A power management method for an energy storage type intelligent microgrid used for frequency modulation and peak shaving

Abstract

The present invention relates to a power management method for a frequency-modulated and peak-shaved energy storage type intelligent microgrid, and relates to the technical field of power grid connection, including: obtaining the electricity consumption demands of users at the first node, the second node, up to the Nth node; obtaining the time series information of the pre-allocated output power of the large power grid in the first substation area and inputting it into the power grid frequency trend prediction model to output the first power grid frequency trend prediction result; when deviating from the reference power grid frequency, configuring the grid-connected output power of the energy storage type intelligent microgrid at the first node, the grid-connected output power of the energy storage type intelligent microgrid at the second node, up to the grid-connected output power of the energy storage type intelligent microgrid at the Mth node; obtaining the second power grid frequency trend prediction result; when not deviating from the reference power grid frequency, performing power grid connection management. It solves the technical problem in the prior art that due to using real-time monitoring of the power grid frequency for frequency modulation and peak shaving control, there is a large time delay and it is impossible to respond to the change of the power grid frequency in a timely manner.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid connection, and particularly to a power management method for an energy storage type intelligent microgrid for frequency modulation and peak shaving. Background Art

[0002] In modern power systems, as a new power supply and management method, intelligent microgrids have received extensive attention due to their flexibility and reliability. Intelligent microgrids can achieve self-control, protection, and management, and can operate in parallel with the external power grid or operate in island mode when the external power grid is unavailable.

[0003] After an intelligent microgrid is connected to the large power grid, it can monitor the grid frequency and peak value in real time, so as to achieve adaptive frequency modulation and peak shaving. However, the traditional frequency modulation and peak shaving strategy of intelligent microgrids depends on real-time monitoring of the deviation of the grid frequency. This strategy has a time delay and cannot respond to the change of the grid frequency in time, resulting in an unsatisfactory effect of frequency modulation and peak shaving, and affecting the stability and power supply quality of the power grid. Summary of the Invention

[0004] In view of the technical problem in the prior art that the use of real-time monitoring of the grid frequency for frequency modulation and peak shaving control results in a large time delay and inability to respond to the change of the grid frequency in time, the present invention provides a power management method for an energy storage type intelligent microgrid for frequency modulation and peak shaving to solve this problem.

[0005] The technical solution of the present invention to solve the above technical problems is as follows:

[0006] The present invention provides a power management method for an energy storage type intelligent microgrid for frequency modulation and peak shaving, including: traversing the user distribution nodes in the first substation area for inertial power consumption analysis to obtain the power consumption of users in the first node, the power consumption of users in the second node until the power consumption of users in the Nth node; obtaining the time series information of the pre-allocated output power of the large power grid in the first substation area; inputting the time series information of the pre-allocated output power of the large power grid in the first substation area, the power consumption of users in the first node, the power consumption of users in the second node until the power consumption of users in the Nth node into the power grid frequency trend prediction model, and outputting the first power grid frequency trend prediction result; when the first power grid frequency trend prediction result deviates from the reference power grid frequency, configuring the output power of the energy storage type intelligent microgrid incorporated into the nodes in the first substation area, such as the output power of the energy storage type intelligent microgrid incorporated into the first node, the output power of the energy storage type intelligent microgrid incorporated into the second node until the output power of the energy storage type intelligent microgrid incorporated into the Mth node; inputting the time series information of the pre-allocated output power of the large power grid in the first substation area, the output power of the energy storage type intelligent microgrid incorporated into the first node, the output power of the energy storage type intelligent microgrid incorporated into the second node until the output power of the energy storage type intelligent microgrid incorporated into the Mth node, and the power consumption of users in the first node, the power consumption of users in the second node until the power consumption of users in the Nth node into the power grid frequency trend prediction model, and outputting the second power grid frequency trend prediction result; when the second power grid frequency trend prediction result does not deviate from the reference power grid frequency, performing power grid connection management on the energy storage type intelligent microgrid incorporated into the nodes according to the output power of the energy storage type intelligent microgrid incorporated into the first node, the output power of the energy storage type intelligent microgrid incorporated into the second node until the output power of the energy storage type intelligent microgrid incorporated into the Mth node.

[0007] The beneficial effects of the present invention are as follows: By traversing the user distribution nodes for inertial power consumption analysis, the power consumption demand on the user side can be predicted in advance; combining the time series information of the pre-allocated output power of the large power grid and the power consumption of users on the user side, and using the power grid frequency trend prediction model, the power grid frequency trend can be predicted in advance, reducing the latency; when the prediction result shows that the power grid frequency will deviate from the reference frequency, the incorporated output power of the energy storage type intelligent microgrid is configured in a timely manner to achieve rapid adjustment of the power grid frequency, improving the timeliness of frequency modulation and peak shaving, thereby achieving the technical effect of reducing the latency of frequency modulation and peak shaving of the intelligent microgrid. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 It is a schematic flow chart of a power management method for an energy storage type intelligent microgrid for frequency modulation and peak shaving provided by the present invention;

[0009] Figure 2 It is a schematic structural diagram of an electronic device provided by the present invention;

[0010] Figure 3Structural schematic diagram of a computer-readable storage medium provided by the present invention.

[0011] In the drawings, the components represented by the reference numerals are described as follows:

[0012] Electronic device 500, memory 510, processor 520, first computer program 511, computer-readable storage medium 600, second computer program 611. Detailed implementation manners

[0013] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present invention.

[0014] In the description of the present invention, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality of" means two or more, unless otherwise specifically defined.

[0015] In the description of the present invention, the term "for example" is used to mean "serving as an example, illustration, or explanation". Any embodiment described as "for example" in the present invention is not necessarily construed as being more preferred or having more advantages than other embodiments. In order for any person skilled in the art to implement and use the present invention, the following description is given. In the following description, details are set forth for the purpose of explanation. It should be understood that those skilled in the art can recognize that the present invention can be implemented without using these specific details. In other instances, well-known structures and processes are not elaborated in detail to avoid unnecessary details from obscuring the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope that conforms to the principles and features disclosed in the present invention.

[0016] Embodiment 1: As Figure 1 shown, the embodiment of the present invention provides a power management method for an energy storage type intelligent microgrid for frequency modulation and peak shaving, including the steps of:

[0017] S10: Traverse the user distribution nodes of the first substation area to perform inertial power consumption analysis, and obtain the power consumption required by the users at the first node, the power consumption required by the users at the second node until the power consumption required by the users at the Nth node;

[0018] Further, traverse the user distribution nodes in the first power consumption area to perform inertia power consumption analysis, and obtain the power consumption demanded by users at the first node, the power consumption demanded by users at the second node, until the power consumption demanded by users at the Nth node. Step S10 includes the steps:

[0019] S11: Obtain the first-node users of the user distribution nodes in the first power consumption area, where the first-node users have user type labels and user area labels;

[0020] S12: Obtain the time zone portrait information of the inertia power consumption analysis time zone, where the time zone portrait information includes month portrait labels, week portrait labels, and clock portrait labels;

[0021] S13: Perform inertia sample fitting according to the user type label, the user area label, the month portrait label, the week portrait label, and the clock portrait label, and obtain the power consumption demanded by the first-node users;

[0022] S13: Traverse the second-node users until the Nth-node users respectively to perform inertia power consumption analysis, and obtain the power consumption demanded by the second-node users until the power consumption demanded by the Nth-node users.

[0023] Further, perform inertia sample fitting according to the user type label, the user area label, the month portrait label, the week portrait label, and the clock portrait label, and obtain the power consumption demanded by the first-node users. Step S13 includes the steps:

[0024] S131: Based on the user type label, the user area label, and the month portrait label, construct a fixed background condition;

[0025] S132: Configure a binary background condition for the week portrait label, where the binary background condition is Monday to Friday or Saturday to Sunday;

[0026] S133: Based on the moment deviation threshold, configure a dynamic background condition for the clock portrait label;

[0027] S134: Perform first-level anomaly-free sample collection according to the fixed background condition, the binary background condition, and the dynamic background condition, and obtain first-level power consumption samples, where the first-level power consumption samples include first-level sample user type labels, first-level sample user area labels, first-level sample month portrait labels, first-level sample week portrait labels, and first-level sample clock portrait labels;

[0028] S135: Collect secondary anomaly-free samples based on the first-level sample user type tags, the first-level sample user area tags, the first-level sample monthly portrait tags, the first-level sample weekly portrait tags, and the first-level sample clock portrait tags to obtain secondary power consumption samples;

[0029] S136: Fit the secondary power consumption samples and the first-level power consumption samples to obtain the power consumption demanded by the users at the first node.

[0030] Furthermore, fitting the secondary power consumption samples and the first-level power consumption samples to obtain the power consumption demanded by the users at the first node, step S136 includes the steps:

[0031] S1361: Group the secondary power consumption samples according to the first-level power consumption samples to obtain multiple groups of power consumption samples;

[0032] S1362: Traverse the multiple groups of power consumption samples for central tendency evaluation to obtain multiple central power consumptions demanded;

[0033] S1363: Conduct central tendency evaluation on the multiple central power consumptions demanded and the first-level power consumption samples to obtain the power consumption demanded by the users at the first node.

[0034] S20: Obtain the time series information of the pre-allocated output power of the large power grid in the first transformer area;

[0035] Specifically, the first transformer area refers to the power generation transformer area, which is the area powered by one or more transformers, usually including the range where one or more transformers supply power to users; the user distribution node refers to the physical location or connection point of the user's electrical equipment in the power system; the power consumption demanded by the users at the first node, the power consumption demanded by the users at the second node up to the power consumption demanded by the users at the Nth node refer to the power consumption demanded by each user at the user distribution nodes in the first transformer area after inertial power consumption analysis, and the future time zone is the future time zone preset by the user for energy storage type intelligent microgrid power management, where N is an integer representing the total number of user nodes, and N≥1.

[0036] Furthermore, the time series information of the pre-allocated output power of the large power grid in the first transformer area refers to the time series information of the output power preset by the large power grid in the first transformer area in the future time zone.

[0037] By combining the power consumption demand prediction on the user side and the time series information of the pre-allocated output power of the power grid side, the actual trend of the power grid frequency can be predicted more accurately, thereby providing a scientific basis for the grid connection management of the energy storage type intelligent microgrid and ensuring the stable operation of the power grid and the quality of power supply.

[0038] Furthermore, the first node user refers to any user of the user distribution node. Taking the first node user as an example, the process of inertia power consumption analysis is described as follows:

[0039] The user type label and the user area label are two attribute identifiers used to describe the characteristics of users. The user type label includes the industrial category to which the user belongs, while the user area label refers to the physical space area occupied by the user. The inertia power consumption analysis time zone refers to a specific time period used to analyze the electricity consumption habits of users, which is custom-set by the power generation management terminal, that is, the aforementioned future time zone. The time zone portrait information represents the time characteristic identifier of the inertia power consumption analysis time zone, including the month portrait label representing the distribution month of the inertia power consumption analysis time zone, the week portrait label representing the day of the week in the inertia power consumption analysis time zone, and the clock portrait label representing the distribution time in the inertia power consumption analysis time zone. Exemplarily, if the inertia power consumption analysis time zone is from 1 am to 5 am on Thursday every week in March, the month portrait label is March, the week portrait label is Thursday in March, and the clock portrait label is from 1 am to 5 am.

[0040] Taking the user type label, the user area label, the month portrait label, the week portrait label, and the clock portrait label as constraint conditions, collecting the user electricity consumption record data with the same constraint conditions, and performing mode statistics on the user electricity consumption record data, the demand electricity consumption of the first node user can be obtained. Using the same method, processing the second node user until the Nth node user, the demand electricity consumption of the second node user until the demand electricity consumption of the Nth node user can be obtained.

[0041] By collecting the user type label, the user area label, the month portrait label, the week portrait label, and the clock portrait label to construct multi-factor constraint conditions, it is ensured that the extracted user electricity consumption record data has a high degree of association with the first node user, thereby ensuring the accuracy of the analysis of the demand electricity consumption.

[0042] Furthermore, the detailed steps of sampling with the user type label, the user area label, the month portrait label, the week portrait label, and the clock portrait label as constraint conditions are as follows:

[0043] Based on the user type label, the user area label, and the monthly portrait label, a fixed background condition is constructed, and the fixed background condition represents a constraint condition without the slightest deviation; a binary background condition is configured for the weekly portrait label, where the binary background condition is Monday to Friday or Saturday to Sunday. Preferably, if the weekly portrait label belongs to Monday to Friday, it is labeled as 1, and if it belongs to Saturday to Sunday, it is labeled as 0. The binary background condition is used to numerically transform the feature into 0 and 1. If the numerical values are the same, it conforms to the binary background condition; if the numerical values are different, it does not conform to the binary background condition; based on the time deviation threshold, a dynamic background condition is configured for the clock portrait label. Simply put, according to the clock portrait label, the time deviation threshold is pushed forward and backward to obtain a new time zone. Samples that conform to this time zone conform to the dynamic background condition. Exemplarily, if the inertial power consumption analysis time zone is from 1 am to 5 am every Thursday in March and the time deviation threshold is 20 minutes / hour, the dynamic background condition configured by the time deviation threshold is from 0:40 am to 5:20 am. Then, if the collection time zone of the new sample user belongs to 0:40 am to 5:20 am, it is considered to conform to the dynamic background condition; if it does not belong to 0:40 am to 5:20 am, it is considered not to conform to the dynamic background condition.

[0044] The first-level power consumption sample refers to the user power consumption record data of non-abnormal power consumption that simultaneously satisfies the fixed background condition, the binary background condition, and the dynamic background condition; the first-level sample user type label, the first-level sample user area label, the first-level sample monthly portrait label, the first-level sample weekly portrait label, and the first-level sample clock portrait label refer to the constraint condition features of the first-level power consumption sample; the first-level sample fixed background condition, the first-level sample binary background condition, and the first-level sample dynamic background condition are constructed based on the first-level sample user type label, the first-level sample user area label, the first-level sample monthly portrait label, the first-level sample weekly portrait label, and the first-level sample clock portrait label, and then the second-level power consumption sample that simultaneously satisfies the first-level sample fixed background condition, the first-level sample binary background condition, and the first-level sample dynamic background condition is collected.

[0045] Furthermore, the power consumption demand of the first-node user refers to the feature data obtained by sample fitting of the power consumption of the second-level power consumption sample and the first-level power consumption sample. Since the amount of data of the first-level power consumption sample that meets the requirements may be insufficient, in order to ensure the representativeness of the collected sample data in the embodiments of the present application, sampling is continued based on the first-level power consumption sample to obtain the second-level power consumption sample, expanding the data collection volume. In particular, it should be noted that in order to avoid the sample data deviating from the first-node user, only secondary sampling is allowed to take into account the advantages of data accuracy and data volume expansion.

[0046] The detailed process of sample fitting for the second-level power consumption sample and the first-level power consumption sample proposed in the embodiments of the present application is as follows:

[0047] First, since any sample of the primary electricity consumption samples corresponds to multiple samples of the secondary electricity consumption samples, the secondary electricity consumption samples are grouped according to the primary electricity consumption samples to obtain multiple groups of electricity consumption samples. Then, central tendency analysis is performed on the electricity consumption record data of each group of electricity consumption samples, and multiple central demand electricity consumptions are calculated. Further, central tendency evaluation is performed on the multiple central demand electricity consumptions and the primary electricity consumption samples to obtain the electricity consumption demand of the first node user.

[0048] Preferably, taking any group of electricity consumption record data as an example, the calculation steps of the central tendency analysis mentioned in the embodiments of the present application are as follows:

[0049] Calculate the pairwise electricity consumption deviation modulus values of the electricity consumption record data and store them as a number of electricity consumption deviation modulus values. Based on the number of electricity consumption deviation modulus values, for each electricity consumption record data of the electricity consumption record data from near to far, screen a preset number of adjacent electricity consumption record data to construct the characteristic neighborhood of each electricity consumption record data, and each electricity consumption record data is the central demand electricity consumption of the characteristic neighborhood. Calculate the reciprocal of the mean value of the deviation modulus between the electricity consumption record data and the central demand electricity consumption in each characteristic neighborhood, and set it as the density parameter of the central demand electricity consumption of each characteristic neighborhood. Extract the central demand electricity consumption with the maximum density parameter and set it as the selected central demand electricity consumption of the corresponding group for output. By default, the preset number is set to 0.25 times the total number of electricity consumption record data. Through central tendency evaluation, more representative characteristic data can be extracted, avoiding the interference of accidental data, and providing a data basis for the accurate analysis of the subsequent power grid frequency.

[0050] S30: Input the first substation large grid pre-allocated output power time series information, the electricity consumption demand of the first node user, the electricity consumption demand of the second node user until the electricity consumption demand of the Nth node user into the power grid frequency trend prediction model, and output the first power grid frequency trend prediction result;

[0051] Further, the power grid frequency trend prediction model includes a substation large grid input channel, a storage-type intelligent microgrid input channel, a user demand input channel, and a power grid frequency trend output channel. Inputting the first substation large grid pre-allocated output power time series information, the electricity consumption demand of the first node user, the electricity consumption demand of the second node user until the electricity consumption demand of the Nth node user into the power grid frequency trend prediction model and outputting the first power grid frequency trend prediction result includes:

[0052] Input the first substation large grid pre-allocated output power time series information into the substation large grid input channel, configure the input of the energy storage type intelligent microgrid input channel to 0, input the first node user demand electricity consumption, the second node user demand electricity consumption until the Nth node user demand electricity consumption into the user demand input channel, and obtain the first power grid frequency trend prediction result output by the power grid frequency trend output channel;

[0053] Among them, the steps for constructing the power grid frequency trend prediction model include:

[0054] Obtain the first substation power grid topology, where the first substation power grid topology includes the substation large grid output power incorporation position, the energy storage type intelligent microgrid power incorporation position, and the user side incorporation position;

[0055] Based on the first substation power grid topology, construct a graph neural network topology, where the graph neural network topology has the same structure as the first substation power grid topology, configure the substation large grid output power incorporation position, the energy storage type intelligent microgrid power incorporation position, and the user side incorporation position as input nodes, and perform full connection on the input nodes to set them as the output nodes of the graph neural network topology, where the input nodes are long short-term memory neural networks;

[0056] Collect the first substation historical power management data, where the first substation historical power management data includes the first substation large grid pre-allocated output power time series record information, the first node energy storage type intelligent microgrid recorded incorporated output power, the second node energy storage type intelligent microgrid recorded incorporated output power until the Mth node energy storage type intelligent microgrid recorded incorporated output power, and the first node user recorded demand electricity consumption, the second node user recorded demand electricity consumption until the Nth node user recorded demand electricity consumption, as well as the power grid frequency time series identification information;

[0057] With the supervision of the power grid frequency time series identification information as the output node, and with the first substation large grid pre-allocated output power time series record information, the first node energy storage type intelligent microgrid recorded incorporated output power, the second node energy storage type intelligent microgrid recorded incorporated output power until the Mth node energy storage type intelligent microgrid recorded incorporated output power, and the first node user recorded demand electricity consumption, the second node user recorded demand electricity consumption until the Nth node user recorded demand electricity consumption as the input of the input nodes, train the graph neural network topology to obtain the power grid frequency trend prediction model.

[0058] Further, with the supervision of the grid frequency time series identification information as the output node, and with the pre-allocated output power time series record information of the first substation area's large power grid, the recorded grid-connected output power of the first node's energy storage type intelligent microgrid, the recorded grid-connected output power of the second node's energy storage type intelligent microgrid until the recorded grid-connected output power of the Mth node's energy storage type intelligent microgrid, and the recorded required electricity consumption of the first node's users, the recorded required electricity consumption of the second node's users until the recorded required electricity consumption of the Nth node's users as the input of the input nodes, train the graph neural network topology to obtain the grid frequency trend prediction model, including:

[0059] Construct a grid frequency trend prediction loss function:

[0060] ,

[0061] ,

[0062] ,

[0063] ,

[0064] wherein, represents the grid frequency trend prediction loss, represents the probability of selecting the trend from to , represents the cumulative cost of the optimal alignment time series from the start of the grid frequency time series prediction information to the th element, and from the start of the grid frequency time series identification information to the th element, represents the time alignment cost between the ith element of the grid frequency time series prediction information and the ith element of the grid frequency time series identification information , represents the square difference between two elements, represents the temperature parameter, >0, The larger the the more concentrated the probability distribution is on the minimum cost trend, The smaller the the smoother the probability distribution is. n represents the length of the grid frequency time series identification information , and m represents the length of the grid frequency time series prediction information , represents the grid frequency time series prediction information, represents the grid frequency time series identification information, Characterize the time element of Characterize the time element;

[0065] Based on the power grid frequency trend prediction loss function, supervised by using the power grid frequency time series identification information as the output node, and using the time series record information of the pre-allocated output power of the large power grid in the first substation area, the recorded grid-connected output power of the first node energy storage type intelligent microgrid, the recorded grid-connected output power of the second node energy storage type intelligent microgrid until the recorded grid-connected output power of the Mth node energy storage type intelligent microgrid, and the recorded required power consumption of the users of the first node, the recorded required power consumption of the users of the second node until the recorded required power consumption of the users of the Nth node as the input of the input node, train the graph neural network topology to obtain the power grid frequency trend prediction model.

[0066] Specifically, the power grid frequency trend prediction model is a functional module constructed based on a neural network model for predicting the power grid frequency trend, and is used to predict the change trend of the power grid frequency according to the input power grid and user power consumption data. The specific construction process is as follows:

[0067] The power grid topology of the first substation area refers to the organizational structure characteristics of the power grid in the first substation area. The power grid topology of the first substation area includes the grid-connected position of the output power of the large power grid in the substation area, the grid-connected position of the power of the energy storage type intelligent microgrid, and the grid-connected position on the user side. The grid-connected position of the output power of the large power grid in the substation area refers to the physical distribution position of the substation in the substation area. The grid-connected position of the power of the energy storage type intelligent microgrid refers to the physical grid-connected position of the energy storage type intelligent microgrid. The grid-connected position on the user side refers to the user load distribution position.

[0068] The graph neural network topology refers to the neural network topology obtained by performing topology simulation on the power grid topology of the first substation area and having the same topology structure as the power grid topology of the first substation area. Through the graph neural network, graph structure data can be learned. In the embodiment of the present application, the frequency analysis problem of the power grid in the first substation area is abstracted into a graph structure problem, and the graph neural network topology is used for model topology construction. Preferably, the grid-connected position of the output power of the large power grid in the substation area, the grid-connected position of the power of the energy storage type intelligent microgrid, and the grid-connected position on the user side are configured as input nodes, and the input nodes are fully connected to obtain a fully connected layer as the output node of the graph neural network topology. Preferably, each input node is configured as a long short-term memory neural network. The long short-term memory neural network is sensitive to time series data. Therefore, the long short-term memory neural network is used here to process the time series data of each input node to improve the processing accuracy.

[0069] Furthermore, the historical power management data of the first power region refers to the historical power operation record data of the first power region, including the time series record information of the pre-allocated output power of the large power grid in the first power region, the recorded grid-connected output power of the energy storage type intelligent microgrid at the first node, the recorded grid-connected output power of the energy storage type intelligent microgrid at the second node until the recorded grid-connected output power of the energy storage type intelligent microgrid at the Mth node, as well as the recorded power consumption demand of users at the first node, the recorded power consumption demand of users at the second node until the recorded power consumption demand of users at the Nth node, and the grid frequency time series identification information. Preferably, with the grid frequency time series identification information as the supervision of the output node, and with the time series record information of the pre-allocated output power of the large power grid in the first power region, the recorded grid-connected output power of the energy storage type intelligent microgrid at the first node, the recorded grid-connected output power of the energy storage type intelligent microgrid at the second node until the recorded grid-connected output power of the energy storage type intelligent microgrid at the Mth node, and the recorded power consumption demand of users at the first node, the recorded power consumption demand of users at the second node until the recorded power consumption demand of users at the Nth node as the input of the input nodes, a dataset for constructing a grid frequency trend prediction model is constructed. The dataset for constructing the grid frequency trend prediction model is divided in a ratio of 8:2 to obtain an 8-ratio training dataset for the grid frequency trend prediction model and a 2-ratio training dataset for the grid frequency trend prediction model.

[0070] Furthermore, construct a loss function for predicting the grid frequency trend: ,

[0071] , , , the loss function built through the embodiments of the present application combines the time alignment ability of DTW and the differentiability of the probability distribution, and is suitable for training a deep learning model for time series prediction. It not only pays attention to local deviations, but also pays more attention to the overall deviation of the grid frequency trend, improving the model stability.

[0072] Based on the loss function for predicting the grid frequency trend, retrieve the training dataset for the grid frequency trend prediction model, and train the graph neural network topology. Whenever the loss value of the continuous preset number of trainings of the loss function for predicting the grid frequency trend is less than or equal to the loss value threshold preset by the user, retrieve the verification dataset for the grid frequency trend prediction model for verification. When the loss value of the continuous preset number of verifications is less than or equal to the loss value threshold, it is considered that the model converges, and the grid frequency trend prediction model is output. Set the input node at the power grid-connected position of the energy storage type intelligent microgrid as the input channel of the energy storage type intelligent microgrid, set the input node at the output power grid-connected position of the large power grid in the power region as the input channel of the large power grid in the power region, and set the input node at the user-side grid-connected position as the input channel of the user demand.

[0073] When the power grid frequency trend prediction model is scheduled for the first time, input the time series information of the pre-configured output power of the large power grid in the first substation area into the input channel of the large power grid in the substation area, configure the input of the input channel of the energy storage type intelligent microgrid to 0, and input the electricity consumption of the user demand at the first node, the electricity consumption of the user demand at the second node until the electricity consumption of the user demand at the Nth node into the input channel of the user demand quantity, and obtain the first power grid frequency trend prediction result output by the output channel of the power grid frequency trend, that is, the power grid frequency trend prediction result in the inertia analysis time zone.

[0074] S40: When the first power grid frequency trend prediction result deviates from the reference power grid frequency, configure the input power of the energy storage type intelligent microgrid incorporated into the nodes in the first substation area, including the input power of the energy storage type intelligent microgrid incorporated into the first node, the input power of the energy storage type intelligent microgrid incorporated into the second node until the input power of the energy storage type intelligent microgrid incorporated into the Mth node;

[0075] Specifically, calculate the proportion of the time when the deviation value between the first power grid frequency trend prediction result and the reference power grid frequency is greater than or equal to the frequency deviation threshold, which is set as the power grid frequency trend deviation degree. When the power grid frequency trend deviation degree ≥ the power grid frequency trend deviation degree threshold, it is regarded that the first power grid frequency trend prediction result deviates from the reference power grid frequency. The power grid frequency trend deviation degree threshold is a threshold value preset by the user, and the default value is 0.2. When the first power grid frequency trend prediction result does not deviate from the reference power grid frequency, there is no need to configure the grid connection of the energy storage type intelligent microgrid. If the first power grid frequency trend prediction result deviates from the reference power grid frequency, it is necessary to configure the grid connection of the energy storage type intelligent microgrid for power grid frequency regulation. Therefore, set the input power of the energy storage type intelligent microgrid incorporated into the nodes in the first substation area, including the input power of the energy storage type intelligent microgrid incorporated into the first node, the input power of the energy storage type intelligent microgrid incorporated into the second node until the input power of the energy storage type intelligent microgrid incorporated into the Mth node. The output power refers to the power generation output power. M represents the number of energy storage type intelligent microgrid nodes incorporated, M ≥ 1, and the output power is randomly determined within the rated range of each incorporated energy storage type intelligent microgrid node.

[0076] S50: Input the time series information of the pre-configured output power of the large power grid in the first substation area, the input power of the energy storage type intelligent microgrid incorporated into the first node, the input power of the energy storage type intelligent microgrid incorporated into the second node until the input power of the energy storage type intelligent microgrid incorporated into the Mth node, and the electricity consumption of the user demand at the first node, the electricity consumption of the user demand at the second node until the electricity consumption of the user demand at the Nth node into the power grid frequency trend prediction model, and output the second power grid frequency trend prediction result;

[0077] Specifically, in the second call of the power grid frequency trend prediction model, the time series information of the pre-allocated output power of the large power grid in the first sub-region, the output power incorporated by the energy storage type intelligent microgrid at the first node, the output power incorporated by the energy storage type intelligent microgrid at the second node until the output power incorporated by the energy storage type intelligent microgrid at the Mth node, and the electricity consumption demand of users at the first node, the electricity consumption demand of users at the second node until the electricity consumption demand of users at the Nth node are input into the power grid frequency trend prediction model, and a second power grid frequency trend prediction result is output.

[0078] S60: When the second power grid frequency trend prediction result does not deviate from the reference power grid frequency, power grid connection management of the nodes where the energy storage type intelligent microgrids are incorporated is performed according to the output power incorporated by the energy storage type intelligent microgrid at the first node, the output power incorporated by the energy storage type intelligent microgrid at the second node until the output power incorporated by the energy storage type intelligent microgrid at the Mth node.

[0079] Specifically, when the second power grid frequency trend prediction result does not deviate from the reference power grid frequency, it indicates that the current power grid connection strategy is feasible. Then, power grid connection management of the nodes where the energy storage type intelligent microgrids are incorporated can be performed according to the output power incorporated by the energy storage type intelligent microgrid at the first node, the output power incorporated by the energy storage type intelligent microgrid at the second node until the output power incorporated by the energy storage type intelligent microgrid at the Mth node during the inertial power consumption analysis time zone.

[0080] Furthermore, it also includes: when the second power grid frequency trend prediction result deviates from the reference power grid frequency, after updating the output power incorporated by the energy storage type intelligent microgrid at the first node, the output power incorporated by the energy storage type intelligent microgrid at the second node until the output power incorporated by the energy storage type intelligent microgrid at the Mth node, loop analysis is performed.

[0081] Specifically, when the second power grid frequency trend prediction result deviates from the reference power grid frequency, after updating the output power incorporated by the energy storage type intelligent microgrid at the first node, the output power incorporated by the energy storage type intelligent microgrid at the second node until the output power incorporated by the energy storage type intelligent microgrid at the Mth node, it returns to step S50 again to execute the loop until the power grid frequency trend prediction result does not deviate from the reference power grid frequency, and then the incorporated output frequencies of the intelligent microgrids from the first node to the Mth node are output correspondingly.

[0082] Furthermore, when the second power grid frequency trend prediction result deviates from the reference power grid frequency, after updating the output power incorporated by the energy storage type intelligent microgrid at the first node, the output power incorporated by the energy storage type intelligent microgrid at the second node until the output power incorporated by the energy storage type intelligent microgrid at the Mth node, loop analysis is performed, including:

[0083] When the number of loop analysis times meets the population size threshold, obtain the historical grid connection strategy set of the energy storage type intelligent microgrid;

[0084] Taking the deviation degree from the reference grid frequency as the fitness function, perform grid connection strategy optimization based on the historical grid connection strategy set of the energy storage type intelligent microgrid, and obtain the loop analysis for executing the expanded grid connection strategy of the energy storage type intelligent microgrid.

[0085] Specifically, the population size threshold refers to the preset number of loop analysis times, which is defaulted to 500 groups. If the number of loop analysis times is greater than or equal to the population size threshold and the grid connection strategy when not deviating from the reference grid frequency has not been obtained yet, the subsequent each update uses the following method:

[0086] Retrieve the grid connection output frequency of the intelligent microgrid from the first node to the Mth node for each update and store it as the historical grid connection strategy set of the energy storage type intelligent microgrid; taking the deviation degree from the reference grid frequency as the fitness function, sort the historical grid connection strategy set of the energy storage type intelligent microgrid from small to large to obtain the sorting result of the historical grid connection strategy of the energy storage type intelligent microgrid; using the preset number of historical grid connection strategies of the energy storage type intelligent microgrid with the front sorting as the target of the preset number of historical grid connection strategies of the energy storage type intelligent microgrid with the back sorting, perform the mutation of the grid connection output power for the same nodes, and return the obtained expanded grid connection strategy of the energy storage type intelligent microgrid to step S50 for loop execution until the predicted result of the grid frequency trend does not deviate from the reference grid frequency, then output the grid connection output frequency of the intelligent microgrid from the first node to the Mth node corresponding to it. Preferably, the mutation method 1 is: using the grid connection output power of some nodes of the target strategy to replace the grid connection output power of the same dimension nodes of the historical grid connection strategy of the energy storage type intelligent microgrid with the back sorting; the mutation method 2 is: updating the grid connection output power of the same dimension nodes of the historical grid connection strategy of the energy storage type intelligent microgrid with the back sorting to be closer to the grid connection output power of the corresponding dimension nodes of the target strategy. Preferably, the total number of mutated nodes is less than M. Through the group optimization mechanism, the probability of obtaining the convergent grid connection strategy can be improved and the processing efficiency can be improved.

[0087] The power management method of the energy storage type intelligent microgrid for frequency modulation and peak shaving provided by the embodiment of the present invention has at least the following technical effects:

[0088] By traversing the user distribution nodes for inertia power consumption analysis, the power consumption demand on the user side can be predicted in advance; combining the preconfigured output power time series information of the large power grid and the power consumption amount demanded on the user side, using the grid frequency trend prediction model, the grid frequency trend can be predicted in advance, reducing the latency; when the prediction result shows that the grid frequency will deviate from the reference frequency, timely configure the grid connection output power of the energy storage type intelligent microgrid to achieve rapid adjustment of the grid frequency, improve the timeliness of frequency modulation and peak shaving, and thus achieve the technical effect of reducing the latency of frequency modulation and peak shaving of the intelligent microgrid.

[0089] Example 2: Please refer to Figure 2 , Figure 2 which is a schematic diagram of the embodiment of the electronic device provided by the embodiment of the present invention. As Figure 2 shown, the embodiment of the present invention provides an electronic device 500, including a memory 510, a processor 520, and a first computer program 511 stored in the memory 510 and operable on the processor 520. When the processor 520 executes the first computer program 511, the following steps are implemented:

[0090] Traverse the user distribution nodes in the first power grid area for inertial power consumption analysis to obtain the power consumption required by the users at the first node, the power consumption required by the users at the second node until the power consumption required by the users at the Nth node;

[0091] Obtain the time series information of the pre-allocated output power of the large power grid in the first power grid area;

[0092] Input the time series information of the pre-allocated output power of the large power grid in the first power grid area, the power consumption required by the users at the first node, the power consumption required by the users at the second node until the power consumption required by the users at the Nth node into the power grid frequency trend prediction model, and output the first power grid frequency trend prediction result;

[0093] When the first power grid frequency trend prediction result deviates from the reference power grid frequency, configure the output power of the energy storage type intelligent microgrid incorporated into the nodes in the first power grid area, including the output power of the energy storage type intelligent microgrid incorporated into the first node, the output power of the energy storage type intelligent microgrid incorporated into the second node until the output power of the energy storage type intelligent microgrid incorporated into the Mth node;

[0094] Input the time series information of the pre-allocated output power of the large power grid in the first power grid area, the output power of the energy storage type intelligent microgrid incorporated into the first node, the output power of the energy storage type intelligent microgrid incorporated into the second node until the output power of the energy storage type intelligent microgrid incorporated into the Mth node, and the power consumption required by the users at the first node, the power consumption required by the users at the second node until the power consumption required by the users at the Nth node into the power grid frequency trend prediction model, and output the second power grid frequency trend prediction result;

[0095] When the second power grid frequency trend prediction result does not deviate from the reference power grid frequency, perform power grid connection management for the nodes incorporated with the energy storage type intelligent microgrid according to the output power of the energy storage type intelligent microgrid incorporated into the first node, the output power of the energy storage type intelligent microgrid incorporated into the second node until the output power of the energy storage type intelligent microgrid incorporated into the Mth node.

[0096] Example 3: Please refer to Figure 3 , Figure 3 which is a schematic diagram of the embodiment of a computer-readable storage medium provided by the embodiment of the present invention. As Figure 3As shown in the figure, this embodiment provides a computer-readable storage medium 600, on which a second computer program 611 is stored. When the second computer program 611 is executed by a processor, the following steps are implemented:

[0097] Traverse the user distribution nodes in the first power distribution area to perform inertial power consumption analysis, and obtain the power consumption requirements of users at the first node, the power consumption requirements of users at the second node, until the power consumption requirements of users at the Nth node;

[0098] Obtain the time series information of the pre-allocated output power of the large power grid in the first power distribution area;

[0099] Input the time series information of the pre-allocated output power of the large power grid in the first power distribution area, the power consumption requirements of users at the first node, the power consumption requirements of users at the second node, until the power consumption requirements of users at the Nth node into the power grid frequency trend prediction model, and output the first power grid frequency trend prediction result;

[0100] When the first power grid frequency trend prediction result deviates from the reference power grid frequency, configure the output power of the energy storage type intelligent microgrid incorporated into the nodes in the first power distribution area, including the output power of the energy storage type intelligent microgrid incorporated into the first node, the output power of the energy storage type intelligent microgrid incorporated into the second node, until the output power of the energy storage type intelligent microgrid incorporated into the Mth node;

[0101] Input the time series information of the pre-allocated output power of the large power grid in the first power distribution area, the output power of the energy storage type intelligent microgrid incorporated into the first node, the output power of the energy storage type intelligent microgrid incorporated into the second node, until the output power of the energy storage type intelligent microgrid incorporated into the Mth node, and the power consumption requirements of users at the first node, the power consumption requirements of users at the second node, until the power consumption requirements of users at the Nth node into the power grid frequency trend prediction model, and output the second power grid frequency trend prediction result;

[0102] When the second power grid frequency trend prediction result does not deviate from the reference power grid frequency, perform power grid connection management for the energy storage type intelligent microgrid incorporated into the nodes according to the output power of the energy storage type intelligent microgrid incorporated into the first node, the output power of the energy storage type intelligent microgrid incorporated into the second node, until the output power of the energy storage type intelligent microgrid incorporated into the Mth node.

[0103] It should be noted that in the above embodiments, the descriptions of each embodiment have their own focuses. For the parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0104] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a method, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) that contain computer-usable program code.

[0105] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (methods), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one or more of the processes or multiple processes and / or blocks Figure 1 one or more of the blocks or multiple blocks.

[0106] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one or more of the processes or multiple processes and / or blocks Figure 1 one or more of the blocks or multiple blocks.

[0107] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one or more of the processes or multiple processes and / or blocks Figure 1 one or more of the blocks or multiple blocks.

[0108] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications to these embodiments once they know the basic creative concepts.

[0109] Obviously, those skilled in the art can make various changes and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A method for power management of energy storage type smart microgrid for frequency and peak regulation, characterized in that: include: Traverse the user distribution nodes in the first substation to perform inertial power consumption analysis, and obtain the power consumption required by the user at the first node, the power consumption required by the user at the second node, and finally the power consumption required by the user at the Nth node; Obtain the timing information of the pre-allocated output power of the large power grid in the first substation area; Input the pre-allocated output power timing information of the first substation area large power grid, the power consumption demanded by the first node user, the power consumption demanded by the second node user, and the power consumption demanded by the Nth node user into the power grid frequency trend prediction model, and output the first power grid frequency trend prediction result; When the first grid frequency trend prediction result deviates from the reference grid frequency, the first node energy storage smart microgrid incorporation node of the first substation is configured to incorporate the output power of the first node energy storage smart microgrid, the output power of the second node energy storage smart microgrid, and the output power of the Mth node energy storage smart microgrid; Input the pre-allocated output power timing information of the first substation area large power grid, the output power of the first node energy storage type smart microgrid, the output power of the second node energy storage type smart microgrid until the output power of the M-th node energy storage type smart microgrid, and the power consumption required by the user of the first node, the power consumption required by the user of the second node until the power consumption required by the user of the N-th node into the power grid frequency trend prediction model, and output the second power grid frequency trend prediction result; When the second grid frequency trend prediction result does not deviate from the reference grid frequency, the power grid connection management of the energy storage smart microgrid connection node is performed according to the first node energy storage smart microgrid connection output power, the second node energy storage smart microgrid connection output power, and so on until the Mth node energy storage smart microgrid connection output power.

2. The method according to claim 1, characterized in that Traverse the user distribution nodes in the first substation to perform inertial power consumption analysis, and obtain the power consumption required by the user at the first node, the power consumption required by the user at the second node, and finally the power consumption required by the user at the Nth node, including: Obtain a first node user of the user distribution node of the first station area, wherein the first node user has a user type label and a user area label; Obtaining time zone portrait information of the inertial power consumption analysis time zone, wherein the time zone portrait information includes a month portrait label, a week portrait label, and a clock portrait label; Perform inertial sample fitting according to the user type label, the user area label, the month portrait label, the week portrait label, and the clock portrait label to obtain the power consumption required by the user at the first node; Traverse the second node user until the Nth node user and perform inertial power consumption analysis respectively to obtain the power consumption required by the second node user until the Nth node user.

3. The method according to claim 2, characterized in that Performing inertial sample fitting according to the user type label, the user area label, the month portrait label, the week portrait label, and the clock portrait label to obtain the power consumption required by the user at the first node includes: Building a fixed background condition based on the user type label, the user area label, and the month portrait label; Configuring a binary background condition for the week portrait label, wherein the binary background condition is Monday to Friday or Saturday to Sunday; Based on the time deviation threshold, configuring a dynamic background condition for the clock portrait tag; According to the fixed background condition, the binary background condition and the dynamic background condition, a first-level normal sample is collected to obtain a first-level electricity consumption sample, wherein the first-level electricity consumption sample includes a first-level sample user type label, a first-level sample user area label, a first-level sample month portrait label, a first-level sample week portrait label and a first-level sample clock portrait label; Perform secondary normal sample collection according to the primary sample user type label, the primary sample user area label, the primary sample month portrait label, the primary sample week portrait label, and the primary sample clock portrait label to obtain a secondary electricity consumption sample; Sample fitting is performed on the secondary power consumption sample and the primary power consumption sample to obtain the power consumption required by the user of the first node.

4. The method according to claim 3, characterized in that Performing sample fitting on the secondary power consumption sample and the primary power consumption sample to obtain the power consumption required by the user of the first node includes: Grouping the secondary power usage samples according to the primary power usage samples to obtain multiple groups of power usage samples; Traversing the plurality of groups of electricity consumption samples to perform a central trend assessment, and obtaining a plurality of center demand electricity consumptions; A central tendency assessment is performed on the multiple center demand power consumptions and the first-level power consumption samples to obtain the first-node user demand power consumption.

5. The method according to claim 1, characterized in that The grid frequency trend prediction model includes a large grid input channel in the substation area, an energy storage type smart microgrid input channel, a user demand input channel and a grid frequency trend output channel. The pre-allocated output power timing information of the large grid in the substation area, the power demand of the user at the first node, the power demand of the user at the second node until the power demand of the user at the Nth node are input into the grid frequency trend prediction model, and the first grid frequency trend prediction result is output, including: Input the pre-allocated output power timing information of the first large power grid in the substation area into the input channel of the large power grid in the substation area, configure the input of the energy storage type smart microgrid input channel to 0, input the power demand of the first node user, the power demand of the second node user until the power demand of the Nth node user into the user demand input channel, and obtain the first power grid frequency trend prediction result output by the power grid frequency trend output channel; The step of constructing the power grid frequency trend prediction model includes: Obtaining a first area power grid topology, wherein the first area power grid topology includes an area large power grid output power incorporation position, an energy storage type smart microgrid power incorporation position, and a user side incorporation position; Based on the first substation area power grid topology, a graph neural network topology is constructed, wherein the graph neural network topology is the same as the first substation area power grid topology structure, the output power incorporation position of the substation area large power grid, the power incorporation position of the energy storage type smart microgrid and the user side incorporation position are configured as input nodes, and the input nodes are fully connected to be set as output nodes of the graph neural network topology, wherein the input nodes are long short-term memory neural networks; Collecting historical power management data of the first substation, wherein the historical power management data of the first substation includes the timing record information of the pre-allocated output power of the large power grid in the first substation, the output power recorded by the first node energy storage type smart microgrid, the output power recorded by the second node energy storage type smart microgrid until the output power recorded by the M-th node energy storage type smart microgrid, and the power consumption demand recorded by the first node user, the power consumption demand recorded by the second node user until the power consumption demand recorded by the N-th node user, and the timing identification information of the power grid frequency; The grid frequency timing identification information is used as the supervision of the output node, the timing record information of the pre-allocated output power of the first substation large power grid, the record of the output power incorporated by the first node energy storage type smart microgrid, the record of the output power incorporated by the second node energy storage type smart microgrid until the record of the output power incorporated by the Mth node energy storage type smart microgrid, and the record of the required power consumption by the user of the first node, the record of the required power consumption by the user of the second node until the record of the required power consumption by the user of the Nth node are used as the input of the input node, the graph neural network topology is trained to obtain the grid frequency trend prediction model.

6. The method according to claim 5, characterized in that The grid frequency timing identification information is used as the supervision of the output node, the pre-allocated output power timing record information of the first substation large grid, the first node energy storage type smart microgrid record and the second node energy storage type smart microgrid record and the output power record and the Mth node energy storage type smart microgrid record and the first node user record demand power consumption, the second node user record demand power consumption and the Nth node user record demand power consumption are used as the input of the input node, and the graph neural network topology is trained to obtain the grid frequency trend prediction model, including: Construct the power grid frequency trend prediction loss function: ， ， ， ， in, Characterize the power grid frequency trend and predict losses, Characterization selection from arrive The probability of the trend, Characterize the information from the grid frequency time series prediction From the beginning to the elements, and the timing identification information from the power grid frequency From the beginning to the The cumulative cost of the optimal alignment sequence of elements, Characterizing the timing prediction information of power grid frequency The i-th element of Timing identification information of power grid frequency The i-th element of The time alignment cost, Represents the square difference of two elements, Characterize the temperature parameters, >0, The larger the probability distribution More focus on the minimum cost trend, The smaller the probability distribution The smoother, n represents the timing identification information of the power grid frequency The length of m represents the grid frequency timing prediction information Length, Characterize the grid frequency timing prediction information, Characterize the timing identification information of the power grid frequency, Characterization No. Moment elements, Characterization No. Moment element; Based on the grid frequency trend prediction loss function, with the grid frequency timing identification information as the supervision of the output node, with the first substation large grid pre-allocated output power timing record information, the first node energy storage type smart microgrid record integrated output power, the second node energy storage type smart microgrid record integrated output power until the Mth node energy storage type smart microgrid record integrated output power, and the first node user record demand power consumption, the second node user record demand power consumption until the Nth node user record demand power consumption as the input node input, the graph neural network topology is trained to obtain the grid frequency trend prediction model.

7. The method according to claim 1, characterized in that Also includes: When the second grid frequency trend prediction result deviates from the reference grid frequency, a cyclic analysis is performed after updating the first node energy storage type smart microgrid integrated output power, the second node energy storage type smart microgrid integrated output power, and the Mth node energy storage type smart microgrid integrated output power.

8. The method according to claim 7, characterized in that When the second grid frequency trend prediction result deviates from the reference grid frequency, the first node energy storage type smart microgrid integrated output power, the second node energy storage type smart microgrid integrated output power, and the Mth node energy storage type smart microgrid integrated output power are updated and then a cyclic analysis is performed, including: When the number of cycle analysis meets the population size threshold, the historical grid-connected strategy set of energy storage smart microgrid is obtained; Taking the deviation from the reference grid frequency as the fitness function, the grid connection strategy is optimized based on the historical grid connection strategy set of the energy storage type smart microgrid, and the energy storage type smart microgrid expansion grid connection strategy is obtained to perform a cyclic analysis.

Images