Electric power and electric quantity balancing method and system based on dual-carbon target

Abstract

The invention relates to the technical field of data analysis, and discloses an electric power and electric quantity balancing method and system based on a dual-carbon target, and the method comprises the steps: obtaining multi-source electric power and electric quantity data, and extracting multi-source carbon emission data of the multi-source electric power and electric quantity data; constructing a multi-dimensional electric power and electric quantity function according to the multi-source carbon emission data and the multi-source electric power and electric quantity data; performing multi-target particle swarm optimization on the multi-dimensional power and electric quantity function based on a dual-carbon target constraint condition to obtain a target power and electric quantity balance function; performing carbon emission analysis on the multi-source electric power and electric quantity data according to the target electric power and electric quantity balance function to obtain predicted carbon emission data; constructing an electric power and electric quantity balance model according to the multi-source carbon emission data and the predicted carbon emission data, and generating an electric power and electric quantity scheduling scheme; and performing power and electric quantity balance on the power generation source by using the power and electric quantity scheduling scheme. According to the invention, the power and electric quantity balance optimization based on the dual-carbon target can be realized, and the power and electric quantity balance efficiency and accuracy can be improved.

Description

Technical Field

[0001] This invention relates to the field of data analysis technology, and in particular to a power balance method and system based on dual carbon targets. Background Technology

[0002] With the deepening implementation of the dual carbon goals of "peak carbon and carbon neutrality," the green and low-carbon transformation of the power industry, as a major source of carbon emissions, has become an inevitable requirement. Traditional power systems rely heavily on fossil fuel power generation, resulting in persistently high carbon emissions. Therefore, under the constraints of these dual carbon goals, the power industry must accelerate its transformation towards cleaner and lower-carbon practices to achieve coordinated development of power balance and carbon emission control.

[0003] However, under the rigid constraints of dual-carbon objectives, traditional power balance models mostly treat carbon emissions as an external constraint or ex-post evaluation indicator, rather than a core optimization objective on par with generation costs and system reliability. This results in power balance models generating dispatch schemes that are economically optimal but may not be low-carbon or even high-carbon, thus failing to proactively respond to and support the achievement of dual-carbon objectives.

[0004] Meanwhile, power balance under dual-carbon objectives is essentially a complex multi-objective optimization problem that requires balancing economy, security, and low carbon emissions. Existing methods often employ simple linear programming or tighten constraints, which fail to accurately reflect the competition and trade-offs between multiple objectives and cannot find the optimal solution that satisfies different objectives. This limits the flexibility and scientific rigor of scheduling strategies.

[0005] In summary, how to achieve optimal power balance based on dual-carbon objectives and improve the efficiency and accuracy of power balance has become an urgent problem to be solved. Summary of the Invention

[0006] This invention provides a power balance method based on dual carbon objectives, the main purpose of which is to solve the problems of how to achieve optimal power balance based on dual carbon objectives and the low efficiency and accuracy of power balance.

[0007] In a first aspect, to achieve the above objectives, the present invention provides an electricity balance method based on a dual-carbon objective, comprising: Acquire multi-source power data from multiple power sources and extract corresponding multi-source carbon emission data from the multi-source power data; A multi-dimensional power function of the power source is constructed based on the multi-source carbon emission data and the multi-source power consumption data. Based on the predetermined dual-carbon objective constraints, the multi-dimensional power-to-energy function is subjected to multi-objective particle swarm optimization to obtain the objective power-to-energy balance function. Carbon emission analysis is performed on the multi-source power data based on the target power balance function to obtain predicted carbon emission data. A power balance model is constructed based on the multi-source carbon emission data and the predicted carbon emission data, and a power dispatching scheme is generated based on the power balance model. The power dispatching scheme is used to balance the power of multiple power sources, and target power data is collected based on the power sources after power balance.

[0008] Secondly, the present invention also provides a power balance system based on dual carbon targets, the system comprising: The data extraction module is used to acquire multi-source power data from multiple power sources and extract the corresponding multi-source carbon emission data from the multi-source power data. The function construction module is used to construct a multi-dimensional power function of the power source based on the multi-source carbon emission data and the multi-source power data. The function optimization module is used to perform multi-objective particle swarm optimization on the multi-dimensional power-to-energy function based on predetermined dual-carbon objective constraints, so as to obtain the target power-to-energy balance function. The function prediction module is used to perform carbon emission analysis on the multi-source power data according to the target power balance function to obtain predicted carbon emission data. The model generation module is used to construct a power balance model based on the multi-source carbon emission data and the predicted carbon emission data, and to generate a power dispatching scheme based on the power balance model. The data balancing module is used to balance the power of multiple power sources using the power dispatching scheme, and to collect target power data based on the power sources after power balancing.

[0009] This invention achieves efficient correlation between multi-source power consumption data and carbon emissions through automated processes, significantly improving the intelligence level of power consumption management. It also eliminates manual processing errors, improves data processing efficiency, and ensures the real-time and accuracy of carbon emission calculation results. By constructing a multi-dimensional function, it can automatically correlate power consumption data and carbon emission data, uncovering hidden correlation features in multi-source heterogeneous data and providing data support for subsequent scheduling decisions. By directly embedding constraints such as total carbon emissions and intensity into the model, it can accurately match dual-carbon objectives with power demand, while balancing multiple objective conflicts and improving the efficiency of subsequent power consumption balancing. Carbon emission analysis based on the target power consumption balancing function for multi-source power consumption data significantly reduces manual intervention and the risk of data error propagation, ensuring the deviation rate of predicted carbon emission data. The power consumption balancing model constructed based on multi-source carbon emission data and predicted carbon emission data allows for in-depth analysis of predicted carbon emission data, accurately grasping carbon emission trends. The final generated power consumption scheduling scheme can be automatically executed and monitored in real time using a computer system, greatly improving scheduling efficiency and accuracy, and simultaneously enhancing the efficiency and accuracy of power consumption balancing. Attached Figure Description

[0010] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is a flowchart illustrating an embodiment of the present invention of an electricity balance method based on dual carbon targets; Figure 2 A schematic diagram of a power balance system based on dual carbon targets is provided in an embodiment of the present invention. The objectives, features, and advantages of this invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0012] To enable those skilled in the art to better understand the technical solutions of this disclosure, and to fully understand and implement the process of how this disclosure applies technical means to solve technical problems and achieve corresponding technical effects, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, not all embodiments. The embodiments of this disclosure and the various features within them can be combined with each other without conflict, and the resulting technical solutions are all within the protection scope of this disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort should fall within the protection scope of this disclosure.

[0013] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0014] This application provides a power balance method based on dual-carbon targets. This method can be executed by software or hardware installed on terminal or server devices. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be a standalone server or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and demand forecasting platforms.

[0015] Reference Figure 1 The diagram shown is a flowchart illustrating a power balance method based on dual carbon targets according to an embodiment of the present invention. In this embodiment, the power balance method based on dual carbon targets includes: S1. Obtain multi-source power data from multiple power sources and extract the corresponding multi-source carbon emission data from the multi-source power data.

[0016] In this embodiment of the invention, the multi-source power data refers to power production and power consumption data from multiple power sources of different power generation methods (such as thermal power, hydropower, wind power, photovoltaic, etc.), including power generation, power consumption, load curves, etc.; the multi-source carbon emission data refers to greenhouse gas emission data related to power production, including direct emissions (such as fossil fuel combustion) and indirect emissions (such as emissions implied by purchased electricity).

[0017] In this embodiment of the invention, extracting the corresponding multi-source carbon emission data from the multi-source electricity data includes: The multi-source power data is converted to a standardized power data format. Extract the power source identifier from the standardized power consumption data; The target carbon emission factor corresponding to the standardized electricity data is obtained by matching and searching the preset carbon emission factor database according to the electricity source identifier. Calculate the total power generation of the standardized power data, and multiply the total power generation with the corresponding target carbon emission factor to obtain the multi-source carbon emission data corresponding to the multi-source power data.

[0018] In this embodiment of the invention, an XML / JSON parser (such as Python's ElementTree or json library) can be used to parse multi-source power consumption data to identify the field hierarchy structure of the multi-source power consumption data; the timestamp field in the field hierarchy structure is extracted, and the timestamp field is uniformly processed, converting formats such as "2023-01-01 08:00:00" into the ISO 8601 standard format to obtain standardized power consumption data.

[0019] Among these methods, the "generation type" or "energy type" field is located from standardized power generation data. This field typically contains text descriptions (such as "coal-fired" or "hydropower") or codes (such as "COAL" or "HYDRO"). For the text description field, keyword matching (such as Python's in operator) or natural language processing (NLP) techniques (such as matching a keyword library after word segmentation) are used to identify the power source identifier.

[0020] Furthermore, the carbon emission factor database includes fields such as power generation type, region, time range, carbon emission factor value, and data source. Among them, an index is created for the power generation type field to accelerate matching queries. Based on the index, precise matching is performed first by “power generation type + region + time range”. If no match is found, the conditions are relaxed to obtain the target carbon emission factor.

[0021] Specifically, the power generation data is grouped by power generation type or data source, and the power generation field of the standardized power generation data is summed (e.g., SQL's GROUP BY power generation type SUM(power generation)). At the same time, the time granularity (e.g., hourly data) is rolled up to calculate the total daily / monthly / yearly power generation. The total power generation (unit: megawatt-hour) is multiplied by the carbon emission factor (unit: tons of carbon dioxide / megawatt-hour) to obtain multi-source carbon emission data (unit: tons of carbon dioxide).

[0022] In this embodiment of the invention, an automated process is used to achieve efficient correlation between multi-source power consumption data and carbon emissions, which significantly improves the intelligence level of power consumption management, eliminates manual sorting errors, and improves data processing efficiency. Secondly, the carbon emission factor database matching mechanism based on distributed index avoids the delays and errors of manual table lookup in traditional methods, ensuring the real-time performance and accuracy of carbon emission calculation results.

[0023] S2. Construct a multi-dimensional power function for the power source based on the multi-source carbon emission data and the multi-source power consumption data.

[0024] In this embodiment of the invention, the multi-dimensional power generation function refers to a functional relationship constructed through mathematical modeling using multi-source power generation data and multi-source carbon emission data as inputs. It is used to describe the power generation characteristics of power sources under different dimensions (such as time, space, power generation type, and carbon emission intensity). The multi-dimensional power generation function can output key indicators such as power generation efficiency, carbon emission trends, and power generation optimization suggestions.

[0025] In this embodiment of the invention, constructing a multi-dimensional power function for the power source based on the multi-source carbon emission data and the multi-source power consumption data includes: The multi-source carbon emission data and the multi-source electricity consumption data are timestamped to obtain an aligned carbon-electricity dataset. Extract multi-dimensional indicators from the aligned carbon electricity dataset, and divide the aligned carbon electricity dataset according to the multi-dimensional indicators to obtain multiple dimensional carbon electricity datasets corresponding to the multi-dimensional indicators. Extract the dimensional features of the dimensional carbon electricity dataset, and calculate the correlation strength between the dimensional feature datasets based on the dimensional features; The correlation strength is compared with a preset correlation threshold, and dimensional feature data with a correlation strength greater than the correlation threshold are selected. Use the selected dimensional feature data as the target feature data; A multi-dimensional power consumption function is constructed based on the target feature data and preset weighting coefficients.

[0026] In this embodiment of the invention, time field parsing is performed on multi-source carbon emission data and multi-source electricity consumption data. The data is uniformly converted into a standard time format (such as ISO 8601) using a time parsing library (such as Python's datetime module). For data with missing timestamps, interpolation is performed to supplement the missing timestamps based on the data generation logic (such as log recording intervals) or the time difference between adjacent records to obtain the corresponding supplementary data.

[0027] Specifically, the minimum time granularity (e.g., hour, minute) of the supplementary data is determined, low-frequency data (e.g., daily data) is split into time windows, and high-frequency data (e.g., second-level data) is aggregated and downsampled. A sliding window algorithm is used to ensure that carbon emission data and electricity consumption data match within the same time interval (e.g., aligning 15-minute-level electricity consumption data with hourly-level carbon emission data to the hourly granularity). Based on the timestamp field, carbon emission data and electricity consumption data are associated through a hash table or database index (e.g., SQL JOIN operation) to generate an aligned carbon-electricity dataset containing electricity consumption, carbon emissions, and timestamps.

[0028] Furthermore, the multi-dimensional indicators include time dimension, spatial dimension, energy type dimension, and operational status dimension. Using grouping and aggregation techniques (such as SQL's GROUP BY or Pandas' groupby), the aligned carbon electricity dataset is sliced ​​according to the multi-dimensional indicators to obtain the dimensional carbon electricity dataset. For each dimensional carbon electricity dataset, statistical features and business features are extracted. The statistical features include mean, variance, maximum value, minimum value, median, etc. The business features include carbon emission intensity (carbon emissions / power generation), power generation efficiency (power generation / installed capacity), load factor (actual power generation / theoretical maximum power generation), etc.

[0029] In detail, correlation analysis methods (such as Pearson correlation coefficient and mutual information) are used to quantify the degree of association between dimensional features. For numerical features, their linear correlation is calculated (such as the positive correlation between power generation and carbon emissions). For categorical features (such as energy type), chi-square statistic or information gain is calculated to assess their weighting on carbon emissions.

[0030] In this process, dimensional features of different dimensions (such as electricity generation in megawatt-hours and carbon emissions in tons) are normalized (e.g., Z-score standardization) to avoid the influence of dimensional differences on the correlation strength calculation results; correlation thresholds are set according to business needs, for example: strong correlation: threshold set to 0.7 (Pearson coefficient), indicating a high degree of linear correlation; medium correlation: threshold set to 0.4-0.7; weak correlation: threshold set to 0.1-0.4.

[0031] Specifically, the correlation strength between all dimensional feature datasets is traversed, and dimensional feature data that meet the correlation threshold are selected (e.g., the correlation strength of "coal-fired power generation - carbon emissions" is 0.85 > 0.7). The selected dimensional feature data is then used as the target feature data. Weighting coefficients are set according to business priorities. For example, the weight of carbon emission intensity is set to 0.5 (reflecting environmental protection goals); the weight of power generation efficiency is set to 0.3 (reflecting economic efficiency); and the weight of load factor is set to 0.2 (reflecting operational stability).

[0032] Among them, a linear weighted model is adopted to combine the target feature data with weighting coefficients to generate a comprehensive multi-dimensional power function. Optionally, the weighting coefficients can be adjusted by grid search or Bayesian optimization to minimize the error between the multi-dimensional power function output (such as predicted carbon emissions) and the actual value.

[0033] In this embodiment of the invention, by constructing a multi-dimensional function, power generation data and carbon emission data can be automatically correlated, and the correlation features hidden in multi-source heterogeneous data (such as the positive correlation between power generation and carbon emissions from coal-fired power plants) can be mined, providing data support for subsequent scheduling decisions.

[0034] S3. Based on the predetermined dual-carbon objective constraints, perform multi-objective particle swarm optimization on the multi-dimensional power-to-energy function to obtain the objective power-to-energy balance function.

[0035] In this embodiment of the invention, the dual-carbon target constraints include: a maximum carbon emission limit: limiting the absolute value of carbon dioxide emissions during power generation (e.g., annual emissions ≤ X tons); carbon emission intensity constraints: limiting carbon emissions per unit of power generation (e.g., ≤ Y tons / MWh); renewable energy ratio requirements: specifying the minimum proportion of renewable energy power generation in total power generation (e.g., ≥ Z%); and energy structure adjustment targets: limiting the proportion of high-carbon energy (e.g., coal-fired power) and encouraging the development of low-carbon energy (e.g., wind power and photovoltaic power).

[0036] Multi-objective particle swarm optimization (MOPSO) is a heuristic algorithm based on swarm intelligence that finds the optimal solution by simulating the cooperative behavior of flocks of birds or schools of fish. It is used to simultaneously optimize multiple conflicting objectives (such as minimizing carbon emissions, maximizing power generation efficiency, and minimizing costs).

[0037] In this embodiment of the invention, the step of performing multi-objective particle swarm optimization on the multi-dimensional power-to-energy function based on predetermined dual-carbon objective constraints to obtain the target power-to-energy balance function includes: The dual-carbon target constraints are quantified to obtain a dual-carbon constraint index system; Based on the dual-carbon constraint index system, the parameters to be optimized for the multi-dimensional power function are determined, and the parameters to be optimized are weighted to obtain the weight parameters to be optimized. Multiple initial particle swarms are obtained, and the initial particle swarms are dimensionally aligned according to the parameters to be optimized to obtain the target particle swarm. Based on the target particle swarm, the multi-dimensional electrical quantity function is iteratively optimized to obtain particle velocity updates and particle position updates. The target optimized weight parameters are obtained by updating the particle velocity and particle position based on the particle velocity update and the particle position update. The multi-dimensional power balance function is optimized based on the target optimization weight parameters to obtain the target power balance function.

[0038] In detail, the particle velocity update is shown in the following formula:

[0039] in, Indicates the first The target particle Particle velocity update in the next iteration Indicates inertia weight, This represents the particle's own learning factor. Represents the particle swarm learning factor. Represents the random number of the particle itself. Represents a random number in a particle swarm. Indicates the first The target particle Particle velocity at the next iteration Indicates the first The target particle The particle's optimal position at the next iteration. Indicates the first The target particle The optimal position of the particle swarm in the next iteration.

[0040] In detail, the particle position update is shown in the following formula:

[0041] in, Indicates the first The target particle Particle position update in the next iteration Indicates the first The target particle Particle position at the next iteration Indicates the first The target particle Particle velocity update during the next iteration.

[0042] In this embodiment of the invention, dual carbon targets (such as total carbon emissions, carbon intensity, and the proportion of renewable energy consumption) are transformed into quantifiable mathematical indicators; for example: total carbon emissions = Σ(power generation of each power source type × carbon emission factor per unit of power generation), carbon intensity = total carbon emissions / total power generation.

[0043] In detail, parameters affected by dual carbon constraints are screened from multi-dimensional power functions (such as functions that include generation costs, grid losses, and reserve capacity), such as thermal power generation, wind / photovoltaic installed capacity, and energy storage configuration ratio; weights are automatically calculated based on data characteristics using entropy weight method or principal component analysis (PCA) to obtain the weight parameters to be optimized.

[0044] Furthermore, the parameters to be optimized are mapped to particle position vectors. For example, the particle dimension is set to [thermal power ratio, wind power ratio, energy storage capacity, ...]. All particle position vectors are then dimension-aligned to ensure that the dimensions of all particles are consistent with the parameters to be optimized, thus obtaining the target particle swarm.

[0045] Specifically, based on the iterative optimization of the multi-dimensional function by the target particle swarm, particle velocity updates and particle position updates are obtained. The velocity is adjusted according to the particle's own historical best position and the swarm's best position, for example, accelerating towards a better solution to avoid getting trapped in local optima. The particle position is adjusted according to the updated velocity, for example, by simulating the movement of particles in the search space, thereby obtaining the target optimization weight parameters.

[0046] In detail, the multi-dimensional power and energy function is optimized according to the target optimization weight parameters, that is, the weights are dynamically adjusted. For example, if carbon emissions exceed the standard, the weight of the carbon emission target is increased; if the cost is too high, the weight of the economic target is increased. The optimized weights and parameters are substituted into the multi-dimensional power and energy function to generate the target power and energy balance function.

[0047] In this embodiment of the invention, by directly embedding constraints such as total carbon emissions and intensity into the construction model, the dual carbon objectives and electricity demand can be accurately matched, while balancing the conflict of multiple objectives and improving the overall efficiency of the system. Through detailed modeling of multi-dimensional functions (such as time, space, and energy type), the optimization results are closer to the actual operating conditions, reducing long-term emission reduction costs and improving the efficiency of subsequent power balance.

[0048] S4. Perform carbon emission analysis on the multi-source power data according to the target power balance function to obtain predicted carbon emission data.

[0049] In this embodiment of the invention, the carbon emission analysis refers to the process of quantifying the emissions of greenhouse gases such as carbon dioxide generated during the operation of a power source based on a target power balance function and multi-source power data. The predicted carbon emission data refers to the predicted carbon emissions of the power source over a future period obtained by modeling and simulating multi-source power data using the target power balance function.

[0050] In this embodiment of the invention, the step of performing carbon emission analysis on the multi-source power data based on the target power balance function to obtain predicted carbon emission data includes: The carbon emission variable parameters are obtained by performing function analysis on the target power balance function; Construct carbon emission correlations based on the aforementioned carbon emission variable parameters; Based on the carbon emission correlation, the power flow data in the multi-source power data is determined using the target power balance function; A carbon emission calculation sub-model is constructed based on the power flow data and the carbon emission correlation. The carbon emission calculation sub-model was used to analyze the preliminary carbon emission data of the multi-source power generation data; The preliminary carbon emission data is corrected for network loss carbon emissions based on a preset carbon emission conversion factor to obtain the predicted carbon emission data.

[0051] In this embodiment of the invention, key parameters directly related to carbon emission calculation are extracted from the target power balance function, which can be achieved through function structure decomposition and variable attribute identification. The variable modules describing different power generation, power transmission, and power consumption stages in the target power balance function are identified. Then, the physical meaning of the variables in each module is analyzed one by one, and variables related to carbon emission generation or calculation are selected. The selected variables are then categorized and organized, and the carbon emission correlation dimension corresponding to each variable is clarified (e.g., thermal power output variables correspond to direct carbon emissions, and new energy output variables correspond to implicit carbon emissions), forming a complete set of carbon emission variable parameters.

[0052] Specifically, the study analyzes the impact path of each carbon emission variable parameter on carbon emissions. For example, the variables related to thermal power generation directly determine the carbon emissions generated by fuel combustion during thermal power production, while the variables related to new energy power generation affect the substitution of traditional thermal power, thus indirectly affecting carbon emissions. Then, in conjunction with the carbon emission accounting rules of the power industry, the study clarifies the quantitative correlation logic between different carbon emission variables and carbon emissions, such as "the higher the thermal power output, the higher the direct carbon emissions" and "the higher the proportion of new energy power output, the greater the carbon emission reduction generated by replacing thermal power." Finally, these logical relationships are sorted and integrated in a structured manner to form a clear carbon emission correlation, ensuring that targeted carbon emission analysis can be carried out based on this relationship system in the future.

[0053] Furthermore, based on the established carbon emission correlation, key power flow information is extracted from multi-source power data through the application of the target power balance function. The multi-source power data is then organized according to the input requirements of the target power balance function to ensure that the data format matches the variable input requirements of the function. Next, in conjunction with the carbon emission correlation, the types of power flow data that need to be obtained from the function output are identified. The multi-source power data is substituted into the target power balance function, and the power flow data corresponding to the carbon emission correlation is filtered out through function calculation to ensure that these data can accurately reflect the flow of electricity in each stage.

[0054] In detail, carbon emission calculation is divided into corresponding data sub-modules based on electricity flow data. Each sub-module corresponds to a carbon emission calculation for a specific electricity flow link. The carbon emission correlation is embedded in each sub-module, and the calculation logic and data transmission relationship of each sub-module are clarified. All sub-modules are integrated based on the calculation logic and data transmission relationship to form a logically coherent carbon emission calculation sub-model that covers the entire electricity flow link. This ensures that the model can output accurate carbon emission related results based on electricity flow data.

[0055] The multi-source power data is allocated according to the input requirements of each sub-module of the carbon emission calculation sub-model to ensure that each sub-module can obtain the corresponding power data. During the model calculation, the operating status of each sub-module is monitored in real time to ensure that there are no data anomalies or logical errors. After the calculation is completed, the carbon emission calculation results of each sub-module are collected and integrated into a total carbon emission data covering the entire power process and the carbon emission data of each process, forming preliminary carbon emission data.

[0056] Furthermore, the carbon emission conversion factor is used to quantify the carbon emission amount corresponding to a unit of network loss; the additional carbon emission amount corresponding to the preliminary carbon emission data is calculated by combining the preset carbon emission conversion factor; finally, the additional carbon emission amount is added to the preliminary carbon emission data to correct the preliminary carbon emission data, and at the same time, it is checked whether the corrected carbon emission data meets the integrity requirements of carbon emission accounting to ensure that there is no double counting or omission, and finally obtain accurate and comprehensive predicted carbon emission data.

[0057] In this embodiment of the invention, carbon emission analysis is carried out on multi-source power data based on the target power balance function, which greatly reduces the manual intervention process. Compared with the traditional manual statistical analysis method, it improves data processing efficiency, reduces the risk of data error transmission, and ensures the deviation rate of predicted carbon emission data.

[0058] S5. Construct a power balance model based on the multi-source carbon emission data and the predicted carbon emission data, and generate a power dispatching scheme based on the power balance model.

[0059] In this embodiment of the invention, the power balance model is a mathematical model constructed based on "multi-source carbon emission data" and "predicted carbon emission data" combined with the supply and demand relationship of power generation sources; the power dispatching scheme includes the output arrangement of various power generation sources, the charging and discharging strategy of energy storage devices, and the power transmission plan of cross-regional power grids.

[0060] In this embodiment of the invention, constructing an electricity balance model based on the multi-source carbon emission data and the predicted carbon emission data includes: A bias analysis is performed on the predicted carbon emission data to obtain the confidence interval of the predicted carbon emission data; A carbon emission deviation index is constructed based on the confidence interval and the multi-source carbon emission data; The preset power generation model is optimized based on the carbon emission deviation index to obtain an optimized power generation model. The optimized power generation model is analyzed based on pre-acquired historical power operation data, and the average percentage error of the optimized power generation model is calculated based on the results of the power generation analysis. Determine whether the average power percentage error is greater than a preset power error threshold; When the average percentage error of electricity consumption is greater than the electricity consumption error threshold, the electricity consumption model is fine-tuned to obtain an electricity consumption balance model. When the average percentage error of electricity consumption is greater than the electricity consumption error threshold, the optimized electricity consumption model is used as the electricity consumption balance model.

[0061] In this embodiment of the invention, multi-source carbon emission data (actual monitoring values) are combined, and the difference between the predicted data and the actual data is compared. The causes of the prediction deviation (such as parameter error and scenario assumption deviation) are analyzed based on the difference. The reasonable fluctuation range of the causes of the prediction deviation is defined by the deviation analysis method, that is, the confidence interval, to ensure that the confidence interval can cover the real carbon emission situation with a high probability.

[0062] In detail, using the confidence interval as a reference range and multi-source carbon emission data as the actual benchmark, indicators that can reflect the difference between predicted and actual carbon emissions are designed from dimensions such as the magnitude of deviation and the frequency of fluctuation. For example, by comparing the degree of fit between the two in the same time period, the difference characteristics are transformed into quantifiable indicators, providing a basis for model optimization.

[0063] In this process, carbon emission deviation indicators are integrated into a preset power generation model, and parameters related to carbon emissions (such as power output constraints and carbon emission control coefficients) in the power generation model are adjusted to adapt the power generation model to carbon emission deviation conditions. This corrects the logic in the original power generation model that does not match actual carbon emissions, resulting in an optimized power generation model.

[0064] Furthermore, historical power operation data (past power generation, load, etc.) is input into the optimized power generation model. The matching degree between the power generation results output by the optimized power generation model and the historical actual data is analyzed. Based on the difference between the two, the average percentage error of power generation, reflecting the prediction accuracy of the optimized power generation model, is calculated. The calculated average percentage error of power generation is compared with a preset threshold to determine whether the accuracy of the optimized power generation model meets the standard. If the error exceeds the threshold, it indicates that the optimized power generation model needs further adjustment; otherwise, the optimized power generation model can be preliminarily identified as qualified.

[0065] If the error exceeds the standard, the variable weights and constraint boundaries in the power generation model are slightly adjusted to address the source of the error (such as parameter settings and constraints), and the calculation logic of the power generation model is optimized until the error of the power generation model meets the requirements, thus obtaining the power generation balance model. If the error is within an acceptable range, it means that the optimized power generation model can accurately reflect the relationship between power generation and carbon emissions, and it is directly used as the final power generation balance model.

[0066] In this embodiment of the invention, generating a power dispatching scheme based on the power balance model includes: Obtain power load data within the target scheduling period, and divide the power load data into time-spatial dimensions to obtain time-slot and region-slot load demand data; The power balance model is used to calculate the preliminary power dispatch data for the target dispatch period based on the time-sharing and regional load demand data. An initial scheduling scheme is generated based on the preliminary power dispatch data, and the initial scheduling scheme is executed using a preset simulation system to obtain the initial simulation scheduling results. The initial simulation scheduling results are evaluated to obtain initial evaluation results; Based on the initial evaluation results, the initial scheduling scheme is optimized to obtain a power dispatching scheme.

[0067] In this embodiment of the invention, power load data within the target scheduling period is collected, covering electricity consumption data of different user types such as residential, industrial, and commercial users. From the time dimension, the data is split according to daily electricity consumption patterns (such as peak and valley periods). From the spatial dimension, the load data is mapped to each region according to the power grid supply area division. By removing abnormal data and supplementing missing data, the load demand data by time period and region is finally obtained, providing accurate load basis for subsequent scheduling calculations.

[0068] In detail, the load demand data by time period and region is input into the power balance model to analyze the power supply and demand situation in each region at different times, thereby determining the preliminary dispatch data that meets the load demand and the constraints, including the time-sharing output of each power source and the time-sharing transmission power between regions.

[0069] Based on the preliminary dispatch data, the dispatch instructions of each link are sorted out (such as the output value of a power plant at a certain time period, the transmission power of a transmission line at a certain time period) to form an initial dispatch plan; the plan is then imported into a preset simulation system, which simulates the actual power grid operating environment, restores the execution process of the dispatch plan, records data such as power grid frequency, voltage, and operating status of each power source at each time period, and generates initial simulation dispatch results to reflect the actual operating effect of the plan.

[0070] Furthermore, the initial simulation results are evaluated from multiple dimensions to determine whether power supply and demand are balanced, and whether there is a load deficit or power surplus; to check whether grid safety indicators (such as frequency and voltage) are within normal ranges; to verify whether carbon emissions meet the dual carbon constraints; and to calculate whether dispatch costs are reasonable. By comprehensively considering these dimensions, the feasibility and rationality of the initial plan are determined, resulting in an initial evaluation that includes both advantages and problems.

[0071] Specifically, based on the initial assessment results, the scheme is optimized to address existing problems (such as insufficient power supply in a certain area during a certain period or overload of a certain transmission line). If the power supply is insufficient, the output of relevant power sources is adjusted or cross-regional power transmission is increased. If the line is overloaded, the transmission power of the line is reduced and the load of other lines is redistributed. After optimization, the scheme is verified again through the simulation system until it meets the requirements of supply and demand balance, safety, and low carbon emissions, and finally the power dispatch scheme is obtained.

[0072] In this embodiment of the invention, optimizing the initial scheduling scheme based on the initial evaluation results to obtain a power dispatching scheme includes: Based on the initial evaluation results, the initial scheduling scheme is randomly perturbed to generate a neighborhood pre-scheduling scheme; Obtain the number of neighborhood transformations in the neighborhood pre-scheduling scheme, and determine the neighborhood transformation coefficients based on the number of neighborhood transformations; The neighborhood transformation coefficients are compared with a preset neighborhood transformation probability threshold to obtain the comparison result; Based on the comparison results, the initial scheduling scheme is optimized to obtain a power balance scheme.

[0073] In this embodiment of the invention, based on the initial evaluation results, the problems of the initial scheduling scheme are identified (such as regional power shortage or line overload during a certain period). Guided by these problems, the key scheduling parameters in the scheme (such as power output and cross-regional transmission power) are randomly adjusted in a small range. Through this perturbation, multiple neighborhood pre-scheduling schemes that are similar to the initial scheme but have slight differences are generated, providing alternative directions for subsequent optimization.

[0074] Specifically, during the process of generating neighborhood pre-scheduling schemes, the total number of times the initial scheme was adjusted (the number of neighborhood transformations) is counted to determine the neighborhood transformation coefficients that can reflect the rationality of the current neighborhood schemes. A preset neighborhood transformation probability threshold (set based on past optimization experience and power grid safety requirements) is retrieved, and the neighborhood transformation coefficients are compared with the threshold. If the coefficients meet the threshold range, it indicates that the diversity of neighborhood schemes meets the standard; if they do not meet the threshold, it indicates that the scheme adjustment is insufficient or excessive and further processing is required. Finally, a clear comparison result is obtained.

[0075] Furthermore, if the comparison results show that the coefficient meets the standard, a scheme that can solve the initial problem is selected from the neighborhood pre-scheduling schemes, and the details are fine-tuned in combination with safety, low carbon and economic requirements; if the coefficient does not meet the standard, the arrangement of the generated neighborhood scheme is returned, and finally the power balance scheme is obtained.

[0076] In this embodiment of the invention, an electricity balance model is constructed based on multi-source carbon emission data and predicted carbon emission data. This model allows for in-depth analysis of predicted carbon emission data, accurately grasping carbon emission trends. Simultaneously, through simulation technology, it can simulate the electricity balance state under different scheduling schemes, identify potential problems in advance, and make timely adjustments and optimizations. The final generated electricity scheduling scheme can be automatically executed and monitored in real time using a computer system, greatly improving scheduling efficiency and accuracy.

[0077] S6. Use the power dispatching scheme to balance the power of multiple power sources, and collect target power data based on the power sources after power balance.

[0078] In this embodiment of the invention, the power balance refers to the real-time monitoring of the actual power generation of each power source according to the output requirements of various power sources in the power dispatching scheme (such as the output range that thermal power needs to maintain and the maximum power that wind power needs to absorb). If a deviation occurs (such as insufficient output of wind power due to a sudden drop in wind speed), other power sources are adjusted through dispatching instructions (such as starting standby thermal power or calling energy storage to discharge) to make up for the shortfall. At the same time, it is ensured that the total power generation matches the real-time power load and grid loss, and finally the power balance is achieved.

[0079] In this embodiment of the invention, the step of using the power dispatching scheme to balance the power of multiple power sources includes: The power generation dispatch instruction is generated according to the power dispatch scheme; According to the scheduling instruction, the power generation source is scheduled to obtain the scheduled power generation source; Extract the actual frequency of the scheduled power source and calculate the frequency deviation between the actual frequency and the preset target frequency; An adjustment command is generated based on the frequency deviation, and the power balance of the scheduled power source is achieved according to the adjustment command.

[0080] In this embodiment of the invention, the power generation scheme requirements are transformed into specific and executable instructions by combining the type of each power source (such as thermal power, wind power, and photovoltaic) and its operating characteristics (such as the peak-shaving capacity of thermal power and the fluctuation of new energy output). For example, the output value of thermal power during a certain period and the compensation requirement for the fluctuation of wind power output are formed to create a scheduling instruction exclusive to each power source, ensuring that the instructions are in line with the actual operating capacity of the power source.

[0081] In detail, the generated scheduling instructions are sent to the control terminals of the corresponding power sources. During the scheduling process, the response of each power source is monitored in real time to ensure that the power sources strictly follow the instructions and ultimately form a scheduled power source that operates according to the scheduling requirements, laying the foundation for subsequent balance regulation.

[0082] Furthermore, the actual operating frequency of each dispatched power source after being connected to the power grid is collected in real time by the power grid frequency monitoring equipment. At the same time, the preset target frequency (set according to the power grid safety and stability operation standard to ensure the frequency benchmark when power supply and demand are balanced) is retrieved. The actual frequency is compared with the target frequency, the difference between the two is analyzed, and the frequency deviation is determined. This deviation can intuitively reflect the degree of matching between the current power generation output and the power grid load demand.

[0083] The supply and demand status is determined based on the frequency deviation. If the deviation indicates insufficient or excessive power supply, a targeted adjustment command is generated and sent to the dispatching power source. The output adjustment effect is tracked in real time until the actual frequency approaches the target frequency, thereby achieving power balance among multiple power sources.

[0084] In this embodiment of the invention, by determining the collection range, identifying the power sources that need to be monitored after power balance, locking in the key data items of each power source, such as actual output, running time, energy consumption, etc., starting the monitoring equipment, and capturing the operating data of each power source in real time through the sensors built into the power source or the power grid monitoring system, ensuring the continuity of data collection, while eliminating abnormal data in the collection process, comparing the data with the consistency of the state that should be reached after balance, ensuring data accuracy, and finally obtaining the target power data.

[0085] In this embodiment of the invention, relying on a computer-automated monitoring system, no manual intervention is required for power source data acquisition. The operating data of each power source after balancing can be synchronized in real time, which greatly shortens the data acquisition cycle, avoids the delay and error of manual acquisition, ensures data timeliness, and improves the efficiency and accuracy of power balance.

[0086] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0087] like Figure 2 The diagram shown is a functional block diagram of a power balance system based on dual carbon targets provided in an embodiment of the present invention.

[0088] This disclosure provides an electricity balance system based on dual carbon targets, which corresponds one-to-one with the electricity balance method based on dual carbon targets described in the previous embodiments. For example... Figure 2 As shown, the power balance system 100 based on dual carbon targets includes a data extraction module 101, a function construction module 102, a function optimization module 103, a function prediction module 104, a model generation module 105, and a data balancing module 106. Detailed descriptions of each functional module are as follows: Data extraction module 101 is used to acquire multi-source power data from multiple power sources and extract multi-source carbon emission data corresponding to the multi-source power data. Function construction module 102 is used to construct a multi-dimensional power function of the power source based on the multi-source carbon emission data and the multi-source power data; The function optimization module 103 is used to perform multi-objective particle swarm optimization on the multi-dimensional power-to-energy function based on the predetermined dual-carbon objective constraints, so as to obtain the objective power-to-energy balance function. The function prediction module 104 is used to perform carbon emission analysis on the multi-source power data according to the target power balance function to obtain predicted carbon emission data. The model generation module 105 is used to construct an electricity balance model based on the multi-source carbon emission data and the predicted carbon emission data, and to generate an electricity dispatching scheme based on the electricity balance model. The data balancing module 106 is used to balance the power of multiple power sources using the power dispatching scheme, and to collect target power data based on the power sources after power balancing.

[0089] In one embodiment, when the data extraction module 101 extracts the multi-source carbon emission data corresponding to the multi-source electricity data, it is used to: The multi-source power data is converted to a standardized power data. Extract the power source identifier from the standardized power consumption data; The target carbon emission factor corresponding to the standardized electricity data is obtained by matching and searching the preset carbon emission factor database according to the electricity source identifier. Calculate the total power generation of the standardized power data, and multiply the total power generation with the corresponding target carbon emission factor to obtain the multi-source carbon emission data corresponding to the multi-source power data.

[0090] In one embodiment, when the function construction module 102 executes the construction of a multi-dimensional power function of the power source based on the multi-source carbon emission data and the multi-source power data, it is used to: The multi-source carbon emission data and the multi-source electricity consumption data are timestamped to obtain an aligned carbon-electricity dataset. Extract multi-dimensional indicators from the aligned carbon electricity dataset, and divide the aligned carbon electricity dataset according to the multi-dimensional indicators to obtain multiple dimensional carbon electricity datasets corresponding to the multi-dimensional indicators. Extract the dimensional features of the dimensional carbon electricity dataset, and calculate the correlation strength between the dimensional feature datasets based on the dimensional features; The correlation strength is compared with a preset correlation threshold, and dimensional feature data with a correlation strength greater than the correlation threshold are selected. Use the selected dimensional feature data as the target feature data; A multi-dimensional power consumption function is constructed based on the target feature data and preset weighting coefficients.

[0091] In one embodiment, when the function optimization module 103 performs multi-objective particle swarm optimization on the multi-dimensional power-to-electricity function based on predetermined dual-carbon objective constraints to obtain the target power-to-electricity balance function, it is used to: The dual-carbon target constraints are quantified to obtain a dual-carbon constraint index system; Based on the dual-carbon constraint index system, the parameters to be optimized for the multi-dimensional power function are determined, and the parameters to be optimized are weighted to obtain the weight parameters to be optimized. Multiple initial particle swarms are obtained, and the initial particle swarms are dimensionally aligned according to the parameters to be optimized to obtain the target particle swarm. Based on the target particle swarm, the multi-dimensional electrical quantity function is iteratively optimized to obtain particle velocity updates and particle position updates. The target optimized weight parameters are obtained by updating the particle velocity and particle position based on the particle velocity update and the particle position update. The multi-dimensional power balance function is optimized based on the target optimization weight parameters to obtain the target power balance function.

[0092] In one embodiment, when the function prediction module 104 performs carbon emission analysis on the multi-source power data according to the target power balance function to obtain predicted carbon emission data, it is used to: The carbon emission variable parameters are obtained by performing function analysis on the target power balance function; Construct carbon emission correlations based on the aforementioned carbon emission variable parameters; Based on the carbon emission correlation, the power flow data in the multi-source power data is determined using the target power balance function; A carbon emission calculation sub-model is constructed based on the power flow data and the carbon emission correlation. The carbon emission calculation sub-model was used to analyze the preliminary carbon emission data of the multi-source power generation data; The preliminary carbon emission data is corrected for network loss carbon emissions based on a preset carbon emission conversion factor to obtain the predicted carbon emission data.

[0093] In one embodiment, the model generation module 105 constructs an electricity balance model based on the multi-source carbon emission data and the predicted carbon emission data, including: A bias analysis is performed on the predicted carbon emission data to obtain the confidence interval of the predicted carbon emission data; A carbon emission deviation index is constructed based on the confidence interval and the multi-source carbon emission data; The preset power generation model is optimized based on the carbon emission deviation index to obtain an optimized power generation model. The optimized power consumption model is analyzed based on the historical power operation data obtained in advance, and the average percentage error of the optimized power consumption model is calculated based on the results of the power consumption analysis. Determine whether the average power percentage error is greater than a preset power error threshold; When the average percentage error of electricity consumption is greater than the electricity consumption error threshold, the electricity consumption model is fine-tuned to obtain an electricity consumption balance model. When the average percentage error of electricity consumption is greater than the electricity consumption error threshold, the optimized electricity consumption model is used as the electricity consumption balance model.

[0094] In one embodiment, when the model generation module 105 generates a power dispatching scheme based on the power balance model, it is used to: Obtain power load data within the target scheduling period, and divide the power load data into time-spatial dimensions to obtain time-slot and region-slot load demand data; The power balance model is used to calculate the preliminary power dispatch data for the target dispatch period based on the time-sharing and regional load demand data. An initial scheduling scheme is generated based on the preliminary power dispatch data, and the initial scheduling scheme is executed using a preset simulation system to obtain the initial simulation scheduling results. The initial simulation scheduling results are evaluated to obtain initial evaluation results; Based on the initial evaluation results, the initial scheduling scheme is optimized to obtain a power dispatching scheme.

[0095] In one embodiment, when the model generation module 105 performs scheme optimization on the initial scheduling scheme based on the initial evaluation results to obtain a power dispatching scheme, it is used to: Based on the initial evaluation results, the initial scheduling scheme is randomly perturbed to generate a neighborhood pre-scheduling scheme; Obtain the number of neighborhood transformations in the neighborhood pre-scheduling scheme, and determine the neighborhood transformation coefficients based on the number of neighborhood transformations; The neighborhood transformation coefficients are compared with a preset neighborhood transformation probability threshold to obtain the comparison result; Based on the comparison results, the initial scheduling scheme is optimized to obtain a power balance scheme.

[0096] In one embodiment, when the data balancing module 106 performs power balancing on multiple power sources using the power dispatching scheme, it is configured to: The power generation dispatch instruction is generated according to the power dispatch scheme; According to the scheduling instruction, the power generation source is scheduled to obtain the scheduled power generation source; Extract the actual frequency of the scheduled power source and calculate the frequency deviation between the actual frequency and the preset target frequency; An adjustment command is generated based on the frequency deviation, and the power balance of the scheduled power source is achieved according to the adjustment command.

[0097] In this invention, the specific limitations of a power balance system based on dual-carbon targets can be found in the above-described limitations of a power balance method based on dual-carbon targets, and will not be repeated here. Each module in the aforementioned power balance system based on dual-carbon targets can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0098] In the embodiments provided by this invention, it should be understood that the disclosed system can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0099] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0100] Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within the invention. No appended diagram markings in the claims should be construed as limiting the scope of the claims.

[0101] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0102] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0103] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0104] In the embodiments provided in this disclosure, it should be understood that the disclosed systems and methods can also be implemented in other ways. The system embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0105] It should be noted that, in this disclosure, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element limited by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0106] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A power balance method based on dual carbon targets, characterized in that, The method includes: Obtain multi-source carbon emission data; Based on multi-source carbon emission data, a multi-dimensional electricity consumption function is constructed. Using the dual-carbon objective as a constraint, multi-objective particle swarm optimization is performed on the multi-dimensional power-to-energy function to obtain the target power-to-energy balance function; Carbon emission analysis is performed on the energy balance function to obtain predicted carbon emission data; A power balance model is constructed based on predicted carbon emission data to generate power dispatching schemes. The scheduling scheme is executed to achieve power balance among multiple power sources, and the target power data after balance is collected.

2. The power balance method based on dual-carbon targets as described in claim 1, characterized in that, The acquisition of multi-source carbon emission data includes: Standardize the multi-source power data to obtain standardized power data. Extract the power source identifier from standardized power consumption data; Based on the identifier matching the preset carbon emission factor database, the corresponding target carbon emission factor is obtained; Multi-source carbon emission data are calculated based on the total power generation and target carbon emission factor of standardized electricity data.

3. The power balance method based on dual carbon targets as described in claim 2, characterized in that, The construction of a multi-dimensional electricity consumption function based on multi-source carbon emission data includes: Timestamp alignment processing is performed on multi-source carbon emission data and multi-source electricity data to obtain an aligned carbon-electricity dataset. Multi-dimensional indicators are extracted from the aligned carbon electricity dataset, and the data is divided according to the multi-dimensional indicators to obtain a multi-dimensional carbon electricity dataset. Calculate the correlation strength between carbon electricity datasets of various dimensions, and filter out target feature data based on preset correlation thresholds; A multi-dimensional power consumption function is constructed based on the target feature data and preset weighting coefficients.

4. The power balance method based on dual-carbon targets as described in claim 1 or 3, characterized in that, The process of using a dual-carbon objective as a constraint to perform multi-objective particle swarm optimization on a multi-dimensional electricity-energy balance function yields the target electricity-energy balance function, including: The dual-carbon target constraints are quantified into an indicator system; Based on the indicator system, the parameters to be optimized for the multi-dimensional power consumption function are determined and weights are assigned. A multi-objective particle swarm optimization algorithm is used to iteratively optimize the parameters to be optimized, thereby obtaining the target optimization weight parameters. The multi-dimensional power balance function is optimized based on the target optimization weight parameters to obtain the target power balance function.

5. The power balance method based on dual-carbon targets as described in claim 1, characterized in that, Carbon emission analysis is performed on the aforementioned power balance function to obtain predicted carbon emission data, including: Determine the carbon emission correlation based on the target power balance function; A carbon emission calculation sub-model is constructed based on the aforementioned carbon emission correlations; Preliminary carbon emission data were obtained by analyzing multi-source electricity data using a carbon emission calculation sub-model. The preliminary carbon emission data is corrected for network loss carbon emissions to obtain the predicted carbon emission data.

6. The power balance method based on dual-carbon targets as described in claim 1, characterized in that, The electricity balance model constructed based on predicted carbon emission data includes: A carbon emission deviation index is constructed based on the confidence interval of predicted carbon emission data and multi-source carbon emission data. The electricity consumption model is optimized based on the carbon emission deviation index to obtain an optimized electricity consumption model. Calculate the average percentage error of the optimized power consumption model; The final power balance model is determined based on the comparison between the average percentage error of power consumption and the preset error threshold.

7. The power balance method based on dual carbon targets as described in claim 1, characterized in that, The production steps of the power dispatching scheme include: Obtain power load data for the target scheduling period and perform spatiotemporal partitioning to obtain load demand data; The preliminary scheduling data corresponding to the load demand data is calculated using the power balance model. An initial scheduling scheme is generated based on the preliminary scheduling data, and simulation results are obtained through simulation execution. The simulation results are evaluated, and the initial scheduling scheme is optimized based on the evaluation results to obtain the power dispatching scheme.

8. The power balance method based on dual carbon targets as described in claim 7, characterized in that, The process of optimizing the initial scheduling scheme based on the evaluation results to obtain a power dispatching scheme includes: Based on the initial evaluation results, the initial scheduling scheme is randomly perturbed to generate a neighborhood pre-scheduling scheme; The neighborhood transformation coefficients are determined based on the number of transformations in the neighborhood pre-scheduling scheme. The neighborhood transformation coefficients are compared with a preset threshold. The initial scheduling scheme is optimized based on the comparison results to obtain a power balance scheme.

9. The power balance method based on dual-carbon targets as described in claim 1, characterized in that, The execution scheduling scheme to achieve power balance among multiple power sources includes: Generate and execute dispatch instructions for power generation sources based on the power dispatching scheme; Obtain the actual frequency of the power source after scheduling, and calculate its frequency deviation from the target frequency; Adjustment commands are generated based on frequency deviation, and power balance is achieved by executing the adjustment commands.

10. A power balance system based on dual carbon targets, characterized in that, The system includes: The data extraction module is used to acquire multi-source carbon emission data; The function building module is used to construct multi-dimensional electricity and energy functions based on multi-source carbon emission data; The function optimization module is used to perform multi-objective particle swarm optimization on multi-dimensional electricity and energy functions under dual-carbon objectives to obtain the target electricity and energy balance function. The function prediction module is used to perform carbon emission analysis on the power balance function to obtain predicted carbon emission data. The model generation module is used to build an electricity balance model based on predicted carbon emission data and generate electricity dispatching schemes. The data balancing module is used to execute scheduling schemes to achieve power balance among multiple power sources and to collect the target power data after balancing.

Images