Electric vehicle charging pile intelligent scheduling method based on big data analysis

Abstract

The invention discloses an electric vehicle charging pile intelligent scheduling method based on big data analysis, and the method comprises the steps: obtaining traffic flow, user charging behaviors, a power grid load and weather data, and building a data fusion model; performing short-term charging demand prediction on the data fusion model by using an enhanced exponential smoothing method to generate an optimal charging pile scheduling scheme; establishing a scheduling feedback mechanism, monitoring whether the time error of the user in the driving process and the idle rate of the charging pile are matched with the optimal scheduling scheme or not, and selecting to update or regenerate the optimal scheduling scheme according to a matching result; through dynamic weight adjustment, demand prediction and scheduling feedback mechanisms, efficient scheduling of charging pile resources in an environment with large demand fluctuation and complex load is ensured, response delay is effectively reduced, and the stability of a scheduling system is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of big data and charging pile scheduling, and in particular to an intelligent scheduling method for electric vehicle charging piles based on big data analysis. Background Art

[0002] With the rapid growth of electric vehicles (EVs), the demand for the construction and management of charging infrastructure has surged, driving the development of intelligent charging pile scheduling technology. The initial charging pile scheduling scheme mainly adopted a static deployment mode, that is, the distribution and resource allocation of charging piles at fixed locations were carried out according to the short-term average demand of the region. Such schemes usually rely on historical data and a single data source to set the number and location of charging piles for a city or a specific area. They are suitable for environments with stable demand, but are prone to resource shortages when demand fluctuates. With the increasing dynamics of charging demand, prediction models based on user travel patterns, daily traffic flow and other data are gradually applied to charging pile scheduling systems. Through simple weighting or rule setting of data, resource allocation is optimized to improve the utilization efficiency of charging piles. However, these methods are mostly based on historical average data and are not responsive to real-time data, resulting in poor performance in dealing with complex urban environments or sudden charging demands. In recent years, with the development of big data and artificial intelligence technologies, more and more charging pile scheduling schemes have begun to adopt multi-data source fusion analysis, trying to integrate dynamic factors such as traffic flow, power grid load, and weather in demand forecasting, and provide data support and prediction basis for dynamic scheduling of charging resources.

[0003] However, the existing charging pile scheduling technology has significant deficiencies in its ability to cope with changes in demand, sudden peak loads and environmental changes. Specifically, the real-time feedback mechanism of the scheduling system is generally not flexible enough, lacking the ability to adaptively adjust the utilization rate of charging piles and the actual driving path of users. It is difficult to quickly update the scheduling plan according to changes in traffic and user charging behavior, resulting in inefficient allocation of resources among different regions. Second, the lack of deep fusion and dynamic weighted processing of multi-source data makes the charging demand forecast lack accuracy and precise regional response. Third, the path recommendation function in the current scheduling method is relatively basic and cannot provide users with the optimal charging path selection considering real-time traffic conditions, thereby extending the user's waiting time and reducing the overall utilization of charging piles. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the above existing problems, the present invention is proposed. Therefore, the present invention provides an intelligent scheduling method for electric vehicle charging piles based on big data analysis to solve the problems raised in the background art.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: An intelligent scheduling method for electric vehicle charging piles based on big data analysis, including:

[0007] Obtain traffic flow, user charging behavior, grid load, and weather data, and establish a data fusion model;

[0008] Use the enhanced exponential smoothing method to predict the short-term charging demand for the data fusion model, schedule the short-term charging demand prediction results, and generate an optimal charging pile scheduling plan;

[0009] Establish a scheduling feedback mechanism to monitor whether the time error and the charging pile idle rate during the current driving process of the user match each item of data in the optimal charging pile scheduling plan;

[0010] According to the matching results, select to update or regenerate the optimal charging pile scheduling plan, thereby forming an intelligent scheduling method for electric vehicle charging piles.

[0011] As a preferred solution of the intelligent scheduling method for electric vehicle charging piles based on big data analysis of the present invention, wherein: obtaining traffic flow, user charging behavior, grid load, and weather data, and establishing a data fusion model, including:

[0012] Assign different weight coefficients to the traffic flow, user charging behavior, grid load, and weather data respectively, and perform weighted summation to obtain a data fusion model.

[0013] As a preferred solution of the intelligent scheduling method for electric vehicle charging piles based on big data analysis of the present invention, wherein: assigning different weight coefficients to the traffic flow, user charging behavior, grid load, and weather data respectively, including:

[0014] Calculate the historical traffic flow, user charging behavior, grid load, and weather data with the real-time traffic flow, user charging behavior, grid load, and weather data to obtain an influence coefficient;

[0015] Represent the real-time data as a time window, and define the change rate of each real-time data as the difference ratio within two adjacent time windows;

[0016] According to the influence coefficient and the change rate of each real-time data, obtain the comprehensive scores of the historical data and the real-time data, sort them in descending order based on the comprehensive scores, and assign the first two data sources after sorting to high priority, and the remaining data sources to low priority.

[0017] As a preferred solution of the intelligent scheduling method for electric vehicle charging piles based on big data analysis according to the present invention, wherein: the enhanced exponential smoothing method is used to predict the short-term charging demand of the data fusion model, including:

[0018] Let the predicted value of the data fusion model at the current moment be The short-term charging demand value at the current moment is F(t), and the short-term charging demand value at the previous moment is F(t-1);

[0019] By considering the idle rate of the charging pile and the traffic convenience in and the influence of F(t), an exponential smoothing formula is obtained;

[0020] According to the short-term charging demand value F(t) at the current moment and the short-term charging demand value F(t-1) at the previous moment, the demand volatility ΔF is calculated;

[0021] The demand volatility ΔF is used as the smoothing coefficient to participate in the operation of the exponential smoothing formula, and an enhanced exponential smoothing formula is obtained.

[0022] As a preferred solution of the intelligent scheduling method for electric vehicle charging piles based on big data analysis according to the present invention, wherein: the short-term charging demand prediction result is scheduled to generate an optimal charging pile scheduling plan, including:

[0023] Taking the optimal charging pile scheduling as the goal, an optimization objective function in the enhanced exponential smoothing formula is established to generate an optimal charging pile scheduling plan;

[0024] Wherein, the optimization objective function is obtained by minimizing the idle rate of the charging pile and maximizing the traffic convenience.

[0025] As a preferred solution of the intelligent scheduling method for electric vehicle charging piles based on big data analysis according to the present invention, wherein: it further includes:

[0026] Every once in a while Δt, the current idle rate and power load data of each charging pile, as well as the traffic flow and road traffic conditions, are obtained from various data platforms, and the current idle rate and power load data of each charging pile, as well as the traffic flow and road traffic conditions, are input into the optimization objective function.

[0027] As a preferred solution of the intelligent scheduling method for electric vehicle charging piles based on big data analysis according to the present invention, wherein: a scheduling feedback mechanism is established, including:

[0028] Based on the obtained optimal charging pile scheduling scheme, the available charging pile locations are recommended to users through a mobile application or in-vehicle system. When the user selects a charging pile location, path navigation will be provided according to the optimization objective function to guide the user to the most suitable charging pile.

[0029] As a preferred embodiment of the intelligent scheduling method for electric vehicle charging piles based on big data analysis according to the present invention, wherein: monitor whether the time error and the charging pile idle rate of the user during the current driving process match each piece of data in the optimal charging pile scheduling scheme, including:

[0030] The monitored data includes the time difference between the user's actual arrival at the charging pile and the real-time utilization rate change of the charging pile.

[0031] If the user's actual arrival time does not match the time in the optimal charging pile scheduling scheme, then increment the traffic convenience in the optimal charging pile scheduling scheme and increase the weight of traffic convenience in the scheduling scheme.

[0032] If the real-time utilization rate of the charging pile is higher than the idle rate of the charging pile in the optimal charging pile scheduling scheme, then reduce the idle rate of the charging pile in the optimal charging pile scheduling scheme.

[0033] As a preferred embodiment of the intelligent scheduling method for electric vehicle charging piles based on big data analysis according to the present invention, wherein: according to the matching result, select to update or regenerate the optimal charging pile scheduling scheme, including:

[0034] If the increased weight of traffic convenience exceeds 1, then regenerate the optimal charging pile scheduling scheme; otherwise, update the charging pile scheduling scheme.

[0035] As a preferred embodiment of the intelligent scheduling method for electric vehicle charging piles based on big data analysis according to the present invention, wherein: further include:

[0036] Before reducing the idle rate of the charging pile, use a time window to judge the real-time utilization rate. If the real-time utilization rate continuously occurs within multiple time windows, then reduce the idle rate of the charging pile and update the charging pile scheduling scheme; otherwise, regenerate the optimal charging pile scheduling scheme.

[0037] Compared with the prior art, the beneficial effects of the invention are:

[0038] 1. The present invention adopts a dynamic weighted adjustment mechanism, adjusts the weights of different data sources according to the real-time change rate and influence coefficient of the data sources, so it has high adaptability. It can not only respond to the changes in charging demands in a timely manner but also avoid the lag of resource allocation.

[0039] 2. By considering the idle rate of charging piles and traffic convenience in the scheduling optimization objective and generating the optimal charging path based on this, more efficient path recommendations are provided for users, effectively shortening the charging waiting time and driving time. In addition, by combining path recommendations with real-time traffic conditions, users can be dynamically guided to the most suitable charging piles, enhancing the overall charging experience of users.

[0040] 3. A scheduling feedback mechanism is constructed to monitor the actual arrival time of users and the real-time utilization rate of charging piles. By judging the utilization situation of charging piles and the path deviation of users, the scheduling scheme is selected for update or regeneration to optimize the resource utilization efficiency, effectively solving the problems of rigid scheduling schemes and inability to flexibly respond to environmental changes in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts. Among them:

[0042] Figure 1 It is the overall flowchart of the intelligent scheduling method for electric vehicle charging piles based on big data analysis according to an embodiment of the present invention;

[0043] Figure 2 It is the influence diagram of the dynamic weight adjustment on the utilization rate of charging piles of the intelligent scheduling method for electric vehicle charging piles based on big data analysis according to an embodiment of the present invention;

[0044] Figure 3 It is the scheduling system response delay diagram under multi-variable dynamic prediction and feedback control of the intelligent scheduling method for electric vehicle charging piles based on big data analysis according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] In order to make the above objects, features, and advantages of the present invention more obvious and understandable, the specific embodiments of the present invention will be described in detail below with reference to the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0046] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. However, the present invention may be practiced in other ways than those specifically described herein. Those skilled in the art can make similar extensions without departing from the spirit of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0047] Secondly, as used herein, "one embodiment" or "an embodiment" refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or alternative embodiments that exclude each other.

[0048] The present invention is described in detail in conjunction with schematic diagrams. When describing the embodiments of the present invention in detail, for the sake of clarity, the cross-sectional views showing the device structure will be enlarged locally out of the general scale, and the schematic diagrams are only examples and should not limit the scope of protection of the present invention herein. In addition, in actual production, three-dimensional spatial dimensions of length, width, and depth should be included.

[0049] Meanwhile, in the description of the present invention, it should be noted that the orientation or positional relationships indicated by terms such as "upper, lower, inner, and outer" are based on the orientation or positional relationships shown in the drawings. They are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of the present invention. In addition, the terms "first, second, or third" are only used for descriptive purposes and should not be construed as indicating or implying relative importance.

[0050] Unless otherwise clearly defined and limited in the present invention, the terms "mounted, connected, and coupled" shall be understood in a broad sense. For example, they can be fixedly connected, detachably connected, or integrally connected; they can also be mechanically connected, electrically connected, or directly connected, or indirectly connected through an intermediate medium, or be in communication with each other inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0051] Embodiment 1

[0052] Referring to Figure 1 , this is the first embodiment of the present invention. This embodiment provides an intelligent scheduling method for electric vehicle charging piles based on big data analysis, including:

[0053] S1. Obtain traffic flow, user charging behavior, grid load, and weather data, and establish a data fusion model;

[0054] Specifically, traffic flow includes the real-time road traffic conditions, vehicle flow speed, and congestion index; user charging behavior includes the charging time, frequency, and charging volume of user charging behavior; grid load includes the real-time load conditions of each region; weather data includes temperature, humidity, and weather conditions (such as rain, snow, sunny days, etc.).

[0055] It should be explained that to ensure the effective utilization of data in the model, an adaptive weighting method needs to be adopted to assign different weight coefficients to different data sources.

[0056] Furthermore, different weight coefficients are respectively assigned to traffic flow, user charging behavior, grid load, and weather data, and weighted summation is performed to obtain a data fusion model.

[0057] Specifically, the data fusion model D(t) is expressed as:

[0058] D(t) = α × T(t) + β × U(t) + γ × W(t) + δ × L(t)

[0059] Where, T(t) represents traffic flow, U(t) represents user charging behavior, W(t) represents grid load, L(t) represents weather data; α, β, γ, δ respectively represent the weight coefficients of traffic flow, user charging behavior, grid load, and weather data.

[0060] Even further, historical traffic flow, user charging behavior, grid load, and weather data are calculated with real-time traffic flow, user charging behavior, grid load, and weather data to obtain an influence coefficient.

[0061] Specifically, the influence coefficient is expressed as:

[0062]

[0063] Where, H i is the historical mean of each data source; R i is the real-time value at the current moment of each data source; σ i,r represents the historical standard deviation of each data source; σ i,h represents the real-time standard deviation of each data source; i represents the number of data sources.

[0064] It should be noted that I i represents the relative influence of each data source at the current moment compared to historical data. The larger the value of I i , the greater the influence of the data source on the current demand.

[0065] Even further, real-time data is represented as a time window, and the change rate of each real-time data is defined as the difference ratio within adjacent two time windows.

[0066] Specifically, the change rate ΔR of each real-time data i (t) is expressed as:

[0067]

[0068] where R i (t) represents the real-time value of each data source in the current window, and R i (t - 1) represents the real-time value of each data source in the next window;

[0069] Specifically, by monitoring the change rate of each data source in real time, significant fluctuations in demand can be obtained. For example, the travel rush of users or weather changes, etc.;

[0070] It should be noted that the influence coefficient captures the differences in the short-term stability and short-term volatility of the data source through the comparison of historical data and real-time data, while the real-time change rate quantifies the volatility of each data source at the current moment. For example, when the demand fluctuates significantly, since the real-time change rate amplifies the weight of the demand response, the scheduling response is accelerated, and when the demand is stable, the scheduling frequency is maintained at a low level, avoiding frequent resource reallocation;

[0071] Furthermore, based on the influence coefficient and the change rate of each real-time data, the comprehensive scores of historical data and real-time data are obtained. Based on the comprehensive scores, a descending order is performed, and the top two data sources after the descending order are assigned to high priority, and the remaining data sources are assigned to low priority;

[0072] Specifically, assigning the top two data sources after the descending order to high priority and the remaining data sources to low priority is equivalent to selecting the top two data with the highest priority from each data source and excluding the remaining data. If the two data are different, the data with the second priority is used as the alternative data for the data with the first priority;

[0073] Specifically, the comprehensive scores of historical data and real-time data are expressed as:

[0074] S i = I i ×(1 + ΔR i (t))

[0075] where S i represents the comprehensive score of each data source;

[0076] It should be noted that by calculating the comprehensive scores and sorting them in descending order, high priority and low priority can be assigned to different data sources, ensuring that data sources with greater influence are given priority in scheduling. In addition, the priority division can reduce the dependence on low-priority data sources and avoid the influence of noise data;

[0077] S2. Use the enhanced exponential smoothing method to predict the short-term charging demand of the data fusion model, schedule the short-term charging demand prediction results, and generate an optimal charging pile scheduling plan;

[0078] It should be noted that for the scheduling of electric vehicle charging piles, it is necessary to consider both the past demand trend and respond promptly to the current demand fluctuations; while the traditional exponential smoothing method cannot effectively balance these two aspects during the smoothing process, often either lagging behind the real-time demand or being overly sensitive to short-term fluctuations, so it is necessary to enhance the traditional exponential smoothing method;

[0079] Specifically, the enhancement steps are as follows:

[0080] Furthermore, let the predicted value of the data fusion model at the current moment be The short-term charging demand value at the current moment is F(t), and the short-term charging demand value at the previous moment is F(t - 1);

[0081] Even further, by considering the influence of the idle rate of the charging pile and traffic convenience on and F(t), the exponential smoothing formula is obtained;

[0082] Specifically, the exponential smoothing formula is expressed as:

[0083]

[0084] Among them, ε is the smoothing coefficient with a value range of 0.1 - 0.9, R(t) is the comprehensive influence value of the idle rate of the charging pile and traffic convenience, is the output value of the exponential smoothing formula;

[0085] Even further, R(t) is expressed as:

[0086] R(t) = L(t) × γ + (1 - C(t)) × α

[0087] Among them, C(t) is the traffic convenience, reflecting the influence of traffic flow α. The higher the value of C(t), the worse the traffic convenience; L(t) represents the idle rate of the charging pile. The higher the value of L(t), the more idle the charging pile;

[0088] Even further, according to the short-term charging demand value F(t) at the current moment and the short-term charging demand value F(t - 1) at the previous moment, the demand volatility ΔF is calculated;

[0089] It should be noted that the change degree of the short-term charging demand needs to be judged by the volatility of the short-term charging demand;

[0090] Specifically, the demand volatility ΔF is expressed as:

[0091]

[0092] Furthermore, the demand volatility ΔF is used as a smoothing coefficient to participate in the operation of the exponential smoothing formula, resulting in an enhanced exponential smoothing formula;

[0093] Specifically, the enhanced exponential smoothing formula is expressed as:

[0094]

[0095] It should be noted that by performing operations on and F(t), the exponential smoothing formula can instantaneously correct the accuracy of the predicted value, enabling the formula to adjust the prediction weight according to the actual changes in demand, rather than simply relying on historical trends;

[0096] S3. Establish a scheduling feedback mechanism to monitor whether the time error and the charging pile idle rate during the current driving process of the user match each item of data in the optimal charging pile scheduling plan;

[0097] Furthermore, with the optimal charging pile scheduling as the goal, an optimization objective function in the enhanced exponential smoothing formula is established to generate an optimal charging pile scheduling plan;

[0098] Specifically, the optimization objective function is obtained by minimizing the idle rate of the charging pile and maximizing the traffic convenience;

[0099] Specifically, the optimization objective function J is expressed as:

[0100]

[0101] Among them, N represents the total number of charging piles, and L i (t) represents the idle rate of the i-th charging pile at the current moment t, and C i (t) represents the traffic convenience of the i-th charging pile at the current moment t; ∈ is a very small positive number to ensure that the denominator is not zero; ω L and ω C respectively represent the weights of the charging pile idle rate and the traffic convenience;

[0102] It should be noted that by participating in the operation of , it is possible to tend to select a charging pile with a lower idle rate. Because the smaller the idle rate, the larger the denominator value, thereby making the value of this term smaller, achieving the minimization of the idle rate; as mentioned before, the higher the value of c(t), the worse the traffic convenience, so it can be obtained that the lower the value of C i (t), the better the traffic convenience, so minimizing C

[0103] Further, every period of time Δt, obtain the current idle rate and power load data of each charging pile, as well as the traffic flow and road traffic conditions from various data platforms, and input the current idle rate and power load data of each charging pile, as well as the traffic flow and road traffic conditions into the optimization objective function;

[0104] It should be noted that by obtaining the current idle rate and power load data of each charging pile, as well as the traffic flow and road traffic conditions in real time, the resource misallocation caused by data lag is avoided, ensuring that the charging pile allocation scheme can be adjusted in a timely manner as the demand changes, so as to achieve efficient and reasonable utilization of charging resources;

[0105] Further, based on the obtained optimal charging pile scheduling scheme, recommend the available charging pile locations to users through a mobile application or in-vehicle system. When the user selects a charging pile location, path navigation will be provided according to the optimization objective function to guide the user to the most suitable charging pile;

[0106] S4. According to the matching result, select to update or regenerate the optimal charging pile scheduling scheme, thus forming an intelligent scheduling method for electric vehicle charging piles;

[0107] Further, the monitoring data includes the time difference between the user's actual arrival at the charging pile and the real-time utilization rate change of the charging pile;

[0108] Further, if the user's actual arrival time does not match the time in the optimal charging pile scheduling scheme, then increment the traffic convenience in the optimal charging pile scheduling scheme and increase the weight of traffic convenience in the scheduling scheme;

[0109] It should be noted that when it is found that the actual arrival time does not match the expected arrival time at the charging pile, it means that the current traffic condition has changed, affecting the user's charging experience; by increasing the weight of traffic convenience, the importance of traffic factors can be enhanced, making the scheduling scheme pay more attention to traffic convenience, so as to give priority to locations with better traffic conditions when selecting charging piles;

[0110] Furthermore, if the increased weight of traffic convenience exceeds 1, regenerate the optimal charging pile scheduling scheme, otherwise update the charging pile scheduling scheme;

[0111] Further, if the real-time utilization rate of the charging pile is higher than the idle rate of the charging pile in the optimal charging pile scheduling scheme, then reduce the idle rate of the charging pile in the optimal charging pile scheduling scheme;

[0112] Further, before reducing the idle rate of the charging pile, the real-time utilization rate is judged using a time window. If the real-time utilization rate continuously occurs within multiple time windows, the idle rate of the charging pile is reduced and the charging pile scheduling scheme is updated. Otherwise, the optimal charging pile scheduling scheme is regenerated.

[0113] It should be noted that if the idle rate is directly reduced for short-term fluctuations in demand, it may lead to over-response. Through the judgment of the time window, the "temporary fluctuations" (intermittent time windows) and "continuous growth" (continuous occurrence of time windows) of the charging pile utilization rate can be clearly distinguished. For temporary fluctuations, the method of regenerating the scheme is adopted without adjusting the idle rate of the charging pile, ensuring an appropriate response to the demand for charging piles without affecting long-term resource allocation.

[0114] Embodiment 2

[0115] Refer to Figure 2 and Figure 3 This is the second embodiment of the present invention. This embodiment provides an intelligent scheduling method for electric vehicle charging piles based on big data analysis, including: In order to verify the application effect of the intelligent scheduling system of the present invention in a dynamic environment, the response performance of the traditional scheduling method and the scheduling method of the present invention under different traffic flows, grid loads, user demands, and weather conditions is compared.

[0116] Experimental site: Select an area with a dense distribution of charging piles in a large city. There are multiple charging stations in the area, and each charging station is equipped with 5 - 10 charging piles. The data collection frequency is once every 5 minutes, and real-time data on traffic, weather, and grid load are obtained through the platform in real time to simulate the charging demand in different time periods.

[0117] Through Figure 2 It can be seen that the change in the utilization rate of the charging piles in the traditional scheduling system shows a certain degree of volatility. It shows a relatively high utilization rate at high loads (at time steps 20 - 40), but then as the demand decreases (at time steps 50 - 80), the utilization rate of the charging piles drops rapidly, failing to stably utilize resources efficiently. While the utilization rate of the charging piles in the scheduling system of the present invention shows a more stable trend. Even in the stage of decreasing demand (at time steps 50 - 80), it still maintains a high resource utilization rate. During the time period when the resource demand increases, the system responds quickly and can maintain the efficient use of the charging piles within a relatively stable range. Secondly, refer to Figure 3, the response delay of the traditional scheduling system fluctuates greatly over time. Especially during high-load periods (at time steps 20 - 40), the response delay reaches more than 80 minutes, indicating that the system experiences significant delays under high demand. In contrast, the response delay of the scheduling system of the present invention is significantly lower than that of the traditional system and is more stable at different time steps. Even under high-load conditions (time steps 20 - 40), the response delay remains around 60 minutes, far lower than that of the traditional system.

[0118] This shows that the scheduling system of the present invention significantly reduces the response delay under different load conditions. Especially under high-demand loads, it demonstrates the advantages of stability and fast response, enabling the scheduling and management of charging piles for short-term demands.

[0119] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code. The solutions in the embodiments of this application can be implemented using various computer languages. For example, object-oriented programming languages such as Java and interpreted scripting languages such as JavaScript.

[0120] This application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of this application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to generate a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0121] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0122] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus, causing a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process, so that the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one process or a plurality of processes and / or blocks Figure 1 one process or a plurality of processes and / or blocks Figure 1 steps for implementing the functions specified in one block or a plurality of blocks.

[0123] Although the preferred embodiments of the present application have been described, additional changes and modifications can be made by those skilled in the art once they learn of the basic inventive concept. Therefore, the appended claims are intended to be construed to cover the preferred embodiments as well as all changes and modifications falling within the scope of the present application.

[0124] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. An intelligent scheduling method for electric vehicle charging piles based on big data analysis, characterized in that: include: Obtain traffic flow, user charging behavior, grid load, and weather data to build a data fusion model; Using the enhanced exponential smoothing method to predict the short-term charging demand of the data fusion model, scheduling the short-term charging demand prediction results, and generating an optimal charging pile scheduling plan; Establish a scheduling feedback mechanism to monitor whether the time error and charging pile idle rate of the user during the current driving process match each data in the optimal charging pile scheduling plan; According to the matching results, the optimal charging pile scheduling plan is updated or regenerated, thereby forming an intelligent scheduling method for electric vehicle charging piles.

2. The intelligent scheduling method for electric vehicle charging piles based on big data analysis according to claim 1, characterized in that: Obtain traffic flow, user charging behavior, grid load, and weather data, and build a data fusion model, including: Different weight coefficients are respectively assigned to the traffic flow, user charging behavior, grid load and weather data, and weighted summation is performed to obtain a data fusion model.

3. The intelligent scheduling method for electric vehicle charging piles based on big data analysis as claimed in claim 2, characterized in that: Different weight coefficients are assigned to the traffic flow, user charging behavior, grid load, and weather data, including: The historical traffic flow, user charging behavior, grid load, and weather data are calculated with the real-time traffic flow, user charging behavior, grid load, and weather data to obtain the influence coefficient; The real-time data is represented as a time window, and the change rate of each real-time data is defined as the difference ratio between two adjacent time windows; According to the influence coefficient and the change rate of each real-time data, a comprehensive score of the historical data and the real-time data is obtained, and the data sources are sorted in descending order based on the comprehensive score, and the first two data sources after descending order are assigned to high priority, and the remaining data sources are assigned to low priority.

4. The intelligent dispatching method for electric vehicle charging piles based on big data analysis as claimed in claim 2, characterized in that: The enhanced exponential smoothing method is used to predict the short-term charging demand of the data fusion model, including: Assume that the prediction value of the data fusion model at the current moment is The short-term charging demand value at the current moment is F(t), and the short-term charging demand value at the previous moment is F(t-1); By considering the idle rate of charging piles and traffic convenience and F(t), we get the exponential smoothing formula; According to the short-term charging demand value F(t) at the current moment and the short-term charging demand value F(t-1) at the previous moment, the demand fluctuation rate ΔF is calculated; The demand volatility ΔF is used as a smoothing coefficient in the calculation of the exponential smoothing formula to obtain an enhanced exponential smoothing formula.

5. The intelligent scheduling method for electric vehicle charging piles based on big data analysis as claimed in claim 4 is characterized in that: Schedule the short-term charging demand forecast results and generate the optimal charging pile scheduling plan, including: Taking the optimal charging pile scheduling as the goal, the optimization objective function in the enhanced exponential smoothing formula is established to generate the optimal charging pile scheduling plan; The optimization objective function is obtained by minimizing the idle rate of charging piles and maximizing traffic convenience.

6. The intelligent dispatching method for electric vehicle charging piles based on big data analysis as claimed in claim 5, characterized in that: Also includes: At regular intervals of Δt, the current idle rate and power load data of each charging pile, as well as traffic flow and road conditions, are obtained from various data platforms, and the current idle rate and power load data of each charging pile, as well as traffic flow and road conditions are input into the optimization objective function.

7. The intelligent scheduling method for electric vehicle charging piles based on big data analysis according to claim 1 or 5, characterized in that: Establish a scheduling feedback mechanism, including: Based on the obtained optimal charging pile scheduling plan, the available charging pile locations are recommended to the user through the mobile application or the vehicle system. When the user selects the charging pile location, path navigation will be provided according to the optimization objective function to guide the user to the most suitable charging pile.

8. The intelligent dispatching method for electric vehicle charging piles based on big data analysis as claimed in claim 7, characterized in that: Monitor whether the time error and charging pile idle rate of the user during the current driving process match each data in the optimal charging pile scheduling plan, including: The monitoring data includes the time difference between the user's actual arrival at the charging station and the real-time utilization rate change of the charging station; If the user's actual arrival time does not match the time in the optimal charging pile scheduling plan, the traffic convenience in the optimal charging pile scheduling plan is incremented to increase the weight of traffic convenience in the scheduling plan; If the real-time utilization rate of the charging piles is higher than the idle rate of the charging piles in the optimal charging pile scheduling plan, the idle rate of the charging piles in the optimal charging pile scheduling plan is reduced.

9. The intelligent dispatching method for electric vehicle charging piles based on big data analysis as claimed in claim 8, characterized in that: According to the matching results, choose to update or regenerate the optimal charging pile scheduling plan, including: If the increased traffic convenience weight exceeds 1, the optimal charging pile scheduling plan is regenerated, otherwise the charging pile scheduling plan is updated.

10. The intelligent dispatching method for electric vehicle charging piles based on big data analysis according to claim 8, characterized in that: Also includes: Before reducing the idle rate of the charging pile, the real-time utilization rate is judged using the time window. If the real-time utilization rate continues to occur in multiple time windows, the idle rate of the charging pile is reduced and the charging pile scheduling plan is updated. Otherwise, the optimal charging pile scheduling plan is regenerated.

Images