Electric power indirect carbon emission metering platform

Abstract

The invention is suitable for the technical field of electric power systems, and provides an electric power indirect carbon emission metering platform, which comprises an equipment layer comprising an electric energy meter, an electric carbon meter, a sensor and communication equipment; the data layer comprises a source side, a network side and a load side; and the application layer is used for equipment operation management, operation state monitoring, a carbon emission trading system, carbon reduction analysis and traceability analysis. According to the invention, comprehensive tracking of carbon emission is taken as a core target, and an electric power indirect carbon emission metering platform is designed. According to the method, a source-network-load three-side'power-carbon emission 'model in an electric power system is integrated, the correction problem of distributed energy output data is considered, and the measurement precision of the platform on electric power carbon emission is remarkably improved. According to the invention, electric power is taken as a center, a typical application scene is constructed by realizing convergence, fusion, sharing exchange and deep mining analysis of various energy data, multi-dimensional and real-time carbon emission monitoring and metering are realized, and an effective carbon treatment support tool is provided for the government.

Description

Technical Field

[0001] The present invention belongs to the technical field of power systems, and in particular relates to an indirect carbon emission metering platform for power. Background Art

[0002] With the rapid growth of the world economy, environmental problems are becoming increasingly serious, especially greenhouse gas emissions, which have become the focus of global attention. It is imperative to explore new contributions in the field of construction and enhance the competitiveness of enterprises in the wave of the carbon era.

[0003] The existing carbon emission monitoring and carbon governance system has some defects: 1) Low data accuracy: Due to the limitations of monitoring methods, carbon emission data often have errors and it is difficult to accurately reflect the actual situation. 2) Limited coverage: Most monitoring focuses on direct emission sources, and insufficient monitoring of indirect emission sources such as electricity leads to incomplete carbon footprint tracking. 3) Poor real-time performance: The lack of a real-time monitoring system makes it impossible to respond to changes in carbon emissions in a timely manner, affecting the efficiency and effectiveness of carbon governance. 4) Low level of intelligence: Insufficient data processing and analysis capabilities make it difficult to deeply explore the laws and trends behind carbon emissions and provide strong support for policy making. For this reason, an indirect carbon emission measurement platform for electricity is proposed. Summary of the invention

[0004] The purpose of the present invention is to provide an electricity indirect carbon emission measurement platform, aiming to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] An electricity indirect carbon emission measurement platform, comprising:

[0007] The equipment layer includes energy meters, carbon meters, sensors, and communication equipment for collecting and transmitting data;

[0008] The data layer includes:

[0009] The source side includes carbon emission source data, forecast data and unit output data;

[0010] The grid side includes power transmission data and carbon calculation results;

[0011] The load side is used to record electricity consumption and carbon emissions;

[0012] The application layer is used for equipment operation management, operation status monitoring, carbon emission trading system, carbon reduction analysis and traceability analysis.

[0013] Furthermore, the source side adopts a power plant carbon emission model to calculate the electric carbon factor of the generator set based on the carbon emission and power generation data collected at the equipment layer.

[0014] Furthermore, the carbon emission model of the power plant is as follows:

[0015] Based on the carbon emissions and power generation data collected at the equipment level, the generator carbon factor is calculated as shown in Formula 1:

[0016] Formula 1: λ Gi =E Gi / P Gi ;

[0017] Where λ Gi is the carbon emission factor of unit i; E Gi is the carbon emission of unit i; P Gi It is the real-time output data of unit i.

[0018] Furthermore, the grid side applies the basic theory of carbon flow and uses the data from the electricity meter and the electricity carbon meter to update the carbon information of each node in the system in real time, including calculating the carbon input and carbon emission intensity of the node.

[0019] Furthermore, the specific calculation process on the network side is as follows:

[0020] According to the principle of carbon emission conservation, the node input carbon amount is shown in formula 2:

[0021] Formula 2:

[0022] Where E in is the total carbon input at node n; in_k is the electric carbon factor of the kth input branch of the node; P in_k is the power of the kth input branch of the node;

[0023] Based on the basic theory of carbon flow, the node carbon emission intensity e n The calculation is shown in formula 3:

[0024] Formula 3:

[0025] Where e n is the carbon potential at node n; Ω is the unit set.

[0026] Furthermore, the load side combines the user's electricity consumption and the node carbon emission intensity, adopts the user's electricity carbon emission measurement model, and calculates the user's electricity carbon emission.

[0027] Furthermore, the user electricity carbon emissions measurement model is as follows:

[0028] Carbon emissions generated by electricity consumption n The power consumption of the user P n and the carbon emission intensity e at the user node n Product, see formula 4:

[0029] Formula 4: E n =e n ·P n ;

[0030] Where E n is the user’s carbon emissions; P n For users' electricity consumption.

[0031] Furthermore, the data layer adopts a data correction model, which performs outlier processing and new energy output prediction on the data on the source side, grid side and load side. The outlier processing method uses moving smoothing to replace the abnormal data values, and the new energy output prediction uses a direct method or an indirect method to predict the output of new energy.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] 1. This invention focuses on the power system and takes comprehensive tracking of carbon emissions as its core goal, aiming to design a set of indirect carbon emission measurement platform for power. This innovative solution integrates the "power-carbon emission" model of the three sides of the power system, namely source-grid-load, and considers the correction of distributed energy output data, thereby significantly improving the platform's measurement accuracy of power carbon emissions.

[0034] 2. The present invention takes electricity as the center and constructs a typical application scenario by realizing the aggregation, integration, sharing and exchange of various energy data and deep mining and analysis. This not only realizes multi-dimensional and real-time carbon emission monitoring and measurement, but also provides the government with an effective carbon governance support tool. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a framework diagram of the present invention.

[0036] Figure 2 It is the principle diagram of the BP neural network in the present invention. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0038] The specific implementation of the present invention is described in detail below in conjunction with specific embodiments.

[0039] An embodiment of the present invention provides an indirect carbon emission measurement platform for electricity. The platform construction idea is as follows:

[0040] Multi-source data integration: collects relevant data models such as regional site carbon emission monitoring, line power monitoring, cloud platform communication calculation, and outputs carbon potential and carbon emission data of each node on the user side in real time.

[0041] Promote carbon data aggregation: Create a carbon data aggregation platform that integrates data collection, cleaning, integration, storage, analysis, and application functions to achieve the aggregation, fusion, sharing, exchange, and mining and analysis of multi-source heterogeneous carbon data;

[0042] Build an indirect carbon emission measurement platform for electricity: Based on the carbon data fusion platform, build an indirect carbon emission measurement platform for electricity that integrates real-time carbon emission monitoring, carbon emission prediction and early warning, carbon emission management, and carbon emission reduction strategy simulation;

[0043] Develop carbon digital products and services: Develop carbon digital products and services such as carbon emission accounting, carbon trading, carbon finance, carbon footprint, and carbon neutrality assessment for government decision-making, social governance, and user smart energy use, to provide data support and decision-making services.

[0044] like Figure 1 As shown, the electricity indirect carbon emission measurement platform specifically includes:

[0045] The equipment layer includes energy meters, carbon meters, sensors, and communication equipment for collecting and transmitting data;

[0046] The data layer includes:

[0047] The source side includes carbon emission source data, forecast data and unit output data;

[0048] The grid side includes power transmission data and carbon calculation results;

[0049] The load side is used to record electricity consumption and carbon emissions;

[0050] The application layer is used for equipment operation management, operation status monitoring, carbon emission trading system, carbon reduction analysis and traceability analysis.

[0051] In the embodiment of the present invention, the present invention is designed from the device layer, data layer and application layer, integrating carbon emission monitoring, power transmission and cloud computing to achieve full-link carbon footprint tracking.

[0052] As a preferred embodiment of the present invention, the data layer includes power plant carbon emission model, carbon flow basic theory, user electricity carbon emission measurement, and data correction model. Specifically:

[0053] 1) Power plant carbon emission model (on the source side):

[0054] Based on the generator carbon emission data and power generation data measured by the carbon emission metering device, the generator carbon factor is calculated as shown in Formula 1. The carbon factor of the generator set is the node carbon potential at the power plant and the branch carbon flow rate on the outgoing line of the power plant.

[0055] Formula 1: λ Gi =E Gi / P Gi ;

[0056] Where λ Gi is the carbon emission factor of unit i; E Gi is the carbon emission of unit i; P Gi It is the real-time output data of unit i.

[0057] 2) Basic theory of carbon flow (on the network side):

[0058] For transmission lines, due to the interconnectivity and complexity of the power grid, any node may contain electricity from different power plants and multiple energy conversions at the same time. According to the principle of carbon emission conservation, the node input carbon amount is shown in Formula 2:

[0059] Formula 2:

[0060] Where E in is the total carbon input at node n; in_k is the electric carbon factor of the kth input branch of the node; P in_k is the power of the kth input branch of the node;

[0061] Based on the basic theory of carbon flow, the node carbon emission intensity e n The calculation is shown in formula 3:

[0062] Formula 3:

[0063] Where e n is the carbon potential at node n; Ω is the unit set.

[0064] 3) User electricity carbon emissions measurement (on the load side):

[0065] For users’ electricity consumption, the carbon emissions generated by users’ electricity consumption are R n , is the power consumption of the user P n and the carbon emission intensity e at the user node n Product, see formula 4:

[0066] Formula 4: E n =e n ·P n ;

[0067] Where E n is the user’s carbon emissions; Pn For users' electricity consumption.

[0068] 4) Data correction model (throughout the data layer), which processes outliers and predicts the output of renewable energy for data on the source side, grid side, and load side;

[0069] Outlier processing: Common outlier processing methods include deletion, replacement, transformation, or machine learning when the data volume is large and complex. For carbon emission data values ​​sorted by time, due to the randomness of renewable energy output, moving smoothing can be used to replace abnormal data values.

[0070] New energy output prediction: The power output of new energy has a direct impact on the calculation of carbon emissions. Common prediction methods include direct method and indirect method. The direct method is to directly predict the historical data of new energy power, and the indirect method is to first predict the required meteorological data and then predict the power of new energy. Taking wind power generation as an example, the BP (Back propagation) neural network model is used to first correct the wind speed sequence, and then polynomials, Fourier transforms, etc. are used to compare the power output data of new energy before and after correction.

[0071] like Figure 2 As shown, the principle of BP neural network is as follows:

[0072] Initialization: Setting the initial weights and biases of the neural network.

[0073] Input training data: The collected wind speed sequence and other relevant meteorological data are input as training samples.

[0074] Training data normalization: In order to improve training efficiency and model performance, the training data is normalized.

[0075] Establish BP neural network: construct a neural network structure including input layer, hidden layer and output layer.

[0076] Set parameters and train: Set parameters such as learning rate and number of iterations, and adjust network weights through the back-propagation algorithm so that the model output gradually approaches the true value.

[0077] Testing the BP network model: Use an independent test dataset to evaluate the prediction performance of the model.

[0078] Data denormalization: Denormalize the predicted values ​​output by the model to obtain the actual wind speed or power prediction values.

[0079] Result analysis: Analyze the prediction results and evaluate the accuracy and reliability of the model. If the error or number of learning times reaches the preset requirements, the training ends; otherwise, it may be necessary to adjust the model parameters or retrain.

[0080] Embodiment 1: Taking distributed wind power generation as an example, the data correction method adopted by the platform is experimentally simulated and its effectiveness is verified.

[0081] This embodiment is based on 360 groups of actual wind speed-actual power data in the region over 30 days, where the wind speed information comes from the actual wind speed information of the numerical weather forecast NWP, and the SCADA wind speed information recorded by the wind turbine is used as a correction reference. This experiment will use the 1st to 180th groups of SCADA data to correct the NWP wind speed information, and on this basis, use the corrected NWP wind speed sequence to perform power prediction training for groups 181-358. The data correction and prediction both use BP neural network, and finally obtain the power prediction data for groups 359 and 360. The experimental control group uses the uncorrected NWP wind speed sequence and actual power data for Fourier curve fitting, and performs power prediction on groups 359 and 360. The power prediction results under the curve fitting model are shown in Table 1. The power prediction results under the BP neural network correction model are shown in Table 2.

[0082] Table 1

[0083] Group Curve Fitting Power Prediction Actual power output Curve fitting error 359 51.3516 1310.156372 96.8％ 360 87.1854 1272.199829 83.15％

[0084] Table 2

[0085]

[0086] The results show that under the BP neural network correction model, the data accuracy is significantly improved, proving the effectiveness of the data correction method adopted by the platform.

[0087] The above are only preferred embodiments of the present invention. It should be pointed out that, for those skilled in the art, several modifications and improvements can be made without departing from the concept of the present invention. These should also be regarded as the protection scope of the present invention. These will not affect the effect of the implementation of the present invention and the practicality of the patent.

Claims

1. An indirect carbon emission measurement platform for electricity, characterized in that: include: The equipment layer includes energy meters, carbon meters, sensors, and communication equipment for collecting and transmitting data; The data layer includes: The source side includes carbon emission source data, forecast data and unit output data; The grid side includes power transmission data and carbon calculation results; The load side is used to record electricity consumption and carbon emissions; The application layer is used for equipment operation management, operation status monitoring, carbon emission trading system, carbon reduction analysis and traceability analysis.

2. The indirect carbon emission measurement platform for electricity according to claim 1 is characterized in that: The source side adopts the power plant carbon emission model to calculate the electric carbon factor of the generator set based on the carbon emission and power generation data collected at the equipment layer.

3. The indirect carbon emission measurement platform for electricity according to claim 2 is characterized in that: The carbon emission model of the power plant is as follows: Based on the carbon emissions and power generation data collected at the equipment level, the generator carbon factor is calculated as shown in Formula 1: Formula 1: λ Gi =E Gi / P Gi ; Where λ Gi is the carbon emission factor of unit i; E Gi is the carbon emission of unit i; P Gi It is the real-time output data of unit i.

4. The indirect carbon emission measurement platform for electricity according to claim 3 is characterized in that: The grid side applies the basic theory of carbon flow and uses the data from the electricity meter and the electricity carbon meter to update the carbon information of each node in the system in real time, including calculating the carbon input and carbon emission intensity of the node.

5. The indirect carbon emission measurement platform for electricity according to claim 4 is characterized in that: The specific calculation process on the network side is as follows: According to the principle of carbon emission conservation, the node input carbon amount is shown in formula 2: Formula 2: Where E in is the total carbon input at node n; in_k is the electric carbon factor of the kth input branch of the node; P in_k is the power of the kth input branch of the node; Based on the basic theory of carbon flow, the node carbon emission intensity e n The calculation is shown in formula 3: Formula 3: Where e n is the carbon potential at node n; Ω is the unit set.

6. The indirect carbon emission measurement platform for electricity according to claim 5 is characterized in that: The load side combines the user's electricity consumption and the node carbon emission intensity, adopts the user's electricity carbon emission measurement model, and calculates the user's electricity carbon emission.

7. The indirect carbon emission measurement platform for electricity according to claim 6 is characterized in that: The user electricity carbon emissions measurement model is as follows: Carbon emissions generated by electricity consumption n The power consumption of the user P n and the carbon emission intensity e at the user node n Product, see formula 4: Formula 4: E n =e n ·P n ; Where E n is the user’s carbon emissions; P n For users' electricity consumption.

8. The indirect carbon emission measurement platform for electricity according to claim 1, characterized in that: The data layer adopts a data correction model, which processes outliers and predicts new energy output on the data on the source side, grid side and load side. The outlier processing method uses moving smoothing to replace abnormal data values, and the new energy output prediction uses a direct method or an indirect method to predict the output of new energy.

Images