Charging station resource sharing scheduling method, computer program product and system based on power distribution safety inspection in substations
By performing time-sequential processing and machine learning prediction on charging station data, identifying power usage patterns and charging behavior characteristics, and performing resource sharing scheduling of charging stations, solving the problems of virtual capacity increase and distribution safety inspection of charging stations, realizing the charging station Flexible management and security of resources.
Patent Information
- Application Number
- CN202410604882.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-15
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-05-15
AI Technical Summary
The existing technology is difficult to realize the flexible virtual capacity increase strategy of charging stations on the basis of meeting the power distribution safety inspection in Taiwan, resulting in limited revenue from charging stations and difficult to ensure the safety and stability of residential electricity use.
By collecting charging station data, performing timing processing and machine learning prediction, identifying power usage patterns and charging behavior characteristics, performing charging station resource sharing scheduling, dynamically allocating charging resources, meeting charging needs and conducting distribution safety inspections, and realizing charging stations Collaboration and virtual capacity enhancement.
Effectively manage charging station resources, ensure that charging behavior complies with distribution safety inspection, realize virtual capacity increase of charging stations, improve charging efficiency and safety, and ensure the stability of residents' electricity use.
Smart Images

Figure CN118521088B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of charging station resource sharing, and in particular to a charging station resource sharing scheduling method based on area power distribution safety inspection, a computer program product, and a charging station intelligent scheduling system. Background Art
[0002] There are various forms of charging facilities, including AC charging piles, DC charging piles, AC / DC integrated charging piles, battery swap stations, etc. These charging facilities are widely distributed and have various access methods, including centralized access using dedicated distribution lines and decentralized access using existing public distribution facilities. The current complex and changeable access methods have brought difficulties to the power consumption calculation, fault analysis and other safety inspection work of the power distribution network of the power system in the area.
[0003] Among the various existing charging facilities, charging stations are high-power, high-frequency electrical equipment, and their load characteristics are significantly different from those of traditional electrical equipment. The plug-and-play charging characteristics of charging stations cause their loads to be random and intermittent, and the charging power is large and the starting current is high, which has a great impact and fluctuation on the voltage and current of the distribution network. Taking the charging station mainly deployed in the residential area with 7kW orderly slow charging piles as an example, the charging piles of the charging station are often used one after another after 20 o'clock, and the access peak is reached around 23 o'clock, which is very different from the power grid distribution network in the traditional residential area. As a result, the traditional power distribution safety inspection method of the power system is difficult to directly apply to the scene of large-scale disorderly access to the power grid for charging of electric vehicles at charging stations in the residential area, which brings risks to the safe and stable operation of residents' electricity. In order to avoid the above risks, the existing power system power distribution network implements extremely strict power distribution safety inspection strategies for residential charging stations, which leads to great restrictions on the charging stations when implementing the virtual capacity increase strategy, affecting the revenue of the charging stations. Summary of the invention
[0004] The technical problem to be solved by the present invention is to provide a charging station resource sharing and scheduling method based on the power distribution safety inspection of the substation, a computer program product storing a computer program that implements the steps of the method when executed, and a charging station intelligent scheduling system. The charging station resource sharing and scheduling method can execute a flexible charging station virtual capacity expansion strategy based on compliance with the power distribution safety inspection of the substation.
[0005] In order to solve the above technical problems, in a first aspect, the present invention provides a charging station resource sharing scheduling method based on area power distribution safety inspection, comprising the following steps:
[0006] The charging station data collection step includes collecting power usage data, user charging behavior and power distribution safety information of each charging pile at the charging station within a preset time period.
[0007] The charging station data processing step is to perform time series processing on the collected power usage data and user charging behavior, and cluster them to obtain power usage patterns and charging behavior characteristics respectively; perform text recognition processing on the collected power distribution safety information to obtain power distribution safety strategy characteristics;
[0008] The power distribution safety inspection step of the substation uses the current power usage mode and charging behavior characteristics of each charging pile as the feature quantity, and uses the pre-trained machine learning model to predict the power distribution safety strategy characteristics; if the predicted power distribution safety strategy characteristics are not within the preset range, it is judged that the current resources of the charging station do not meet the power distribution safety inspection of the substation, and the charging station resource sharing scheduling step is executed;
[0009] The charging station resource sharing scheduling step obtains the scheduled charging information of each charging pile, generates multiple charging behavior combinations that meet the scheduled charging requirements of all charging piles, performs the area distribution safety inspection step for each charging behavior combination, and obtains the target charging behavior combination whose distribution safety strategy characteristics are predicted to be within the preset range;
[0010] The charging execution step of the charging station, each charging pile of the charging station executes the reserved charging demand according to the target charging behavior combination.
[0011] Furthermore, in the charging station data processing step, a data mining algorithm is used to obtain the temporal correlation between the power usage pattern and the charging behavior characteristics, and the matching degree of the temporal correlation is calculated, and the calculated matching degree is used as the feature quantity weight for machine learning model training.
[0012] Furthermore, the power usage mode includes one or more of the following: single charging power, cumulative charging power, power peak, and the matching degree between the power usage curve and the power consumption waveform of the substation.
[0013] Furthermore, the charging behavior characteristics include one or more of the following: charging frequency, charging start time, charging end time, single charging time, and cumulative charging time.
[0014] Furthermore, in the charging station data processing step, performing text recognition processing on the collected power distribution safety information refers to: obtaining text data of the power distribution safety information, and using a keyword extraction algorithm to extract distribution restriction instruction related keywords from the obtained text data as power distribution safety strategy features.
[0015] Furthermore, in the power distribution safety inspection step of the substation, the power distribution safety strategy feature is not within the preset range, which means that the matching degree between the predicted power distribution safety strategy feature and the key words related to the power distribution restriction instruction is lower than the preset degree.
[0016] Furthermore, the keyword extraction algorithm is one or more of the following algorithms: TF-IDF, TextRank, LDA, Word2Vec, and an algorithm model based on deep learning.
[0017] Furthermore, in the charging station resource sharing scheduling step, the plurality of charging behavior combinations that meet the reserved charging requirements of all charging piles means that each charging pile completes the charging amount requirement within its own reserved charging time.
[0018] In a second aspect, a computer program product is also provided, which stores a computer program, and when the computer program is executed by a processor, it can implement the steps of the above-mentioned charging station resource sharing scheduling method based on the power distribution safety inspection of the substation.
[0019] On the third aspect, a charging station intelligent scheduling system is also provided, including a processor and a charging pile and a charging reservation terminal respectively connected to the processor, the charging reservation terminal is used to obtain the user's charging needs, the charging pile charges according to the charging needs, and also includes the above-mentioned computer program product, the computer program on the computer program product can be executed by the processor.
[0020] The charging station intelligent scheduling system of the present invention executes the steps of the charging station resource sharing scheduling method based on the power distribution safety inspection of the substation. When it is predicted that the charging behavior to be executed has the risk of not meeting the power distribution safety inspection of the substation, the charging station is managed through the intelligent scheduling system to achieve collaboration between the charging piles of the charging station and dynamic allocation of charging resources, so that the charging station can effectively implement the virtual capacity expansion strategy and complete the scheduled charging tasks of each charging pile. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for describing the embodiments are briefly introduced below.
[0022] Figure 1 It is a flow chart of the steps of the charging station resource sharing scheduling method based on the power distribution safety inspection in the substation area. DETAILED DESCRIPTION
[0023] The present invention is further described in detail below in conjunction with specific implementation methods.
[0024] The charging station intelligent dispatching system of this embodiment includes a processor, a charging pile and a charging reservation terminal connected to the processor respectively. The charging reservation terminal is used to obtain the user's charging demand, and the charging pile charges according to the charging demand. When the charging station intelligent dispatching system predicts that the charging behavior to be executed does not meet the risk of the power distribution safety inspection in the substation area, it executes Figure 1The resource sharing scheduling method of charging stations based on the power distribution safety inspection of the substation ensures that the charging process of each charging pile of the charging station meets the safety inspection and realizes the virtual capacity expansion strategy of the charging station. The specific description is as follows.
[0025] (1) Charging station data collection step: The charging station has multiple charging piles. During a preset time period, the power usage data, user charging behavior and power distribution safety information of each charging pile in the charging station are collected.
[0026] (2) Charging station data processing step: the collected power usage data and user charging behavior are processed in a time series manner, and the power usage pattern and charging behavior characteristics are clustered respectively; the collected distribution safety information is processed through text recognition to obtain the distribution safety strategy characteristics.
[0027] Specifically: based on the power usage data of the charging station, a data mining algorithm is used to obtain the power usage pattern of the charging station; by clustering the user's charging behavior data, the characteristics of different types of user charging behaviors are determined; the text data of the power distribution safety information is obtained, and a keyword extraction algorithm is used to extract distribution restriction instruction-related keywords from the obtained text data as distribution safety strategy features.
[0028] Among them, the data mining algorithm is used to obtain the time series correlation between the power usage pattern and the charging behavior characteristics, and the matching degree of the time series correlation is calculated, and the calculated matching degree is used as the feature quantity weight for machine learning model training. The power usage pattern includes the single charging power, cumulative charging power, power peak, and the matching degree between the power usage curve and the power consumption waveform of the substation. The charging behavior characteristics include charging frequency, charging start time, charging end time, single charging duration, and cumulative charging duration.
[0029] Among them, the keyword extraction algorithm is TF-IDF, TextRank, LDA, Word2Vec or other general deep learning-based algorithm models, such as CNN (convolutional neural network), RNN (recurrent neural network), and BERT (Bidirectional Encoder Representations from Transformers).
[0030] (3) The power distribution safety inspection step of the substation uses the current power usage mode and charging behavior characteristics of each charging pile as the feature quantity, and uses the pre-trained machine learning model to predict the power distribution safety strategy characteristics. If the predicted power distribution safety strategy characteristics are not within the preset range, such as the matching degree between the predicted power distribution safety strategy characteristics and the keywords related to the power distribution restriction instruction is lower than the preset degree, it is judged that the current resources of the charging station do not meet the substation power distribution safety inspection, and the charging station resource sharing scheduling step is executed.
[0031] Before predicting the characteristics of the power distribution safety strategy through the machine learning model, this embodiment uses an anomaly detection algorithm to perform real-time analysis of the power distribution safety information to determine whether there are conventional abnormal situations. If a power distribution safety abnormality is found, the early warning mechanism is immediately triggered to notify relevant personnel to handle it. In addition, based on the power usage pattern of the charging station and the characteristics of the user's charging behavior, a charging demand prediction model is constructed to predict the charging demand in the future; through the optimization algorithm, combined with the charging demand prediction results and the power distribution safety constraints, the optimal power allocation plan for the charging station is obtained; the optimal power allocation plan is sent to each charging pile to control the power output of the charging pile and ensure the quality of charging service; an incremental learning algorithm is used to update and optimize the charging demand prediction model and power allocation algorithm in real time based on the newly collected data.
[0032] For example, by conducting data mining and analysis on the power usage data of charging stations in the past month, it was found that the peak power usage from Monday to Friday is from 8 to 10 am and from 6 to 8 pm, with an average power of about 500 kW, while the power usage on weekends is relatively average, with a peak from 2 to 4 pm and an average power of about 300 kW. For example, by clustering the charging behavior data of 1,000 users, users are divided into three categories: the first category is commuters, who usually charge during peak hours in the morning and evening, with an average charging time of 30 minutes; the second category is leisure users, who usually charge on weekend afternoons, with an average charging time of 1 hour; the third category is random users, with relatively random charging time and duration. For example, the anomaly detection algorithm analyzes the power distribution safety data in real time. When the voltage of a certain line suddenly drops from 220V to 180V and the current increases from 100A to 150A, it is determined to be an abnormal situation. Once the power distribution safety anomaly is detected, the system automatically notifies the on-duty personnel and maintenance personnel to go and handle it within 1 minute in the form of text messages and voice calls. For example, a charging demand prediction model was constructed based on the user charging behavior characteristics obtained through cluster analysis, combined with factors such as weather and holidays. The model predicts that the daily charging demand in the next week will be 8000kWh, 9000kWh, 7500kWh, 8200kWh, 9100kWh, 6500kWh and 7000kWh respectively.
[0033] For example, a charging station has 50 charging piles, each with a power of 20kW. The control system of the charging station automatically adjusts the power output of each charging pile according to the optimal power allocation plan issued. For example, when the total power allocated is 400kW, the average power of each charging pile is set to 8kW. For example, the prediction model was updated based on the actual charging demand data collected in the past week, and it was found that the prediction error was reduced by 10%. At the same time, the power allocation algorithm is optimized according to the latest distribution equipment status data, which can increase the total power of the charging station by 5% while ensuring safety. Managers can view the operating information such as power, power, occupancy rate of each charging station, the status of each charging pile, and the voltage, current, temperature and other safety information of the distribution line in real time through the visual interface. When an abnormal situation occurs, the corresponding indicator will be highlighted in a striking color, and an alarm prompt box will pop up automatically.
[0034] (4) Charging station resource sharing and scheduling step, obtaining the scheduled charging information of each charging pile, generating multiple charging behavior combinations that meet the scheduled charging requirements of all charging piles, that is, each charging pile completes the charging demand within its scheduled charging time, and performing the area distribution safety inspection step for each charging behavior combination to obtain the target charging behavior combination whose predicted distribution safety strategy characteristics are within the preset range.
[0035] (5) Charging execution step of the charging station: each charging pile of the charging station executes the reserved charging demand according to the target charging behavior combination.
[0036] This embodiment uses the steps of the above-mentioned charging station resource sharing scheduling method based on the power distribution safety inspection of the substation. When it is predicted that the charging behavior to be executed has the risk of not meeting the power distribution safety inspection of the substation, the charging station is managed through the intelligent scheduling system to achieve collaboration between the charging piles of the charging station and dynamic allocation of charging resources, so that the charging station can effectively implement the virtual capacity expansion strategy and complete the scheduled charging tasks of each charging pile.
[0037] This embodiment implements the above-mentioned charging station resource sharing and scheduling method based on the power distribution safety inspection of the substation through a computer program. The computer program is stored in a computer program product for execution by a computer processor to implement the above-mentioned charging station resource sharing and scheduling method based on the power distribution safety inspection of the substation. The above-described charging station intelligent scheduling system embodiment is only schematic, in which the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without creative labor.
[0038] Finally, it should be noted that the charging station resource sharing and scheduling method based on the power distribution safety inspection in the embodiment of the present invention discloses only a preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.
Claims
1. A charging station resource sharing scheduling method based on power distribution safety inspection in the substation area, characterized in that: The following steps are involved: The charging station data collection step includes collecting power usage data, user charging behavior and power distribution safety information of each charging pile at the charging station within a preset time period. The charging station data processing step performs time series processing on the collected power usage data and user charging behavior, and clusters the power usage pattern and charging behavior characteristics respectively; The collected power distribution safety information is subjected to text recognition processing, specifically: obtaining text data of the power distribution safety information, and using a keyword extraction algorithm to extract distribution restriction instruction-related keywords from the obtained text data as power distribution safety strategy features; the power usage mode includes multiple types of single charging power, cumulative charging power, power peak, and the matching degree between the power usage curve and the power consumption waveform of the substation; the charging behavior features include multiple types of charging frequency, charging start time, charging end time, single charging duration, and cumulative charging duration; The power distribution safety inspection step in the substation area uses the current power usage mode and charging behavior characteristics of each charging pile as the feature quantity, and uses the pre-trained machine learning model to predict the power distribution safety strategy characteristics; If the predicted power distribution safety strategy characteristics are not within the preset range, it is determined that the current resources of the charging station do not meet the power distribution safety inspection of the substation, and the charging station resource sharing scheduling step is executed; The charging station resource sharing scheduling step obtains the scheduled charging information of each charging pile, generates multiple charging behavior combinations that meet the scheduled charging requirements of all charging piles, performs the area distribution safety inspection step for each charging behavior combination, and obtains the target charging behavior combination whose distribution safety strategy characteristics are predicted to be within the preset range; The charging execution step of the charging station, each charging pile of the charging station executes the reserved charging demand according to the target charging behavior combination.
2. The charging station resource sharing and scheduling method based on the power distribution safety inspection of the substation as claimed in claim 1 is characterized in that In the charging station data processing step, a data mining algorithm is used to obtain the temporal correlation between the power usage pattern and the charging behavior characteristics, and the matching degree of the temporal correlation is calculated, and the calculated matching degree is used as the feature quantity weight for machine learning model training.
3. The charging station resource sharing and scheduling method based on the power distribution safety inspection in the substation area as claimed in claim 1 is characterized in that: In the power distribution safety inspection step of the substation, the power distribution safety strategy feature is not within the preset range means that the matching degree between the predicted power distribution safety strategy feature and the key words related to the power distribution restriction instruction is lower than the preset degree.
4. The charging station resource sharing and scheduling method based on the power distribution safety inspection in the substation area according to claim 1 is characterized in that: The keyword extraction algorithm is one or more of the following algorithms: TF-IDF, TextRank, LDA, Word2Vec, and an algorithm model based on deep learning.
5. The charging station resource sharing and scheduling method based on the power distribution safety inspection of the substation as claimed in claim 1 is characterized in that In the charging station resource sharing scheduling step, the plurality of charging behavior combinations that meet the reserved charging requirements of all charging piles means that each charging pile completes the charging amount requirement within its own reserved charging time.
6. A computer program product storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the charging station resource sharing scheduling method based on area power distribution safety inspection according to any one of claims 1 to 5 can be implemented.
7. Intelligent dispatching system for charging stations, characterized by: It includes a processor and a charging pile and a charging reservation terminal respectively connected to the processor, the charging reservation terminal is used to obtain the user's charging demand, the charging pile charges according to the charging demand, and also includes a computer program product as claimed in claim 6, and the computer program on the computer program product can be executed by the processor.
