CN118630789A - Power control method and system for distribution network based on charging station power aggregation - Google Patents

Abstract

The invention provides a power regulation and control method and a power regulation and control system for a power distribution network based on charging station power aggregation, which are applied to the technical field of electric automobile aggregation. The method comprises the following steps: acquiring charging power data of a target charging station in a current dispatching period; aiming at a target charging station, charging condition prediction is carried out based on historical charging related data, and flowing vehicle data and vehicle charging conditions in the next dispatching period are obtained; carrying out power aggregation on the target charging stations based on the flowing vehicle data and the vehicle charging condition of the next dispatching period to obtain the aggregate power of the target charging stations of the next dispatching period; determining charging power data of a target charging station in a next dispatching period based on a power association relationship between the current dispatching period and the next dispatching period of the target charging station; and determining the power regulation range of the next scheduling period based on the charging power data of the next scheduling period, and then carrying out power regulation and control of the power distribution network in the next scheduling period. The method solves the problem of low control accuracy of the operation of the power distribution network of the electric automobile network access.

Description

Power control method and system for distribution network based on charging station power aggregation

Technical Field

The present invention relates to the technical field of electric vehicle aggregation, and in particular to a power control method and system for a distribution network based on charging station power aggregation.

Background Art

With the gradual advancement of vehicle-to-grid (V2G) technology, the energy storage potential of electric vehicles has been explored. Electric vehicles can be charged as loads or discharged as power sources. They have two-way interaction capabilities with the power grid and can be regarded as mobile energy storage devices for distribution networks to reduce investment in fixed energy storage. However, due to the mobility of electric vehicles and the uncertainty of charging behavior, it is difficult to regulate the distribution network. How to achieve accurate regulation of the distribution network with electric vehicles connected to the grid to improve the stability of the distribution network operation has become an urgent problem to be solved.

Summary of the invention

In order to overcome the problem of low accuracy of distribution network control for electric vehicles, the present invention provides a distribution network power control method based on charging station power aggregation, the method comprising:

Obtain charging power data of the target charging station during the current scheduling period;

For the target charging station, the charging status is predicted based on the historical charging data, and the flow vehicle data and vehicle charging status of the next scheduling period are obtained;

Based on the mobile vehicle data and vehicle charging status of the next scheduling period, the target charging station is aggregated to obtain the aggregated power corresponding to the target charging station in the next scheduling period;

Based on the power correlation relationship between the target charging station in the current scheduling period and the next scheduling period, the charging power data of the target charging station in the next scheduling period is determined by using the charging power data of the current scheduling period and the aggregate power corresponding to the next scheduling period;

The power regulation range of the next scheduling period is determined based on the charging power data of the next scheduling period, and the power regulation of the distribution network in the next scheduling period is performed based on the power regulation range.

Optionally, the charging status prediction based on historical charging-related data to obtain the flow vehicle data and vehicle charging status in the next scheduling period includes:

Obtain the influencing factor data of the charging vehicle flow of the target charging station during the historical scheduling period and the historical vehicle flow data and historical charging status in the target charging station;

Based on the influencing factor data, the historical vehicle flow data and historical charging conditions and the charging status prediction model, the flow vehicle data and vehicle charging conditions of the target charging station in several future scheduling periods are predicted, and the several future scheduling periods include the next scheduling period; the charging status prediction model is obtained by training the long short-term memory neural network based on historical data.

Optionally, the mobile vehicle data includes inbound vehicles and outbound vehicles in the next scheduling period, the vehicle charging status includes the remaining power of the inbound vehicles and the outbound vehicles and the vehicle charging power of the inbound vehicles and the outbound vehicles, and the power aggregation of the target charging station based on the mobile vehicle data and the vehicle charging status in the next scheduling period to obtain the aggregated power corresponding to the target charging station in the next scheduling period includes:

Based on the remaining power of the inbound vehicle and the outbound vehicle, the inbound vehicle and the outbound vehicle are divided into sections respectively;

For the incoming and outgoing vehicles in each section, the charging power of the vehicles in the section is aggregated within the section to obtain the initial aggregated power of the incoming vehicles and the initial aggregated power of the outgoing vehicles corresponding to each section;

Based on the number of inbound vehicles and outbound vehicles in each section, the initial aggregated power of each section is aggregated between sections to obtain the aggregated power of inbound vehicles and the aggregated power of outbound vehicles of the target charging station in the next scheduling period.

Optionally, the calculation formulas for the initial gathering power of the incoming vehicle and the initial gathering power of the outgoing vehicle are as follows:

in, represents the initial power of incoming vehicles in the i-th section in the k+1th scheduling period, represents the initial aggregate power of outbound vehicles in the i-th section in the k+1-th scheduling period, represents the charging power of vehicle m entering the station in the i-th section of the k+1-th scheduling period, represents the number of vehicles entering the station in the i-th section in the k+1-th scheduling period, represents the charging power of outbound vehicle n in the i-th section of the k+1-th scheduling period, It represents the number of outgoing vehicles in the i-th section in the k+1-th scheduling period.

Optionally, the charging power data includes the charging power of each electric vehicle in the target charging station and the maximum charging power of each charging pile in the target charging station, and the method further includes:

The charging power of each electric vehicle and the maximum charging power of each charging pile are respectively aggregated within the target charging station to obtain the aggregated power and maximum aggregated charging power of the target charging station in the current scheduling period.

Optionally, the vehicle charging status includes the identification of charging piles connected to inbound vehicles and outbound vehicles, and the use of the charging power data of the current scheduling period and the aggregate power corresponding to the next scheduling period to determine the charging power data of the target charging station in the next scheduling period includes:

Determine the total charging power of the target charging station in the next scheduling period based on the aggregate power of the target charging station in the current scheduling period and the aggregate power of the incoming vehicles in the next scheduling period;

Determine the charging power of the target charging station in the next scheduling period based on the total charging power of the target charging station in the next scheduling period and the aggregate power of the outbound vehicles in the next scheduling period;

The maximum charging power of the target charging station in the next scheduling period is determined based on the maximum aggregate charging power of the target charging station in the current scheduling period and the maximum aggregate charging power corresponding to the incoming vehicles and the outgoing vehicles in the next scheduling period. The maximum aggregate charging power corresponding to the incoming vehicles and the outgoing vehicles is determined based on the charging pile identifiers connected to the incoming vehicles and the outgoing vehicles.

Optionally, the power adjustment range includes a power increase range and a power decrease range, and determining the power adjustment range of the next scheduling period based on the charging power data of the next scheduling period includes:

Determine the power increase range of the target charging station in the next scheduling period based on the maximum charging power of the target charging station in the next scheduling period and the charging power of the target charging station in the next scheduling period;

The charging power of the target charging station in the next scheduling period is used as the power reduction range of the target charging station in the next scheduling period.

Optionally, the power regulation of the distribution network in the next scheduling period based on the power regulation range includes:

Incorporating the target charging station into the distribution network as an energy storage node;

Based on the power regulation range of the energy storage node, the power distribution network is regulated.

On the other hand, the present invention also provides a power control system for a distribution network based on charging station power aggregation, comprising:

An acquisition module is used to obtain charging power data of a target charging station during a current scheduling period;

The prediction module is used to predict the charging status of the target charging station based on the historical charging related data, and obtain the mobile vehicle data and vehicle charging status of the next scheduling period;

An aggregation module is used to aggregate the power of the target charging station based on the mobile vehicle data and vehicle charging status of the next scheduling period, and obtain the aggregated power corresponding to the target charging station in the next scheduling period;

An association calculation module, for calculating the charging power data of the target charging station in the next scheduling period based on the power association relationship between the target charging station in the current scheduling period and the next scheduling period, using the charging power data of the current scheduling period and the aggregate power corresponding to the next scheduling period;

The power regulation module is used to determine the power regulation range of the next scheduling period based on the charging power data of the next scheduling period, and to perform power regulation on the target charging station in the next scheduling period based on the power regulation range.

On the other hand, the present invention also provides an electronic device, comprising: at least one processor and a memory; the memory and the processor are connected via a bus;

The memory is used to store one or more programs;

When the one or more programs are executed by the at least one processor, any one of the above-mentioned methods for power regulation of the distribution network based on charging station power aggregation is implemented.

On the other hand, the present invention also provides a readable storage medium having an execution program stored thereon, and when the execution program is executed, any one of the above-mentioned methods for power control of the distribution network based on charging station power aggregation is implemented.

Compared with the prior art, the present invention has the following beneficial effects:

The present invention provides a power control method for a distribution network based on power aggregation of charging stations. On the one hand, by aggregating the power of individual electric vehicles in a fast charging station, the mobility characteristics of the electric vehicles are converted into fixed characteristics of the charging station, thereby realizing the quantification of mobile resources and facilitating the control of the distribution network after the electric vehicles are connected to the network; on the other hand, considering the changes in the number of electric vehicles in different scheduling periods, the power adjustable range of the fast charging station is predicted, which can improve the prediction accuracy of flexible resources, improve the accuracy of distribution network control, and thus improve the stability of distribution network operation.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a schematic diagram of a flow chart of a power distribution network power control method based on charging station power aggregation of the present invention;

FIG2 is a schematic diagram of the structure of a power distribution network power control system based on charging station power aggregation according to the present invention;

FIG. 3 is a schematic structural diagram of an electronic device of the present invention.

DETAILED DESCRIPTION

As the contradiction between energy supply and demand continues to increase, electric vehicles, as a green travel mode, have received widespread attention, giving full play to the role of electric vehicles in energy conservation and emission reduction to alleviate energy pressure. Electric vehicles provide strong support for the development of the new energy vehicle industry. At present, the construction of electric vehicles and related infrastructure has begun to take shape, but with the continuous increase in the number of electric vehicles, the impact of their charging behavior on the power system has become an important issue that must be considered. As an uncertain load, the law of change of electric vehicles is subject to the user's travel mode and the state of charge of electric vehicles. The randomness of their charging has both spatial and temporal characteristics.

With the in-depth study of vehicle-to-grid (V2G) technology, the energy storage potential of electric vehicles has been further explored. Electric vehicles can be charged as loads or discharged as power sources, and have two-way interaction capabilities with the power grid. They can be regarded as mobile energy storage devices for distribution networks to reduce the investment in fixed energy storage. However, due to the mobility of electric vehicles and the uncertainty of charging behavior, it is difficult to regulate the distribution network. How to achieve accurate regulation of the distribution network for electric vehicles to improve the stability of distribution network operation has become an urgent problem to be solved. By developing electric vehicle aggregation regulation technology, the excellent characteristics of electric vehicle mobile energy storage can be fully utilized, which is of great significance to ensure the stable operation of the power grid, improve the capacity of renewable energy consumption, smooth load fluctuations, and ensure the reliability and economy of distribution network operation.

Based on this, an embodiment of the present invention provides a power control method and system for a distribution network based on charging station power aggregation. The specific implementation of the present invention is further described in detail below with reference to the accompanying drawings.

Embodiment 1:

The present invention provides a power distribution network power control method based on charging station power aggregation, the flow chart of which is shown in FIG1 , and includes:

Step S110, obtaining charging power data of the target charging station during the current scheduling period;

Step S120, for the target charging station, a charging status prediction is performed based on historical charging related data to obtain the flow vehicle data and vehicle charging status for the next scheduling period;

Step S130, performing power aggregation on the target charging station based on the mobile vehicle data and vehicle charging status of the next scheduling period to obtain the aggregated power corresponding to the target charging station in the next scheduling period;

Step S140, based on the power correlation relationship between the target charging station in the current scheduling period and the next scheduling period, the charging power data of the target charging station in the next scheduling period is determined by using the charging power data of the current scheduling period and the aggregate power corresponding to the next scheduling period;

Step S150: determining a power regulation range for the next scheduling period based on the charging power data for the next scheduling period, and performing power regulation of the distribution network in the next scheduling period based on the power regulation range.

In this embodiment, the target charging station can be any charging station connected to the power grid (such as a fast charging station). When the electric vehicle is charging, the system can obtain relevant information about the electric vehicle. This embodiment achieves mobile resource quantification by aggregating the power of individual electric vehicles in the target charging station; considering the changes in the number of electric vehicles in different scheduling cycles, the power adjustable range of the target charging station is predicted, which can improve the prediction accuracy of flexible resources and thus improve the accuracy of distribution network regulation.

In one implementation, the future charging status of the target charging station can be predicted based on the neural network model. For example, the charging status prediction based on the historical charging related data in the above step S120 is performed to obtain the flow vehicle data and vehicle charging status of the next scheduling period, including the following process:

Obtain the influencing factor data of the charging vehicle flow of the target charging station during the historical scheduling period and the historical vehicle flow data and historical charging status in the target charging station;

Based on the influencing factor data, historical vehicle flow data, historical charging conditions and charging status prediction model, the flow vehicle data and vehicle charging conditions of the target charging station in several future scheduling periods are predicted; the charging status prediction model is obtained by training the long short-term memory neural network based on historical data.

In this implementation, the historical scheduling period can be a fixed time range before the current time point, for example, several days before the current time point. The influencing factor data may include weather, season, charging pile type, charging station location, electric vehicle flow in the area where the charging station is located, etc. The historical vehicle flow data refers to the electric vehicle flow data in the target charging station during the historical scheduling period, which may specifically include inbound vehicle information (vehicle type, vehicle license plate, etc.) and outbound vehicle information (vehicle type, vehicle license plate, etc.); the historical charging situation includes the charging pile information (charging pile rated charging power, charging pile identification, etc.) connected to the vehicle in the target charging station during the historical scheduling period, the remaining power of the vehicle and the charging power of the vehicle.

In this implementation, the charging status prediction model needs to be obtained through historical data training. The historical data can be data from the past few months or previous years. The range of historical data can be adjusted according to the model training effect. The historical data also includes the influencing factor data of charging traffic, traffic data and charging status in the selected historical period. The charging status prediction model can be a network model with time series characteristics, such as a model based on a long short-term memory network (LSTM). The training process can include the following steps:

The first step is to preprocess the historical data.

The historical data may be preprocessed to facilitate subsequent processing. For example, the preprocessing may include data cleaning and data normalization. Data cleaning is used to remove erroneous data or duplicate data, and data normalization is used to normalize the data to between [0, 1].

The second step is data vectorization;

Non-continuous data (such as charging pile type, weather, season, etc.) can be one-hot encoded (i.e., unique hot encoding) to generate corresponding vectors; continuous data can be arranged in chronological order, and finally different physical quantities can be spliced in order to form input data. For example, the charging pile type is a categorical feature, which can be converted into a numerical form acceptable to the model using one-hot encoding; weather is a continuous feature and is standardized; seasonal data is also a categorical variable, and each season can be converted into a one-hot encoded vector.

The third step is model training.

The input data is fed into the input layer of the model, processed by the stacked multi-layer LSTM layers, and finally outputs the prediction results through the fully connected layer. The LSTM layer includes a forget gate, an input gate, and an output gate. The forget gate is used to determine what information is forgotten from the cell state; the input gate is used to update the cell state, determine important new information and retain it in the network's memory; the output gate is used to determine the output based on the current cell state. The training process can optimize parameters through the back-propagation gradient descent algorithm to minimize the error between the predicted value and the true value; the Adam (adaptive moment estimation) optimizer is used to accelerate the convergence process.

In the prediction process, the data of several scheduling periods before the current scheduling period in a day can be used to predict the mobile vehicles and their charging conditions in several scheduling periods after the current scheduling moment, and several future scheduling periods include the next scheduling period. For example, the data of 10 scheduling periods before the current time point can be used to predict the data of 3 scheduling periods after the current time point to adapt to the situation of shorter scheduling cycles.

After obtaining the mobile vehicle data and vehicle charging conditions of several future scheduling periods, the charging power conditions of the next scheduling period can be determined based on the correlation between adjacent scheduling periods. The above S130 performs power aggregation on the target charging station based on the mobile vehicle data and vehicle charging conditions of the next scheduling period to obtain the aggregated power corresponding to the target charging station in the next scheduling period. The implementation process is as follows:

Based on the remaining power of incoming and outgoing vehicles, the incoming and outgoing vehicles are divided into sections respectively;

For the incoming and outgoing vehicles in each section, the charging power of the vehicles in the section is aggregated within the section to obtain the initial aggregated power of the incoming vehicles and the initial aggregated power of the outgoing vehicles corresponding to each section;

Based on the number of inbound and outbound vehicles in each section, the initial aggregated power of each section is aggregated between sections to obtain the aggregated power of inbound vehicles and the aggregated power of outbound vehicles at the target charging station in the next scheduling period.

In this implementation, since the charging behavior is related to the remaining power of the vehicle, the vehicle can be divided into sections according to the remaining power, and power aggregation can be performed by section to improve the effect of power aggregation. For example, the incoming and outgoing vehicles are divided into 10 sections [0, 10%], (10%, 20%], ..., (90, 100%], respectively, and the number of electric vehicles in each section is counted. Each section is aggregated within the section. The aggregation within the section can be the mean, mode, or median within the section. Finally, the initial aggregation results within the section are aggregated between sections to obtain the aggregated power of the incoming and outgoing vehicles in the target charging station. The aggregation between sections can be the summation or weighted summation of the initial aggregation results of different sections.

Exemplarily, the aggregate power of inbound vehicles and outbound vehicles may be determined by the following formula:

First, the inbound and outbound vehicles are aggregated in the segment, as shown in the following formula:

in, represents the initial power of incoming vehicles in the i-th section in the k+1th scheduling period, represents the initial aggregate power of outbound vehicles in the i-th section in the k+1-th scheduling period, represents the charging power of vehicle m entering the station in the i-th section of the k+1-th scheduling period, represents the number of vehicles entering the station in the i-th section in the k+1-th scheduling period, represents the charging power of outbound vehicle n in the i-th section of the k+1-th scheduling period, It represents the number of outgoing vehicles in the i-th section in the k+1-th scheduling period.

Then, the initial aggregate power of each section is aggregated among sections, as shown in the following formula:

in, represents the aggregate power of vehicles entering the station in the k+1th scheduling period, represents the aggregate power of outgoing vehicles in the k+1th scheduling period.

Similarly, the power of electric vehicles in the current scheduling period of the target charging station can be aggregated through intra-segment aggregation and inter-segment aggregation to obtain the aggregated power of the target charging station in the current scheduling period. The specific process is as follows:

in, represents the initial power of electric vehicles in the i-th section in the k-th scheduling period, represents the charging power of electric vehicle l in the i-th section in the k-th scheduling period, represents the number of electric vehicles charged at the target charging station in the kth scheduling period, represents the aggregate power of the target charging station in the kth scheduling period, It represents the number of electric vehicles in the i-th section in the k-th scheduling period.

Furthermore, in order to obtain the adjustable range of charging power of the target charging station in each scheduling period, it is also necessary to determine the maximum charging power of the target charging station in each scheduling period. Specifically, the maximum charging power of the current scheduling period can be the maximum output power of the charging piles connected to each electric vehicle in the aggregated target charging station, as shown in the following formula:

in, represents the maximum aggregate charging power of the target charging station in the kth scheduling period, It represents the maximum output power of the charging pile connected to electric vehicle l in the kth scheduling period, and N represents the number of electric vehicles in the target charging station in the kth scheduling period.

Similarly, the charging power data of the next scheduling period needs to be determined. In the above step S140, the charging power data of the current scheduling period and the aggregate power corresponding to the next scheduling period are used to determine the charging power data of the target charging station in the next scheduling period. The charging power data may include the following process:

Determine the total charging power of the target charging station in the next scheduling period based on the aggregate power of the target charging station in the current scheduling period and the aggregate power of the incoming vehicles in the next scheduling period;

Determine the charging power of the target charging station in the next scheduling period based on the total charging power of the target charging station in the next scheduling period and the aggregate power of the outbound vehicles in the next scheduling period;

Based on the maximum aggregate charging power of the target charging station in the current scheduling period and the maximum aggregate charging power corresponding to the incoming and outgoing vehicles in the next scheduling period, the maximum charging power of the target charging station in the next scheduling period is determined. The maximum aggregate charging power corresponding to the incoming and outgoing vehicles is determined based on the charging pile identifiers connected to the incoming and outgoing vehicles.

In this implementation, the vehicle charging status of the next scheduling period may include the charging pile identifications connected to the incoming vehicles and the outgoing vehicles. The charging piles connected to each incoming vehicle and the outgoing vehicle can be determined based on the charging pile identifications connected to the incoming vehicles and the outgoing vehicles. The maximum output power of the charging pile is then used as the maximum charging power of the corresponding vehicle. The maximum charging power of all vehicles in the station is aggregated, and the maximum aggregate charging power of the target charging station in the current scheduling period and the maximum aggregate charging power corresponding to the incoming vehicles and the outgoing vehicles in the next scheduling period can be obtained.

The maximum aggregate charging power of the target charging station in the next scheduling period is calculated as follows:

in, represents the maximum aggregate charging power of the target charging station in the k+1th scheduling period, represents the maximum aggregate charging power of the target charging station in the kth scheduling period, represents the maximum charging power of vehicle m entering the station during the k+1th scheduling period, represents the number of vehicles entering the station during the k+1th scheduling period, represents the maximum charging power of vehicle l leaving the station during the k+1th scheduling period, Represents the number of vehicles leaving the station in the k+1th scheduling period.

The charging power of the target charging station in the next scheduling period is calculated as follows:

in, represents the charging power of the target charging station in the k+1th scheduling period, represents the charging power of the target charging station in the kth scheduling period, represents the aggregate power of vehicles entering the target charging station in the k+1th scheduling period, represents the aggregate power of vehicles leaving the target charging station in the k+1th scheduling period.

In another implementation, determining the power adjustment range of the next scheduling period based on the charging power data of the next scheduling period in step S150 may include the following steps:

Determine the power increase range of the target charging station in the next scheduling period based on the maximum charging power of the target charging station in the next scheduling period and the charging power of the target charging station in the next scheduling period;

The charging power of the target charging station in the next scheduling period is used as the power reduction range of the target charging station in the next scheduling period.

In this implementation, the power adjustment range may include a power increase range and a power decrease range. The power increase range of the next scheduling period may be determined by subtracting the maximum charging power of the target charging station in the next scheduling period from the charging power of the target charging station in the next scheduling period. The formula is as follows:

in, It represents the power increase range of the target charging station in the k+1th scheduling period.

The charging power of the target charging station in the next scheduling period can be used as the power reduction range of the target charging station in the next scheduling period, that is, It represents the power reduction range of the target charging station in the k+1th scheduling period.

After determining the power increase range and the power decrease range of the target charging station in the next scheduling period, the power regulation of the distribution network in the next scheduling period based on the power regulation range in step S150 specifically includes the following processes:

Incorporate the target charging station into the distribution network as an energy storage node;

Based on the power regulation range of the energy storage node, the power of the distribution network is regulated.

In this implementation, the target charging station can be incorporated into the distribution network as an energy storage node and/or energy consumption node, and then the power of the distribution network can be regulated based on the power adjustment range of the energy storage node to improve the accuracy of distribution network regulation and better enable electric vehicle clusters to participate in the regulation of the power grid.

The present invention is described below with a specific embodiment, which specifically includes the following steps:

1) Assume that the kth scheduling period is expressed as [t _k ,t _k +T] (scheduling period T is 15 minutes), count the number of electric vehicles N in the fast charging station, and the maximum charging power of a single charging pile is _tk represents the starting time of the kth scheduling cycle, and T represents the duration of a scheduling cycle.

2) Randomly select N/5 electric vehicles in the fast charging station, divide the SOC (State Of Charge, i.e. the remaining battery power ratio) of the electric vehicles into 10 segments [0, 10%], (10%, 20%], ..., (90, 100%], and count the SOC of each electric vehicle and the number of electric vehicles in each SOC segment. The charging power of electric vehicle l in the i-th SOC section is

3) Use the trained LSTM neural network model (charging status prediction model) to predict the flow vehicle data and vehicle charging status in the fast charging station for several future scheduling periods. The predicted data includes: the number of new electric vehicles entering the station at time t _k+1 Number of electric vehicles leaving the station Charging power of new electric vehicles m at fast charging stations and the charging pile to which it is connected, the charging power of the electric vehicle n leaving the charging station and the charging station it is connected to.

4) Randomly select electric vehicles from the newly entering and leaving the station The number of electric vehicles entering and leaving the station is counted in each SOC segment. Based on the charging pile connected to the new electric vehicle m entering the fast charging station, the maximum charging power corresponding to the electric vehicle is determined as follows: Based on the charging pile connected to the electric vehicle n leaving the fast charging station, the maximum charging power corresponding to the electric vehicle is determined as

5) According to formula (1), the average charging power of electric vehicles in SOC segment i in the kth scheduling period [t _k ,t _k +T] of the fast charging station is calculated: The average charging power of each section is used to replace the charging power of the electric vehicles in that section.

6) According to formula (2), calculate the charging power of N electric vehicles in the kth scheduling period [t _k ,t _k +T] of the fast charging station As follows:

7) According to formula (3), calculate the number of N/5 electric vehicles and the maximum charging power in the kth scheduling period [t _k ,t _k +T] of the fast charging station

in, It represents the maximum charging power of the charging pile connected to the electric vehicle s in the kth scheduling period of the fast charging station.

8) According to equations (5) and (6), the average charging power of the new electric vehicle entering the fast charging station at SOC segment i at time _tk+1 is calculated respectively: and average charging power of off-site electric vehicles The average charging power of electric vehicles in each SOC section is used to replace the charging power of electric vehicles in that section in the fast charging station.

9) According to equations (7) and (8), the charging power of the new electric vehicle entering the fast charging station at time _tk+1 is calculated respectively: and charging power of off-station electric vehicles

Among them, ΔN _e,i represents the total number of new electric vehicles entering the station at time t _k+1 , and ΔN _l,i represents the total number of electric vehicles leaving the station at time t _k+1 .

10) According to formula (9), calculate the charging power of the fast charging station in the k+1th scheduling period [t _k+1 ,t _k+1 +T]

11) According to formula (10), calculate the maximum charging power of the fast charging station in the k+1th scheduling period [t _k+1 ,t _k+1 +T]

12) According to formula (11), calculate the power increase range of the fast charging station in the k+1th scheduling period [t _k+1 ,t _k+1 +T] That is, the maximum charging power of the fast charging station in the k+1th scheduling period With charging power The difference.

13) According to formula (12), calculate the power reduction range of the fast charging station in the k+1th scheduling period [t _k+1 ,t _k+1 +T]

The embodiment of the present invention first aggregates the charging power and maximum charging power of the electric vehicle cluster in the current fast charging station according to the charging power and maximum charging power of the single electric vehicle in a certain scheduling cycle, and then obtains the charging power and maximum charging power in the next scheduling cycle by considering the changes in the charging power and maximum charging power due to the changes in the number of electric vehicles entering and leaving the fast charging station; then, the power increase range and power decrease range of the fast charging station in the next scheduling period are calculated according to the charging power and maximum charging power of the fast charging station in the current scheduling cycle, so as to obtain the adjustable power boundary of the flexible resources of the fast charging station; considering the changes in the number of electric vehicles in the fast charging station resulting in the changes in the charging power of the fast charging station, the charging power of the fast charging station is obtained by aggregating the single electric vehicles in the same time dimension, and under the condition that the number of electric vehicles participating in the aggregation remains unchanged, the charging power of the electric vehicle cluster has the same continuous change characteristics as conventional energy storage; as the number of electric vehicles participating in the aggregation increases or decreases, the charging power of the fast charging station will also undergo sudden changes. The embodiment of the present invention aggregates the power of the electric vehicle cluster in the fast charging station, considers the change in the number of electric vehicles in the fast charging station in each scheduling cycle, calculates the power adjustable boundary of the fast charging station, and determines the impact of the electric vehicle cluster on the power grid and participates in the power grid regulation strategy.

Embodiment 2:

Based on the same inventive concept, the present invention also provides a power control system for a distribution network based on power aggregation of charging stations, the structural schematic diagram of which is shown in FIG2 and includes:

An acquisition module 210 is used to acquire charging power data of a target charging station during a current scheduling period;

The prediction module 220 is used to predict the charging status of the target charging station based on the historical charging related data, and obtain the mobile vehicle data and vehicle charging status of the next scheduling period;

Aggregation module 230, used to aggregate the power of the target charging station based on the mobile vehicle data and vehicle charging status of the next scheduling period, and obtain the aggregated power corresponding to the target charging station in the next scheduling period;

The correlation calculation module 240 is used to calculate the charging power data of the target charging station in the next scheduling period based on the power correlation relationship between the target charging station in the current scheduling period and the next scheduling period, using the charging power data of the current scheduling period and the aggregate power corresponding to the next scheduling period;

The power adjustment module 250 is used to determine the power adjustment range of the next scheduling period based on the charging power data of the next scheduling period, and adjust the power of the target charging station in the next scheduling period based on the power adjustment range.

In a possible implementation, the prediction module 220 is further configured to:

Obtain the influencing factor data of the charging vehicle flow of the target charging station during the historical scheduling period and the historical vehicle flow data and historical charging status in the target charging station;

Based on the influencing factor data, historical vehicle flow data, historical charging conditions and the charging status prediction model, the flow vehicle data and vehicle charging conditions of the target charging station in several future scheduling periods are predicted. The future several scheduling periods include the next scheduling period. The charging status prediction model is obtained by training the long short-term memory neural network based on historical data.

In a possible implementation, the mobile vehicle data includes inbound vehicles and outbound vehicles in the next scheduling period, and the vehicle charging status includes the remaining power of the inbound vehicles and the outbound vehicles and the vehicle charging power of the inbound vehicles and the outbound vehicles. The aggregation module 230 is further used to:

Based on the remaining power of incoming and outgoing vehicles, the incoming and outgoing vehicles are divided into sections respectively;

For the incoming and outgoing vehicles in each section, the charging power of the vehicles in the section is aggregated in the section to obtain the initial aggregated power of the incoming vehicles and the initial aggregated power of the outgoing vehicles corresponding to each section;

Based on the number of inbound and outbound vehicles in each section, the initial aggregated power of each section is aggregated between sections to obtain the aggregated power of inbound vehicles and the aggregated power of outbound vehicles at the target charging station in the next scheduling period.

In a possible implementation manner, the calculation formulas for the initial convergence power of incoming vehicles and the initial convergence power of outgoing vehicles are as follows:

in, represents the initial power of incoming vehicles in the i-th section in the k+1th scheduling period, represents the initial aggregate power of outbound vehicles in the i-th section in the k+1-th scheduling period, represents the charging power of vehicle m entering the station in the i-th section of the k+1-th scheduling period, represents the number of vehicles entering the station in the i-th section in the k+1-th scheduling period, represents the charging power of outbound vehicle n in the i-th section of the k+1-th scheduling period, It represents the number of outgoing vehicles in the i-th section in the k+1-th scheduling period.

In a possible implementation, the charging power data includes the charging power of each electric vehicle in the target charging station and the maximum charging power of each charging pile in the target charging station, and the aggregation module is further used to:

The charging power of each electric vehicle and the maximum charging power of each charging pile are respectively aggregated within the target charging station to obtain the aggregated power and maximum aggregated charging power of the target charging station in the current scheduling period.

In a possible implementation, the vehicle charging status includes the charging pile identifiers to which the incoming vehicle and the outgoing vehicle are connected, and the association calculation module 240 is further used to:

Determine the total charging power of the target charging station in the next scheduling period based on the aggregate power of the target charging station in the current scheduling period and the aggregate power of the incoming vehicles in the next scheduling period;

Determine the charging power of the target charging station in the next scheduling period based on the total charging power of the target charging station in the next scheduling period and the aggregate power of the outbound vehicles in the next scheduling period;

Based on the maximum aggregate charging power of the target charging station in the current scheduling period and the maximum aggregate charging power corresponding to the incoming and outgoing vehicles in the next scheduling period, the maximum charging power of the target charging station in the next scheduling period is determined. The maximum aggregate charging power corresponding to the incoming and outgoing vehicles is determined based on the charging pile identifiers connected to the incoming and outgoing vehicles.

In a possible implementation manner, the power adjustment range includes a power increase range and a power decrease range, and the power adjustment module 250 is further configured to:

Determine the power increase range of the target charging station in the next scheduling period based on the maximum charging power of the target charging station in the next scheduling period and the charging power of the target charging station in the next scheduling period;

The charging power of the target charging station in the next scheduling period is used as the power reduction range of the target charging station in the next scheduling period.

In a possible implementation manner, the power regulation module 250 is further configured to:

Incorporate the target charging station into the distribution network as an energy storage node;

Based on the power regulation range of the energy storage node, the power of the distribution network is regulated.

Embodiment 3:

As shown in FIG3 , the present invention also provides an electronic device, which may be a computer device, a single-chip device, an intelligent mobile device, etc. The electronic device in this embodiment may include a processor, a memory, a transceiver component, etc. The memory, the processor, and the transceiver component are connected via a bus; the memory may be used to store an execution program, and an exemplary execution program may include instructions; the processor is used to execute the instructions stored in the memory. The memory may also be used to store data, which may be called and/or modified when executing instructions.

The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in a storage medium to implement the corresponding method flow or corresponding functions, so as to implement the steps of a distribution network power control method based on charging station power aggregation in the above embodiment.

Example 4

Based on the same inventive concept, the present invention also provides a readable storage medium, specifically an electronic device readable storage medium (Memory), which is a memory device in an electronic device for storing programs and data. It can be understood that the storage medium here can include both built-in storage media in electronic devices and, of course, extended storage media supported by electronic devices. The storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by a processor are also stored in the storage space, and these instructions can be one or more execution programs (including program codes). It should be noted that the storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk storage. The processor loads and executes one or more instructions stored in the storage medium, which can implement the steps of a power control method for a distribution network based on charging station power aggregation in the above embodiment.

Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

The present invention is described with reference to the flowchart and/or block diagram of the method, device (system), and computer program product according to the embodiment of the present invention. It should be understood that each process and/or box in the flowchart and/or block diagram, as well as the combination of the process and/or box in the flowchart and/or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one or more processes in the flowchart and/or one or more boxes in the block diagram.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device that implements the functions specified in one or more processes in the flowchart and/or one or more boxes in the block diagram.

These computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and/or one or more boxes in the block diagram.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit its protection scope. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that after reading the present invention, those skilled in the art can still make various changes, modifications or equivalent substitutions to the specific implementation methods of the application, but these changes, modifications or equivalent substitutions are all within the protection scope of the claims to be approved.

Claims (10)

1. The utility model provides a distribution network power regulation and control method based on charging station power aggregation which is characterized by comprising the following steps:

Acquiring charging power data of a target charging station in a current dispatching period;

Aiming at a target charging station, charging condition prediction is carried out based on historical charging related data, and flowing vehicle data and vehicle charging conditions in the next dispatching period are obtained;

carrying out power aggregation on the target charging stations based on the flowing vehicle data and the vehicle charging condition of the next dispatching period to obtain aggregation power corresponding to the target charging stations of the next dispatching period;

based on the power association relation of the target charging station between the current dispatching period and the next dispatching period, charging power data of the target charging station in the next dispatching period is determined by using charging power data of the current dispatching period and the aggregate power corresponding to the next dispatching period;

and determining a power regulation range of the next scheduling period based on the charging power data of the next scheduling period, and regulating and controlling the power of the power distribution network in the next scheduling period based on the power regulation range.

2. The method of claim 1, wherein the predicting the charging condition based on the historical charging related data to obtain the mobile vehicle data and the vehicle charging condition for the next dispatch period comprises:

acquiring influence factor data of charging traffic flow of a target charging station in a historical dispatching period and historical traffic flow data and historical charging conditions in the target charging station;

Based on the influence factor data, the historical traffic flow data, the historical charging situation and the charging situation prediction model, predicting the flowing vehicle data and the vehicle charging situation of the target charging station in a plurality of scheduling periods in the future, wherein the plurality of scheduling periods in the future comprise the next scheduling period; the charge situation prediction model is obtained by training the long-term and short-term memory neural network based on historical data.

3. The method of claim 2, wherein the mobile vehicle data includes an inbound vehicle and an outbound vehicle for a next dispatch period, the vehicle charging condition includes remaining amounts of the inbound vehicle and the outbound vehicle and vehicle charging powers of the inbound vehicle and the outbound vehicle, the power aggregating the target charging stations based on the mobile vehicle data and the vehicle charging condition for the next dispatch period, and obtaining an aggregate power corresponding to the target charging stations for the next dispatch period, comprising:

Dividing the inbound vehicle and the outbound vehicle into sections based on the residual electric quantity of the inbound vehicle and the outbound vehicle respectively;

for the inbound vehicles and the outbound vehicles of each section, respectively carrying out intra-section aggregation on the vehicle charging power in the section to obtain the initial aggregation power of the inbound vehicles and the initial aggregation power of the outbound vehicles corresponding to each section;

and carrying out inter-zone aggregation on the initial aggregation power of each zone based on the number of the inbound vehicles and the outbound vehicles in each zone, and obtaining the aggregation power of the inbound vehicles and the aggregation power of the outbound vehicles of the target charging station in the next dispatching period.

4. A method according to claim 3, wherein the calculation formula of the incoming vehicle prime mover and the outgoing vehicle prime mover is as follows:

wherein, Represents the inbound vehicle prime power for the ith zone in the k +1 schedule period,Represents the outbound vehicle prime power for the ith zone in the k +1 scheduling period,Representing the charging power of the inbound vehicle m in the (k + 1) th schedule period i-th zone,Indicating the number of inbound vehicles in the ith zone of the k +1 schedule period,Representing the charge power of the outbound vehicle n in the (k + 1) schedule period zone i,Indicating the number of outbound vehicles in the ith zone of the k+1th schedule period.

5. The method of claim 3, wherein the charging power data includes a charging power of each electric vehicle within the target charging station and a maximum charging power of each charging peg within the target charging station, the method further comprising:

And respectively carrying out power aggregation in the target charging stations on the charging power of each electric automobile and the maximum charging power of each charging pile to obtain the aggregate power and the maximum aggregate charging power of the target charging stations in the current dispatching period.

6. The method of claim 5, wherein the vehicle charging condition includes a charging post identifier of an inbound vehicle and an outbound vehicle connection, and wherein determining charging power data of a target charging station in a next dispatch period using charging power data of a current dispatch period and aggregate power corresponding to the next dispatch period includes:

determining the total charging power of the target charging station in the next dispatching period based on the aggregate power of the target charging station in the current dispatching period and the aggregate power of the inbound vehicle in the next dispatching period;

determining the charging power of the target charging station in the next dispatching period based on the total charging power of the target charging station in the next dispatching period and the aggregate power of the outbound vehicles in the next dispatching period;

And determining the maximum charging power of the target charging station in the next dispatching period based on the maximum aggregate charging power of the target charging station in the current dispatching period and the maximum aggregate charging power corresponding to the inbound vehicle and the outbound vehicle in the next dispatching period, wherein the maximum aggregate charging power corresponding to the inbound vehicle and the outbound vehicle is determined based on charging pile identifiers connected with the inbound vehicle and the outbound vehicle.

7. The method of claim 6, wherein the power adjustment range comprises a power up-regulation range and a power down-regulation range, wherein the determining the power adjustment range for the next scheduling period based on the charging power data for the next scheduling period comprises:

Determining a power up-regulation range of the target charging station in the next dispatching period based on the maximum charging power of the target charging station in the next dispatching period and the charging power of the target charging station in the next dispatching period;

And taking the charging power of the target charging station in the next dispatching period as the power down-regulating range of the target charging station in the next dispatching period.

8. The method according to any one of claims 1-7, wherein said performing power regulation of the distribution network in a next scheduling period based on said power regulation range comprises:

Incorporating the target charging station as an energy storage node into the power distribution network;

and carrying out power regulation and control on the power distribution network based on the power regulation range of the energy storage node.

9. A charging station power conditioning system based on power aggregation, comprising:

the acquisition module is used for acquiring charging power data of the target charging station in the current dispatching period;

The prediction module is used for predicting the charging condition of the target charging station based on the historical charging related data to obtain the flowing vehicle data and the vehicle charging condition of the next dispatching period;

The aggregation module is used for carrying out power aggregation on the target charging stations based on the flowing vehicle data and the vehicle charging condition of the next dispatching period to obtain the aggregation power corresponding to the target charging stations of the next dispatching period;

The association calculation module is used for calculating the charging power data of the target charging station in the next dispatching period by utilizing the charging power data of the current dispatching period and the aggregation power corresponding to the next dispatching period based on the power association relation of the target charging station in the current dispatching period and the next dispatching period;

and the power adjusting module is used for determining the power adjusting range of the next dispatching period based on the charging power data of the next dispatching period and adjusting the power of the target charging station in the next dispatching period based on the power adjusting range.

10. An electronic device, comprising: at least one processor and memory; the memory is connected with the processor through a bus;

the memory is used for storing one or more programs;

The method of any one of claims 1 to 8 is implemented when the one or more programs are executed by the at least one processor.