Method and system for constructing user electricity utilization carbon emission portrait based on spatial and temporal distribution characteristics

Abstract

The invention is suitable for the technical field of carbon emission, and provides a method and a system for constructing a user power utilization carbon emission portrait based on spatial and temporal distribution characteristics, and the method comprises the steps: obtaining information data of a target user, historical power utilization data of the target user and power grid power generation structure data, and carrying out the preprocessing of the obtained data; extracting target feature data related to time and target feature data related to regional distribution based on the preprocessed data; according to the target feature data related to the time and the target feature data related to the regional distribution, analyzing the time change feature and the regional distribution change feature of the carbon emission factor of the target user; and according to the time change characteristic and the regional distribution change characteristic of the carbon emission factor of the target user, constructing a dynamic portrait of the power utilization carbon emission of the target user, so that the power utilization carbon emission condition of the user under different time and regional conditions can be accurately reflected, and accurate data can be provided for subsequent work.

Description

Technical Field

[0001] The present invention relates to the field of carbon emission technology, and in particular to a method and system for constructing a user electricity carbon emission portrait based on spatiotemporal distribution characteristics. Background Art

[0002] Currently, most power companies can understand the electricity consumption patterns and carbon emissions of different user groups through portraits, and thus optimize grid planning and power dispatching through accurate observation of portraits. For government departments, portraits can provide a strong basis for formulating energy and environmental policies, and scientific and reasonable energy-saving and emission reduction targets can be set accordingly, and differentiated supervision can be implemented for different types of users. From the user's perspective, carbon emission portraits can enable users to intuitively understand the impact of their own user behavior on the environment, enabling them to adjust their electricity usage habits or replace energy-saving equipment, etc., to achieve the goal of reducing electricity costs and carbon emissions.

[0003] In the existing technology, the rich information of the time dimension is ignored in the carbon emission portrait of user electricity consumption, and the changes in user electricity consumption behavior at different time scales are not considered, such as the significant difference in electricity consumption patterns on weekdays and holidays, the difference in peak and trough electricity consumption at different times of the day, and the impact of seasonal changes on electricity demand and carbon emissions. In addition, in the spatial dimension, factors such as the user's geographical location, the functional attributes of the area where they are located, the distribution of energy infrastructure in the area, and the spatial aggregation of users are not taken into consideration. This makes it impossible to depict the spatial characteristics of carbon emissions of users in different regions, and thus it is impossible to build a comprehensive and accurate user carbon emission portrait, resulting in the problem that the user's electricity carbon emission portrait is not accurate and lacks comprehensiveness.

[0004] In view of this, there is a need for a method and system for constructing a user electricity carbon emission portrait based on spatiotemporal distribution characteristics. Summary of the invention

[0005] The embodiments of the present application provide a method and system for constructing a user electricity carbon emission portrait based on spatiotemporal distribution characteristics, which is used to solve the problem that the user electricity carbon emission portrait is not accurate enough and lacks comprehensiveness.

[0006] The first aspect of the embodiment of the present application provides a method for constructing a user electricity carbon emission portrait based on spatiotemporal distribution characteristics, including:

[0007] Obtain information data of target users, historical electricity consumption data of target users, and power grid generation structure data, and pre-process the acquired data;

[0008] Extracting target feature data related to time and target feature data related to geographical distribution based on the preprocessed data;

[0009] Analyzing the time variation characteristics and the regional distribution variation characteristics of the carbon emission factor of the target user according to the time-related target characteristic data and the regional distribution-related target characteristic data respectively;

[0010] A dynamic profile of the target user's electricity carbon emissions is constructed based on the temporal variation characteristics and the regional distribution variation characteristics of the target user's carbon emission factor.

[0011] Furthermore, the extracting of target feature data related to time and target feature data related to geographical distribution based on the preprocessed data includes:

[0012] The principal component analysis method is used to determine the eigenvectors related to time and the eigenvectors related to geographical distribution;

[0013] The target characteristic data related to time and the target characteristic data related to geographical distribution are determined according to the calculated scores on the time principal component and the geographical principal component.

[0014] Furthermore, the step of determining the target characteristic data related to time and the target characteristic data related to geographical distribution according to the calculated scores of the time principal component and the geographical principal component includes:

[0015] Time principal component score PC time,ij :

[0016]

[0017] in: is the row vector of the i-th user sample in the standardized time series data matrix, v time,j is the corresponding eigenvector;

[0018] Regional principal component score FC region,ij :

[0019]

[0020] In the district: is the row vector of the i-th user sample in the standardized regional data matrix, v region,j is the corresponding feature vector.

[0021] Furthermore, the analyzing the time variation characteristics and the regional distribution variation characteristics of the carbon emission factor of the target user according to the time-related target characteristic data and the regional distribution-related target characteristic data respectively includes:

[0022] Taking the carbon emission factor of the target user as the dependent variable, constructing a dummy variable with the target characteristic data related to time and the target characteristic data related to geographical distribution respectively;

[0023] Determine an initial time dummy variable model based on the dependent variable and the dummy variables constructed with the target characteristic data related to time, and determine a spatial dummy variable model based on the dependent variable and the dummy variables constructed with the target characteristic data related to the geographical distribution;

[0024] Calculating the coefficients of the time dummy variable model and the coefficients of the space dummy variable model respectively by using the least square method;

[0025] The target time dummy variable model and the target space dummy variable model are determined according to the calculated coefficients.

[0026] Furthermore, the using of the least square method to calculate the coefficients of the time dummy variable model and the coefficients of the space dummy variable model respectively includes:

[0027] Coefficients of the time dummy variable model

[0028]

[0029]

[0030]

[0031]

[0032] Where: D mn is n time dummy variables among m observations;

[0033] Coefficients of the spatial dummy variable model

[0034]

[0035]

[0036]

[0037]

[0038] Where: R pm is the m time dummy variable in p observations.

[0039] Furthermore, the target time dummy variable model and the target space dummy variable model are determined according to the calculated coefficients, including:

[0040] Target time dummy variable model:

[0041]

[0042] Among them: CF is the carbon emission factor, β0 is the intercept term of the time factor, β i is the time dummy variable D i The corresponding coefficient, ∈1, is the time factor error term.

[0043] Furthermore, the target time dummy variable model and the target space dummy variable model are determined according to the calculated coefficients, including:

[0044] Target space dummy variable model:

[0045]

[0046] Among them: α0 is the intercept term of spatial factor, α j is the spatial dummy variable R j The corresponding coefficient, ∈2, is the spatial factor error term.

[0047] Furthermore, the step of constructing a dynamic profile of the target user's electricity carbon emissions based on the temporal variation characteristics and the regional distribution variation characteristics of the target user's carbon emission factor includes:

[0048] Determine the change of the time dummy variable coefficient over time according to the target time dummy variable model, and predict the change of the dummy variable coefficient within a preset time in combination with the time series analysis method;

[0049] Determine the change of spatial virtual variable coefficients with regional development according to the target spatial virtual variable model, and analyze the impact of regional-related external factors on the coefficients;

[0050] A first dynamic profile of carbon emissions from electricity consumption is constructed based on the time coefficient change and the prediction results, and a second dynamic profile of carbon emissions from electricity consumption is constructed based on the space coefficient change and external factors.

[0051] A target dynamic portrait of the user's electricity carbon emissions is determined based on the first dynamic portrait and the second dynamic portrait.

[0052] Furthermore, determining the target dynamic profile of the user's electricity carbon emissions according to the first dynamic profile and the second dynamic profile includes:

[0053] The comprehensive model expression of the target dynamic portrait is as follows:

[0054]

[0055] Where: γ ij is the interaction term D i R j The coefficient of .

[0056] A second aspect of the embodiment of the present application provides a system for constructing a user electricity carbon emission profile based on spatiotemporal distribution characteristics, including:

[0057] A data acquisition and preprocessing unit, used to acquire information data of target users, historical electricity consumption data of target users, and power grid generation structure data, and preprocess the acquired data;

[0058] A target feature data extraction unit, used to extract target feature data related to time and target feature data related to geographical distribution based on the preprocessed data;

[0059] A time variation characteristic and regional distribution variation characteristic analysis unit, used for analyzing the time variation characteristic and regional distribution variation characteristic of the carbon emission factor of the target user according to the target characteristic data related to time and the target characteristic data related to regional distribution respectively;

[0060] A dynamic portrait construction unit is used to construct a dynamic portrait of the target user's electricity carbon emissions based on the time variation characteristics and regional distribution variation characteristics of the target user's carbon emission factor.

[0061] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0062] The present invention collects information data, historical electricity consumption data, and power grid generation structure data of target users, and pre-processes these data to extract target feature data related to time and geographical distribution. On this basis, the change characteristics of the carbon emission factors of target users are analyzed from the two dimensions of time and region, and finally a dynamic portrait of the carbon emissions of electricity consumption of target users is constructed based on these change characteristics. The target dynamic portrait can accurately reflect the carbon emissions of electricity consumption of target users under different time and geographical conditions, and provide strong data support and scientific basis for power companies to formulate personalized energy service strategies and governments to implement precise carbon emission reduction policies.

[0063] Other advantages, objectives, and features of the present invention will be set forth in part in the following description, and in part will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 A schematic flow chart of a method for constructing a user electricity carbon emission profile based on spatiotemporal distribution characteristics in the present invention;

[0065] Figure 2 Another flowchart of a method for constructing a user electricity carbon emission profile based on spatiotemporal distribution characteristics in the present invention;

[0066] Figure 3 This is another flowchart of a method for constructing a user electricity carbon emission profile based on spatiotemporal distribution characteristics in the present invention. DETAILED DESCRIPTION

[0067] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein, for example. In addition, the terms "including" and "corresponding to" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0068] Embodiment 1

[0069] The implementation method in this embodiment can be implemented in the system, in the server, or in the terminal, and there is no specific limitation. The following will introduce the coordinated control method for fault ride-through of multiple equipment in the photovoltaic station in this application from the perspective of system implementation. Figure 1-Figure 3 , the method provided in the embodiment of the present application comprises the following steps:

[0070] S11. Obtain information data of target users, historical electricity consumption data of target users, and power grid generation structure data, and pre-process the acquired data;

[0071] In this embodiment, the user information data includes geographic location information data, user type, business category of commercial users, production type of industrial users, population size, scale of commercial venues, scale of factory production and number of employees, etc. The region, industry and group type of the target user are determined by obtaining the user information data.

[0072] Historical electricity consumption data includes electricity consumption data, electricity consumption time data, and electricity power data. The electricity consumption data includes time resolution data and cumulative electricity consumption, such as electricity consumption recorded at different time intervals and total electricity consumption within a certain period. Electricity consumption time data includes daily electricity consumption time distribution, weekly electricity consumption time pattern, and seasonal electricity consumption time changes. Electricity power data includes the user's electricity power at each moment and the efficiency of the user's electrical equipment in utilizing electricity.

[0073] The power grid generation structure data includes power generation methods and proportion data, power generation time series data, and power grid connection and transmission data. The power generation methods and proportion data include the proportion of various power generation methods such as coal power generation, hydropower generation, wind power generation, solar power generation, nuclear power generation, and natural gas power generation in the total power generation of the power grid, and the contribution of the power generation of large power stations and distributed power generation facilities to the power grid. The power generation time series data includes the changes in the power generation time of each power generation method within a day, a week, or a month, and the power generation plan formulated by the power grid dispatching department based on power demand forecasts and power generation resources. The power grid connection and transmission data includes information such as the connection method between different power grids, the amount of power exchanged and the exchange time, and the loss rate of different transmission lines, transmission distance and other data.

[0074] The above data are preprocessed, including data cleaning and standardization, to check whether the user power consumption data and power grid power generation structure data are complete. For missing data points, appropriate methods are used to fill them according to the characteristics and distribution of the data. Data of different magnitudes are standardized so that all data are at the same magnitude. For example, for power consumption data and power generation ratio data, the Z-score standardization method is used here to convert the data into a standard normal distribution with a mean of 0 and a standard deviation of 1.

[0075] S12. Extracting target feature data related to time and target feature data related to geographical distribution based on the preprocessed data;

[0076] Step S12 includes the following steps:

[0077] 1. Use principal component analysis to determine the eigenvectors related to time and the eigenvectors related to geographical distribution;

[0078] 2. Determine the target characteristic data related to time and the target characteristic data related to geographical distribution according to the calculated scores on the time principal component and the geographical principal component.

[0079] Specifically, the preprocessed time series data is organized into a data matrix X time , where rows represent different user samples and columns represent variables at different time points. time Perform standardization to obtain the standardized matrix Calculate the covariance matrix Where n is the number of user samples, and the covariance matrix reflects the covariance relationship between variables at different time points, that is, the correlation of time series data at different time points. time Perform eigendecomposition and obtain the eigenvalue λ time,1 ,λ time,2 ,…,λ time,m, where m is the number of time point variables, and the corresponding eigenvector is v time,1 ,v time,2 ,…,v time,m For example, the first eigenvector has the largest eigenvalue, indicating that the variance of the time series data in this direction is the largest. This direction may correspond to the main trend of electricity consumption in a day. time principal components, so that To reach the set ratio, k time The principal components represent the main time patterns in the time series data. For each user sample i, in the jth (j=1,2,…,k time The scoring formula for the time principal components is as follows:

[0080]

[0081] in: is the row vector of the i-th user sample in the standardized time series data matrix.

[0082] These scores constitute new time-related feature data, which may, for example, represent the user's performance on major time patterns.

[0083] As above, the preprocessed regional data is organized into a data matrix X region , where the rows represent different user samples and the columns represent different region-related variables. region Perform standardization to obtain the standardized matrix Calculate the covariance matrix The covariance matrix reflects the covariance relationship between variables in different regions, that is, the correlation between regional related data. region Perform eigendecomposition and obtain the eigenvalue λ region,1 ,λ region,2 ,…,λ region,m , where m is the number of time point variables, and the corresponding eigenvector is v region,1 ,v region,2 ,…,v region,m The first eigenvector has the largest eigenvalue, indicating that the variance of the regional data in this direction is the largest. This direction may correspond to the main differences between regions. The principal components are selected based on the cumulative variance contribution rate. Assuming that the first k region principal components, so that To reach the set ratio, k region The principal components represent the main regional difference patterns in the regional data. For each user sample i, in the jth (j=1,2,…,k regionThe scoring formula for the time principal components is as follows:

[0084]

[0085] In the district: is the row vector of the i-th user sample in the standardized regional data matrix.

[0086] S13. Analyze the time variation characteristics and the regional distribution variation characteristics of the carbon emission factor of the target user according to the time-related target characteristic data and the regional distribution-related target characteristic data respectively;

[0087] In this embodiment, step S13 further includes the following steps:

[0088] S131. Taking the carbon emission factor of the target user as the dependent variable, constructing a dummy variable with the target characteristic data related to time and the target characteristic data related to geographical distribution respectively;

[0089] Construct dummy variables with time-related target characteristic data:

[0090] First, analyze the time-related target feature data to determine the appropriate time period division method. For example, it can be divided by time period of the day, divided into 0-6 o'clock (time period 1), 6-12 o'clock (time period 2), 12-18 o'clock (time period 3), 18-24 o'clock (time period 4); it can also be divided by week, divided into working days and rest days; it can also be divided by season into spring, summer, autumn and winter.

[0091] Dummy variables are constructed based on the time period. Taking the time period of a day as an example, four dummy variables D1, D2, D3, and D4 are created. When the time corresponding to the data is between 0 and 6 o'clock, D1 = 1, and the rest are D2 = D3 = D4 = 0; when the time is between 6 and 12 o'clock, D2 = 1, and the rest are 0, and so on.

[0092] If divided by week, let D1 be the dummy variable for weekdays, D1 = 1 on weekdays and D1 = 2 on weekends.

[0093] =0, set D2 as a dummy variable for rest days, D2 = 1 for rest days, and D2 = 0 for working days. For seasonal division, set D1 as a dummy variable for spring, D1 = 1 for spring, and D1 = 0 for other seasons; similarly set D2, D3, and D4 to correspond to summer, autumn, and winter respectively.

[0094] Construct dummy variables with target characteristic data related to geographical distribution:

[0095] Analyze the target characteristic data related to regional distribution and determine the division method of regional types. Regional types can be divided according to administrative regions, such as different cities and provinces; they can also be divided according to functional areas, such as commercial areas, industrial areas, and residential areas; they can also be divided according to geographical features, such as coastal areas, inland areas, mountainous areas, etc.

[0096] Taking the city division as an example, suppose there are three cities A, B, and C. Construct three dummy variables R1, R2, and R3. When the target user is located in city A, R1=1, R2=R3=0; when the target user is located in city B, R2=1, R1=R3=0; when the target user is located in city C, R3=1, R1=R2=0. If divided by functional area, let R1 be the commercial area dummy variable. If it is located in the commercial area, R1=1, otherwise R1

[0097] =0, let R2 be the dummy variable of industrial area, R2=1 when located in industrial area, otherwise R2=0; let R3 be the dummy variable of residential area, R3=1 when located in residential area, otherwise R3=0.

[0098] In the above manner, virtual variables are constructed using target characteristic data related to time and target characteristic data related to geographical distribution. These virtual variables can be used to further analyze the relationship between the carbon emission factors of target users and time and geographical factors.

[0099] S132. Determine an initial time dummy variable model based on the dummy variables constructed based on the dependent variable and the target characteristic data related to time, and determine a spatial dummy variable model based on the dummy variables constructed based on the dependent variable and the target characteristic data related to geographical distribution;

[0100] In this embodiment, the carbon emission factor of the target user is taken as the core dependent variable, and the initial time virtual variable model is established by means of the virtual variables constructed by the target characteristic data related to time, so as to explore the changing rules of the carbon emission factor in the time dimension; at the same time, the spatial virtual variable model is determined based on the virtual variables constructed according to the target characteristic data related to the geographical distribution, so as to explore the changing pattern of the carbon emission factor under different geographical conditions, and provide a data basis for comprehensively analyzing the carbon emissions of the target users.

[0101] S133. Calculate the coefficients of the time dummy variable model and the coefficients of the space dummy variable model respectively by using the least square method;

[0102] Coefficients of the time dummy variable model

[0103]

[0104]

[0105]

[0106]

[0107] Where: D mn is n time dummy variables among m observations;

[0108] Coefficients of the spatial dummy variable model

[0109]

[0110]

[0111]

[0112]

[0113] Where: R pm is the m time dummy variable in p observations.

[0114] S134. Determine the target time dummy variable model and the target space dummy variable model respectively according to the calculated coefficients.

[0115] Target time dummy variable model:

[0116]

[0117] Among them: CF is the carbon emission factor, β0 is the intercept term of the time factor, β i is the time dummy variable D i The corresponding coefficient, ∈1, is the time factor error term.

[0118] In the time dummy variable model, the coefficient β i The change of can reflect the dynamic change of carbon emission factor in the time dimension. For example, if β i It increases with time, indicating that the user's carbon emission factor is on an upward trend during this time period.

[0119] Target space dummy variable model:

[0120]

[0121] Among them: α0 is the intercept term of spatial factor, α j is the spatial dummy variable R j The corresponding coefficient, ∈2, is the spatial factor error term.

[0122] In the spatial dummy variable model, α j The change of coefficient reflects the dynamic change of carbon emission factor in spatial dimension.j An increase may mean that the carbon emission factor of users in the region is increasing.

[0123] S14. Construct a dynamic profile of the target user’s electricity carbon emissions based on the temporal variation characteristics and regional distribution variation characteristics of the target user’s carbon emission factors.

[0124] In this embodiment, step S14 further includes:

[0125] S141. Determine the change of the time dummy variable coefficient over time according to the target time dummy variable model, and predict the change of the dummy variable coefficient within a preset time by combining the time series analysis method;

[0126] Observe the coefficients of dummy variables at different times Changes over time (e.g., different seasons, different years). For example, if it is summer, the coefficient of the time dummy variable representing the daytime period is It increases year by year, indicating that the carbon emission factor of electricity consumption by users during the day in summer is on the rise. Combined with the time series analysis method, the change of the virtual variable coefficient in the future is predicted. Build a simple first-order autoregressive model:

[0127]

[0128] where ρ is the autoregressive coefficient, ∈ t is the error term. By estimating ρ, we can predict future coefficient changes and thus predict the user's future carbon emission behavior.

[0129] S142. Determine the change of spatial virtual variable coefficient with regional development according to the target spatial virtual variable model, and analyze the impact of regional-related external factors on the coefficient;

[0130] Observe the coefficients of different spatial virtual variables Changes with regional development. For example, if a city is vigorously developing renewable energy, the spatial dummy variable coefficient representing the city It may gradually decrease. Consider the impact of regional external factors on the coefficient. For example, after a new carbon reduction policy is implemented in a certain area, the policy effect can be evaluated by comparing the changes in the spatial virtual variable coefficients before and after the policy, and the user profile can be updated.

[0131] S143. construct a first dynamic portrait of the user's electricity carbon emissions based on the time coefficient change and the prediction results, and construct a second dynamic portrait of the user's electricity carbon emissions based on the space coefficient change and external factors;

[0132] The first dynamic portrait is constructed based on the above coefficient changes and prediction results. For example, if it is predicted that the carbon emission factor coefficient of a certain user will increase significantly in a certain period of time in the future, and the user is a residential user, the dynamic portrait can be a "future high carbon emission growth residential user."

[0133] The second dynamic portrait is constructed based on the above-mentioned changes in spatial coefficients and external factors. For example, if a region leads to the concentration of high-energy-consuming industries due to new industrial policies and the coefficient of the spatial virtual variable increases, the dynamic portrait of users in this region can be "high-carbon emission growth users affected by industrial policies."

[0134] S144. Determine a target dynamic portrait of the user's electricity carbon emissions based on the first dynamic portrait and the second dynamic portrait.

[0135] Combining the analysis results of the time and space models, that is, determining the target dynamic portrait of the user's electricity carbon emissions based on the first dynamic portrait and the second dynamic portrait, the target dynamic portrait is a more detailed user portrait. For example, the spatial model determines that the user is in a certain city, and the time model determines that the user's carbon emission factor is high in winter nights, and the user type is a resident. The portrait can be "a resident user with high carbon emissions in a certain city in winter nights."

[0136] Specifically, we can build a model that includes time and space interaction terms by integrating time and space models, analyze the interaction coefficient, and use it to describe the dynamic image of the target. The expression is as follows:

[0137]

[0138] Where: γ ij is the interaction term D i R j If the coefficient of a time-space interaction term is large, it means that under a specific time and space combination, the user's carbon emission factor has a special change pattern, and this interactive effect can be reflected in the portrait.

[0139] For the above comprehensive model with interaction terms, the carbon emission factor can be predicted by comprehensively considering the changes in time and space. For example, the carbon emission factor of a user after moving to a specific region at a certain point in the future is predicted, which fully reflects the combination of time and space dynamic portraits. By fitting these models and estimating the coefficients, the combination of time and space dynamic portraits can be quantitatively represented. By continuously updating the coefficients (β i , α j , γ ij), can timely reflect the dynamic changes of users' carbon emission factors in time and space, and then accurately present the combination of time and space dynamic portraits. For example, due to the adjustment of energy structure in a certain region, users' electricity consumption behavior has also changed at different times. Refitting the model can capture the impact of these changes on the interaction coefficients and achieve accurate representation of the combination of dynamic portraits.

[0140] The above-mentioned embodiment constructs a user portrait based on the carbon emission factors that vary in time and space, which can present the carbon emission characteristics of the user's electricity consumption in different time and space scenarios. The portrait shows the user's carbon emissions at a specific time and in a specific region. Power companies can provide users with personalized energy-saving suggestions and customized electricity price packages based on the portrait, encouraging users to adjust their electricity usage behavior and achieve energy conservation and emission reduction; government departments can formulate more targeted and scientific carbon emission reduction policies based on the portrait, and rationally plan energy structure adjustments and regional development strategies. At the same time, it also provides an intuitive basis for evaluating the effectiveness of policy implementation; from a broader perspective, it helps to improve the overall social awareness of carbon emissions and promote the whole society to actively shift towards a low-carbon development direction.

[0141] Embodiment 2

[0142] An embodiment of a system for constructing a user electricity carbon emission profile based on spatiotemporal distribution characteristics in the present invention includes the following steps:

[0143] A data acquisition and preprocessing unit, used to acquire information data of target users, historical electricity consumption data of target users, and power grid generation structure data, and preprocess the acquired data;

[0144] A target feature data extraction unit, used to extract target feature data related to time and target feature data related to geographical distribution based on the preprocessed data;

[0145] A time variation characteristic and regional distribution variation characteristic analysis unit, used to analyze the time variation characteristic and regional distribution variation characteristic of the carbon emission factor of the target user according to the target characteristic data related to time and the target characteristic data related to regional distribution respectively;

[0146] The dynamic portrait construction unit is used to construct a dynamic portrait of the target user's electricity carbon emissions based on the time variation characteristics and regional distribution variation characteristics of the target user's carbon emission factors.

[0147] For the specific definition of the system, please refer to the definition of the method above, which will not be repeated here. Each module in the above system can be implemented in whole or in part by software, hardware and a combination thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0148] Those of ordinary skill in the art will appreciate that the units of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition of each example has been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0149] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored. In addition, each functional unit in each embodiment of the present invention can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units.

[0150] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-0nlyMemory), random access memory (RAM, RandomAccessMemory), mobile hard disk, magnetic disk or optical disk, etc., which can store program code.

[0151] It can be understood that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A method for constructing a user electricity carbon emission profile based on spatiotemporal distribution characteristics, characterized in that: include: Obtain information data of target users, historical electricity consumption data of target users, and power grid generation structure data, and pre-process the acquired data; Extracting target feature data related to time and target feature data related to geographical distribution based on the preprocessed data; Analyzing the time variation characteristics and the regional distribution variation characteristics of the carbon emission factor of the target user according to the time-related target characteristic data and the regional distribution-related target characteristic data respectively; A dynamic profile of the target user's electricity carbon emissions is constructed based on the temporal variation characteristics and the regional distribution variation characteristics of the target user's carbon emission factor.

2. The method for constructing a user electricity carbon emission profile based on spatiotemporal distribution characteristics according to claim 1 is characterized in that: The extracting of target feature data related to time and target feature data related to geographical distribution based on the preprocessed data includes: The principal component analysis method is used to determine the eigenvectors related to time and the eigenvectors related to geographical distribution; The target characteristic data related to time and the target characteristic data related to geographical distribution are determined according to the calculated scores on the time principal component and the geographical principal component.

3. The method for constructing a user electricity carbon emission profile based on spatiotemporal distribution characteristics according to claim 2 is characterized in that: The step of determining the target characteristic data related to time and the target characteristic data related to geographical distribution according to the calculated scores of the time principal component and the geographical principal component includes: Time principal component score PC time,ij : in: is the row vector of the i-th user sample in the standardized time series data matrix, v time,j is the corresponding eigenvector; Regional principal component score PC region,ij : In the district: is the row vector of the i-th user sample in the standardized regional data matrix, v region,j is the corresponding feature vector.

4. The method for constructing a user electricity carbon emission profile based on spatiotemporal distribution characteristics according to claim 1 is characterized in that: The step of analyzing the time variation characteristics and the regional distribution variation characteristics of the carbon emission factor of the target user according to the time-related target characteristic data and the regional distribution-related target characteristic data, respectively, includes: Taking the carbon emission factor of the target user as the dependent variable, constructing a dummy variable with the target characteristic data related to time and the target characteristic data related to geographical distribution respectively; Determine an initial time dummy variable model based on the dependent variable and the dummy variables constructed with the target characteristic data related to time, and determine a spatial dummy variable model based on the dependent variable and the dummy variables constructed with the target characteristic data related to the geographical distribution; Calculating the coefficients of the time dummy variable model and the coefficients of the space dummy variable model respectively by using the least square method; The target time dummy variable model and the target space dummy variable model are determined according to the calculated coefficients.

5. The method for constructing a user electricity carbon emission profile based on spatiotemporal distribution characteristics according to claim 4 is characterized in that: The using of the least square method to respectively calculate the coefficients of the time dummy variable model and the coefficients of the space dummy variable model comprises: Coefficients of the time dummy variable model Where: D mn is the coefficient of the spatial dummy variable model for n time dummy variables in m observations; Where: R pm is the m time dummy variable in p observations.

6. The method for constructing a user electricity carbon emission profile based on spatiotemporal distribution characteristics according to claim 5 is characterized in that: The step of determining the target time dummy variable model and the target space dummy variable model respectively according to the calculated coefficients includes: Target time dummy variable model: Among them: CF is the carbon emission factor, β0 is the intercept term of the time factor, β i is the time dummy variable D i The corresponding coefficient, ∈1, is the time factor error term.

7. The method for constructing a user electricity carbon emission profile based on spatiotemporal distribution characteristics according to claim 5, characterized in that: The step of determining the target time dummy variable model and the target space dummy variable model respectively according to the calculated coefficients includes: Target space dummy variable model: Among them: α0 is the intercept term of spatial factor, α j is the spatial dummy variable R j The corresponding coefficient, ∈2, is the spatial factor error term.

8. The method for constructing a user electricity carbon emission profile based on spatiotemporal distribution characteristics according to any one of claims 1 to 7, characterized in that: The step of constructing a dynamic profile of the target user's electricity carbon emissions according to the temporal variation characteristics and the regional distribution variation characteristics of the target user's carbon emission factor includes: Determine the change of the time dummy variable coefficient over time according to the target time dummy variable model, and predict the change of the dummy variable coefficient within a preset time in combination with the time series analysis method; Determine the change of spatial virtual variable coefficients with regional development according to the target spatial virtual variable model, and analyze the impact of regional-related external factors on the coefficients; A first dynamic profile of carbon emissions from electricity consumption is constructed based on the time coefficient change and the prediction results, and a second dynamic profile of carbon emissions from electricity consumption is constructed based on the space coefficient change and external factors. A target dynamic portrait of the user's electricity carbon emissions is determined based on the first dynamic portrait and the second dynamic portrait.

9. The method for constructing a user electricity carbon emission profile based on spatiotemporal distribution characteristics according to claim 8, characterized in that: The determining the target dynamic profile of the user's electricity carbon emissions according to the first dynamic profile and the second dynamic profile includes: The comprehensive model expression of the target dynamic portrait is as follows: Where: γ ij is the interaction term D i R j The coefficient of .

10. A system for constructing a user electricity carbon emission profile based on spatiotemporal distribution characteristics, characterized in that: include: A data acquisition and preprocessing unit is used to acquire information data of target users, historical electricity consumption data of target users, and power grid generation structure data, and preprocess the acquired data; A target feature data extraction unit, used to extract target feature data related to time and target feature data related to geographical distribution based on the preprocessed data; A time variation characteristic and regional distribution variation characteristic analysis unit, used for analyzing the time variation characteristic and regional distribution variation characteristic of the carbon emission factor of the target user according to the target characteristic data related to time and the target characteristic data related to regional distribution respectively; A dynamic portrait construction unit is used to construct a dynamic portrait of the target user's electricity carbon emissions based on the time variation characteristics and regional distribution variation characteristics of the target user's carbon emission factor.

Images