Regional energy-carbon emission prediction, planning and optimization method and system

Abstract

The invention discloses a regional energy-carbon emission prediction, planning and optimization method and system, and relates to the technical field of carbon emission monitoring analysis, and the method comprises the steps: obtaining historical weather data in a region where a target park is located, obtaining electric power data corresponding to each user in the target park, performing feature extraction on the historical weather data in the region of the target park to obtain weather influence features; performing feature extraction on the power data corresponding to each user in the target park to obtain electrical influence features; and inputting the weather influence characteristics and the electrical influence characteristics into a pre-trained regional carbon emission prediction network, determining carbon emission prediction data of the target park in a preset monitoring time period, and optimizing power data of the target park based on the carbon emission prediction data. The method has the effect of improving the accuracy of the carbon emission prediction data.

Description

Technical Field

[0001] The present application relates to the technical field of carbon emission monitoring and analysis, and in particular to a method and system for regional energy-carbon emission forecasting, planning and optimization. Background Art

[0002] Carbon emissions refer to the greenhouse gas emissions generated during the production, transportation, use and recycling of a product. Dynamic carbon emissions refer to the cumulative greenhouse gas emissions per unit of goods. Different batches of the same product will have different dynamic carbon emissions.

[0003] In the relevant technologies, carbon emissions generated by electricity consumption in the park account for a large proportion of carbon emissions. Accurately predicting carbon emissions from electricity consumption in the park can provide important data basis for better planning and optimization of carbon emissions. In some scenarios, it is necessary to rely on carbon emission records of historical electricity consumption data when predicting carbon emissions from electricity consumption in the park. However, in some scenarios, it may not be possible to obtain carbon emission records of historical electricity consumption data in the park, which leads to inaccurate prediction results and cannot provide effective data support for carbon emission planning and optimization. There is room for improvement. Summary of the invention

[0004] In view of the deficiencies of the prior art, the present application provides a method and system for regional energy-carbon emission prediction, planning and optimization.

[0005] In a first aspect, the present application provides a regional energy-carbon emission prediction, planning and optimization method, comprising the following steps:

[0006] Acquire historical weather data in the area where the target park is located, wherein the historical weather data includes meteorological data in a historical continuous time period, and the meteorological data includes one or more of temperature, humidity, wind speed, and sunshine intensity;

[0007] Obtaining power data corresponding to each user in the target park, wherein the power data includes power user type, power consumption data corresponding to each power user type, and power production capacity data;

[0008] Extracting features from historical weather data in the area where the target park is located to obtain weather impact features;

[0009] Extracting features of power data corresponding to each user in the target park to obtain electrical impact features;

[0010] The weather impact characteristics and the electrical impact characteristics are input into a pre-trained regional carbon emission prediction network to confirm the carbon emission prediction data of the target park within a preset monitoring time period, and the electricity data of the target park is optimized based on the carbon emission prediction data.

[0011] Preferably, the types of electricity users include residential users, commercial users and industrial users;

[0012] The electricity consumption data corresponding to each type of electricity user includes daily electricity consumption duration and average unit electricity consumption;

[0013] The capacity data is set as the capacity data corresponding to the manufacturing type industry among industrial users, and the capacity data includes daily working hours and average unit production volume.

[0014] Preferably, the production capacity data corresponding to the manufacturing industry among the industrial users specifically includes:

[0015] Obtaining the corresponding industrial users in the target park, extracting manufacturing type industrial users from the corresponding industrial users in the target park, and setting a corresponding number for each manufacturing type industrial user;

[0016] Obtain the historical capacity sequence corresponding to each manufacturing type industry user, and extract the capacity data of each manufacturing type industry user on each day under the same weather from the historical capacity sequence, and mark the capacity data of each manufacturing type industry user on each day under the same weather as CNin, where i represents the number corresponding to each manufacturing type industry user, i=1,2,3...j, and n represents the number corresponding to the number of days with the same weather, n=1,2,3...m;

[0017] Based on the historical capacity sequence, the daily working hours SJin of users in each manufacturing industry under the same weather conditions are obtained, and then the calculation formula is used to calculate The analysis yields the average unit production volume SCin corresponding to users in each manufacturing type industry.

[0018] Preferably, extracting features from historical weather data in the area where the target park is located to obtain weather impact features specifically includes:

[0019] Confirm the historical weather data in the area where the target park is located, and classify the historical weather data to confirm the historical weather data corresponding to each type of weather, input the historical weather data corresponding to each type of weather into the weather feature extraction network for processing, and then confirm the weather impact characteristics corresponding to each type of weather;

[0020] Feature extraction is performed on the power data corresponding to each user in the target park to obtain electrical impact features, specifically including:

[0021] Confirm the power data corresponding to each user in the target park, classify and divide the power data, and then confirm the power consumption data corresponding to each type of power user and the production capacity data corresponding to the manufacturing type industrial users, and input the power consumption data corresponding to each type of power user and the production capacity data corresponding to the manufacturing type industrial users into the power feature extraction network for processing, and then confirm the electrical impact characteristics.

[0022] Preferably, the weather impact characteristics and the electrical impact characteristics are input into a pre-trained regional carbon emission prediction network to confirm the carbon emission prediction data of the target park within a preset monitoring time period, specifically including:

[0023] Fusing the weather impact features corresponding to each type of weather and the electrical impact features to determine a fusion vector;

[0024] The fusion vector is input into a pre-trained regional carbon emission prediction network to confirm the carbon emission prediction data of the target park within a preset monitoring time period.

[0025] Preferably, it also includes:

[0026] By calculating the formula Calculate the corresponding electricity carbon emissions Cyd in the target park, where a1, a2, and a3 represent the numbers of each residential user, each commercial user, and each industrial user in the target park, respectively; Qa1, Qa2, and Qa3 represent the average unit electricity consumption of each residential user, each commercial user, and each industrial user in the target park, respectively; Ta1, Ta2, and Ta3 represent the daily electricity consumption time of each residential user, each commercial user, and each industrial user in the target park, respectively; ω1, ω2, and ω3 represent the average emission factors of the regional power grid corresponding to each residential user, each commercial user, and each industrial user in the target park, respectively;

[0027] The corresponding production capacity carbon emissions Csc in the target park are calculated by the calculation formula Csc=ln[1+(SCin*Tin*ω4)], where Tin represents the daily working hours of each manufacturing type industrial user under the same weather conditions, and ω4 represents the average emission factor of the regional power grid corresponding to the manufacturing type industrial users in the target park;

[0028] The corresponding electricity carbon emissions in the target park are summed with the corresponding production capacity carbon emissions in the target park, and then the actual total carbon emissions in the target park are confirmed, and the actual total carbon emissions in the target park are compared with the carbon emission forecast data of the target park within the preset monitoring time period, and then the regional carbon emission prediction network is further optimized.

[0029] Preferably, optimizing the power data of the target park based on the carbon emission prediction data specifically includes:

[0030] The predicted carbon emission prediction data will be compared with the corresponding planned carbon emission data in the target park. If the carbon emission prediction data does not exceed the corresponding planned carbon emission data in the target park, there is no need to optimize the carbon emission of the target park. If the carbon emission prediction data exceeds the corresponding planned carbon emission data in the target park, the carbon emission prediction data corresponding to each power user type will be further confirmed, and the carbon emission prediction data corresponding to each power user type will be compared with the planned carbon emission data corresponding to each power user type to further confirm the abnormal power user type and optimize it based on the power consumption data or production capacity data corresponding to the abnormal power user type.

[0031] In a second aspect, the present application provides a regional energy-carbon emission forecasting, planning and optimization system, comprising:

[0032] A weather information acquisition module is used to acquire historical weather data in the area where the target park is located, wherein the historical weather data includes meteorological data in a historical continuous time period, and the meteorological data includes one or more of temperature, humidity, wind speed, and sunshine intensity;

[0033] A power data acquisition module is used to acquire power data corresponding to each user in the target park, wherein the power data includes power user type, power consumption data corresponding to each power user type, and power production capacity data;

[0034] A weather feature extraction module is used to extract features from historical weather data in the area where the target park is located to obtain weather impact features;

[0035] An electrical feature extraction module, used to extract features from the power data corresponding to each user in the target park to obtain electrical impact features;

[0036] A prediction optimization module is used to input the weather impact characteristics and the electrical impact characteristics into a pre-trained regional carbon emission prediction network, confirm the carbon emission prediction data of the target park within a preset monitoring time period, and optimize the electricity data of the target park based on the carbon emission prediction data.

[0037] In a third aspect, the present application provides a computer-readable storage medium storing instructions, which, when executed on a computer, enables the computer to execute any one of the above-described methods for regional energy-carbon emission forecasting, planning and optimization.

[0038] In summary, the present application includes at least one of the following beneficial technical effects:

[0039] 1. The present invention provides a regional energy-carbon emission prediction, planning and optimization method, which obtains and analyzes historical weather data and electricity data in a target park, extracts weather impact characteristics and electrical impact characteristics, inputs the weather impact characteristics and electrical impact characteristics into a pre-trained regional carbon emission prediction network, thereby confirming the carbon emission prediction data of the target park within a preset monitoring time period, and then optimizes the electricity data of the target park based on the carbon emission prediction data, thereby effectively improving the accuracy of the carbon emission prediction data, thereby further effectively providing effective data support for the planning and optimization of carbon emissions;

[0040] 2. By comparing the actual total carbon emissions in the target park with the carbon emission forecast data of the target park within the preset monitoring period, the regional carbon emission forecast network is further optimized, thereby effectively improving the accuracy of the carbon emission forecast data. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a flow chart of the method for regional energy-carbon emission prediction, planning and optimization in an embodiment of the present application.

[0042] Figure 2 It is a system diagram of regional energy-carbon emission prediction, planning and optimization in an embodiment of the present application. DETAILED DESCRIPTION

[0043] The following is combined with Figure 1-2 This application is described in further detail.

[0044] Example 1

[0045] The embodiment of the present application discloses a regional energy-carbon emission prediction, planning and optimization method.

[0046] Reference Figure 1 , a regional energy-carbon emission prediction, planning and optimization method, comprising the following steps:

[0047] S1. Obtain historical weather data in the area where the target park is located, wherein the historical weather data includes meteorological data within a continuous historical time period, and the meteorological data includes one or more of temperature, humidity, wind speed, and sunshine intensity;

[0048] S2. Obtaining power data corresponding to each user in the target park, the power data including power user type, power consumption data and capacity data corresponding to each power user type;

[0049] S3. Extract features from historical weather data in the target park area to obtain weather impact features;

[0050] S4. Extracting features from the power data corresponding to each user in the target park to obtain electrical impact features;

[0051] S5. Input the weather impact characteristics and the electrical impact characteristics into a pre-trained regional carbon emission prediction network, confirm the carbon emission prediction data of the target park within a preset monitoring time period, and optimize the electricity data of the target park based on the carbon emission prediction data.

[0052] Specifically, while ensuring that the electricity consumption of the target park is constant, the outdoor weather conditions have a certain impact on the electricity consumption of the target park. Therefore, in this embodiment, historical weather data is introduced into the prediction process of the carbon emissions of the target park, thereby introducing the impact of weather changes on the carbon emissions of the target park.

[0053] Furthermore, the types of electricity users include residential users, commercial users and industrial users;

[0054] The electricity consumption data corresponding to each type of electricity user includes daily electricity consumption duration and average unit electricity consumption;

[0055] The capacity data is set as the capacity data corresponding to the manufacturing type industry among industrial users, and the capacity data includes daily working hours and average unit production volume.

[0056] It should be noted that the capacity data corresponding to the manufacturing industry among industrial users include:

[0057] Obtaining the corresponding industrial users in the target park, extracting manufacturing type industrial users from the corresponding industrial users in the target park, and setting a corresponding number for each manufacturing type industrial user;

[0058] Obtain the historical capacity sequence corresponding to each manufacturing type industry user, and extract the capacity data of each manufacturing type industry user on each day under the same weather from the historical capacity sequence, and mark the capacity data of each manufacturing type industry user on each day under the same weather as CNin, where i represents the number corresponding to each manufacturing type industry user, i=1,2,3...j, and n represents the number corresponding to the number of days with the same weather, n=1,2,3...m;

[0059] Based on the historical capacity sequence, the daily working hours SJin of users in each manufacturing industry under the same weather conditions are obtained, and then the calculation formula is used to calculate The analysis yields the average unit production volume SCin corresponding to users in each manufacturing type industry.

[0060] Specifically, in the embodiment of the present application, the same type of weather can be set according to different angles. For example, from the meteorological aspect, it can be divided into sunny days, rainy days and snowy days, and from the temperature aspect, each temperature interval can be divided.

[0061] It should be noted that the feature extraction of the historical weather data in the area where the target park is located to obtain the weather impact features specifically includes:

[0062] Confirm the historical weather data in the area where the target park is located, and classify the historical weather data to confirm the historical weather data corresponding to each type of weather, input the historical weather data corresponding to each type of weather into the weather feature extraction network for processing, and then confirm the weather impact characteristics corresponding to each type of weather;

[0063] Specifically, in an embodiment of the present application, historical weather data corresponding to each type of weather can be input into a weather feature extraction network for processing, thereby confirming the weather impact characteristics corresponding to each type of weather. Optionally, the weather feature extraction network can be a neural network model for extracting data features based on time series.

[0064] Feature extraction is performed on the power data corresponding to each user in the target park to obtain electrical impact features, specifically including:

[0065] Confirm the power data corresponding to each user in the target park, classify and divide the power data, and then confirm the power consumption data corresponding to each type of power user and the production capacity data corresponding to the manufacturing type industrial users, and input the power consumption data corresponding to each type of power user and the production capacity data corresponding to the manufacturing type industrial users into the power feature extraction network for processing, and then confirm the electrical impact characteristics.

[0066] Specifically, in the embodiment of the present application, the electricity consumption data corresponding to each type of electricity user and the production capacity data corresponding to the manufacturing type industrial users are input into the electricity feature extraction network for processing to confirm the electrical impact characteristics. Optionally, the electricity feature extraction network is a neural network model that can feature-associate electricity consumption data and production capacity data with weather data.

[0067] Furthermore, the weather impact characteristics and the electrical impact characteristics are input into a pre-trained regional carbon emission prediction network to confirm the carbon emission prediction data of the target park within a preset monitoring time period, specifically including:

[0068] Fusing the weather impact features corresponding to each type of weather and the electrical impact features to determine a fusion vector;

[0069] The fusion vector is input into a pre-trained regional carbon emission prediction network to confirm the carbon emission prediction data of the target park within a preset monitoring time period.

[0070] Specifically, the regional carbon emission prediction network includes a first prediction module, a second prediction module and a third prediction module, wherein the first prediction module is set to the carbon emission prediction data corresponding to residential users, the second prediction module is set to the carbon emission prediction data corresponding to commercial users, and the third prediction module is set to the carbon emission prediction data corresponding to industrial users.

[0071] Furthermore, it also includes:

[0072] By calculating the formula Calculate the corresponding electricity carbon emissions Cyd in the target park, where a1, a2, and a3 represent the numbers of each residential user, each commercial user, and each industrial user in the target park, respectively; Qa1, Qa2, and Qa3 represent the average unit electricity consumption of each residential user, each commercial user, and each industrial user in the target park, respectively; Ta1, Ta2, and Ta3 represent the daily electricity consumption time of each residential user, each commercial user, and each industrial user in the target park, respectively; ω1, ω2, and ω3 represent the average emission factors of the regional power grid corresponding to each residential user, each commercial user, and each industrial user in the target park, respectively;

[0073] The corresponding production capacity carbon emissions Csc in the target park are calculated by the calculation formula Csc=ln[1+(SCin*Tin*ω4)], where Tin represents the daily working hours of each manufacturing type industrial user under the same weather conditions, and ω4 represents the average emission factor of the regional power grid corresponding to the manufacturing type industrial users in the target park;

[0074] The corresponding electricity carbon emissions in the target park are summed with the corresponding production capacity carbon emissions in the target park, and then the actual total carbon emissions in the target park are confirmed, and the actual total carbon emissions in the target park are compared with the carbon emission forecast data of the target park within the preset monitoring time period, and then the regional carbon emission prediction network is further optimized.

[0075] Specifically, in the embodiment of the present application, the average emission factors of the regional power grids corresponding to each type of electricity user are different, among which the average emission factors of the regional power grids corresponding to residential users, commercial users and industrial users increase step by step, and by comparing the corresponding actual total carbon emissions in the target park with the carbon emission forecast data of the target park within a preset monitoring time period, the regional carbon emission forecast network is further optimized, thereby effectively improving the accuracy of the carbon emission forecast data.

[0076] It should be noted that optimizing the power data of the target park based on the carbon emission prediction data specifically includes:

[0077] The predicted carbon emission prediction data will be compared with the corresponding planned carbon emission data in the target park. If the carbon emission prediction data does not exceed the corresponding planned carbon emission data in the target park, there is no need to optimize the carbon emission of the target park. If the carbon emission prediction data exceeds the corresponding planned carbon emission data in the target park, the carbon emission prediction data corresponding to each power user type will be further confirmed, and the carbon emission prediction data corresponding to each power user type will be compared with the planned carbon emission data corresponding to each power user type to further confirm the abnormal power user type and optimize it based on the power consumption data or production capacity data corresponding to the abnormal power user type.

[0078] Exemplarily, when the predicted carbon emission data does not exceed the corresponding planned carbon emission data in the target park, there is no need to optimize the carbon emission of the target park. When the predicted carbon emission data corresponding to the residential user exceeds the planned carbon emission data corresponding to the residential user, the residential user is set as an abnormal electricity user type, and the corresponding electricity consumption data of the residential user is planned and optimized.

[0079] Example 2

[0080] The embodiments of the present application also disclose a regional energy-carbon emission prediction, planning and optimization system.

[0081] Reference Figure 2 , a regional energy-carbon emission forecasting, planning and optimization system, including:

[0082] A weather information acquisition module is used to acquire historical weather data in the area where the target park is located, wherein the historical weather data includes meteorological data in a historical continuous time period, and the meteorological data includes one or more of temperature, humidity, wind speed, and sunshine intensity;

[0083] A power data acquisition module is used to acquire power data corresponding to each user in the target park, wherein the power data includes power user type, power consumption data corresponding to each power user type, and power production capacity data;

[0084] A weather feature extraction module is used to extract features from historical weather data in the area where the target park is located to obtain weather impact features;

[0085] An electrical feature extraction module, used to extract features from the power data corresponding to each user in the target park to obtain electrical impact features;

[0086] A prediction optimization module is used to input the weather impact characteristics and the electrical impact characteristics into a pre-trained regional carbon emission prediction network, confirm the carbon emission prediction data of the target park within a preset monitoring time period, and optimize the electricity data of the target park based on the carbon emission prediction data.

[0087] The above contents are merely examples and explanations of the concept of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

[0088] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0089] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A regional energy-carbon emissions forecasting, planning and optimization method, It is characterized in that The following steps are involved: Acquire historical weather data in the area where the target park is located, wherein the historical weather data includes meteorological data in a historical continuous time period, and the meteorological data includes one or more of temperature, humidity, wind speed, and sunshine intensity; Obtaining power data corresponding to each user in the target park, wherein the power data includes power user type, power consumption data corresponding to each power user type, and power production capacity data; Extracting features from historical weather data in the area where the target park is located to obtain weather impact features; Extracting features of power data corresponding to each user in the target park to obtain electrical impact features; The weather impact characteristics and the electrical impact characteristics are input into a pre-trained regional carbon emission prediction network to confirm the carbon emission prediction data of the target park within a preset monitoring time period, and the electricity data of the target park is optimized based on the carbon emission prediction data.

2. A regional energy-carbon emission prediction, planning and optimization method according to claim 1, Features: The types of electricity users include residential users, commercial users and industrial users; The electricity consumption data corresponding to each type of electricity user includes daily electricity consumption duration and average unit electricity consumption; The capacity data is set as the capacity data corresponding to the manufacturing type industry among industrial users, and the capacity data includes daily working hours and average unit production volume.

3. A regional energy-carbon emission prediction, planning and optimization method according to claim 2, Features: The production capacity data corresponding to the manufacturing industry among the industrial users specifically include: Obtaining the corresponding industrial users in the target park, extracting manufacturing type industrial users from the corresponding industrial users in the target park, and setting a corresponding number for each manufacturing type industrial user; Obtain the historical capacity sequence corresponding to each manufacturing type industry user, and extract the capacity data of each manufacturing type industry user on each day under the same weather from the historical capacity sequence, and mark the capacity data of each manufacturing type industry user on each day under the same weather as CNin, where i represents the number corresponding to each manufacturing type industry user, i=1,2,3...j, and n represents the number corresponding to the number of days with the same weather, n=1,2,3...m; Based on the historical capacity sequence, the daily working hours SJin of users in each manufacturing industry under the same weather conditions are obtained, and then the calculation formula is used to calculate The analysis yields the average unit production volume SCin corresponding to users in each manufacturing type industry.

4. A method for forecasting, planning and optimizing regional energy-carbon emissions according to claim 3, Features: The feature extraction of the historical weather data in the area where the target park is located to obtain the weather impact features specifically includes: Confirm the historical weather data in the area where the target park is located, and classify the historical weather data to confirm the historical weather data corresponding to each type of weather, input the historical weather data corresponding to each type of weather into the weather feature extraction network for processing, and then confirm the weather impact characteristics corresponding to each type of weather; Feature extraction is performed on the power data corresponding to each user in the target park to obtain electrical impact features, specifically including: Confirm the power data corresponding to each user in the target park, classify and divide the power data, and then confirm the power consumption data corresponding to each type of power user and the production capacity data corresponding to the manufacturing type industrial users, and input the power consumption data corresponding to each type of power user and the production capacity data corresponding to the manufacturing type industrial users into the power feature extraction network for processing, and then confirm the electrical impact characteristics.

5. A regional energy-carbon emission prediction, planning and optimization method according to claim 4, Features: Inputting the weather impact characteristics and the electrical impact characteristics into a pre-trained regional carbon emission prediction network to confirm the carbon emission prediction data of the target park within a preset monitoring time period, specifically including: Fusing the weather impact features corresponding to each type of weather and the electrical impact features to determine a fusion vector; The fusion vector is input into a pre-trained regional carbon emission prediction network to confirm the carbon emission prediction data of the target park within a preset monitoring time period.

6. A method for forecasting, planning and optimizing regional energy-carbon emissions according to claim 5, It is characterized in that Also includes: By calculating the formula The corresponding electricity carbon emissions Cyd in the target park are calculated, where a1, a2, and a3 represent the numbers of each residential user, each commercial user, and each industrial user in the target park, respectively, and Qa 1 , Qa 2 , Qa 3 They are respectively represented as the average unit power consumption of each residential user, each commercial user, and each industrial user in the target park, Ta 1 、 2 、 3 They are respectively represented by the daily electricity consumption duration of each residential user, each commercial user, and each industrial user in the target park; ω1, ω2, and ω3 are respectively represented by the average emission factors of the regional power grid corresponding to each residential user, each commercial user, and each industrial user in the target park; The corresponding production capacity carbon emissions Csc in the target park are calculated by the calculation formula Csc=ln[1+(SCin*Tin*ω4)], where Tin represents the daily working hours of each manufacturing type industrial user under the same weather conditions, and ω4 represents the average emission factor of the regional power grid corresponding to the manufacturing type industrial users in the target park; The corresponding electricity carbon emissions in the target park are summed with the corresponding production capacity carbon emissions in the target park, and then the actual total carbon emissions in the target park are confirmed, and the actual total carbon emissions in the target park are compared with the carbon emission forecast data of the target park within the preset monitoring time period, and then the regional carbon emission prediction network is further optimized.

7. A method for forecasting, planning and optimizing regional energy-carbon emissions according to claim 6, Features: Optimizing the power data of the target park based on the carbon emission prediction data specifically includes: The predicted carbon emission prediction data will be compared with the corresponding planned carbon emission data in the target park. If the carbon emission prediction data does not exceed the corresponding planned carbon emission data in the target park, there is no need to optimize the carbon emission of the target park. If the carbon emission prediction data exceeds the corresponding planned carbon emission data in the target park, the carbon emission prediction data corresponding to each power user type will be further confirmed, and the carbon emission prediction data corresponding to each power user type will be compared with the planned carbon emission data corresponding to each power user type to further confirm the abnormal power user type and optimize it based on the power consumption data or production capacity data corresponding to the abnormal power user type.

8. A regional energy-carbon emission forecasting, planning and optimization system, It is characterized in that include: A weather information acquisition module is used to acquire historical weather data in the area where the target park is located, wherein the historical weather data includes meteorological data in a historical continuous time period, and the meteorological data includes one or more of temperature, humidity, wind speed, and sunshine intensity; A power data acquisition module is used to acquire power data corresponding to each user in the target park, wherein the power data includes power user type, power consumption data corresponding to each power user type, and power production capacity data; A weather feature extraction module is used to extract features from historical weather data in the area where the target park is located to obtain weather impact features; An electrical feature extraction module, used to extract features from the power data corresponding to each user in the target park to obtain electrical impact features; A prediction optimization module is used to input the weather impact characteristics and the electrical impact characteristics into a pre-trained regional carbon emission prediction network, confirm the carbon emission prediction data of the target park within a preset monitoring time period, and optimize the electricity data of the target park based on the carbon emission prediction data.

9. A computer-readable storage medium, Features: Instructions are stored, and when the instructions are executed on a computer, the computer is caused to execute a regional energy-carbon emission prediction, planning and optimization method as described in any one of claims 1 to 7.

Images