New energy power generation power prediction method and device

Abstract

The application relates to the technical field of data processing, and discloses a new energy power generation power prediction method and device, which comprises the following steps: obtaining initial data of each station, performing meteorological characteristic analysis on the initial data to determine an analysis result; wherein the station is at least two; establishing a corresponding single-station power prediction model based on the analysis result, and determining a power model prediction result based on the single-station power prediction model; establishing a whole-network power prediction model based on the power model prediction result and a whole-network total actual power value; and performing new energy power generation power prediction based on the whole-network power prediction model, and correcting and determining a new energy total power prediction value based on a station processing strategy. Through the steps of establishing a corresponding single-station power prediction model, determining a power model prediction result based on the single-station power prediction model, establishing a whole-network power prediction model based on the power model prediction result and a whole-network total actual power value, and performing new energy power generation power prediction, more accurate power prediction can be realized.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method for predicting the power generation capacity of new energy sources. Background Technology

[0002] Currently, power grid dispatching departments require power plants (including wind and solar power) to report power forecasts, including short-term and ultra-short-term forecasts. Short-term forecasts predict the power output of the power plant for the 72 hours following 00:00, with a time resolution of 15 minutes, and are used for system power generation planning. Ultra-short-term forecasts provide rolling forecasts with a lead time of 0-4 hours and are used for real-time power system dispatching. Currently, power grid dispatching generates cluster output forecast services by simply summing the predicted power output of power plants. However, all power plant power forecasts have some degree of error, different power plants use different forecasting models, and all operational data from all power plants are required, all of which increase the error in cluster power forecasts.

[0003] Power plant power prediction methods are mainly divided into statistical methods and physical methods. Physical methods do not require a large amount of measurement data, but they require an accurate mathematical description of the physical properties of the atmosphere and the characteristics of the power plant. These equations are difficult to solve and involve a large amount of computation. Statistical methods do not require solving physical equations and are fast in calculation, but they require a large amount of historical data. At the same time, most prediction manufacturers do not currently provide cluster power prediction. Some manufacturers calculate cluster power prediction by simply accumulating the power plant power predictions, which has low accuracy and cannot meet the actual needs of guiding dispatch decisions.

[0004] Therefore, a better solution is urgently needed. Summary of the Invention

[0005] In view of this, the present invention provides a method for predicting the power generation of new energy sources to address the technical deficiencies existing in the prior art.

[0006] According to a first aspect of the invention, a method for predicting the power generation capacity of a new energy source is provided, comprising:

[0007] Acquire initial data from each station, and perform meteorological characteristic analysis on the initial data to determine the analysis results; wherein, there are at least two stations.

[0008] Based on the analysis results, a corresponding power prediction model for a single power station is established, and the power prediction results are determined based on the power prediction model for a single power station.

[0009] Based on the power model prediction results and the total actual power value of the entire network, a power prediction model for the entire network is established.

[0010] The power generation of new energy sources is predicted based on the whole-network power prediction model, and the total power prediction value of new energy sources is determined by correction based on the power plant processing strategy.

[0011] One possible implementation also includes:

[0012] Based on the geographical location and meteorological characteristics of at least two stations, cluster analysis is used to identify at least two regions;

[0013] Based on the analysis of meteorological characteristics in each region, a regional power prediction model is established.

[0014] Based on the meteorological forecasts for the locations of each station, a first power prediction model for the entire network was established.

[0015] One possible implementation also includes:

[0016] A second power prediction model for the entire network was established based on the meteorological forecasts for the locations of each station.

[0017] In one possible implementation, meteorological characteristic analysis is performed on the initial data to determine the analysis results, including:

[0018] Correlation analysis was performed on the initial data to identify the target factors that affect the power of the power plant;

[0019] Based on the target factors, key influencing factors are identified, and based on the key influencing factors, the results of the influencing factor analysis are determined.

[0020] Based on the analysis of influencing factors, factors whose impact on power generation exceeds the threshold are selected as the analysis results.

[0021] In one possible implementation, a corresponding single-station power prediction model is established based on the analysis results, including:

[0022] The reference sequence and comparison sequence were determined based on the analysis results;

[0023] The degree of correlation is determined based on the reference sequence and the comparison sequence;

[0024] Training samples are determined based on correlation, and corresponding single-site power prediction models are established based on the training samples.

[0025] In one possible implementation, the predicted total power of new energy sources is determined by adjusting the power plant processing strategy, including:

[0026] Determine the maintenance plan handling and correction strategies, extreme weather correction strategies, power field expansion handling strategies, and power curtailment handling strategies for each station;

[0027] Based on maintenance plan correction strategies, extreme weather correction strategies, power plant expansion correction strategies, and power curtailment correction strategies, the power forecast values ​​of each power station are corrected to determine the total power forecast value of new energy sources.

[0028] One possible implementation also includes:

[0029] The predicted total power of the new energy source is evaluated based on the prediction accuracy calculation formula, and the evaluation result is determined.

[0030] The formula for calculating the prediction accuracy includes:

[0031]

[0032] Wherein, Acc represents accuracy, p represents actual power, and p ′ The predicted power is represented by , and time i represents the time step.

[0033] According to a second aspect of the present invention, a new energy power generation prediction device is provided, comprising:

[0034] The data analysis module is configured to acquire initial data from each station, perform meteorological characteristic analysis on the initial data, and determine the analysis results; wherein there are at least two stations.

[0035] The power station model module is configured to establish a corresponding single power station power prediction model based on the analysis results, and to determine the power model prediction results based on the single power station power prediction model.

[0036] The whole network model module is configured to establish a whole network power prediction model based on the power model prediction results and the total actual power value of the whole network.

[0037] The model prediction module is configured to predict the power generation of new energy sources based on the whole network power prediction model, and to determine the total power prediction value of new energy sources by correcting it based on the power plant processing strategy.

[0038] According to a third aspect of the present invention, a computing device is provided, comprising:

[0039] Memory and processor;

[0040] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, they implement the steps of the above-mentioned new energy power generation prediction method.

[0041] According to a fourth aspect of the present invention, a computer-readable storage medium is provided that stores computer-executable instructions, which, when executed by a processor, implement the steps of the above-described new energy power generation prediction method.

[0042] According to a fifth aspect of the present invention, a computer program is provided, wherein when the computer program is executed in a computer, the computer is instructed to perform the steps of the above-described new energy power generation prediction method.

[0043] This invention provides a method and apparatus for predicting renewable energy power generation. The method includes: acquiring initial data from each power station; performing meteorological characteristic analysis on the initial data to determine the analysis results; wherein at least two power stations are used; establishing corresponding single-station power prediction models based on the analysis results; determining the power model prediction results based on the single-station power prediction models; establishing a network-wide power prediction model based on the power model prediction results and the total actual power value of the entire network; predicting renewable energy power generation based on the network-wide power prediction model; and determining the total renewable energy power prediction value by correcting the prediction based on the power station processing strategy. By establishing corresponding single-station power prediction models and determining the power model prediction results based on the single-station power prediction models; and by establishing a network-wide power prediction model based on the power model prediction results and the total actual power value of the entire network to predict renewable energy power generation, more accurate power prediction can be achieved. Attached Figure Description

[0044] Figure 1 This is a flowchart of a new energy power generation prediction method provided in one embodiment of this specification;

[0045] Figure 2 This is a schematic diagram illustrating the principle of a new energy power generation prediction method provided in one embodiment of this specification;

[0046] Figure 3 This is a clustering diagram illustrating a new energy power generation prediction method provided in one embodiment of this specification;

[0047] Figure 4 This is a schematic diagram illustrating the prediction correction of a new energy power generation prediction method provided in one embodiment of this specification;

[0048] Figure 5 This is a schematic diagram of the structure of a new energy power generation prediction device provided in one embodiment of this specification;

[0049] Figure 6 This is a structural block diagram of a computing device provided in one embodiment of this specification. Detailed Implementation

[0050] Many specific details are set forth in the following description to provide a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar extensions without departing from the spirit of this specification. Therefore, this specification is not limited to the specific implementations disclosed below.

[0051] The terminology used in one or more embodiments of this specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the one or more embodiments of this specification. The singular forms “a” and “the” as used in one or more embodiments of this specification and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0052] It should be understood that although the terms first, second, etc., may be used to describe various information in one or more embodiments of this specification, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first may also be referred to as second without departing from the scope of one or more embodiments of this specification, and similarly, second may also be referred to as first. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to a determination."

[0053] This specification provides a method for predicting the power generation capacity of new energy sources. It also relates to a device for predicting the power generation capacity of new energy sources, a computing device, and a computer-readable storage medium, which will be described in detail in the following embodiments.

[0054] See Figure 1 , Figure 1 A flowchart of a new energy power generation prediction method according to an embodiment of this specification is shown, which specifically includes the following steps.

[0055] Step 101: Obtain initial data from each station and perform meteorological characteristic analysis on the initial data to determine the analysis results; where there are at least two stations.

[0056] In practical applications, see Figure 2 This can include three modeling schemes: single-station modeling, regional modeling, and network-wide modeling. The single-station modeling scheme includes the following steps: Meteorological characteristic analysis is performed on each station in the network, and a corresponding single-station power prediction model is established. Based on the power model prediction results of the single station and the total actual power value of the entire network, a network-wide power prediction model is established.

[0057] One possible implementation also includes: performing cluster analysis to determine at least two regions based on the geographical location and meteorological characteristics of at least two stations; establishing a regional power prediction model based on meteorological characteristic analysis of each region; and establishing a first network-wide power prediction model based on meteorological forecasts of the locations of each station.

[0058] Specifically, the regional modeling scheme includes the following steps: Based on the geographical location and meteorological characteristics of all power stations in the network, cluster analysis is performed to divide the network into multiple regions (Region 1, Region 2...Region m). Based on the meteorological characteristics analysis of each region, a regional power prediction model is established. Based on the meteorological forecasts for the locations of each power station, a first network-wide power prediction model is established.

[0059] For example, see Figure 3 Based on the geographical location, meteorological and other characteristics of all grid-connected power plants, and combined with K-means clustering analysis, different regions are divided. This scheme not only considers the geographical location of the power plants, but also explores the similarities in meteorological characteristics and power generation patterns. Wind and solar power prediction models are established for different regions, and finally the results are summarized into the power prediction results for the entire grid, thereby improving the accuracy of regional predictions.

[0060] Another possible implementation includes: establishing a second network-wide power prediction model based on weather forecasts for the locations of each station.

[0061] Specifically, a second network-wide power prediction model is established based on weather forecasts for the locations of each wind farm. Graph Convolutional Networks (GCNs), as a structure for extracting spatiotemporal features, are used to extract the spatiotemporal correlations of power and numerical weather predictions for each wind farm cluster containing geographical location information. This information is then fused using multimodal learning. By mining the spatiotemporal features of the wind farm cluster and introducing correlation analysis between the wind farms, the accuracy of regional predictions is improved.

[0062] In one possible implementation, meteorological characteristic analysis is performed on the initial data to determine the analysis results, including: performing correlation analysis on the initial data to identify target factors that affect the power of the station; identifying important influencing factors based on the target factors; determining the analysis results of influencing factors based on the important influencing factors; and selecting factors whose impact on the power of the station exceeds a threshold as the analysis results based on the analysis results of the influencing factors.

[0063] In practical applications, the analysis of power station characteristics and influencing factors proposes the concepts of effective cluster influencing factors and power station power. Through correlation analysis, factors with significant impact on power station power are identified as important influencing factors for power station power at the prediction time. Information reflecting the characteristics of power station power is extracted. Based on the analysis results of power station power influencing factors, factors with significant impact on power station power are selected as representative information features.

[0064] Step 102: Establish a corresponding single-station power prediction model based on the analysis results, and determine the power model prediction results based on the single-station power prediction model.

[0065] In one possible implementation, a corresponding single-site power prediction model is established based on the analysis results, including: determining a reference sequence and a comparison sequence based on the analysis results; determining the correlation degree based on the reference sequence and the comparison sequence; determining training samples based on the correlation degree; and establishing a corresponding single-site power prediction model based on the training samples.

[0066] In practical applications, a reference sequence and a comparison sequence are determined. The information features of the power station power at the predicted time are selected as the reference sequence, and the information feature vectors of the power station power at the corresponding time in the historical samples from the previous n days are selected as the comparison sequence. Samples with high data completeness and accuracy are selected, and the grey relational degree between the comparison sequence and the reference sequence is calculated using correlation and association degree calculation formulas. The correlation degrees are sorted in descending order, and samples with a high correlation to the predicted time are selected as the final training samples. A prediction model is then established. The m samples with a high correlation to the predicted time are selected as the final training samples. The input variable is the power station power information feature at the predicted time, and the output variable is the predicted power station power.

[0067] Step 103: Based on the power model prediction results and the total actual power value of the entire network, establish a power prediction model for the entire network.

[0068] In practical applications, a power prediction model for the entire network is established based on the power model prediction results of each power station and the total actual power value of the entire network. The scheme for establishing this network-wide power prediction model is similar to the construction method of the single power station power prediction model mentioned above, and will not be elaborated here.

[0069] Step 104: Predict the power generation of new energy sources based on the whole network power prediction model, and determine the total power prediction value of new energy sources by correcting it based on the power plant processing strategy.

[0070] In one possible implementation, the total power forecast of renewable energy is determined by correcting the power plant processing strategy, including: determining the maintenance plan processing correction strategy, extreme weather correction strategy, power plant expansion processing strategy, and power curtailment processing strategy for each power plant; and correcting the power forecast of each power plant based on the maintenance plan processing correction strategy, extreme weather correction strategy, power plant expansion processing strategy, and power curtailment processing strategy to determine the total power forecast of renewable energy.

[0071] In practical applications, see Figure 4 By combining strategies such as maintenance plan adjustments at the power station scale, extreme weather adjustments, and new power plant capacity expansion, as well as regional-scale batch power curtailment judgment and handling strategies, the total power prediction value of new energy sources across the entire network is finally formed.

[0072] One possible implementation also includes:

[0073] The predicted total power of the new energy source is evaluated based on the prediction accuracy calculation formula, and the evaluation result is determined.

[0074] The formula for calculating the prediction accuracy includes:

[0075]

[0076] Wherein, Acc represents accuracy, p represents actual power, and p ′ The predicted power is represented by , and time i represents the time step.

[0077] The accuracy of predictions can be determined based on the above formula, which can be used to evaluate the performance of the model and adjust relevant parameters to improve the accuracy of predictions.

[0078] Corresponding to the above method embodiments, this specification also provides embodiments of a new energy power generation prediction device. Figure 5 A schematic diagram of a new energy power generation prediction device according to one embodiment of this specification is shown. Figure 5 As shown, the device includes:

[0079] The data analysis module 501 is configured to acquire initial data from each station, perform meteorological characteristic analysis on the initial data, and determine the analysis results; wherein there are at least two stations.

[0080] The power station model module 502 is configured to establish a corresponding single power station power prediction model based on the analysis results, and to determine the power model prediction results based on the single power station power prediction model.

[0081] The whole network model module 503 is configured to establish a whole network power prediction model based on the power model prediction results and the total actual power value of the whole network.

[0082] The model prediction module 504 is configured to predict the power generation of new energy sources based on the whole network power prediction model, and to determine the total power prediction value of new energy sources by correcting it based on the power plant processing strategy.

[0083] In one possible implementation, the model prediction module 504 is further configured as follows:

[0084] Based on the geographical location and meteorological characteristics of at least two stations, cluster analysis is used to identify at least two regions;

[0085] Based on the analysis of meteorological characteristics in each region, a regional power prediction model is established.

[0086] Based on the meteorological forecasts for the locations of each station, a first power prediction model for the entire network was established.

[0087] In one possible implementation, the model prediction module 504 is further configured as follows:

[0088] A second power prediction model for the entire network was established based on the meteorological forecasts for the locations of each station.

[0089] In one possible implementation, the data analysis module 501 is further configured as follows:

[0090] Correlation analysis was performed on the initial data to identify the target factors that affect the power of the power plant;

[0091] Based on the target factors, key influencing factors are identified, and based on the key influencing factors, the results of the influencing factor analysis are determined.

[0092] Based on the analysis of influencing factors, factors whose impact on power generation exceeds the threshold are selected as the analysis results.

[0093] In one possible implementation, the site model module 502 is further configured as follows:

[0094] The reference sequence and comparison sequence were determined based on the analysis results;

[0095] The degree of correlation is determined based on the reference sequence and the comparison sequence;

[0096] Training samples are determined based on correlation, and corresponding single-site power prediction models are established based on the training samples.

[0097] In one possible implementation, the model prediction module 504 is further configured as follows:

[0098] Determine the maintenance plan handling and correction strategies, extreme weather correction strategies, power field expansion handling strategies, and power curtailment handling strategies for each station;

[0099] Based on maintenance plan correction strategies, extreme weather correction strategies, power plant expansion correction strategies, and power curtailment correction strategies, the power forecast values ​​of each power station are corrected to determine the total power forecast value of new energy sources.

[0100] In one possible implementation, the model prediction module 504 is further configured as follows:

[0101] The predicted total power of the new energy source is evaluated based on the prediction accuracy calculation formula, and the evaluation result is determined.

[0102] The formula for calculating the prediction accuracy includes:

[0103]

[0104] Wherein, Acc represents accuracy, p represents actual power, and p ′ The predicted power is represented by , and time i represents the time step.

[0105] The above is a schematic scheme of a new energy power generation prediction device according to this embodiment. It should be noted that the technical solution of this new energy power generation prediction device and the technical solution of the new energy power generation prediction method described above belong to the same concept. For details not described in detail in the technical solution of the new energy power generation prediction device, please refer to the description of the technical solution of the new energy power generation prediction method described above.

[0106] Figure 6 A structural block diagram of a computing device 600 according to one embodiment of this specification is shown. The components of the computing device 600 include, but are not limited to, a memory 610 and a processor 620. The processor 620 is connected to the memory 610 via a bus 630, and a database 650 is used to store data.

[0107] The computing device 600 also includes an access device 640, which enables the computing device 600 to communicate via one or more networks 660. Examples of these networks include Public Switched Telephone Network (PSTN), Local Area Network (LAN), Wide Area Network (WAN), Personal Area Network (PAN), or combinations of communication networks such as the Internet. The access device 640 may include one or more of any type of wired or wireless network interface (e.g., a network interface card (NIC)), such as an IEEE 802.11 Wireless Local Area Network (WLAN) wireless interface, a Wi-MAX (Worldwide Interoperability for Microwave Access) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, or a Near Field Communication (NFC) interface.

[0108] In one embodiment of this specification, the above-described components of the computing device 600 and Figure 6 Other components, not shown, can also be connected to each other, for example, via a bus. It should be understood that... Figure 6 The block diagram of the computing device shown is for illustrative purposes only and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0109] The computing device 600 can be any type of stationary or mobile computing device, including mobile computers or mobile computing devices (e.g., tablet computers, personal digital assistants, laptop computers, notebook computers, netbooks, etc.), mobile phones (e.g., smartphones), wearable computing devices (e.g., smartwatches, smart glasses, etc.) or other types of mobile devices, or stationary computing devices such as desktop computers or personal computers (PCs). The computing device 600 can also be a mobile or stationary server.

[0110] The processor 620 is configured to execute the following computer-executable instructions, which, when executed by the processor, implement the steps of the aforementioned new energy power generation prediction method. The above is an illustrative scheme of a computing device according to this embodiment. It should be noted that the technical solution of this computing device and the technical solution of the aforementioned new energy power generation prediction method belong to the same concept. Details not described in detail in the technical solution of the computing device can be found in the description of the technical solution of the aforementioned new energy power generation prediction method.

[0111] An embodiment of this specification also provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the above-described new energy power generation prediction method.

[0112] The above is an illustrative scheme of a computer-readable storage medium according to this embodiment. It should be noted that the technical solution of this storage medium belongs to the same concept as the technical solution of the aforementioned new energy power generation prediction method. Details not described in detail in the technical solution of the storage medium can be found in the description of the technical solution of the aforementioned new energy power generation prediction method.

[0113] An embodiment of this specification also provides a computer program, wherein when the computer program is executed in a computer, it causes the computer to perform the steps of the above-described new energy power generation prediction method.

[0114] The above is an illustrative scheme of a computer program according to this embodiment. It should be noted that the technical solution of this computer program and the technical solution of the above-described new energy power generation prediction method belong to the same concept. For details not described in detail in the technical solution of the computer program, please refer to the description of the technical solution of the above-described new energy power generation prediction method.

[0115] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0116] The computer instructions include computer program code, which may be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium may be appropriately added to or subtracted according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media may not include electrical carrier signals and telecommunication signals.

[0117] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments in this specification are not limited to the described order of actions, because according to the embodiments in this specification, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the embodiments in this specification.

[0118] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0119] The preferred embodiments disclosed above are merely illustrative of this specification. The optional embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the embodiments described herein. These embodiments are selected and specifically described in this specification to better explain the principles and practical applications of the embodiments, thereby enabling those skilled in the art to better understand and utilize this specification. This specification is limited only by the claims and their full scope and equivalents.

Claims

1. A new energy power generation power prediction method, characterized in that, include: Acquire initial data from each station, and perform meteorological characteristic analysis on the initial data to determine the analysis results, including: Correlation analysis was performed on the initial data to identify the target factors that affect the power of the power station; Based on the target factors, important influencing factors are identified, and the results of the influencing factor analysis are determined based on the important influencing factors. Based on the analysis results of the influencing factors, factors that have an impact on the power of the power station exceeding the threshold are selected as the analysis results; The power stations are at least two, and power prediction is performed using any one of the following modeling schemes: single-station modeling, regional modeling, or whole-network modeling. For the single-site modeling scheme, a corresponding single-site power prediction model is established based on the analysis results, and the power model prediction result is determined based on the single-site power prediction model. Based on the power model prediction results, a power prediction model for the entire network from a single power station is established. The power generation of new energy sources is predicted based on the single power station network power prediction model, and the total power prediction value of new energy sources is determined by correction based on the power station processing strategy. For the regional modeling scheme, cluster analysis is performed based on the geographical location and meteorological characteristics of at least two of the said stations to determine at least two regions; meteorological characteristic analysis is performed on each of the said regions to establish a regional power prediction model; and a first whole-network power prediction model is established based on the meteorological forecast of the location of each of the said stations and combined with K-means cluster analysis. The power generation of new energy sources is predicted based on the first whole-network power prediction model, and the total power prediction value of new energy sources is determined by correction based on the power station processing strategy. For the whole network modeling scheme, a whole network power prediction model is established based on the total actual power value of the whole network; The power generation of new energy sources is predicted based on the network-wide power prediction model, and the total power prediction value of new energy sources is determined by correction based on the power plant processing strategy.

2. The method of claim 1, wherein: Also includes: Based on the meteorological forecasts for the locations of each of the aforementioned stations, a second power prediction model for the entire network is established.

3. The method of claim 1, wherein: The establishment of a corresponding single-station power prediction model based on the analysis results includes: Based on the analysis results, a reference sequence and a comparison sequence are determined; The correlation degree is determined based on the reference sequence and the comparison sequence; Training samples are determined based on the correlation, and a corresponding single-site power prediction model is established based on the training samples.

4. The method of claim 1, wherein: The process of determining the predicted total power of new energy sources based on the power plant processing strategy includes: determining the maintenance plan processing correction strategy, extreme weather correction strategy, power plant expansion processing strategy, and power curtailment processing strategy for each of the power plants. Based on the maintenance plan correction strategy, the extreme weather correction strategy, the power expansion processing strategy, and the power curtailment processing strategy, the power prediction values ​​of each of the power plants are corrected to determine the total power prediction value of new energy sources.

5. The method according to claim 1, characterized in that: Also includes: The predicted total power of the new energy source is evaluated based on the prediction accuracy calculation formula, and the evaluation result is determined. The formula for calculating the prediction accuracy includes: ， Among them, the Characterization accuracy Characterizing actual power, Characterize the predicted power, Represents the moment.

6. A new energy power generation prediction device, implementing the new energy power generation prediction method as described in any one of claims 1-5, characterized in that, include: The data analysis module is configured to acquire initial data from each station, perform meteorological characteristic analysis on the initial data, and determine the analysis results; wherein, there are at least two stations. The power station model module is configured to establish a corresponding single power station power prediction model based on the analysis results, and to determine the power model prediction results based on the single power station power prediction model. The whole network model module is configured to establish a single-station whole network power prediction model based on the power model prediction results. A power prediction model for the entire network is established based on the actual total power value of the entire network. The model prediction module is configured to predict the power generation of new energy sources based on the whole network power prediction model, and to determine the total power prediction value of new energy sources by making corrections based on the power station processing strategy.

7. A computing device, characterized in that, include: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, they implement the steps of the new energy power generation prediction method according to any one of claims 1 to 5.

8. A computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the new energy power generation prediction method according to any one of claims 1 to 5.

Images