A power and electricity balance method and system based on a double carbon target

Abstract

The present application relates to the technical field of data analysis, and discloses a power and electricity balance method and system based on a double-carbon target, the method comprising: acquiring multi-source power and electricity data, and extracting multi-source carbon emission data of the multi-source power and electricity data; constructing a multi-dimensional power and electricity function according to the multi-source carbon emission data and the multi-source power and electricity data; performing multi-objective particle swarm optimization on the multi-dimensional power and electricity function based on double-carbon target constraint conditions to obtain a target power and electricity balance function; performing carbon emission analysis on the multi-source power and electricity data according to the target power and electricity balance function to obtain predicted carbon emission data; constructing a power and electricity balance model according to the multi-source carbon emission data and the predicted carbon emission data and generating a power and electricity dispatching scheme; and performing power and electricity balance on a power generation source by using the power and electricity dispatching scheme. The present application can realize optimal power and electricity balance based on a double-carbon target and improve power and electricity balance efficiency and accuracy.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data analysis, and in particular to a power and electricity balance method and system based on a double carbon target. BACKGROUND

[0002] With the deepening of the double carbon target of "carbon peak and carbon neutral", the green and low-carbon transformation of the power industry, as the main source of carbon emissions, has become an inevitable requirement. In the traditional power system, a large number of fossil energy power generation leads to high carbon emissions. Therefore, under the constraint of the double carbon target, the power industry must accelerate the transformation to clean and low-carbon, in order to realize the coordinated development of power and electricity balance and carbon emission control.

[0003] However, under the rigid constraint of the double carbon target, the traditional power and electricity balance model mostly takes carbon emissions as an external constraint or an ex post evaluation index, rather than a core optimization target parallel to generation cost and system reliability. This leads to the scheduling scheme generated by the power and electricity balance model being optimal in economy, but may not be low-carbon or even high-carbon, and thus cannot actively respond to and support the realization of the double carbon target.

[0004] At the same time, the power and electricity balance under the double carbon target is essentially a complex multi-objective optimization problem that needs to balance economy, safety and low carbon. Existing methods often use simple linear programming or tighten the constraint conditions, which is difficult to truly reflect the competition and trade-off relationship between multiple target requirements, and cannot find the optimal solution that meets different target requirements, thus limiting the flexibility and scientificity of the scheduling strategy.

[0005] In summary, how to realize the optimal power and electricity balance based on the double carbon target and improve the efficiency and accuracy of power and electricity balance has become a problem to be solved. SUMMARY

[0006] The present application provides a power and electricity balance method based on a double carbon target, which mainly aims to solve the problem of how to realize the optimal power and electricity balance based on the double carbon target and improve the efficiency and accuracy of power and electricity balance.

[0007] In the first aspect, to achieve the above-mentioned purpose, the present application provides a power and electricity balance method based on a double carbon target, comprising:

[0008] Obtaining multi-source power and electricity data of a plurality of power sources, and extracting corresponding multi-source carbon emission data from the multi-source power and electricity data;

[0009] Constructing a multi-dimensional power and electricity function of the power source according to the multi-source carbon emission data and the multi-source power and electricity data;

[0010] perform multi-objective particle swarm optimization on the multi-dimensional power and electricity function based on predetermined double carbon target constraint conditions to obtain a target power and electricity balance function;

[0011] perform carbon emission analysis on the multi-source power and electricity data according to the target power and electricity balance function to obtain predicted carbon emission data;

[0012] construct a power and electricity balance model according to the multi-source carbon emission data and the predicted carbon emission data, and generate a power and electricity dispatching scheme based on the power and electricity balance model;

[0013] balance power and electricity of the multiple power generation sources using the power and electricity dispatching scheme, and collect target power and electricity data according to the power generation sources after power and electricity balance.

[0014] In a second aspect, the present application further provides a power and electricity balance system based on a double carbon target, the system comprising:

[0015] a data extraction module configured to acquire multi-source power and electricity data of multiple power generation sources, and extract corresponding multi-source carbon emission data in the multi-source power and electricity data;

[0016] a function construction module configured to construct a multi-dimensional power and electricity function of the power generation sources according to the multi-source carbon emission data and the multi-source power and electricity data;

[0017] a function optimization module configured to perform multi-objective particle swarm optimization on the multi-dimensional power and electricity function based on predetermined double carbon target constraint conditions to obtain a target power and electricity balance function;

[0018] a function prediction module configured to perform carbon emission analysis on the multi-source power and electricity data according to the target power and electricity balance function to obtain predicted carbon emission data;

[0019] a model generation module configured to construct a power and electricity balance model according to the multi-source carbon emission data and the predicted carbon emission data, and generate a power and electricity dispatching scheme based on the power and electricity balance model;

[0020] a data balance module configured to balance power and electricity of the multiple power generation sources using the power and electricity dispatching scheme, and collect target power and electricity data according to the power generation sources after power and electricity balance.

[0021] The application realizes efficient association of multi-source power electricity data and carbon emissions through an automated process, significantly improving the intelligent level of power electricity management, eliminating manual sorting errors, improving data processing efficiency, and ensuring the real-time and accuracy of carbon emission calculation results; by constructing a multi-dimensional function, the power electricity data and carbon emission data can be automatically associated, the correlation characteristics hidden in multi-source heterogeneous data can be mined, and data support can be provided for subsequent scheduling decisions; by directly embedding carbon emission total and intensity constraints into the constructed model, the double carbon target and power demand can be accurately matched, while balancing multi-objective conflicts and improving subsequent power electricity balance efficiency; based on the target power electricity balance function, carbon emission analysis is carried out on multi-source power electricity data, which greatly reduces the manual intervention link and reduces the risk of data error transmission, ensures the deviation rate of predicted carbon emission data, and according to the multi-source carbon emission data and predicted carbon emission data, a power electricity balance model is constructed, which can deeply analyze the predicted carbon emission data, accurately grasp the carbon emission trend, and finally generate a power electricity scheduling scheme that can be automatically executed and real-time monitored by a computer system, greatly improving the scheduling efficiency and accuracy, while improving the power electricity balance efficiency and accuracy. BRIEF DESCRIPTION OF DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the description of the embodiments of the present application. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor under the premise of the drawings.

[0023] Figure 1 A flowchart of a power electricity balance method based on a double carbon target provided by an embodiment of the present application is shown in the figure.

[0024] Figure 2 A module diagram of a power electricity balance system based on a double carbon target provided by an embodiment of the present application is shown in the figure.

[0025] The purpose of the present application, functional characteristics and advantages will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0026] In order for those skilled in the art to better understand the technical solutions of the present disclosure, and to understand the implementation process of how the present disclosure applies technical means to solve technical problems and achieve corresponding technical effects, and to fully understand and implement the present disclosure, the technical solutions in the embodiments of the present disclosure will be described clearly and completely below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, not all. The embodiments of the present disclosure and various features in the embodiments can be combined with each other without conflict, and the technical solutions formed thereby are all within the protection scope of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative labor should be within the protection scope of the present disclosure.

[0027] It should be noted that the terms "first", "second" and the like in the specification and claims of the present disclosure and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0028] The embodiment of the present application provides a power and electricity balance method based on a double carbon target. The power and electricity balance method based on the double carbon target can be executed by software or hardware installed in a terminal device or a server device. The server device includes but is not limited to a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be a stand-alone server, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content distribution networks (CDN), and big data and demand prediction platforms, etc. basic cloud computing services.

[0029] Referring to Figure 1 FIG. 1 shows a flowchart of a power and electricity balance method based on a double carbon target provided by an embodiment of the present application. In this embodiment, the power and electricity balance method based on the double carbon target includes:

[0030] S1, obtaining multi-source power and electricity data of a plurality of power sources, and extracting corresponding multi-source carbon emission data in the multi-source power and electricity data.

[0031] In the embodiment of the present application, the multi-source power and electricity data refers to the power production and electricity consumption data of multiple power sources from different power generation methods (such as thermal power, hydropower, wind power, photovoltaic power, etc.), including power generation, electricity consumption, load curve, etc.; the multi-source carbon emission data refers to the greenhouse gas emission data related to power production, including direct emission (such as fossil fuel combustion) and indirect emission (such as implicit emission of purchased power).

[0032] In the embodiment of the present application, the extraction of the corresponding multi-source carbon emission data in the multi-source power and electricity data includes:

[0033] Performing format conversion on the multi-source power and electricity data to obtain standardized power and electricity data;

[0034] Extracting the power source identifier of the standardized power and electricity data;

[0035] According to the power source identifier, performing matching search in the preset carbon emission factor database to obtain the target carbon emission factor corresponding to the standardized power and electricity data;

[0036] Calculating the total power generation of the standardized power and electricity data, and performing product operation on the total power generation and the corresponding target carbon emission factor to obtain the corresponding multi-source carbon emission data in the multi-source power and electricity data.

[0037] In the embodiment of the present application, an XML / JSON parser (such as Python's ElementTree or json library) can be used to parse the multi-source power and electricity data to identify the field hierarchy structure of the multi-source power and electricity data; the timestamp field in the field hierarchy structure is extracted, and the timestamp field is uniformly processed to convert formats such as “2023-01-01 08:00:00” into ISO 8601 standard format to obtain standardized power and electricity data.

[0038] Among them, the “power generation type” or “energy type” field is located from the standardized power and electricity data, which usually contains text description (such as “coal-fired” “hydropower”) or coding (such as “COAL” “HYDRO”), and the power source identifier is identified by using keyword matching (such as Python's in operator) or natural language processing (NLP) technology (such as matching keyword library after word segmentation) on the text description field.

[0039] Further, the carbon emission factor database includes fields such as power generation type, region, time range, carbon emission factor value, data source, etc., wherein, the power generation type field is indexed to speed up matching query, and according to the index, the “power generation type+region+time range” is matched accurately in priority, and if not found, the condition is relaxed to obtain the target carbon emission factor.

[0040] Specifically, the power generation fields of the standardized power and energy data are summed (such as SQL GROUP BY power generation type SUM(power generation)) according to the power generation type or data source, and the total power generation of days / months / years is calculated by rolling up the time granularity (such as hourly data); the total power generation (unit: megawatt-hour) is multiplied by the carbon emission factor (unit: ton of carbon dioxide / megawatt-hour) to obtain multi-source carbon emission data (unit: ton of carbon dioxide).

[0041] In the embodiment of the present application, the efficient association of multi-source power and energy data and carbon emissions is realized through an automated process, significantly improving the intelligent level of power and energy management, while eliminating manual sorting errors and improving data processing efficiency. Secondly, the carbon emission factor database matching mechanism based on distributed indexing avoids the delay and errors of manual table lookup in traditional methods, ensuring the real-time and accuracy of the carbon emission calculation results.

[0042] S2, constructing a multi-dimensional power and energy function of the power generation source according to the multi-source carbon emission data and the multi-source power and energy data.

[0043] In the embodiment of the present application, the multi-dimensional power and energy function refers to a function relationship constructed by mathematical modeling with multi-source power and energy data and multi-source carbon emission data as input, used to describe the power production characteristics of the power generation source in different dimensions (such as time, space, power generation type, carbon emission intensity); the multi-dimensional power and energy function can output key indicators such as power generation efficiency, carbon emission trend, and power and energy optimization suggestions.

[0044] In the embodiment of the present application, constructing a multi-dimensional power and energy function of the power generation source according to the multi-source carbon emission data and the multi-source power and energy data comprises:

[0045] Timestamp alignment is performed on the multi-source carbon emission data and the multi-source power and energy data to obtain an aligned carbon and electricity data set;

[0046] Multi-dimensional indicators of the aligned carbon and electricity data set are extracted, and the aligned carbon and electricity data set is divided according to the multi-dimensional indicators to obtain a plurality of dimension carbon and electricity data sets corresponding to the multi-dimensional indicators;

[0047] Dimensional features of the dimension carbon and electricity data set are extracted, and the correlation strength between the dimensional feature data sets is calculated according to the dimensional features;

[0048] The correlation strength is compared with a preset correlation threshold, and the dimensional feature data with a correlation strength greater than the correlation threshold is selected;

[0049] The selected dimensional feature data is used as target feature data;

[0050] constructing a multi-dimensional power and electricity function according to the target feature data and a preset weighting coefficient.

[0051] In the embodiments of the present application, multi-source carbon emission data and multi-source power and electricity data are subjected to time field analysis, and are uniformly converted into a standard time format (such as ISO 8601) through a time analysis library (such as the datetime module of Python). For data with missing time stamps, interpolation is performed according to data generation logic (such as log recording interval) or the time difference of adjacent records to obtain the corresponding supplementary data.

[0052] Specifically, the minimum time granularity (such as hour, minute) of the supplementary data is determined, time window splitting is performed on low-frequency data (such as daily data), and high-frequency data (such as second-level data) is aggregated and down-sampled. A sliding window algorithm is used to ensure that the carbon emission data and the power and electricity data are matched in the same time interval (such as aligning 15-minute-level electricity data and hour-level carbon emission data to the hour granularity). Based on the time stamp field, the carbon emission data and the power and electricity data are associated through a hash table or a database index (such as the JOIN operation of SQL) to generate an aligned carbon and electricity data set containing electricity, carbon emission, and time stamp.

[0053] Further, the multi-dimensional indicators include time dimension, space dimension, energy type dimension, and operation state dimension. A grouping and aggregation technique (such as GROUP BY of SQL or groupby of Pandas) is used to slice the aligned carbon and electricity data set according to the multi-dimensional indicators, thereby obtaining a dimensional carbon and electricity data set. For each dimensional carbon and electricity data set, 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 emission / electricity), power generation efficiency (electricity / installed capacity), load rate (actual electricity / theoretical maximum electricity), etc.

[0054] In detail, a correlation analysis method (such as Pearson correlation coefficient, mutual information) is used to quantify the correlation degree between the dimensional features. For numerical features, the linear correlation (such as the positive correlation degree between electricity and carbon emission) is calculated. For categorical features (such as energy type), the chi-square statistic or information gain is calculated to evaluate the influence weight of carbon emission.

[0055] Among them, the dimensional features of different dimensions (such as electricity in megawatt-hours and carbon emission in tons) are subjected to normalization processing (such as Z-score standardization) to avoid the influence of dimension difference on the calculation result of correlation strength; according to the business requirements, the correlation threshold is set, for example: strong correlation: the threshold is set to 0.7 (Pearson coefficient), indicating a high linear correlation; medium correlation: the threshold is set to 0.4-0.7; weak correlation: the threshold is set to 0.1-0.4.

[0056] Specifically, the correlation strength between all dimensional feature data sets is traversed, dimensional feature data satisfying a correlation threshold (such as the correlation strength of "coal-fired power generation capacity-carbon emission" being 0.85>0.7) is screened out, and the screened-out dimensional feature data is taken as target feature data; a weighting coefficient is set according to a business priority, for example: the carbon emission intensity weight is set to 0.5 (reflecting the environmental protection goal); the power generation efficiency weight is set to 0.3 (reflecting the economy); and the load rate weight is set to 0.2 (reflecting the operation stability).

[0057] The target feature data is combined with the weighting coefficient by using a linear weighting model to generate a comprehensive multi-dimensional power and electricity function. Optionally, the weighting coefficient is adjusted through grid search or Bayesian optimization to minimize the error between the multi-dimensional power and electricity function output (such as predicted carbon emission) and the actual value.

[0058] In the embodiment of the application, by constructing a multi-dimensional function, the power and electricity data and the carbon emission data can be automatically associated, and the correlation characteristics hidden in the multi-source heterogeneous data (such as the positive correlation between the electricity and carbon emission of coal-fired power generation) can be mined, thereby providing data support for subsequent scheduling decisions.

[0059] S3, multi-objective particle swarm optimization is performed on the multi-dimensional power and electricity function based on the pre-determined double carbon target constraint conditions to obtain a target power and electricity balance function.

[0060] In the embodiment of the application, the double carbon target constraint conditions include a carbon emission total amount upper limit: limiting the absolute value of carbon dioxide emission in the power generation process (such as annual emission amount≤X tons); a carbon emission intensity constraint: limiting the carbon emission amount per unit of electricity (such as≤Y tons / MWh); a renewable energy proportion requirement: stipulating the minimum proportion of renewable energy power generation capacity in the total power generation capacity (such as≥Z%); and an energy structure adjustment target: limiting the use proportion of high-carbon energy (such as coal) and encouraging the development of low-carbon energy (such as wind power and photovoltaic power).

[0061] The multi-objective particle swarm optimization (MOPSO) is a heuristic algorithm based on swarm intelligence, which finds the optimal solution by simulating the cooperative behavior of bird flocks or fish flocks, and is used to optimize multiple conflicting targets (such as minimizing carbon emission, maximizing power generation efficiency, and minimizing cost) at the same time.

[0062] In the embodiment of the application, the multi-objective particle swarm optimization is performed on the multi-dimensional power and electricity function based on the pre-determined double carbon target constraint conditions to obtain a target power and electricity balance function, which includes:

[0063] The double carbon target constraint conditions are quantitatively processed to obtain a double carbon constraint index system;

[0064] 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.

[0065] 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.

[0066] Based on the target particle swarm, the multi-dimensional electrical quantity function is iteratively optimized to obtain particle velocity updates and particle position updates.

[0067] 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.

[0068] The multi-dimensional power balance function is optimized based on the target optimization weight parameters to obtain the target power balance function.

[0069] In detail, the particle velocity update is shown in the following formula:

[0070]

[0071] 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.

[0072] In detail, the particle position update is shown in the following formula:

[0073]

[0074] in, Indicates the first The target particle Particle position update in the next iteration Indicates the first a target particle in the first iteration, a particle position in the first iteration, a target particle in the first iteration, a target particle in the first iteration, a particle velocity update of a target particle in the first iteration.

[0075] In the embodiment of the present application, the double-carbon target (such as total carbon emission, carbon intensity, renewable energy consumption ratio, etc.) is converted into a quantifiable mathematical index; for example: total carbon emission = Σ (power generation of each power source type × unit power generation carbon emission factor), carbon intensity = total carbon emission / total power generation.

[0076] In detail, the parameters affected by the double-carbon constraint are screened from the multi-dimensional power and energy function (such as a function including generation cost, network loss, reserve capacity, etc.), such as thermal power generation, wind power / photovoltaic installed capacity, energy storage configuration ratio, etc.; the weight is automatically calculated according to the data characteristics by entropy weight method or principal component analysis (PCA), and then the weight parameter to be optimized is obtained.

[0077] Further, the to-be-optimized parameters are mapped to particle position vectors. For example, the particle dimension = [thermal power ratio, wind power ratio, energy storage capacity, …], and all particle position vectors are dimensionally aligned to ensure that the dimensions of all particles are consistent with the to-be-optimized parameters, and a target particle group is obtained.

[0078] Specifically, the multi-dimensional function is iteratively optimized according to the target particle group, and the particle velocity update and particle position update are obtained, the velocity is adjusted according to the historical optimal position of the particle itself and the optimal position of the group, for example, accelerated in the direction of better solution to avoid falling into local optimum; the particle position is adjusted according to the updated velocity, for example, simulating the movement of particles in the search space, and then the target optimization weight parameter is obtained.

[0079] In detail, the multi-dimensional power and energy function is functionally optimized according to the target optimization weight parameter, that is, the weight is dynamically adjusted, for example, if the carbon emission exceeds 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 weight and parameter are substituted into the multi-dimensional power and energy function, and the target power and energy balance function is generated.

[0080] In the embodiment of the present application, by directly embedding the total carbon emission, intensity and other constraints into the constructed model, the double-carbon target and power demand can be accurately matched, the multi-objective conflict can be balanced, the overall system benefit can be improved, the optimization result is closer to the actual operation condition through the refined modeling of multi-dimensional function (such as time, space, energy type), the long-term emission reduction cost is reduced, and the subsequent power and energy balance efficiency is improved.

[0081] S4, performing carbon emission analysis on the multi-source power flow data according to the target power flow balance function, to obtain predicted carbon emission data.

[0082] In the embodiment of the present application, the carbon emission analysis refers to the process of quantifying the greenhouse gas emission amount of carbon dioxide generated in the operation process of the power generation source based on the target power flow balance function and the multi-source power flow data. The predicted carbon emission data refers to the prediction result of the carbon emission amount of the power generation source in the future period of time obtained by modeling and simulating the multi-source power flow data through the target power flow balance function.

[0083] In the embodiment of the present application, the carbon emission analysis on the multi-source power flow data according to the target power flow balance function to obtain predicted carbon emission data comprises:

[0084] performing function analysis on the target power flow balance function to obtain carbon emission variable parameters;

[0085] constructing a carbon emission correlation relationship according to the carbon emission variable parameters;

[0086] determining power flow conversion data in the multi-source power flow data according to the carbon emission correlation relationship and the target power flow balance function;

[0087] constructing a carbon emission calculation sub-model based on the power flow conversion data and the carbon emission correlation relationship;

[0088] analyzing preliminary carbon emission data of the multi-source power flow data by using the carbon emission calculation sub-model;

[0089] performing network loss carbon emission correction on the preliminary carbon emission data according to a preset carbon emission conversion coefficient, to obtain predicted carbon emission data.

[0090] In the embodiment of the present application, the key parameters directly related to carbon emission calculation are extracted from the target power flow balance function, which can be realized by function structure disassembly and variable attribute identification. The variable modules describing different power generation, power transmission and power consumption links in the target power flow balance function are determined. Then, the physical meaning of the variables in each module is analyzed one by one, and the variables related to carbon emission generation or accounting are screened out. The screened variables are classified and arranged, and the corresponding carbon emission correlation dimensions of each variable (such as direct carbon emission corresponding to thermal power output variable and implicit carbon emission corresponding to new energy output variable) are determined, to form a complete carbon emission variable parameter.

[0091] Specifically, the influence path of each carbon emission variable parameter on carbon emission is analyzed, for example, the variable parameter related to thermal power generation directly determines the carbon emission amount generated by fuel combustion in the thermal power production process, and the variable parameter related to new energy power generation indirectly affects carbon emission by affecting the substitution amount of traditional thermal power; then, combined with the carbon emission accounting rules of the power industry, the quantitative correlation logic between different carbon emission variable parameters and carbon emission is determined, such as “the higher the thermal power output, the higher the direct carbon emission amount” and “the higher the proportion of new energy output, the more carbon emission reduction amount generated by replacing thermal power”, and finally, these logical relationships are sorted and integrated in a structured manner to form a clear carbon emission correlation relationship, ensuring that subsequent targeted carbon emission analysis can be carried out based on the relationship system.

[0092] Further, relying on the constructed carbon emission correlation relationship, key power flow information is extracted from multi-source power flow data through the application of a target power flow balance function; the multi-source power flow data is sorted according to the input requirements of the target power flow balance function to ensure that the data format matches the variable input requirements of the function; then, combined with the carbon emission correlation relationship, the type of power flow data to be obtained from the function output result is determined, and the multi-source power flow data is substituted into the target power flow balance function to filter out the power flow data corresponding to the carbon emission correlation relationship through function operation, ensuring that these data can accurately reflect the flow of power in each link.

[0093] In detail, according to the power flow data, carbon emission calculation is divided into corresponding data sub-modules, each sub-module corresponds to the carbon emission calculation of one power flow link, the carbon emission correlation relationship is embedded in each sub-module, the calculation logic and data transmission relationship of each sub-module are determined, all sub-modules are integrated according to the calculation logic and data transmission relationship to form a carbon emission calculation sub-model covering the whole power flow link and logically coherent, ensuring that the model can output accurate carbon emission related results based on power flow data.

[0094] Among them, the multi-source power flow data is distributed 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, the running state of each sub-module is monitored in real time during the model operation process to ensure that there is no data anomaly or logical error, and after the operation is completed, the carbon emission calculation results of each sub-module are collected and integrated into the total carbon emission amount and sub-link carbon emission data covering the whole power link to form the preliminary carbon emission amount data.

[0095] Further, the carbon emission conversion coefficient is used to quantify the carbon emission corresponding to a unit of network loss; the additional carbon emission corresponding to the preliminary carbon emission data is calculated in combination with the preset carbon emission conversion coefficient; finally, the additional carbon emission is added to the preliminary carbon emission data, the preliminary carbon emission data is corrected, and whether the corrected carbon emission data meets the integrity requirement of carbon emission accounting is checked to ensure that there is no repeated calculation or omission, and finally accurate and comprehensive predicted carbon emission data is obtained.

[0096] In the embodiment of the present application, the carbon emission analysis is carried out on the multi-source power and energy data based on the target power and energy balance function, which greatly reduces the manual intervention link, improves the data processing efficiency compared with the traditional manual statistical analysis method, reduces the risk of data error transmission, and ensures the deviation rate of the predicted carbon emission data.

[0097] S5, constructing a power and energy balance model according to the multi-source carbon emission data and the predicted carbon emission data, and generating a power and energy dispatching scheme based on the power and energy balance model.

[0098] In the embodiment of the present application, the power and energy balance model is a mathematical model constructed based on the multi-source carbon emission data and the predicted carbon emission data in combination with the power supply and demand relationship of the power generation source; the power and energy 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.

[0099] In the embodiment of the present application, the construction of the power and energy balance model according to the multi-source carbon emission data and the predicted carbon emission data comprises:

[0100] performing deviation analysis on the predicted carbon emission data to obtain a confidence interval of the predicted carbon emission data;

[0101] constructing a carbon emission deviation index according to the confidence interval and the multi-source carbon emission data;

[0102] performing model optimization on a preset power and energy model based on the carbon emission deviation index to obtain an optimized power and energy model;

[0103] performing power and energy analysis on the optimized power and energy model according to the historical power operation data obtained in advance, and calculating the average power and energy percentage error of the optimized power and energy model according to the result of the power and energy analysis;

[0104] determining whether the average power and energy percentage error is greater than a preset power and energy error threshold;

[0105] when the average power and energy percentage error is greater than the power and energy error threshold, fine-tuning the power and energy model to obtain a power and energy balance model.

[0106] When the average power energy percentage error is greater than the power energy error threshold, the optimized power energy model is taken as a power energy balance model.

[0107] In the embodiment of the present application, the multi-source carbon emission data (actual monitoring value) is combined, the difference between the predicted data and the actual data is compared, the prediction deviation causes (such as parameter error, scene assumption deviation) are analyzed according to the difference, the reasonable fluctuation range of the prediction deviation causes is determined through the deviation analysis method, that is, the confidence interval, and it is ensured that the confidence interval can cover the real carbon emission situation with a high probability.

[0108] In detail, taking the confidence interval as a reference range and the multi-source carbon emission data as an actual benchmark, an index reflecting the difference between the predicted and actual carbon emissions is designed from the deviation size, fluctuation frequency and other dimensions, such as by comparing the fitting degree of the two in the same time period, the difference characteristics are converted into quantifiable indexes, and a basis is provided for model optimization.

[0109] Among them, the carbon emission deviation index is integrated into the preset power energy model, the parameters related to carbon emission in the power energy model (such as power output constraint, carbon emission control coefficient) are adjusted, the power energy model can adapt to the carbon emission deviation situation, the logic inconsistent with the actual carbon emission in the original power energy model is corrected, and the optimized power energy model is obtained.

[0110] Further, the historical power operation data (past power generation, load and other data) is input into the optimized power energy model, the matching degree of the power energy results output by the optimized power energy model and the historical actual data is analyzed, the average power energy percentage error reflecting the prediction accuracy of the optimized power energy model is calculated according to the difference between the two, the calculated average power energy percentage error is compared with the preset threshold, whether the accuracy of the optimized power energy model meets the standard is judged, if the error exceeds the threshold, it means that the optimized power energy model needs to be further adjusted, otherwise the optimized power energy model can be preliminarily identified as qualified.

[0111] Among them, if the error exceeds the standard, the variable weight, constraint boundary and other variables in the power energy model are adjusted slightly according to the error source (such as parameter setting, constraint condition), the operation logic of the power energy model is optimized, until the error of the power energy model meets the requirements, and the power energy balance model is obtained; if the error is within the acceptable range, it means that the optimized power energy model can accurately reflect the relationship between power energy and carbon emission, and it is directly taken as the final power energy balance model.

[0112] In the embodiment of the present application, the power energy scheduling scheme is generated based on the power energy balance model, which comprises:

[0113] acquire power load data in a target scheduling period, perform time-space dimension division on the power load data to obtain time-period and region-divided load demand data;

[0114] calculate preliminary power and energy scheduling data in the target scheduling period according to the time-period and region-divided load demand data by using the power and energy balance model;

[0115] generate an initial scheduling scheme according to the preliminary power and energy scheduling data, and execute the initial scheduling scheme by using a preset simulation system to obtain initial simulation scheduling results;

[0116] evaluate the initial simulation scheduling results to obtain initial evaluation results;

[0117] perform scheme optimization on the initial scheduling scheme according to the initial evaluation results to obtain a power and energy scheduling scheme.

[0118] In the embodiment of the application, power load data in a target scheduling period is collected, covering power consumption data of different user types such as residents, industries and businesses. From the time dimension, the data is split according to daily power consumption rules (such as peak and valley periods), and from the space dimension, the load data is corresponded to each region according to power grid power supply region division. Through the elimination of abnormal data and the completion of missing data, time-period and region-divided load demand data is finally obtained, providing accurate load basis for subsequent scheduling calculation.

[0119] In detail, the time-period and region-divided load demand data is input into a power and energy balance model to analyze power supply and demand in different periods and regions, so as to determine preliminary scheduling data that meets the load demand and complies with the constraint conditions, including time-period power output of each power source and time-period transmission power between regions.

[0120] According to the preliminary scheduling data, scheduling instructions of each link (such as output value of a power plant at a certain time period and transmission power of a certain transmission line at a certain time period) are sorted out to form an initial scheduling scheme. The scheme is imported into a preset simulation system, the simulation system simulates the actual power grid operation environment, restores the scheduling scheme execution process, records data such as power grid frequency, voltage and operation state of each power source at each time period, generates initial simulation scheduling results, and reflects the actual operation effect of the scheme.

[0121] Further, the initial simulation results are evaluated from multiple dimensions to see whether the power supply and demand are balanced, whether there is a load shortage or power surplus, whether the power grid safety indicators (such as frequency and voltage) are within the normal range, whether the carbon emission meets the double carbon constraint requirement, and whether the scheduling cost is reasonable. Comprehensive evaluation of these dimensions can determine the feasibility and rationality of the initial scheme, and form an initial evaluation result containing advantages and problems.

[0122] Specifically, according to the initial evaluation result, optimization is performed on the problems of the scheme (such as power supply shortage in a certain period in a certain region, overload of a certain power transmission line), if the power supply is insufficient, the output of the related power supply is adjusted or the 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, and after optimization, the scheme is verified again through the simulation system until the scheme meets the requirements of supply and demand balance, safety and low carbon, and finally the power and electricity scheduling scheme is obtained.

[0123] In the embodiment of the application, the scheme optimization is performed on the initial scheduling scheme according to the initial evaluation result to obtain a power and electricity scheduling scheme, which comprises:

[0124] According to the initial evaluation result, random disturbance is performed on the initial scheduling scheme to generate a neighborhood pre-scheduling scheme;

[0125] The number of neighborhood transformations of the neighborhood pre-scheduling scheme is obtained, and a neighborhood transformation coefficient is determined according to the number of neighborhood transformations;

[0126] The neighborhood transformation coefficient is compared with a preset neighborhood transformation probability threshold to obtain a comparison result;

[0127] According to the comparison result, the scheme optimization is performed on the initial scheduling scheme to obtain a power and electricity balance scheme.

[0128] In the embodiment of the application, according to the initial evaluation result, the problems (such as power supply shortage in a certain period in a certain region, line overload) of the initial scheduling scheme are determined, and small-amplitude random adjustment is performed on the key scheduling parameters (such as power supply output and cross-regional power transmission power) in the scheme guided by these problems, and through this disturbance, a plurality of neighborhood pre-scheduling schemes similar to the initial scheme but with slight differences are generated to provide alternative directions for subsequent optimization.

[0129] Specifically, the total number of adjustments (number of neighborhood transformations) of the initial scheme in the process of generating the neighborhood pre-scheduling scheme is counted to determine a neighborhood transformation coefficient that can reflect the rationality of the current neighborhood scheme; a preset neighborhood transformation probability threshold (set according to past optimization experience and power grid safety requirements) is retrieved, and the neighborhood transformation coefficient is compared with the threshold, if the coefficient meets the threshold range, it means that the diversity of the neighborhood scheme meets the standard, if it does not meet the threshold, it means that the scheme adjustment is insufficient or excessive, and further processing is required, and finally a clear comparison result is obtained.

[0130] Further, if the comparison result shows that the coefficient meets the standard, the scheme that can solve the initial problem is selected from the neighborhood pre-scheduling scheme, and the details are fine-tuned in combination with the safety, low carbon and economic requirements; if the coefficient does not meet the standard, the arrangement of generating the neighborhood scheme is returned, and finally the power and electricity balance scheme is obtained.

[0131] In the embodiment of the present application, the power and electricity balance model is constructed according to the multi-source carbon emission data and the predicted carbon emission data, the predicted carbon emission data can be deeply analyzed, the carbon emission trend can be accurately grasped, and through the simulation technology, the power and electricity balance state under different scheduling schemes can be simulated, potential problems can be found in advance, and timely adjustment and optimization can be made; finally, the generated power and electricity scheduling scheme can be automatically executed and real-time monitored by means of the computer system, and the scheduling efficiency and accuracy are greatly improved.

[0132] S6, power and electricity balance is performed on the plurality of power sources by using the power and electricity scheduling scheme, and target power and electricity data is collected from the power sources after power and electricity balance.

[0133] In the embodiment of the present application, the power and electricity balance refers to real-time monitoring of the actual power generation of each power source according to the output requirements of various power sources in the power and electricity scheduling scheme (such as the output interval that the thermal power needs to maintain and the maximum power that the wind power needs to consume), if there is a deviation (such as insufficient output of wind power due to sudden drop of wind speed), the gap is supplemented by adjusting other power sources (such as starting standby thermal power and calling energy storage discharge), while ensuring that the total power generation matches the real-time power consumption load and network loss, and finally realizing power and electricity balance.

[0134] In the embodiment of the present application, the power and electricity balance of the plurality of power sources by using the power and electricity scheduling scheme comprises:

[0135] generating scheduling instructions of the power sources according to the power and electricity scheduling scheme;

[0136] performing power and electricity scheduling on the power sources according to the scheduling instructions to obtain scheduled power sources;

[0137] extracting the actual frequency of the scheduled power sources, calculating the frequency deviation between the actual frequency and the preset target frequency;

[0138] generating adjustment instructions based on the frequency deviation, and realizing power and electricity balance of the scheduled power sources according to the adjustment instructions.

[0139] In the embodiment of the present application, the power and electricity scheduling scheme requirements are converted into specific and executable instructions in combination with the types (such as thermal power, wind power and photovoltaic power) and operating characteristics (such as thermal power peak shaving capacity and new energy output fluctuation) of each power source, such as output value of certain thermal power period and output fluctuation compensation requirements of certain wind power, forming scheduling instructions exclusive to each power source, and ensuring that the instructions fit the actual operating capacity of the power source.

[0140] In detail, the generated scheduling instruction is issued to the control terminal of the corresponding power generation source, the response of each power generation source is monitored in real time during the scheduling process, the power generation source is ensured to strictly follow the instruction operation, and finally the scheduling power generation source operating according to the scheduling requirement is formed, thereby laying a foundation for subsequent balance adjustment.

[0141] Further, the actual operation frequency of each scheduling power generation source after being connected to the power grid is collected in real time by a power grid frequency monitoring device, and the preset target frequency (which is set according to the power grid safety and stability operation standard, and is the frequency benchmark when the power supply and demand are balanced) is called, the actual frequency and the target frequency are compared, the difference between the two is analyzed, and the frequency deviation is determined. The deviation can directly reflect the matching degree of the current power generation source output and the power grid load demand.

[0142] According to the frequency deviation, the supply and demand state is judged, if the deviation shows that the power supply is insufficient or excessive, the corresponding adjustment instruction is generated, the adjustment instruction is issued to the scheduling power generation source, the output adjustment effect is tracked in real time, until the actual frequency approaches the target frequency, and the power and energy balance of multiple power generation sources is realized.

[0143] In the embodiment of the application, by determining the collection range, the power generation sources to be monitored after the power and energy balance are determined, the key data items of each power source such as actual output, operation time, energy consumption, etc. are locked, the monitoring device is started, the operation data of each power source is captured in real time through the sensors of the power generation source or the power grid monitoring system, the continuity of data collection is ensured, and the consistency of the data and the state after the balance is compared, the accuracy of the data is ensured, and finally the target power and energy data is obtained.

[0144] In the embodiment of the application, relying on the computer automatic monitoring system, the power generation source data collection does not need manual intervention, the operation data of each power generation source after the balance can be synchronized in real time, the data acquisition period is greatly shortened, the delay and error of manual collection are avoided, the data timeliness is ensured, and the power and energy balance efficiency and accuracy are improved.

[0145] It should be understood that the size of the serial number of each step in the above embodiment does not mean the order of execution, the execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the application.

[0146] As shown in Figure 2 is a functional module diagram of a power and energy balance system based on a double carbon target provided by an embodiment of the application.

[0147] In the embodiment of the disclosure, a power and energy balance system based on a double carbon target is provided, which corresponds to the power and energy balance method based on a double carbon target in the above embodiment. As shown in Figure 2As shown, the power and electricity balance system 100 based on the double carbon target 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 balance module 106. The functions of each module are described in detail as follows:

[0148] The data extraction module 101 is configured to obtain multi-source power and electricity data of a plurality of power sources, and extract corresponding multi-source carbon emission data from the multi-source power and electricity data.

[0149] The function construction module 102 is configured to construct a multi-dimensional power and electricity function of the power source according to the multi-source carbon emission data and the multi-source power and electricity data.

[0150] The function optimization module 103 is configured to perform multi-objective particle swarm optimization on the multi-dimensional power and electricity function based on a predetermined double carbon target constraint condition, to obtain a target power and electricity balance function.

[0151] The function prediction module 104 is configured to perform carbon emission analysis on the multi-source power and electricity data according to the target power and electricity balance function, to obtain predicted carbon emission data.

[0152] The model generation module 105 is configured to construct a power and electricity balance model according to the multi-source carbon emission data and the predicted carbon emission data, and generate a power and electricity dispatching scheme based on the power and electricity balance model.

[0153] The data balance module 106 is configured to balance the power and electricity of the plurality of power sources using the power and electricity dispatching scheme, and collect target power and electricity data from the power sources after the power and electricity balance.

[0154] In an embodiment, the data extraction module 101, when extracting the corresponding multi-source carbon emission data from the multi-source power and electricity data, is configured to:

[0155] perform format conversion on the multi-source power and electricity data to obtain standardized power and electricity data;

[0156] extract a power source identifier of the standardized power and electricity data;

[0157] perform matching search in a preset carbon emission factor database according to the power source identifier to obtain a target carbon emission factor corresponding to the standardized power and electricity data;

[0158] calculate the total power generation of the standardized power and electricity data, and perform multiplication operation on the total power generation and the corresponding target carbon emission factor to obtain the corresponding multi-source carbon emission data in the multi-source power and electricity data.

[0159] In an embodiment, the function construction module 102, when performing construction of the multi-dimensional power generation function of the power generation source according to the multi-source carbon emission data and the multi-source power generation data, is configured to:

[0160] timestamp alignment of the multi-source carbon emission data and the multi-source power generation data to obtain an aligned carbon power dataset;

[0161] extracting multi-dimensional indicators of the aligned carbon power dataset, and performing data division on the aligned carbon power dataset according to the multi-dimensional indicators to obtain a plurality of dimension carbon power datasets corresponding to the multi-dimensional indicators;

[0162] extracting dimension features of the dimension carbon power datasets, and calculating correlation strengths between the dimension feature datasets according to the dimension features;

[0163] comparing the correlation strengths with a preset correlation threshold, and screening out dimension feature data with a correlation strength greater than the correlation threshold;

[0164] the screened dimension feature data is used as target feature data;

[0165] constructing a multi-dimensional power generation function according to the target feature data and a preset weighting coefficient.

[0166] In an embodiment, the function optimization module 103, when performing multi-objective particle swarm optimization of the multi-dimensional power generation function based on a pre-determined double carbon target constraint condition to obtain a target power generation balance function, is configured to:

[0167] quantitative processing of the double carbon target constraint condition to obtain a double carbon constraint index system;

[0168] determining a to-be-optimized parameter of the multi-dimensional power generation function according to the double carbon constraint index system, and performing weight distribution on the to-be-optimized parameter to obtain a to-be-optimized weight parameter;

[0169] obtaining a plurality of initial particle swarms, and performing dimension alignment on the initial particle swarms according to the to-be-optimized parameter to obtain a target particle swarm;

[0170] iterative optimization of the multi-dimensional power generation function according to the target particle swarm to obtain particle speed updates and particle position updates;

[0171] parameter updating of the to-be-optimized weight parameter according to the particle speed updates and the particle position updates to obtain a target optimization weight parameter;

[0172] function optimization of the multi-dimensional power generation function according to the target optimization weight parameter to obtain a target power generation balance function.

[0173] In an embodiment, the function prediction module 104, when performing carbon emission analysis on the multi-source power flow data according to the target power flow balance function to obtain predicted carbon emission data, is configured to:

[0174] perform function analysis on the target power flow balance function to obtain carbon emission variable parameters;

[0175] construct a carbon emission correlation relationship according to the carbon emission variable parameters;

[0176] determine power flow conversion data in the multi-source power flow data according to the carbon emission correlation relationship and the target power flow balance function;

[0177] construct a carbon emission calculation sub-model based on the power flow conversion data and the carbon emission correlation relationship;

[0178] analyze preliminary carbon emission data of the multi-source power flow data using the carbon emission calculation sub-model;

[0179] correct network loss carbon emissions of the preliminary carbon emission data according to a preset carbon emission conversion coefficient to obtain predicted carbon emission data.

[0180] In an embodiment, the model generation module 105, when performing construction of a power flow balance model according to the multi-source carbon emission data and the predicted carbon emission data, is configured to:

[0181] perform bias analysis on the predicted carbon emission data to obtain a confidence interval of the predicted carbon emission data;

[0182] construct a carbon emission bias index according to the confidence interval and the multi-source carbon emission data;

[0183] perform model optimization on a preset power flow model based on the carbon emission bias index to obtain an optimized power flow model;

[0184] perform power flow analysis on the optimized power flow model according to pre-acquired historical power operation data, and calculate an average power flow percentage error of the optimized power flow model according to a result of the power flow analysis;

[0185] determine whether the average power flow percentage error is greater than a preset power flow error threshold;

[0186] when the average power flow percentage error is greater than the power flow error threshold, fine-tune the power flow model to obtain a power flow balance model;

[0187] When the average power energy percentage error is greater than the power energy error threshold, the optimized power energy model is taken as a power energy balance model.

[0188] In an embodiment, the model generation module 105, when performing generation of a power energy scheduling scheme based on the power energy balance model, is configured to:

[0189] obtain power load data in a target scheduling period, perform time-space dimension division on the power load data to obtain time-period and region-divided load demand data;

[0190] calculate preliminary power energy scheduling data in the target scheduling period according to the time-period and region-divided load demand data using the power energy balance model;

[0191] generate an initial scheduling scheme according to the preliminary power energy scheduling data, and perform the initial scheduling scheme using a preset simulation system to obtain an initial simulation scheduling result;

[0192] evaluate the initial simulation scheduling result to obtain an initial evaluation result;

[0193] perform scheme optimization on the initial scheduling scheme according to the initial evaluation result to obtain a power energy scheduling scheme.

[0194] In an embodiment, the model generation module 105, when performing scheme optimization on the initial scheduling scheme according to the initial evaluation result to obtain a power energy scheduling scheme, is configured to:

[0195] perform random disturbance on the initial scheduling scheme according to the initial evaluation result to generate a neighborhood pre-scheduling scheme;

[0196] obtain a neighborhood transformation number of the neighborhood pre-scheduling scheme, and determine a neighborhood transformation coefficient according to the neighborhood transformation number;

[0197] compare the neighborhood transformation coefficient with a preset neighborhood transformation probability threshold to obtain a comparison result;

[0198] perform scheme optimization on the initial scheduling scheme according to the comparison result to obtain a power energy balance scheme.

[0199] In an embodiment, the data balance module 106, when performing power energy balance on a plurality of power generation sources using the power energy scheduling scheme, is configured to:

[0200] generate scheduling instructions of the power generation sources according to the power energy scheduling scheme;

[0201] perform power energy scheduling on the power generation sources according to the scheduling instructions to obtain scheduled power generation sources;

[0202] extracting an actual frequency of the dispatch power source, calculating a frequency deviation between the actual frequency and a preset target frequency;

[0203] generating an adjustment instruction based on the frequency deviation, and realizing power balance of the dispatch power source according to the adjustment instruction.

[0204] In the present application, the specific limitations of the power balance system based on the double carbon target can be seen in the above limitations of the power balance method based on the double carbon target, which will not be repeated here. Each module in the above power balance system based on the double carbon target can be realized by software, hardware and their combinations. The above modules can be embedded in or independent of the processor in the computer device in hardware form, or stored in the memory in the computer device in software form, so as to call and execute the operations corresponding to each module by the processor.

[0205] In the embodiments provided by the present application, it should be understood that the disclosed system can be implemented in other ways. For example, the above-mentioned system embodiments are merely illustrative. For example, the division of the modules is only a logical function division. In actual implementation, there can be another division manner.

[0206] In addition, each functional module in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The above integrated unit can be realized in the form of hardware, or in the form of hardware plus software function module.

[0207] Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-limiting, and the scope of the present application is defined by the appended claims rather than the above description, and therefore all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present application. Any reference signs in the claims should not be regarded as limiting the claims involved.

[0208] It is obvious for those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application.

[0209] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, storage, database or other medium used in each embodiment provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0210] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of functional units and modules is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the system is divided into different functional units or modules to complete all or part of the above-mentioned functions.

[0211] In the embodiments provided in the present disclosure, it should be understood that the disclosed system and method can also be implemented in other manners. The above described system embodiments are merely illustrative, for example, the flowcharts and block diagrams in the accompanying drawings show possible implementation architectures, functions and operation of the system, method and computer program product according to the embodiments of the present disclosure. In this regard, each block in the flowcharts or block diagrams can represent a module, a segment or a portion of code which comprises one or more executable instructions for implementing the specified logic function. It should also be noted that in some alternative implementations, the functions shown in the blocks can occur in different orders than those shown in the figures. For example, two blocks shown in succession can in fact be executed substantially concurrently or in the reverse order, depending on the functionality involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented by dedicated hardware-based systems which perform the specified functions or actions, or can be implemented by a combination of dedicated hardware-based systems and computer instructions.

[0212] It should be noted that in the present disclosure, the terms "comprising", "containing" or any other variant thereof are intended to cover non-exclusive inclusion, such that a process, method, article or apparatus that comprises a list of elements does not only include those elements, but also includes other elements not expressly listed or inherent to such process, method, article or apparatus. Without more limitations, the element limited by the phrase "comprising a" does not exclude the presence of additional identical elements in the process, method, article or apparatus comprising the element.

[0213] The above described embodiments are merely used to illustrate the technical solutions of the present disclosure, rather than limiting them; although the present disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the protection scope of the present disclosure.

Claims

1. A power and energy balancing method based on a double carbon target, characterized in that, The method comprises: acquiring multi-source carbon emission data; timestamp alignment of multi-source carbon emission and power data to form carbon power data set; extracting multi-dimensional indicators from the data set and dividing to obtain multiple dimensional carbon power data sets; calculating the correlation strength between each dimensional carbon power data set, and screening out target feature data based on a preset correlation threshold; constructing a multi-dimensional power function using the target feature data and a preset weighting coefficient; quantifying the double carbon target constraint condition into an index system; determining the to-be-optimized parameters of the multi-dimensional power function based on the index system and performing weight distribution, iteratively optimizing the to-be-optimized parameters to obtain target optimization weight parameters; optimizing the power function using the target optimization weight parameters to obtain a target power balance function; performing carbon emission analysis on the power balance function to obtain predicted carbon emission data; constructing a carbon emission deviation index based on the confidence interval of the predicted carbon emission data and the multi-source carbon emission data; optimizing the power and electricity model using the deviation index; calculating the average power and electricity percentage error of the power and electricity model, and comparing it with a preset error threshold to determine the final model; acquiring power load data of a target scheduling period and performing time and space dimension division to obtain load demand data; calculating the preliminary scheduling data corresponding to the load demand data using the power balance model; generating an initial scheduling scheme based on the preliminary scheduling data, and obtaining simulation results through simulation execution; evaluating the simulation results and optimizing the scheme to obtain a final scheduling scheme; executing the scheduling scheme to achieve power balance of multiple power sources, and collecting target power data after balance.

2. The dual-carbon-target-based power and energy balancing method of claim 1, wherein, The method comprises: standardizing multi-source power data to obtain standardized power data; extracting power source identification from the standardized power data; matching a preset carbon emission factor database based on the identification to obtain corresponding target carbon emission factor; calculating the multi-source carbon emission data according to the total power generation of the standardized power data and the target carbon emission factor.

3. The dual-carbon-target-based power and energy balancing method of claim 1 or 2, wherein, The multi-objective particle swarm optimization algorithm is used to iteratively optimize the to-be-optimized parameters to obtain the target optimization weight parameters.

4. The dual-carbon-target-based power energy balance method of claim 1, wherein, The method comprises: determining the carbon emission correlation relationship according to the target power balance function; constructing a carbon emission calculation sub-model based on the carbon emission correlation relationship; analyzing multi-source power data using the carbon emission calculation sub-model to obtain preliminary carbon emission data; performing network loss carbon emission correction on the preliminary carbon emission data to obtain predicted carbon emission data.

5. The dual-carbon-target-based power and energy balancing method of claim 4, wherein, The method comprises: performing random disturbance on the initial scheduling scheme based on the initial evaluation results to generate a neighborhood pre-scheduling scheme; determining a neighborhood transformation coefficient according to the number of transformations of the neighborhood pre-scheduling scheme; comparing the neighborhood transformation coefficient with a preset threshold; optimizing the initial scheduling scheme according to the comparison result to obtain a power balance scheme.

6. The dual-carbon-target-based power energy balance method of claim 1, wherein, The method comprises: generating scheduling instructions for power sources according to the power scheduling scheme and executing the scheduling. An actual frequency of the dispatched power generation source is acquired, and a frequency deviation from a target frequency is calculated; An adjustment instruction is generated based on the frequency deviation, and power and energy balance is achieved by executing the adjustment instruction.

7. A system for balancing electricity power based on a double carbon target according to any one of claims 1-6, characterized in that, The system comprises: A data extraction module for acquiring multi-source carbon emission data; A function construction module for constructing a multi-dimensional power and energy function based on the multi-source carbon emission data; A function optimization module for performing multi-objective particle swarm optimization on the multi-dimensional power and energy function with a double-carbon target as a constraint condition to obtain a target power and energy balance function; A function prediction module for performing carbon emission analysis on the power and energy balance function to obtain predicted carbon emission data; A model generation module for constructing a power and energy balance model based on the predicted carbon emission data to generate a power and energy dispatching scheme; A data balance module for executing the dispatching scheme to achieve power and energy balance of multiple power generation sources and collecting target power and energy data after balance.

Images