging time as comprehensive search conditions to retrieve the corresponding preliminary scheduling target from the database.

[0035] The habit coefficient is expressed as normalizing the average values of the number of charging times, the charging amount, and the charging time, and then calculating the weighted sum of the average values of the normalized number of charging times, the charging amount, and the charging time to obtain the habit coefficient at this time.

[0036] Since the average value of the above-mentioned charging time is different from the number of charges and the charging amount, it cannot be directly quantified into a specific value. The charging time at this time will be expressed as the value of the length of the time period from the start of charging to the completion of charging. At the same time, when conducting a comprehensive search, it is also necessary to use the peak and valley periods of charging pile use as initial conditions to find the corresponding adjustment targets when charging is frequent and charging is infrequent. At this time, during the comprehensive search, it is necessary to compare the current number of charges, charging amount, charging time, and habit coefficient values with the values in the database to obtain the confidence levels in turn. At this time, the confidence levels are required to be 0.6, 0.7, 0.5, and 0.7 according to the number of charges, charging amount, charging time, and habit coefficient settings, respectively. When the confidence level meets the requirements, the preliminary scheduling targets for the corresponding data at this time will be output. The preliminary scheduling targets output at this time are presented in the form of a list, containing multiple preliminary scheduling targets, and the preliminary scheduling targets will be set in the database in advance to facilitate subsequent selection and retrieval.

[0037] A5, prioritize the sub-elements in the preliminary scheduling target, obtain the importance ranking of different preliminary scheduling targets, and output it as the scheduling target in the scheduling identification module.

[0038] At this time, the sub-elements in the preliminary scheduling target can be sorted according to different preliminary scheduling targets. For example, when maximizing the utilization rate of charging piles, reducing user waiting time, reducing charging costs, balancing the grid load, and reducing queuing time mentioned above, the sub-elements in the preliminary scheduling target can be expressed as shown below.

[0039] Maximize the utilization rate of charging piles: utilization rate, average usage time, and idle time; utilization rate: the proportion of the usage time of the charging pile in a certain time period to the total time; average usage time: the average usage time of each charging pile in a certain period of time; idle time: the total time that the charging pile is not in use.

[0040] Reduce user waiting time: average waiting time, maximum waiting time, and waiting queue length; average waiting time: the average waiting time from the time a user arrives at the charging station to the start of charging; maximum waiting time: the longest time a user waits for charging; waiting queue length: the number of users waiting in line for charging.

[0041] Reduce charging costs: average charging cost, total charging cost, and electricity price fluctuations; average charging cost: the average cost of charging for each user; total charging cost: the total charging cost of all users in a certain time period; electricity price fluctuations: the change in electricity prices in different time periods.

[0042] Balanced grid load: grid load distribution, peak load, average load; grid load distribution: the load of the grid in different time periods; peak load: the highest load of the grid in a certain time period; average load: the average load of the grid in a certain time period.

[0043] Reduce queuing time: queuing time, queue length, and average number of people in queue; queuing time: the actual waiting time from when a user arrives at the charging station to when charging begins; queue length: the number of users waiting for charging; average number of people in queue: the average number of users queuing for charging within a certain period of time.

[0044] The priorities at this time may be as shown in Table 1 below.

[0045] Table 1 Priority list

[0046]

[0047]

[0048] At this time, the sub-elements in the preliminary scheduling target are sorted according to the above form, and after sorting for different preliminary scheduling targets, the importance ranking can be obtained. The importance ranking at this time is expressed as a sorted list. At this time, the scheduling target is output according to the priority situation; at this time, the content included in the sub-elements in the scheduling target is the content of the sub-elements in the preliminary scheduling target.

[0049] The method for obtaining dispatch pricing is to obtain real-time electricity price information, take the dispatch target as input based on the real-time electricity price information, determine the dispatch factor corresponding to the dispatch target, and obtain the dispatch pricing based on the dispatch factor and real-time electricity price information.

[0050] The value of the scheduling factor at this time is expressed as the average value of the sub-elements in the scheduling target. The composition of the sub-elements of the scheduling target here is consistent with the content in the preliminary scheduling target above; the number of scheduling factors is consistent with the number of sub-elements in the scheduling target.

[0051] Then the scheduling pricing at this time can be expressed as follows.

[0052] Where SP′ represents the dispatch pricing, SP represents the value of the real-time electricity price information, and w i represents the weight of the i-th scheduling factor, F i Indicates the value of the i-th dispatch factor, n indicates the number of dispatch factors, and the value of i ranges from 1 to n. During the calculation, the real-time electricity price information, the weight of the dispatch factor, and the value of the dispatch factor will be normalized in advance. The dispatch pricing output at this time is more inclined to a percentage type value. This value can be used to determine whether the price needs to be adjusted at this time.

[0053] For example, if the dispatch pricing is close to 1, it means that the pricing is not much different from the implemented electricity price. This means that the system does not need to adjust or restrict users. When it is close to the range of 0.4-0.8, it means that the system needs to incentivize users to optimize resource utilization. When the dispatch pricing is greater than 1.1, it means that the grid load is high, and it is hoped that adjustments will be made to limit user charging to avoid overload.

[0054] The purpose of checking the power consumption distribution within each scheduling cycle is to determine whether the current power consumption trend is consistent with the power consumption trend in historical data; by checking, it is possible to find out whether there is an anomaly in the current power consumption and identify the corresponding changes; the power consumption distribution will construct a coordinate system according to the time and power consumption value, with time as the vertical coordinate and the power consumption value as the horizontal coordinate to form a coordinate system, and calculate the slope value of the corresponding point in the power consumption distribution at this time.

[0055] For example, according to the scheduling target and scheduling pricing within the scheduling period, the power consumption distribution within the corresponding scheduling period is selected, and the current power consumption distribution is compared with the power consumption distribution at the same time in the historical data to obtain the consumption assessment factor corresponding to the power consumption distribution under each corresponding scheduling target and scheduling pricing; at this time, according to the number of scheduling factors in the scheduling pricing, the slope value corresponding to the power consumption distribution under the corresponding scheduling factor is obtained. This slope value indicates that the value of the power consumption corresponding to the scheduling factor is obtained at the corresponding time, and the slope value of the current power consumption distribution is compared with the standard value of the slope value in the historical data to obtain the consumption assessment factor at this time; at this time, the standard value of the slope value in the historical data is expressed as the standard deviation of the slope value in the historical data.

[0056] The consumption assessment factors are shown below.

[0057] Among them, CEF represents the consumption evaluation factor, S i represents the slope value of the power consumption distribution corresponding to the i-th scheduling factor, S avg represents the average value of the slope value of the power consumption distribution; S std It represents the standard value of the slope value in the historical data, n represents the number of scheduling factors, and the value range of i is 1 to n.

[0058] In the scheduling adjustment module, a data set of incentive clusters is first constructed. Each incentive cluster contains scheduling targets, scheduling pricing and incentive effects. The number of incentive clusters at this time represents the length of this set. When multiple incentive clusters are clustered according to scheduling pricing, the incentive clusters are clustered according to the value range of scheduling pricing at this time. The value ranges of scheduling pricing selection at this time are 0-0.4, 0.4-0.8, 0.8-1.0, 1.0-1.1, and 1.1-1.5 respectively. All data are clustered according to this range, and the incentive factor after clustering is calculated. The corresponding situation under each cluster category is judged at this time, so as to select the target set that needs attention at this time. The incentive factor is expressed as the average value of the incentive effect under each cluster category. The output target set is the cluster with the highest incentive effect, and the cluster with the largest incentive factor value is output as the target set.

[0059] In order to make the output target set more in line with the current processing needs, the incentive effect needs to be set and automatically adjusted according to the scenario or the corresponding processing method, so that the most suitable set of data can be selected.

[0060] Then the incentive effect at this time can be expressed as: obtaining the initial value of the incentive effect corresponding to the scheduling target, adjusting the initial value of the incentive effect according to the sub-elements existing in the scheduling target, and obtaining the output incentive effect.

[0061] IE′(j)=ABS{IE(j)-IE(j) 2 ·In(1+α·IE(j))}; where IE′(j) represents the incentive effect of the output corresponding to the j-th scheduling target, IE(j) represents the initial value of the incentive effect corresponding to the j-th scheduling target, α represents the scheduling coefficient, and ABS{} represents the absolute value of the data in the brackets.

[0062] The scheduling coefficient can be expressed as follows.

[0063] Among them, α represents the scheduling coefficient, represents the average value of the initial value of the incentive effect, m represents the number of scheduling targets; the value range of j is 1 to m, and max(IE(j)) represents the maximum value of the initial value of the incentive effect.

[0064] The incentive effect at this time will be adjusted according to the different initial values of the incentive effect. The initial value of the incentive effect is directly affected by the scheduling target. Therefore, when the sub-elements in the scheduling target change, the incentive effect at this time will also be adjusted accordingly, so that it can be more in line with the current scenario, thereby selecting the most appropriate target set and the corresponding scheduling targets that need to be processed.

[0065] When judging the scheduling order during multi-objective scheduling, you can select the priority of the sub-element of the corresponding scheduling target in the target set, the value of the scheduling pricing, and the value of the incentive factor to set the current scheduling order; the target set obtained at this time is a cluster of scheduling pricing within the corresponding value range, which will contain multiple scheduling targets. The scheduling target can reflect the corresponding needs of users when the current charging pile is in use. Therefore, you can select the priority of the sub-element in the scheduling target at this time to set the scheduling order. At the same time, the target set will also reflect the value of the scheduling pricing and the incentive factor. At this time, you should comprehensively consider the values of the three values to obtain a scheduling order coefficient for the scheduling order, and use the scheduling order coefficient obtained at this time as the evaluation result of the scheduling order at this time, thereby completing the evaluation of the scheduling order.

[0066] At the same time, the scheduling order will be affected by the value of the scheduling order coefficient, and the part with a larger value of the scheduling order coefficient will be given priority scheduling.

[0067] Therefore, the scheduling order coefficient is expressed as shown below. The priority, scheduling price, and incentive factor of the sub-element corresponding to the scheduling target in the target set are obtained to obtain the scheduling order coefficient.

[0068] SSC = β1 × PSO + β2 × SP′ + β3 × IF; where SSC represents the scheduling order coefficient, PSO represents the priority of the sub-element of the scheduling target, SP′ represents the scheduling price, IF represents the incentive factor, β1 represents the weight of the priority of the sub-element of the scheduling target, β2 represents the weight of the scheduling price, and β3 represents the weight of the incentive factor; these three weights are set to 0.6, 0.3, and 0.1 in the order of β1, β2, and β3.

[0069] In the scheduling evaluation module, when evaluating based on the output results of the scheduling identification module, the scheduling adjustment module, and the scheduling parallel module, the output result of the scheduling identification module is the consumption evaluation factor, the scheduling adjustment module is the target set including the scheduling target and scheduling pricing, and the scheduling parallel module is the scheduling sequence coefficient. When comprehensively evaluating the contents of these three modules, it is necessary to calculate the loss value between the target set and the predicted value, and combine the consumption evaluation factor and the scheduling sequence coefficient at this time to obtain a comprehensive evaluation result.

[0070] The comprehensive evaluation results are shown below.

[0071] Among them, CEE represents the comprehensive evaluation result, CEF represents the consumption evaluation factor, SSC represents the scheduling order coefficient, and x(k) represents the value of the kth element in the target set. It represents the predicted value of the kth element in the target set, k represents the number of elements in the target set, and the value range of k is 1 to K. At this time, the elements in the target set include not only the scheduling target but also the scheduling pricing. The losses generated by these elements are calculated in sequence, which can quantify the losses generated after the current scheduling target is selected, thereby facilitating the verification of the overall comprehensive evaluation effect. λ1 represents the weight of the consumption evaluation factor, λ2 represents the weight of the scheduling order coefficient, λ3 represents the weight of the target set, and e represents the exponential constant. According to the order of consumption evaluation factor, scheduling order coefficient, and target set, the weights can be set to 0.4, 0.4, and 0.2 respectively to quantify the evaluation effect at this time.

[0072] By obtaining this comprehensive evaluation result, we can determine the deficiencies in the scheduling of the charging pile at this time, and then evaluate the overall status of the charging pile based on the multiple coefficients calculated in this part to obtain the overall evaluation result of the charging pile at this time.

[0073] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention, which are still covered by the scope of protection of the present invention.

Claims

1. The intelligent dispatching system of new energy charging piles based on big data is characterized by: include: The information collection module is used to obtain the scheduling cycle of the charging pile and collect the charging capacity, power consumption and charging time of the charging pile in each scheduling cycle; The dispatch identification module is used to identify the dispatch target and dispatch pricing in each dispatch cycle, and to check the power consumption distribution in each dispatch cycle to obtain the consumption assessment factor; The scheduling target is obtained by obtaining the usage data of the number of charging times, charging amount, and charging time of the charging piles within the scheduling period, analyzing the user's charging habits, and identifying the peak and off-peak periods of charging pile usage; classifying users and setting behavioral labels; Calculate the user's habit coefficient under the behavior tag, and use the habit coefficient, charging times, charging amount, and charging time as comprehensive search conditions to retrieve the preliminary scheduling target; prioritize the sub-elements in the preliminary scheduling target and output them as the scheduling target for the scheduling identification module; The scheduling adjustment module is used to obtain multiple incentive clusters corresponding to the scheduling target based on the scheduling target and scheduling pricing within each scheduling cycle. Each incentive cluster contains the scheduling target, scheduling pricing, and incentive effect. The multiple incentive clusters are clustered according to the scheduling pricing to obtain the incentive factor for each scheduling cycle. Based on the obtained incentive factor, the target set for charging pile scheduling is determined. The scheduling parallel module is used to determine the scheduling order coefficient of the charging piles in multi-objective scheduling according to the target set of the charging pile scheduling, and obtain the evaluation result of the scheduling order; The scheduling evaluation module is used to evaluate the current scheduling mode according to the output results of the scheduling identification module, the scheduling adjustment module and the scheduling parallel module, and obtain a comprehensive evaluation result of the charging pile scheduling.

2. The intelligent dispatching system for new energy charging piles based on big data according to claim 1 is characterized in that: The specific method for obtaining the scheduling target is as follows: Calculate the average number of times each user charges, the amount of charge, and the charging time; categorize users based on the average number of times, amount of charge, and charging time, and assign behavior labels to each user; Calculate the user's habit coefficient for charging times, charging amount, and charging time under each behavior tag, and use the habit coefficient, charging times, charging amount, and charging time as comprehensive search conditions to retrieve the corresponding preliminary scheduling targets from the database; The sub-elements in the preliminary scheduling target are prioritized to obtain the importance ranking of different preliminary scheduling targets, and the ranking is output as the scheduling target in the scheduling identification module.

3. The intelligent dispatching system for new energy charging piles based on big data according to claim 1 is characterized in that: The method for obtaining dispatch pricing is to obtain real-time electricity price information, take the dispatch target as input based on the real-time electricity price information, determine the dispatch factor corresponding to the dispatch target, and obtain the dispatch pricing based on the dispatch factor and real-time electricity price information.

4. The intelligent dispatching system for new energy charging piles based on big data according to claim 3 is characterized in that: Dispatch pricing can be expressed as follows: Where SP′ represents the dispatch pricing, SP represents the value of the real-time electricity price information, and w i represents the weight of the i-th scheduling factor, F i Represents the value of the i-th scheduling factor, n represents the number of scheduling factors, and the value of i ranges from 1 to n.

5. The intelligent dispatching system for new energy charging piles based on big data according to claim 3 is characterized in that: The consumption assessment factors are as follows: Among them, CEF represents the consumption evaluation factor, S i represents the slope value of the power consumption distribution corresponding to the i-th scheduling factor, S avg represents the average value of the slope value of the power consumption distribution; S std It represents the standard value of the slope value in the historical data, n represents the number of scheduling factors, and the value range of i is 1 to n.

6. The intelligent dispatching system for new energy charging piles based on big data according to claim 1 is characterized in that: When multiple incentive clusters are clustered according to the dispatch pricing in the dispatch adjustment module, the incentive clusters are clustered according to the value range of the dispatch pricing; The incentive factor in each scheduling cycle is expressed as the average value of the incentive effect under each cluster category; the cluster with the largest incentive factor value is output as the target set.

7. The intelligent dispatching system for new energy charging piles based on big data according to claim 1 is characterized in that: The incentive effect can be expressed as follows: obtaining the initial value of the incentive effect corresponding to the scheduling target, adjusting the initial value of the incentive effect according to the sub-elements in the scheduling target, and obtaining the output incentive effect; IE′(j)=ABS{IE(j)-IE(j) 2 ·In(1+α·IE(j))}; Among them, IE′(j) represents the incentive effect of the output corresponding to the j-th scheduling target, IE(j) represents the initial value of the incentive effect corresponding to the j-th scheduling target, α represents the scheduling coefficient, and ABS{} represents the absolute value of the data in the brackets.

8. The intelligent dispatching system for new energy charging piles based on big data according to claim 7 is characterized in that: The scheduling coefficient can be expressed as follows; Among them, α represents the scheduling coefficient, IE represents the average value of the initial value of the incentive effect, and m represents the number of scheduling targets; the value range of j is 1 to m, and max(IE(j)) represents the maximum value of the initial value of the incentive effect.

9. The intelligent dispatching system for new energy charging piles based on big data according to claim 1 is characterized in that: The scheduling order coefficient is expressed as follows: the priority, scheduling price, and incentive factor of the sub-element corresponding to the scheduling target in the target set are obtained to obtain the scheduling order coefficient; SSC=β1×PSO+β2×SP′+β3×IF; Among them, SSC represents the scheduling order coefficient, PSO represents the priority of the sub-elements of the scheduling target, SP′ represents the scheduling price, IF represents the incentive factor, β1 represents the weight of the priority of the sub-elements of the scheduling target, β2 represents the weight of the scheduling price, and β3 represents the weight of the incentive factor.

10. The intelligent dispatching system for new energy charging piles based on big data according to claim 1 is characterized in that: The comprehensive evaluation results are shown as follows: Among them, CEE represents the comprehensive evaluation result, CEF represents the consumption evaluation factor, SSC represents the scheduling order coefficient, and x(k) represents the value of the kth element in the target set. represents the predicted value of the kth element in the target set, k represents the number of elements in the target set, and the value range of k is 1 to K; λ1 represents the weight of the consumption evaluation factor, λ2 represents the weight of the scheduling order coefficient, λ3 represents the weight of the target set, and e represents the exponential constant.

Images