Air conditioner load analysis method and system based on data fusion and carbon emission reduction accounting

Abstract

The invention relates to the technical field of power systems, and discloses an air conditioner load analysis method and system based on data fusion and carbon emission reduction accounting. The method comprises the following steps: acquiring air conditioner related data under different dimensions, and performing fusion processing on all the air conditioner related data to obtain air conditioner load fusion knowledge; setting a plurality of reference scenes based on the first power consumption behavior characteristics, and determining first air conditioner carbon emission of each reference scene according to air conditioner load fusion knowledge; setting a project scene based on the second power consumption behavior characteristic, and determining a second air conditioner carbon emission of the project scene according to the air conditioner load fusion knowledge; and obtaining air conditioner carbon emission reduction based on each first air conditioner carbon emission and each second air conditioner carbon emission, and integrating the air conditioner carbon emission reduction with air conditioner power consumption and billing data obtained by analyzing the air conditioner load fusion knowledge to form an air conditioner load analysis result. According to the invention, air conditioner load data and carbon emission reduction accounting are deeply coupled, and an energy system is boosted to be intelligently upgraded.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power systems, in particular to an air conditioner load analysis method and system based on data fusion and carbon emission reduction accounting. BACKGROUND

[0002] With the deep integration of smart grid and user-side digitization, residential electricity consumption behavior analysis and energy saving guidance have become an important direction for the upgrading of power grid services. At present, residential smart air conditioner load data (such as analysis period, device SN, rated power), power grid operation data (such as time-of-use electricity price, step threshold) and residential activity data (such as power saving notification, reward rules) are stored in heterogeneous platforms such as load interaction platform, power grid business system and online State Grid, and the data resources are scattered and lack effective correlation. The existing electricity bill generation technology only completes electricity quantity accounting based on single power grid data, and the output result is limited to total electricity charges and sub-grade electricity quantity, which cannot present fine information such as peak-valley distribution of air conditioner load, step electricity price jump threshold trigger point, etc., resulting in that residents cannot understand the influence of air conditioner electricity consumption on electricity charges, the initiative of users to participate in power saving response is insufficient, and the practicability of electricity bill and user stickiness are low.

[0003] As an important part of adjustable load in the power system, residential air conditioner has increasingly prominent carbon emission reduction value in participating in power grid energy saving interaction. However, in the existing technology, such as a demand response mechanism model establishment method considering real-time carbon emission reduction, although it involves carbon cost modeling in demand response, it does not define a standardized carbon emission reduction accounting method for residential air conditioner, especially lacks technical specifications for key links such as baseline setting and emission reduction quantification, resulting in that the emission reduction effect cannot be accurately measured. At present, there is no carbon emission reduction methodology for residential air conditioner participating in power grid interaction, forming a technical application blank, resulting in that the carbon emission accounting and verification system on the residential side cannot be effectively established.

[0004] Therefore, it is necessary to build a load analysis system integrating multi-source data and a standardized carbon emission reduction methodology to improve the quality of power grid services and the initiative of residential energy saving behavior. SUMMARY

[0005] In order to make up for the deficiencies of the existing technology in multi-dimensional fusion of residential electricity data and quantification of air conditioner electricity saving carbon emission, the present application provides an air conditioner load analysis method and system based on data fusion and carbon emission reduction accounting.

[0006] In a first aspect, an air conditioner load analysis method based on data fusion and carbon emission reduction accounting is provided, comprising: obtaining air conditioner related data in different dimensions, and performing fusion processing on all the air conditioner related data to obtain air conditioner load fusion knowledge; a plurality of benchmark scenarios are set based on first electricity consumption behavior characteristics reflecting that the air conditioner does not participate in power saving activities, and a first air conditioner carbon emission of each of the benchmark scenarios is determined according to the air conditioner load fusion knowledge; a project scenario is set based on second electricity consumption behavior characteristics reflecting that the air conditioner participates in power saving activities, and a second air conditioner carbon emission of the project scenario is determined according to the air conditioner load fusion knowledge; an air conditioner carbon emission reduction is obtained based on each of the first air conditioner carbon emission and the second air conditioner carbon emission, and air conditioner electricity consumption and billing data obtained by analyzing the air conditioner load fusion knowledge are integrated to form an air conditioner load analysis result.

[0007] Preferably, the air conditioner related data in different dimensions is obtained, and the air conditioner load fusion knowledge is obtained by fusing all the air conditioner related data. Accessing a plurality of power service association platforms to obtain air conditioner load data, power grid operation data and resident activity data respectively; The air conditioner load data, the power grid operation data and the resident activity data are associated, fused and structured modeled to obtain an air conditioner load data graph; The air conditioner load data graph is rule-inferred to obtain air conditioner load association rules; The air conditioner load fusion knowledge is formed based on the air conditioner load data graph and the air conditioner load association rules.

[0008] Preferably, the air conditioner load data, the power grid operation data and the resident activity data are associated, fused and structured modeled to obtain an air conditioner load data graph, including: The air conditioner load data, the power grid operation data and the resident activity data are preprocessed to obtain a standardized data set; Based on a preset ontology relationship, entity recognition and attribute extraction are performed on the standardized data set to obtain a multi-source entity set; The multi-source entity set is aligned to obtain an inter-entity mapping relationship; An air conditioner load data graph containing hierarchical structure and associated attributes is constructed with entities as nodes and the inter-entity mapping relationship as edges.

[0009] Preferably, the plurality of benchmark scenarios are set based on first electricity consumption behavior characteristics reflecting that the air conditioner does not participate in power saving activities, and a first air conditioner carbon emission of each of the benchmark scenarios is determined according to the air conditioner load fusion knowledge, including: The first benchmark scenario, the second benchmark scenario and the third benchmark scenario are set based on first electricity consumption behavior characteristics reflecting that the air conditioner does not participate in power saving activities; determine a first air conditioner carbon emission of the first benchmark scene based on the air conditioner load fusion knowledge, wherein the first benchmark scene is a scene in which the air conditioner is operated in an average power consumption mode of a power grid operation area; determine a first air conditioner carbon emission of the second benchmark scene based on the air conditioner load fusion knowledge, wherein the second benchmark scene is a scene in which the air conditioner is operated in a user historical same period power consumption mode; determine a first air conditioner carbon emission of the third benchmark scene based on the air conditioner load fusion knowledge, wherein the third benchmark scene is a scene in which the air conditioner is operated in a preset standard benchmark load curve.

[0010] Preferably, the determining of the first air conditioner carbon emission of the first benchmark scene based on the air conditioner load fusion knowledge comprises: perform parameter extraction on the first benchmark scene based on the air conditioner load data graph to obtain a first parameter set, wherein the first parameter set comprises total power consumption of residents in the power grid operation area, a power grid comprehensive marginal emission factor, a power grid transmission and distribution loss rate, total number of households of residents in the power grid operation area, and an advancedness coefficient, and the power grid comprehensive marginal emission factor is obtained based on a power grid power quantity marginal emission factor and a power grid capacity marginal emission factor; perform operation processing on the total power consumption of residents in the power grid operation area, the power grid comprehensive marginal emission factor, the power grid transmission and distribution loss rate, the total number of households of residents in the power grid operation area, and the advancedness coefficient based on the air conditioner load association rules to obtain the first air conditioner carbon emission of the first benchmark scene.

[0011] Preferably, the determining of the first air conditioner carbon emission of the second benchmark scene based on the air conditioner load fusion knowledge comprises: perform parameter extraction on the second benchmark scene based on the air conditioner load data graph to obtain a second parameter set, wherein the second parameter set comprises resident power consumption of a corresponding billing period of a user historical same period, a power grid comprehensive marginal emission factor, a power grid transmission and distribution loss rate, a meteorological factor correlation correction coefficient, and a work and rest feature correlation correction coefficient, and the power grid comprehensive marginal emission factor is obtained based on a power grid power quantity marginal emission factor and a power grid capacity marginal emission factor; perform operation processing on the resident power consumption of the corresponding billing period of the user historical same period, the power grid comprehensive marginal emission factor, the power grid transmission and distribution loss rate, the meteorological factor correlation correction coefficient, and the work and rest feature correlation correction coefficient based on the air conditioner load association rules to obtain the first air conditioner carbon emission of the second benchmark scene.

[0012] Preferably, the determining of the first air conditioner carbon emission of the third benchmark scene based on the air conditioner load fusion knowledge comprises: extracting parameters of the third reference scene based on the air conditioner load data graph, to obtain a third parameter set, wherein the third parameter set comprises a resident baseline load at each time point in the billing period, a power grid comprehensive marginal emission factor, a power grid transmission and distribution loss rate, and a total number of resident households in the power grid operation area, and the power grid comprehensive marginal emission factor is obtained based on a power grid power marginal emission factor and a power grid capacity marginal emission factor; performing operation processing on the resident baseline load at each time point in the billing period, the power grid comprehensive marginal emission factor, the power grid transmission and distribution loss rate, and the total number of resident households in the power grid operation area based on the air conditioner load association rules, to obtain the first air conditioner carbon emission of the third reference scene.

[0013] Preferably, the second electricity consumption behavior characteristic reflecting the participation of the air conditioner in the power saving activity is set to project a scene, and the second air conditioner carbon emission of the project scene is determined according to the air conditioner load fusion knowledge, comprising: setting a project scene based on the second electricity consumption behavior characteristic reflecting the participation of the air conditioner in the power saving activity, wherein the project scene is an operation scene of the air conditioner participating in the power saving activity; extracting parameters of the project scene based on the air conditioner load data graph, to obtain a fourth parameter set, wherein the fourth parameter set comprises an air conditioner power consumption participating in the power saving activity, a power grid comprehensive marginal emission factor, and a power grid transmission and distribution loss rate, and the power grid comprehensive marginal emission factor is obtained based on a power grid power marginal emission factor and a power grid capacity marginal emission factor; performing operation processing on the air conditioner power consumption participating in the power saving activity, the power grid comprehensive marginal emission factor, and the power grid transmission and distribution loss rate based on the air conditioner load association rules, to obtain the second air conditioner carbon emission of the project scene.

[0014] Preferably, the air conditioner carbon emission reduction is obtained based on each of the first air conditioner carbon emission and the second air conditioner carbon emission, and the air conditioner electricity and billing data obtained by analyzing the air conditioner load fusion knowledge are integrated to form an air conditioner load analysis result, comprising: performing extreme value screening on each of the first air conditioner carbon emission to obtain a maximum air conditioner carbon emission of the reference scene, and performing difference operation on the maximum air conditioner carbon emission of the reference scene and the second air conditioner carbon emission to obtain the air conditioner carbon emission reduction; extracting indexes from the air conditioner load fusion knowledge and performing association calculation to obtain air conditioner electricity and billing data, and integrating the air conditioner carbon emission reduction and the air conditioner electricity and billing data to form an air conditioner load analysis result, wherein the air conditioner electricity and billing data comprises electricity consumption and electricity charges of the air conditioner in different time periods, and electricity consumption and electricity charges of the air conditioner in different step electricity price intervals.

[0015] In a second aspect, an embodiment of the present invention provides an air conditioning load analysis system based on data fusion and carbon emission reduction accounting, including: A data fusion processing module is used to obtain air conditioning related data in different dimensions and fuse all the air conditioning related data to obtain air conditioning load fusion knowledge; a baseline carbon emission determination module, configured to set a plurality of baseline scenarios based on a first electricity usage behavior characteristic reflecting that the air conditioner does not participate in the power-saving activity, and determine a first air conditioner carbon emission amount for each of the baseline scenarios based on the air conditioner load fusion knowledge; a project carbon emission determination module, configured to set a project scenario based on a second electricity usage behavior characteristic reflecting the air conditioner's participation in the electricity saving activity, and determine a second air conditioner carbon emission amount for the project scenario based on the air conditioner load fusion knowledge; An analysis result generation module is used to obtain air conditioning carbon emission reduction based on each of the first air conditioning carbon emissions and the second air conditioning carbon emissions, and integrate the air conditioning carbon emission reduction with the air conditioning electricity consumption and billing data obtained by analyzing the air conditioning load fusion knowledge to form an air conditioning load analysis result.

[0016] Compared with the existing technology, the air-conditioning load analysis method and system based on data fusion and carbon emission reduction accounting in the embodiment of the present invention have the following beneficial effects: according to the refined decomposition of electricity consumption and billing data based on the air-conditioning load data map, combined with the calculation of the carbon emission difference between the baseline scenario and the project scenario, the time-sharing electricity consumption, tiered electricity charges and carbon emission reduction of the air-conditioning single equipment are quantitatively associated for the first time, breaking through the limitation that traditional electricity consumption data only reflects the total amount, providing data-based guidance for energy-saving behavior, and promoting the transformation of residents' electricity consumption from passive response to active optimization; by identifying the carbon emission differences of air-conditioning loads in different scenarios, demand response plans can be formulated in a targeted manner to achieve flexible regulation of air-conditioning loads, effectively suppress the peak and valley differences in electricity consumption, reduce the impact of extreme loads on power grid equipment, and improve the economy and reliability of power grid operation; deeply coupling air-conditioning load data with carbon emission reduction accounting, promotes the transformation of the power grid from a traditional power supplier to a comprehensive energy service provider, and helps the energy system to upgrade to intelligence. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flow chart of an air conditioning load analysis method based on data fusion and carbon emission reduction accounting according to an embodiment of the present invention; Figure 2 This is a flow chart of the fusion processing according to an embodiment of the present invention; Figure 3 is a schematic diagram of a process for determining carbon emissions of a first air conditioner according to an embodiment of the present invention; Figure 4 is a schematic diagram of a process for determining carbon emissions of a second air conditioner according to an embodiment of the present invention; Figure 5is a schematic diagram of a process for forming an air conditioning load analysis result according to an embodiment of the present invention; Figure 6 is a schematic diagram of the air conditioning load analysis results according to an embodiment of the present invention; Figure 7 This is a schematic structural diagram of an air conditioning load analysis system based on data fusion and carbon emission reduction accounting according to an embodiment of the present invention; Reference numerals: 1. Data fusion processing module; 2. Baseline carbon emission determination module; 3. Project carbon emission determination module; 4. Analysis result generation module. DETAILED DESCRIPTION

[0018] The following embodiments of the present invention are described in further detail with reference to the accompanying drawings and examples. The following examples are used to illustrate the present invention but are not intended to limit the scope of the present invention.

[0019] In the description of the present invention, it should be understood that the terms "first" and "second" etc. are used in the present invention to distinguish different objects rather than to describe a specific order.

[0020] In describing the present invention, it should be noted that, unless otherwise defined, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. Those skilled in the art will understand the specific meanings of the above terms in the present invention in specific circumstances.

[0021] like Figure 1 As shown, it is a flow chart of an air conditioning load analysis method based on data fusion and carbon emission reduction accounting according to an embodiment of the present invention. Figure 1 An embodiment of the present invention provides an air conditioning load analysis method based on data fusion and carbon emission reduction accounting, comprising the steps of: S1. Acquire air conditioning related data in different dimensions and fuse all air conditioning related data to obtain air conditioning load fusion knowledge; like Figure 2 As shown, it is a flow chart of step S1 of an embodiment of the present invention. Figure 2 In the embodiment of the present invention, step S1 includes: S101. Access several power service related platforms to obtain air conditioning load data, power grid operation data, and resident activity data; The air conditioner related data in different dimensions includes air conditioner load data (device operation dimension), power grid operation data (power grid management dimension), and resident activity data (user behavior dimension). Specifically, through API interface and data synchronization protocol, etc. Access to load interaction platform, new type of power load management system and online State Grid, etc. Power service related platform, air conditioner load data, power grid operation data and resident activity data are collected respectively to form a multi-source heterogeneous original data set. Among them, the air conditioner load data includes device SN, rated power, working mode, running power, date, time period; the power grid operation data covers time-of-use electricity price, ladder electricity price threshold, power grid transmission and distribution loss rate; the resident activity data includes date, time period, power saving notice, and reward rule.

[0022] S102, correlating and fusing the air conditioner load data, the power grid operation data and the resident activity data, and structuring modeling to obtain an air conditioner load data graph; Considering that the correlating and fusing and the structuring modeling are key links for transforming multi-source heterogeneous data into an air conditioner load data graph, the process is specifically described below.

[0023] Specifically, step S102 includes: 1) preprocessing the air conditioner load data, the power grid operation data and the resident activity data to obtain a standardized data set; Specifically, the preprocessing includes data cleaning, removing outliers and filling missing values.

[0024] Further, for the air conditioner load data, the power grid operation data and the resident activity data, first, data cleaning is performed to remove duplicate records, format error data and redundant information irrelevant to the analysis period; then, statistical methods are used to identify and remove extreme values caused by device failure or data transmission anomaly, such as abnormal data of air conditioner running power exceeding the reasonable range of rated power; for missing values caused by collection interval or system failure, according to the data characteristics, mean filling (such as short-term missing of power grid transmission and distribution loss rate), interpolation method filling (such as continuous period missing of air conditioner running power) or association filling based on the ontology relationship of knowledge graph (such as missing of reward rule bound to a specific period in resident activity data) are used, and finally a standardized data set with unified format and complete data is formed.

[0025] 2) entity recognition and attribute extraction are performed on the standardized data set based on preset ontology relationship to obtain a multi-source entity set; Specifically, the preset ontology relationship includes multi-dimensional relationship definitions such as "air conditioner associated user", "resident associated activity", "air conditioner associated electricity price", "air conditioner associated activity", and "air conditioner associated operation".

[0026] Further, according to the definition of entities such as "air conditioner", "resident", "electricity price", "activity", and "operation" in the ontology layer, corresponding entities are identified from the standardized data set, such as an air conditioner entity containing attributes such as equipment SN and running power, and a resident entity containing attributes such as house number and electricity quantity; meanwhile, according to preset attribute items of each entity (such as analysis period and working mode of the air conditioner, and time-of-use electricity price and step electricity price threshold of the electricity price), corresponding attribute values are extracted from the standardized data set, ensuring that the attributes of each entity are complete and consistent with the ontology definition; and finally, a multi-source entity set containing multiple types of entities and their attributes is formed, so that data from different sources are associated to form a whole.

[0027] 3) Aligning the same source entities in the multi-source entity set to obtain the mapping relationship between entities; Based on the association rules of entity attributes in the preset ontology relationship, the entities in the multi-source entity set are compared across data sets. The association rules include but are not limited to the binding relationship between the air conditioner equipment SN and the resident house number, and the matching relationship between the activity date and the air conditioner running period.

[0028] Specifically, the records of the same air conditioner in different platform data are associated through the equipment unique identifier (equipment SN), the information of the same resident in the load data and the activity data is matched through the house number, and the time dimension of the electricity price rule and the corresponding air conditioner running data is aligned through the period and the analysis period; for the same source entities with slight differences in attribute values, consistency verification and correction are performed in combination with the knowledge graph reasoning rules (such as reasonable fluctuation range of running power), and finally the mapping relationship between entities is determined, realizing the cross-data set association and fusion of multi-source entities.

[0029] 4) Taking entities as nodes and the mapping relationship between entities as edges, an air conditioner load data graph containing hierarchical structure and associated attributes is constructed.

[0030] The aligned entities in the multi-source entity set are taken as nodes of the knowledge graph, and the connection edges between nodes are constructed according to the determined mapping relationship between entities; meanwhile, attribute information extracted from the standardized data set is loaded for each node, and hierarchical division is performed according to the hierarchical structure defined in the ontology layer. Further, the nodes, edges, and attribute information are stored in a structured manner by the knowledge graph construction tool Neo4j, forming an air conditioner load data graph containing hierarchical relationships of entities and cross-class associated attributes.

[0031] In order to facilitate understanding, the structure design of the air conditioner load data graph is described below in combination with an embodiment: 1) Ontology layer (entity); Air conditioner (attributes: analysis period, equipment SN, rated power, working mode, running power, date, period); Resident (attributes: household number, this month's indicator, last month's indicator, electricity consumption, response reward, this period's response, this period's adjustability, amount, this period's start, this period's reduction, this period's emission); Electricity price (attributes: time-of-use electricity price, tiered electricity price threshold, grid transmission and distribution loss rate); Activity (attributes: date, time period, notification, reward rule); Operation (attributes: analyst, reviewer, power supply unit, analysis unit, data unit, single date, analysis period).

[0032] 2) Ontology layer (relationship); "Air conditioner associated user" (many-to-one); "Resident associated activity" (many-to-many); "Air conditioner associated electricity price" (one-to-many); "Air conditioner associated activity" (one-to-many); "Air conditioner associated operation" (many-to-one).

[0033] 3) Instance layer (mapping).

[0034] Instance 1: Air conditioner device_0000005112201299747090520589KPBJ (analysis period = June 1, 2025 - June 30, 2025, device SN = 0000005112201299747090520589KPBJ, date = 20250612, time period = 25, belongs to resident = [household number = 3750012340453]).

[0035] Instance 2: Resident_3750012340453 (household number = 3750012340453, this month's indicator = 335.4 (total), 172.2 (peak), 163.2 (valley), last month's indicator = 322.4 (total), 167.2 (peak), 155.2 (valley), electricity consumption = 13 (total), 5 (peak), 8 (valley), amount = 5.8997 (total), 2.8845 (peak), 3.0152 (valley), has device = [air conditioner device_0000005112201299747090520589KPBJ]).

[0036] Instance 3: Electricity price_202406 (time-of-use electricity price = 0.5769 (peak), 0.3769 (valley), tiered electricity price = 210 (first tier), 400 (second tier), belongs to time period = [analysis period = June 1, 2025 - June 30, 2025]).

[0037] S103, rule reasoning on air conditioner load data graph, to get air conditioner load associated rules; Based on the entity, attribute and hierarchical association relationship constructed in the air conditioner load data graph, the preset reasoning rule is used to perform logical deduction on the entity attribute and relationship in the air conditioner load data graph. The preset deduction rule includes but is not limited to: If the air conditioner running power ≠ 0, it is marked as "on"; If the air conditioner time period ∈ [32, 87], it is marked as "peak"; If the air conditioner time period ∈ [0, 31]∪[88, 95], it is marked as "valley"; If the air conditioner time period matches the activity time period, and the air conditioner date matches the activity date, it is marked as "participating in the activity".

[0038] By analyzing the implicit association between entities through the rule engine (such as deducing the peak and valley power consumption attributes by matching the air conditioner running time period with the electricity price time period, and associating the reward rules according to the air conditioner participating in the activity), new attributes (such as on state, peak valley identification, activity participation state) deduced by reasoning are supplemented to the corresponding entity, and the association logic formed by reasoning is solidified as structured air conditioner load association rules.

[0039] S104, based on the air conditioner load data graph and the air conditioner load association rule, form the air conditioner load fusion knowledge.

[0040] That is, the air conditioner load fusion knowledge includes the air conditioner load data graph and the air conditioner load association rule.

[0041] S2, based on the first electricity consumption behavior characteristics reflecting that the air conditioner does not participate in the energy-saving activity, set a plurality of benchmark scenarios, and determine the first air conditioner carbon emission of each benchmark scenario according to the air conditioner load fusion knowledge; It should be noted that the setting of the above-mentioned benchmark scenarios is strictly limited within the project boundary (the resident intelligent air conditioner in the invitation mode or the management mode included in the operation area range of the power grid) and the project counting period (the analysis period of the present application), and only focuses on carbon dioxide (CO2) as the main emission source for accounting greenhouse gas emission sources of the benchmark scenario and the project scenario. Methane (CH4) and nitrous oxide (N2O) are not included due to their small emission proportion, so as to ensure that the carbon emission calculation is carried out in the framework of clear boundary and reasonable selection of emission sources.

[0042] As shown in Figure 3 , it is a flowchart of step S2 of the embodiment of the present application. Referring to Figure 3 , the step S2 of the embodiment of the present application comprises: S201, based on the first electricity consumption behavior characteristics reflecting that the air conditioner does not participate in the energy-saving activity, set the first benchmark scenario, the second benchmark scenario and the third benchmark scenario; The first reference scene is a scene in which the air conditioner operates according to an average power consumption mode of a power grid operation area. If the power consumption information collection system lacks sufficient sample data covering the power grid operation area, the average power consumption mode cannot be accurately fitted, and the scene setting is not applicable.

[0043] The second reference scene is a scene in which the air conditioner operates according to a historical power consumption mode of a user. If the power consumption information collection system does not store historical data of the corresponding period, it is difficult to restore the historical power consumption mode, and the scene setting is not applicable.

[0044] The third reference scene is a scene in which the air conditioner operates according to a preset standard reference load curve. If the fine load data (such as device-level operation parameters and time period price-related load response data) of the load interaction platform are missing, the standard reference load curve cannot be calculated according to the standard rules, and the scene setting is not applicable.

[0045] S202, determining a first air conditioner carbon emission of the first reference scene based on air conditioner load fusion knowledge; Specifically, step S202 includes: 1) performing parameter extraction on the first reference scene based on an air conditioner load data graph to obtain a first parameter set; The first parameter set includes total residential power consumption of a power grid operation area, a power grid comprehensive marginal emission factor, a power grid transmission and distribution loss rate, total residential household number of the power grid operation area, and an advanced coefficient. The power grid comprehensive marginal emission factor is obtained based on a power grid power consumption marginal emission factor and a power grid capacity marginal emission factor.

[0046] Specifically, based on the association relationship between the "air conditioner" and the "resident" entities in the air conditioner load data graph, the total residential power consumption of the power grid operation area and the total residential household number of the power grid operation area (associated with the household number statistical information of the resident entity) are extracted. The power grid transmission and distribution loss rate is obtained through the "price" entity attribute, and based on the association rule between the "price" and the "emission factor" in the air conditioner load data graph, the power grid power consumption marginal emission factor and the power grid capacity marginal emission factor are extracted, and the power grid comprehensive marginal emission factor is calculated in combination with a preset weight. At the same time, according to the group characteristic data such as the proportion of efficient and energy-saving air conditioners in the power grid operation area, the advanced coefficient is extracted from the inference result of the air conditioner load data graph, and finally the first parameter set containing the above parameters is formed.

[0047] 2) performing operation processing on the total residential power consumption of the power grid operation area, the power grid comprehensive marginal emission factor, the power grid transmission and distribution loss rate, the total residential household number of the power grid operation area, and the advanced coefficient based on the air conditioner load association rule to obtain the first air conditioner carbon emission of the first reference scene.

[0048] In an embodiment, the operation processing is characterized by the following formula to calculate the first air conditioner carbon emission of the first reference scene: wherein, represents the first air conditioner carbon emission of the first reference scene, in tons of carbon dioxide equivalent, represents the total electricity consumption of residents in the power grid operation area, in kilowatt-hours, represents the power grid comprehensive marginal emission factor, in tons of carbon dioxide per megawatt-hour, represents the power grid transmission and distribution loss rate, in percent, represents the total number of households of residents in the power grid operation area, in households, represents the advanced coefficient.

[0049] In another embodiment, an operation process is implemented based on an artificial intelligence model to calculate the first air conditioner carbon emission of the first reference scene: By analyzing the parameter correlation of the first reference scene in the air conditioner load data graph, an artificial intelligence model is constructed with the first parameter set as input and the first air conditioner carbon emission of the first reference scene as output. In the training stage, the carbon emission calculation result obtained based on the above formula is used as the label, and the gradient boosting tree algorithm is used to optimize the model parameters, so that the model learns the complex mapping relationship between multiple parameters and carbon emission. In online operation, the first parameter set extracted in real time is input into the trained model, and the model output value is taken as the first air conditioner carbon emission of the first reference scene.

[0050] S203, determining the first air conditioner carbon emission of the second reference scene based on air conditioner load fusion knowledge; Specifically, step S203 includes: 1) performing parameter extraction on the second reference scene based on the air conditioner load data graph to obtain a second parameter set; The second parameter set includes the resident electricity consumption of the user in the corresponding period of the accounting period, the power grid comprehensive marginal emission factor, the power grid transmission and distribution loss rate, the meteorological factor correlation correction coefficient, and the work and rest feature correlation correction coefficient. The power grid comprehensive marginal emission factor is obtained based on the power grid electricity marginal emission factor and the power grid capacity marginal emission factor.

[0051] Specifically, according to the association relationship between the “resident” entity and the “date, time period” attribute in the air conditioner load data graph, the resident electricity consumption of the user in the corresponding period of the accounting period is extracted (matching the historical electricity consumption record in the time dimension of the accounting period); the power grid transmission and distribution loss rate is obtained through the “electricity price” entity attribute, and the power grid electricity marginal emission factor and the power grid capacity marginal emission factor are extracted according to the association rule of “electricity price” and “emission factor” in the air conditioner load data graph, and the power grid comprehensive marginal emission factor is calculated by combining the preset weight.

[0052] Further, based on the implicit correlation reasoning results of "air conditioner running power and daily maximum / minimum temperature" and "resident activity period and weekend / holiday" in the air conditioner load data atlas, meteorological factor correlation correction coefficients and work-rest feature correlation correction coefficients are extracted respectively, and a second parameter set containing the above parameters is finally formed.

[0053] 2) Based on the air conditioner load correlation rules, the resident electricity consumption of the user historical same period corresponding to the billing period, the grid comprehensive marginal emission factor, the grid transmission and distribution loss rate, the meteorological factor correlation correction coefficient and the work-rest feature correlation correction coefficient are calculated and processed to obtain the first air conditioner carbon emission of the second benchmark scenario.

[0054] In an embodiment, the calculation and processing are characterized by the following formula to calculate the first air conditioner carbon emission of the second benchmark scenario: wherein, represents the first air conditioner carbon emission of the second benchmark scenario, with the unit of tons of carbon dioxide equivalent, represents the resident electricity consumption of the user historical same period corresponding to the billing period, with the unit of kilowatt-hours, represents the grid comprehensive marginal emission factor, with the unit of tons of carbon dioxide per megawatt-hour, represents the grid transmission and distribution loss rate, with the unit of percentage, represents the meteorological factor correlation correction coefficient, represents the work-rest feature correlation correction coefficient.

[0055] In another embodiment, the calculation and processing are realized based on an artificial intelligence model to calculate the first air conditioner carbon emission of the second benchmark scenario: By analyzing the parameter correlation relationship of the second benchmark scenario in the air conditioner load data atlas, an artificial intelligence model is constructed with the second parameter set as input and the first air conditioner carbon emission of the second benchmark scenario as output; in the training stage, the carbon emission calculation result based on the above formula is used as the label, and the gradient boosting tree algorithm is used to optimize the model parameters, so that the model learns the complex mapping relationship between multiple parameters and carbon emission; in online operation, the second parameter set extracted in real time is input into the trained model, and the model output value is taken as the first air conditioner carbon emission of the second benchmark scenario.

[0056] S204, determining the first air conditioner carbon emission of the third benchmark scenario based on the air conditioner load fusion knowledge.

[0057] Specifically, step S204 includes: 1) Based on the air conditioner load data atlas, parameters of the third benchmark scenario are extracted to obtain a third parameter set; The third parameter set comprises a resident baseline load at each time point in the accounting period, a grid comprehensive marginal emission factor, a grid transmission and distribution loss rate, and a total number of resident households in a grid operation area. The grid comprehensive marginal emission factor is obtained based on a grid power marginal emission factor and a grid capacity marginal emission factor.

[0058] Specifically, according to the time dimension association relationship between the "analysis period" attribute of the "operation" entity in the air conditioner load data graph and the "air conditioner associated electricity price", the resident baseline load at each time point in the accounting period (the load record at each time point matching the start time point and the end time point) is extracted according to the user baseline load calculation principle in GB / T32127-2015; the grid transmission and distribution loss rate is obtained through the "electricity price" entity attribute, and the grid power marginal emission factor and the grid capacity marginal emission factor are extracted according to the association rule between "electricity price" and "emission factor" in the air conditioner load data graph, and the grid comprehensive marginal emission factor is calculated by combining the preset weight; at the same time, based on the household number statistical information of the "resident" entity, the total number of resident households in the grid operation area is extracted, and finally the third parameter set containing the above parameters is formed.

[0059] 2) The resident baseline load at each time point in the accounting period, the grid comprehensive marginal emission factor, the grid transmission and distribution loss rate, and the total number of resident households in the grid operation area are calculated based on the air conditioner load association rule, and the first air conditioner carbon emission of the third reference scenario is obtained.

[0060] In an embodiment, the operation processing is characterized by the following formula to calculate the first air conditioner carbon emission of the third reference scenario: wherein, represents the first air conditioner carbon emission of the third reference scenario, and the unit is ton of carbon dioxide equivalent, represents the resident baseline load at each time point in the accounting period, and the unit is kilowatt, represents the grid comprehensive marginal emission factor, and the unit is ton of carbon dioxide per megawatt hour, represents the grid transmission and distribution loss rate, and the unit is percent, represents the total number of resident households in the grid operation area, and the unit is household, represents the start time point of the accounting period, represents the end time point of the accounting period. In another embodiment, the operation processing is realized based on an artificial intelligence model to calculate the first air conditioner carbon emission of the third reference scenario:

[0061] ​By combing the parameter correlation relationship of the third reference scene in the air conditioner load data graph, an artificial intelligence model is constructed, taking the third parameter set as input and the first air conditioner carbon emission of the third reference scene as output; in the training stage, the calculation result of carbon emission obtained based on the above formula is taken as a label, and the gradient boosting tree algorithm is used to optimize the model parameters, so that the model learns the complex mapping relationship between multiple parameters and carbon emission; in online operation, the third parameter set extracted in real time is input into the trained model, and the output value of the model is taken as the first air conditioner carbon emission of the third reference scene.

[0062] S3, based on the second electricity consumption behavior characteristics reflecting the air conditioner participating in the electricity-saving activity, set the project scene, and determine the second air conditioner carbon emission of the project scene according to the air conditioner load fusion knowledge; As Figure 4 shown, it is the flowchart of step S3 of the embodiment of the present application. Referring to Figure 4 , the step S3 of the embodiment of the present application comprises: S301, based on the second electricity consumption behavior characteristics reflecting the air conditioner participating in the electricity-saving activity, set the project scene; The project scene is the running scene of the air conditioner participating in the electricity-saving activity.

[0063] S302, based on the air conditioner load data graph, perform parameter extraction on the project scene to obtain a fourth parameter set; The fourth parameter set comprises the air conditioner participating in the electricity-saving activity power consumption, the power grid comprehensive marginal emission factor and the power grid transmission and distribution loss rate. The power grid comprehensive marginal emission factor is obtained based on the power grid power marginal emission factor and the power grid capacity marginal emission factor.

[0064] Specifically, according to the "air conditioner associated activity" relationship (many-to-one) between the "air conditioner" entity and the "activity" entity in the air conditioner load data graph, combined with the knowledge reasoning rule (if air conditioner. Time period = activity. Time period and air conditioner. Date = activity. Date, then marked as "participating in the activity"), the running data of the air conditioner participating in the electricity-saving activity is screened out, and the air conditioner participating in the electricity-saving activity power consumption is calculated through the "running power" and "time period" attributes of the "air conditioner" entity (the total power consumption of the air conditioner in the statistical project is counted).

[0065] Further, the power grid transmission and distribution loss rate is extracted from the "electricity price" entity attribute in the air conditioner load data graph, and the power grid power marginal emission factor and the power grid capacity marginal emission factor are extracted according to the correlation rule of "electricity price" and "emission factor", and the power grid comprehensive marginal emission factor is calculated combined with the preset weight (power grid power marginal emission factor weight and power grid capacity marginal emission factor weight).

[0066] Finally, the above parameters are integrated to form the fourth parameter set comprising the air conditioner participating in the electricity-saving activity power consumption, the power grid comprehensive marginal emission factor and the power grid transmission and distribution loss rate.

[0067] S303、based on air conditioning load association rule to air conditioning participating in power saving activity power consumption, power grid comprehensive marginal emission factor and power grid transmission and distribution loss rate are calculated and processed, the second air conditioning carbon emission of project scene is obtained.

[0068] In an embodiment, the following formula is used to represent the calculation to calculate the second air conditioning carbon emission of the project scene: Wherein, The second air conditioning carbon emission of the project scene is represented by the unit of tons of carbon dioxide equivalent, The air conditioning participating in power saving activity power consumption is represented by the unit of megawatt hours, The power grid comprehensive marginal emission factor is represented by the unit of tons of carbon dioxide per megawatt hour, The power grid transmission and distribution loss rate is represented by the unit of percentage.

[0069] In another embodiment, the following formula is used to represent the calculation to calculate the second air conditioning carbon emission of the project scene: By analyzing the parameter correlation of the project scene in the air conditioning load data graph, an artificial intelligence model is constructed, which takes the fourth parameter set as input and the second air conditioning carbon emission of the project scene as output. In the training stage, the carbon emission calculation result obtained based on the above formula is used as the label, and the gradient boosting tree algorithm is used to optimize the model parameters, so that the model learns the complex mapping relationship between multiple parameters and carbon emission. In online operation, the fourth parameter set extracted in real time is input into the trained model, and the model output value is used as the second air conditioning carbon emission of the project scene.

[0070] S4, based on each first air conditioning carbon emission and second air conditioning carbon emission, the air conditioning carbon emission reduction is obtained, and the air conditioning carbon emission reduction and the air conditioning electricity and billing data obtained by analyzing the air conditioning load fusion knowledge are integrated to form the air conditioning load analysis result.

[0071] As shown in Figure 5 , it is the flowchart of step S4 of the embodiment of the present application. Referring to Figure 5 , the step S4 of the embodiment of the present application comprises: S401, the extreme value screening is carried out on each first air conditioning carbon emission to obtain the maximum air conditioning carbon emission of the reference scene, and the difference operation is carried out on the maximum air conditioning carbon emission of the reference scene and the second air conditioning carbon emission to obtain the air conditioning carbon emission reduction; Specifically, the following formula is used to calculate the air conditioning carbon emission reduction in this embodiment: Wherein, The air conditioning carbon emission reduction of a single resident is represented by the unit of tons of carbon dioxide equivalent, represents the maximum air conditioner carbon emission reduction amount of the reference scenario, in tons of carbon dioxide equivalent, represents the second air conditioner carbon emission of the project scenario, in tons of carbon dioxide equivalent.

[0072] It should be noted that the above calculation logic of single household carbon emission reduction can be further extended to the full amount of project reduction accounting.

[0073] Specifically, when extended to the first period, if it is an invitation mode, the total number of residents responding to the invitation task needs to be counted, and the single household reduction amount is accumulated according to the following formula to account for the project reduction amount in this mode: wherein, represents the project reduction amount in the first period using the electricity saving activity invitation mode, in tons of carbon dioxide equivalent, represents the single household reduction amount in the first period, in tons of carbon dioxide equivalent, represents the total number of residents responding to the electricity saving activity invitation task, in households.

[0074] If it is a hosting mode, the total number of residents responding to the hosting agreement needs to be counted, and the project reduction amount in this mode is accounted for by the following formula: wherein, represents the project reduction amount in the first period using the electricity saving activity hosting mode, in tons of carbon dioxide equivalent, represents the single household reduction amount in the first period, in tons of carbon dioxide equivalent, represents the total number of residents responding to the electricity saving activity hosting agreement, in households.

[0075] Finally, the total project reduction amount is determined by superimposing the reduction amount of the invitation mode and the reduction amount of the hosting mode, so as to realize the hierarchical accounting from single household carbon emission reduction to project full amount reduction, and to ensure that the reduction amount accounting covers different groups of residents in different participation modes, and to fit the multiple operation scenarios of invitation and hosting in actual business.

[0076] S402, index extraction and correlation calculation are performed on the air conditioner load fusion knowledge to obtain air conditioner electricity and billing data, and air conditioner carbon emission reduction amount and air conditioner electricity and billing data are integrated to form air conditioner load analysis results.

[0077] The air conditioner electricity and billing data includes the electricity consumption and electricity charges of the air conditioner in different time periods, and the electricity consumption and electricity charges of the air conditioner in different ladder electricity price intervals.

[0078] Specifically, based on the association relationship between the "air conditioner" entity and the "time period" and "electricity price" entities in the air conditioner load data graph, the running power, time length and other data of the air conditioner in different time periods (peak and valley periods) are extracted, combined with the time-of-use electricity price, step electricity price threshold and other information of the "electricity price" entity, the electricity consumption is calculated by the product of power and time, and the electricity charge is calculated by the product of electricity consumption and corresponding time period electricity price, to obtain the electricity consumption and electricity charge of the air conditioner in different time periods; similarly, according to the electricity threshold of the step electricity price interval, the electricity consumption of the air conditioner in each step interval is counted, multiplied by the corresponding step electricity price to calculate the electricity charge, and the electricity consumption and electricity charge in different step electricity price intervals are generated.

[0079] Further, the calculated carbon emission reduction amount of the air conditioner is associated according to a preset data integration rule, such as a household unit, and the carbon emission reduction amount of a single household is associated with the electricity consumption and billing details of the household, and the two types of data are structured and integrated to form the final air conditioner load analysis result.

[0080] As shown in Figure 6 , it is a schematic diagram of the air conditioner load analysis result of the embodiment of the present application. Referring to Figure 6 , the air conditioner load analysis result is output in the form of a resident air conditioner load analysis report, integrating the carbon emission reduction amount (such as the current period reduction value) of a single household with the electricity consumption and billing data (including basic electricity charge, peak and valley electricity consumption, amount, step electricity charge statistics of each step), supplementing equipment SN, analysis period, power supply / data / analysis unit and other information, and structured according to the report format, so that residents can clearly view the electricity consumption time period distribution, electricity charge composition and carbon emission reduction effectiveness, and also provide intuitive data carriers for the power grid side to carry out load management and energy saving guidance.

[0081] The air conditioner load analysis method based on data fusion and carbon emission reduction accounting according to the embodiment of the present application, according to the fine disassembly of the electricity consumption and billing data by the air conditioner load data graph, combined with the carbon emission difference value calculation of the reference scene and the project scene, firstly forms a quantitative association between the time-of-use electricity consumption, step electricity charge and carbon emission reduction amount of the air conditioner single device, breaks through the limitation of traditional electricity consumption data only reflecting the total amount, provides data-based guidance for energy saving behavior, and promotes the change of resident electricity consumption from passive response to active optimization; by identifying the carbon emission difference of the air conditioner load in different scenes, demand response schemes can be developed accordingly to realize flexible regulation and control of the air conditioner load, effectively suppress the peak-valley difference of electricity consumption, reduce the impact of extreme load on power grid equipment, and improve the economy and reliability of power grid operation; deeply coupling the air conditioner load data and carbon emission reduction accounting promotes the transformation of the power grid from a traditional power supplier to a comprehensive energy service provider, and helps the intelligent upgrading of the energy system.

[0082] As shown in Figure 7 , it is a structural schematic diagram of an air conditioner load analysis system based on data fusion and carbon emission reduction accounting according to an embodiment of the present application. Referring to Figure 7An embodiment of the present invention provides an air conditioning load analysis system based on data fusion and carbon emission reduction accounting, including: Data fusion processing module 1 is used to obtain air conditioning related data in different dimensions and fuse all air conditioning related data to obtain air conditioning load fusion knowledge; A baseline carbon emission determination module 2 is configured to set a plurality of baseline scenarios based on a first electricity usage behavior characteristic reflecting that the air conditioner does not participate in the electricity saving activity, and determine a first air conditioner carbon emission amount for each baseline scenario based on the air conditioner load fusion knowledge; The project carbon emission determination module 3 is configured to set a project scenario based on a second electricity consumption behavior characteristic reflecting the air conditioner's participation in the power saving activity, and determine a second air conditioner carbon emission amount in the project scenario based on the air conditioner load fusion knowledge; The analysis result generation module 4 is used to obtain the air conditioning carbon emission reduction based on each first air conditioning carbon emission and the second air conditioning carbon emission, and integrate the air conditioning carbon emission reduction with the air conditioning electricity consumption and billing data obtained by analyzing the air conditioning load fusion knowledge to form the air conditioning load analysis result.

[0083] It should be noted that the various modules in the above-mentioned air-conditioning load analysis system based on data fusion and carbon emission reduction accounting can be implemented in whole or in part through software, hardware, and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules. For the specific definition of an air-conditioning load analysis system based on data fusion and carbon emission reduction accounting, please refer to the definition of an air-conditioning load analysis method based on data fusion and carbon emission reduction accounting above. The two have the same functions and effects and will not be repeated here.

[0084] In summary, the embodiment of the present invention provides an air-conditioning load analysis method and system based on data fusion and carbon emission reduction accounting. According to the air-conditioning load data map, the electricity consumption and billing data are refinedly disassembled, and the carbon emission difference between the baseline scenario and the project scenario is combined to form a quantitative correlation between the time-sharing electricity consumption, tiered electricity charges and carbon emission reduction of the air-conditioning unit equipment for the first time. It breaks through the limitation that traditional electricity consumption data only reflects the total amount, provides data guidance for energy-saving behavior, and promotes the transformation of residents' electricity consumption from passive response to active optimization; by identifying the carbon emission differences of air-conditioning loads in different scenarios, demand response plans can be formulated in a targeted manner to achieve flexible regulation of air-conditioning loads, effectively suppress the peak and valley differences in electricity consumption, reduce the impact of extreme loads on power grid equipment, and improve the economy and reliability of power grid operation; deeply couples air-conditioning load data with carbon emission reduction accounting, promotes the transformation of the power grid from a traditional power supplier to a comprehensive energy service provider, and helps the energy system to upgrade to intelligence.

[0085] Each embodiment in this specification is described in a progressive manner, and the same or similar parts of each embodiment can be directly referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. It should be noted that the various technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the various technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0086] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and substitutions can be made without departing from the technical principles of the present invention. These improvements and substitutions should also be regarded as the scope of protection of the present invention.

Claims

1. An air conditioner load analysis method based on data fusion and carbon emission reduction accounting, characterized in that, The method comprises the following steps: acquiring air conditioner related data in different dimensions, and performing fusion processing on all the air conditioner related data to obtain air conditioner load fusion knowledge; setting a plurality of benchmark scenarios based on first electricity consumption behavior characteristics reflecting that the air conditioner does not participate in power saving activities, and determining first air conditioner carbon emissions of each of the benchmark scenarios according to the air conditioner load fusion knowledge; setting a project scenario based on second electricity consumption behavior characteristics reflecting that the air conditioner participates in power saving activities, and determining second air conditioner carbon emissions of the project scenario according to the air conditioner load fusion knowledge; obtaining air conditioner carbon emission reduction based on each of the first air conditioner carbon emissions and the second air conditioner carbon emissions, and integrating the air conditioner carbon emission reduction and air conditioner electricity and billing data obtained by analyzing the air conditioner load fusion knowledge to form an air conditioner load analysis result.

2. The air conditioning load analysis method based on data fusion and carbon emission reduction accounting according to claim 1, characterized in that, The method of acquiring air conditioner related data in different dimensions and performing fusion processing on all the air conditioner related data to obtain air conditioner load fusion knowledge comprises the following steps: accessing a plurality of power service associated platforms to respectively acquire air conditioner load data, power grid operation data and resident activity data; performing associated fusion and structured modeling on the air conditioner load data, the power grid operation data and the resident activity data to obtain an air conditioner load data graph; performing rule reasoning on the air conditioner load data graph to obtain air conditioner load association rules; forming air conditioner load fusion knowledge based on the air conditioner load data graph and the air conditioner load association rules.

3. The air conditioning load analysis method based on data fusion and carbon emission reduction accounting of claim 2, wherein, The method of performing associated fusion and structured modeling on the air conditioner load data, the power grid operation data and the resident activity data to obtain an air conditioner load data graph comprises the following steps: performing preprocessing on the air conditioner load data, the power grid operation data and the resident activity data to obtain a standardized data set; performing entity recognition and attribute extraction on the standardized data set based on a preset ontology relationship to obtain a multi-source entity set; performing homologous entity alignment on the multi-source entity set to obtain inter-entity mapping relationships; constructing an air conditioner load data graph containing hierarchical structure and associated attributes by taking entities as nodes and the inter-entity mapping relationships as edges.

4. The air conditioning load analysis method based on data fusion and carbon emission reduction accounting according to claim 2, characterized in that, The method of setting a plurality of benchmark scenarios based on first electricity consumption behavior characteristics reflecting that the air conditioner does not participate in power saving activities, and determining first air conditioner carbon emissions of each of the benchmark scenarios according to the air conditioner load fusion knowledge comprises the following steps: setting a first benchmark scenario, a second benchmark scenario and a third benchmark scenario based on first electricity consumption behavior characteristics reflecting that the air conditioner does not participate in power saving activities; determining first air conditioner carbon emissions of the first benchmark scenario based on the air conditioner load fusion knowledge, wherein the first benchmark scenario is a scenario in which the air conditioner operates in an average electricity consumption mode according to power grid operation regions; determining first air conditioner carbon emissions of the second benchmark scenario based on the air conditioner load fusion knowledge, wherein the second benchmark scenario is a scenario in which the air conditioner operates in a historical same period electricity consumption mode of a user; determining first air conditioner carbon emissions of the third benchmark scenario based on the air conditioner load fusion knowledge, wherein the third benchmark scenario is a scenario in which the air conditioner operates in a preset standard benchmark load curve.

5. The air conditioning load analysis method based on data fusion and carbon emission reduction accounting according to claim 4, characterized in that, The first air conditioner carbon emission of the first reference scene is determined based on the air conditioner load fusion knowledge, and the method comprises the steps of: The first reference scene is parameter extracted based on the air conditioner load data graph to obtain a first parameter set, wherein the first parameter set comprises total residential electricity consumption in the power grid operation area, power grid comprehensive marginal emission factor, power grid transmission and distribution loss rate, total number of residential households in the power grid operation area, and advanced coefficient, and the power grid comprehensive marginal emission factor is obtained based on power grid electricity quantity marginal emission factor and power grid capacity marginal emission factor; The total residential electricity consumption in the power grid operation area, the power grid comprehensive marginal emission factor, the power grid transmission and distribution loss rate, the total number of residential households in the power grid operation area, and the advanced coefficient are processed based on the air conditioner load association rule to obtain the first air conditioner carbon emission of the first reference scene.

6. The air conditioning load analysis method based on data fusion and carbon emission reduction accounting according to claim 4 is characterized in that: The first air conditioner carbon emission of the second reference scene is determined based on the air conditioner load fusion knowledge, and the method comprises the steps of: The second reference scene is parameter extracted based on the air conditioner load data graph to obtain a second parameter set, wherein the second parameter set comprises user historical corresponding period resident electricity consumption, power grid comprehensive marginal emission factor, power grid transmission and distribution loss rate, meteorological factor correlation correction coefficient, and work and rest feature correlation correction coefficient, and the power grid comprehensive marginal emission factor is obtained based on power grid electricity quantity marginal emission factor and power grid capacity marginal emission factor; The user historical corresponding period resident electricity consumption, the power grid comprehensive marginal emission factor, the power grid transmission and distribution loss rate, the meteorological factor correlation correction coefficient, and the work and rest feature correlation correction coefficient are processed based on the air conditioner load association rule to obtain the first air conditioner carbon emission of the second reference scene.

7. The air conditioning load analysis method based on data fusion and carbon emission reduction accounting according to claim 4 is characterized in that: The first air conditioner carbon emission of the third reference scene is determined based on the air conditioner load fusion knowledge, and the method comprises the steps of: The third reference scene is parameter extracted based on the air conditioner load data graph to obtain a third parameter set, wherein the third parameter set comprises hourly resident baseline load in the accounting period, power grid comprehensive marginal emission factor, power grid transmission and distribution loss rate, and total number of residential households in the power grid operation area, and the power grid comprehensive marginal emission factor is obtained based on power grid electricity quantity marginal emission factor and power grid capacity marginal emission factor; The hourly resident baseline load in the accounting period, the power grid comprehensive marginal emission factor, the power grid transmission and distribution loss rate, and the total number of residential households in the power grid operation area are processed based on the air conditioner load association rule to obtain the first air conditioner carbon emission of the third reference scene.

8. The air conditioning load analysis method based on data fusion and carbon emission reduction accounting according to claim 2, characterized in that, The second electricity consumption behavior characteristic setting project scene reflecting the air conditioner participating in the power saving activity is set, and the second air conditioner carbon emission of the project scene is determined based on the air conditioner load fusion knowledge, and the method comprises the steps of: The second electricity consumption behavior characteristic setting project scene reflecting the air conditioner participating in the power saving activity is set, wherein the project scene is the operation scene of the air conditioner participating in the power saving activity; extract parameters of the project scene based on the air conditioner load data graph, to obtain a fourth parameter set, wherein the fourth parameter set includes air conditioner power consumption in power saving activities, grid comprehensive marginal emission factor and grid transmission and distribution loss rate, the grid comprehensive marginal emission factor is obtained based on grid power marginal emission factor and grid capacity marginal emission factor; based on the air conditioner load association rule, the air conditioner power consumption in power saving activities, the grid comprehensive marginal emission factor and the grid transmission and distribution loss rate are calculated and processed to obtain the second air conditioner carbon emission of the project scene.

9. The air conditioning load analysis method based on data fusion and carbon emission reduction accounting according to claim 1, characterized in that, based on each of the first air conditioner carbon emission and the second air conditioner carbon emission, the air conditioner carbon emission reduction is obtained, and the air conditioner carbon emission reduction and the air conditioner power and billing data obtained by analyzing the air conditioner load fusion knowledge are integrated to form the air conditioner load analysis result, including: extreme value screening is performed on each of the first air conditioner carbon emission to obtain the maximum air conditioner carbon emission of the benchmark scene, and difference operation is performed on the maximum air conditioner carbon emission of the benchmark scene and the second air conditioner carbon emission to obtain the air conditioner carbon emission reduction; index extraction and association calculation are performed on the air conditioner load fusion knowledge to obtain the air conditioner power and billing data, and the air conditioner carbon emission reduction and the air conditioner power and billing data are integrated to form the air conditioner load analysis result, wherein the air conditioner power and billing data includes the power consumption and electricity fee of the air conditioner in different time periods and the power consumption and electricity fee of the air conditioner in different ladder electricity price intervals.

10. An air conditioner load analysis system based on data fusion and carbon emission reduction accounting, characterized by, including: a data fusion processing module for obtaining air conditioner related data in different dimensions and performing fusion processing on all the air conditioner related data to obtain air conditioner load fusion knowledge; a benchmark carbon emission determination module for setting a plurality of benchmark scenes based on first electricity consumption behavior characteristics reflecting that air conditioners do not participate in power saving activities, and determining the first air conditioner carbon emission of each of the benchmark scenes according to the air conditioner load fusion knowledge; a project carbon emission determination module for setting a project scene based on second electricity consumption behavior characteristics reflecting that air conditioners participate in power saving activities, and determining the second air conditioner carbon emission of the project scene according to the air conditioner load fusion knowledge; an analysis result generation module for obtaining air conditioner carbon emission reduction based on each of the first air conditioner carbon emission and the second air conditioner carbon emission, and integrating the air conditioner carbon emission reduction and the air conditioner power and billing data obtained by analyzing the air conditioner load fusion knowledge to form the air conditioner load analysis result.

Images