A method for carbon flow monitoring and accounting based on the Internet of Things

Abstract

The application discloses a kind of carbon flow monitoring and accounting method based on Internet of Things, specifically comprising the following steps: S1.collection power system tidal information;S2.carries out flow calculation to power network, obtains the active power flow matrix F of entire power network;S3.carbon flow density is calculated to the grid in stages, gradually obtains the carbon flow data of entire power network;S4.through the carbon flow data obtained carbon flow matrix C, and provide final visual result;S5.collection carbon emission data;S6.create carbon flow neural network model;S7.train carbon flow neural network model;S8.utilize carbon flow neural network model to the carbon emission of entire system is accounted for.This application mainly utilizes Internet of Things data acquisition technology and data analysis visualization technology, for power system manager directly shows carbon flow in entire power network The flow path of, help to realize the low carbonization and green of entire system.

Description

Technical Field

[0001] This invention relates to the field of carbon flow in the Internet of Things (IoT), and more particularly to a method for monitoring and calculating carbon flow based on the IoT. Background Technology

[0002] Carbon flow monitoring provides a feasible implementation path for carbon responsibility allocation in the power system. However, there is currently no technology that can intuitively display the flow of carbon in the entire power network for monitoring and accounting. Therefore, there is an urgent need for a carbon flow monitoring and accounting method that allows power system managers to intuitively display the flow path of carbon in the entire power network and carbon emission data including but not limited to carbon emissions from fossil fuel combustion, production processes, electricity and water resources, and other sources, to help achieve the decarbonization and greening of the entire system. Summary of the Invention

[0003] To address the above shortcomings, this invention provides a carbon flow monitoring and accounting method based on the Internet of Things, specifically including the following steps:

[0004] S1. Collect power flow information of the power system, including node power, network loss power, and line topology;

[0005] S2. Perform flow calculations on the power network to obtain the active power flow matrix F of the entire power network;

[0006] S3. Perform hierarchical iterative calculations on the carbon flow density of the power grid to gradually obtain carbon flow data for the entire power network;

[0007] S4. Obtain the carbon flow matrix C by processing the carbon flow data and provide the final visualization results;

[0008] S5. Collect carbon emission data;

[0009] S6. Establish a carbon flow neural network model;

[0010] S7. Train the carbon flow neural network model by randomly dividing the dataset obtained in step S5 into a training set and a validation set in a 9:1 ratio; train the carbon flow neural network model using the training set and validate it using the validation set to obtain the optimal model.

[0011] S8. Calculate the carbon emissions of the entire system using the trained carbon flow neural network model.

[0012] Specifically, the active power flow matrix F mentioned in step S2 is formulated as follows:

[0013] F k5 =P ij -T ij (1);

[0014] In the formula, F k5 P represents the outflow power of the k-th line. ij T represents the active power provided by node i to node j; ij This represents the power loss between node i and node j, where i ≠ j.

[0015] Specifically, the carbon flux density iteration algorithm described in step S3 is as follows:

[0016] (1) Starting from the initial node, calculate the carbon flow density of the path to the next level based on the known carbon emission intensity of the power flow starting node. The calculation process is as follows:

[0017] F k4 / F k5 =ρ i ' j / ρ i ' j '(2);

[0018] In the formula, Fk4 represents the injected power of the power flow on the k-th line; Fk5 represents the outflow power of the power flow on the k-th line; ρ i ' j The initial node carbon flux density ρ represents the power flow from node i to node j. i ' j =ρ i ;ρ i ρ represents the carbon emission intensity of node i; i ' j 'The carbon flow density at the terminating node represents the power flow from node i to node j.'

[0019] (2) Check if there is a next-level node in this level; if there is, calculate the carbon emission intensity of the next-level node and repeat step (1); if there is no next-level node, terminate the algorithm and output the carbon flow matrix C of the entire power network.

[0020] Specifically, the carbon emission intensity calculation method for the next level node is as follows:

[0021]

[0022] In the formula, ρ j This represents the carbon emission intensity of node j.

[0023] Specifically, in step S4, the first column of the carbon flow matrix C is the node number i;

[0024] The second column of the carbon flow matrix C mentioned in step S4 represents the power injected into the power grid at node i. The calculation process is as follows:

[0025]

[0026] The third column of the carbon flow matrix C mentioned in step S4 represents the carbon emission intensity of node i.

[0027] C i3 =ρ i (5);

[0028] In step S4, the fourth column of the carbon flux matrix C represents the carbon flux time density (in kilograms of CO) at node i. 2 / s):

[0029] C i4 =C i3 *C i2 (6).

[0030] Specifically, step S6 establishes a carbon flow neural network model, as shown below:

[0031] The data matching error function is:

[0032]

[0033] In the formula, NN(C i The carbon flow neural network model represents the carbon flow matrix as C. i The carbon emissions of the entire system are predicted at that time. i This represents the actual carbon emissions of the entire system at this point.

[0034] The physical governing equations are:

[0035]

[0036] in, This represents gradient operation. Indicates the Laplace operation;

[0037] The loss function resulting from the physical control equations is:

[0038]

[0039] Specifically, the carbon flow neural network model calculation process in step S8 is as follows:

[0040] Input the carbon flow matrix within a sliding window into the trained carbon flow neural network model to obtain the predicted carbon emission sequence Pre(t) for the entire system.

[0041] The error ε is calculated by comparing it with the currently reported carbon emission sequence Rel(t). The calculation method is as follows:

[0042]

[0043] In the formula, n represents the total number of sample points within the sliding window;

[0044] Within the sliding window, the mean, variance, and range of the prediction errors for n sample points are as follows:

[0045]

[0046] The error threshold is calculated as follows:

[0047]

[0048] In the formula, ε up and ε down These are the upper and lower thresholds for the error ε, respectively; α is the coefficient of the standard deviation; and β is the coefficient of the range.

[0049] Specifically, the coefficients α for standard deviation and β for range are determined as follows:

[0050]

[0051] Generally speaking, the greater the volatility of the predicted sequence, the less reliable the prediction result is, and the threshold range for judging the error should be expanded accordingly. Considering the above principles, the method for determining the coefficient α of the standard deviation and the coefficient β of the range is confirmed by equation (13).

[0052] The calculation result is considered to be unsuccessful if the error between the carbon emission data predicted by the carbon flow neural network model and the calculation result exceeds a threshold; the calculation result is considered to be successful if the error between the carbon emission data predicted by the carbon flow neural network model and the calculation result is within the threshold range.

[0053] Compared with existing technologies, the beneficial effects of this invention are: by utilizing Internet of Things data acquisition technology and data analysis visualization technology, it provides power system managers with an intuitive display of the flow path of carbon flow in the entire power network, helping to achieve the decarbonization and greening of the entire system. Attached Figure Description

[0054] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below.

[0055] Figure 1 This is a flowchart illustrating a carbon flow monitoring and calculation method based on the Internet of Things (IoT) according to an embodiment of the present invention.

[0056] Figure 2 This is a visualization result of the carbon flow path of an IEEE 14-node system based on an Internet of Things-based carbon flow monitoring and accounting method, according to an embodiment of the present invention.

[0057] Figure 3This is a structural diagram of a carbon flow neural network model for a carbon flow monitoring and accounting method based on the Internet of Things, according to an embodiment of the present invention. Detailed Implementation

[0058] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0059] In the description of this invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0060] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances. Furthermore, the technical features involved in the different embodiments of this invention described below can be combined with each other as long as they do not conflict with each other.

[0061] This invention provides a method for carbon flow monitoring and calculation based on the Internet of Things, such as... Figure 1 As shown, the specific steps include:

[0062] S1. Collect power flow information of the power system, including node power, network loss power, and line topology; and obtain the active power flow of the system through data processing.

[0063] Taking the IEEE 14-node system as an example, the system includes two generator nodes. Node 1 is a coal-fired generator with a carbon emission intensity of 0.855 kg CO2 / (kWh), and Node 2 is a natural gas generator with a carbon emission intensity of 0.382 kg CO2 / (kW-h).

[0064] The system has a total of 14 nodes and 21 lines. The node power information is stored in matrix P, where each element P... ijThis represents the active power supplied by node i to node j, in MW. Network loss power information and line topology information are stored in matrix T, where the elements T in matrix T... ij A value of 0 indicates that there is no path between node i and node j. ij A non-zero value indicates that there is a path between node i and node j, and its value represents the network loss of that path, in MW.

[0065] S2. Perform flow calculations on the power network to obtain the active power flow matrix F of the entire power network.

[0066] The active power flow of the power network is obtained through data processing methods, as follows:

[0067] For the upper triangular matrix T′ of matrix T, traverse all its upper triangular elements in row-major order. Suppose T′ ij If i = 1 and i ≠ j, then add a row to the active power flow matrix F. The first column of this row is the row number, the second column is the index i (representing the starting node index of the power flow), the third column is the index j (representing the ending node index of the power flow), and the fourth column is the injected power magnitude of the power flow on this line (i.e., P). ij The fifth column represents the outflow power of the power flow on this line, and the calculation process is as follows:

[0068] F k5 =P ij -T ij (1);

[0069] In the formula, F k5 This represents the outflow power of the k-th line in the power network.

[0070] Since the system has a total of 21 lines, the F matrix in this case is a 21*5 matrix. The active power flow matrix data of the IEEE 14-bus system is shown in Table 1.

[0071] Table 1. Active power flow matrix data for the IEEE 14-bus system.

[0072]

[0073]

[0074] S3. Perform hierarchical iterative calculations on the carbon flow density of the power grid to gradually obtain carbon flow data for the entire power network; the carbon flow density iterative algorithm flow is as follows:

[0075] (1) Starting from the initial node, calculate the carbon flow density of the path to the next level based on the known carbon emission intensity of the power flow starting node. The calculation process is as follows:

[0076] Fk4 / F k5 =ρ i ' j / ρ i ' j '(2);

[0077] In the formula, F k4 F represents the injected power of the power flow on the k-th line; k5 ρ represents the outflow power of the power flow on the k-th line; i ' j The initial node carbon flux density ρ represents the power flow from node i to node j. i ' j =ρ i ;ρ i ρ represents the carbon emission intensity of node i; i ' j 'Represents the carbon flow density at the terminating node of the power flow from node i to node j.

[0078] (2) Check if there is a next-level node for this level. If there is, calculate the carbon emission intensity of the next-level node and repeat step (1); if there is no next-level node, terminate the algorithm and output the carbon flow density matrix of the entire power network. The method for calculating the carbon emission intensity of the next-level node is as follows:

[0079]

[0080] In the formula, ρ j This represents the carbon emission intensity of node j.

[0081] S4. Obtain the carbon flow matrix C by processing the carbon flow data and provide the final visualization results. As shown in Table 2, the carbon flow matrix C in this case is a 14-row matrix, with each row storing the carbon flow information of a corresponding node.

[0082] The first column of the carbon flow matrix C is the node number i.

[0083] The second column of the carbon flow matrix C represents the power injected into the grid at node i, and the calculation process is as follows:

[0084]

[0085] The third column of the carbon flow matrix C represents the carbon emission intensity at node i:

[0086] C i3 =ρ i (5);

[0087] The fourth column of the carbon flux matrix C represents the carbon flux time density at node i (in kilograms of CO). 2 / s):

[0088] C i4 =C i3 *C i2 (6);

[0089] Visualizing the carbon flow matrix C can intuitively show the dynamic changes in carbon flow.

[0090] Table 2 Carbon Flow Matrix Data for the IEEE 14-Node System

[0091]

[0092] S5. Collect carbon emission data, including but not limited to real-time data y of total carbon emissions, including carbon emissions from fossil fuel combustion, carbon emissions from production processes, carbon emissions from electricity and water resources, and other carbon emissions, as well as the corresponding carbon flow matrix C for the same time period.

[0093] S6. Establish a carbon flow neural network model; the data matching error function is:

[0094]

[0095] In the formula, NN(C i The carbon flow neural network model represents the carbon flow matrix as C. i The carbon emissions of the entire system are predicted at that time. i This represents the actual carbon emissions of the entire system at this point.

[0096] The physical governing equations are:

[0097]

[0098] in, This represents gradient operation. This indicates the Laplace operation.

[0099] The loss function resulting from the physical control equations is:

[0100]

[0101] S7. Train the carbon flow neural network model by randomly dividing the dataset obtained in step S5 into a training set and a validation set in a 9:1 ratio. Train the carbon flow neural network model using the training set and validate it using the validation set to obtain the optimal model.

[0102] Table 3 shows the prediction accuracy of the carbon flow neural network model.

[0103] Table 3 Prediction Accuracy of Carbon Flow Neural Network Model

[0104]

[0105] S8. Calculate the carbon emissions of the entire system using the trained carbon flow neural network model. The calculation steps are as follows: Input the carbon flow matrix within a sliding window into the trained optimal physical information neural network model to obtain the predicted carbon emission sequence Pre(t) for the entire system. Generally, a five-day sliding window is used, and the carbon flow matrix of the system to be calculated is obtained every hour within a sliding window, resulting in a total of 120 sample points.

[0106] The error ε is calculated by comparing it with the currently reported carbon emission sequence Rel(t). The calculation method is as follows:

[0107]

[0108] In the formula, n represents the total number of sample points within the sliding window.

[0109] Within the sliding window, the mean, variance, and range of the prediction errors for n sample points are as follows:

[0110]

[0111] The error threshold is calculated as follows:

[0112]

[0113] In the formula, ε up and ε down These are the upper and lower thresholds for the error ε, respectively; α is the coefficient of the standard deviation; and β is the coefficient of the range.

[0114] Generally, the greater the volatility of the predicted sequence, the less reliable the prediction result, and the threshold range for judging the error should be correspondingly expanded. Considering the above principles, the methods for determining α and β are as follows:

[0115]

[0116] The calculation result is considered to be unsuccessful if the error between the carbon emission data predicted by the carbon flow neural network model and the calculation result exceeds a threshold; the calculation result is considered to be successful if the error between the carbon emission data predicted by the carbon flow neural network model and the calculation result is within the threshold range.

[0117] The visualization result of the carbon flow path of the IEEE 14-node system according to an embodiment of the present invention is shown in the figure below. Figure 2 As shown, the structure of the established carbon flow neural network model is as follows: Figure 3 As shown.

[0118] This embodiment proposes an IoT-based carbon flow monitoring and visualization method. This method utilizes IoT data acquisition and data analysis visualization technologies, and mainly includes four steps: data collection, power flow calculation, iterative carbon flow density calculation, and carbon flow path visualization. First, power system flow information is collected, including node power, network loss power, and line topology. Second, flow calculation is performed on the power network to obtain the active power flow matrix F of the entire power network. Then, the carbon flow density of the power grid is calculated iteratively in stages to gradually obtain the carbon flow matrix C of the entire power network, and the final visualization result is provided. Finally, a carbon flow neural network model is established to calculate the total carbon emissions of the entire system. This method will provide power system managers with an intuitive display of the carbon flow path in the entire power network and carbon emission data including but not limited to carbon emissions from fossil fuel combustion, production processes, electricity and water resources, and other carbon emissions, helping to achieve the decarbonization and greening of the entire system.

[0119] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A carbon flow monitoring and accounting method based on Internet of Things, specifically comprising the following steps: S1. Collecting power system flow information, the flow information including node power, network loss power, line topology; S2. Calculating the flow of the power network to obtain the active power flow matrix F of the entire power network; S3. Iteratively calculating the carbon flow density of the power grid to gradually obtain the carbon flow data of the entire power network; The carbon flow density iterative algorithm in step S3 is as follows: (1) Starting from the initial node, the carbon flow density of the line leading to the next level is calculated according to the known power flow starting node carbon emission intensity, and the calculation process is as follows: ； wherein represents the injection power of the power flow on the kth line; represents the outflow power of the power flow on the kth line; represents the starting node carbon flow density of the power flow from node i to node j and = represents the carbon emission intensity of node i; represents the ending node carbon flow density of the power flow from node i to node j; (2) Detecting whether there is a next level node for the node; if there is, calculating the carbon emission intensity of the next level node and re-executing step (1); if there is no next level node, terminating the algorithm and outputting the carbon flow matrix C of the entire power network; The carbon emission intensity calculation method of the next level node is as follows: ； wherein represents the carbon intensity of node j; S4. Obtaining the carbon flow matrix C by arranging the carbon flow data and providing the final visualization result; S5. Collecting carbon emission data; S6. Establishing a carbon flow neural network model; S7. Training the carbon flow neural network model, dividing the data set obtained in step S5 into a training set and a validation set in a ratio of 9:1, training the carbon flow neural network model using the training set, verifying through the validation set, and obtaining an optimal model; S8. Using the trained carbon flow neural network model to account for the carbon emissions of the entire system.

2. The carbon flow monitoring and accounting method based on Internet of Things according to claim 1, wherein the active power flow matrix F in step S2 is calculated according to the formula: (1)； wherein Pij(k) denotes the power flowing out of the kth line, Pij(k) denotes the active power provided by node i to node j; Pij(k) denotes the loss power between node i and node j and i≠j.

3. The carbon flow monitoring and accounting method based on Internet of Things according to claim 1, wherein the first column of the carbon flow matrix C in step S4 is the node sequence number i; The second column of the carbon flow matrix C in step S4 is the power injected into the power grid by node i, and the calculation process is as follows: ； The third column of the carbon flow matrix C in step S4 is the carbon emission intensity of node i, and the calculation process is as follows: ； The fourth column of the carbon flow matrix C in step S4 is the carbon flow time density of node i, and the unit of the carbon flow time density is kilogram CO 2 / s, and the calculation process is as follows: 。 4. The carbon flow monitoring and accounting method based on Internet of Things according to claim 1, wherein the carbon flow neural network model in step S6 is established as follows: The data matching error function is calculated as follows: ； In the formula, The carbon flow matrix of the carbon flow neural network model is The carbon emission prediction of the entire system at this time, The true value of the carbon emission of the entire system at this time; The physical control equation is calculated as follows: ； wherein, denotes a gradient operation, denotes a Laplace operation; The loss function caused by the physical control equation is calculated as follows: 。 5. The carbon flow monitoring and accounting method based on Internet of Things according to claim 1, wherein the carbon flow neural network model accounting process in step S8 is as follows: Input the carbon flow matrix in a sliding window into the trained carbon flow neural network model to obtain a carbon emission prediction value sequence Pre(t) of the entire system at the current time; In comparison with the current reported carbon emission sequence Rel(t), the error is calculated The calculation method is as follows: ； Wherein, n represents the total number of sample points in the sliding window; The average, variance, and range of the prediction error of the n sample points in the sliding window are calculated as follows: ； The error threshold is calculated as follows: ； wherein and are the upper and lower thresholds of the error respectively; is a coefficient of the standard deviation; is a coefficient of the range.

6. The carbon flow monitoring and accounting method based on the Internet of Things according to claim 5, the calculation method of the coefficient of the standard deviation and the coefficient of the range is as follows: 。

Images