Intelligent charging network topology optimization method, device, equipment and storage medium

Abstract

The present invention relates to a method, device, equipment and storage medium for optimizing the topology of an intelligent charging network, comprising the following steps: monitoring parameters of a target charging network in a charging area through a preset sensor to obtain operating data of the target charging network; wherein the target charging network has a plurality of charging piles; performing a time-series charging demand analysis on the target charging network based on the operating data to obtain time-series charging demand data; performing topology planning on the charging piles based on the operating data and the time-series charging demand data to obtain a preliminary planned charging network structure; performing multi-objective balanced optimization on the preliminary planned charging network structure to obtain an optimized charging network; and solving the technical problem of how to achieve a balance between charging load and power supply capacity of a power grid as the pressure on the power grid increases with the increase in the number of electric vehicles.

Description

Technical Field

[0001] The present invention relates to the field of charging network technology, and in particular to a method, device, equipment and storage medium for optimizing the topology of an intelligent charging network. Background Art

[0002] As the popularity of electric vehicles (EVs) continues to grow, the need for efficient and reliable charging infrastructure has become increasingly prominent. In this context, the construction of a smart charging network has become one of the key factors in promoting the development of the electric vehicle industry. However, existing charging facilities often face problems such as uneven distribution and low utilization efficiency. Especially during peak hours, some charging piles may have queues, while other charging piles may be idle, which not only affects the user experience, but also limits the overall service efficiency of charging facilities. In addition, as the number of electric vehicles increases, the pressure on the power grid is also increasing. How to achieve a balance between charging load and power supply capacity of the power grid has become an urgent problem to be solved.

[0003] Traditional charging network planning is usually based on static analysis, ignoring the dynamic characteristics of charging demand, resulting in planning results that are difficult to adapt to demand fluctuations in actual operation. For example, during the morning and evening peak hours on weekdays, the charging demand in the city center is significantly higher than in other time periods, while during non-peak hours, the utilization rate of charging piles in these areas will drop significantly. This imbalance between supply and demand not only wastes charging resources, but also brings inconvenience to users. Therefore, developing an intelligent charging network topology optimization method that can respond to changes in charging demand in real time and effectively balance the charging load between different areas is of great significance to improving the service quality and user experience of charging facilities.

[0004] In order to meet the above challenges, researchers have begun to explore the application of advanced information technology, data analysis technology and optimization algorithms in the planning and management of charging networks, aiming to improve the flexibility and adaptability of charging networks through intelligent means. This study proposes a smart charging network topology optimization method, which integrates sensor technology to monitor the operating data in the charging area in real time, and combines time-series charging demand analysis to achieve dynamic adjustment and optimal configuration of charging piles. This method not only helps to alleviate the problem of uneven distribution of charging facilities, but also promotes the effective use of power resources, providing technical support for the realization of a green and sustainable urban transportation system. Summary of the invention

[0005] The main purpose of the present invention is to provide a method, device, equipment and storage medium for optimizing the topology of an intelligent charging network, which solves the technical problem of how to achieve a balance between the charging load and the power supply capacity of the power grid as the number of electric vehicles increases and the pressure on the power grid is also increasing.

[0006] To achieve the above object, the present invention provides a method for optimizing the topology of a smart charging network, comprising the following steps:

[0007] Monitoring parameters of a target charging network in a charging area through a preset sensor to obtain operating data of the target charging network; wherein the target charging network has a plurality of charging piles;

[0008] Performing a time-series charging demand analysis on the target charging network based on the operation data to obtain time-series charging demand data;

[0009] Performing topological planning on the charging piles based on the operating data and the sequential charging demand data to obtain a preliminary planned charging network structure;

[0010] The preliminary planned charging network structure is subjected to multi-objective balance optimization to obtain an optimized charging network.

[0011] Furthermore, the parameter monitoring of the target charging network in the charging area by a preset sensor to obtain the operation data of the target charging network includes:

[0012] Independently monitoring the electrical signals of each charging pile in the target charging network in the charging area through a preset sensor to obtain a monitoring electrical signal;

[0013] Performing signal filtering and amplification on the monitoring electrical signal to obtain a filtered and amplified electrical signal;

[0014] Converting the filtered and amplified electrical signal into a digital format to obtain digital electrical signal data;

[0015] The digitized electrical signal data is classified to obtain electrical classification data, and the electrical classification data is used as target charging network operation data; wherein the electrical classification data includes voltage data, current data and charging power data.

[0016] Further, the performing a time-series charging demand analysis on the target charging network based on the operation data to obtain time-series charging demand data includes:

[0017] Performing a multi-scale time-frequency analysis on the operation data to obtain a multi-scale time-frequency analysis feature; wherein the multi-scale time-frequency analysis feature includes a charging fluctuation feature, a charging duration distribution feature, and a charging frequency change feature;

[0018] Through a preset long short-term memory network, a charging demand trend analysis is performed on the charging pile based on the multi-scale time-frequency analysis characteristics to obtain a charging demand trend characteristic; wherein the charging demand trend characteristic includes a long-term trend characteristic, a seasonal change characteristic, and a random fluctuation characteristic;

[0019] Performing charging pattern recognition on the charging demand trend characteristics to obtain a typical charging demand pattern;

[0020] Performing a correlation analysis on the typical charging demand pattern to obtain the weights of factors affecting the charging demand;

[0021] Based on the weights of the charging demand influencing factors, the typical mode of charging demand and the trend characteristics of charging demand, a time-series charging demand analysis is performed on the target charging network to obtain time-series charging demand data.

[0022] Furthermore, the performing preliminary topology planning on the charging piles based on the operation data and the sequential charging demand data to obtain a preliminary planned charging network structure includes:

[0023] Based on the operation data and the time-series charging demand data, the spatial density of the charging area is estimated to obtain a charging demand spatial distribution density map; wherein the charging demand spatial distribution density map includes charging hot spots, charging demand intensity and spatial aggregation degree;

[0024] By using a preset spatially constrained Delaunay triangulation algorithm, the charging area is divided into charging demand areas based on the charging demand spatial distribution density map to obtain charging demand division areas;

[0025] Based on the charging demand division area, the charging demand spatial interpolation is performed on the charging area to obtain a continuous charging demand distribution map;

[0026] Based on the continuous charging demand distribution map, topological layout settings are performed on each of the charging piles of the target charging network to obtain an initial charging pile layout structure; wherein the initial charging pile layout structure includes candidate locations, capacity allocation, and coverage of the charging piles;

[0027] The initial charging pile layout structure is collaboratively optimized to obtain a preliminary planned charging network structure.

[0028] Furthermore, the topological layout of each charging pile of the target charging network is set based on the continuous charging demand distribution map to obtain an initial charging pile layout structure, including:

[0029] Prioritize each of the charging piles in the target charging network based on the continuous charging demand distribution map to obtain a charging pile layout priority list;

[0030] Allocating the number and position of each of the charging piles in the target charging network based on the charging pile layout priority list and the operating data of the target charging network to obtain a preliminary charging pile allocation plan;

[0031] Calling the multi-factor data in the database, optimizing and adjusting the charging piles in the preliminary charging pile allocation plan based on the multi-factor data, and obtaining an initial charging pile layout structure; wherein the multi-factor data includes user waiting time, charging pile utilization rate target and user travel pattern;

[0032] Constructing a future charging network based on the initial charging pile layout structure, and performing a feasibility analysis on the future charging network to obtain an analysis result;

[0033] If the analysis result shows that the future charging network is feasible, the initial charging pile layout structure is used as the initial charging pile layout structure.

[0034] Furthermore, the prioritization of each of the charging piles of the target charging network based on the continuous charging demand distribution map to obtain a charging pile layout priority list includes:

[0035] By using a preset charging area positioning system, the continuous charging demand distribution map is assigned positioning coordinates to obtain a geographically coordinated charging demand distribution map;

[0036] Performing multi-scale segmentation processing on the geographical coordinate charging demand distribution map to obtain a plurality of demand distribution submaps with different resolutions;

[0037] Performing vector transformation on each of the demand distribution subgraphs to obtain a transformation vector, and sorting the transformation vectors from left to right to obtain a charging demand feature matrix; wherein the columns of the charging demand feature matrix represent the resolution levels, the rows of the charging demand feature matrix represent the geographical location coordinates of the charging area, and the elements of the charging demand feature matrix represent the charging demand intensity of a specific geographical location at a specific resolution;

[0038] Inputting the charging demand characteristic matrix into a preset charging pile ranking model for priority evaluation to obtain a charging pile layout score;

[0039] The charging piles of the target charging network are prioritized based on the charging pile layout scores to obtain a charging pile layout priority list.

[0040] Furthermore, the multi-objective optimization of the preliminary planned charging network structure to obtain an optimized charging network includes:

[0041] Performing a multi-objective performance evaluation on the preliminary planned charging network structure to obtain a multi-objective performance evaluation result;

[0042] Based on the multi-objective performance evaluation result, weights are assigned to the preliminary planned charging network structure to obtain multi-objective weights;

[0043] Based on the multi-objective weights, the preliminary planned charging network structure is simulated and adjusted to obtain multiple groups of topology adjustment solutions;

[0044] Performing simulation tests on the multiple groups of topology adjustment schemes to obtain simulation test results, and performing performance evaluation on the simulation test results to obtain a performance evaluation value corresponding to each group of topology adjustment schemes;

[0045] The topology adjustment scheme corresponding to the highest performance evaluation value is used to optimize the network structure of the initially planned charging network to obtain an optimized charging network.

[0046] The present invention also includes a smart charging network topology optimization device, comprising:

[0047] A monitoring module, used to monitor parameters of a target charging network in a charging area through a preset sensor to obtain operation data of the target charging network; wherein the target charging network has a plurality of charging piles;

[0048] An analysis module, configured to perform a sequential charging demand analysis on the target charging network based on the operation data to obtain sequential charging demand data;

[0049] A planning module, used to perform topology planning on the charging piles based on the operation data and the sequential charging demand data to obtain a preliminary planned charging network structure;

[0050] The optimization module is used to perform multi-objective balance optimization on the preliminary planned charging network structure to obtain an optimized charging network.

[0051] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0052] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned methods are implemented.

[0053] The intelligent charging network topology optimization method provided by the present invention comprises the following steps: monitoring the parameters of the target charging network in the charging area through a preset sensor to obtain the operation data of the target charging network; wherein the target charging network has a plurality of charging piles; performing a time-series charging demand analysis on the target charging network based on the operation data to obtain the time-series charging demand data; performing topology planning on the charging piles based on the operation data and the time-series charging demand data to obtain a preliminary planned charging network structure; performing multi-objective balance optimization on the preliminary planned charging network structure to obtain an optimized charging network; through the above-mentioned technical means, the technical problem of how to achieve a balance between charging load and power supply capacity of the power grid as the pressure faced by the power grid increases with the increase in the number of electric vehicles is solved, and the intelligent charging network topology optimization method is realized. It not only focuses on the reasonable layout and efficient operation of charging piles, but also particularly emphasizes the effective use of power resources. By optimizing the charging time arrangement, more electric vehicles can be guided to charge during the period when the power grid load is low, thereby helping to smooth the load curve of the power grid, reduce the peak-to-valley difference of the power system, and is conducive to the beneficial effects of energy conservation, emission reduction and environmental protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 is a schematic diagram of the steps of a method for optimizing a topology of an intelligent charging network in one embodiment of the present invention;

[0055] Figure 2 is a structural block diagram of a smart charging network topology optimization device in one embodiment of the present invention;

[0056] Figure 3 It is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0057] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0059] like Figure 1 As shown, Figure 1 It is a schematic diagram of the steps of a smart charging network topology optimization method in one embodiment of the present invention;

[0060] In one embodiment of the present invention, a method for optimizing a smart charging network topology is provided, comprising the following steps:

[0061] Step S1, monitoring parameters of a target charging network in a charging area through a preset sensor to obtain operating data of the target charging network; wherein the target charging network has a plurality of charging piles.

[0062] Specifically, in the process of implementing the intelligent charging network topology optimization method, it is first necessary to monitor the parameters of the target charging network in the charging area through preset sensors to obtain the operating data of the target charging network. The target charging network here refers to a collection of charging facilities in a specific area containing multiple charging piles. For example, in a large commercial area or residential area, multiple electric vehicle charging piles are deployed. In order to ensure that these charging piles can operate efficiently, it is necessary to install various sensors to collect real-time status information of each charging pile, such as the usage of the charging pile, charging power, charging time and other data. These sensors can be intelligent modules built into the charging piles, or they can be external devices installed around the charging piles. They can continuously collect data and transmit the data to the central processing system through wireless communication technology. In this way, based on the collected operating data, the system can timely understand the working status of each charging pile and the operating status of the entire charging network, providing basic support for subsequent sequential charging demand analysis and charging pile topology planning. For example, during peak hours in the morning and evening, the system can analyze the data sent back by sensors and find that the utilization rate of charging piles in a commercial area has increased sharply. It can then issue early warnings and take measures, such as guiding users to nearby charging piles or adjusting charging prices to balance charging demand, thereby avoiding charging problems caused by insufficient charging piles.

[0063] Step S2: performing a sequential charging demand analysis on the target charging network based on the operating data to obtain sequential charging demand data.

[0064] Specifically, after obtaining the operating data of the target charging network, the next step is to conduct an in-depth analysis of these data. Specifically, it is to conduct a time-series charging demand analysis on the target charging network based on the operating data to obtain the time-series charging demand data. This means that by using data analysis technology, the system can identify the changing trend of charging demand in different time periods. For example, in the large commercial or residential areas mentioned above, the system can analyze that the frequency of use of charging piles during the morning and evening peak hours on weekdays is significantly higher than that in other time periods, while at night or on weekends, the charging demand is relatively stable. Such an analysis not only depends on the actual use records of charging piles, but also includes consideration of external factors such as weather forecasts and holiday arrangements, because these factors will also affect people's travel plans and charging behaviors. Through such a time-series charging demand analysis, the system can predict future charging demand patterns and provide a scientific basis for subsequent charging pile topology planning and optimization. For example, the system predicts that there may be a small holiday on the upcoming weekend, and it is expected that the charging demand around the commercial area will increase significantly, so it is prepared in advance, such as adding temporary charging piles or adjusting charging fees to better meet user needs.

[0065] Step S3, performing topology planning on the charging piles based on the operation data and the sequential charging demand data to obtain a preliminary planned charging network structure.

[0066] Specifically, in the process of topological planning of charging piles, it is necessary to first collect and analyze operation data and time-series charging demand data, including but not limited to the actual use frequency of charging piles, charging peak period, and the time distribution of vehicle arrival and departure. Based on the in-depth analysis of these data, it is possible to effectively identify which areas or time periods have high charging demand, thereby providing a scientific basis for the reasonable layout of charging piles. For example, in the central area of ​​the city, due to the large flow of electric vehicles during the daytime hours on weekdays and the concentrated charging demand, it may be necessary to add fast charging piles in this area to meet the demand during peak hours. At the same time, by analyzing the time-series charging demand data, it is also possible to predict the trend of charging load changes in the future, which is also of great significance for optimizing power grid dispatching and ensuring stable power supply. On this basis, combined with multiple factors such as geographic information, traffic flow, and user behavior, mathematical models and algorithms (such as linear programming, genetic algorithms, etc.) are used to carry out topological planning of charging piles, and finally a preliminary planned charging network structure that meets actual needs and is economical and efficient can be obtained. This process can not only improve the utilization rate of charging piles, but also effectively alleviate the "mileage anxiety" caused by insufficient charging facilities, and promote the popularization and development of new energy vehicles.

[0067] Step S4, performing multi-objective balance optimization on the preliminary planned charging network structure to obtain an optimized charging network.

[0068] Specifically, in the intelligent charging network topology optimization method, the multi-objective balance optimization of the preliminary planned charging network structure is performed to obtain an optimized charging network, which is an important link to ensure the efficient, economical and environmentally friendly operation of the charging network. This process is based on the preliminary planning, comprehensively considering multiple optimization objectives, such as minimizing construction costs, maximizing user convenience, reducing the impact on the power grid, etc., and fine-tuning the charging network structure through advanced optimization algorithms. For example, in a large commercial or residential area, the preliminary planning may have determined the approximate location and number of charging piles, but in the multi-objective balance optimization stage, the system will further evaluate the utilization rate of these charging piles in different time periods, whether the distance between charging stations is convenient for users to use, and the impact of charging load on the local power grid. By introducing mathematical modeling and simulation technology, the optimization algorithm can simulate different scenarios, such as how to reasonably allocate charging resources during peak hours to avoid local overload, or encourage charging during low hours to make full use of excess electricity. After multiple rounds of iterative optimization, the optimized charging network finally formed can not only meet daily charging needs, but also effectively respond to emergencies, such as surges in charging demand during holidays or special events. In addition, the optimized charging network can also reduce operating costs and energy waste while ensuring service quality, thereby achieving both economic and social benefits. For example, after optimization, the system successfully reduced the number of charging piles in certain high-cost areas, while increasing the charging capacity during low-price periods, thus ensuring the charging needs of users and achieving the goal of energy conservation and emission reduction.

[0069] In a specific embodiment, the parameter monitoring of the target charging network in the charging area by a preset sensor to obtain the operation data of the target charging network includes:

[0070] Independently monitoring the electrical signals of each charging pile in the target charging network in the charging area through a preset sensor to obtain a monitoring electrical signal;

[0071] Performing signal filtering and amplification on the monitoring electrical signal to obtain a filtered and amplified electrical signal;

[0072] Converting the filtered and amplified electrical signal into a digital format to obtain digital electrical signal data;

[0073] The digitized electrical signal data is classified to obtain electrical classification data, and the electrical classification data is used as target charging network operation data; wherein the electrical classification data includes voltage data, current data and charging power data.

[0074] Specifically, in the intelligent charging network topology optimization method, the target charging network in the charging area is monitored by the preset sensors to obtain the operation data of the target charging network, which is the basis for ensuring the efficient operation of the entire system. This process specifically includes four closely connected steps, namely, the electrical signals of each charging pile in the target charging network in the charging area are independently monitored by the preset sensors to obtain the monitoring electrical signals; the monitoring electrical signals are filtered and amplified to obtain the filtered and amplified electrical signals; the filtered and amplified electrical signals are converted into digital format to obtain digital electrical signal data; finally, the digital electrical signal data is classified to obtain electrical classification data, and the electrical classification data is used as the target charging network operation data, wherein the electrical classification data includes voltage data, current data and charging power data. First, the electrical signals of each charging pile in the target charging network in the charging area are independently monitored by the preset sensors, which is the first step of the entire data collection process. For example, in a large commercial area or residential area, each charging pile is equipped with a special sensor, which can monitor the working status of the charging pile in real time, including but not limited to key electrical parameters such as voltage, current and charging power. These sensors are designed to withstand not only the harsh conditions of the outdoor environment, but also to have high precision and high stability to ensure that the collected data is true and reliable. The independent monitoring of the electrical signal of each charging pile means that the data of each charging pile is obtained separately, which can avoid mutual interference between data and improve the accuracy and reliability of the data. Next, the monitored electrical signal is filtered and amplified, which is a process to remove noise and enhance useful signals. In the actual environment, due to the influence of various factors, such as electromagnetic interference, temperature changes, etc., the collected original electrical signals often contain different degrees of noise. If not processed, these noises will seriously affect the accuracy of subsequent data processing. Therefore, it is very necessary to use appropriate filtering techniques (such as low-pass filtering, band-pass filtering, etc.) to eliminate high-frequency noise and retain useful signal components. At the same time, in order to make the signal reach a level suitable for further processing, it is also necessary to amplify it appropriately. This step ensures the quality of the signal and lays a good foundation for subsequent data processing. Subsequently, the filtered and amplified electrical signal is converted into a digital format to obtain digital electrical signal data. This is a process of converting an analog signal into a digital signal, which is usually completed by an analog-to-digital converter (ADC). Compared with analog signals, digital signals have stronger anti-interference ability and are easier to store, transmit and process. In this process, it is very important to choose the appropriate sampling rate and quantization bit number, which directly affect the quality of the converted digital signal.For example, in the electrical signal monitoring of charging piles, if the sampling rate is too low, signal distortion may occur; and the selection of the number of quantization bits determines the resolution of the digital signal, which in turn affects the accuracy of the final data analysis. Through the carefully designed digital format conversion, it can be ensured that the electrical signals collected from the physical world can be efficiently and accurately represented in digital form, providing a high-quality data source for subsequent data analysis. Finally, the digitized electrical signal data is classified to obtain electrical classification data, and the electrical classification data is used as the target charging network operation data. The purpose of this step is to organize the complex electrical signal data into a format that is easy to understand and use. Specifically, according to different types of electrical parameters, such as voltage, current, and charging power, the digitized electrical signal data is classified to form structured electrical classification data. These classification data not only contain the specific working status of each charging pile at a certain moment, but also reflect the working trend of the charging pile over time. For example, by analyzing the voltage data, the stability of the power supply of the power grid can be understood; by analyzing the current data, the load condition of the charging pile can be evaluated; and by analyzing the charging power data, the efficiency of the charging pile can be mastered. These electrical classification data are the basis for subsequent sequential charging demand analysis, charging pile topology planning and multi-objective balance optimization, and are essential for realizing intelligent management and optimization of the charging network. In summary, through the above four steps, high-quality operating data can be collected from each of the charging piles in the target charging network in the charging area, providing solid data support for the optimization of the intelligent charging network. For example, in a large commercial area, through this complete set of data collection and processing processes, the system can monitor the operating status of each charging pile in real time, accurately predict the changing trend of charging demand, and reasonably plan the layout of charging piles, ultimately achieving efficient, economical, and environmentally friendly operation of the charging network.

[0075] In a specific embodiment, the performing a time-series charging demand analysis on the target charging network based on the operation data to obtain time-series charging demand data includes:

[0076] Performing a multi-scale time-frequency analysis on the operation data to obtain a multi-scale time-frequency analysis feature; wherein the multi-scale time-frequency analysis feature includes a charging fluctuation feature, a charging duration distribution feature, and a charging frequency change feature;

[0077] Through a preset long short-term memory network, a charging demand trend analysis is performed on the charging pile based on the multi-scale time-frequency analysis characteristics to obtain a charging demand trend characteristic; wherein the charging demand trend characteristic includes a long-term trend characteristic, a seasonal change characteristic, and a random fluctuation characteristic;

[0078] Performing charging pattern recognition on the charging demand trend characteristics to obtain a typical charging demand pattern;

[0079] Performing a correlation analysis on the typical charging demand pattern to obtain the weights of factors affecting the charging demand;

[0080] Based on the weights of the charging demand influencing factors, the typical mode of charging demand and the trend characteristics of charging demand, a time-series charging demand analysis is performed on the target charging network to obtain time-series charging demand data.

[0081] Specifically, in the intelligent charging network topology optimization method, it is a complex but crucial task to analyze the time-series charging demand of the target charging network based on the operation data to obtain the time-series charging demand data. This process mainly includes four closely related steps: multi-scale time-frequency analysis of the operation data to obtain multi-scale time-frequency analysis features; through a preset long-short memory network, the charging demand trend analysis of the charging pile is performed based on the multi-scale time-frequency analysis features to obtain the charging demand trend features; the charging mode recognition of the charging demand trend features is performed to obtain the typical mode of charging demand; the correlation analysis of the typical mode of charging demand is performed to obtain the weight of the influencing factor of charging demand; finally, the time-series charging demand analysis of the target charging network is performed based on the weight of the influencing factor of charging demand, the typical mode of charging demand and the trend feature of charging demand to obtain the time-series charging demand data. First, the multi-scale time-frequency analysis of the operation data is performed to fully understand the changing characteristics of the charging demand from different time and frequency scales. For example, in a large commercial area or residential area, the use of charging piles will be affected by many factors, such as time, weather, holidays, etc. Through multi-scale time-frequency analysis, the charging fluctuation characteristics, charging duration distribution characteristics and charging frequency change characteristics can be extracted. The charging fluctuation characteristics reflect the changes in charging demand in a short period of time (such as a few hours), which can help identify peak and valley periods; the charging duration distribution characteristics reveal the average duration of each charging of users and its distribution, which is very important for optimizing charging strategies and improving the utilization rate of charging piles; the charging frequency change characteristics focus on the changes in the frequency of use of charging piles in a day, a week or even a year, which helps to discover periodic demand patterns. For example, the system may find that the frequency of use of charging piles in commercial areas during the morning and evening peak hours on weekdays is significantly higher than that in other time periods, while this demand pattern will change on weekends or holidays. Next, the charging demand trend analysis of the charging piles is performed based on the multi-scale time-frequency analysis characteristics through the preset long short-term memory network (LSTM) to obtain the charging demand trend characteristics. LSTM is a special recursive neural network that is particularly good at processing data with time series properties and can capture long-term dependencies in the data. In this process, the LSTM model will learn and predict the long-term trend characteristics, seasonal change characteristics and random fluctuation characteristics of charging demand based on the multi-scale time-frequency analysis characteristics. The long-term trend characteristics reflect the overall changing trend of charging demand over time. For example, as the number of electric vehicles increases, the charging demand increases year by year. The seasonal change characteristics point out the differences in charging demand in different seasons. For example, in winter, the cold weather may shorten the range of electric vehicles, thereby increasing the charging demand. The random fluctuation characteristics capture short-term changes that are not affected by seasons and long-term trends, such as the surge in charging demand caused by emergencies.Through the training and prediction of the LSTM model, a relatively accurate estimate of the charging demand in the future can be made. Then, the charging demand trend characteristics are subjected to charging mode recognition to obtain the typical charging demand pattern. This step aims to identify representative charging modes from a large number of charging demand trend characteristics. For example, the system may find that there are several typical charging modes, including weekday peak mode, weekend leisure mode, holiday travel mode, etc. Each mode corresponds to a specific charging demand characteristic. For example, in the weekday peak mode, the charging piles in the commercial area are highly used during the morning and evening peak hours, but relatively low during the non-peak hours; in the weekend leisure mode, the charging piles near the residential area are frequently used during the day, but tend to be quiet at night. Through charging mode recognition, a basis can be provided for the subsequent optimization of charging pile layout and adjustment of charging strategy. Then, the typical charging demand pattern is subjected to correlation analysis to obtain the weights of the factors affecting the charging demand. This step is to determine which factors have the greatest impact on the charging demand. Through statistical analysis and machine learning methods, the contribution of different factors (such as time, weather, holidays, etc.) to the charging demand, that is, the weights of the influencing factors, can be calculated. For example, the system may find that time factors have the most significant impact on charging demand, followed by weather factors, and then holiday factors. These weight values ​​can not only help understand the reasons behind charging demand, but also be used to guide the dynamic pricing strategy of charging piles, such as appropriately increasing charging fees during peak hours to disperse charging demand and reduce the burden on the power grid. Finally, based on the weights of the factors affecting charging demand, the typical mode of charging demand, and the trend characteristics of charging demand, the target charging network is analyzed for time-series charging demand to obtain time-series charging demand data. This final step is to combine all the previous analysis results to form a comprehensive forecast of future charging demand. For example, the system can predict that in the upcoming weekend, due to good weather, the charging demand in both commercial and residential areas will increase, especially in the afternoon, when users may charge in a concentrated manner. Based on such predictions, the available status of charging piles can be adjusted in advance, temporary charging piles can be added, or the best charging time and place can be recommended to users through mobile applications to improve charging efficiency and service quality. Through this series of analysis and optimization, the smart charging network can not only better meet the charging needs of users, but also effectively balance the load of the power grid and promote the rational use of energy. In summary, through multi-scale time-frequency analysis of operating data, charging demand trend analysis, charging pattern recognition, and correlation analysis, the time-series charging demand analysis of the target charging network is finally achieved. This process not only improves the intelligent management level of the charging network, but also provides strong technical support for the realization of a green and sustainable urban transportation system.

[0082] In a specific embodiment, the preliminary topology planning of the charging piles based on the operation data and the sequential charging demand data to obtain a preliminary planned charging network structure includes:

[0083] Based on the operation data and the time-series charging demand data, the spatial density of the charging area is estimated to obtain a charging demand spatial distribution density map; wherein the charging demand spatial distribution density map includes charging hot spots, charging demand intensity and spatial aggregation degree;

[0084] By using a preset spatially constrained Delaunay triangulation algorithm, the charging area is divided into charging demand areas based on the charging demand spatial distribution density map to obtain charging demand division areas;

[0085] Based on the charging demand division area, the charging demand spatial interpolation is performed on the charging area to obtain a continuous charging demand distribution map;

[0086] Based on the continuous charging demand distribution map, topological layout settings are performed on each of the charging piles of the target charging network to obtain an initial charging pile layout structure; wherein the initial charging pile layout structure includes candidate locations, capacity allocation, and coverage of the charging piles;

[0087] The initial charging pile layout structure is collaboratively optimized to obtain a preliminary planned charging network structure.

[0088] Specifically, in the intelligent charging network topology optimization method, it is a key step to perform preliminary topology planning on the charging piles based on the operation data and the time-series charging demand data to obtain a preliminary planned charging network structure. This process includes five closely connected steps: based on the operation data and the time-series charging demand data, the spatial density of the charging area is estimated to obtain a charging demand spatial distribution density map; based on the charging demand spatial distribution density map, the charging area is divided into charging demand areas by a preset spatial constraint Delaunay triangulation algorithm to obtain a charging demand division area; based on the charging demand division area, the charging area is interpolated with charging demand space to obtain a continuous charging demand distribution map; based on the continuous charging demand distribution map, the topological layout of each charging pile of the target charging network is set to obtain an initial charging pile layout structure; finally, the initial charging pile layout structure is collaboratively optimized to obtain a preliminary planned charging network structure. First, the spatial density of the charging area is estimated based on the operation data and the time-series charging demand data to obtain a charging demand spatial distribution density map. The purpose of this process is to determine the spatial distribution of charging demand by analyzing historical charging data and predicted charging demand. For example, in a large commercial or residential area, the system will comprehensively consider the actual use records of charging piles and the predicted charging demand, and calculate the charging demand density in different areas. The charging demand spatial distribution density map includes not only the charging hotspot areas, that is, the places with the highest demand, but also the charging demand intensity and spatial aggregation degree. This information helps to identify which areas need more charging piles and which areas can be appropriately reduced. For example, the system may find that the central area of ​​the commercial district is a charging hotspot area, while the demand in the edge areas is relatively low. Next, the charging demand is divided into the charging area based on the charging demand spatial distribution density map through the preset spatial constraint Delaunay triangulation algorithm to obtain the charging demand division area. The Delaunay triangulation algorithm is a commonly used geographic information system (GIS) technology that can divide the space into several non-overlapping triangular areas. By introducing spatial constraints, such as obstacles such as roads and buildings, it can be ensured that the division results are more in line with actual needs. Based on the charging demand spatial distribution density map, the system can divide the charging area into multiple charging demand division areas, each with clear boundaries and demand characteristics. For example, the central area of ​​a commercial district may be divided into several high-demand areas, while the residential area may be divided into multiple medium- and low-demand areas. This division helps to optimize the subsequent layout of charging piles and ensure that each area can get reasonable resource allocation. Then, based on the charging demand division area, the charging demand spatial interpolation is performed on the charging area to obtain a continuous charging demand distribution map. Spatial interpolation is a commonly used data processing technology that can convert discrete charging demand data into a continuous distribution map.Through interpolation algorithms, such as Kriging, the intensity of charging demand in each divided area can be estimated, and a continuous charging demand distribution map can be generated. This map not only shows the continuous change of charging demand in space, but also reveals some potential hot spots of charging demand. For example, the system may find that although some areas are not obvious hot spots, through interpolation analysis, it is found that their charging demand cannot be ignored, and these areas also need to increase the charging piles appropriately. Then, based on the continuous charging demand distribution map, the topological layout of each charging pile of the target charging network is set to obtain the initial charging pile layout structure. This process is to convert the charging demand distribution map into a specific charging pile layout plan. The system will determine the candidate location, capacity allocation and coverage of the charging pile according to the continuous charging demand distribution map. For example, in high-demand areas, the system may recommend adding large-capacity charging piles to meet the charging demand during peak hours; while in low-demand areas, a small number of small-capacity charging piles can be set to save investment costs. At the same time, the system will also consider the coverage between charging piles to ensure that the service radius of each charging pile can cover the surrounding charging demand points. In this way, the layout structure of the charging piles can be preliminarily determined, providing a basis for subsequent optimization. Finally, the initial charging pile layout structure is collaboratively optimized to obtain a preliminary planned charging network structure. Collaborative optimization refers to the process of seeking the best balance between multiple optimization objectives. For example, the system needs to find the optimal solution between multiple objectives such as minimizing construction costs, maximizing user convenience, and reducing the impact on the power grid. By introducing multi-objective optimization algorithms, such as genetic algorithms, particle swarm optimization algorithms, etc., the system can perform multiple iterations on the initial charging pile layout structure, and gradually adjust the location, number and capacity of the charging piles until a satisfactory optimization result is achieved. For example, the system may find that the layout of charging piles in a certain area is too dense, resulting in a waste of resources, while the number of charging piles in another area is insufficient to meet the demand. Through collaborative optimization, the layout of charging piles in these areas can be readjusted to ensure the efficient operation of the entire charging network. In summary, through the comprehensive analysis of the operating data and the time-series charging demand data, combined with spatial density estimation, charging demand division, spatial interpolation, topological layout setting and collaborative optimization processing, a preliminary planned charging network structure can be obtained. This process not only ensures a more reasonable layout of charging piles, but also effectively responds to the temporal and spatial changes in charging demand, providing users with efficient and convenient charging services. For example, in a large commercial area, through this series of optimization steps, the system can ensure that there are enough charging piles for users during peak hours, and the number of charging piles can be appropriately reduced during off-peak hours to save operating costs. Ultimately, the smart charging network can not only improve the user's charging experience, but also promote the rational use of energy, achieving a win-win situation of economic and social benefits.

[0089] In a specific embodiment, the topological layout of each charging pile of the target charging network is set based on the continuous charging demand distribution map to obtain an initial charging pile layout structure, including:

[0090] Prioritize each of the charging piles in the target charging network based on the continuous charging demand distribution map to obtain a charging pile layout priority list;

[0091] Allocating the number and position of each of the charging piles in the target charging network based on the charging pile layout priority list and the operating data of the target charging network to obtain a preliminary charging pile allocation plan;

[0092] Calling the multi-factor data in the database, optimizing and adjusting the charging piles in the preliminary charging pile allocation plan based on the multi-factor data, and obtaining an initial charging pile layout structure; wherein the multi-factor data includes user waiting time, charging pile utilization rate target and user travel pattern;

[0093] Constructing a future charging network based on the initial charging pile layout structure, and performing a feasibility analysis on the future charging network to obtain an analysis result;

[0094] If the analysis result shows that the future charging network is feasible, the initial charging pile layout structure is used as the initial charging pile layout structure.

[0095] Specifically, in the intelligent charging network topology optimization method, it is a complex but crucial step to set the topological layout of each charging pile of the target charging network based on the continuous charging demand distribution map to obtain the initial charging pile layout structure. This process specifically includes five closely connected sub-steps: prioritize each charging pile of the target charging network based on the continuous charging demand distribution map to obtain a charging pile layout priority list; allocate the number and position of each charging pile of the target charging network based on the charging pile layout priority list and the operation data of the target charging network to obtain a preliminary charging pile allocation plan; call the multi-factor data in the database, optimize and adjust the charging piles in the preliminary charging pile allocation plan based on the multi-factor data, and obtain the initial charging pile layout structure; construct the future charging network based on the initial charging pile layout structure, and analyze the feasibility of the future charging network to obtain the analysis result; if the analysis result is that the future charging network is feasible, the initial charging pile layout structure is used as the initial charging pile layout structure. First, prioritize each charging pile of the target charging network based on the continuous charging demand distribution map to obtain a charging pile layout priority list. The purpose of this process is to determine which areas have the highest priority for charging pile layout and which areas can be considered later. For example, in a large commercial or residential area, the system will identify the areas with the highest charging demand, such as the central area of ​​the commercial area, major traffic intersections, etc., based on the continuous charging demand distribution map. The charging pile layout priority of these areas will be ranked first, while the areas with lower demand will be ranked later. In this way, efficient use of resources can be ensured, and the charging needs of high-demand areas can be met first. For example, the system may find that the central area of ​​the commercial area has extremely high charging demand during the morning and evening peak hours on weekdays, so it is listed as the highest priority area. Next, based on the charging pile layout priority list and the operating data of the target charging network, the number and location of each charging pile of the target charging network are allocated to obtain a preliminary charging pile allocation plan. This process is based on the determination of the priority, and the number and location of charging piles in each area are specifically planned. The system will comprehensively consider the charging pile layout priority list and the operating data of the target charging network, such as the historical usage records of charging piles, charging demand forecasts, etc., to determine the number and location of charging piles in each area. For example, in the central area of ​​a commercial district, the system may recommend setting up multiple large-capacity charging piles to cope with high demand during peak hours; while in residential areas, some small-capacity charging piles can be set up to meet daily charging needs. In this way, the charging pile layout plan for each area can be preliminarily determined to provide a basis for subsequent optimization. Then, the multi-factor data in the database is called, and the charging piles in the preliminary charging pile allocation plan are optimized and adjusted based on the multi-factor data to obtain the initial charging pile layout structure.Multi-factor data include user waiting time, charging pile utilization rate target and user travel pattern. These data can help the system evaluate the rationality of the preliminary charging pile allocation plan more comprehensively. For example, the system may find that although there are enough charging piles in a certain area, the user experience is poor due to the long waiting time of users. In this case, the system can reduce the user waiting time by increasing the number of charging piles or optimizing the use scheduling of charging piles. At the same time, the system will also consider the utilization rate target of the charging piles to ensure that the utilization rate of each charging pile remains within a reasonable range to avoid resource waste. In addition, the user's travel pattern is also an important reference for optimization. For example, the system can find that the charging demand on weekends and holidays is quite different from that on weekdays, so the layout and use strategy of charging piles can be appropriately adjusted during these time periods. Through these optimization adjustments, a more reasonable initial charging pile layout structure can be obtained. Then, based on the initial charging pile layout structure, a future charging network is constructed, and the feasibility of the future charging network is analyzed to obtain analysis results. This process is to verify whether the optimized charging pile layout plan is feasible. Based on the initial charging pile layout structure, the system will construct a future charging network model and evaluate its performance through simulation analysis. For example, the system can simulate the charging demand in a certain time period in the future, and evaluate the usage of charging piles, user waiting time, grid load and other indicators. If the simulation results show that the future charging network can meet the expected charging demand and all performance indicators are within an acceptable range, then the solution can be considered feasible. On the contrary, if certain problems are found, such as the charging pile utilization rate is too low, the user waiting time is too long, etc., the system needs to further optimize the charging pile layout plan until a satisfactory result is achieved. Finally, if the analysis result shows that the future charging network is feasible, the initial charging pile layout structure is used as the initial charging pile layout structure. This means that after a series of optimization adjustments and feasibility analysis, the system finally determines a reasonable charging pile layout plan. This plan can not only meet the current charging demand, but also cope with future demand changes and ensure the efficient operation of the charging network. For example, in a large commercial area, the charging pile layout plan optimized by the above steps can ensure that there are enough charging piles for users to use during peak hours, and the number of charging piles can be appropriately reduced during off-peak hours to save operating costs. Ultimately, the smart charging network can not only improve the user's charging experience, but also promote the rational use of energy, and achieve a win-win situation of economic and social benefits. In summary, through the analysis of the continuous charging demand distribution map, combined with the priority sorting of charging pile layout, the formulation of the preliminary charging pile allocation plan, the optimization and adjustment of multi-factor data, and the feasibility analysis of the future charging network, a reasonable initial charging pile layout structure can be obtained. This process not only ensures that the layout of the charging piles is more scientific and reasonable, but also can effectively respond to the temporal and spatial changes in charging demand, and provide users with efficient and convenient charging services.For example, in a large commercial area, through this series of optimization steps, the system can ensure that there are enough charging piles for users during peak hours, and the number of charging piles can be appropriately reduced during off-peak hours to save operating costs. Ultimately, the smart charging network can not only improve the user's charging experience, but also promote the rational use of energy, achieving a win-win situation in economic and social benefits.

[0096] In a specific embodiment, the prioritization of each charging pile of the target charging network based on the continuous charging demand distribution map to obtain a charging pile layout priority list includes:

[0097] By using a preset charging area positioning system, the continuous charging demand distribution map is assigned positioning coordinates to obtain a geographically coordinated charging demand distribution map;

[0098] Performing multi-scale segmentation processing on the geographical coordinate charging demand distribution map to obtain a plurality of demand distribution submaps with different resolutions;

[0099] Performing vector transformation on each of the demand distribution subgraphs to obtain a transformation vector, and sorting the transformation vectors from left to right to obtain a charging demand feature matrix; wherein the columns of the charging demand feature matrix represent the resolution levels, the rows of the charging demand feature matrix represent the geographical location coordinates of the charging area, and the elements of the charging demand feature matrix represent the charging demand intensity of a specific geographical location at a specific resolution;

[0100] Inputting the charging demand characteristic matrix into a preset charging pile ranking model for priority evaluation to obtain a charging pile layout score;

[0101] The charging piles of the target charging network are prioritized based on the charging pile layout scores to obtain a charging pile layout priority list.

[0102] Specifically, in the intelligent charging network topology optimization method, it is a key preliminary work to prioritize the charging piles of the target charging network based on the continuous charging demand distribution map to obtain a priority list of charging pile layout. This process includes five closely connected steps: assigning positioning coordinates to the continuous charging demand distribution map through a preset charging area positioning system to obtain a geographically coordinated charging demand distribution map; performing multi-scale segmentation processing on the geographically coordinated charging demand distribution map to obtain multiple demand distribution submaps with different resolutions; performing vector transformation on each demand distribution submap to obtain a transformation vector, and sorting the transformation vectors from left to right to obtain a charging demand feature matrix; inputting the charging demand feature matrix into a preset charging pile sorting model for priority evaluation to obtain a charging pile layout score; and prioritizing the charging piles of the target charging network based on the charging pile layout score to obtain a charging pile layout priority list. First, assigning positioning coordinates to the continuous charging demand distribution map through a preset charging area positioning system to obtain a geographically coordinated charging demand distribution map. The purpose of this process is to assign specific geographical location coordinates to each point in the charging demand distribution map for subsequent processing and analysis. For example, in a large commercial or residential area, the system uses GPS or other positioning technology to convert each charging demand point in the continuous charging demand distribution map into specific longitude and latitude coordinates. In this way, each charging demand point has a clear geographical location, which is convenient for subsequent spatial analysis. For example, the system may find that the central area of ​​the commercial area has the highest charging demand near the longitude and latitude (39.9042, 116.4074), while the edge of the residential area has a lower charging demand near the longitude and latitude (39.9000, 116.4000). Next, the geographically coordinated charging demand distribution map is subjected to multi-scale segmentation processing to obtain multiple demand distribution sub-maps with different resolutions. The purpose of multi-scale segmentation processing is to analyze the distribution of charging demand from different spatial scales in order to more comprehensively understand the spatial characteristics of charging demand. For example, the system can divide the entire charging area into multiple sub-areas of different sizes, such as 1 km × 1 km, 500 m × 500 m, and 100 m × 100 m. The distribution of charging demand in each sub-area will be recorded separately to form multiple demand distribution sub-maps with different resolutions. In this way, the system can capture the changes in charging demand from macro to micro, and provide multi-level data support for subsequent analysis. For example, the system may find that in a 1 km × 1 km sub-area, the charging demand is highest in the center of the commercial district, and in a 100 m × 100 m sub-area, the charging demand in certain specific parking lots is also very concentrated. Then, each of the demand distribution sub-maps is vectorized to obtain a transformation vector, and the transformation vectors are sorted from left to right to obtain a charging demand feature matrix.The purpose of this process is to convert the demand distribution submap obtained by multi-scale segmentation into a numerical vector form for computer processing and analysis. For example, the system can convert the charging demand intensity in each demand distribution submap into a vector, in which each element represents the charging demand intensity of a sub-area. Then, these vectors are arranged from left to right according to the resolution level to form a charging demand feature matrix. In this matrix, the columns represent the resolution level, the rows represent the geographical coordinates of the charging area, and the elements represent the charging demand intensity of a specific geographical location at a specific resolution. For example, the first column of the charging demand feature matrix may represent the charging demand distribution at a resolution of 1 km × 1 km, the second column represents the charging demand distribution at a resolution of 500 m × 500 m, and so on. In this way, the system can simplify the complex charging demand distribution map into a structured data matrix for subsequent priority evaluation. Then, the charging demand feature matrix is ​​input into a preset charging pile ranking model for priority evaluation to obtain a charging pile layout score. The charging pile ranking model is a pre-trained machine learning model that can evaluate the charging pile layout priority of each geographical location based on the data in the charging demand feature matrix. For example, the system can use models such as decision trees, random forests, or neural networks to calculate the charging pile layout score for each geographic location based on the data in the charging demand feature matrix. These scores reflect the importance of setting up charging piles at the geographic location. The higher the score, the more urgent the charging demand at the geographic location, and the higher the priority of setting up charging piles. For example, the system may find that the central area of ​​the commercial district has very high charging demand at multiple resolution levels, so the charging pile layout score in this area is the highest. Finally, the charging piles of the target charging network are prioritized based on the charging pile layout score to obtain a charging pile layout priority list. The purpose of this process is to determine the charging pile layout priority for each geographic location based on the charging pile layout score. The system will sort all geographic locations from high to low according to the charging pile layout score to form a charging pile layout priority list. This list not only clarifies which areas have the highest charging pile layout priority, but also provides a basis for the subsequent allocation of the number and location of charging piles. For example, the system may find that the charging pile layout priority is highest in the central area of ​​the commercial district, major traffic intersections, and large parking lots, while the charging pile layout priority is lower in the edge of the residential area and secondary roads. In this way, the system can ensure efficient use of resources and give priority to meeting the charging needs of high-demand areas. In summary, by geo-coordinateizing, multi-scale segmentation, vector conversion, priority evaluation and priority sorting the continuous charging demand distribution map, a reasonable charging pile layout priority list can be obtained. This process not only ensures that the layout of the charging piles is more scientific and reasonable, but also can effectively respond to the temporal and spatial changes in charging demand, and provide users with efficient and convenient charging services.For example, in a large commercial area, through this series of optimization steps, the system can ensure that there are enough charging piles for users during peak hours, and the number of charging piles can be appropriately reduced during off-peak hours to save operating costs. Ultimately, the smart charging network can not only improve the user's charging experience, but also promote the rational use of energy, achieving a win-win situation in economic and social benefits.

[0103] In a specific embodiment, the multi-objective optimization of the preliminary planned charging network structure to obtain an optimized charging network includes:

[0104] Performing a multi-objective performance evaluation on the preliminary planned charging network structure to obtain a multi-objective performance evaluation result;

[0105] Based on the multi-objective performance evaluation result, weights are assigned to the preliminary planned charging network structure to obtain multi-objective weights;

[0106] Based on the multi-objective weights, the preliminary planned charging network structure is simulated and adjusted to obtain multiple groups of topology adjustment solutions;

[0107] Performing simulation tests on the multiple groups of topology adjustment schemes to obtain simulation test results, and performing performance evaluation on the simulation test results to obtain a performance evaluation value corresponding to each group of topology adjustment schemes;

[0108] The topology adjustment scheme corresponding to the highest performance evaluation value is used to optimize the network structure of the initially planned charging network to obtain an optimized charging network.

[0109] Specifically, in the intelligent charging network topology optimization method, multi-objective optimization of the preliminary planned charging network structure to obtain an optimized charging network is a key step to ensure efficient and reliable operation of the charging network. This process includes five closely connected steps: multi-objective performance evaluation of the preliminary planned charging network structure to obtain a multi-objective performance evaluation result; weight allocation of the preliminary planned charging network structure based on the multi-objective performance evaluation result to obtain a multi-objective weight; simulation adjustment of the preliminary planned charging network structure based on the multi-objective weight to obtain multiple groups of topology adjustment schemes; simulation test of the multiple groups of topology adjustment schemes to obtain simulation test results, and performance evaluation of the simulation test results to obtain the performance evaluation value corresponding to each group of topology adjustment schemes; the topology adjustment scheme corresponding to the highest performance evaluation value is used to optimize the network structure of the preliminary planned charging network structure to obtain an optimized charging network. First, a multi-objective performance evaluation is performed on the preliminary planned charging network structure to obtain a multi-objective performance evaluation result. The purpose of this process is to evaluate the performance of the preliminary planned charging network structure from multiple perspectives to ensure that the optimized network can achieve the best state in multiple aspects. For example, in a large commercial or residential area, the system will evaluate the following aspects: the utilization rate of charging piles, the waiting time of users, the load balance of the power grid, the construction and maintenance costs of charging piles, etc. By comprehensively considering these indicators, the system can obtain the multi-objective performance evaluation results of the preliminary planning of the charging network structure. For example, the system may find that the utilization rate of the charging pile layout in the preliminary planning is high during peak hours, but the waiting time of users is long, while the utilization rate is low during off-peak hours, but the load of the power grid is more balanced. Next, the weight of the preliminary planning charging network structure is assigned based on the multi-objective performance evaluation results to obtain the multi-objective weights. The purpose of this process is to determine the importance of each evaluation indicator so that it can be given corresponding attention in the subsequent optimization process. For example, based on actual needs and user feedback, the system may determine that the weight of the utilization rate of the charging pile is 0.4, the weight of the waiting time of the user is 0.3, the weight of the load balance of the power grid is 0.2, and the weight of the construction and maintenance cost of the charging pile is 0.1. In this way, the system can ensure that the most important indicators are given priority in the optimization process while taking other indicators into consideration. For example, if users report that long waiting time is a major problem, the system can appropriately increase the user's waiting time weight to ensure that the optimized network can significantly improve the user experience. Then, based on the multi-objective weights, the preliminary planned charging network structure is simulated and adjusted to obtain multiple groups of topology adjustment schemes. This process is to explore the optimal charging pile layout by simulating different adjustment schemes. The system will generate multiple different topology adjustment schemes based on the multi-objective weights, each of which attempts to achieve the best balance on different indicators.For example, the system may generate a plan to increase the number of charging piles during peak hours and reduce the number of charging piles during off-peak hours; another plan may focus on optimizing the distribution of charging piles so that they cover the entire area more evenly. In this way, the system can generate multiple alternative plans to provide a basis for subsequent simulation tests. Then, the multiple groups of topology adjustment plans are simulated and tested to obtain simulation test results, and the simulation test results are evaluated to obtain performance evaluation values ​​corresponding to each group of topology adjustment plans. The purpose of this process is to evaluate the performance of each topology adjustment plan by simulating actual operation. The system will use simulation software to simulate charging demand in different time periods and evaluate the performance of each plan in terms of charging pile utilization, user waiting time, and grid load balance. For example, the system may find that a certain plan significantly reduces the user's waiting time during peak hours, but the charging pile utilization rate is low during off-peak hours; another plan may perform well in balancing the grid load, but the user waiting time during peak hours is long. Through performance evaluation, the system can score each plan and obtain the performance evaluation value corresponding to each group of topology adjustment plans. Finally, the topology adjustment scheme corresponding to the highest performance evaluation value is used to optimize the network structure of the preliminary planned charging network structure to obtain an optimized charging network. The purpose of this process is to select the topology adjustment scheme with the best performance and optimize the charging network structure of the preliminary plan. The system will select the scheme with the highest performance evaluation value based on the simulation test results and apply it to the charging network structure of the preliminary plan. For example, if a scheme performs well in terms of charging pile utilization rate, user waiting time, grid load balance, etc., and has the highest performance evaluation value, the system will select the scheme for optimization. In this way, the system can ensure that the optimized charging network reaches the best state in many aspects, improve the overall operation efficiency and user satisfaction. In summary, by performing multi-objective performance evaluation, weight allocation, simulation adjustment, simulation test and performance evaluation on the preliminary planned charging network structure, and finally selecting the topology adjustment scheme with the best performance for network structure optimization, an efficient optimized charging network can be obtained. This process not only ensures that the performance of the charging network in many aspects reaches the best state, but also can effectively respond to the spatiotemporal changes in charging demand, and provide users with efficient and convenient charging services. For example, in a large commercial area, through this series of optimization steps, the system can ensure that there are enough charging piles for users during peak hours, and the number of charging piles can be appropriately reduced during off-peak hours to save operating costs. Ultimately, the smart charging network can not only improve the user's charging experience, but also promote the rational use of energy, achieving a win-win situation in economic and social benefits.

[0110] The above describes the intelligent charging network topology optimization method in the embodiment of the present invention. The following describes the intelligent charging network topology optimization system in the embodiment of the present invention. Figure 2 , an embodiment of the intelligent charging network topology optimization system in the embodiment of the present invention includes:

[0111] The monitoring module 21 is used to monitor the parameters of the target charging network in the charging area through a preset sensor to obtain the operation data of the target charging network; wherein the target charging network has a plurality of charging piles;

[0112] An analysis module 22, configured to perform a sequential charging demand analysis on the target charging network based on the operation data to obtain sequential charging demand data;

[0113] A planning module 23, configured to perform topology planning on the charging piles based on the operation data and the sequential charging demand data to obtain a preliminary planned charging network structure;

[0114] The optimization module 24 is used to perform multi-objective balance optimization on the preliminary planned charging network structure to obtain an optimized charging network.

[0115] In this embodiment, for the specific implementation of each unit in the above system embodiment, please refer to the above method embodiment, which will not be repeated here.

[0116] Reference Figure 3 The present invention also provides a computer device in an embodiment, wherein the internal structure of the computer device can be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a display screen, an input device, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above method is implemented.

[0117] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0118] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above method is implemented. It can be understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0119] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided by the present invention and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM.

[0120] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0121] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for optimizing the topology of an intelligent charging network, characterized in that: The following steps are involved: Monitoring parameters of a target charging network in a charging area through a preset sensor to obtain operating data of the target charging network; wherein the target charging network has a plurality of charging piles; Performing a time-series charging demand analysis on the target charging network based on the operation data to obtain time-series charging demand data; Performing topological planning on the charging piles based on the operating data and the sequential charging demand data to obtain a preliminary planned charging network structure; Performing multi-objective balance optimization on the initially planned charging network structure to obtain an optimized charging network; The parameter monitoring of the target charging network in the charging area by the preset sensors to obtain the operation data of the target charging network includes: Independently monitoring the electrical signals of each charging pile in the target charging network in the charging area through a preset sensor to obtain a monitoring electrical signal; Performing signal filtering and amplification on the monitoring electrical signal to obtain a filtered and amplified electrical signal; Converting the filtered and amplified electrical signal into a digital format to obtain digital electrical signal data; Classifying the digitized electrical signal data to obtain electrical classification data, and using the electrical classification data as target charging network operation data; wherein the electrical classification data includes voltage data, current data and charging power data; The performing a time-series charging demand analysis on the target charging network based on the operation data to obtain time-series charging demand data includes: Performing a multi-scale time-frequency analysis on the operation data to obtain a multi-scale time-frequency analysis feature; wherein the multi-scale time-frequency analysis feature includes a charging fluctuation feature, a charging duration distribution feature, and a charging frequency change feature; Through a preset long short-term memory network, a charging demand trend analysis is performed on the charging pile based on the multi-scale time-frequency analysis characteristics to obtain a charging demand trend characteristic; wherein the charging demand trend characteristic includes a long-term trend characteristic, a seasonal change characteristic, and a random fluctuation characteristic; Performing charging pattern recognition on the charging demand trend characteristics to obtain a typical charging demand pattern; Performing a correlation analysis on the typical charging demand pattern to obtain the weights of factors affecting the charging demand; Based on the weights of the charging demand influencing factors, the typical mode of charging demand and the trend characteristics of charging demand, a time-series charging demand analysis is performed on the target charging network to obtain time-series charging demand data.

2. The smart charging network topology optimization method according to claim 1, characterized in that: The performing preliminary topology planning on the charging piles based on the operation data and the sequential charging demand data to obtain a preliminary planned charging network structure includes: Based on the operation data and the time-series charging demand data, the spatial density of the charging area is estimated to obtain a charging demand spatial distribution density map; wherein the charging demand spatial distribution density map includes charging hot spots, charging demand intensity and spatial aggregation degree; By using a preset spatially constrained Delaunay triangulation algorithm, the charging area is divided into charging demand areas based on the charging demand spatial distribution density map to obtain charging demand division areas; Based on the charging demand division area, the charging demand spatial interpolation is performed on the charging area to obtain a continuous charging demand distribution map; Based on the continuous charging demand distribution map, topological layout settings are performed on each of the charging piles of the target charging network to obtain an initial charging pile layout structure; wherein the initial charging pile layout structure includes candidate locations, capacity allocation, and coverage of the charging piles; The initial charging pile layout structure is collaboratively optimized to obtain a preliminary planned charging network structure.

3. The intelligent charging network topology optimization method according to claim 2, characterized in that: The topological layout of each charging pile of the target charging network is set based on the continuous charging demand distribution map to obtain an initial charging pile layout structure, including: Prioritize each of the charging piles in the target charging network based on the continuous charging demand distribution map to obtain a charging pile layout priority list; Allocating the number and position of each of the charging piles in the target charging network based on the charging pile layout priority list and the operating data of the target charging network to obtain a preliminary charging pile allocation plan; Calling the multi-factor data in the database, optimizing and adjusting the charging piles in the preliminary charging pile allocation plan based on the multi-factor data, and obtaining an initial charging pile layout structure; wherein the multi-factor data includes user waiting time, charging pile utilization rate target and user travel pattern; Constructing a future charging network based on the initial charging pile layout structure, and performing a feasibility analysis on the future charging network to obtain an analysis result; If the analysis result shows that the future charging network is feasible, the initial charging pile layout structure is used as the initial charging pile layout structure.

4. The intelligent charging network topology optimization method according to claim 3, characterized in that: The prioritizing the charging piles of the target charging network based on the continuous charging demand distribution map to obtain a charging pile layout priority list includes: By using a preset charging area positioning system, the continuous charging demand distribution map is assigned positioning coordinates to obtain a geographically coordinated charging demand distribution map; Performing multi-scale segmentation processing on the geographical coordinate charging demand distribution map to obtain a plurality of demand distribution submaps with different resolutions; Performing vector transformation on each of the demand distribution subgraphs to obtain a transformation vector, and sorting the transformation vectors from left to right to obtain a charging demand feature matrix; wherein the columns of the charging demand feature matrix represent the resolution levels, the rows of the charging demand feature matrix represent the geographical location coordinates of the charging area, and the elements of the charging demand feature matrix represent the charging demand intensity of a specific geographical location at a specific resolution; Inputting the charging demand characteristic matrix into a preset charging pile ranking model for priority evaluation to obtain a charging pile layout score; The charging piles of the target charging network are prioritized based on the charging pile layout scores to obtain a charging pile layout priority list.

5. The smart charging network topology optimization method according to claim 1, characterized in that: The performing multi-objective optimization on the preliminary planned charging network structure to obtain an optimized charging network includes: Performing a multi-objective performance evaluation on the preliminary planned charging network structure to obtain a multi-objective performance evaluation result; Based on the multi-objective performance evaluation result, weights are assigned to the preliminary planned charging network structure to obtain multi-objective weights; Based on the multi-objective weights, the preliminary planned charging network structure is simulated and adjusted to obtain multiple groups of topology adjustment solutions; Performing simulation tests on the multiple groups of topology adjustment schemes to obtain simulation test results, and performing performance evaluation on the simulation test results to obtain a performance evaluation value corresponding to each group of topology adjustment schemes; The topology adjustment scheme corresponding to the highest performance evaluation value is used to optimize the network structure of the initially planned charging network to obtain an optimized charging network.

6. A smart charging network topology optimization device, characterized in that: include: A monitoring module, used to monitor parameters of a target charging network in a charging area through a preset sensor to obtain operation data of the target charging network; wherein the target charging network has a plurality of charging piles; An analysis module, configured to perform a sequential charging demand analysis on the target charging network based on the operation data to obtain sequential charging demand data; A planning module, used to perform topology planning on the charging piles based on the operation data and the sequential charging demand data to obtain a preliminary planned charging network structure; An optimization module, used for performing multi-objective balance optimization on the preliminary planned charging network structure to obtain an optimized charging network; The parameter monitoring of the target charging network in the charging area by the preset sensors to obtain the operation data of the target charging network includes: Independently monitoring the electrical signals of each charging pile in the target charging network in the charging area through a preset sensor to obtain a monitoring electrical signal; Performing signal filtering and amplification on the monitoring electrical signal to obtain a filtered and amplified electrical signal; Converting the filtered and amplified electrical signal into a digital format to obtain digital electrical signal data; Classifying the digitized electrical signal data to obtain electrical classification data, and using the electrical classification data as target charging network operation data; wherein the electrical classification data includes voltage data, current data and charging power data; The performing a time-series charging demand analysis on the target charging network based on the operation data to obtain time-series charging demand data includes: Performing a multi-scale time-frequency analysis on the operation data to obtain a multi-scale time-frequency analysis feature; wherein the multi-scale time-frequency analysis feature includes a charging fluctuation feature, a charging duration distribution feature, and a charging frequency change feature; Through a preset long short-term memory network, a charging demand trend analysis is performed on the charging pile based on the multi-scale time-frequency analysis characteristics to obtain a charging demand trend characteristic; wherein the charging demand trend characteristic includes a long-term trend characteristic, a seasonal change characteristic, and a random fluctuation characteristic; Performing charging pattern recognition on the charging demand trend characteristics to obtain a typical charging demand pattern; Performing a correlation analysis on the typical charging demand pattern to obtain the weights of factors affecting the charging demand; Based on the weights of the charging demand influencing factors, the typical mode of charging demand and the trend characteristics of charging demand, a time-series charging demand analysis is performed on the target charging network to obtain time-series charging demand data.

7. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images