Natural gas consumption prediction method and device, electronic equipment and storage medium

Abstract

The invention provides a natural gas consumption prediction method and device, electronic equipment and a storage medium. The natural gas consumption prediction method comprises the steps that data information of natural gas at a first moment is collected in a natural gas data source; performing data standardization processing on the data information of the natural gas, and determining the processed data information of the natural gas; inputting the processed data information of the natural gas into a pre-trained data analysis model, performing gas consumption analysis processing on the processed data information of the natural gas, and outputting the gas consumption corresponding to the processed data information of the natural gas; wherein the data analysis model is obtained by training a neural network model. The edge computing nodes are deployed near the data source, efficient collection and real-time processing of the natural gas data are achieved, the data collection and processing efficiency is improved, the real-time performance and accuracy of the data are ensured, and accurate decision support is provided for natural gas suppliers and operators through deep analysis of the natural gas data.

Description

Technical Field

[0001] The present application relates to the technical field of data processing, and particularly to a method, device, electronic device and storage medium for predicting the gas consumption of natural gas. Background Art

[0002] As an important energy resource, the sales and supply management of natural gas is crucial for the stable operation of the energy industry. However, in traditional natural gas sales operations, data collection and processing are often restricted by many factors, including data transmission delays, data security, etc. Current data collection methods often rely on centralized data centers, resulting in large amounts of data transmission, high network loads, and limitations in application scenarios with high requirements for data real-time performance. At the same time, since natural gas sales operations involve a large amount of data processing and analysis, traditional data processing methods often cannot meet the needs of real-time processing and efficient analysis. The traditional centralized data processing method also leads to low data processing efficiency, affecting the decision-making and operation efficiency of natural gas sales operations. Summary of the Invention

[0003] In view of this, the purpose of the present application is to provide a method, device, electronic device and storage medium for predicting the gas consumption of natural gas. By deploying edge computing nodes near the data source, efficient collection and real-time processing of natural gas data are achieved, improving data collection and processing efficiency, ensuring data real-time performance and accuracy, and providing accurate decision-making support for natural gas suppliers and operators through in-depth analysis of natural gas data.

[0004] An embodiment of the present application provides a method for predicting the gas consumption of natural gas. The gas consumption prediction method is applied to a gas consumption prediction device for natural gas, and the gas consumption prediction device for natural gas is deployed on an edge computing node of a natural gas data source. The gas consumption prediction method includes:

[0005] Collect data information of natural gas at a first moment in the natural gas data source;

[0006] Perform data standardization processing on the data information of the natural gas to determine the processed data information of the natural gas;

[0007] Input the processed data information of the natural gas into a pre-trained data analysis model, perform gas consumption analysis processing on the processed data information of the natural gas, and output the gas consumption corresponding to the processed data information of the natural gas; wherein, the data analysis model is obtained by training a neural network model.

[0008] In a possible implementation manner, the performing data standardization processing on the data information of the natural gas to determine the processed data information of the natural gas includes:

[0009] Perform a mean calculation on the data information of the natural gas to determine the mean information corresponding to the data information of the natural gas;

[0010] Perform data standardization based on the data information of the natural gas and the mean information to determine the processed data information of the natural gas.

[0011] In a possible implementation manner, inputting the processed data information of the natural gas into a pre-trained data analysis model, performing gas consumption analysis on the processed data information of the natural gas, and outputting the gas consumption corresponding to the processed data information of the natural gas, including:

[0012] Input the processed data information of the natural gas into the input layer of the data analysis model, process the processed data information of the natural gas, and output the first vector information corresponding to the processed data information of the natural gas;

[0013] Input the first vector information into the hidden layer of the data analysis model, and based on the second vector information corresponding to the second moment in the hidden layer, the first vector information, the input value weight matrix, the hidden layer bias, and the hidden value weight matrix, output the third vector information; wherein, the second moment is the previous moment of the first moment;

[0014] Input the third vector information into the output layer of the data analysis model, and based on the output layer bias of the output layer, the output value weight coefficient, and the third vector information, output the gas consumption corresponding to the processed data information of the natural gas.

[0015] In a possible implementation manner, inputting the first vector information into the hidden layer of the data analysis model, and based on the second vector information corresponding to the second moment in the hidden layer, the first vector information, the input value weight matrix, the hidden layer bias, and the hidden value weight matrix, outputting the third vector information, including:

[0016] Multiply the input value weight matrix by the first vector information to determine the first information;

[0017] Multiply the hidden value weight matrix by the second vector information to determine the second information;

[0018] Add the first information, the second information, and the hidden layer bias to determine the third information;

[0019] Process the third information and output the third vector information.

[0020] In a possible implementation manner, inputting the third vector information into the output layer of the data analysis model, and based on the output layer bias of the output layer, the output value weight coefficient, and the third vector information, outputting the gas consumption corresponding to the processed natural gas data information, includes:

[0021] Multiplying the third vector information by the output value weight coefficient to determine a fourth piece of information;

[0022] Adding the fourth piece of information to the output layer bias to output the gas consumption corresponding to the processed natural gas data information.

[0023] In a possible implementation manner, after inputting the processed natural gas data information into a pre-trained data analysis model, performing gas consumption analysis processing on the processed natural gas data information, and outputting the gas consumption corresponding to the processed natural gas data information, the gas consumption prediction method further includes:

[0024] Visualizing the gas consumption and the natural gas data information.

[0025] In a possible implementation manner, determining the data analysis model through the following steps:

[0026] Obtaining sample natural gas data information and the actual gas consumption of the sample natural gas data information;

[0027] Inputting the sample natural gas data information into the neural network model, processing the sample natural gas data information, and outputting the predicted gas consumption of the sample natural gas data information;

[0028] Processing the predicted gas consumption and the actual gas consumption based on the loss function calculation formula to determine the loss value of the neural network model;

[0029] Iteratively changing the input value weight matrix, the hidden layer bias, the hidden value weight matrix, the output layer bias, and the output value weight coefficient of the neural network model based on the loss value to determine the data analysis model.

[0030] The embodiment of the present application further provides a gas consumption prediction device for natural gas, and the gas consumption prediction device includes:

[0031] A data acquisition module, configured to acquire the natural gas data information at the first moment in the natural gas data source;

[0032] A data cleaning module for performing data standardization processing on the data information of the natural gas to determine the processed data information of the natural gas;

[0033] A data analysis module for inputting the processed data information of the natural gas into a pre-trained data analysis model, performing gas consumption analysis processing on the processed data information of the natural gas, and outputting the gas consumption corresponding to the processed data information of the natural gas; wherein, the data analysis model is obtained by training a neural network model.

[0034] An embodiment of the present application further provides an electronic device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device runs, the processor communicates with the memory through the bus. When the machine-readable instructions are executed by the processor, the steps of the above-mentioned natural gas gas consumption prediction method are executed.

[0035] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, the steps of the above-mentioned natural gas gas consumption prediction method are executed.

[0036] The natural gas gas consumption prediction method, device, electronic device, and storage medium provided by the embodiments of the present application. The gas consumption prediction method includes: collecting the data information of natural gas at the first moment in the natural gas data source; performing data standardization processing on the data information of the natural gas to determine the processed data information of the natural gas; inputting the processed data information of the natural gas into a pre-trained data analysis model, performing gas consumption analysis processing on the processed data information of the natural gas, and outputting the gas consumption corresponding to the processed data information of the natural gas; wherein, the data analysis model is obtained by training a neural network model. Deploying edge computing nodes near the data source realizes the efficient collection and real-time processing of natural gas data, improves the data collection and processing efficiency, ensures the real-time nature and accuracy of the data, and provides accurate decision-making support for natural gas suppliers and operators through in-depth analysis of natural gas data.

[0037] To make the above objects, features, and advantages of the present application more obvious and understandable, the following specifically enumerates preferred embodiments and, in conjunction with the accompanying drawings, makes the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] To more clearly illustrate the technical solutions of the embodiments of the present application, the accompanying drawings required for the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present application and should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0039] Figure 1 It is a flowchart of a method for predicting the gas consumption of natural gas provided by an embodiment of the present application;

[0040] Figure 2 It is one of the structural schematic diagrams of a device for predicting the gas consumption of natural gas provided by an embodiment of the present application;

[0041] Figure 3 It is another structural schematic diagram of a device for predicting the gas consumption of natural gas provided by an embodiment of the present application;

[0042] Figure 4 It is a structural schematic diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0043] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. It should be understood that the accompanying drawings in the present application are only for the purposes of illustration and description and are not used to limit the protection scope of the present application. In addition, it should be understood that the schematic drawings are not drawn to actual scale. The flowcharts used in the present application show the operations implemented according to some embodiments of the present application. It should be understood that the operations in the flowchart may not be implemented in sequence, and steps without logical context relationships may be reversed or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart or remove one or more operations from the flowchart under the guidance of the content of the present application.

[0044] In addition, the described embodiments are only some embodiments of the present application, rather than all embodiments. The components of the embodiments of the present application usually described and illustrated in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application to be protected, but only represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0045] To enable those skilled in the art to use the content of this application, in combination with a specific application scenario of "predicting the gas consumption of natural gas", the following embodiments are given. For those skilled in the art, without departing from the spirit and scope of this application, the general principles defined here can be applied to other embodiments and application scenarios.

[0046] First, an introduction to the application scenarios applicable to this application is provided. This application can be applied to the technical field of data processing.

[0047] Through research, it is found that as an important energy resource, the sales and supply management of natural gas is crucial for the stable operation of the energy industry. However, in traditional natural gas sales operations, data collection and processing are often restricted by many factors, including data transmission delays, data security, etc. Current data collection methods often rely on centralized data centers, resulting in large amounts of data transmission, high network loads, and limitations in application scenarios with high requirements for data real-time performance. At the same time, since natural gas sales operations involve a large amount of data processing and analysis, traditional data processing methods often cannot meet the requirements of real-time processing and efficient analysis. Traditional centralized data processing methods also lead to low data processing efficiency, affecting the decision-making and operational efficiency of natural gas sales operations.

[0048] Based on this, the embodiments of this application provide a method for predicting the gas consumption of natural gas. By deploying edge computing nodes near the data source, efficient collection and real-time processing of natural gas data are achieved, improving data collection and processing efficiency, ensuring data real-time performance and accuracy, and providing accurate decision-making support for natural gas suppliers and operators through in-depth analysis of natural gas data.

[0049] Please refer to Figure 1 , Figure 1 which is a flowchart of a method for predicting the gas consumption of natural gas provided by the embodiments of this application. As shown in Figure 1 , the gas consumption prediction method provided by the embodiments of this application includes:

[0050] S101: Collect the data information of natural gas at the first moment in the natural gas data source.

[0051] In this step, the data information of natural gas at the first moment is collected in the natural gas data source through sensors and data interfaces.

[0052] Among them, the data information of natural gas includes other data information such as natural gas supply volume, sales volume, price, inventory, market demand, and sales data.

[0053] S102: Perform data standardization processing on the data information of the natural gas to determine the processed data information of the natural gas.

[0054] In this step, data standardization processing is performed on the data information of natural gas to determine the processed data information of natural gas. Thus, preprocessing of the data is achieved. On the edge computing node, the collected data is preprocessed and screened to reduce the data transmission volume, reduce the network burden, and ensure the security and integrity of the data.

[0055] In a possible implementation manner, the performing data standardization processing on the data information of the natural gas to determine the processed data information of the natural gas includes:

[0056] A: Perform mean calculation processing on the data information of the natural gas to determine the mean information corresponding to the data information of the natural gas.

[0057] Here, mean calculation processing is performed on the data information of the natural gas to determine the mean information corresponding to the data information of the natural gas.

[0058] B: Based on the data information of the natural gas and the mean information, perform data standardization processing to determine the processed data information of the natural gas.

[0059] Here, data standardization processing is performed according to the data information of the natural gas and the mean information to determine the processed data information of the natural gas.

[0060] Among them, the data information of the natural gas is processed by data standardization through the following formula:

[0061]

[0062] where, X i ′ is the processed data information of the natural gas, X i is the data information of the natural gas, μ is the mean information, i is the i-th data in the data information of the natural gas, and N is the total number of data in the data information of the natural gas.

[0063] S103: Input the processed data information of the natural gas into a pre-trained data analysis model, perform gas consumption analysis processing on the processed data information of the natural gas, and output the gas consumption corresponding to the processed data information of the natural gas.

[0064] In this step, the processed data information of the natural gas is input into a pre-trained data analysis model, gas consumption analysis processing is performed on the processed data information of the natural gas, and the gas consumption corresponding to the processed data information of the natural gas is output. Real-time analysis and prediction of the collected natural gas data are realized, providing decision-making support for natural gas suppliers and operators.

[0065] Among them, the data analysis model is obtained by training a neural network model.

[0066] In a possible implementation manner, inputting the processed natural gas data information into a pre-trained data analysis model, performing gas consumption analysis processing on the processed natural gas data information, and outputting the gas consumption corresponding to the processed natural gas data information includes:

[0067] (1): Input the processed natural gas data information into the input layer of the data analysis model, process the processed natural gas data information, and output the first vector information corresponding to the processed natural gas data information.

[0068] Here, input the processed natural gas data information into the input layer, perform vector processing on the processed natural gas data information, and output the first vector information corresponding to the processed natural gas data information.

[0069] Among them, the input layer generates an n-dimensional vector x t =(x t 1 …x t n ) according to the data at time t collected, including natural gas sales volume, price, weather conditions, local industrial production index, market demand, and sales data.

[0070] (2): Input the first vector information into the hidden layer of the data analysis model, and output the third vector information based on the second vector information corresponding to the second moment in the hidden layer, the first vector information, the input value weight matrix, the hidden layer bias, and the hidden value weight matrix; where the second moment is the previous moment of the first moment.

[0071] Here, input the first vector information into the hidden layer, and output the third vector information according to the second vector information corresponding to the second moment in the hidden layer, the first vector information, the input value weight matrix, the hidden layer bias, and the hidden value weight matrix.

[0072] Among them, the second vector information corresponding to the second moment in the hidden layer is an m-dimensional vector pre-generated by the hidden layer.

[0073] In a possible implementation manner, inputting the first vector information into the hidden layer of the data analysis model, and outputting the third vector information based on the second vector information corresponding to the second moment in the hidden layer, the first vector information, the input value weight matrix, the hidden layer bias, and the hidden value weight matrix includes:

[0074] a: Multiply the input value weight matrix by the first vector information to determine the first information.

[0075] Here, multiply the input value weight matrix by the first vector information to determine the first information.

[0076] b: Multiply the hidden value weight matrix by the second vector information to determine the second information.

[0077] Here, multiply the hidden value weight matrix by the second vector information to determine the second information.

[0078] c: Add the first information, the second information, and the hidden layer bias to determine the third information.

[0079] Here, add the first information, the second information, and the hidden layer bias to determine the third information.

[0080] Here, process the third information and output the third vector information.

[0081] Among them, the third information is determined by the following formula:

[0082] Z t = U * x t + W * h t-1 + b;

[0083] Among them, Z t is the third information, U is the input value weight matrix, W is the hidden value weight matrix, b is the hidden layer bias, and h t-1 is the m-dimensional second vector information output by the hidden layer at time t-1, and x t is the first vector information.

[0084] d: Process the third information and output the third vector information.

[0085] Here, the third vector information is determined by the following formula:

[0086] h t = tanh(Z t )

[0087] Among them, h tt is the third vector information, and Z t is the third information.

[0088] (3): Input the third vector information into the output layer of the data analysis model, and based on the output layer bias, output value weight coefficient of the output layer, and the third vector information, output the gas consumption corresponding to the processed natural gas data information.

[0089] Here, the third vector information is input into the output layer of the data analysis model, and according to the output layer bias, the output value weight coefficient, and the third vector information, the gas consumption corresponding to the processed natural gas data information is output.

[0090] In a possible implementation manner, the step of inputting the third vector information into the output layer of the data analysis model and outputting the gas consumption corresponding to the processed natural gas data information based on the output layer bias, the output value weight coefficient, and the third vector information includes:

[0091] Multiplying the third vector information by the output value weight coefficient to determine a fourth piece of information; adding the fourth piece of information to the output layer bias to output the gas consumption corresponding to the processed natural gas data information.

[0092] Here, the third vector information is multiplied by the output value weight coefficient to determine a fourth piece of information; the fourth piece of information is added to the output layer bias to output the gas consumption corresponding to the processed natural gas data information.

[0093] Among them, the gas consumption is determined by the following formula:

[0094] O t =V*h t +c

[0095] Among them, V is the output value weight coefficient of m dimensions, h t is the third vector information, and c is the output layer bias.

[0096] In a possible implementation manner, the data analysis model is determined through the following steps:

[0097] i: Obtain the sample natural gas data information and the actual gas consumption of the sample natural gas data information.

[0098] Here, the sample natural gas data information and the actual gas consumption of the sample natural gas data information are obtained.

[0099] ii: Input the sample natural gas data information into the neural network model, process the sample natural gas data information, and output the predicted gas consumption of the sample natural gas data information.

[0100] Here, the sample natural gas data information is input into the neural network model, the sample natural gas data information is processed, and the predicted gas consumption of the sample natural gas data information is output.

[0101] Here, the process of the neural network model processing the sample natural gas data information is the same as that of the above data analysis model processing the processed natural gas data information, and this part will not be elaborated here.

[0102] iii: Based on the loss function calculation formula, process the predicted gas consumption and the actual gas consumption to determine the loss value of the neural network model.

[0103] Here, according to the loss function calculation formula, process the predicted gas consumption and the actual gas consumption to determine the loss value of the neural network model.

[0104] Among them, the loss value of the neural network model is determined through the following loss function calculation formula:

[0105]

[0106] Among them, L is the loss value, Y t is the actual gas consumption, O t is the predicted gas consumption, and t is the time.

[0107] iv Based on the loss value, iteratively change the input value weight matrix, hidden layer bias, hidden value weight matrix, output layer bias, and output value weight coefficient of the neural network model to determine the data analysis model.

[0108] Here, according to the loss value, iteratively change the input value weight matrix, hidden layer bias, hidden value weight matrix, output layer bias, and output value weight coefficient of the neural network model to determine the data analysis model.

[0109] Among them, if the loss value is greater than the preset threshold, then iteratively change the input value weight matrix, hidden layer bias, hidden value weight matrix, output layer bias, and output value weight coefficient of the neural network model.

[0110] In a possible implementation manner, after inputting the processed natural gas data information into a pre-trained data analysis model, performing gas consumption analysis processing on the processed natural gas data information, and outputting the gas consumption corresponding to the processed natural gas data information, the gas consumption prediction method further includes:

[0111] Visually display the gas consumption and the natural gas data information.

[0112] Here, according to the processing results of the data, the system should also generate a visualization display interface, specifically including: Overall data chart: showing the changing trend of natural gas sales volume over time and the comparison data of sales volumes in different regions; Map visualization: marking the natural gas sales volumes in different regions on a map, with colors representing the magnitudes of the sales volumes; Trend analysis chart: showing the trend chart of historical natural gas sales volumes to help users discover periodic or seasonal sales patterns; Reports and statistical information: providing detailed reports and statistical information such as sales amount, sales volume ratio, and sales trend, presented in the form of tables or charts; Prediction model results: showing information such as model prediction results and confidence intervals; Alarms and notifications: setting up alarm and notification functions when key indicators exceed the thresholds to promptly remind users to pay attention to abnormal situations.

[0113] In this solution, the analysis results are presented to users through an intuitive visualization display interface, enabling users to intuitively understand the natural gas sales situation and make decisions and adjust strategies in a timely manner. Through the application of the present invention, natural gas suppliers and operators can formulate sales strategies more accurately, improving operational efficiency and profitability.

[0114] A method for predicting the gas consumption of natural gas provided by an embodiment of the present application, the gas consumption prediction method includes: collecting the data information of natural gas at a first moment in a natural gas data source; performing data standardization processing on the data information of the natural gas to determine the processed data information of the natural gas; inputting the processed data information of the natural gas into a pre-trained data analysis model, performing gas consumption analysis processing on the processed data information of the natural gas, and outputting the gas consumption corresponding to the processed data information of the natural gas; wherein, the data analysis model is obtained by training a neural network model. Deploying edge computing nodes near the data source realizes the efficient collection and real-time processing of natural gas data, improves the data collection and processing efficiency, ensures the real-time and accuracy of the data, and provides accurate decision-making support for natural gas suppliers and operators through in-depth analysis of natural gas data.

[0115] Please refer to Figure 2 、 Figure 3 , Figure 2 which is one of the structural schematic diagrams of a device for predicting the gas consumption of natural gas provided by an embodiment of the present application; Figure 3 which is the second structural schematic diagram of a device for predicting the gas consumption of natural gas provided by an embodiment of the present application. As Figure 2 shown in

[0116] A data collection module 210, configured to collect the data information of natural gas at a first moment in a natural gas data source;

[0117] The data cleaning module 220 is used to perform data standardization processing on the data information of the natural gas to determine the processed data information of the natural gas;

[0118] The data analysis module 230 is used to input the processed data information of the natural gas into a pre-trained data analysis model, perform gas consumption analysis processing on the processed data information of the natural gas, and output the gas consumption corresponding to the processed data information of the natural gas; wherein, the data analysis model is obtained by training a neural network model.

[0119] Further, when the data cleaning module 220 is used to perform data standardization processing on the data information of the natural gas to determine the processed data information of the natural gas, the data cleaning module 220 is specifically used for:

[0120] Perform mean calculation processing on the data information of the natural gas to determine the mean information corresponding to the data information of the natural gas;

[0121] Based on the data information of the natural gas and the mean information, perform data standardization processing to determine the processed data information of the natural gas.

[0122] Further, when the data analysis module 230 is used to input the processed data information of the natural gas into a pre-trained data analysis model, perform gas consumption analysis processing on the processed data information of the natural gas, and output the gas consumption corresponding to the processed data information of the natural gas, the data analysis module 230 is specifically used for:

[0123] Input the processed data information of the natural gas into the input layer of the data analysis model, process the processed data information of the natural gas, and output the first vector information corresponding to the processed data information of the natural gas;

[0124] Input the first vector information into the hidden layer of the data analysis model, and based on the second vector information corresponding to the second moment in the hidden layer, the first vector information, the input value weight matrix, the hidden layer bias, and the hidden value weight matrix, output the third vector information; wherein, the second moment is the previous moment of the first moment;

[0125] Input the third vector information into the output layer of the data analysis model, and based on the output layer bias of the output layer, the output value weight coefficient, and the third vector information, output the gas consumption corresponding to the processed data information of the natural gas.

[0126] Further, when the data analysis module 230 is used to input the first vector information into the hidden layer of the data analysis model and output the third vector information based on the second vector information corresponding to the second moment in the hidden layer, the first vector information, the input value weight matrix, the hidden layer bias, and the hidden value weight matrix, the data analysis module 230 is specifically configured to:

[0127] Multiply the input value weight matrix by the first vector information to determine the first information;

[0128] Multiply the hidden value weight matrix by the second vector information to determine the second information;

[0129] Add the first information, the second information, and the hidden layer bias to determine the third information;

[0130] Process the third information and output the third vector information.

[0131] Further, when the data analysis module 230 is used to input the third vector information into the output layer of the data analysis model and output the gas consumption corresponding to the processed natural gas data information based on the output layer bias, the output value weight coefficient, and the third vector information, the data analysis module 230 is specifically configured to:

[0132] Multiply the third vector information by the output value weight coefficient to determine the fourth information;

[0133] Add the fourth information to the output layer bias and output the gas consumption corresponding to the processed natural gas data information.

[0134] Further, as Figure 3 shown, the gas consumption prediction device 200 further includes a visualization display module 240, and the visualization display module 240 is used to:

[0135] Visualize and display the gas consumption and the natural gas data information.

[0136] Further, as Figure 3 shown, the gas consumption prediction device 200 further includes a model training module 250, and the model training module 250 is used to:

[0137] Obtain the sample natural gas data information and the actual gas consumption of the sample natural gas data information;

[0138] Input the sample natural gas data information into the neural network model, process the sample natural gas data information, and output the predicted gas consumption of the sample natural gas data information;

[0139] Process the predicted gas consumption and the actual gas consumption based on the loss function calculation formula to determine the loss value of the neural network model;

[0140] Iteratively change the input value weight matrix, hidden layer bias, hidden value weight matrix, output layer bias, and output value weight coefficient of the neural network model based on the loss value to determine the data analysis model.

[0141] A gas consumption prediction device for natural gas provided by an embodiment of the present application. The gas consumption prediction device includes: a data acquisition module for acquiring data information of natural gas at a first moment in a natural gas data source; a data cleaning module for performing data standardization processing on the data information of the natural gas to determine the processed data information of the natural gas; a data analysis module for inputting the processed data information of the natural gas into a pre-trained data analysis model, performing gas consumption analysis processing on the processed data information of the natural gas, and outputting the gas consumption corresponding to the processed data information of the natural gas; wherein, the data analysis model is obtained by training a neural network model. Deploying edge computing nodes near the data source realizes efficient acquisition and real-time processing of natural gas data, improves data acquisition and processing efficiency, ensures the real-time and accuracy of data, and provides accurate decision-making support for natural gas suppliers and operators through in-depth analysis of natural gas data.

[0142] Please refer to Figure 4 , Figure 4 which is a schematic structural diagram of an electronic device provided by an embodiment of the present application. As Figure 4 shown in, the electronic device 400 includes a processor 410, a memory 420, and a bus 430.

[0143] The memory 420 stores machine-readable instructions executable by the processor 410. When the electronic device 400 runs, the processor 410 communicates with the memory 420 through the bus 430. When the machine-readable instructions are executed by the processor 410, the steps of the gas consumption prediction method for natural gas in the method embodiment as shown above can be executed. The specific implementation manner can refer to the method embodiment and will not be elaborated here. Figure 1 shown in

[0144] An embodiment of the present application further provides a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is run by a processor, the steps of the gas consumption prediction method for natural gas in the method embodiment as shown above can be executed. The specific implementation manner can refer to the method embodiment and will not be elaborated here. Figure 1 shown in

[0145] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0146] In several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For another example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some communication interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0147] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0148] In addition, in each embodiment of the present application, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0149] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer-readable storage medium executable by a processor. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0150] Finally, it should be noted that the above-described embodiments are only specific embodiments of the present application, which are used to illustrate the technical solutions of the present application, rather than limiting them. The protection scope of the present application is not limited thereto. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that any person skilled in the art within the technical scope disclosed by the present application can still modify the technical solutions described in the foregoing embodiments, or can easily conceive of changes, or make equivalent replacements for some of the technical features; and these modifications, changes or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for predicting the gas consumption of natural gas, characterized in that, The gas consumption prediction method is applied to a gas consumption prediction device for natural gas. The gas consumption prediction device for natural gas is deployed on an edge computing node of a natural gas data source. The gas consumption prediction method includes: Collect data information of natural gas at a first moment in the natural gas data source; Perform data standardization processing on the data information of the natural gas to determine the processed data information of the natural gas; Input the processed data information of the natural gas into a pre-trained data analysis model, perform gas consumption analysis processing on the processed data information of the natural gas, and output the gas consumption corresponding to the processed data information of the natural gas. Wherein, the data analysis model is obtained by training a neural network model.

2. The method for predicting gas consumption according to claim 1, characterized in that, The performing data standardization processing on the data information of the natural gas to determine the processed data information of the natural gas includes: Perform mean calculation processing on the data information of the natural gas to determine the mean information corresponding to the data information of the natural gas; Perform data standardization processing based on the data information of the natural gas and the mean information to determine the processed data information of the natural gas.

3. The method for predicting gas consumption according to claim 1, characterized in that, The inputting the processed data information of the natural gas into a pre-trained data analysis model, performing gas consumption analysis processing on the processed data information of the natural gas, and outputting the gas consumption corresponding to the processed data information of the natural gas includes: Input the processed data information of the natural gas into the input layer of the data analysis model, process the processed data information of the natural gas, and output the first vector information corresponding to the processed data information of the natural gas; Input the first vector information into the hidden layer of the data analysis model, and based on the second vector information corresponding to the second moment in the hidden layer, the first vector information, the input value weight matrix, the hidden layer bias, and the hidden value weight matrix, output the third vector information. Wherein, the second moment is the previous moment of the first moment; Input the third vector information into the output layer of the data analysis model, and based on the output layer bias of the output layer, the output value weight coefficient, and the third vector information, output the gas consumption corresponding to the processed data information of the natural gas.

4. The method for predicting gas consumption according to claim 3, characterized in that, The inputting the first vector information into the hidden layer of the data analysis model, and based on the second vector information corresponding to the second moment in the hidden layer, the first vector information, the input value weight matrix, the hidden layer bias, and the hidden value weight matrix, outputting the third vector information includes: Multiply the input value weight matrix by the first vector information to determine the first information; Multiply the hidden value weight matrix by the second vector information to determine the second information; Add the first information, the second information, and the hidden layer bias to determine the third information; Process the third information to output the third vector information.

5. The method for predicting gas consumption according to claim 3, characterized in that, Inputting the third vector information into the output layer of the data analysis model, and based on the output layer bias, output value weight coefficient, and the third vector information, outputting the gas consumption corresponding to the processed natural gas data information, including: Multiplying the third vector information by the output value weight coefficient to determine a fourth piece of information; Adding the fourth piece of information to the output layer bias to output the gas consumption corresponding to the processed natural gas data information.

6. The method for predicting gas consumption according to claim 1, characterized in that, After inputting the processed natural gas data information into a pre-trained data analysis model, performing gas consumption analysis processing on the processed natural gas data information, and outputting the gas consumption corresponding to the processed natural gas data information, the gas consumption prediction method further includes: Visualizing the gas consumption and the natural gas data information.

7. The method for predicting gas consumption according to claim 1, characterized in that, Determining the data analysis model through the following steps: Obtaining sample natural gas data information and the actual gas consumption of the sample natural gas data information; Inputting the sample natural gas data information into the neural network model, processing the sample natural gas data information, and outputting the predicted gas consumption of the sample natural gas data information; Based on the loss function calculation formula, processing the predicted gas consumption and the actual gas consumption to determine the loss value of the neural network model; Based on the loss value, iteratively changing the input value weight matrix, hidden layer bias, hidden value weight matrix, output layer bias, and output value weight coefficient of the neural network model to determine the data analysis model.

8. A device for predicting the gas consumption of natural gas, characterized in that, The gas consumption prediction device includes: A data acquisition module for acquiring natural gas data information at a first moment in a natural gas data source; A data cleaning module for performing data standardization processing on the natural gas data information to determine the processed natural gas data information; A data analysis module for inputting the processed natural gas data information into a pre-trained data analysis model, performing gas consumption analysis processing on the processed natural gas data information, and outputting the gas consumption corresponding to the processed natural gas data information; wherein the data analysis model is obtained by training a neural network model.

9. An electronic device, characterized in that,Including: A processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device runs, the processor communicates with the memory through the bus. When the machine-readable instructions are run by the processor, the steps of the natural gas consumption prediction method according to any one of claims 1 to 7 are executed.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium. When the computer program is run by the processor, the steps of the natural gas consumption prediction method according to any one of claims 1 to 7 are executed.

Images