Electric-carbon collaborative data processing method, device and storage medium

Abstract

The present invention provides an electric-carbon collaborative data processing method, device and storage medium, which relates to data processing technology, including: extracting electric-carbon data from an electric-carbon meter within a first preset time period, and generating a first electric-carbon function after functional processing of the electric-carbon data based on the time dimension; extracting power generation and storage data of a power generation and storage device within the first preset time period, and generating a second electric-carbon function after functional processing of the power generation and storage data based on the time dimension; regularizing and analyzing the first electric-carbon function and the second electric-carbon function based on a pre-trained regular processing model, respectively, to generate a first piecewise function set and a second piecewise function set for multiple corresponding time periods; collaboratively processing the first piecewise function set and the second piecewise function set to generate a collaborative data control strategy. The present invention can provide timely and effective decision-making basis for energy scheduling and carbon emission control.

Description

Technical Field

[0001] The present invention relates to data processing technology, and in particular to an electric-carbon collaborative data processing method, device and storage medium. Background Art

[0002] In various power companies, industrial production, and large commercial complexes, the production and consumption of electricity continues, accompanied by the generation of a large amount of electricity carbon data. The energy structure in these scenarios is complex and diverse, covering traditional thermal power, hydropower, and emerging new energy power generation such as solar energy and wind power. The carbon emissions generated by different energy sources vary significantly, and there is an urgent need for accurate processing and coordinated management of electricity carbon data.

[0003] Existing electricity-carbon data processing technologies often separate electricity data from carbon data for separate processing. In terms of electricity data processing, the main focus is on the statistics and analysis of basic information such as power generation and electricity consumption, and the impact of electricity sources on carbon emissions is not fully considered. Carbon data processing, on the other hand, focuses on the accounting of the overall total carbon emissions and lacks real-time connection with the electricity production and consumption process. This separate processing method makes it impossible to accurately reveal the inherent connection between electricity and carbon in the process of electricity production and consumption, and it is difficult to meet the increasingly stringent requirements of energy management and carbon emission control. For example, when faced with differences in carbon consumption caused by changes in electricity sources in different time periods, existing technologies cannot respond quickly and accurately, and cannot provide timely and effective decision-making basis for energy scheduling and carbon emission control.

[0004] Therefore, how to collaboratively process electricity data and carbon data, dynamically generate collaborative control strategies, and provide timely and effective decision-making basis for energy scheduling and carbon emission control. Summary of the invention

[0005] The embodiments of the present invention provide an electricity-carbon collaborative data processing method, device and storage medium, which can provide timely and effective decision-making basis for energy scheduling and carbon emission control.

[0006] A first aspect of an embodiment of the present invention provides an electric-carbon collaborative data processing method, comprising:

[0007] Extracting the electric carbon data of the electric carbon meter within a first preset time period, and generating a first electric carbon function after functional processing of the electric carbon data based on the time dimension;

[0008] Extract the power generation and storage data of the power generation and storage device in the first preset time period, and generate a second electric carbon function after functional processing of the power generation and storage data based on the time dimension;

[0009] Based on the pre-trained regularization processing model, regularization analysis is performed on the first electric-carbon function and the second electric-carbon function respectively to generate a first piecewise function set and a second piecewise function set for a plurality of corresponding time periods;

[0010] The first piecewise function set and the second piecewise function set are collaboratively processed to generate a collaborative data control strategy.

[0011] Optionally, the extracting of the electric carbon data of the electric carbon meter within the first preset time period, and generating a first electric carbon function after functional processing of the electric carbon data based on the time dimension, includes:

[0012] Obtaining the carbon data of a first preset time period, and establishing an initial coordinate system with the horizontal axis being the time and the vertical axis being the carbon value;

[0013] Extracting the coordinates of the electric carbon data in the first preset time period, and performing multi-dimensional zeroing processing based on the attributes of the electric carbon data to obtain the electric carbon-time coordinates after zeroing processing;

[0014] Determine all the electron-carbon-time coordinates in the coordinate system and generate the first electron-carbon function.

[0015] Optionally, the extracting the coordinates of the electric carbon data of the first preset time period, and performing multi-dimensional zeroing processing based on the attributes of the electric carbon data to obtain the electric carbon-time coordinates after zeroing processing includes:

[0016] Extracting time points within a first preset time period at preset time intervals to obtain a plurality of time reference coordinates, wherein the time reference coordinates are one-dimensional coordinates;

[0017] Determine the electric carbon data corresponding to each time reference coordinate to obtain the electric carbon-time coordinate, wherein the electric carbon-time coordinate is a two-dimensional coordinate;

[0018] The farthest electric carbon-time coordinate is extracted as the zeroing reference coordinate, and all the electric carbon-time coordinates are subtracted from the zeroing reference coordinate to obtain the electric carbon-time coordinate after zeroing.

[0019] Optionally, the step of extracting the power generation and storage data of the power generation and storage device in the first preset time period, and generating a second electric-carbon function after functional processing of the power generation and storage data based on the time dimension, includes:

[0020] Acquire the power generation and storage data of the first preset time period, and establish an initial coordinate system with the horizontal axis as time and the vertical axis as power value;

[0021] Extracting the coordinates of the power generation and storage data of the first preset time period, and performing multi-dimensional zeroing processing based on the attributes of the power generation and storage data to obtain power generation-time coordinates and power storage-time coordinates after the zeroing processing;

[0022] Determine all power generation-time coordinates and power storage-time coordinates in the coordinate system and generate a first power generation function and a first power storage function, wherein the second electric-carbon function includes the first power generation function and the first power storage function.

[0023] Optionally, the regularization processing model based on pre-training respectively analyzes the regularization of the first electric-carbon function and the second electric-carbon function to generate a first piecewise function set and a second piecewise function set of multiple corresponding time periods, including:

[0024] The regularization processing model obtains the total power consumption, total power generation consumption and total power storage in the first preset time period, and calculates the power generation and storage participation coefficient in the first preset time period;

[0025] Calculating a first average slope of a first electro-carbon function and adjacent sub-slopes of the electro-carbon-time coordinate;

[0026] A segmentation standard is obtained based on the generation and storage participation coefficient and the first average slope, and a first segmentation function set and a second segmentation function set are obtained according to the segmentation standard.

[0027] Optionally, the calculating of the generation and storage participation coefficient within the first preset time period includes:

[0028] The total power generation consumption is weighted based on the power generation consumption weight to obtain a first weighted value, the total storage capacity is weighted based on the storage capacity weight to obtain a second weighted value, and the sum of the first weighted value and the second weighted value is calculated to obtain a numerator weighted value;

[0029] The total power generation consumption is weighted based on the power consumption weight to obtain the parent-child weighted value, and the numerator weighted value is divided by the denominator weighted value to obtain the power generation and storage participation coefficient.

[0030] Optionally, obtaining a segmentation standard based on the generation and storage participation coefficient and the first average slope, and obtaining a first segmentation function set and a second segmentation function set according to the segmentation standard, comprises:

[0031] The first normalized value is obtained after normalizing the participation coefficient of the production and storage based on the normalized value, and the actual adjustment value is obtained by subtracting the first normalized value from the standard adjustment value;

[0032] Multiplying the actual adjustment value by the first average slope to obtain a threshold slope and use it as a segmentation standard;

[0033] All segments of the first electro-carbon function having a slope greater than the threshold value are extracted to obtain a corresponding first piecewise function set, and a second piecewise function set is determined based on the first piecewise function set.

[0034] Optionally, determining the second piecewise function set based on the first piecewise function set includes:

[0035] Extracting all the piecewise functions in the first piecewise function set to obtain a plurality of piecewise times;

[0036] The interval segments corresponding to the segmented time in the second electric-carbon function are determined to obtain a second segmented function set, wherein the second segmented function set includes a power generation function set and a power storage function set.

[0037] Optionally, the collaborative processing of the first piecewise function set and the second piecewise function set to generate a collaborative data control strategy includes:

[0038] Determine the second piecewise function corresponding to each first piecewise function, extract the power generation consumption and power storage corresponding to the second piecewise function, and add the power generation consumption and power storage to obtain the total power generation;

[0039] Extract the rated discharge capacity of the power storage device and add it to the total power generation to obtain the total regulated power, and correspond the total regulated power to the first piecewise function;

[0040] Determine a second time period in the future corresponding to the first preset time period, and determine a second time sub-segment corresponding to the second time period in the first segmentation function;

[0041] When it is determined that the second time sub-segment has been reached, the total regulated power is mobilized to supply power to the load or the regulated power corresponding to the value of the power required by the load is mobilized to supply power.

[0042] Optionally, also include:

[0043] After determining that the power supply in the second time period is completed, obtaining a third electric-carbon function that has actually occurred in the second time period, wherein the third electric-carbon function is a function generated by functionalizing the electric-carbon data in the second time period according to the time dimension;

[0044] If the maximum value of the third electric-carbon function is less than or equal to the maximum value of the first electric-carbon function, the normalized value is not adjusted;

[0045] If the maximum value of the third electric-carbon function is less than the maximum value of the first electric-carbon function, the normalized value is increased to reduce the first normalized value, so as to achieve re-training of the regularization processing model.

[0046] Optionally, if the maximum value of the third electric-carbon function is less than the maximum value of the first electric-carbon function, the normalized value is increased to reduce the first normalized value, including:

[0047] calculating the absolute value of the difference between the maximum value of the third electric-carbon function and the maximum value of the first electric-carbon function;

[0048] The absolute value is divided by the standard value and then weighted and added to the original normalized value to obtain the normalized value after the regularization processing model is adjusted up.

[0049] In a second aspect, the present application provides an electronic device, including:

[0050] processor; and,

[0051] A memory, configured to store executable instructions of the processor;

[0052] The processor is configured to perform any possible method described in the first aspect by executing the executable instructions.

[0053] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement any possible method described in the first aspect.

[0054] Technical effects:

[0055] 1. Generate the first carbon function and the second carbon function by extracting the carbon data of the carbon meter and the power generation and storage data of the power generation and storage equipment within the preset time period, and performing functional processing based on the time dimension. This process realizes the orderly integration and intuitive presentation of carbon data and power generation and storage data. When processing carbon data, the trend of carbon value changes over time is clearly displayed through the steps of establishing a coordinate system, extracting coordinates, and returning to zero; the same is true for power generation and storage data. This processing method provides a solid data foundation for subsequent regular analysis, can accurately reflect the carbon situation in the process of power production and consumption, and improves the accuracy and availability of data compared to traditional data processing methods.

[0056] 2. Based on the regular processing model, the first electric-carbon function and the second electric-carbon function are analyzed in a regularized manner to generate the first piecewise function set and the second piecewise function set, and on this basis, collaborative processing is performed to generate a collaborative data control strategy. The segmentation standard is determined by calculating parameters such as the generation and storage participation coefficient and the slope of the electric-carbon function, thereby realizing the reasonable allocation of energy in different time periods. When the system determines that a specific time segment has been reached, it can flexibly mobilize the total regulated power or the corresponding regulated power supply according to the load power demand. This series of operations effectively improves energy utilization efficiency, reduces carbon emissions, and realizes the intelligence and optimization of energy management.

[0057] 3. After completing the power supply in a specific time period (the second time period), obtain the third electric-carbon function that actually occurs in the time period and compare it with the maximum value of the first electric-carbon function. If the maximum value of the third electric-carbon function does not meet expectations, the regularization processing model is retrained by calculating the absolute value of the difference, adjusting the normalization value, and other operations. According to the comparison result between the maximum values ​​of the third electric-carbon function and the first electric-carbon function, the normalization value is increased to change the output of the regularization processing model. This mechanism enables the model to continuously adapt to changes in actual electricity consumption and carbon emissions, continuously optimize energy management and carbon emission control strategies, and improve the adaptability and flexibility of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 It is a flow chart of the electric-carbon collaborative data processing method provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0060] See also Figure 1 , is a flow chart of an electric-carbon collaborative data processing method provided by an embodiment of the present invention, the method comprising:

[0061] S1, extracting the electric carbon data of the electric carbon meter within a preset time period, and generating a first electric carbon function after functional processing of the electric carbon data based on the time dimension.

[0062] Among them, the electricity carbon meter can collect statistics on carbon consumption data in each time period. It is worth mentioning that since the sources of electricity used in the electricity consumption time period are different, the corresponding carbon consumption data are different even if the electricity consumption in some time periods is the same. For example, if the new energy electricity consumption in a time period is more, the corresponding carbon consumption will be less, and vice versa.

[0063] In some embodiments, the extracting of the electric-carbon data of the electric-carbon table within a preset time period and generating a first electric-carbon function after functionalizing the electric-carbon data based on the time dimension includes:

[0064] S11, obtaining the carbon data of a preset time period, and establishing an initial coordinate system with the horizontal axis representing time and the vertical axis representing carbon value.

[0065] Obtain the electric carbon data for a preset time period. This preset time period can be flexibly set according to the actual application scenario, such as one day, one week, one month, etc. This solution will be explained using an example of 1 day and 24 hours. Establish an initial coordinate system with time as the horizontal axis and the electric carbon value as the vertical axis. This coordinate system provides an intuitive spatial framework for subsequent data processing, so that the electric carbon data can be presented in an orderly manner in the time dimension. For example, in the carbon emission monitoring scenario of an electric power company, taking one day as the preset time period, the electric carbon data of each hour is mapped to the coordinate system, and the changing trend of the electric carbon value over time within a day can be clearly observed.

[0066] S12, extracting the coordinates of the electric carbon data in a preset time period, and performing multi-dimensional zeroing processing based on the attributes of the electric carbon data to obtain the electric carbon-time coordinates after the zeroing processing.

[0067] Since the carbon consumption data increases gradually, the carbon consumption data at 0:00 every day is not reset to zero. This step can reset the coordinates to zero.

[0068] The extraction of coordinates of the electric carbon data of a preset time period and the multi-dimensional zeroing processing based on the attributes of the electric carbon data to obtain the electric carbon-time coordinates after the zeroing processing include:

[0069] S121, extracting time points within a preset time period at preset time intervals to obtain multiple time reference coordinates, where the time reference coordinates are one-dimensional coordinates.

[0070] Among them, the preset time interval extracts multiple time reference coordinates for time points within the preset time period (for example, 24 hours from 0:00 to 24:00), and these time reference coordinates are one-dimensional coordinates (located on the X-axis). The setting of the preset time interval depends on the accuracy requirements of the data and the actual application scenario. If high-precision monitoring of electric carbon data changes is required, the preset time interval can be set to 15 minutes or even shorter; in some scenarios with relatively low requirements for data accuracy, the preset time interval can be 1 hour. In this way, the continuous time axis can be discretized, which is convenient for the subsequent processing of the electric carbon data corresponding to each time point.

[0071] S122, determining the electric carbon data corresponding to each time reference coordinate to obtain the electric carbon-time coordinate, wherein the electric carbon-time coordinate is a two-dimensional coordinate.

[0072] This step achieves a one-to-one correspondence between time and carbon value, and closely combines the originally independent time information and carbon data. For example, in the above-mentioned power company's one-day monitoring scenario, the carbon value corresponding to the time reference coordinate of 1:00 is 103, so the carbon-time coordinate (1,103) is obtained.

[0073] S123, extracting the farthest electric carbon-time coordinate as the zeroing reference coordinate, subtracting all the electric carbon-time coordinates from the zeroing reference coordinate, and obtaining the electric carbon-time coordinate after zeroing processing.

[0074] Extract the farthest electric carbon-time coordinate as the zero reference coordinate (for example, the electric carbon value at 0:00 is 100), subtract all the electric carbon-time coordinates from the zero reference coordinate (for example, the electric carbon value at 24:00 is 120, then the electric carbon-time coordinate at 24:00 is (24,120-100) or (24,20) after zero processing, and get the electric carbon-time coordinate after zero processing. This zeroing processing method helps to eliminate the initial offset in the data, so that data from different time periods can be compared and analyzed under the same benchmark. For example, in the comparison of electric carbon data on different dates, through zeroing processing, the difference in the changing trend of daily electric carbon data can be more clearly seen, without being affected by different initial electric carbon values.

[0075] S13, determining all the electro-carbon-time coordinates in the coordinate system and generating a first electro-carbon function.

[0076] Determine all the zeroed carbon-time coordinates in the coordinate system and generate the first carbon-time function. This function connects the discrete carbon-time coordinates into a continuous function curve, which can more accurately describe the change of carbon value over time. Through the first carbon-time function, we can conduct a more in-depth analysis of carbon-time data, providing a basis for subsequent regular analysis and collaborative processing.

[0077] S2, extracting the power generation and storage data of the power generation and storage equipment in a preset time period, and generating a second electric-carbon function after functional processing of the power generation and storage data based on the time dimension.

[0078] The power generation and storage equipment may be new energy power generation and power storage equipment installed by the enterprise, and the new energy power generation equipment may be, for example, wind power generation, photovoltaic power generation, etc. This step is mainly used to process the above data to generate a second electric-carbon function.

[0079] In some embodiments, the extracting of the power generation and storage data of the power generation and storage device in the preset time period, and generating a second electric-carbon function after functional processing of the power generation and storage data based on the time dimension, includes:

[0080] S21, obtaining the power generation and storage data of a preset time period, and establishing an initial coordinate system with the horizontal axis being time and the vertical axis being power value.

[0081] Get the power generation and storage data for the preset time period. This preset time period must be consistent with the preset time period in the electric carbon data processing to ensure the accuracy of subsequent collaborative processing. Establish an initial coordinate system with time as the horizontal axis and power value as the vertical axis. For example, in a distributed energy system equipped with solar panels and energy storage batteries, with one day as the preset time period, the hourly power generation and storage data are mapped to the coordinate system, which can clearly show the changes in power generation and storage over time within a day.

[0082] S22, extracting the coordinates of the power generation and storage data in a preset time period, and performing multi-dimensional zeroing processing based on the attributes of the power generation and storage data to obtain power generation-time coordinates and power storage-time coordinates after the zeroing processing.

[0083] The operation logic of this step is similar to the coordinate extraction and zeroing processing in the electric carbon data processing. First, the time points within the preset time period are extracted at preset intervals to obtain multiple time reference coordinates (one-dimensional coordinates, located on the X-axis). The preset time interval is also flexibly set according to actual needs. If you want to finely monitor the dynamic changes of power generation and storage data, you can set a shorter time interval, such as 15 minutes; if the requirements for grasping the data change trend are relatively low, it can be set to 1 hour. Through such time discretization, it is convenient to process the power generation and storage data at each time point.

[0084] Determine the power generation and storage data corresponding to each time reference coordinate, and then obtain the power generation and storage-time coordinate, which is a two-dimensional coordinate. For example, in the above distributed energy system, the power generation corresponding to the time reference coordinate of 10:00 is 80 degrees and the storage is 30 degrees, so the power generation-time coordinate (10,80) and the storage-time coordinate (10,30) are obtained.

[0085] Extract the farthest generation and storage energy-time coordinates as the zero reference coordinates. Assuming that the power generation at 0:00 is 0 and the storage is 50, then the generation-time coordinate (0,0) and storage-time coordinate (0,50) at 0:00 are used as the zero reference coordinates for the power generation and storage data, respectively. Subtract all the generation and storage energy-time coordinates from the corresponding zero reference coordinates to obtain the generation-time coordinates and storage-time coordinates after zeroing. For example, at 11:00, the power generation is 90 degrees and the storage is 100 degrees, then the generation-time coordinate after zeroing is (11,90-0) or (11,90), and the storage-time coordinate is (11,100-50) or (11,50). This zeroing process helps to eliminate the initial deviation in the data, so that the power generation and storage data of different time periods can be compared and analyzed under a unified benchmark, and more accurately reflect the changes in power generation and storage.

[0086] S23, determining all power generation-time coordinates and power storage-time coordinates in the coordinate system and generating a first power generation function and a first power storage function, wherein the second electric-carbon function includes the first power generation function and the first power storage function.

[0087] Determine all the zeroed power generation-time coordinates and power storage-time coordinates in the coordinate system, and connect them to generate the first power generation function and the first power storage function respectively. These two functions can describe the changing patterns of power generation and power storage over time. For example, the first power generation function can reflect the power generation trend of solar panels at different times of the day, and the first power storage function can show the change of the charge and discharge state of the energy storage battery over time. The second electric carbon function is composed of the first power generation function and the first power storage function, which comprehensively reflects the power-related characteristics of the power generation and storage equipment within a preset time period.

[0088] S3, regularly analyzing the first electro-carbon function and the second electro-carbon function based on the pre-trained regularization processing model, and generating a first piecewise function set and a second piecewise function set of multiple corresponding time periods.

[0089] In the electric-carbon collaborative data processing method of the present invention, after completing the functional processing of the electric-carbon data and the power generation and storage data, it is necessary to conduct regular analysis of these functions based on the pre-trained regular processing model to generate a first set of piecewise functions and a second set of piecewise functions.

[0090] In some embodiments, the pre-trained regularization processing model respectively performs regularization analysis on the first electric-carbon function and the second electric-carbon function to generate a first piecewise function set and a second piecewise function set for a plurality of corresponding time periods, including:

[0091] S31, the regular processing model obtains the total power consumption, total power generation and total power storage within a preset time period, and calculates the power generation and storage participation coefficient within the preset time period.

[0092] This step introduces a regularization processing model, which calculates the total electricity consumption, total power generation and total storage within a preset time period to obtain the generation and storage participation coefficient. It is worth mentioning that the higher the generation and storage participation coefficient, the higher the degree of participation of the enterprise's new energy in the entire energy supply system. This coefficient provides a key reference indicator for subsequent analysis combined with the electricity-carbon function.

[0093] The step of calculating the participation coefficient of issuance and storage within a preset time period includes:

[0094] S311, weighting the total power generation consumption based on the power generation consumption weight to obtain a first weighted value, weighting the total storage capacity based on the storage capacity weight to obtain a second weighted value, and calculating the sum of the first weighted value and the second weighted value to obtain a numerator weighted value.

[0095] The regular processing model obtains the total power generation and consumption (for example, the power generated by new energy equipment, such as solar panels and wind turbines for consumption) and the total power storage (the power generated and stored by new energy equipment) within a preset time period. Among them, the total power generation and consumption is the power that is used immediately after it is generated. For example, if 10 degrees are generated, they are directly used without participating in energy storage. Energy storage refers to the storage of excess power generation.

[0096] The total power generation consumption is weighted based on the power generation consumption weight to obtain the first weighted value, and the total storage capacity is weighted based on the storage capacity weight to obtain the second weighted value. The two weighted values ​​are added together to obtain the numerator weighted value. The weight setting is usually determined based on the importance of power generation and energy storage in the energy structure in the actual application scenario. For example, in an energy system that vigorously develops solar power generation and focuses on energy storage regulation, the power generation consumption weight can be set to 0.7 and the storage capacity weight can be set to 0.3. This numerator weighted value reflects the comprehensive contribution of power generation and energy storage in the overall energy from the dimension of new energy.

[0097] S312, based on the electricity consumption weight, weight the total power generation consumption to obtain the denominator weighted value (electricity consumption dimension), and divide the denominator weighted value by the denominator weighted value to obtain the generation and storage participation coefficient (the higher the participation of new energy),

[0098] The total power generation power consumption is weighted based on the power consumption weight to obtain the denominator weighted value. The power consumption weight here is generally determined based on the proportion of power demand in energy distribution. Divide the denominator weighted value by itself to obtain the power generation and storage participation coefficient. The higher the power generation and storage participation coefficient, the higher the participation of new energy in the entire energy supply system of the enterprise. This coefficient provides a key reference indicator for subsequent analysis combined with the power-carbon function.

[0099] S32, calculating a first average slope of the first electro-carbon function and sub-slopes of adjacent electro-carbon-time coordinates.

[0100] Calculate the first average slope of the first electric-carbon function, which reflects the overall trend of the electric-carbon value changing over time during the entire preset time period. At the same time, calculate the sub-slopes of adjacent electric-carbon-time coordinates. The size of the sub-slope can intuitively reflect the severity of the change in the electric-carbon value in each small time period. The larger the sub-slope, the faster the carbon consumption in this time period increases, and the higher the carbon consumption. By calculating these slopes, we can have a more detailed understanding of the changing characteristics of electric-carbon data in different time periods, providing a strong basis for the subsequent formulation of segmentation standards.

[0101] S33, obtaining a segmentation standard based on the generation and storage participation coefficient and the first average slope, and obtaining a first segmentation function set and a second segmentation function set according to the segmentation standard.

[0102] This step is a key step for determining the segmentation standard based on the generation and storage participation coefficient and the first average slope, and obtaining the first segmentation function set and the second segmentation function set accordingly.

[0103] In some embodiments, obtaining a segmentation standard based on the emission and storage participation coefficient and the first average slope, and obtaining a first segmentation function set and a second segmentation function set according to the segmentation standard include:

[0104] S331, the power generation and storage participation coefficient is normalized based on the normalized value to obtain a first normalized value, and the standard adjustment value is subtracted from the first normalized value to obtain an actual adjustment value.

[0105] Normalization is a common data processing method, which maps the different ranges of the participation coefficients of the power generation and storage to a specific interval, which is convenient for subsequent comprehensive analysis with other parameters. For example, suppose the power generation and storage participation coefficient is normalized to the interval of 0-1. Then, the actual adjustment value is obtained by subtracting the first normalized value from the standard adjustment value. The standard adjustment value is a fixed value set according to actual application requirements and experience, which is used to adjust the strictness of the segmentation standard.

[0106] S332: Multiply the actual adjustment value by the first average slope to obtain a threshold slope, and use the threshold slope as a segmentation standard.

[0107] Among them, the first average slope reflects the overall trend of the electric carbon value of the first electric carbon function changing over time during the entire preset time period. This threshold slope plays a key role in judging the change in carbon consumption and determining the set of piecewise functions. The higher the slope, the greater the change in the electric carbon value per unit time, which means more carbon is used. From the perspective of energy management, when the carbon consumption is large, it is necessary to increase the participation of new energy (the company's new energy equipment) to optimize the energy structure and reduce carbon consumption. The larger the threshold slope, the greater the adjustment of the energy supply and carbon emission control strategy. By using the threshold slope as the segmentation standard, the function segments corresponding to the time periods with large carbon consumption can be screened out.

[0108] S333, extracting all segments of the first electro-carbon function whose slope is greater than the threshold value to obtain a corresponding first piecewise function set, and determining a second piecewise function set based on the first piecewise function set.

[0109] The determining of the second piecewise function set based on the first piecewise function set includes:

[0110] S3331, extract all the piecewise functions in the first piecewise function set to obtain multiple piecewise times.

[0111] Extract all the segments in the first electric-carbon function whose slope is greater than the threshold slope. The time periods corresponding to these segments are the periods with relatively large carbon consumption. These segments constitute the corresponding first piecewise function set. For example, in the first electric-carbon function, by calculating and comparing the slope of each small segment, find the part whose slope is greater than the threshold slope calculated previously. Assume that the function segments correspond to time periods such as (3-5) hours and (10-11) hours. Extract these function segments to form the first piecewise function set. Then, extract multiple segmented times corresponding to all the piecewise functions in the first piecewise function set.

[0112] S3332, determining the interval segments corresponding to the segmented time in the second electric-carbon function to obtain a second segmented function set, wherein the second segmented function set includes a power generation function set and a power storage function set.

[0113] Since the second electric-carbon function includes the first power generation function and the first power storage function, the second piecewise function set includes the power generation function set and the power storage function set. For example, for the (3-5) hour segment in the first piecewise function set, find the corresponding (3-5) hour interval in the first power generation function of the second electric-carbon function, and assume that the power generation values ​​in this interval are 40 degrees, 45 degrees, and 50 degrees, respectively, which constitute a part of the power generation function set; find the corresponding (3-5) hour interval in the first power storage function, and assume that the power storage values ​​in this interval are 25 degrees, 28 degrees, and 30 degrees, respectively, which constitute a part of the power storage function set. By analogy, all the intervals corresponding to the segmented time are extracted from the first power generation function and the first power storage function, respectively, to form a complete second piecewise function set. In this way, through the segmentation standard determined based on the generation and storage participation coefficient and the slope of the electricity-carbon function, the first electricity-carbon function and the second electricity-carbon function are successfully segmented according to the changing characteristics of carbon consumption and generation and storage of electric energy, providing a clear data structure for subsequent collaborative processing and control strategy formulation, which helps to achieve more accurate electricity-carbon collaborative management.

[0114] S4: collaboratively process the first piecewise function set and the second piecewise function set to generate a collaborative data control strategy.

[0115] This step is to perform collaborative processing based on the first piecewise function set and the second piecewise function set generated previously to generate a collaborative data control strategy.

[0116] In some embodiments, the collaborative processing of the first piecewise function set and the second piecewise function set to generate a collaborative data control strategy includes:

[0117] S41, determining the second piecewise function corresponding to each first piecewise function, extracting the power generation consumption and power storage corresponding to the second piecewise function, and adding the power generation consumption and power storage to obtain the total power generation.

[0118] In this step, it is necessary to establish the correspondence between the first piecewise function set and the second piecewise function set. Since the first piecewise function set represents the electric-carbon function part corresponding to the time period with a large carbon consumption, the second piecewise function set reflects the power generation and storage of the power generation and storage equipment in the same time period. For example, in a certain energy management system, a piecewise function in the first piecewise function set corresponds to a time interval of (9-11) hours. Find the corresponding power generation function segment and power storage function segment in the second piecewise function set. Then, extract the power generation consumption (i.e., the power directly put into use after power generation) and power storage (the power stored after power generation without immediate consumption) corresponding to the second piecewise function. Assume that in the interval of (9-11) hours, the power generation function segment shows that the power generation consumption is 25 degrees per hour, a total of 50 degrees in two hours; the power storage function segment shows that the power storage is 15 degrees per hour, a total of 30 degrees in two hours. Add the power generation consumption and the power storage to get the total power generation, i.e., 50+30=80 degrees. This calculation result comprehensively considers the electricity output of power generation and energy storage during that specific time period, providing key basic data for subsequent energy regulation operations.

[0119] S42, extracting the rated discharge capacity of the power storage device and adding it to the total power generation to obtain a total regulated power, and making the total regulated power correspond to the first piecewise function.

[0120] Each energy storage device has its own specific rated discharge capacity, which is a fixed value determined by the design specifications and performance parameters of the device. Extract the rated discharge capacity of the energy storage device, for example, the rated discharge capacity of a certain energy storage device is 40 degrees. Add the rated discharge capacity to the total power generation calculated previously to obtain the total regulated power, that is, 80+40=120 degrees. Next, establish a close correspondence between the total regulated power and the corresponding first piecewise function (here is the first piecewise function corresponding to (9-11) hours). This correspondence makes it possible to clearly identify the power resources that can be used for regulation when energy is allocated for time periods with large carbon consumption in the future. Through this operation, a clear basis for power allocation is provided for the entire energy management system, ensuring that the power generation, storage and discharge capacity of the storage equipment can be reasonably utilized during critical time periods.

[0121] S43, determining a second time period in the future corresponding to the first preset time period, and determining a second time sub-segment corresponding to the second time period in the first segmentation function.

[0122] First, determine the second time period in the future that corresponds to the first preset time period. The first preset time period is a basic time range set at the beginning of the entire data processing process, for example, it can be one day (0:00-24:00). The second time period is a specific time period in the future determined based on the actual application scenario and energy management requirements, assuming it is (10-12) hours. Then, determine the second time sub-segment corresponding to the second time period in the first segmented function. If there is a segmented function with a time interval of (10-12) hours in the first segmented function set, then the part of this segmented function corresponding to (10-12) hours is the second time sub-segment we want to determine.

[0123] S44, when it is determined that the second time sub-segment has been reached, the total regulated power is mobilized to supply power to the load or the regulated power corresponding to the value of the power required by the load is mobilized to supply power.

[0124] When it is judged that the second time sub-segment has been reached, the actual power supply operation link will be entered. At this time, the system will determine the power supply mode according to the actual power demand of the load. If the power required by the load in this time period is less than or equal to the total regulated power, the total regulated power can be directly mobilized to supply power to the load. For example, the power required by the load in (10-12) hours is 100 degrees, and the total regulated power corresponding to this time period calculated above is 120 degrees. At this time, the system can directly supply these 120 degrees of electricity to the load to meet its power demand. If the power required by the load exceeds the total regulated power, the system will mobilize the regulated power corresponding to the value of the power required by the load for power supply. This flexible power supply control method is based on the collaborative analysis results of electric carbon data and power generation and storage data. It can reasonably allocate energy according to actual conditions, while meeting the power demand of the load, maximizing energy utilization efficiency and reducing carbon emissions, thereby effectively achieving the goal of electric carbon collaborative management and providing strong support for sustainable energy development.

[0125] In the above embodiment, it also includes:

[0126] A1. After determining that the power supply in the second time period is completed, obtain a third electric-to-carbon function that has actually occurred in the second time period, where the third electric-to-carbon function is a function generated by functionalizing the electric-to-carbon data according to the time dimension in the second time period.

[0127] After the power supply of the second time period is completed, the server starts to obtain the third electric carbon function that has actually occurred in the time period. The generation method of this function is similar to the first electric carbon function. For example, at intervals of 1 hour, the electric carbon value corresponding to each time point in the time period is obtained, and a coordinate system is constructed. After steps such as coordinate extraction and zeroing processing (if necessary), the third electric carbon function is generated.

[0128] A2: If the maximum value of the third electric-carbon function is less than or equal to the maximum value of the first electric-carbon function, the normalized value is not adjusted.

[0129] The maximum value of the third electric-carbon function is compared with the maximum value of the first electric-carbon function. If the maximum value of the third electric-carbon function is less than or equal to the maximum value of the first electric-carbon function, it means that the actual carbon consumption is well controlled during the second time period. At this time, there is no need to adjust the normalized value because the current energy management strategy performs well in controlling carbon consumption.

[0130] A3, if the maximum value of the third electric-carbon function is less than the maximum value of the first electric-carbon function, the normalized value is increased to reduce the first normalized value, so as to realize re-training of the regularization processing model.

[0131] If the maximum value of the third electric-carbon function is less than the maximum value of the first electric-carbon function, for example, the maximum value of the third electric-carbon function is 140 and the maximum value of the first electric-carbon function is 130, it means that the carbon consumption in the second time period exceeds expectations and the system needs to be optimized.

[0132] In some embodiments, if the maximum value of the third electric-carbon function is less than the maximum value of the first electric-carbon function, the normalized value is adjusted up to reduce the first normalized value, including:

[0133] B1, calculating the absolute value of the difference between the maximum value of the third electric-carbon function and the maximum value of the first electric-carbon function.

[0134] First, the absolute value of the difference between the maximum value of the third electric-carbon function and the maximum value of the first electric-carbon function is calculated. The larger the absolute value, the larger the corresponding adjustment range.

[0135] B2, the absolute value is divided by the standard value and then weighted and added to the original normalized value to obtain the normalized value after the regularization processing model is adjusted up.

[0136] By adjusting the normalized value in this way, the first normalized value of the subsequent calculation of the power generation and storage participation coefficient will change accordingly, which will in turn affect the determination of the segmentation standard and the output of the entire regularization processing model, thereby achieving re-training of the regularization processing model so that it can better adapt to actual electricity consumption and carbon emissions, and optimize energy management and carbon emission control strategies.

[0137] This embodiment provides an electronic device including: a processor and a memory; wherein:

[0138] Memory is used to store computer programs. The memory can also be flash memory.

[0139] The processor is used to execute the execution instructions stored in the memory to implement each step in the above method. For details, please refer to the relevant description in the previous method embodiment.

[0140] Optionally, the memory can be independent or integrated with the processor.

[0141] When the memory is a device independent of the processor, the electronic device may further include:

[0142] A bus is used to connect the memory and the processor.

[0143] This embodiment further provides a readable storage medium, in which a computer program is stored. When at least one processor of an electronic device executes the computer program, the electronic device executes the methods provided in the above-mentioned various implementation modes.

[0144] This embodiment also provides a program product, which includes a computer program stored in a readable storage medium. At least one processor of the electronic device can read the computer program from the readable storage medium, and at least one processor executes the computer program so that the electronic device implements the methods provided in the above various embodiments.

[0145] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the claims.

[0146] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. The electric-carbon collaborative data processing method is characterized by: include: Extracting the electric carbon data of the electric carbon meter within a first preset time period, and generating a first electric carbon function after functional processing of the electric carbon data based on the time dimension; Extract the power generation and storage data of the power generation and storage device in the first preset time period, and generate a second electric carbon function after functional processing of the power generation and storage data based on the time dimension; Based on the pre-trained regularization processing model, the first electric-carbon function and the second electric-carbon function are respectively regularized and analyzed to generate a first piecewise function set and a second piecewise function set of multiple corresponding time periods, including: The regularization processing model obtains the total power consumption, total power generation consumption and total power storage in the first preset time period, and calculates the power generation and storage participation coefficient in the first preset time period; Calculating a first average slope of a first electro-carbon function and adjacent sub-slopes of the electro-carbon-time coordinate; A segmentation standard is obtained based on the generation and storage participation coefficient and the first average slope, and a first segmentation function set and a second segmentation function set are obtained according to the segmentation standard; The first piecewise function set and the second piecewise function set are collaboratively processed to generate a collaborative data control strategy, including: Determine the second piecewise function corresponding to each first piecewise function, extract the power generation consumption and power storage corresponding to the second piecewise function, and add the power generation consumption and power storage to obtain the total power generation; Extract the rated discharge capacity of the power storage device and add it to the total power generation to obtain the total regulated power, and correspond the total regulated power to the first piecewise function; Determine a second time period in the future corresponding to the first preset time period, and determine a second time sub-segment corresponding to the second time period in the first segmentation function; When it is determined that the second time sub-segment has been reached, the total regulated power is mobilized to supply power to the load or the regulated power corresponding to the value of the power required by the load is mobilized to supply power.

2. The method according to claim 1, characterized in that The step of extracting the electric carbon data of the electric carbon meter within the first preset time period and generating a first electric carbon function after functional processing of the electric carbon data based on the time dimension includes: Obtaining the carbon data of a first preset time period, and establishing an initial coordinate system with the horizontal axis representing time and the vertical axis representing carbon value; Extracting the coordinates of the electric carbon data of the first preset time period, and performing multi-dimensional zeroing processing based on the attributes of the electric carbon data to obtain the electric carbon-time coordinates after zeroing processing; Determine all the electron-carbon-time coordinates in the coordinate system and generate the first electron-carbon function.

3. The method according to claim 2, characterized in that The extracting the coordinates of the electric carbon data of the first preset time period and performing multi-dimensional zeroing processing based on the attributes of the electric carbon data to obtain the electric carbon-time coordinates after zeroing processing includes: Extracting time points within a first preset time period at preset time intervals to obtain a plurality of time reference coordinates, wherein the time reference coordinates are one-dimensional coordinates; Determine the electric carbon data corresponding to each time reference coordinate to obtain the electric carbon-time coordinate, wherein the electric carbon-time coordinate is a two-dimensional coordinate; The farthest electric carbon-time coordinate is extracted as the zeroing reference coordinate, and all the electric carbon-time coordinates are subtracted from the zeroing reference coordinate to obtain the electric carbon-time coordinate after zeroing.

4. The method according to claim 1, characterized in that: The step of extracting the power generation and storage data of the power generation and storage device in the first preset time period, and generating a second electric-carbon function after functional processing of the power generation and storage data based on the time dimension, includes: Acquire the power generation and storage data of the first preset time period, and establish an initial coordinate system with the horizontal axis as time and the vertical axis as power value; Extracting the coordinates of the power generation and storage data in the first preset time period, and performing multi-dimensional zeroing processing based on the attributes of the power generation and storage data to obtain power generation-time coordinates and power storage-time coordinates after the zeroing processing; Determine all power generation-time coordinates and power storage-time coordinates in the coordinate system and generate a first power generation function and a first power storage function. The second electric-carbon function includes the first power generation function and the first power storage function.

5. The method according to claim 1, characterized in that The calculating of the generation and storage participation coefficient within the first preset time period includes: The total power generation consumption is weighted based on the power generation consumption weight to obtain a first weighted value, the total storage capacity is weighted based on the storage capacity weight to obtain a second weighted value, and the sum of the first weighted value and the second weighted value is calculated to obtain a numerator weighted value; The total power generation consumption is weighted based on the power consumption weight to obtain the parent-child weighted value, and the numerator weighted value is divided by the denominator weighted value to obtain the power generation and storage participation coefficient.

6. The method according to claim 1, characterized in that The step of obtaining a segmentation standard based on the generation and storage participation coefficient and the first average slope, and obtaining a first segmentation function set and a second segmentation function set according to the segmentation standard, comprises: The first normalized value is obtained after normalizing the participation coefficient of the production and storage based on the normalized value, and the actual adjustment value is obtained by subtracting the first normalized value from the standard adjustment value; Multiplying the actual adjustment value by the first average slope to obtain a threshold slope and use it as a segmentation standard; All segments of the first electro-carbon function having a slope greater than the threshold value are extracted to obtain a corresponding first piecewise function set, and a second piecewise function set is determined based on the first piecewise function set.

7. The method according to claim 6, characterized in that The determining a second piecewise function set based on the first piecewise function set comprises: Extracting all the piecewise functions in the first piecewise function set to obtain a plurality of piecewise times; The interval segments corresponding to the segmented time in the second electric-carbon function are determined to obtain a second segmented function set, wherein the second segmented function set includes a power generation function set and a power storage function set.

8. The method according to claim 1, characterized in that Also includes: After determining that the power supply in the second time period is completed, obtaining a third electric-carbon function that has actually occurred in the second time period, wherein the third electric-carbon function is a function generated by functionalizing the electric-carbon data in the second time period according to the time dimension; If the maximum value of the third electric-carbon function is less than or equal to the maximum value of the first electric-carbon function, the normalized value is not adjusted; If the maximum value of the third electric-carbon function is less than the maximum value of the first electric-carbon function, the normalized value is adjusted to reduce the first normalized value, so as to re-train the regularization processing model.

9. The method according to claim 8, characterized in that If the maximum value of the third electric-carbon function is less than the maximum value of the first electric-carbon function, the normalized value is adjusted to decrease the first normalized value, including: calculating the absolute value of the difference between the maximum value of the third electric-carbon function and the maximum value of the first electric-carbon function; The absolute value is divided by the standard value and then weighted and added to the original normalized value to obtain the normalized value after the regularization processing model is adjusted up.

10. An electronic device, characterized in that: include: processor; as well as, A memory, configured to store executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 9 by executing the executable instructions.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 9 when executed by a processor.

Images