A method for predicting the load of new energy photovoltaic power generation

Abstract

This invention relates to the field of power generation load forecasting technology, and particularly to a method for forecasting the load of new energy photovoltaic power generation. The method includes: locating the deployment location of the new energy photovoltaic power station, calculating the average output power, configuring the grid connection area of ​​the new energy photovoltaic power station, collecting radar cloud images at the deployment location, and inputting them into a pre-constructed multi-level forecasting model to output the load gap and corresponding peak periods of the grid connection area; constructing a mobile energy storage platform and extracting registrants; determining the target time period based on the peak periods; issuing access reminders for new energy vehicles to the registrants, obtaining power access permissions, and using the power access permissions and peak periods. This invention stabilizes the predicted load gap at a fixed value through a peak-shaving and valley-filling mechanism, significantly reducing power load fluctuations in the grid connection area while greatly improving user experience and economic benefits.

Description

Technical Field

[0001] This invention relates to the field of power generation load forecasting technology, and in particular to a method for forecasting the load of new energy photovoltaic power generation. Background Technology

[0002] New energy photovoltaic power generation load forecasting refers to using multi-source data such as meteorological data, historical power generation data and photovoltaic power plant parameters, combined with machine learning, deep learning or data modeling methods, to predict the photovoltaic power generation power at future moments. New energy photovoltaic power generation load is usually related to solar radiation intensity and duration.

[0003] However, load forecasts are generally approximate. When clouds suddenly block the sun, the amount of radiation received by photovoltaic modules drops sharply, leading to a sudden drop in photovoltaic power generation. When the clouds disperse or thin, the photovoltaic power generation quickly rebounds. This change can cause drastic fluctuations in the output power of photovoltaic power generation. Although traditional controllable power generation systems such as thermal power and hydropower can play a regulatory role, these systems usually have a slow response speed and are unable to cope with the rapid fluctuations in photovoltaic power. Therefore, "how to balance the predicted grid-connected power of new energy photovoltaic power plants" is the technical problem that this invention aims to solve. Summary of the Invention

[0004] The purpose of this invention is to provide a method for predicting the load of new energy photovoltaic power generation, so as to solve the problem of "how to balance the predicted grid-connected power of new energy photovoltaic power plants" mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] A method for predicting the load of new energy photovoltaic power generation, the method comprising:

[0007] The deployment location of the new energy photovoltaic power station is located, the average output power is calculated, the grid connection area of ​​the new energy photovoltaic power station is configured, radar cloud images of the deployment location are collected and input into a pre-built multi-level prediction model, and the load gap and corresponding peak period of the grid connection area are output.

[0008] A mobile energy storage platform is constructed, and registrants are extracted. Based on the peak period, a target period is determined, and a reminder for the access of new energy vehicles is sent to the registrants to obtain power access rights. Based on the power access rights and the peak period, the new energy vehicles are connected to the mobile energy storage platform to construct a load balancing mechanism.

[0009] Create a root node that corresponds one-to-one with a new energy photovoltaic power station, define the new energy vehicles in the corresponding grid-connected area as target vehicles, create child nodes corresponding to the target vehicles, and attach the child nodes to the root nodes. Calculate the fixed gap for each root node, configure the scheduling starting point, construct a backup link between the scheduling starting point and the grid-connected area, and optimize the fixed gap.

[0010] Furthermore, the steps of locating the deployment location of the new energy photovoltaic power station, calculating the average output power, and collecting radar cloud images at the deployment location include:

[0011] The new energy photovoltaic power station is divided into several groups, a mapping between the fixed gap and the group is established, and the backup link is corrected;

[0012] Insert timestamps into the radar cloud image and configure the statistical step size of the average output power.

[0013] Furthermore, the step of collecting radar cloud images at the deployment location and inputting them into a pre-built load forecasting model to output the load gap and corresponding time includes:

[0014] An output power prediction model is created, historical power generation data of the new energy power plant is configured, the irradiance is identified from the radar cloud image, the historical power generation data and irradiance are input into the output power prediction model, and the predicted power generation is output.

[0015] Create a load forecasting model, collect historical load data of the grid-connected area, input the predicted power generation and historical load data into the load forecasting model, and output the load gap;

[0016] Based on the timestamp, a correspondence between load gaps and peak periods is established, and the output power prediction model and load prediction model are integrated to obtain a multi-level prediction model.

[0017] Furthermore, the step of determining the target time period based on the peak period includes:

[0018] Select a test day, determine if there is a peak period on the test day, and if so, receive the charging and discharging reminder time uploaded by the user and determine it as the target period;

[0019] When the current time coincides with the target time period, an access reminder is generated and sent to the registrant.

[0020] Furthermore, the method also includes:

[0021] Using the multi-level prediction model, load troughs in the grid-connected area are identified, and the time corresponding to the load troughs is defined as the trough period.

[0022] Furthermore, the load balancing mechanism is as follows: during peak hours, new energy vehicles are used to discharge electricity to replenish the grid-connected area, and during off-peak hours, new energy vehicles in the grid-connected area are charged.

[0023] Furthermore, the method also includes:

[0024] The total discharge power of new energy vehicles was calculated, and several power ranges were defined.

[0025] Edit the reward rule set and construct a lookup table, wherein the lookup table consists of power range items and reward rule items.

[0026] Furthermore, the steps of creating a root node corresponding one-to-one with a new energy photovoltaic power station, defining the new energy vehicles in the corresponding grid-connected area as target vehicles, and creating child nodes corresponding to the target vehicles include:

[0027] Integrate the root node and child nodes to generate a balanced tree, set its height, and construct relevant relationships based on the height of the balanced tree and the fixed gap;

[0028] Grant management permissions to the mobile energy storage platform to the balanced tree and correct its height.

[0029] Furthermore, the step of calculating the fixed notch for each root node includes:

[0030] Determine whether the fixed gap is greater than a threshold. If so, define a critical node and embed a tag generated from historical load data.

[0031] Switch the backup link to the scarce node.

[0032] Furthermore, the method also includes:

[0033] Configure a set value, and when the fixed gap is greater than the set value, define the target area;

[0034] From the grid-connected area, select adjacent areas and establish temporary links between the target area and the adjacent areas.

[0035] Compared with the prior art, the beneficial effects of the present invention are:

[0036] By determining the average output power, a data foundation can be provided for grid load forecasting, ensuring grid stability. By collecting radar cloud images, cloud changes can be accurately predicted, optimizing the operation and maintenance management of photovoltaic power plants. By connecting new energy vehicles to the grid-connected area, these vehicles can be used as mobile energy storage, stabilizing the predicted load gap at a fixed value through a peak-shaving and valley-filling method. This greatly reduces the fluctuation of power load in the grid-connected area while significantly improving user experience and economic benefits. Attached Figure Description

[0037] Figure 1 A flowchart illustrating the new energy photovoltaic power generation load forecasting method provided in this embodiment of the invention;

[0038] Figure 2 This is a first sub-flowchart of the new energy photovoltaic power generation load forecasting method provided in an embodiment of the present invention;

[0039] Figure 3 This is a second sub-flowchart of the new energy photovoltaic power generation load forecasting method provided in an embodiment of the present invention;

[0040] Figure 4 This is a third sub-flowchart of the new energy photovoltaic power generation load prediction method provided in an embodiment of the present invention. Detailed Implementation

[0041] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0042] In Example 1, Figure 1 The implementation flow of the new energy photovoltaic power generation load forecasting method provided in the embodiment of the present invention is shown below in detail:

[0043] S100: Locate the deployment location of the new energy photovoltaic power station, calculate the average output power, configure the grid connection area of ​​the new energy photovoltaic power station, collect radar cloud images at the deployment location, and input them into the pre-built multi-level prediction model to output the load gap and corresponding peak period of the grid connection area.

[0044] The deployment location of the new energy photovoltaic power station is determined. Based on solar radiation data, photovoltaic panel conversion efficiency, and actual operating data at the deployment location, the average daily output power is determined. If the day is inclement weather or rain / snow, the output power for that day is not included in the calculation of the average output power. The power grid to which the new energy photovoltaic power station is connected is determined, and the area corresponding to this power grid is defined as the grid-connected area. In other words, the power generation of the new energy photovoltaic power station will affect the grid load in the grid-connected area. Radar cloud images of the deployment location are collected from publicly available data or using meteorological radar equipment and input into a multi-level prediction model. The multi-level prediction model is divided into multiple levels, each of which contains at least one data module. The multi-level prediction model includes at least: a data preprocessing level, an output power prediction level, and a load prediction level. Through learning and analysis of radar cloud images and historical meteorological data, the multi-level prediction model can predict the power generation at the deployment location and obtain the load gap of the grid-connected area by comparing it with the average daily output power, that is, the gap between the current power generation capacity and the grid demand, and determine the time corresponding to the load gap as the peak period.

[0045] For example, based on historical data, the average daily output power at the deployment location in May is 1200 kilowatts, and the average hourly output power is about 86 kilowatts. By inputting the radar cloud image into a multi-level model, it is calculated that the output power in the next hour (e.g., 14:00-15:00) will be about 23 kilowatts, and the load gap will be 63 kilowatts. The peak period is 14:00-15:00. It should be noted that there will not be a peak period every day in May. If the power grid output power can meet the electricity load on a certain day, then there will be no peak period on that day.

[0046] In this application, by utilizing new energy vehicles and combining them with new energy photovoltaic power stations, the average output power per hour is stabilized at 86 kilowatts, thereby reducing the fluctuation of the grid load in the grid-connected area. In this application, only the daytime power generation of the new energy photovoltaic power station is considered. When night falls, the power supply in the grid-connected area is completely handed over to traditional thermal power, hydropower and other power generation systems.

[0047] S200: Construct a mobile energy storage platform and extract registrants. Based on the peak period, determine the target period and send a reminder to the registrants to access the new energy vehicles, obtain power access permissions, and connect the new energy vehicles to the mobile energy storage platform through the power access permissions and peak periods to construct a load balancing mechanism.

[0048] By leveraging the Internet of Things, smart grids, and cloud computing, and combining them with new energy vehicles and energy storage systems, a mobile energy storage platform is constructed. This platform is primarily used to manage all mobile energy storage devices in a unified manner. Through a user registration system, information on all registrants is obtained and extracted, including: device type, location, energy consumption history, and energy storage capacity. On the day corresponding to peak hours, a target time period is selected, which is mainly used to remind users to connect their mobile energy storage devices to the grid in the grid-connected area.

[0049] For example, continuing with the above example, if there is a peak time on May 1st, the target time period can be 8:00 on that day or any other time set by the user.

[0050] Once the target period arrives, a reminder to registrants regarding the access of new energy vehicles will be sent. This reminder can be delivered via voice broadcast; for example, the reminder could be: "Please remember to plug your vehicle into the charging station." Power access permissions for new energy vehicles will be granted, and adjustments will be made to their connection to or disconnection from the power grid, based on a load balancing mechanism. Furthermore, when a load gap exists, new energy vehicles will be connected to the power grid to fill the gap; conversely, when the output power exceeds the average output power, the excess power will be used to charge the new energy vehicles.

[0051] S300: Create a root node corresponding to each new energy photovoltaic power station, define the new energy vehicles in the corresponding grid-connected area as target vehicles, create child nodes corresponding to the target vehicles, attach the child nodes to the root nodes, calculate the fixed gap for each root node, configure the scheduling starting point, construct a backup link between the scheduling starting point and the grid-connected area, and optimize the fixed gap.

[0052] A root node is created, corresponding one-to-one with each new energy photovoltaic power station. This root node primarily represents the new energy photovoltaic power station and stores information such as its location, capacity, average output power, and grid connection status. New energy vehicles within the grid-connected area are defined as target vehicles; these are vehicles located within the grid-connected area and already connected to the power grid. Child nodes are created, corresponding one-to-one with each target vehicle. These child nodes primarily represent the target vehicle and also contain information such as vehicle type, charging demand, estimated charging time, geographical location, and current battery status. Based on the relationship between the new energy photovoltaic power station, the grid-connected area, and the new energy vehicles, the child nodes are attached to the root node. It is important to note that even after connecting all new energy vehicles to the grid-connected area, a load gap may still exist. In this case, a dispatching starting point is selected from the power grid in other areas, and this dispatching starting point, along with backup links, is used to fill the fixed gap.

[0053] Continuing with the example in S100 above, if the load gap from 14:00 to 15:00 is 63 kilowatts, but the number of new energy vehicles connected to the grid in the grid-connected area is small and cannot be completely filled, then a backup link should be established between the grid in the grid-connected area and the grid in other areas. This backup link should be used for load dispatching, so as to cooperate with the new energy vehicles to fill the load gap.

[0054] In Example 2, Figure 2 The implementation flow of the new energy photovoltaic power generation load forecasting method provided by the embodiment of the present invention is shown. The following details the steps of locating the deployment location of the new energy photovoltaic power station, calculating the average output power, and collecting radar cloud images at the deployment location:

[0055] S101: Divide the new energy photovoltaic power station into several groups, establish a mapping between the fixed gap and the groups, and correct the backup link.

[0056] Based on the location of the new energy photovoltaic power stations, the new energy photovoltaic power stations are divided into several groups. When a fixed shortage occurs, load dispatch is prioritized within each group.

[0057] S102: Insert a timestamp into the radar cloud image and configure the statistical step size of the average output power.

[0058] The radar cloud image should include data such as weather conditions, cloud thickness, precipitation, wind speed, and sunshine. Since the radar cloud image is constantly changing, each radar cloud image needs to correspond to a specific point in time. A timestamp should be inserted into the radar cloud image, and the timestamp should be in a standard date and time format. The statistical step size of the average output power should be determined, and the statistical step size can be set by the power grid manager. In the example of S100, the statistical step size is 1 hour.

[0059] In Example 3, Figure 2 The implementation flow of the new energy photovoltaic power generation load forecasting method provided by the embodiment of the present invention is illustrated. The following details the steps of collecting radar cloud images at the deployment location, inputting them into a pre-built load forecasting model, and outputting the load gap and corresponding time, as follows:

[0060] S103: Create an output power prediction model, configure historical power generation data of new energy power plants, identify the irradiance from the radar cloud map, input the historical power generation data and irradiance into the output power prediction model, and output the predicted power generation.

[0061] Historical power generation data of new energy power plants is collected, including information such as daily or hourly power generation, radiation intensity, weather conditions, and equipment operation status in the same period of previous years. In addition, historical power generation data should also include the power generation and radiation intensity of adjacent new energy power plants. The power generation capacity of each new energy power plant is determined, and based on the irradiance in the radar cloud image, the predicted power generation of the new energy power plant in the next statistical step is determined using the output power prediction model. Both the output power prediction model and the load prediction model are obtained through multi-layer neural network simulation. After the model is constructed, both models need to be trained.

[0062] S104: Create a load forecasting model, collect historical load data of the grid-connected area, input the predicted power generation and historical load data into the load forecasting model, and output the load gap.

[0063] From existing technologies, a load forecasting model is selected. Historical load data of the grid-connected area is input into the load forecasting model. The historical load data is the historical electricity consumption data of the grid-connected area. The load data is input into the load forecasting model, and the output is the predicted electricity load in the next statistical step. The difference between the predicted power generation and the predicted electricity load is defined as the load gap.

[0064] S105: Based on the timestamp, establish the correspondence between load gap and peak period, integrate the output power prediction model and load prediction model to obtain a multi-level prediction model.

[0065] The statistical step size corresponding to the peak period, i.e. the load gap, is used to establish the correspondence between the load gap and the peak period; the output power prediction model and the load prediction model are integrated to generate a process-oriented processing step, thereby obtaining a multi-level prediction model.

[0066] In Example 4, Figure 3 The implementation flow of the new energy photovoltaic power generation load forecasting method provided by the embodiment of the present invention is shown below. The steps of determining the target time period based on the peak time period are described in detail below:

[0067] S201: Select a test day, determine whether there is a peak period on the test day, and if so, receive the charging and discharging reminder time uploaded by the user and determine it as the target period.

[0068] During peak hours, a reminder time for charging and discharging is selected, i.e., the target time period; the reminder time can be determined by the owners of new energy vehicles based on their daily routines.

[0069] S202: When the current time coincides with the target time period, generate an access reminder and send it to the registrant.

[0070] When the target time period arrives, an access reminder is generated and sent to the registrant via voice.

[0071] In Example 5, unlike Example 1, the method further includes:

[0072] Using the multi-level prediction model, load troughs in the grid-connected area are identified, and the time corresponding to the load troughs is defined as the trough period.

[0073] Multi-level prediction models are used to identify load troughs in grid-connected areas, and the time corresponding to the load troughs is defined as the trough period. The load trough usually refers to the period when the grid load is low. At this time, the electricity demand is small, the power generation capacity of the new energy photovoltaic power station exceeds the consumption capacity, and the grid load is relatively relaxed.

[0074] The implementation process of the new energy photovoltaic power generation load forecasting method provided in this embodiment of the invention is as follows: during peak hours, new energy vehicles are used to discharge and replenish energy in the grid-connected area; during off-peak hours, new energy vehicles in the grid-connected area are charged.

[0075] During peak hours, new energy vehicles are used to supplement the grid-connected area with electricity, while during off-peak hours, the grid in the connected area is used to charge the new energy vehicles. The advantage of doing this is that it can greatly improve the stability of the grid load, whether the grid load is at its peak or off.

[0076] In Example 6, unlike Example 1, the method further includes:

[0077] The total discharge power of new energy vehicles was calculated, and several power ranges were defined.

[0078] Edit the reward rule set and construct a lookup table, wherein the lookup table consists of power range items and reward rule items.

[0079] After new energy vehicles are connected to the grid, the total discharge power of each new energy vehicle in the grid-connected area is recorded. The grid manager divides the area into multiple power ranges and determines the power range of each new energy vehicle based on the total discharge power. Each power range corresponds to a reward rule. In other words, when the total discharge power of a new energy vehicle in the grid-connected area reaches a certain amount, a corresponding reward is given according to the reward rule. The correspondence between the reward rule and the power range is stored in a lookup table.

[0080] In Example 7, Figure 4The implementation flow of the new energy photovoltaic power generation load forecasting method provided in this embodiment of the invention is shown below. The steps of creating a root node corresponding one-to-one with the new energy photovoltaic power station, defining the new energy vehicles in the corresponding grid-connected area as target vehicles, and creating child nodes corresponding to the target vehicles are described in detail below:

[0081] S301: Integrate the root node and child nodes to generate a balanced tree, set its height, and construct relevant relationships based on the height of the balanced tree and the fixed gap.

[0082] A balanced tree is generated using the root node and child nodes. The balanced tree is a tree-like data structure similar to a binary tree, but unlike a binary tree, the height of the balanced tree changes dynamically. Furthermore, the height of the balanced tree is changed by adjusting the spacing between the root node and child nodes. A positive correlation is established between the height of the balanced tree and a fixed gap; that is, the larger the fixed gap, the higher the height of the balanced tree.

[0083] S302: Grant management permissions for the mobile energy storage platform to the balance tree and correct the height.

[0084] As the balance tree grows taller, mobile energy storage platforms are used to connect new energy vehicles to the grid, thereby reducing grid load fluctuations.

[0085] In Example 8, Figure 4 The implementation flow of the new energy photovoltaic power generation load forecasting method provided by the embodiment of the present invention is shown. The steps for calculating the fixed gap of each root node are described in detail below:

[0086] S303: Determine whether the fixed gap is greater than the threshold. If so, define the shortage node and embed the tag generated by the historical load data.

[0087] If the fixed gap is greater than the threshold, it indicates that the power generation capacity of the corresponding new energy photovoltaic power station is poor. At this time, the new energy photovoltaic power station is defined as a shortage node, and the feature label generated by the historical load data is embedded in the shortage node. The advantage of doing this is that the reasons for the poor power generation capacity can be analyzed in a timely manner, thereby providing data support for power supply adjustment.

[0088] S304: Switch the backup link to the scarce node.

[0089] When the power generation capacity of a new energy photovoltaic power station is poor, the backup link is reconstructed by utilizing the grid connection area corresponding to the dispatch starting point and the scarce node.

[0090] In Example 9, unlike Example 1, the method further includes:

[0091] Configure a set value, and when the fixed gap is greater than the set value, define the target area;

[0092] From the grid-connected area, select adjacent areas and establish temporary links between the target area and the adjacent areas.

[0093] The grid manager configures a set value, defining the area corresponding to the fixed gap being greater than the set value as the target area; the target area is the area where the power generation capacity of the new energy photovoltaic power station is poor; based on the target area, adjacent areas are selected and temporary links are built, using the traditional power generation system or new energy power generation system in the adjacent areas to assist the target area in adjusting the grid load.

[0094] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0095] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

[0096] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for predicting the load of new energy photovoltaic power generation, characterized in that, The method includes: The deployment location of the new energy photovoltaic power station is located, the average output power is calculated, the grid connection area of ​​the new energy photovoltaic power station is configured, radar cloud images of the deployment location are collected and input into a pre-built multi-level prediction model, and the load gap and corresponding peak period of the grid connection area are output. A mobile energy storage platform is constructed, and registrants are extracted. Based on the peak period, a target period is determined, and a reminder for the access of new energy vehicles is sent to the registrants to obtain power access rights. Based on the power access rights and the peak period, the new energy vehicles are connected to the mobile energy storage platform to construct a load balancing mechanism. Create a root node that corresponds one-to-one with a new energy photovoltaic power station, define the new energy vehicles in the corresponding grid-connected area as target vehicles, create child nodes corresponding to the target vehicles, attach the child nodes to the root nodes, calculate the fixed gap for each root node, configure the scheduling starting point, construct a backup link between the scheduling starting point and the grid-connected area, and optimize the fixed gap. The steps of locating the deployment location of the new energy photovoltaic power station, calculating the average output power, and collecting radar cloud images at the deployment location include: The new energy photovoltaic power station is divided into several groups, a mapping between the fixed gap and the group is established, and the backup link is corrected; Insert timestamps into the radar cloud image and configure the statistical step size of the average output power; The steps of collecting radar cloud images at the deployment location, inputting them into a pre-built load forecasting model, and outputting the load gap and corresponding time include: An output power prediction model is created, historical power generation data of the new energy power plant is configured, the irradiance is identified from the radar cloud image, the historical power generation data and irradiance are input into the output power prediction model, and the predicted power generation is output. Create a load forecasting model, collect historical load data of the grid-connected area, input the predicted power generation and historical load data into the load forecasting model, and output the load gap; Based on the timestamp, a correspondence between load gaps and peak periods is established, and the output power prediction model and load prediction model are integrated to obtain a multi-level prediction model; The step of determining the target time period based on the peak period includes: Select a test day, determine if there is a peak period on the test day, and if so, receive the charging and discharging reminder time uploaded by the user and determine it as the target period; When the current time coincides with the target time period, an access reminder is generated and sent to the registrant.

2. The new energy photovoltaic power generation load forecasting method according to claim 1, characterized in that, The method further includes: Using the multi-level prediction model, load troughs in the grid-connected area are identified, and the time corresponding to the load troughs is defined as the trough period.

3. The new energy photovoltaic power generation load forecasting method according to claim 2, characterized in that, The load balancing mechanism is as follows: during peak hours, new energy vehicles discharge to replenish energy in the grid-connected area; during off-peak hours, new energy vehicles in the grid-connected area are charged.

4. The new energy photovoltaic power generation load forecasting method according to claim 3, characterized in that, The method further includes: The total discharge power of new energy vehicles was calculated, and several power ranges were defined. Edit the reward rule set and construct a lookup table, wherein the lookup table consists of power range items and reward rule items.

5. The new energy photovoltaic power generation load forecasting method according to claim 1, characterized in that, The steps of creating a root node corresponding to a new energy photovoltaic power station, defining the new energy vehicles in the corresponding grid-connected area as target vehicles, and creating child nodes corresponding to the target vehicles include: Integrate the root node and child nodes to generate a balanced tree, set its height, and construct relevant relationships based on the height of the balanced tree and the fixed gap; Grant management permissions to the mobile energy storage platform to the balanced tree and correct its height.

6. The new energy photovoltaic power generation load forecasting method according to claim 1, characterized in that, The steps for calculating the fixed gap for each root node include: Determine whether the fixed gap is greater than a threshold. If so, define a critical node and embed a tag generated from historical load data. Switch the backup link to the scarce node.

7. The new energy photovoltaic power generation load forecasting method according to claim 1, characterized in that, The method further includes: Configure a set value, and when the fixed gap is greater than the set value, define the target area; From the grid-connected area, select adjacent areas and establish temporary links between the target area and the adjacent areas.

Images