Power distribution optimization method and system based on photovoltaic energy storage equipment

Abstract

The invention provides a power distribution optimization method and system based on photovoltaic energy storage equipment. The method comprises the steps of S1, obtaining photovoltaic energy storage residual total electric quantity corresponding to each sunshine period of a photovoltaic energy storage equipment cluster in a target area in a target to-be-optimized day; s2, judging whether the last sunshine time period in the target day to be optimized is a photovoltaic energy storage full-amount time period or not; when the judgment result of the step S2 is no, executing the step S3; and S3, according to the photovoltaic energy storage residual total electric quantity corresponding to each sunshine time period in the target to-be-optimized day, determining at least one sunshine time period from all sunshine time periods in the target to-be-optimized day as a daytime charging time period and a power grid charging quantity for charging the photovoltaic energy storage equipment cluster by using a power grid system in each daytime charging time period, the sum of the power grid charging amounts corresponding to all the daytime charging periods in the target to-be-optimized day is equal to the difference between the preset photovoltaic energy storage maximum electric quantity and the photovoltaic energy storage residual total electric quantity corresponding to the last sunshine period.

Description

Technical Field

[0001] The present disclosure relates to the field of photovoltaic energy storage technology, and in particular to a power distribution optimization method and system based on photovoltaic energy storage equipment. Background Art

[0002] Photovoltaic energy storage equipment is a device that can convert light energy into electrical energy and store electrical energy. It is widely used in residents' real lives. Currently, it has become a common scenario to use photovoltaic energy storage equipment in conjunction with power grid systems to power loads in the target area. How to achieve efficient and low-cost coordinated power supply between photovoltaic energy storage equipment and power grid systems is one of the research hotspots in this field. Summary of the Invention

[0003] In a first aspect, an embodiment of the present disclosure provides a power distribution optimization method based on photovoltaic energy storage equipment, which divides a full day into multiple statistical periods and determines whether the corresponding statistical period is a sunshine period or a non-sunshine period according to the sunrise time and sunset time of the day. The power distribution optimization method includes:

[0004] Step S1: Obtain the total remaining photovoltaic energy storage capacity of the photovoltaic energy storage device cluster in the target area corresponding to each sunshine period on the target day to be optimized;

[0005] Step S2: determining whether the last sunshine period of the target day to be optimized is a period of full photovoltaic energy storage, wherein the period of full photovoltaic energy storage refers to a period when the remaining total amount of photovoltaic energy storage is equal to the preset maximum amount of photovoltaic energy storage;

[0006] When the judgment result of step S2 is no, step S3 is executed;

[0007] Step S3: Based on the total remaining photovoltaic energy storage capacity corresponding to each sunshine period within the target day to be optimized, determine at least one sunshine period from all sunshine periods within the target day to be optimized as a daytime charging period and the grid charging amount for charging the photovoltaic energy storage device cluster using the power grid system during each daytime charging period, and the sum of the grid charging amounts corresponding to all the daytime charging periods within the target day to be optimized is equal to the difference between the preset maximum photovoltaic energy storage capacity and the total remaining photovoltaic energy storage capacity corresponding to the last sunshine period.

[0008] In some embodiments, step S3 includes:

[0009] Step S301: Determine whether there is at least one sunshine period in the target day to be optimized, except for the last sunshine period, that is a period of full photovoltaic energy storage;

[0010] When the judgment result of step S301 is yes, step S301 is executed; when the judgment result of step S301 is no, step S302 is executed;

[0011] Step S302: determining each sunshine period after the last photovoltaic energy storage full-rate period within the target day to be optimized as a charging candidate period;

[0012] Step S303: determining each sunshine period within the target day to be optimized as a candidate charging period;

[0013] After step S302 and step S303 are completed, step S304 is executed, wherein the number of the determined optional charging time periods is recorded as N, where N is a positive integer;

[0014] Step S304: Constructing a charging optimization model for representing charging the photovoltaic energy storage device cluster using the power grid system during the N candidate charging time periods. The decision variables in the charging optimization model are the power grid charging amounts corresponding to charging the photovoltaic energy storage device cluster using the power grid system during the N candidate charging time periods. The objective of the charging optimization model is to minimize the total charging cost of charging the photovoltaic energy storage device cluster using the power grid system during the N candidate charging time periods.

[0015] Step S305: Solve the charging optimization model using a first preset target optimization algorithm to obtain a corresponding current optimal solution. The current optimal solution includes the current optimal value of the grid charging amount corresponding to charging the photovoltaic energy storage device cluster using the power grid system in N optional charging time periods. The optional charging time period in which the corresponding current optimal value of the grid charging amount is not 0 is used as the daytime charging time period.

[0016] In some embodiments, the total charging cost of charging the photovoltaic energy storage device cluster using the power grid system during N optional charging time periods is minimized, which is expressed as follows:

[0017]

[0018] Cost represents the total charging cost, Q_in n Price_in represents the amount of grid charging corresponding to charging the photovoltaic energy storage device cluster using the grid system in the nth charging alternative period. n The unit price of charging the photovoltaic energy storage device cluster using the power grid system during the nth charging alternative time period;

[0019] The constraints of the charging optimization model include:

[0020] Condition 1: During the N available charging periods, the photovoltaic energy storage device cluster will not discharge to the grid system:

[0021] Q_in n ≥0

[0022] Condition 2: Among the N available charging time periods, the charging power of each available charging time period cannot be higher than the maximum charging power of the photovoltaic energy storage device cluster:

[0023]

[0024] Among them, t n Indicates the duration of the nth charging alternative period, P_in max Indicates the maximum charging power of the photovoltaic energy storage device cluster;

[0025] Condition 3: After the photovoltaic energy storage device cluster is charged using the power grid system during N optional charging time periods, the total remaining photovoltaic energy storage capacity during the last sunshine period of the target day to be optimized is increased to the preset maximum photovoltaic energy storage capacity;

[0026]

[0027] C last C represents the total remaining photovoltaic energy storage capacity of the photovoltaic energy storage device cluster corresponding to the last sunshine period of the target day to be optimized when the grid system is not charged. max Indicates the preset maximum amount of photovoltaic energy storage, represents the total amount of grid charging used to charge the photovoltaic energy storage device cluster during N optional charging periods;

[0028] Condition 4: During any available charging period, the total remaining photovoltaic energy storage capacity of the photovoltaic energy storage device cluster after completing the grid system charging will not exceed the preset maximum photovoltaic energy storage capacity:

[0029]

[0030] Among them, C n represents the total remaining photovoltaic energy storage capacity of the photovoltaic energy storage device cluster in the nth charging alternative time period when the grid system is not charging. It represents the total amount of grid charging that is used to charge the photovoltaic energy storage device using the grid system during the first n charging alternative time periods.

[0031] In some embodiments, before step S1, the method further includes:

[0032] Step Sa, generating a photovoltaic energy storage remaining total power prediction model for a sunshine period that can predict the photovoltaic energy storage remaining total power corresponding to the target sunshine period;

[0033] The input information of the photovoltaic energy storage remaining total power prediction model for sunshine period includes: the time period identifier of the target sunshine period within the target day to be optimized, the regional total power consumption of all loads connected to the photovoltaic energy storage device cluster in the target area during the target sunshine period, the temperature of the target area during the target sunshine period, and the cumulative sunshine duration of the target area during the target day to be optimized during the target sunshine period; the output of the photovoltaic energy storage remaining total power prediction model for sunshine period is the photovoltaic energy storage remaining total power corresponding to the target sunshine period;

[0034] Step S1 includes:

[0035] Step S101: Acquire first input information corresponding to each sunshine period within a target day to be optimized, the first input information including: a period identifier of the corresponding sunshine period within the target day to be optimized, the total regional power consumption of all loads connected to the photovoltaic energy storage device cluster within the target area during the corresponding sunshine period, the temperature of the target area during the corresponding sunshine period, and the cumulative sunshine duration of the target area within the target day to be optimized at the end of the corresponding sunshine period;

[0036] Step S102: input the first input information corresponding to each sunshine period in the target day to be optimized into the trained photovoltaic energy storage remaining total power prediction model for the sunshine period to obtain the photovoltaic energy storage remaining total power corresponding to each sunshine period in the target day to be optimized.

[0037] In some embodiments, step Sa includes:

[0038] Step Sa1: Collecting first historical period comprehensive information of the target area for multiple sunshine periods within multiple historical days, the first historical period comprehensive information including: a period identifier for indicating the position of the corresponding sunshine period in a day, the total regional power consumption of all loads connected to the photovoltaic energy storage device cluster in the target area during the corresponding sunshine period, the temperature of the target area during the corresponding sunshine period, the cumulative sunshine duration of the target area on the day at the end of the corresponding sunshine period, and the total remaining photovoltaic energy storage power of the photovoltaic energy storage device cluster in the target area corresponding to the corresponding sunshine period;

[0039] Step Sa2: Use the comprehensive information of the first historical period as a training sample, the period identifier, the total power consumption of the area, the cumulative sunshine duration, the temperature and the cumulative sunshine duration in the comprehensive information of the first historical period as model inputs, and the total remaining photovoltaic energy storage power in the comprehensive information of the first historical period as model output. Train the first preset prediction model to obtain a prediction model for the total remaining photovoltaic energy storage power for the sunshine period.

[0040] In some embodiments, step Sa2 includes:

[0041] Step Sa21: Divide all the historical days into 8 groups according to a preset classification rule, wherein the preset classification rule is: statutory holidays are divided into 1 group, and non-statutory holidays are divided into the remaining 7 groups according to 7 different dates from Monday to Sunday;

[0042] Step Sa22: for each group, the first historical period comprehensive information of all sunshine periods in each historical day included in the group is used to form a first historical period comprehensive information set corresponding to the group;

[0043] Step Sa23: For each group, the first historical period comprehensive information set corresponding to the group is used as a training sample set to train the first preset prediction model to obtain a prediction model for the total remaining photovoltaic energy storage power during the sunshine period corresponding to the group;

[0044] Step S102 includes:

[0045] Step S1021: determining the group to which the target day to be optimized belongs according to the preset classification rule based on the date of the target day to be optimized;

[0046] Step S1022: input the first input information corresponding to each sunshine period within the target day to be optimized into the photovoltaic energy storage remaining total power prediction model for the sunshine period corresponding to the group to which the target day to be optimized belongs, and obtain the photovoltaic energy storage remaining total power corresponding to each sunshine period within the target day to be optimized.

[0047] In some embodiments, it further includes:

[0048] Sb, generating a non-sunshine period photovoltaic energy storage remaining total power prediction model capable of predicting the target non-sunshine period after the last sunshine period in a day.

[0049] The input information of the prediction model for the total remaining photovoltaic energy storage capacity for non-sunshine periods includes: the period identifier of the non-target sunshine period within the target day to be optimized, the total remaining photovoltaic energy storage capacity corresponding to the sunshine period that is immediately before and closest to the target non-sunshine period, the total regional power consumption of all loads connected to the photovoltaic energy storage device cluster in the target area during the target non-sunshine period, and the temperature of the target area during the target non-sunshine period; the output of the prediction model for the total remaining photovoltaic energy storage capacity for non-sunshine periods is the total remaining photovoltaic energy storage capacity corresponding to the target non-sunshine period;

[0050] Step S4: selecting non-sunshine periods that are during the peak power consumption period of the power grid during the target day to be optimized from all non-sunshine periods after the last sunshine period during the target day to be optimized as candidate discharge periods;

[0051] Step S5: Obtain second input information of the last dischargeable alternative time period within the target day to be optimized, the second input information including: a time period identifier of the last dischargeable alternative time period, a total remaining photovoltaic energy storage capacity corresponding to a sunshine period immediately preceding and closest to the last dischargeable alternative time period, a total regional power consumption of all loads connected to the photovoltaic energy storage device cluster within the target area during the last dischargeable alternative time period, and a temperature of the target area during the last dischargeable alternative time period, wherein the total remaining photovoltaic energy storage capacity corresponding to the sunshine period immediately preceding and closest to the last dischargeable alternative time period is set to the preset maximum photovoltaic energy storage capacity;

[0052] Step S6: inputting the second input information of the last dischargeable alternative time period within the target day to be optimized into the trained photovoltaic energy storage remaining total power prediction model for the non-sunshine period to obtain the photovoltaic energy storage remaining total power corresponding to the last dischargeable alternative time period within the target day to be optimized;

[0053] Step S7: determining whether the total remaining amount of photovoltaic energy storage corresponding to the last dischargeable alternative time period within the target day to be optimized is 0;

[0054] When the judgment result of step S7 is no, step S8 is executed;

[0055] Step S8: Determine at least one optional discharge time period from all the optional discharge time periods within the target day to be optimized as the peak power consumption discharge time period, and the energy storage cluster discharge amount of the photovoltaic energy storage device cluster discharged to the power grid system during each peak power consumption discharge time period, and the sum of the energy storage cluster discharge amounts corresponding to all the peak power consumption discharge time periods within the target day to be optimized and the total remaining photovoltaic energy storage capacity corresponding to the last optional discharge time period within the target day to be optimized.

[0056] In some embodiments, step Sb includes:

[0057] Step Sb1: Collecting comprehensive information of a second historical period for a plurality of non-sunshine periods after the last sunshine period in the target area over a plurality of historical days, the second historical period comprehensive information including: a period identifier indicating the position of the corresponding non-sunshine period in a day, the total remaining photovoltaic energy storage capacity corresponding to a sunshine period immediately before and closest to the corresponding non-sunshine period, the total regional power consumption of all loads connected to the photovoltaic energy storage device cluster in the target area during the corresponding non-sunshine period, the temperature of the target area during the corresponding non-sunshine period, and the total remaining photovoltaic energy storage capacity corresponding to the photovoltaic energy storage device cluster in the target area during the corresponding sunshine period;

[0058] Step Sb2: Using the second historical period comprehensive information as a training sample, the period identifier in the second historical period comprehensive information, the total remaining photovoltaic energy storage capacity corresponding to the sunshine period immediately before and closest to the corresponding non-sunshine period, the total regional power consumption, and the temperature as model inputs, and the total remaining photovoltaic energy storage capacity corresponding to the photovoltaic energy storage device cluster in the target area during the corresponding sunshine period in the second historical period comprehensive information as the model output, training the second preset prediction model to obtain a photovoltaic energy storage remaining total capacity prediction model for the non-sunshine period;

[0059] Wherein, step Sb2 includes:

[0060] Step Sb21: Divide all the historical days into 8 groups according to a preset classification rule, wherein the preset classification rule is: statutory holidays are divided into 1 group, and non-statutory holidays are divided into the remaining 7 groups according to 7 different dates from Monday to Sunday;

[0061] Step Sb22: for each group, the second historical period comprehensive information of all non-sunshine periods after the last sunshine period in each historical day included in the group is used to form a second historical period comprehensive information set corresponding to the group;

[0062] Step Sa23: For each group, the second historical period comprehensive information set corresponding to the group is used as a training sample set to train the second preset prediction model to obtain a prediction model for the total remaining photovoltaic energy storage power for the non-sunshine period corresponding to the group;

[0063] Step S6 includes:

[0064] Step S601: determining the group to which the target day to be optimized belongs according to the preset classification rule based on the date of the target day to be optimized;

[0065] Step S602: Input the second input information of the last dischargeable alternative time period within the target day to be optimized into the photovoltaic energy storage remaining total power prediction model for the non-sunshine time period corresponding to the group to which the target day to be optimized belongs, and obtain the photovoltaic energy storage remaining total power corresponding to the last dischargeable alternative time period within the target day to be optimized.

[0066] In some embodiments, the number of the candidate discharge time periods screened out in step S4 is M, where M is a positive integer; and step S8 includes:

[0067] Step S801: constructing a discharge optimization model for representing discharging the power grid system using a photovoltaic energy storage device cluster in M ​​dischargeable candidate time periods;

[0068] The decision variables in the discharge optimization model are the energy storage cluster discharge amounts corresponding to the photovoltaic energy storage device cluster discharging the power grid in the M dischargeable alternative time periods;

[0069] The goal of the discharge optimization model is to maximize the total discharge revenue of discharging the photovoltaic energy storage device cluster to the grid during M dischargeable candidate time periods, which can be expressed as follows:

[0070]

[0071] Gain represents the total discharge gain, Q_out m Price_out represents the energy storage cluster discharge amount corresponding to the discharge of the photovoltaic energy storage device cluster to the grid during the mth discharge alternative period. m represents the unit price benefit of discharging the photovoltaic energy storage device cluster to the grid during the mth discharge alternative period;

[0072] The constraints of the discharge optimization model include:

[0073] Condition 1: During the M dischargeable candidate periods, the grid system will not charge the photovoltaic energy storage device cluster:

[0074] Q_out m ≥0

[0075] Condition 2: Among the M dischargeable candidate time periods, the discharge power of each dischargeable candidate time period cannot exceed the maximum discharge power of the photovoltaic energy storage device cluster:

[0076]

[0077] Among them, t' m Indicates the duration of the mth discharge alternative period, P_out max Indicates the maximum discharge power of the photovoltaic energy storage device cluster;

[0078] Condition 3: After discharging the photovoltaic energy storage device to the power grid during M dischargeable candidate time periods, the total remaining photovoltaic energy storage capacity corresponding to the last dischargeable candidate time period drops to 0;

[0079]

[0080] C' last Indicates the total remaining photovoltaic energy storage capacity of the photovoltaic energy storage device cluster corresponding to the last dischargeable alternative time period within the target day to be optimized when no discharge is performed to the grid system. It represents the total discharge amount of the energy storage cluster that is discharged to the power grid system by using the photovoltaic energy storage device cluster during M dischargeable alternative time periods;

[0081] Step S802: Solve the discharge optimization model using a second preset target optimization algorithm to obtain a corresponding current optimal solution. The current optimal solution includes the current optimal value of the energy storage cluster discharge corresponding to discharging the power grid system using the photovoltaic energy storage device cluster in M ​​dischargeable alternative time periods. The corresponding dischargeable alternative time periods in which the current optimal value of the energy storage cluster discharge is not zero are used as the peak power consumption discharge period.

[0082] In a second aspect, an embodiment of the present disclosure further provides a power distribution optimization system based on a photovoltaic energy storage device. The power distribution optimization system is configured to implement the power distribution optimization method provided in the first aspect, and the power distribution optimization system includes:

[0083] An acquisition module is configured to obtain the total remaining photovoltaic energy storage capacity of the photovoltaic energy storage device cluster in the target area corresponding to each sunshine period within the target day to be optimized;

[0084] a judgment module configured to judge whether the last sunshine period of the target day to be optimized is a period of full photovoltaic energy storage, wherein the period of full photovoltaic energy storage refers to a period when the total remaining amount of photovoltaic energy storage is equal to the preset maximum amount of photovoltaic energy storage;

[0085] The optimization module is configured to, when the judgment module determines that the last sunshine period of the target day to be optimized is not a period with full photovoltaic energy storage, determine, based on the total remaining photovoltaic energy storage power corresponding to each sunshine period of the target day to be optimized, at least one sunshine period from all sunshine periods of the target day to be optimized as a daytime charging period, and a grid charging amount for charging the photovoltaic energy storage device cluster using the power grid system during each daytime charging period, and the sum of the grid charging amounts corresponding to all the daytime charging periods of the target day to be optimized is equal to the difference between the preset maximum photovoltaic energy storage power and the total remaining photovoltaic energy storage power corresponding to the last sunshine period.

[0086] The technical solution disclosed herein first detects whether there is space available for charging by the power grid system during the sunshine period (i.e., determines whether the last sunshine period of the target day to be optimized is a period with full photovoltaic energy storage). Then, when it is detected that there is space available for charging by the power grid system during the sunshine period (i.e., the last sunshine period of the target day to be optimized is not a period with full photovoltaic energy storage), the power grid system can be used to charge the photovoltaic energy storage device cluster during at least part of the sunshine period to appropriately increase the load of the power grid system during the day, thereby achieving the purpose of "filling the valley" of the load of the power grid system.

[0087] In addition, the present disclosure takes into account that the photovoltaic energy storage device cluster itself will also generate a certain amount of electricity and store it. Therefore, while achieving "valley filling" as much as possible, it is also necessary to avoid the problem of charging redundancy caused by overcharging of the photovoltaic energy storage system by the power grid system. Therefore, the present disclosure stipulates that the total grid charging amount of the photovoltaic energy storage device cluster charged by the power grid system in each sunshine period is equal to the difference between the preset maximum photovoltaic energy storage capacity and the total remaining photovoltaic energy storage capacity corresponding to the last sunshine period. As a result, after the power grid system is used to charge the photovoltaic energy storage device cluster, the total remaining photovoltaic energy storage capacity in the last sunshine period of the target day to be optimized is increased to the preset maximum photovoltaic energy storage capacity. BRIEF DESCRIPTION OF THE DRAWINGS

[0088] Figure 1 A schematic diagram of dividing a day into multiple sunshine periods and non-sunshine periods in the present disclosure;

[0089] Figure 2 A schematic diagram of a specific application scenario of the disclosed technical solution;

[0090] Figure 3 A flow chart of a power distribution optimization method based on photovoltaic energy storage equipment provided in an embodiment of the present disclosure;

[0091] Figure 4 A flow chart of another power distribution optimization method based on photovoltaic energy storage equipment provided in an embodiment of the present disclosure;

[0092] Figure 5 A flow chart of another power distribution optimization method based on photovoltaic energy storage equipment provided in an embodiment of the present disclosure;

[0093] Figure 6 A structural block diagram of a power distribution optimization system based on photovoltaic energy storage equipment provided in an embodiment of the present disclosure;

[0094] Figure 7 The figure is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0095] In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the present disclosure is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0096] Unless otherwise defined, the technical or scientific terms used in this disclosure should have the usual meanings understood by people with ordinary skills in the field to which this disclosure belongs. The words "first", "second" and similar words used in this disclosure do not indicate any order, quantity or importance, but are only used to distinguish different components. Similarly, words such as "one", "an" or "the" do not indicate a quantitative limitation, but rather indicate the presence of at least one. Words such as "include" or "comprise" mean that the elements or information preceding the word include the elements or information listed after the word and their equivalents, without excluding other elements or information. Words such as "connect" or "connected" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. Many specific details of the present disclosure are described below, such as the specific implementation process of certain steps and certain specific algorithms, in order to more clearly understand the present disclosure. However, as those skilled in the art will appreciate, the present disclosure may be implemented without following these specific details.

[0097] In the following description, "total remaining PV energy storage capacity" refers to the total remaining PV energy storage capacity of all PV energy storage devices in the PV energy storage device cluster at the end of the corresponding statistical period. "Historical day" refers to a day that occurred before the target optimization day, and "target optimization day" refers to a day that has not yet occurred (has not yet arrived).

[0098] In the present disclosure, a full day is pre-divided into multiple statistical periods, and the corresponding statistical period is determined to be a sunshine period or a non-sunshine period according to the sunrise and sunset times of the day. It should be noted that in the present disclosure, it is assumed that photovoltaic energy storage devices can produce electricity after sunrise, but cannot produce electricity after sunset. Sunshine period refers to the period when photovoltaic energy storage devices can produce electricity, and non-sunshine period refers to the period when photovoltaic energy storage devices cannot produce electricity.

[0099] Figure 1 Schematic diagram of dividing a day into multiple sunshine periods and non-sunshine periods in this disclosure. Figure 1As shown, taking one hour as an example, a day can be divided into 24 statistical periods: 0:00-1:00, 1:00-2:00, ... 23:00-24:00. If the sunrise time in the target area on a certain day is 5:50 and the sunset time is 18:28, then the day includes 14 sunshine periods: 5:00-6:00 (the photovoltaic energy storage device will produce electricity during the period from 5:50 to 6:00, which is the first sunshine period), 6:00-7:00 ... 17:00-18:00, and 18:00-19:00 (the last sunshine period), and 10 non-sunshine periods: 0:00-1:00, 1:00-2:00 ... 4:00-5:00, 19:00-20:00, 20:00-21:00 ... 23:00-24:00.

[0100] In practical applications, the statistical time periods may be divided according to actual needs, and the duration of each statistical time period may be the same or different, which is not limited in the present disclosure.

[0101] In addition, in this disclosure, each statistical period is assigned a different period identifier based on its location. For example, the period from 0:00 to 1:00 can be represented by the period identifier "A1," the period from 1:00 to 2:00 can be represented by the period identifier "A2," and so on, the period from 23:00 to 24:00 can be represented by the period identifier "A24." Based on the period identifier, the specific time of day to which the corresponding period refers can be determined.

[0102] Figure 2 This is a schematic diagram of a specific application scenario of the technical solution disclosed in this disclosure. Figure 2 As shown, a photovoltaic energy storage device cluster is configured in the target area, and the photovoltaic energy storage device cluster includes multiple photovoltaic energy storage devices arranged in a distributed manner, and these photovoltaic energy storage devices are connected to the power supply control device; there are multiple loads in the target area, and these loads are all connected to at least one photovoltaic energy storage device in the photovoltaic energy storage device cluster. At the same time, these loads are also connected to the power grid system (which can supply power to other residential loads) through the power supply control device.

[0103] The power supply controller has at least the following functions: 1) controlling the photovoltaic energy storage device cluster to directly supply power to the loads in the target area; 2) controlling the power grid system to charge the photovoltaic energy storage device cluster; 3) controlling the photovoltaic energy storage device cluster to discharge power to the power grid system; 4) controlling the power grid system to supply power to the loads in the target area.

[0104] In this application scenario, when the PV energy storage device cluster has stored energy, it will be used first to power the loads in the target area. When the stored energy in the PV energy storage device cluster is zero, the power grid system will be used to power the loads in the target area. Specifically, the power supply for the loads in the target area can be in the following situations:

[0105] Case 1: During the sunshine period, when the total power consumption of all loads in the target area (the total regional power consumption per unit time) is less than the total power produced by all photovoltaic panels in the photovoltaic energy storage device cluster, then in response to the control of the power supply control device, the photovoltaic panels in the photovoltaic energy storage device cluster will not only supply power to the loads, but also store the remaining power in the energy storage device, and the total remaining photovoltaic energy storage power corresponding to the photovoltaic energy storage device cluster will increase.

[0106] Case 2: During the sunshine period, when the total power consumption of all loads in the target area is greater than the total power produced by all photovoltaic panels in the photovoltaic energy storage device cluster, and the total remaining photovoltaic energy storage capacity corresponding to the photovoltaic energy storage device cluster is not zero, then in response to the control of the power supply control device, the photovoltaic panels and energy storage devices in the photovoltaic energy storage device cluster will simultaneously supply power to the loads, and the total remaining photovoltaic energy storage capacity corresponding to the photovoltaic energy storage device cluster will decrease.

[0107] Case 3: During the sunshine period, when the total power consumption of all loads in the target area is greater than the total power produced by all photovoltaic panels in the photovoltaic energy storage device cluster, and the total remaining photovoltaic energy storage capacity corresponding to the photovoltaic energy storage device cluster is 0, then in response to the control of the power supply control device, the power grid system and the photovoltaic panels in the photovoltaic energy storage device cluster will simultaneously supply power to the loads, and the total remaining photovoltaic energy storage capacity corresponding to the photovoltaic energy storage device cluster will remain at 0.

[0108] Case 4: During non-sunshine periods, when the total remaining photovoltaic energy storage capacity corresponding to the photovoltaic energy storage device cluster is not zero, then in response to the control of the power supply control device, only the energy storage devices in the photovoltaic energy storage device cluster supply power to the loads in the target area.

[0109] Case 5: During non-sunshine periods, when the total remaining amount of photovoltaic energy storage corresponding to the photovoltaic energy storage device cluster is 0, in response to the control of the power supply control device, only the power grid system supplies power to the loads in the target area.

[0110] Figure 3 This is a flow chart of a power distribution optimization method based on photovoltaic energy storage equipment provided by an embodiment of the present disclosure. Figure 3 As shown, the power distribution optimization method includes

[0111] Step S1: Obtain the total remaining photovoltaic energy storage capacity of the photovoltaic energy storage device cluster in the target area corresponding to each sunshine period within the target day to be optimized.

[0112] Step S2: Determine whether the last sunshine period of the target day to be optimized is a period with full photovoltaic energy storage.

[0113] Among them, the photovoltaic energy storage full-capacity period refers to the period when the corresponding total remaining photovoltaic energy storage capacity is equal to the preset photovoltaic energy storage maximum capacity (that is, the capacity corresponding to the current capacity level of the photovoltaic energy storage equipment cluster is 100%).

[0114] When the judgment result of step S2 is no, it means that there is space that can be charged by the power grid system during the sunshine period, and then step S3 is executed; when the judgment result of step S2 is yes, it means that there is no space that can be charged by the power grid system during the sunshine period.

[0115] Step S3: Based on the total remaining photovoltaic energy storage power corresponding to each sunshine period within the target day to be optimized, determine at least one sunshine period from all sunshine periods within the target day to be optimized as a daytime charging period and the grid charging amount used to charge the photovoltaic energy storage device cluster using the power grid system during each daytime charging period.

[0116] The total amount of grid charging corresponding to all daytime charging periods within the target day to be optimized is equal to the difference between the preset maximum amount of photovoltaic energy storage and the total remaining amount of photovoltaic energy storage corresponding to the last sunshine period.

[0117] According to the daily residential load curves presented by many research institutes, it is found that the electricity power consumed by residents during the day is significantly lower than the electricity power consumed in the period after sunset (there is a peak period of residential electricity consumption after the end of the day). In other words, the power grid system presents a low load period in the period before sunset and a peak load period in the period after sunset. The load of the power grid system will gradually increase in the period before and after sunset.

[0118] Based on the above phenomenon, in the present disclosure, it is first detected whether there is space that can be charged by the power grid system during the sunshine period (that is, it is determined whether the last sunshine period of the target day to be optimized is a period with full photovoltaic energy storage), and when it is detected that there is space that can be charged by the power grid system during the sunshine period (that is, the last sunshine period of the target day to be optimized is not a period with full photovoltaic energy storage), the power grid system can be used to charge the photovoltaic energy storage device cluster during at least part of the sunshine period to appropriately increase the load of the power grid system during the day, thereby achieving the purpose of "filling the valley" of the load of the power grid system.

[0119] In addition, the present disclosure takes into account that the photovoltaic energy storage device cluster itself will also generate a certain amount of electricity and store it. Therefore, while achieving "valley filling" as much as possible, it is also necessary to avoid the problem of charging redundancy caused by overcharging of the photovoltaic energy storage system by the power grid system. Therefore, the present disclosure stipulates that the total grid charging amount of the photovoltaic energy storage device cluster charged by the power grid system in each sunshine period is equal to the difference between the preset maximum photovoltaic energy storage capacity and the total remaining photovoltaic energy storage capacity corresponding to the last sunshine period. As a result, after the power grid system is used to charge the photovoltaic energy storage device cluster, the total remaining photovoltaic energy storage capacity in the last sunshine period of the target day to be optimized is increased to the preset maximum photovoltaic energy storage capacity.

[0120] It should be noted that in the present disclosure, the total remaining power of photovoltaic energy storage in the last sunshine period of the target day to be optimized is increased to the preset maximum power of photovoltaic energy storage, which can prepare for the subsequent use of photovoltaic energy storage equipment to discharge grid equipment during the peak power consumption period of the grid, so as to reduce the load of the grid system during the peak power consumption period and achieve "peak shaving".

[0121] In some embodiments, step S3 includes: the following steps S301 to S305.

[0122] Step S301: Determine whether there is at least one sunshine period with full photovoltaic energy storage capacity among the sunshine periods other than the last sunshine period on the target day to be optimized.

[0123] When the judgment result of step S301 is yes, step S301 is executed; when the judgment result of step S301 is no, step S302 is executed.

[0124] Step S302: All sunshine periods after the last photovoltaic energy storage full-rate period within the target day to be optimized are determined as candidate charging periods.

[0125] Step S303: Determine each sunshine period within the target day to be optimized as a candidate charging period.

[0126] After step S302 and step S303 are completed, step S304 is executed, wherein the number of the determined optional charging time periods is recorded as N, where N is a positive integer.

[0127] Step S304: constructing a charging optimization model for representing charging the photovoltaic energy storage device cluster using the power grid system in N optional charging time periods.

[0128] The decision variable in the charging optimization model is the grid charging amount corresponding to charging the photovoltaic energy storage device cluster using the grid system in N charging alternative time periods:

[0129] {Q_in1, Q_in2, ..., Q_in N}

[0130] The goal of the charging optimization model is to minimize the total charging cost of charging the photovoltaic energy storage device cluster using the power grid system during N charging alternative time periods, which can be expressed as follows:

[0131]

[0132] Cost represents the total charging cost, Q_in n Price_in represents the amount of grid charging corresponding to charging the photovoltaic energy storage device cluster using the grid system in the nth charging alternative period. n It represents the unit price of charging the photovoltaic energy storage device cluster using the power grid system during the nth charging alternative time period.

[0133] In some embodiments, the constraints of the charging optimization model include:

[0134] Condition 1: During the N available charging periods, the photovoltaic energy storage device cluster will not discharge to the grid system:

[0135] Q_in n ≥0

[0136] Condition 2: Among the N available charging time periods, the charging power of each available charging time period cannot be higher than the maximum charging power of the photovoltaic energy storage device cluster:

[0137]

[0138] Among them, t n Indicates the duration of the nth charging alternative period, P_in max Indicates the maximum charging power of the photovoltaic energy storage device cluster;

[0139] Condition 3: After the PV energy storage device cluster is charged using the grid system during N available charging periods, the total remaining PV energy storage capacity during the last sunshine period of the target day to be optimized is increased to the preset maximum PV energy storage capacity;

[0140]

[0141] C last It represents the total remaining photovoltaic energy storage capacity of the photovoltaic energy storage equipment cluster corresponding to the last sunshine period of the target day to be optimized when the grid system is not charged, C max Indicates the preset maximum photovoltaic energy storage capacity. represents the total amount of grid charging used to charge the photovoltaic energy storage device cluster during N optional charging periods;

[0142] Condition 4: During any available charging period, the total remaining photovoltaic energy storage capacity of the photovoltaic energy storage device cluster after completing the grid system charging will not exceed the preset maximum photovoltaic energy storage capacity:

[0143]

[0144] Among them, C n It represents the total remaining amount of photovoltaic energy storage in the nth charging alternative period of the photovoltaic energy storage device cluster when the grid system is not charging. It represents the total amount of grid charging that is used to charge the photovoltaic energy storage device using the grid system during the first n charging alternative time periods.

[0145] Step S305: Solve the charging optimization model using the first preset target optimization algorithm to obtain the corresponding current optimal solution. The current optimal solution includes the current optimal value of the grid charging amount corresponding to charging the photovoltaic energy storage device cluster using the power grid system in N optional charging time periods. The optional charging time periods in which the corresponding current optimal value of the grid charging amount is not 0 are used as daytime charging time periods.

[0146] It should be noted that the first preset target optimization algorithm in the present disclosure can adopt any existing algorithm for target optimization, such as genetic algorithm, particle swarm algorithm, ant colony algorithm, bat algorithm, etc. The specific processes of these target optimization algorithms belong to the conventional technology in this field and will not be elaborated here.

[0147] It should be noted that the above-mentioned step S3 including steps S301 to S305 is only an optional implementation scheme in the present disclosure. In actual applications, other methods can also be used to select the daytime charging period. For example, the last sunshine period is directly used as the daytime charging period, and the grid charging amount in the last sunshine period is equal to the difference between the preset maximum photovoltaic energy storage capacity and the total remaining photovoltaic energy storage capacity corresponding to the last sunshine period; for another example, a rechargeable alternative period with the largest total photovoltaic energy storage capacity can be selected from all rechargeable alternative period as the first daytime charging period, and the last sunshine period can be selected as the second daytime charging period. The grid charging amount corresponding to the first daytime charging period is Q1, and the grid charging amount of the second daytime charging period is Q2, where Q1=C max -C' max , Q1+Q2=C max -C last , C' maxThe maximum value of the total remaining PV energy storage capacity corresponding to all available charging time periods. In this disclosure, the daytime charging period determined in step S3 can be one or more, and the grid charging capacity corresponding to each daytime charging period can be designed accordingly based on the corresponding total remaining PV energy storage capacity. Examples are not given here one by one.

[0148] Figure 4 This is a flow chart of another power distribution optimization method based on photovoltaic energy storage equipment provided by the embodiment of the present disclosure. Figure 4 As shown, the power distribution optimization method not only includes steps S1 to S3 in the previous embodiment, but also includes step Sa before step S1.

[0149] Step Sa: Generate a photovoltaic energy storage remaining total power prediction model for a sunshine period that can predict the photovoltaic energy storage remaining total power corresponding to the target sunshine period.

[0150] The input information of the photovoltaic energy storage remaining total power prediction model for sunshine periods includes: the time period identifier of the target sunshine period within the target day to be optimized, the total regional power consumption of all loads connected to the photovoltaic energy storage device cluster in the target area during the target sunshine period, the temperature of the target area during the target sunshine period, and the cumulative sunshine duration of the target area during the target day to be optimized during the target sunshine period; the output of the photovoltaic energy storage remaining total power prediction model for sunshine periods is the photovoltaic energy storage remaining total power corresponding to the target sunshine period.

[0151] It should be noted that the input data of the photovoltaic energy storage remaining total power prediction model for the sunshine period in this disclosure and the subsequent photovoltaic energy storage remaining total power prediction model for the non-sunshine period both contain documents. This is because the temperature factor will affect the charging and discharging efficiency of the photovoltaic energy storage equipment, and therefore will affect the photovoltaic energy storage remaining total power of the photovoltaic energy storage equipment cluster in different time periods.

[0152] At this time, step S1 includes:

[0153] Step S101: Acquire first input information corresponding to each sunshine period within a target day to be optimized.

[0154] The first input information includes: the time period identifier of the corresponding sunshine period within the target day to be optimized, the total regional power consumption of all loads connected to the photovoltaic energy storage device cluster in the target area during the corresponding sunshine period, the temperature of the target area during the corresponding sunshine period, and the cumulative sunshine duration of the target area during the target day to be optimized at the end of the corresponding sunshine period.

[0155] The time period identifier of a sunshine period in the target day to be optimized can be determined according to the pre-configured flag setting rule corresponding to the specific time of the sunshine period. Figure 1 In the situation shown in the figure, the time period corresponding to the sunshine period from 7:00 to 8:00 is marked as "A8".

[0156] The total regional electricity consumption of the target area in a certain statistical period (either sunshine period or non-sunshine period) on the target day to be optimized can be predicted based on the total regional electricity consumption of the current area in the same period on multiple historical days. For example, the total regional electricity consumption in the statistical period on the target day to be optimized can be predicted based on the changing trend of the total regional electricity consumption in the same period on multiple consecutive historical days before the target day to be optimized. For another example, the average of the total regional electricity consumption in the same period on multiple historical days in the current area is taken, and the calculated result is used as the total regional electricity consumption of the target area in the statistical period on the target day to be optimized. Of course, the total regional electricity consumption of the target area in the statistical period on the target day to be optimized can also be set manually based on actual experience.

[0157] The temperature of the target area during a certain period (either a sunshine period or a non-sunshine period) of the target day to be optimized can be extracted from pre-collected weather forecast data of the target area on the target day to be optimized.

[0158] The cumulative sunshine duration of the target area at the end of a sunshine period on the target day to be optimized can be calculated based on the difference between the end time of the sunshine period and the sunrise time of the target day to be optimized (which can be queried through the weather forecast data of the target day to be optimized).

[0159] Step S102: input the first input information corresponding to each sunshine period in the target day to be optimized into the trained photovoltaic energy storage remaining total power prediction model for each sunshine period to obtain the photovoltaic energy storage remaining total power corresponding to each sunshine period in the target day to be optimized.

[0160] In the embodiment of the present disclosure, a prediction model for the total remaining power of photovoltaic energy storage during sunshine periods can be trained based on historical data, and then the trained prediction model can be used to predict the total remaining power of photovoltaic energy storage corresponding to each sunshine period within the target day to be optimized.

[0161] In some embodiments, step Sa includes: step Sa1 and step Sa2.

[0162] Step Sa1: Collect comprehensive information of the first historical period of a target area in multiple sunshine periods within multiple historical days.

[0163] The comprehensive information of the first historical period includes: a period identifier used to indicate the position of the corresponding sunshine period in a day, the total regional power consumption of all loads connected to the photovoltaic energy storage device cluster in the target area during the corresponding sunshine period, the temperature of the target area during the corresponding sunshine period, the cumulative sunshine duration of the target area at the end of the corresponding sunshine period, and the total remaining photovoltaic energy storage power of the photovoltaic energy storage device cluster in the target area corresponding to the corresponding sunshine period.

[0164] Step Sa2: Use the comprehensive information of the first historical period as a training sample, the period identifier, total regional power consumption, cumulative sunshine duration, temperature and cumulative sunshine duration in the comprehensive information of the first historical period as model inputs, and the total remaining photovoltaic energy storage power in the comprehensive information of the first historical period as model output. Train the first preset prediction model to obtain a prediction model for the total remaining photovoltaic energy storage power for the sunshine period.

[0165] In some embodiments, step Sa2 includes: steps Sa21 to Sa23.

[0166] Step Sa21: Divide all historical days into 8 groups according to the preset classification rules. The preset classification rules are: statutory holidays are divided into 1 group, and non-statutory holidays are divided into the remaining 7 groups according to 7 different dates from Monday to Sunday.

[0167] Step Sa22: For each group, the first historical period comprehensive information of all sunshine periods in each historical day included in the group is formed into the first historical period comprehensive information set corresponding to the group.

[0168] Step Sa23: For each group, the first historical period comprehensive information set corresponding to the group is used as a training sample set to train the first preset prediction model to obtain a photovoltaic energy storage remaining total power prediction model for the sunshine period corresponding to the group.

[0169] At this time, step S102 includes: step S1021 and step S1022.

[0170] Step S1021: Determine the group to which the target day to be optimized belongs according to the date of the target day to be optimized and the preset classification rules.

[0171] Step S1022: Input the first input information corresponding to each sunshine period within the target day to be optimized into the photovoltaic energy storage remaining total power prediction model for the sunshine period corresponding to the group to which the target day to be optimized belongs, and obtain the photovoltaic energy storage remaining total power corresponding to each sunshine period within the target day to be optimized.

[0172] In this disclosed embodiment, groups are created by grouping Monday through Sunday, which falls on statutory holidays and non-statutory holidays, and then training is performed separately based on the training sample sets corresponding to these groups. This effectively distinguishes between different date categories. During the prediction phase, the PV energy storage remaining total power prediction model is used to predict the sunshine period corresponding to the group to which the target day belongs, which helps improve the accuracy of the final prediction results.

[0173] Figure 5 This is a flow chart of another method for optimizing power distribution based on photovoltaic energy storage equipment provided by the embodiment of the present disclosure. Figure 5 As shown, the power distribution optimization method includes not only steps S1 to S3 in the previous embodiment, but also step Sb and steps S4 to S8.

[0174] It should be noted that the order in which steps Sb, S4-S8, and steps S1-S3 are executed in this embodiment is not limited. For example, steps Sb, S4-S8 may be executed before steps S1-S3, after steps S1-S3, or simultaneously with steps S1-S3. In this disclosure, it is sufficient to ensure that step Sb is executed before steps S4-S8.

[0175] Sb. Generate a prediction model for the total remaining photovoltaic energy storage power for a non-sunshine period that can predict the total remaining photovoltaic energy storage power corresponding to the target non-sunshine period after the last sunshine period in a day.

[0176] The input information of the prediction model for the total remaining photovoltaic energy storage power during non-sunshine periods includes: the time period identifier of the non-target sunshine period within the target day to be optimized, the total remaining photovoltaic energy storage power corresponding to the sunshine period that is before and closest to the target non-sunshine period, the total regional power consumption of all loads connected to the photovoltaic energy storage device cluster in the target area during the target non-sunshine period, and the temperature of the target area during the target non-sunshine period; the output of the prediction model for the total remaining photovoltaic energy storage power during non-sunshine periods is the total remaining photovoltaic energy storage power corresponding to the target non-sunshine period.

[0177] In practical applications, step Sb can be executed synchronously with step Sa in the previous embodiment.

[0178] Step S4: Filter out non-sunshine periods that are during the peak power consumption period of the power grid within the target day to be optimized from all non-sunshine periods after the last sunshine period within the target day to be optimized as candidate discharge periods.

[0179] The peak power consumption period of the target day to be optimized can be determined based on the historical load of the power grid system (such as the daily load curve of residents obtained based on historical data), or it can be set manually based on actual conditions.

[0180] Step S5: Obtain second input information of the last dischargeable candidate time period within the target day to be optimized.

[0181] The second input information includes: the time period identifier of the last dischargeable alternative time period, the total remaining photovoltaic energy storage capacity corresponding to the sunshine period immediately preceding and closest to the last dischargeable alternative time period, the regional total power consumption of all loads connected to the photovoltaic energy storage device cluster in the target area during the last dischargeable alternative time period, and the temperature of the target area during the last dischargeable alternative time period (for the specific method of obtaining the time period identifier, regional total power consumption, and temperature of the last dischargeable alternative time period, please refer to the previous content). The total remaining photovoltaic energy storage capacity corresponding to the sunshine period immediately preceding and closest to the last dischargeable alternative time period is set to the preset maximum photovoltaic energy storage capacity (this is because the total remaining photovoltaic energy storage capacity of the last sunshine period of the target day to be optimized can be increased to the preset maximum photovoltaic energy storage capacity through step S3).

[0182] Step S6: Input the second input information of the last dischargeable alternative time period in the target day to be optimized into the trained photovoltaic energy storage remaining total power prediction model for non-sunshine period to obtain the photovoltaic energy storage remaining total power corresponding to the last dischargeable alternative time period in the target day to be optimized.

[0183] It should be noted that after entering the non-sunshine period from the sunshine period, since the photovoltaic energy storage equipment no longer produces electricity and the photovoltaic energy storage equipment has priority in power supply over the power grid system, the total remaining photovoltaic energy storage capacity of the photovoltaic energy storage equipment cluster will continue to decrease until the total remaining photovoltaic energy storage capacity of the photovoltaic energy storage equipment cluster reaches 0, and the power grid system will start to supply power.

[0184] Step S7: Determine whether the total remaining amount of photovoltaic energy storage corresponding to the last dischargeable alternative time period within the target day to be optimized is 0.

[0185] If the result of step S7 is negative, it indicates that there is still residual power in the PV energy storage device cluster at the end of the peak period of grid electricity consumption. Therefore, the PV energy storage device cluster can be used to discharge power to the grid system during the peak period to reduce the grid load, thereby achieving load "peak shaving". Then, step S8 is executed. If the result of step S7 is positive, it indicates that there is no residual power in the PV energy storage device cluster before the peak period of grid electricity consumption ends, and load "peak shaving" cannot be performed during the peak period of grid electricity consumption.

[0186] Step S8: Determine at least one candidate discharging time period from all candidate discharging time periods within the target day to be optimized as the peak power consumption discharge time period, and the energy storage cluster discharge amount of the photovoltaic energy storage device cluster to the power grid system during each peak power consumption discharge time period, and the sum of the energy storage cluster discharge amounts corresponding to all peak power consumption discharge time periods within the target day to be optimized and the total remaining photovoltaic energy storage capacity corresponding to the last candidate discharging time period within the target day to be optimized.

[0187] Through step S8, after the photovoltaic energy storage equipment is used to discharge to the power grid system during the peak period of power consumption in the power grid, the total remaining amount of photovoltaic energy storage corresponding to the last dischargeable alternative time period drops to 0, achieving sufficient load "peak shaving".

[0188] In some embodiments, step Sb includes: step Sb1 and step Sb2.

[0189] Step Sb1: Collect comprehensive information about the second historical period of the target area for multiple non-sunshine periods after the last sunshine period within multiple historical days. The comprehensive information about the second historical period includes: a period identifier indicating the position of the corresponding non-sunshine period in a day, the total remaining photovoltaic energy storage capacity corresponding to the sunshine period that is immediately before and closest to the corresponding non-sunshine period, the total regional power consumption of all loads connected to the photovoltaic energy storage device cluster in the target area during the corresponding non-sunshine period, the temperature of the target area during the corresponding non-sunshine period, and the total remaining photovoltaic energy storage capacity of the photovoltaic energy storage device cluster in the target area during the corresponding sunshine period.

[0190] Step Sb2: Use the comprehensive information of the second historical period as a training sample. The period identifier in the comprehensive information of the second historical period, the total remaining photovoltaic energy storage capacity corresponding to the sunshine period immediately before and closest to the corresponding non-sunshine period, the total regional power consumption, and the temperature are used as model inputs. The total remaining photovoltaic energy storage capacity of the photovoltaic energy storage device cluster in the target area corresponding to the sunshine period in the comprehensive information of the second historical period is used as the model output. The second preset prediction model is trained to obtain a prediction model for the total remaining photovoltaic energy storage capacity for the non-sunshine period.

[0191] Wherein, step Sb2 includes: step Sb21 to step Sa23.

[0192] Step Sb21: Divide all historical days into 8 groups according to the preset classification rules. The preset classification rules are: statutory holidays are divided into 1 group, and non-statutory holidays are divided into the remaining 7 groups according to 7 different dates from Monday to Sunday.

[0193] Step Sb22: For each group, the second historical period comprehensive information of all non-sunshine periods after the last sunshine period in each historical day included in the group constitutes the second historical period comprehensive information set corresponding to the group.

[0194] Step Sa23: For each group, the second historical period comprehensive information set corresponding to the group is used as a training sample set to train the second preset prediction model to obtain a prediction model for the total remaining photovoltaic energy storage power for the non-sunshine period corresponding to the group.

[0195] Step S6 includes: step S601 and step S602.

[0196] Step S601: Determine the group to which the target day to be optimized belongs according to the date of the target day to be optimized and the preset classification rules.

[0197] Step S602: Input the second input information of the last dischargeable alternative time period on the target day to be optimized into the photovoltaic energy storage remaining total power prediction model for the non-sunshine period corresponding to the group to which the target day to be optimized belongs, and obtain the photovoltaic energy storage remaining total power corresponding to the last dischargeable alternative time period on the target day to be optimized.

[0198] In this disclosed embodiment, groups are created by grouping Monday through Sunday, which falls on statutory holidays and non-statutory holidays, and then training is performed separately based on the training sample sets corresponding to these groups. This effectively distinguishes between different date categories. During the forecasting phase, the PV energy storage remaining total power prediction model is used for the non-sunshine period corresponding to the group to which the target day belongs, thereby improving the accuracy of the final forecast results.

[0199] In some embodiments, the number of the candidate discharge time periods screened out in step S4 is M, where M is a positive integer; and step S8 includes:

[0200] Step S801: constructing a discharge optimization model for representing discharging the power grid system using a photovoltaic energy storage device cluster in M ​​dischargeable candidate time periods;

[0201] The decision variables in the discharge optimization model are the energy storage cluster discharge amounts corresponding to the photovoltaic energy storage device cluster discharging to the grid in the M dischargeable alternative time periods.

[0202] The goal of the discharge optimization model is to maximize the total discharge revenue of discharging the photovoltaic energy storage device cluster to the grid during the M dischargeable alternative time periods, which can be expressed as follows:

[0203]

[0204] Gain represents the total discharge gain, Q_out mPrice_out represents the energy storage cluster discharge amount corresponding to the discharge of the photovoltaic energy storage device cluster to the grid during the mth discharge alternative period. m represents the unit price benefit of discharging the photovoltaic energy storage device cluster to the grid during the mth discharge alternative period;

[0205] The constraints of the discharge optimization model include:

[0206] Condition 1: During the M dischargeable candidate periods, the grid system will not charge the photovoltaic energy storage device cluster:

[0207] Q_out m ≥0

[0208] Condition 2: Among the M dischargeable candidate time periods, the discharge power of each dischargeable candidate time period cannot exceed the maximum discharge power of the photovoltaic energy storage device cluster:

[0209]

[0210] Among them, t' m Indicates the duration of the mth discharge alternative period, P_out max Indicates the maximum discharge power of the photovoltaic energy storage device cluster;

[0211] Condition 3: After discharging the photovoltaic energy storage device into the grid system during M dischargeable candidate time periods, the total remaining photovoltaic energy storage capacity corresponding to the last dischargeable candidate time period drops to 0;

[0212]

[0213] C' last It indicates the total remaining amount of photovoltaic energy storage power corresponding to the last dischargeable alternative period of the target optimization day when the photovoltaic energy storage device cluster does not discharge the grid system. It represents the total discharge amount of the energy storage cluster that is discharged to the power grid system by using the photovoltaic energy storage device cluster during M dischargeable alternative time periods;

[0214] Step S802: Utilize a second preset target optimization algorithm to solve the discharge optimization model and obtain a corresponding current optimal solution. The current optimal solution includes the current optimal value of the energy storage cluster discharge amount corresponding to discharging the power grid system using the photovoltaic energy storage device cluster in M ​​dischargeable alternative time periods. The corresponding dischargeable alternative time periods in which the current optimal value of the energy storage cluster discharge amount is not 0 are used as peak power consumption discharge periods.

[0215] It should be noted that the second preset target optimization algorithm in this disclosure can adopt any existing algorithm for target optimization, such as a genetic algorithm, a particle swarm algorithm, an ant colony algorithm, a bat algorithm, etc. The specific processes of these target optimization algorithms belong to conventional techniques in the field and are not described in detail here. In this disclosure, the first preset target optimization algorithm and the second preset target optimization algorithm can be the same or different.

[0216] Figure 6 This is a structural block diagram of a power distribution optimization system based on photovoltaic energy storage equipment provided by an embodiment of the present disclosure. Figure 6 As shown, based on the same inventive concept, the embodiment of the present disclosure also provides a power distribution optimization system based on photovoltaic energy storage equipment. The power distribution optimization system can implement the power distribution optimization method provided in the previous embodiment. The power distribution optimization system includes: an acquisition module, a judgment module and an optimization module.

[0217] The acquisition module is configured to obtain the total remaining photovoltaic energy storage capacity of the photovoltaic energy storage device cluster in the target area corresponding to each sunshine period within the target day to be optimized.

[0218] The judgment module is configured to judge whether the last sunshine period of the target day to be optimized is a period of full photovoltaic energy storage. The period of full photovoltaic energy storage refers to a period when the corresponding total remaining photovoltaic energy storage power is equal to the preset maximum photovoltaic energy storage power.

[0219] The optimization module is configured to, when the judgment module determines that the last sunshine period of the target day to be optimized is not a period with full photovoltaic energy storage, determine at least one sunshine period from all sunshine periods of the target day to be optimized as a daytime charging period based on the total remaining photovoltaic energy storage power corresponding to each sunshine period of the target day to be optimized, and the grid charging amount used to charge the photovoltaic energy storage device cluster using the power grid system during each daytime charging period, and the total grid charging amount corresponding to all daytime charging periods of the target day to be optimized is equal to the difference between the preset maximum photovoltaic energy storage power and the total remaining photovoltaic energy storage power corresponding to the last sunshine period.

[0220] For the detailed description of each of the above modules, please refer to the corresponding content in the previous embodiments, which will not be repeated here.

[0221] Based on the same inventive concept, an embodiment of the present disclosure further provides an electronic device. Figure 7 FIG. 1 is a schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure. Figure 7As shown, an embodiment of the present disclosure provides an electronic device comprising: one or more processors 101, a memory 102, and one or more I / O interfaces 103. The memory 102 stores one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement any of the above-described methods for optimizing power distribution based on photovoltaic energy storage devices; the one or more I / O interfaces 103 are connected between the processor and the memory and are configured to implement information exchange between the processor and the memory.

[0222] Among them, the processor 101 is a device with data processing capabilities, including but not limited to a central processing unit (CPU); the memory 102 is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically such as SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), and flash memory (FLASH); the I / O interface (read-write interface) 103 is connected between the processor 101 and the memory 102, and can realize information interaction between the processor 101 and the memory 102, including but not limited to a data bus (Bus), etc.

[0223] In some embodiments, the processor 101 , the memory 102 , and the I / O interface 103 are connected to each other via a bus 104 , and further connected to other components of the computing device.

[0224] In some embodiments, the one or more processors 101 include a field programmable gate array.

[0225] According to an embodiment of the present disclosure, a computer-readable medium is further provided, wherein the computer-readable medium stores a computer program, wherein when the program is executed by a processor, the steps of the power distribution optimization method based on photovoltaic energy storage equipment as described in any of the above embodiments are implemented.

[0226] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, including a computer program carried on a machine-readable medium, the computer program containing program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part, and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), the above-mentioned functions defined in the system of the present disclosure are executed.

[0227] It should be noted that the computer-readable medium described in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wireline, optical fiber cable, RF, or any suitable combination thereof.

[0228] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the aforementioned module, program segment, or a part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0229] It is understood that the above embodiments are merely exemplary embodiments for illustrating the principles of the present disclosure, and the present disclosure is not limited thereto. Those skilled in the art may make various modifications and improvements without departing from the spirit and substance of the present disclosure, and such modifications and improvements are also considered to be within the scope of protection of the present disclosure.

Claims

1. A power distribution optimization method based on photovoltaic energy storage equipment, characterized in that: A full day is divided into multiple statistical periods and the corresponding statistical period is determined to be a sunshine period or a non-sunshine period according to the sunrise time and sunset time of the day. The power distribution optimization method includes: Step S1: Obtain the total remaining photovoltaic energy storage capacity of the photovoltaic energy storage device cluster in the target area corresponding to each sunshine period on the target day to be optimized; Step S2: determining whether the last sunshine period of the target day to be optimized is a period of full photovoltaic energy storage, wherein the period of full photovoltaic energy storage refers to a period when the remaining total amount of photovoltaic energy storage is equal to the preset maximum amount of photovoltaic energy storage; When the judgment result of step S2 is no, step S3 is executed; Step S3: Based on the total remaining photovoltaic energy storage capacity corresponding to each sunshine period within the target day to be optimized, determine at least one sunshine period from all sunshine periods within the target day to be optimized as a daytime charging period and the grid charging amount for charging the photovoltaic energy storage device cluster using the power grid system during each daytime charging period, and the sum of the grid charging amounts corresponding to all the daytime charging periods within the target day to be optimized is equal to the difference between the preset maximum photovoltaic energy storage capacity and the total remaining photovoltaic energy storage capacity corresponding to the last sunshine period.

2. The power distribution optimization method according to claim 1, characterized in that: Step S3 includes: Step S301: Determine whether there is at least one sunshine period in the target day to be optimized, except for the last sunshine period, that is a period of full photovoltaic energy storage; When the judgment result of step S301 is yes, step S301 is executed; when the judgment result of step S301 is no, step S302 is executed; Step S302: determining each sunshine period after the last photovoltaic energy storage full-rate period within the target day to be optimized as a charging candidate period; Step S303: determining each sunshine period within the target day to be optimized as a candidate charging period; After step S302 and step S303 are completed, step S304 is executed, wherein the number of the determined optional charging time periods is recorded as N, where N is a positive integer; Step S304: Constructing a charging optimization model for representing charging the photovoltaic energy storage device cluster using the power grid system during the N candidate charging time periods. The decision variables in the charging optimization model are the power grid charging amounts corresponding to charging the photovoltaic energy storage device cluster using the power grid system during the N candidate charging time periods. The objective of the charging optimization model is to minimize the total charging cost of charging the photovoltaic energy storage device cluster using the power grid system during the N candidate charging time periods. Step S305: Solve the charging optimization model using a first preset target optimization algorithm to obtain a corresponding current optimal solution. The current optimal solution includes the current optimal value of the grid charging amount corresponding to charging the photovoltaic energy storage device cluster using the power grid system in N optional charging time periods. The optional charging time period in which the corresponding current optimal value of the grid charging amount is not 0 is used as the daytime charging time period.

3. The power distribution optimization method according to claim 2, characterized in that: The total charging cost of using the grid system to charge the photovoltaic energy storage device cluster during N charging alternative time periods is minimized, which can be expressed as follows: Cost represents the total charging cost, Q_in n Price_in represents the amount of grid charging corresponding to charging the photovoltaic energy storage device cluster using the grid system in the nth charging alternative period. n The unit price of charging the photovoltaic energy storage device cluster using the power grid system during the nth charging alternative time period; The constraints of the charging optimization model include: Condition 1: During the N available charging periods, the photovoltaic energy storage device cluster will not discharge to the grid system: Q_in n ≥0 Condition 2: Among the N available charging time periods, the charging power of each available charging time period cannot be higher than the maximum charging power of the photovoltaic energy storage device cluster: Among them, t n Indicates the duration of the nth charging alternative period, P_in max Indicates the maximum charging power of the photovoltaic energy storage device cluster; Condition 3: After the photovoltaic energy storage device cluster is charged using the power grid system during N optional charging time periods, the total remaining photovoltaic energy storage capacity during the last sunshine period of the target day to be optimized is increased to the preset maximum photovoltaic energy storage capacity; C last C represents the total remaining photovoltaic energy storage capacity of the photovoltaic energy storage device cluster corresponding to the last sunshine period of the target day to be optimized when the grid system is not charged. max Indicates the preset maximum amount of photovoltaic energy storage, represents the total amount of grid charging used to charge the photovoltaic energy storage device cluster during N optional charging periods; Condition 4: During any available charging period, the total remaining photovoltaic energy storage capacity of the photovoltaic energy storage device cluster after completing the grid system charging will not exceed the preset maximum photovoltaic energy storage capacity: Among them, C n represents the total remaining photovoltaic energy storage capacity of the photovoltaic energy storage device cluster in the nth charging alternative time period when the grid system is not charging. It represents the total amount of grid charging that is used to charge the photovoltaic energy storage device using the grid system during the first n charging alternative time periods.

4. The power distribution optimization method according to claim 1, characterized in that: Before step S1, the method further includes: Step Sa, generating a photovoltaic energy storage remaining total power prediction model for a sunshine period that can predict the photovoltaic energy storage remaining total power corresponding to the target sunshine period; The input information of the photovoltaic energy storage remaining total power prediction model for sunshine period includes: the time period identifier of the target sunshine period within the target day to be optimized, the regional total power consumption of all loads connected to the photovoltaic energy storage device cluster in the target area during the target sunshine period, the temperature of the target area during the target sunshine period, and the cumulative sunshine duration of the target area during the target day to be optimized during the target sunshine period; the output of the photovoltaic energy storage remaining total power prediction model for sunshine period is the photovoltaic energy storage remaining total power corresponding to the target sunshine period; Step S1 includes: Step S101: Acquire first input information corresponding to each sunshine period within a target day to be optimized, the first input information including: a period identifier of the corresponding sunshine period within the target day to be optimized, the total regional power consumption of all loads connected to the photovoltaic energy storage device cluster within the target area during the corresponding sunshine period, the temperature of the target area during the corresponding sunshine period, and the cumulative sunshine duration of the target area within the target day to be optimized at the end of the corresponding sunshine period; Step S102: input the first input information corresponding to each sunshine period in the target day to be optimized into the trained photovoltaic energy storage remaining total power prediction model for the sunshine period to obtain the photovoltaic energy storage remaining total power corresponding to each sunshine period in the target day to be optimized.

5. The power distribution optimization method according to claim 4, characterized in that: Step Sa includes: Step Sa1: Collecting first historical period comprehensive information of the target area for multiple sunshine periods within multiple historical days, the first historical period comprehensive information including: a period identifier for indicating the position of the corresponding sunshine period in a day, the total regional power consumption of all loads connected to the photovoltaic energy storage device cluster in the target area during the corresponding sunshine period, the temperature of the target area during the corresponding sunshine period, the cumulative sunshine duration of the target area on the day at the end of the corresponding sunshine period, and the total remaining photovoltaic energy storage power of the photovoltaic energy storage device cluster in the target area corresponding to the corresponding sunshine period; Step Sa2: Use the comprehensive information of the first historical period as a training sample, the period identifier, the total power consumption of the area, the cumulative sunshine duration, the temperature and the cumulative sunshine duration in the comprehensive information of the first historical period as model inputs, and the total remaining photovoltaic energy storage power in the comprehensive information of the first historical period as model output. Train the first preset prediction model to obtain a prediction model for the total remaining photovoltaic energy storage power for the sunshine period.

6. The power distribution optimization method according to claim 5, characterized in that: The step Sa2 comprises: Step Sa21: Divide all the historical days into 8 groups according to a preset classification rule, wherein the preset classification rule is: statutory holidays are divided into 1 group, and non-statutory holidays are divided into the remaining 7 groups according to 7 different dates from Monday to Sunday; Step Sa22: for each group, the first historical period comprehensive information of all sunshine periods in each historical day included in the group is used to form a first historical period comprehensive information set corresponding to the group; Step Sa23: For each group, the first historical period comprehensive information set corresponding to the group is used as a training sample set to train the first preset prediction model to obtain a prediction model for the total remaining photovoltaic energy storage power during the sunshine period corresponding to the group; Step S102 includes: Step S1021: determining the group to which the target day to be optimized belongs according to the preset classification rule based on the date of the target day to be optimized; Step S1022: input the first input information corresponding to each sunshine period within the target day to be optimized into the photovoltaic energy storage remaining total power prediction model for the sunshine period corresponding to the group to which the target day to be optimized belongs, and obtain the photovoltaic energy storage remaining total power corresponding to each sunshine period within the target day to be optimized.

7. The power distribution optimization method according to any one of claims 1 to 6, characterized in that: Also includes: Sb, generating a non-sunshine period photovoltaic energy storage remaining total power prediction model capable of predicting the target non-sunshine period after the last sunshine period in a day. The input information of the prediction model for the total remaining photovoltaic energy storage capacity for non-sunshine periods includes: the period identifier of the non-target sunshine period within the target day to be optimized, the total remaining photovoltaic energy storage capacity corresponding to the sunshine period that is immediately before and closest to the target non-sunshine period, the total regional power consumption of all loads connected to the photovoltaic energy storage device cluster in the target area during the target non-sunshine period, and the temperature of the target area during the target non-sunshine period; the output of the prediction model for the total remaining photovoltaic energy storage capacity for non-sunshine periods is the total remaining photovoltaic energy storage capacity corresponding to the target non-sunshine period; Step S4: selecting non-sunshine periods that are during the peak power consumption period of the power grid during the target day to be optimized from all non-sunshine periods after the last sunshine period during the target day to be optimized as candidate discharge periods; Step S5: Obtain second input information of the last dischargeable alternative time period within the target day to be optimized, the second input information including: a time period identifier of the last dischargeable alternative time period, a total remaining photovoltaic energy storage capacity corresponding to a sunshine period immediately preceding and closest to the last dischargeable alternative time period, a total regional power consumption of all loads connected to the photovoltaic energy storage device cluster within the target area during the last dischargeable alternative time period, and a temperature of the target area during the last dischargeable alternative time period, wherein the total remaining photovoltaic energy storage capacity corresponding to the sunshine period immediately preceding and closest to the last dischargeable alternative time period is set to the preset maximum photovoltaic energy storage capacity; Step S6: inputting the second input information of the last dischargeable alternative time period within the target day to be optimized into the trained photovoltaic energy storage remaining total power prediction model for the non-sunshine period to obtain the photovoltaic energy storage remaining total power corresponding to the last dischargeable alternative time period within the target day to be optimized; Step S7: determining whether the total remaining amount of photovoltaic energy storage corresponding to the last dischargeable alternative time period within the target day to be optimized is 0; When the judgment result of step S7 is no, step S8 is executed; Step S8: Determine at least one optional discharge time period from all the optional discharge time periods within the target day to be optimized as the peak power consumption discharge time period, and the energy storage cluster discharge amount of the photovoltaic energy storage device cluster discharged to the power grid system during each peak power consumption discharge time period, and the sum of the energy storage cluster discharge amounts corresponding to all the peak power consumption discharge time periods within the target day to be optimized and the total remaining photovoltaic energy storage capacity corresponding to the last optional discharge time period within the target day to be optimized.

8. The power distribution optimization method according to claim 7, characterized in that: Step Sb includes: Step Sb1: Collecting comprehensive information of a second historical period for a plurality of non-sunshine periods after the last sunshine period in the target area over a plurality of historical days, the second historical period comprehensive information including: a period identifier indicating the position of the corresponding non-sunshine period in a day, the total remaining photovoltaic energy storage capacity corresponding to a sunshine period immediately before and closest to the corresponding non-sunshine period, the total regional power consumption of all loads connected to the photovoltaic energy storage device cluster in the target area during the corresponding non-sunshine period, the temperature of the target area during the corresponding non-sunshine period, and the total remaining photovoltaic energy storage capacity corresponding to the photovoltaic energy storage device cluster in the target area during the corresponding sunshine period; Step Sb2: Using the second historical period comprehensive information as a training sample, the period identifier in the second historical period comprehensive information, the total remaining photovoltaic energy storage capacity corresponding to the sunshine period immediately before and closest to the corresponding non-sunshine period, the total regional power consumption, and the temperature as model inputs, and the total remaining photovoltaic energy storage capacity corresponding to the photovoltaic energy storage device cluster in the target area during the corresponding sunshine period in the second historical period comprehensive information as the model output, training the second preset prediction model to obtain a photovoltaic energy storage remaining total capacity prediction model for the non-sunshine period; Wherein, step Sb2 includes: Step Sb21: Divide all the historical days into 8 groups according to a preset classification rule, wherein the preset classification rule is: statutory holidays are divided into 1 group, and non-statutory holidays are divided into the remaining 7 groups according to 7 different dates from Monday to Sunday; Step Sb22: for each group, the second historical period comprehensive information of all non-sunshine periods after the last sunshine period in each historical day included in the group is used to form a second historical period comprehensive information set corresponding to the group; Step Sa23: For each group, the second historical period comprehensive information set corresponding to the group is used as a training sample set to train the second preset prediction model to obtain a prediction model for the total remaining photovoltaic energy storage power for the non-sunshine period corresponding to the group; Step S6 includes: Step S601: determining the group to which the target day to be optimized belongs according to the preset classification rule based on the date of the target day to be optimized; Step S602: Input the second input information of the last dischargeable alternative time period within the target day to be optimized into the photovoltaic energy storage remaining total power prediction model for the non-sunshine time period corresponding to the group to which the target day to be optimized belongs, and obtain the photovoltaic energy storage remaining total power corresponding to the last dischargeable alternative time period within the target day to be optimized.

9. The power distribution optimization method according to claim 7, characterized in that: The number of the candidate discharge time periods screened out in step S4 is M, where M is a positive integer; Step S8 includes: Step S801: constructing a discharge optimization model for representing discharging the power grid system using a photovoltaic energy storage device cluster in M ​​dischargeable candidate time periods; The decision variables in the discharge optimization model are the energy storage cluster discharge amounts corresponding to the photovoltaic energy storage device cluster discharging the power grid in the M dischargeable alternative time periods; The goal of the discharge optimization model is to maximize the total discharge revenue of discharging the photovoltaic energy storage device cluster to the grid during M dischargeable candidate time periods, which can be expressed as follows: Gain represents the total discharge gain, Q_out m Price_out represents the energy storage cluster discharge amount corresponding to the discharge of the photovoltaic energy storage device cluster to the grid during the mth discharge alternative period. m represents the unit price benefit of discharging the photovoltaic energy storage device cluster to the grid during the mth discharge alternative period; The constraints of the discharge optimization model include: Condition 1: During the M dischargeable candidate periods, the grid system will not charge the photovoltaic energy storage device cluster: Q_out m ≥0 Condition 2: Among the M dischargeable candidate time periods, the discharge power of each dischargeable candidate time period cannot exceed the maximum discharge power of the photovoltaic energy storage device cluster: Among them, t' m Indicates the duration of the mth discharge alternative period, P_out max Indicates the maximum discharge power of the photovoltaic energy storage device cluster; Condition 3: After discharging the photovoltaic energy storage device to the power grid during M dischargeable candidate time periods, the total remaining photovoltaic energy storage capacity corresponding to the last dischargeable candidate time period drops to 0; C' last Indicates the total remaining photovoltaic energy storage capacity of the photovoltaic energy storage device cluster corresponding to the last dischargeable alternative time period within the target day to be optimized when no discharge is performed to the grid system. It represents the total discharge amount of the energy storage cluster that is discharged to the power grid system by using the photovoltaic energy storage device cluster during M dischargeable alternative time periods; Step S802: Solve the discharge optimization model using a second preset target optimization algorithm to obtain a corresponding current optimal solution. The current optimal solution includes the current optimal value of the energy storage cluster discharge corresponding to discharging the power grid system using the photovoltaic energy storage device cluster in M ​​dischargeable alternative time periods. The corresponding dischargeable alternative time periods in which the current optimal value of the energy storage cluster discharge is not zero are used as the peak power consumption discharge period.

10. A power distribution optimization system based on photovoltaic energy storage equipment, characterized in that: The power distribution optimization system is configured to implement the power distribution optimization method according to any one of claims 1 to 9, and the power distribution optimization system includes: An acquisition module is configured to obtain the total remaining photovoltaic energy storage capacity of the photovoltaic energy storage device cluster in the target area corresponding to each sunshine period within the target day to be optimized; a judgment module configured to judge whether the last sunshine period of the target day to be optimized is a period of full photovoltaic energy storage, wherein the full photovoltaic energy storage period refers to a period when the corresponding total remaining photovoltaic energy storage capacity is equal to a preset maximum photovoltaic energy storage capacity; The optimization module is configured to, when the judgment module determines that the last sunshine period of the target day to be optimized is not a period with full photovoltaic energy storage, determine, based on the total remaining photovoltaic energy storage power corresponding to each sunshine period of the target day to be optimized, at least one sunshine period from all sunshine periods of the target day to be optimized as a daytime charging period, and a grid charging amount for charging the photovoltaic energy storage device cluster using the power grid system during each daytime charging period, and the sum of the grid charging amounts corresponding to all the daytime charging periods of the target day to be optimized is equal to the difference between the preset maximum photovoltaic energy storage power and the total remaining photovoltaic energy storage power corresponding to the last sunshine period.

Images