Regional power generation power prediction method, device, equipment and storage medium

Abstract

The present disclosure relates to a method, apparatus, device and storage medium for predicting regional power generation. This method can generate ciphertext features corresponding to the original wind and light data at the local client of the wind and light power station, and fuse the ciphertext features of multiple wind and light power stations for regional power generation prediction, avoiding the problem of data islands. Moreover, the original wind and light data of the wind and light power station can only be obtained by the local client and encrypted into ciphertext features, and the server only obtains the ciphertext sum features without knowing the original wind and light data of the wind and light power station, so that the problem of wind and light data leakage will not occur in the third-party server, improving the security of the original wind and light data of the wind and light power station.

Description

Technical Field

[0001] The present disclosure relates to the technical field of power generation, and particularly to a method, device, equipment and storage medium for predicting regional power generation power. Background Art

[0002] As the proportion of renewable energy power generation such as wind power generation and photovoltaic power generation in the power system is increasing, the uncertainty and randomness of its output have brought adverse effects to the efficient operation of the power system. How to accurately predict the regional power generation power based on the wind power, photovoltaic power and other renewable energies of multiple stations in the region is a necessary prerequisite for the safe and stable operation of the power system, optimizing power market transactions and other links.

[0003] At present, generally, the wind power, photovoltaic power and other data of a single station are used for regional power generation prediction. However, data sharing does not occur among multiple stations, resulting in the problem of data islands. If the original wind and light data of multiple stations are entrusted to a third-party server to calculate the power generation power, it is also difficult to ensure the security of the original wind and light data. Summary of the Invention

[0004] In order to solve the above technical problems, the present disclosure provides a method, device, equipment and storage medium for predicting regional power generation power.

[0005] In a first aspect, the present disclosure provides a method for predicting regional power generation power, the method comprising:

[0006] Performing feature extraction on the wind and light data of a target wind and light power station to obtain wind and light features, wherein the target wind and light power station is a power station in a region to be predicted, and the region to be predicted further includes at least one associated wind and light power station related to the output of the target wind and light power station;

[0007] Performing encryption processing on the wind and light features to generate ciphertext features of the target wind and light power station;

[0008] Based on the ciphertext features of the target wind and light power station and the ciphertext features of the associated wind and light power stations, generating ciphertext sum features of the target wind and light power station and the associated wind and light power stations, and sending the ciphertext sum features to a server corresponding to the region to be predicted, wherein the server is used to generate a decrypted fusion feature corresponding to the ciphertext sum features;

[0009] Performing power generation power prediction based on the decrypted fusion feature returned by the server and the wind and light features of the target wind and light power station, and determining the predicted power corresponding to the target wind and light power station, wherein the predicted power corresponding to the target wind and light power station and the predicted power corresponding to the associated wind and light power stations are used to add up to the regional power generation power of the region to be predicted.

[0010] In a second aspect, the present disclosure provides a method for predicting regional power generation, the method comprising:

[0011] Obtaining the ciphertext summation features of a target wind-solar power station and associated wind-solar power stations, wherein the target wind-solar power station and the associated wind-solar power stations are all power generation stations within the area to be predicted, the ciphertext summation features are generated based on the ciphertext features of the target wind-solar power station and the ciphertext features of the associated wind-solar power stations, and the ciphertext feature of each wind-solar power station is generated based on its corresponding wind-solar feature, and the wind-solar feature of each wind-solar power station is obtained by performing feature extraction on its corresponding wind-solar data;

[0012] Generating a decryption summation feature corresponding to the ciphertext summation feature, and performing a fusion process on the decryption summation feature to generate a decryption fusion feature of the area to be predicted;

[0013] Sending the decryption fusion feature to the client corresponding to the target wind-solar power station, wherein the client corresponding to the target wind-solar power station is configured to perform power generation prediction based on the decryption fusion feature and the wind-solar feature corresponding to the target wind-solar power station to determine the predicted power corresponding to the target wind-solar power station, and the predicted power corresponding to the target wind-solar power station and the predicted power corresponding to the associated wind-solar power stations are used to add up to obtain the regional power generation of the area to be predicted.

[0014] In a third aspect, the present disclosure provides a device for predicting regional power generation, the device comprising:

[0015] A first acquisition module, configured to perform feature extraction on the wind-solar data of a target wind-solar power station to obtain a wind-solar feature, wherein the target wind-solar power station is a power generation station within the area to be predicted, and the area to be predicted further includes at least one associated wind-solar power station related to the output of the target wind-solar power station;

[0016] A first generation module, configured to perform encryption processing on the wind-solar feature to generate a ciphertext feature of the target wind-solar power station;

[0017] A second generation module, configured to generate a ciphertext summation feature of the target wind-solar power station and the associated wind-solar power stations based on the ciphertext feature of the target wind-solar power station and the ciphertext features of the associated wind-solar power stations, and send the ciphertext summation feature to the server corresponding to the area to be predicted, wherein the server is configured to generate a decryption fusion feature corresponding to the ciphertext summation feature;

[0018] A second acquisition module, configured to perform power generation prediction based on the decrypted fusion features returned by the server and the wind-solar features of the target wind-solar power station, and determine the predicted power corresponding to the target wind-solar power station. The predicted power corresponding to the target wind-solar power station and the predicted power corresponding to the associated wind-solar power station are used to add up to obtain the regional power generation of the area to be predicted.

[0019] Fourthly, an embodiment of the present disclosure further provides a regional power generation prediction device, which includes:

[0020] A third acquisition module, configured to acquire the ciphertext summation features of the target wind-solar power station and the associated wind-solar power station. The target wind-solar power station and the associated wind-solar power station are both power generation stations in the area to be predicted. The ciphertext summation features are generated based on the ciphertext features of the target wind-solar power station and the ciphertext features of the associated wind-solar power station. Moreover, the ciphertext features of each wind-solar power station are generated based on its corresponding wind-solar features, and the wind-solar features of each wind-solar power station are obtained by extracting features from its corresponding wind-solar data.

[0021] A third generation module, configured to generate the decrypted summation features corresponding to the ciphertext summation features, and perform a fusion process on the decrypted summation features to generate the decrypted fusion features of the area to be predicted.

[0022] A sending module, configured to send the decrypted fusion features to the client corresponding to the target wind-solar power station. The client corresponding to the target wind-solar power station is configured to perform power generation prediction based on the decrypted fusion features and the wind-solar features corresponding to the target wind-solar power station, and determine the predicted power corresponding to the target wind-solar power station. Moreover, the predicted power corresponding to the target wind-solar power station and the predicted power corresponding to the associated wind-solar power station are used to add up to obtain the regional power generation of the area to be predicted.

[0023] Fifthly, an embodiment of the present disclosure further provides an electronic device, which includes:

[0024] One or more processors;

[0025] A storage device, configured to store one or more programs,

[0026] When the one or more programs are executed by the one or more processors, the one or more processors implement the method provided in the first aspect or implement the method provided in the second aspect.

[0027] Sixthly, an embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the method provided in the first aspect or implements the method provided in the second aspect.

[0028] The technical solution provided by the embodiments of the present disclosure has the following advantages compared with the prior art:

[0029] A regional power generation power prediction method, device, equipment and storage medium according to an embodiment of the present disclosure, the method includes: extracting features from the wind-solar data of a target wind-solar power station to obtain wind-solar features, where the target wind-solar power station is a power station in a to-be-predicted area, and the to-be-predicted area further includes at least one associated wind-solar power station related to the output of the target wind-solar power station; performing encryption processing on the wind-solar features to generate ciphertext features of the target wind-solar power station; generating ciphertext sum features of the target wind-solar power station and the associated wind-solar power stations based on the ciphertext features of the target wind-solar power station and the ciphertext features of the associated wind-solar power stations, and sending the ciphertext sum features to a server corresponding to the to-be-predicted area, where the server is used to generate a decrypted fusion feature corresponding to the ciphertext sum feature; performing power generation power prediction based on the decrypted fusion feature returned by the server and the wind-solar features of the target wind-solar power station to determine the predicted power corresponding to the target wind-solar power station, where the predicted power corresponding to the target wind-solar power station and the predicted power corresponding to the associated wind-solar power stations are used to add up to obtain the regional power generation power of the to-be-predicted area. Thus, it is possible to generate ciphertext features corresponding to the original wind-solar data on the local client of the wind-solar power station, and fuse the ciphertext features of multiple wind-solar power stations for regional power generation power prediction, avoiding the problem of data islands. Moreover, the original wind-solar data of the wind-solar power station can only be obtained by the local client and encrypted into ciphertext features, and the server only obtains the ciphertext sum features and cannot know the original wind-solar data of the wind-solar power station, so that the problem of wind-solar data leakage will not occur in the third-party server, improving the security of the original wind-solar data of the wind-solar power station. Brief Description of the Drawings

[0030] The drawings here are incorporated into the description and form a part of this description, showing embodiments consistent with the present disclosure and used together with the description to explain the principles of the present disclosure.

[0031] To more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0032] Figure 1 It is a system architecture diagram of a regional power generation power prediction system provided by an embodiment of the present disclosure;

[0033] Figure 2 It is a flowchart of a regional power generation power prediction method provided by an embodiment of the present disclosure;

[0034] Figure 3Schematic flowchart of another regional power generation prediction method provided by an embodiment of the present disclosure;

[0035] Figure 4 Logical schematic diagram of a regional power generation prediction method provided by an embodiment of the present disclosure;

[0036] Figure 5 Schematic structural diagram of a regional power generation prediction device provided by an embodiment of the present disclosure;

[0037] Figure 6 Schematic structural diagram of another regional power generation prediction device provided by an embodiment of the present disclosure;

[0038] Figure 7 Schematic structural diagram of an electronic device provided by an embodiment of the present disclosure. Detailed implementation manners

[0039] In order to more clearly understand the above objects, features and advantages of the present disclosure, the solutions of the present disclosure will be further described below. It should be noted that, without conflict, the embodiments of the present disclosure and the features in the embodiments may be combined with each other.

[0040] Many specific details are set forth in the following description in order to fully understand the present disclosure, but the present disclosure may be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only a part of the embodiments of the present disclosure, rather than all the embodiments.

[0041] To facilitate the understanding of the regional power generation prediction method, an embodiment of the present disclosure provides a power station system.

[0042] Figure 1 Shows a system architecture diagram of a power system provided by an embodiment of the present disclosure.

[0043] As Figure 1 shown, the power system includes a to-be-predicted area 10 and a third-party server 20, wherein the to-be-predicted area 10 includes a plurality of wind-solar power stations and a plurality of clients, the plurality of wind-solar power stations include wind-solar power station 11, wind-solar power station 12... wind-solar power station 1n, and the plurality of clients include client 21, client 22... client 2n.

[0044] The following explains with the target wind-solar power station being the wind-solar power station 1n. Specifically, the client 2n extracts features from the wind-solar data of the wind-solar power station 1n to obtain the wind-solar features of the wind-solar power station 1n, encrypts the wind-solar features to generate the ciphertext features of the wind-solar power station 1n, and based on the ciphertext features of the wind-solar power station 1n and the ciphertext features corresponding to the wind-solar power stations 11, 12... 1(n - 1) respectively, generates the ciphertext summation features of the wind-solar power station 1n and the wind-solar power stations 11, 12... 1(n - 1), and sends the ciphertext summation features to the server 20, where the server 20 is used to generate the decrypted fusion features corresponding to the ciphertext summation features; further, the client 2n performs power generation prediction based on the decrypted fusion features returned by the server 20 and the wind-solar features of the wind-solar power station 1n to determine the predicted power corresponding to the wind-solar power station 1n; finally, the predicted power corresponding to the wind-solar power station 1n and the predicted powers corresponding to the wind-solar power stations 11, 12... 1(n - 1) respectively are used to add up to obtain the regional power generation power of the area to be predicted 10.

[0045] Based on Figure 1 the system architecture diagram of the power system shown, the embodiments of the present disclosure provide a method, device, equipment and storage medium for predicting regional power generation power.

[0046] Next, in combination with Figure 2 the method for predicting regional power generation power provided by the embodiments of the present disclosure will be described. In the embodiments of the present disclosure, the method for predicting regional power generation power can be executed by the client corresponding to the target wind-solar power station in the area to be predicted. Among them, the client can be understood as the client local to the wind-solar power station.

[0047] Figure 2 The flow diagram of a method for predicting regional power generation power provided by the embodiments of the present disclosure is shown.

[0048] As Figure 2 shown, the method for predicting regional power generation power may include the following steps.

[0049] S210. Extract features from the wind-solar data of the target wind-solar power station to obtain wind-solar features, where the target wind-solar power station is a power generation station in the area to be predicted, and the area to be predicted further includes at least one associated wind-solar power station related to the output of the target wind-solar power station.

[0050] In this embodiment, when it is necessary to predict the regional power generation power of an area to be predicted where multiple wind-solar power stations are deployed, any wind-solar power station in the area to be predicted is used as the target wind-solar power station, and the client local to the target wind-solar power station is used to collect its corresponding wind-solar data.

[0051] Among them, the area to be predicted can be an administrative area where multiple wind and solar power stations are deployed as power generation stations. Specifically, the power outputs of the multiple wind and solar power stations in the area to be predicted are related, that is, there is a restrictive relationship between the power generation powers of the multiple wind and solar power stations, such that each wind and solar power station has at least one associated wind and solar power station with related power output.

[0052] Among them, the wind and solar data refers to the original energy data of the target wind and solar power station, that is, the original wind and solar data. Specifically, the wind and solar power station is used to collect wind power data and photovoltaic data to form the original wind and solar data of the power station.

[0053] Optionally, the wind and solar data may include, but is not limited to, wind speed, wind direction, irradiance, temperature, humidity, air pressure, etc.

[0054] Further, in this embodiment, the client local to the target wind and solar power station extracts features from the wind and solar data, so as to convert the original wind and solar data into wind and solar features in the form of feature vectors. It should be noted that the wind and solar features are represented by a series of feature values, with good stability and not easily directly stolen and used.

[0055] In the embodiments of the present disclosure, optionally, a preset encoder may be used to encode the wind and solar data to obtain encoded features, and the encoded features are used as the wind and solar features of the target wind and solar power station.

[0056] Specifically, for the wind and solar data corresponding to each moment, the client corresponding to the target wind and solar power station uses the preset encoder to extract features therefrom to obtain the wind and solar features at that moment, until the processing of the wind and solar data at all moments is completed, and the wind and solar features of the target wind and solar power station are obtained.

[0057] S220. Perform encryption processing on the wind and solar features to generate ciphertext features of the target wind and solar power station.

[0058] In this embodiment, in order to prevent the original wind and solar data from being leaked on the server of a third party, the client local to the target wind and solar power station may further encrypt the wind and solar features in the form of feature vectors to obtain encrypted ciphertext, and use the encrypted ciphertext as the ciphertext features of the target wind and solar power station. Similarly, the client local to the associated wind and solar power stations in the area to be predicted may also further encrypt the wind and solar features in the form of feature vectors to obtain encrypted ciphertext, and use the encrypted ciphertext as the ciphertext features of the associated wind and solar power stations.

[0059] Specifically, for the target wind-solar power station, the local client of the target wind-solar power station can use an encrypted random number to encrypt the plaintext information contained in the wind-solar characteristics to obtain the ciphertext characteristics of the target wind-solar power station. Among them, the encrypted random number can be any prime number, and the encrypted random number can be the public key generated by a third-party server or the local client of the target wind-solar power station based on the Paillier homomorphic encryption algorithm.

[0060] Similarly, for the associated wind-solar power station, the local client of the associated wind-solar power station can use an encrypted random number to encrypt the plaintext information contained in the wind-solar characteristics to obtain the ciphertext characteristics of the associated wind-solar power station. Among them, the encrypted random number can be any prime number, and the encrypted random number can be the public key generated by a third-party server or the local client of the associated wind-solar power station based on the Paillier homomorphic encryption algorithm.

[0061] It can be understood that the ciphertext characteristics are an encrypted ciphertext. If you want to obtain the original wind-solar data, you need to use the secret key to decrypt it to obtain the original wind-solar data in plaintext form.

[0062] S230. Generate the ciphertext sum characteristics of the target wind-solar power station and the associated wind-solar power station based on the ciphertext characteristics of the target wind-solar power station and the ciphertext characteristics of the associated wind-solar power station, and send the ciphertext sum characteristics to the server corresponding to the area to be predicted, where the server is used to generate the decrypted fusion characteristics corresponding to the ciphertext sum characteristics.

[0063] In this embodiment, the local client of the target wind-solar power station obtains the ciphertext characteristics of the associated wind-solar power station, adds its local ciphertext characteristics and the ciphertext characteristics of the associated wind-solar power station to obtain the ciphertext sum characteristics of the target wind-solar power station and the associated wind-solar power station, and further sends the ciphertext sum characteristics to the server corresponding to the area to be predicted.

[0064] Among them, the ciphertext sum characteristics refer to the weighted values of the ciphertext characteristics of the target wind-solar power station and the associated wind-solar power station, and the ciphertext sum characteristics can characterize the output correlation relationship between the wind-solar power stations.

[0065] In some embodiments, the local client of the associated wind-solar power station separately sends the ciphertext characteristics to the local client of the target wind-solar power station, so that the local client of the target wind-solar power station adds up all the ciphertext characteristics to obtain the ciphertext sum characteristics of the target wind-solar power station and the associated wind-solar power station.

[0066] In some other embodiments, each wind-solar power station in the area to be predicted is numbered in advance. If the target wind-solar power station is the nth wind-solar power station and the first to the (n - 1)th wind-solar power stations are all associated wind-solar power stations, the client at the first wind-solar power station will send the ciphertext features to the client at the second wind-solar power station. The client at the second wind-solar power station will add the obtained ciphertext features to its own ciphertext features to obtain the ciphertext sum features of the second wind-solar power station and the second wind-solar power station. Further, the ciphertext sum features obtained by the client at the second wind-solar power station are sent to the client at the third wind-solar power station. The client at the third wind-solar power station will add the obtained ciphertext sum features to its own ciphertext features to obtain the ciphertext sum features of the first, second, and third wind-solar power stations, and so on, until the ciphertext sum features of the first to the nth wind-solar power stations are obtained, which are used as the ciphertext sum features of the target wind-solar power station and the associated wind-solar power stations.

[0067] Specifically, homomorphic addition calculation can be performed on the ciphertext features of the target wind-solar power station and the ciphertext features of the associated wind-solar power stations to obtain the ciphertext sum features.

[0068] It can be understood that since the ciphertext sum features are the weighted values of the ciphertext features of multiple wind-solar power stations in the area to be predicted, after the third-party server obtains the ciphertext sum features, it can only determine the overall ciphertext features of multiple wind-solar power stations and cannot clarify the detailed ciphertext features of each wind-solar power station. Although the third-party server can decrypt the ciphertext sum features to obtain the decrypted fusion features, it can only determine the overall wind-solar features of multiple wind-solar power stations and cannot clarify the detailed wind-solar features of each wind-solar power station. Moreover, since the wind-solar features are represented by a series of feature values, they are not easily directly stolen and used. Therefore, the third-party server will never obtain the original data of each wind-solar power station, and there will be no problem of the original wind-solar data being leaked on the third-party server.

[0069] S240. Based on the decrypted fusion features returned by the server and the wind-solar features of the target wind-solar power station, perform power generation prediction to determine the predicted power corresponding to the target wind-solar power station. Among them, the predicted power corresponding to the target wind-solar power station and the predicted power corresponding to the associated wind-solar power stations are used to add up to obtain the regional power generation power of the area to be predicted.

[0070] In this embodiment, the client at the target wind-solar power station combines the decrypted fusion feature that can characterize the output correlation relationship between wind-solar power stations and the wind-solar features of the target wind-solar power station to perform power generation prediction, and obtains the predicted power of the target wind-solar power station locally. Similarly, the client at the associated wind-solar power station combines the decrypted fusion feature that can characterize the output correlation relationship between wind-solar power stations and the wind-solar features of the associated wind-solar power station to perform power generation prediction, and obtains the predicted power of the associated wind-solar power station locally.

[0071] Among them, the decrypted fusion feature refers to the decrypted information that fuses the wind-solar features of multiple wind-solar power stations.

[0072] Specifically, the client at the target wind-solar power station can use a preset decoder to decode the decrypted fusion feature and the wind-solar feature corresponding to the target wind-solar power station to obtain decoded data, and use the decoded data as the predicted power corresponding to the target wind-solar power station. Similarly, the client at the associated wind-solar power station can use a preset decoder to decode the decrypted fusion feature and the wind-solar feature corresponding to the associated wind-solar power station to obtain decoded data, and use the decoded data as the predicted power corresponding to the associated wind-solar power station.

[0073] Furthermore, the associated wind-solar power stations respectively send their locally predicted powers to the client at the target wind-solar power station, and the client at the target wind-solar power station adds up all the power generation powers to obtain the regional power generation power of the area to be predicted. Or, the client at the target wind-solar power station and the clients at the associated wind-solar power stations respectively send their corresponding power generation powers to a third-party server, and the third-party server adds up all the power generation powers to obtain the regional power generation power of the area to be predicted.

[0074] Thus, it is possible to fuse the wind-solar features of multiple wind-solar power stations to perform regional power generation prediction and avoid the problem of data islands.

[0075] A method for predicting regional power generation, the method comprising: extracting features from the wind and light data of a target wind and light power station to obtain wind and light features, wherein the target wind and light power station is a power station within the area to be predicted, and the area to be predicted further includes at least one associated wind and light power station related to the output of the target wind and light power station; encrypting the wind and light features to generate ciphertext features of the target wind and light power station; generating ciphertext sum features of the target wind and light power station and the associated wind and light power stations based on the ciphertext features of the target wind and light power station and the ciphertext features of the associated wind and light power stations, and sending the ciphertext sum features to a server corresponding to the area to be predicted, wherein the server is used to generate a decrypted fusion feature corresponding to the ciphertext sum feature; predicting the power generation based on the decrypted fusion feature returned by the server and the wind and light features of the target wind and light power station to determine the predicted power corresponding to the target wind and light power station, wherein the predicted power corresponding to the target wind and light power station and the predicted power corresponding to the associated wind and light power stations are used to add up to obtain the regional power generation of the area to be predicted. Thus, it is possible to generate ciphertext features corresponding to the original wind and light data on the local client of the wind and light power station, and fuse the ciphertext features of multiple wind and light power stations for regional power generation prediction, avoiding the problem of data islands. Moreover, the original wind and light data of the wind and light power station can only be obtained by the local client and encrypted into ciphertext features, and the server only obtains the ciphertext sum features and cannot know the original wind and light data of the wind and light power station, so that the problem of leakage of wind and light data will not occur in the third-party server, improving the security of the original wind and light data of the wind and light power station.

[0076] In another embodiment of the present disclosure, a method for predicting regional power generation is provided. The method for predicting regional power generation can be executed by a third-party server corresponding to the area to be predicted.

[0077] Figure 3 The flowchart of another method for predicting regional power generation provided by the embodiment of the present disclosure is shown.

[0078] As Figure 3 shown, the method for predicting regional power generation may include the following steps.

[0079] S310. Obtain the ciphertext sum features of the target wind and light power station and the associated wind and light power stations, wherein the target wind and light power station and the associated wind and light power stations are both power stations within the area to be predicted, the ciphertext sum features are generated based on the ciphertext features of the target wind and light power station and the ciphertext features of the associated wind and light power stations, and the ciphertext feature of each wind and light power station is generated based on its corresponding wind and light features, and the wind and light features of each wind and light power station are obtained by extracting features from its corresponding wind and light data.

[0080] In this embodiment, the area to be predicted includes a target wind-solar power station and associated wind-solar power stations. First, the client at each wind-solar power station locally collects the corresponding wind-solar data and extracts features from the corresponding wind-solar data to obtain the wind-solar features of each wind-solar power station. Then, the client at each wind-solar power station locally encrypts the obtained wind-solar features to obtain the ciphertext features of each wind-solar power station. Further, the client at the target wind-solar power station generates the ciphertext sum features of the target wind-solar power station and the associated wind-solar power stations based on the ciphertext features of the target wind-solar power station and the ciphertext features of the associated wind-solar power stations. Finally, the client at the target wind-solar power station sends the ciphertext sum features to the server of a third party.

[0081] Specifically, the client at each wind-solar power station can use a preset encoder to encode the corresponding wind-solar data to obtain encoded features, and use the encoded features as the wind-solar features of each wind-solar power station.

[0082] Specifically, the client at each wind-solar power station can use an encryption random number to encrypt the plaintext information included in the corresponding wind-solar features to obtain the ciphertext features of each wind-solar power station.

[0083] Specifically, the client at the target wind-solar power station can perform a homomorphic addition calculation on the ciphertext features of the target wind-solar power station and the ciphertext features of the associated wind-solar power stations to obtain the ciphertext sum features.

[0084] S320. Generate a decryption sum feature corresponding to the ciphertext sum feature, and perform a fusion process on the decryption sum feature to generate a decryption fusion feature of the area to be predicted.

[0085] In this embodiment, the server of a third party can decrypt the ciphertext sum feature to generate a decryption sum feature.

[0086] Among them, the decryption sum feature is the weighted value of the decryption features of the target wind-solar power station and the associated wind-solar power stations, and can represent the output correlation relationship between the wind-solar power stations.

[0087] Specifically, the ciphertext sum feature can be decrypted into plaintext information by using a decryption random number to obtain a decryption sum feature including plaintext information. Among them, the decryption random number can be any prime number, and the decryption random number can be the private key generated by the server of a third party based on the Paillier semi-homomorphic encryption algorithm.

[0088] Further, the server of a third party performs a fusion process on the decryption sum feature to fuse the wind-solar features of the target wind-solar power station and the associated wind-solar power stations to obtain a decryption fusion feature of the area to be predicted.

[0089] Specifically, the average value of the decryption sum feature can be determined based on the decryption sum feature and the number of wind-solar power stations in the area to be predicted, and the preset fusion model can be used to perform fusion processing on the average value of the decryption sum feature to obtain the decryption fusion feature.

[0090] It can be understood that although the third-party server can determine the average value of the decryption sum feature based on the decryption sum feature and the number of wind-solar power stations in the area to be predicted, this average value only represents the average value of the wind-solar characteristics of multiple wind-solar power stations, rather than the true wind-solar characteristics of each wind-solar power station. Therefore, the third-party server will never obtain the original data of each wind-solar power station, and there will be no problem of leakage of the original wind-solar data on the third-party server.

[0091] S330. Send the decryption fusion feature to the client local to the target wind-solar power station. The client local to the target wind-solar power station is used to perform power generation prediction based on the decryption fusion feature and the wind-solar characteristics corresponding to the target wind-solar power station, determine the predicted power corresponding to the target wind-solar power station, and the predicted power corresponding to the target wind-solar power station and the predicted power corresponding to the associated wind-solar power station are used to add up to obtain the regional power generation power of the area to be predicted.

[0092] In this embodiment, after the third-party server sends the decryption fusion feature to the client local to the target wind-solar power station, the client local to the target wind-solar power station combines the decryption fusion feature that can represent the output correlation relationship between wind-solar power stations and the wind-solar characteristics of the target wind-solar power station to perform power generation prediction, and obtains the predicted power local to the target wind-solar power station. Similarly, the client local to the associated wind-solar power station combines the decryption fusion feature that can represent the output correlation relationship between wind-solar power stations and the wind-solar characteristics of the associated wind-solar power station to perform power generation prediction, and obtains the predicted power local to the associated wind-solar power station.

[0093] Specifically, the client local to the target wind-solar power station can use the preset decoder to perform decoding processing on the decryption fusion feature and the wind-solar characteristics corresponding to the target wind-solar power station to obtain the decoded data, and use the decoded data as the predicted power corresponding to the target wind-solar power station. Similarly, the client local to the associated wind-solar power station can use the preset decoder to perform decoding processing on the decryption fusion feature and the wind-solar characteristics corresponding to the associated wind-solar power station to obtain the decoded data, and use the decoded data as the predicted power corresponding to the associated wind-solar power station.

[0094] Further, the associated wind-solar power plants respectively send their local predicted power to the client at the local site of the target wind-solar power plant. The client at the local site of the target wind-solar power plant adds up all the generated powers to obtain the regional generated power of the area to be predicted. Alternatively, the client at the local site of the target wind-solar power plant and the clients at the local sites of the associated wind-solar power plants respectively send their corresponding generated powers to a third-party server, and the third-party server adds up all the generated powers to obtain the regional generated power of the area to be predicted.

[0095] Thereby, it is possible to fuse the wind-solar characteristics of multiple wind-solar power plants to predict the regional generated power and avoid the problem of data islands.

[0096] A method for predicting regional generated power according to an embodiment of the present disclosure, the method includes: obtaining the ciphertext summation characteristics of a target wind-solar power plant and associated wind-solar power plants, where the target wind-solar power plant and the associated wind-solar power plants are all power plants within the area to be predicted, the ciphertext summation characteristics are generated based on the ciphertext characteristics of the target wind-solar power plant and the ciphertext characteristics of the associated wind-solar power plants, and the ciphertext characteristics of each wind-solar power plant are generated based on its corresponding wind-solar characteristics, and the wind-solar characteristics of each wind-solar power plant are obtained by extracting characteristics from its corresponding wind-solar data; generating a decryption summation characteristic corresponding to the ciphertext summation characteristic, and performing a fusion process on the decryption summation characteristic to generate a decryption fusion characteristic of the area to be predicted; sending the decryption fusion characteristic to the client at the local site of the target wind-solar power plant, where the client at the local site of the target wind-solar power plant is used to predict the generated power based on the decryption fusion characteristic and the wind-solar characteristics corresponding to the target wind-solar power plant, determine the predicted power corresponding to the target wind-solar power plant, and the predicted power corresponding to the target wind-solar power plant and the predicted powers corresponding to the associated wind-solar power plants are used to add up to obtain the regional generated power of the area to be predicted. Thereby, it is possible to generate the ciphertext characteristics corresponding to the original wind-solar data at the client at the local site of the wind-solar power plant, fuse the ciphertext characteristics of multiple wind-solar power plants, and fuse the decryption summation characteristics at the third-party server to predict the regional generated power and avoid the problem of data islands. Moreover, the original wind-solar data of the wind-solar power plant can only be obtained by the local client and encrypted into ciphertext characteristics, and the server only obtains the ciphertext summation characteristics and cannot know the original wind-solar data of the wind-solar power plant, so that the third-party server will not have the problem of wind-solar data leakage and improves the security of the original wind-solar data of the wind-solar power plant.

[0097] In another embodiment of the present disclosure, a method for predicting regional generated power is provided. And a specific explanation is given in combination with Figure 4 the logical schematic diagram of the method for predicting regional generated power as shown. Figure 4The third-party server corresponds to the area to be predicted. The area to be predicted includes Wind-Solar Power Station 1, Wind-Solar Power Station 2, and Wind-Solar Power Station 3 (not shown in the figure). Among them, Wind-Solar Power Station 3 is the target wind-solar power station, and Wind-Solar Power Station 1 and Wind-Solar Power Station 2 are associated wind-solar power stations. Moreover, Client 1 corresponds to Wind-Solar Power Station 1, Client 2 corresponds to Wind-Solar Power Station 2, and Client 3 corresponds to Wind-Solar Power Station 3.

[0098] As Figure 4 shown, the method for predicting the power generation of this area includes the following steps:

[0099] S1. Client 1 obtains the wind-solar data of Wind-Solar Power Station 1, Client 2 obtains the wind-solar data of Wind-Solar Power Station 2, and Client 3 obtains the wind-solar data of Wind-Solar Power Station 3;

[0100] S2. The preset encoder in Client 1 extracts features from the wind-solar data to obtain wind-solar features. Similarly, the preset encoder in Client 2 extracts features from the wind-solar data to obtain wind-solar features. Similarly, the preset encoder in Client 3 extracts features from the wind-solar data to obtain wind-solar features;

[0101] S3. The encryption module in Client 1 encrypts the wind-solar features to obtain the ciphertext features of Wind-Solar Power Station 1. Similarly, the encryption module in Client 2 encrypts the wind-solar features to obtain the ciphertext features of Wind-Solar Power Station 2. Similarly, the encryption module in Client 3 encrypts the wind-solar features to obtain the ciphertext features of Wind-Solar Power Station 3;

[0102] S4. The summation module in Client 1 sums up the ciphertext features of Wind-Solar Power Station 1 to generate the ciphertext summation features of Wind-Solar Power Station 1. Moreover, the summation module in Client 2 sums up the ciphertext features of Wind-Solar Power Station 2 and the ciphertext features of Wind-Solar Power Station 1 to generate the ciphertext summation features of Wind-Solar Power Station 1 and Wind-Solar Power Station 2. Moreover, the summation module in Client 3 sums up the ciphertext features of Wind-Solar Power Station 3, the ciphertext features of Wind-Solar Power Station 2, and the ciphertext features of Wind-Solar Power Station 1 to generate the ciphertext summation features of Wind-Solar Power Station 1, Wind-Solar Power Station 2, and Wind-Solar Power Station 3;

[0103] S5. Wind-Solar Power Station 3 sends the obtained ciphertext summation features to the third-party server;

[0104] S6. The third-party server decrypts the received ciphertext summation features to generate decrypted summation features, and uses the preset fusion model to perform fusion processing on the decrypted summation features to generate the decrypted fusion features of the area to be predicted;

[0105] S7. The third-party server sends the decrypted fusion features to Client 1, Client 2, and Client 3 respectively;

[0106] S8. The preset decoder in Client 1 performs power generation prediction based on the decrypted fusion feature and the wind-solar characteristics of Wind-Solar Power Station 1 to obtain the power generation of Wind-Solar Power Station 1. Moreover, the preset decoder in Client 2 performs power generation prediction based on the decrypted fusion feature and the wind-solar characteristics of Wind-Solar Power Station 2 to obtain the power generation of Wind-Solar Power Station 2. Moreover, the preset decoder in Client 3 performs power generation prediction based on the decrypted fusion feature and the wind-solar characteristics of Wind-Solar Power Station 3 to obtain the power generation of Wind-Solar Power Station 3. Among them, the power generations of Wind-Solar Power Station 1, Wind-Solar Power Station 2, and Wind-Solar Power Station 3 are used to be added up to obtain the regional power generation of the area to be predicted.

[0107] The embodiment of the present disclosure also provides a regional power generation prediction device for implementing the above regional power generation prediction method. The following will be described in conjunction with Figure 5 In the embodiment of the present disclosure, the regional power generation prediction device can be configured in the client corresponding to the target wind-solar power station in the area to be predicted. Among them, the client can be understood as the client local to the wind-solar power station.

[0108] Figure 5 The structural schematic diagram of a regional power generation prediction device provided by the embodiment of the present disclosure is shown.

[0109] As Figure 5 shown, the regional power generation prediction device 500 may include:

[0110] The first acquisition module 510 is configured to extract features from the wind-solar data of the target wind-solar power station to obtain wind-solar characteristics, where the target wind-solar power station is a power generation station in the area to be predicted, and the area to be predicted further includes at least one associated wind-solar power station related to the output of the target wind-solar power station;

[0111] The first generation module 520 is configured to perform encryption processing on the wind-solar characteristics to generate the ciphertext feature of the target wind-solar power station;

[0112] The second generation module 530 is configured to generate the ciphertext summation feature of the target wind-solar power station and the associated wind-solar power station based on the ciphertext feature of the target wind-solar power station and the ciphertext features of the associated wind-solar power stations, and send the ciphertext summation feature to the server corresponding to the area to be predicted, where the server is configured to generate the decrypted fusion feature corresponding to the ciphertext summation feature;

[0113] A second acquisition module 540, configured to perform power generation prediction based on the decrypted fusion feature returned by the server and the wind-solar feature of the target wind-solar power station, and determine the predicted power corresponding to the target wind-solar power station, where the predicted power corresponding to the target wind-solar power station and the predicted power corresponding to the associated wind-solar power station are used to add up to obtain the regional power generation power of the area to be predicted.

[0114] A regional power generation prediction device according to an embodiment of the present disclosure, the device includes: extracting features from the wind-solar data of a target wind-solar power station to obtain a wind-solar feature, where the target wind-solar power station is a power station in the area to be predicted, and the area to be predicted further includes at least one associated wind-solar power station related to the output of the target wind-solar power station; encrypting the wind-solar feature to generate a ciphertext feature of the target wind-solar power station; generating a ciphertext summation feature of the target wind-solar power station and the associated wind-solar power station based on the ciphertext feature of the target wind-solar power station and the ciphertext feature of the associated wind-solar power station, and sending the ciphertext summation feature to a server corresponding to the area to be predicted, where the server is configured to generate a decrypted fusion feature corresponding to the ciphertext summation feature; performing power generation prediction based on the decrypted fusion feature returned by the server and the wind-solar feature of the target wind-solar power station, and determining the predicted power corresponding to the target wind-solar power station, where the predicted power corresponding to the target wind-solar power station and the predicted power corresponding to the associated wind-solar power station are used to add up to obtain the regional power generation power of the area to be predicted. Thereby, it is possible to generate a ciphertext feature corresponding to the original wind-solar data at the client of the wind-solar power station, and fuse the ciphertext features of multiple wind-solar power stations for regional power generation prediction, avoiding the problem of data islands. Moreover, the original wind-solar data of the wind-solar power station can only be obtained by the local client and encrypted into ciphertext features, and the server only obtains the ciphertext summation feature and cannot know the original wind-solar data of the wind-solar power station, so that the problem of wind-solar data leakage will not occur in the third-party server, improving the security of the original wind-solar data of the wind-solar power station.

[0115] In some embodiments of the present disclosure, the first acquisition module 510 is specifically configured to perform encoding processing on the wind-solar data by using a preset encoder to obtain an encoding feature, and use the encoding feature as the wind-solar feature of the target wind-solar power station.

[0116] In some embodiments of the present disclosure, the first generation module 520 is specifically configured to encrypt the plaintext information included in the wind-solar feature by using an encryption random number to obtain the ciphertext feature of the target wind-solar power station.

[0117] In some embodiments of the present disclosure, the second generation module 530 is specifically configured to perform a homomorphic addition calculation on the ciphertext feature of the target wind-solar power station and the ciphertext feature of the associated wind-solar power station to obtain the ciphertext summation feature.

[0118] In some embodiments of the present disclosure, the second acquisition module 540 is specifically configured to use a preset decoder to perform decoding processing on the decrypted fusion feature and the wind-solar feature corresponding to the target wind-solar power station, obtain decoded data, and use the decoded data as the predicted power corresponding to the target wind-solar power station.

[0119] It should be noted that Figure 5 the regional power generation prediction device 500 shown can execute Figure 2 each step in the method embodiment shown, and implement Figure 2 each process and effect in the method embodiment shown, which will not be elaborated here.

[0120] The embodiments of the present disclosure also provide a regional power generation prediction device for implementing the above-mentioned regional power generation prediction method. The following will be described in conjunction with Figure 6 In the embodiments of the present disclosure, the regional power generation prediction device can be configured in a third-party server corresponding to the area to be predicted.

[0121] Figure 6 Fig. shows a schematic structural diagram of another regional power generation prediction device provided by the embodiments of the present disclosure.

[0122] As Figure 6 shown, the regional power generation prediction device 600 may include:

[0123] A third acquisition module 610, configured to acquire the ciphertext sum feature of the target wind-solar power station and the associated wind-solar power stations, where the target wind-solar power station and the associated wind-solar power stations are all power generation stations in the area to be predicted, the ciphertext sum feature is generated based on the ciphertext feature of the target wind-solar power station and the ciphertext feature of the associated wind-solar power stations, and the ciphertext feature of each wind-solar power station is generated based on its corresponding wind-solar feature, and the wind-solar feature of each wind-solar power station is obtained by performing feature extraction on its corresponding wind-solar data;

[0124] A third generation module 620, configured to generate the decrypted sum feature corresponding to the ciphertext sum feature, and perform fusion processing on the decrypted sum feature to generate the decrypted fusion feature of the area to be predicted;

[0125] A sending module 630, configured to send the decrypted fusion feature to the client corresponding to the target wind-solar power station, where the client corresponding to the target wind-solar power station is configured to perform power generation prediction based on the decrypted fusion feature and the wind-solar feature corresponding to the target wind-solar power station, determine the predicted power corresponding to the target wind-solar power station, and the predicted power corresponding to the target wind-solar power station and the predicted power corresponding to the associated wind-solar power stations are used to add up to obtain the regional power generation power of the area to be predicted.

[0126] A regional power generation prediction device according to an embodiment of the present disclosure, the device method includes: obtaining the ciphertext summation features of a target wind-solar power station and associated wind-solar power stations, where the target wind-solar power station and the associated wind-solar power stations are all power generation stations within the area to be predicted, the ciphertext summation features are generated based on the ciphertext features of the target wind-solar power station and the ciphertext features of the associated wind-solar power stations, and moreover, the ciphertext features of each wind-solar power station are generated based on its corresponding wind-solar features, and the wind-solar features of each wind-solar power station are obtained by extracting features from its corresponding wind-solar data; generating a decrypted summation feature corresponding to the ciphertext summation feature, and performing a fusion process on the decrypted summation feature to generate a decrypted fusion feature of the area to be predicted; sending the decrypted fusion feature to a client local to the target wind-solar power station, where the client local to the target wind-solar power station is used to perform power generation prediction based on the decrypted fusion feature and the wind-solar features corresponding to the target wind-solar power station to determine the predicted power corresponding to the target wind-solar power station, and the predicted power corresponding to the target wind-solar power station and the predicted power corresponding to the associated wind-solar power stations are used to be added to obtain the regional power generation power of the area to be predicted. Thus, it is possible to generate the ciphertext features corresponding to the original wind-solar data at the client local to the wind-solar power station, fuse the ciphertext features of multiple wind-solar power stations, and fuse the decrypted summation features at the server of a third party to perform regional power generation prediction to avoid the problem of data islands. And, the original wind-solar data of the wind-solar power station can only be obtained by the local client and encrypted into ciphertext features, and the server only obtains the ciphertext summation features and cannot know the original wind-solar data of the wind-solar power station, so that the server of a third party will not have the problem of wind-solar data leakage, improving the security of the original wind-solar data of the wind-solar power station.

[0127] In some embodiments of the present disclosure, the third generation module 620 is specifically configured to decrypt the ciphertext summation feature into plaintext information by using a decryption random number to obtain a decrypted summation feature including the plaintext information.

[0128] In some embodiments of the present disclosure, the third generation module 620 is specifically configured to determine an average value of the decrypted summation feature based on the decrypted summation feature and the number of wind-solar power stations in the area to be predicted;

[0129] Use a preset fusion model to perform a fusion process on the average value of the decrypted summation feature to obtain the decrypted fusion feature.

[0130] It should be noted that, Figure 6 The shown regional power generation prediction device 600 can execute Figure 3 each step in the method embodiment shown, and implement Figure 3 each process and effect in the method embodiment shown, which will not be elaborated here.

[0131] Figure 7 The figure shows a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure.

[0132] As shown Figure 7 in the figure, the electronic device may include a processor 701 and a memory 702 storing computer program instructions.

[0133] Specifically, the processor 701 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0134] The memory 702 may include a mass storage for information or instructions. By way of example and not limitation, the memory 702 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. In a suitable case, the memory 702 may include a removable or non-removable (or fixed) medium. In a suitable case, the memory 702 may be internal or external to the integrated gateway device. In a specific embodiment, the memory 702 is a non-volatile solid state memory. In a specific embodiment, the memory 702 includes a read-only memory (ROM). In a suitable case, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM), or a flash memory, or a combination of two or more of these.

[0135] The processor 701 reads and executes the computer program instructions stored in the memory 702 to perform the steps of the regional power generation prediction method provided by the embodiments of the present disclosure.

[0136] In one example, the electronic device may further include a transceiver 703 and a bus 704. Among them, as Figure 7 shown in the figure, the processor 701, the memory 702, and the transceiver 703 are connected through the bus 704 to complete communication with each other.

[0137] The bus 704 includes hardware, software, or both. By way of example and not limitation, the bus can include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side BUS (FSB), a Hyper Transport (HT) interconnect, an Industrial Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, the bus 704 can include one or more buses. Although the embodiments of the present application describe and illustrate specific buses, the present application contemplates any suitable bus or interconnect.

[0138] The following are embodiments of a computer-readable storage medium provided by the embodiments of the present disclosure. The computer-readable storage medium and the regional power generation prediction method of the above embodiments belong to the same inventive concept. Details not described in detail in the embodiments of the computer-readable storage medium can be referred to the embodiments of the regional power generation prediction method.

[0139] This embodiment provides a storage medium containing computer-executable instructions that are used to execute a regional power generation prediction method when executed by a computer processor.

[0140] Of course, the computer-executable instructions of a storage medium provided by the embodiments of the present disclosure are not limited to the above method operations, and can also execute related operations in the regional power generation prediction method provided by any embodiment of the present disclosure.

[0141] Through the above description of the embodiments, those skilled in the art can clearly understand that the present disclosure can be implemented by means of software and the necessary general hardware. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present disclosure, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as a floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disc of a computer, etc., including several instructions to enable a computer cloud platform (which can be a personal computer, a server, or a network cloud platform, etc.) to execute the regional power generation power prediction method provided by each embodiment of the present disclosure.

[0142] Note that the above is only the preferred embodiment of the present disclosure and the applied technical principle. Those skilled in the art will understand that the present disclosure is not limited to the specific embodiments here. Various obvious changes, re-adjustments and substitutions can be made by those skilled in the art without departing from the protection scope of the present disclosure. Therefore, although the present disclosure has been described in more detail through the above embodiments, the present disclosure is not limited to the above embodiments. Without departing from the concept of the present disclosure, more other equivalent embodiments can be included, and the scope of the present disclosure is determined by the scope of the appended claims.

Claims

1. A method for predicting regional power generation, characterized in that, Including: Performing feature extraction on the wind-solar data of the target wind-solar power station to obtain wind-solar features, where the target wind-solar power station is a power station within the area to be predicted, and the area to be predicted further includes at least one associated wind-solar power station related to the output of the target wind-solar power station; Performing encryption processing on the wind-solar features to generate ciphertext features of the target wind-solar power station; Based on the ciphertext features of the target wind-solar power station and the ciphertext features of the associated wind-solar power stations, generating ciphertext summation features of the target wind-solar power station and the associated wind-solar power stations, and sending the ciphertext summation features to the server corresponding to the area to be predicted, where the server is used to generate a decrypted fusion feature corresponding to the ciphertext summation feature; the ciphertext summation feature refers to a weighted value of the ciphertext features of the target wind-solar power station and the associated wind-solar power stations, and the ciphertext summation feature can characterize the output-related relationship between wind-solar power stations; the decrypted fusion feature characterizes the overall wind-solar features of multiple wind-solar power stations; Performing power generation power prediction based on the decrypted fusion feature returned by the server and the wind-solar features of the target wind-solar power station, and determining the predicted power corresponding to the target wind-solar power station, where the predicted power corresponding to the target wind-solar power station and the predicted power corresponding to the associated wind-solar power stations are used to add up to obtain the regional power generation power of the area to be predicted.

2. The method according to claim 1, wherein The performing feature extraction on the wind-solar data of the target wind-solar power station to obtain wind-solar features includes: Using a preset encoder to perform encoding processing on the wind-solar data to obtain encoded features, and taking the encoded features as the wind-solar features of the target wind-solar power station.

3. The method according to claim 1, wherein The performing encryption processing on the wind-solar features to generate ciphertext features of the target wind-solar power station includes: Using an encrypted random number to perform encryption processing on the plaintext information included in the wind-solar features to obtain the ciphertext features of the target wind-solar power station.

4. The method according to claim 1, characterized in that, The generating ciphertext summation features of the target wind-solar power station and the associated wind-solar power stations based on the ciphertext features of the target wind-solar power station and the ciphertext features of the associated wind-solar power stations includes: Performing homomorphic addition calculation on the ciphertext features of the target wind-solar power station and the ciphertext features of the associated wind-solar power stations to obtain the ciphertext summation feature.

5. The method according to claim 1, wherein The performing power generation power prediction based on the decrypted fusion feature returned by the server and the wind-solar features of the target wind-solar power station, and determining the predicted power corresponding to the target wind-solar power station includes: Using a preset decoder to perform decoding processing on the decrypted fusion feature and the wind-solar features corresponding to the target wind-solar power station to obtain decoded data, and taking the decoded data as the predicted power corresponding to the target wind-solar power station.

6. A method for predicting regional power generation capacity, characterized in that, Including: Obtain the ciphertext summation feature of the target wind-solar power station and associated wind-solar power stations, where the target wind-solar power station and the associated wind-solar power stations are all power stations within the area to be predicted. The ciphertext summation feature is generated based on the ciphertext features of the target wind-solar power station and the associated wind-solar power stations. Moreover, the ciphertext feature of each wind-solar power station is generated based on its corresponding wind-solar feature, and the wind-solar feature of each wind-solar power station is obtained by extracting features from its corresponding wind-solar data; the ciphertext summation feature refers to the weighted value of the ciphertext features of the target wind-solar power station and the associated wind-solar power stations, and the ciphertext summation feature can characterize the output correlation relationship between wind-solar power stations. Generate the decryption summation feature corresponding to the ciphertext summation feature, and perform a fusion process on the decryption summation feature to generate the decryption fusion feature of the area to be predicted; the decryption fusion feature characterizes the overall wind-solar features of multiple wind-solar power stations. Send the decryption fusion feature to the client local to the target wind-solar power station. The client local to the target wind-solar power station is used to predict the power generation based on the decryption fusion feature and the wind-solar feature corresponding to the target wind-solar power station, determine the predicted power corresponding to the target wind-solar power station, and the predicted power corresponding to the target wind-solar power station and the predicted power corresponding to the associated wind-solar power stations are used to add up to obtain the regional power generation of the area to be predicted.

7. The method according to claim 6, wherein The generating the decryption summation feature corresponding to the ciphertext summation feature includes: Use the decryption random number to decrypt the ciphertext summation feature into plaintext information to obtain the decryption summation feature containing the plaintext information.

8. The method according to claim 6, wherein The performing a fusion process on the decryption summation feature to generate the decryption fusion feature of the area to be predicted includes: Based on the decryption summation feature and the number of wind-solar power stations in the area to be predicted, determine the average value of the decryption summation feature. Use a preset fusion model to perform a fusion process on the average value of the decryption summation feature to obtain the decryption fusion feature.

9. A regional power generation power prediction device, characterized in that, Includes: The first obtaining module is used to extract features from the wind-solar data of the target wind-solar power station to obtain wind-solar features, where the target wind-solar power station is a power station within the area to be predicted, and the area to be predicted further includes at least one associated wind-solar power station whose output is related to that of the target wind-solar power station. The first generating module is used to encrypt the wind-solar features to generate the ciphertext features of the target wind-solar power station. The second generating module is used to generate the ciphertext summation feature of the target wind-solar power station and the associated wind-solar power stations based on the ciphertext features of the target wind-solar power station and the ciphertext features of the associated wind-solar power stations, and send the ciphertext summation feature to the server corresponding to the area to be predicted, where the server is used to generate the decryption fusion feature corresponding to the ciphertext summation feature; the ciphertext summation feature refers to the weighted value of the ciphertext features of the target wind-solar power station and the associated wind-solar power stations, and the ciphertext summation feature can characterize the output correlation relationship between wind-solar power stations; the decryption fusion feature characterizes the overall wind-solar features of multiple wind-solar power stations. A second acquisition module, configured to perform power generation prediction based on the decrypted fusion feature returned by the server and the wind-solar feature of the target wind-solar power station, and determine the predicted power corresponding to the target wind-solar power station, wherein the predicted power corresponding to the target wind-solar power station and the predicted power corresponding to the associated wind-solar power station are used to add up to obtain the regional power generation of the area to be predicted.

10. A regional power generation power prediction device, characterized in that Comprising: A third acquisition module, configured to acquire the ciphertext summation feature of the target wind-solar power station and the associated wind-solar power station, wherein both the target wind-solar power station and the associated wind-solar power station are power stations within the area to be predicted, the ciphertext summation feature is generated based on the ciphertext feature of the target wind-solar power station and the ciphertext feature of the associated wind-solar power station, and the ciphertext feature of each wind-solar power station is generated based on its corresponding wind-solar feature, and the wind-solar feature of each wind-solar power station is obtained by performing feature extraction on its corresponding wind-solar data; the ciphertext summation feature refers to the weighted value of the ciphertext features of the target wind-solar power station and the associated wind-solar power station, and the ciphertext summation feature can characterize the output correlation relationship between wind-solar power stations; A third generation module, configured to generate the decrypted summation feature corresponding to the ciphertext summation feature, and perform fusion processing on the decrypted summation feature to generate the decrypted fusion feature of the area to be predicted; the decrypted fusion feature characterizes the overall wind-solar feature of multiple wind-solar power stations; A sending module, configured to send the decrypted fusion feature to the client corresponding to the target wind-solar power station, wherein the client corresponding to the target wind-solar power station is configured to perform power generation prediction based on the decrypted fusion feature and the wind-solar feature corresponding to the target wind-solar power station, and determine the predicted power corresponding to the target wind-solar power station, and the predicted power corresponding to the target wind-solar power station and the predicted power corresponding to the associated wind-solar power station are used to add up to obtain the regional power generation of the area to be predicted.

11. An electronic device, characterized in that, Comprising: A processor; A memory, configured to store executable instructions; Wherein, the processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the method described in any one of claims 1-5 above or implement the method described in any one of claims 6-8 above.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, The storage medium stores a computer program, and when the computer program is executed by the processor, the processor is caused to implement the method described in any one of claims 1-5 above or implement the method described in any one of claims 6-8 above.

Images