New energy generation power prediction method and device

Abstract

The invention relates to the technical field of data processing, and discloses a new energy power generation power prediction method and device, and the method comprises the steps: obtaining the initial data of each station, and carrying out the meteorological feature analysis of the initial data, and determining an analysis result; wherein the number of the stations 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 the whole-network total actual power value; and performing new energy power generation power prediction based on the whole network power prediction model, and performing correction based on a station processing strategy to determine a new energy total power prediction value. A corresponding single-station power prediction model is established, and a power model prediction result is determined based on the single-station power prediction model; and on the basis of the power model prediction result and the whole-network total actual power value, a whole-network power prediction model is established to perform new energy power generation power prediction, so that more accurate power prediction can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method for predicting power generation from renewable energy sources. Background Art

[0002] At present, the power grid dispatching department requires power stations (including wind power and photovoltaic power) to report power forecasts, including short-term and ultra-short-term power forecasts. The short-term forecast is the forecast of the power station output power for 72 hours from 00:00 the next day, with a time resolution of 15 minutes, which is used for system power generation planning; the ultra-short-term forecast is a rolling forecast with a lead time of 0 to 4 hours, which is used for real-time dispatching of the power system. At present, the power grid dispatching produces cluster output forecasting services by simply adding up the predicted power of power stations. There are certain errors in the power forecast of power stations. Different power stations have different prediction modes, and all operating data of all power stations are required, which increases the error of cluster power forecasting.

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

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

[0005] In view of this, the present invention provides a new energy power generation power prediction method to solve the technical defects existing in the prior art.

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

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

[0008] 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;

[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 renewable energy is predicted based on the power prediction model of the entire network, and the total power prediction value of renewable energy is determined by correction based on the site processing strategy.

[0011] In a possible implementation, the method further includes:

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

[0013] Analyze the meteorological characteristics of each region and establish a regional power prediction model;

[0014] According to the weather forecast of each station location, the first full-network power prediction model is established.

[0015] In a possible implementation, the method further includes:

[0016] According to the weather forecast of each station location, a second full-network power prediction model is established.

[0017] In a possible implementation, performing meteorological characteristic analysis on the initial data to determine the analysis result includes:

[0018] Conduct correlation analysis on the initial data to determine the target factors that affect the station power;

[0019] Determine the important influencing factors based on the target factors, and determine the influencing factor analysis results based on the important influencing factors;

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

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

[0022] determining a reference sequence and a comparison sequence based on the analysis results;

[0023] Determining relatedness based on the reference sequence and the comparison sequence;

[0024] The training samples are determined based on the correlation, and the corresponding single-station power prediction model is established based on the training samples.

[0025] In a possible implementation, the predicted value of the total power of renewable energy is determined by making corrections based on the site processing strategy, including:

[0026] Determine the maintenance plan processing and correction strategy, extreme weather correction strategy, power field expansion processing strategy and power restriction processing strategy for each station;

[0027] Based on the maintenance plan correction strategy, extreme weather correction strategy, electric field capacity expansion strategy and power restriction strategy, the power forecast value of each station is corrected to determine the total power forecast value of new energy.

[0028] In a possible implementation, the method further includes:

[0029] Evaluate the predicted value of the total power of the new energy source based on the prediction accuracy calculation formula to determine the evaluation result;

[0030] The prediction accuracy calculation formula includes:

[0031]

[0032] Wherein, Acc represents the accuracy, p represents the actual power, and p ′ represents the predicted power, and i represents the moment.

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

[0034] A data analysis module is configured to obtain initial data of each station, and perform meteorological characteristic analysis on the initial data to determine an analysis result; wherein there are at least two stations;

[0035] The station model module is configured to establish a corresponding single-station power prediction model based on the analysis result, and determine a power model prediction result based on the single-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 result and the total actual power value of the whole network;

[0037] The model prediction module is configured to predict the power generation of renewable energy based on the power prediction model of the entire network, and to make corrections based on the site processing strategy to determine the predicted value of the total power of renewable energy.

[0038] According to a third aspect of the present invention, there is provided a computing device, 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, the steps of the above-mentioned new energy power generation power prediction method are implemented.

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

[0043] The present invention provides a method and device for predicting power generation of renewable energy, wherein the method comprises: obtaining initial data of each station, performing meteorological characteristic analysis on the initial data to determine the analysis result; wherein, there are at least two stations; establishing a corresponding single-station power prediction model based on the analysis result, and determining the power model prediction result based on the single-station power prediction model; establishing a full-network power prediction model based on the power model prediction result and the total actual power value of the whole network; predicting the power generation of renewable energy based on the full-network power prediction model, and correcting and determining the total power prediction value of renewable energy based on the station processing strategy. By establishing a corresponding single-station power prediction model, and determining the power model prediction result based on the single-station power prediction model; and establishing a full-network power prediction model based on the power model prediction result and the total actual power value of the whole network to predict the power generation of renewable energy, a more accurate power prediction can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a flow chart of a new energy power generation power prediction method provided by an embodiment of this specification;

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

[0046] Figure 3 It is a clustering schematic diagram of a new energy power generation power prediction method provided by an embodiment of this specification;

[0047] Figure 4 It is a prediction correction schematic diagram of a new energy power generation power prediction method provided by an embodiment of this specification;

[0048] Figure 5 It is a structural schematic diagram of a new energy power generation prediction device provided by an embodiment of this specification;

[0049] Figure 6 It is a structural block diagram of a computing device provided by an embodiment of this specification. DETAILED DESCRIPTION

[0050] Many specific details are described in the following description to facilitate 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 generalizations without violating the connotation of this specification, so this specification is not limited to the specific implementation disclosed below.

[0051] The terms used in one or more embodiments of this specification are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of this specification. The singular forms of "a" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" 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, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0053] In this specification, a new energy power generation prediction method is provided. This specification also involves a new energy power generation prediction device, a computing device, and a computer-readable storage medium, which are described in detail one by one in the following embodiments.

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

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

[0056] In practical applications, see Figure 2 , which can include three modeling schemes: single station modeling, regional modeling, and full network modeling. Among them, the single station modeling scheme includes the following steps: analyze the meteorological characteristics of each station in the whole network and establish the corresponding single station power prediction model. Based on the power model prediction results of the single station and the total actual power value of the whole network, establish the power prediction model of the whole network.

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

[0058] Specifically, the regional modeling scheme includes the following steps: according to the geographical location and meteorological characteristics of the whole network stations, cluster analysis is performed to divide multiple regions (region 1, region 2...region m). According to the meteorological characteristics analysis of each region, a regional power prediction model is established. Based on the meteorological forecast of the location of each station, a first whole network power prediction model is established.

[0059] For example, see Figure 3 According to the geographical location, meteorological and other characteristics of all grid-connected stations, combined with Kmeans cluster analysis, different regions are divided. This scheme not only considers the geographical location of the station, but also explores the similar characteristics of meteorological characteristics and power generation laws. Wind and solar power prediction models are established in different regions, and finally summarized into the power prediction results of the entire network to improve the accuracy of regional predictions.

[0060] In another possible implementation, the method further includes: establishing a second full-network power prediction model according to the weather forecast of the location of each station.

[0061] Specifically, a second full-network power prediction model is established based on the weather forecast of each station. As a structure for extracting spatiotemporal features, the graph convolutional network (GCN) is used to extract the spatiotemporal correlation of the power and numerical weather forecast of each station in the wind farm cluster containing geographic location information, and then combine multimodal learning for information fusion. By mining the spatiotemporal features of the station cluster and introducing correlation analysis between stations, the accuracy of regional prediction is improved.

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

[0063] In practical applications, the power characteristics and influencing factors of the station are analyzed, and the concepts of cluster effective influencing factors and station power are proposed. Through correlation analysis, factors with greater influence on station power are found as important influencing factors of station power at the prediction time. Information reflecting the power characteristics of the station is extracted. According to the analysis results of the factors affecting station power, factors with greater influence on station power are selected as representative information features.

[0064] Step 102: 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.

[0065] In a possible implementation, a corresponding single-station 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 a correlation based on the reference sequence and the comparison sequence; determining a training sample based on the correlation, and establishing a corresponding single-station power prediction model based on the training sample.

[0066] In practical applications, the reference sequence and the comparison sequence are determined. The information features of the station power at the predicted moment are selected as the reference sequence, and the information feature vectors of the station power at the corresponding moment in the historical samples of the previous n days are selected as the comparison sequence. Samples with high sample data integrity and accuracy are selected, and the correlation and association calculation formulas are used to calculate the gray correlation between the comparison sequence and the reference sequence. The associations are sorted from large to small, and the samples with a large correlation with the predicted moment are selected as the final training samples. A prediction model is established. m samples with a large correlation with the predicted moment are selected as the final training samples. The input variable is the information features of the power station at the predicted moment, and the output variable is the predicted station power.

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

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

[0069] Step 104: forecast the power generated by renewable energy based on the whole network power forecast model, and make corrections based on the site processing strategy to determine the forecast value of the total renewable energy power.

[0070] In one possible implementation, the forecast value of the total power of new energy is determined by correction based on the site processing strategy, including: determining the maintenance plan processing correction strategy, extreme weather correction strategy, electric field capacity expansion processing strategy and power restriction processing strategy of each site; based on the maintenance plan processing correction strategy, extreme weather correction strategy, electric field capacity expansion processing strategy and power restriction processing strategy, the power prediction value of each site is corrected to determine the forecast value of the total power of new energy.

[0071] In practical applications, see Figure 4 , combined with a set of strategies such as station-scale maintenance plan processing and correction, extreme weather correction, new power field expansion processing, and regional-scale batch power restriction judgment and processing strategies, ultimately forming a forecast value for the total renewable energy power of the entire network.

[0072] In a possible implementation, the method further includes:

[0073] Evaluate the predicted value of the total power of the new energy source based on the prediction accuracy calculation formula to determine the evaluation result;

[0074] The prediction accuracy calculation formula includes:

[0075]

[0076] Wherein, Acc represents the accuracy, p represents the actual power, and p ′ represents the predicted power, and i represents the moment.

[0077] Based on the above formula to determine the accuracy of the prediction, the performance of the model can be evaluated to adjust the relevant parameters and improve the accuracy of the prediction.

[0078] Corresponding to the above method embodiment, this specification also provides a new energy power generation power prediction device embodiment, Figure 5 FIG. 1 is a schematic diagram showing a structure of a new energy power generation prediction device provided by an embodiment of the present specification. Figure 5 As shown, the device comprises:

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

[0080] The station model module 502 is configured to establish a corresponding single station power prediction model based on the analysis result, and determine a power model prediction result based on the single 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 result and the total actual power value of the whole network;

[0082] The model prediction module 504 is configured to predict the power generation of renewable energy based on the power prediction model of the entire network, and to make corrections based on the site processing strategy to determine the predicted value of the total power of renewable energy.

[0083] In a possible implementation, the model prediction module 504 is further configured to:

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

[0085] Analyze the meteorological characteristics of each region and establish a regional power prediction model;

[0086] According to the weather forecast of each station location, the first full-network power prediction model is established.

[0087] In a possible implementation, the model prediction module 504 is further configured to:

[0088] According to the weather forecast of each station location, a second full-network power prediction model is established.

[0089] In a possible implementation, the data analysis module 501 is further configured to:

[0090] Conduct correlation analysis on the initial data to determine the target factors that affect the station power;

[0091] Determine the important influencing factors based on the target factors, and determine the influencing factor analysis results based on the important influencing factors;

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

[0093] In a possible implementation, the station model module 502 is further configured to:

[0094] determining a reference sequence and a comparison sequence based on the analysis results;

[0095] Determining relatedness based on the reference sequence and the comparison sequence;

[0096] The training samples are determined based on the correlation, and the corresponding single-station power prediction model is established based on the training samples.

[0097] In a possible implementation, the model prediction module 504 is further configured to:

[0098] Determine the maintenance plan processing and correction strategy, extreme weather correction strategy, power field expansion processing strategy and power restriction processing strategy for each station;

[0099] Based on the maintenance plan correction strategy, extreme weather correction strategy, electric field capacity expansion strategy and power restriction strategy, the power forecast value of each station is corrected to determine the total power forecast value of new energy.

[0100] In a possible implementation, the model prediction module 504 is further configured to:

[0101] Evaluate the predicted value of the total power of the new energy source based on the prediction accuracy calculation formula to determine the evaluation result;

[0102] The prediction accuracy calculation formula includes:

[0103]

[0104] Wherein, Acc represents the accuracy, p represents the actual power, and p ′ represents the predicted power, and i represents the moment.

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

[0106] Figure 6 The block diagram of a computing device 600 according to an embodiment of the present 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 the database 650 is used to store data.

[0107] The computing device 600 also includes an access device 640 that enables the computing device 600 to communicate via one or more networks 660. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 640 may include one or more of any type of network interface (e.g., a network interface card (NIC)) of wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a world-wide interoperability for microwave access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, and a near field communication (NFC).

[0108] In one embodiment of the present specification, the above components of the computing device 600 and Figure 6 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 6 The computing device structure block diagram shown is only for the purpose of illustration, 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 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 600 may also be a mobile or stationary server.

[0110] Among them, the processor 620 is used to execute the following computer executable instructions, which, when executed by the processor, implement the steps of the above-mentioned new energy power generation prediction method. The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the above-mentioned new energy power generation prediction method belong to the same concept. The details of the technical scheme of the computing device that are not described in detail can be found in the description of the technical scheme of the above-mentioned new energy power generation prediction method.

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

[0112] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the above-mentioned new energy power generation prediction method belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the above-mentioned new energy power generation prediction method.

[0113] An embodiment of the present specification further provides a computer program, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned new energy power generation prediction method.

[0114] The above is a schematic scheme of a computer program of this embodiment. It should be noted that the technical scheme of the computer program and the technical scheme of the above-mentioned new energy power generation prediction method belong to the same concept, and the details not described in detail in the technical scheme of the computer program can be referred to the description of the technical scheme of the above-mentioned new energy power generation prediction method.

[0115] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0116] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased 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 do not include electric carrier signals and telecommunication signals.

[0117] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0118] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0119] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to only the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that technicians in the relevant technical field can well understand and use this specification. This specification is only limited by the claims and their full scope and equivalents.

Claims

1. A method for predicting power generation from renewable energy, characterized in that: include: Acquire initial data of each station, and perform meteorological characteristic analysis on the initial data to determine analysis results; wherein the number of the stations 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; Based on the power model prediction result and the total actual power value of the whole network, a whole network power prediction model is established; The power generation power of renewable energy is predicted based on the whole network power prediction model, and the predicted value of the total power of renewable energy is determined by correction based on the site processing strategy.

2. The method according to claim 1, characterized in that Also includes: Based on the geographical locations and meteorological characteristics of at least two of the stations, cluster analysis is performed to determine at least two regions; Conducting meteorological characteristic analysis based on each of the regions and establishing a regional power prediction model; A first network-wide power prediction model is established based on the weather forecast for the location of each of the stations.

3. The method according to claim 1, characterized in that Also includes: A second full-network power prediction model is established based on the weather forecast for the location of each of the stations.

4. The method according to claim 1, characterized in that The step of performing meteorological characteristic analysis on the initial data to determine the analysis result includes: Performing correlation analysis on the initial data to determine target factors that have an impact on the station power; Determine important influencing factors based on the target factors, and determine influencing factor analysis results based on the important influencing factors; According to the analysis result of the influencing factors, the factors whose influence on the station power exceeds a threshold are selected as the analysis result.

5. The method according to claim 1, characterized in that The establishing of a corresponding single-station power prediction model based on the analysis result comprises: Determine a reference sequence and a comparison sequence based on the analysis results; determining a degree of relatedness based on the reference sequence and the comparison sequence; A training sample is determined based on the correlation degree, and a corresponding single-station power prediction model is established based on the training sample.

6. The method according to claim 1, characterized in that The method of correcting and determining the predicted value of the total power of new energy sources based on the site processing strategy includes: Determine the maintenance plan processing correction strategy, extreme weather correction strategy, electric field capacity expansion processing strategy and power restriction processing strategy for each of the stations; Based on the maintenance plan processing correction strategy, the extreme weather correction strategy, the electric field capacity expansion processing strategy and the power restriction processing strategy, the power forecast value of each station is corrected to determine the total power forecast value of new energy.

7. The method according to claim 1, characterized in that Also includes: Evaluate the predicted value of the total power of the new energy source based on the prediction accuracy calculation formula to determine the evaluation result; The prediction accuracy calculation formula includes: Wherein, Acc represents the accuracy, p represents the actual power, and p ′ represents the predicted power, and i represents the moment.

8. A new energy power generation power prediction device, characterized in that: include: A data analysis module is configured to obtain initial data of each station, and perform meteorological characteristic analysis on the initial data to determine an analysis result; wherein the number of the stations is at least two; A station model module is configured to establish a corresponding single-station power prediction model based on the analysis result, and determine a power model prediction result based on the single-station power prediction model; A whole network model module is configured to establish a whole network power prediction model based on the power model prediction result and the whole network total actual power value; The model prediction module is configured to predict the power generation of renewable energy based on the whole network power prediction model, and to make corrections based on the site processing strategy to determine the predicted value of the total power of renewable energy.

9. 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, the steps of the new energy power generation prediction method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the new energy power generation prediction method according to any one of claims 1 to 7.

Images