CN116341152A - Gas load prediction method and device, electronic equipment and storage medium - Google Patents
Gas load prediction method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116341152A CN116341152A CN202111530673.4A CN202111530673A CN116341152A CN 116341152 A CN116341152 A CN 116341152A CN 202111530673 A CN202111530673 A CN 202111530673A CN 116341152 A CN116341152 A CN 116341152A
- Authority
- CN
- China
- Prior art keywords
- data
- historical
- gas
- influence factor
- predicted value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000003860 storage Methods 0.000 title claims abstract description 52
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 claims abstract description 149
- 239000007789 gas Substances 0.000 claims abstract description 145
- 239000003345 natural gas Substances 0.000 claims abstract description 74
- 238000012549 training Methods 0.000 claims abstract description 27
- 238000007726 management method Methods 0.000 claims description 31
- 238000004590 computer program Methods 0.000 claims description 20
- 238000000605 extraction Methods 0.000 claims description 20
- 238000013140 knowledge distillation Methods 0.000 claims description 17
- 238000003062 neural network model Methods 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000004458 analytical method Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 7
- 238000007621 cluster analysis Methods 0.000 claims description 5
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 7
- 238000010438 heat treatment Methods 0.000 description 7
- 238000013473 artificial intelligence Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000007637 random forest analysis Methods 0.000 description 3
- 230000002776 aggregation Effects 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 2
- 238000013499 data model Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000012880 independent component analysis Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000013450 outlier detection Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/18—Network design, e.g. design based on topological or interconnect aspects of utility systems, piping, heating ventilation air conditioning [HVAC] or cabling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/14—Pipes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Geometry (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Computing Systems (AREA)
- Marketing (AREA)
- Mathematical Physics (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Entrepreneurship & Innovation (AREA)
- Primary Health Care (AREA)
- Development Economics (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
Abstract
The invention provides a gas load prediction method, a gas load prediction device, electronic equipment and a storage medium. The method comprises the following steps: acquiring historical original data in a target area; extracting features of the historical original data to obtain data features of the historical original data; determining appointed influence factor data related to the data characteristics of the historical original data according to the data characteristics of the historical original data; comparing the appointed influence factor data with the historical actual influence factor data to obtain variation data of the influence factor data; training and predicting variable data of sample data and influence factor data by using a gas load prediction model, and determining a first predicted value of the gas load; collecting pipeline pressure data in a target area, calling a pipeline storage data prediction model to train the pipeline pressure data, and determining a predicted value of the pipeline storage gas; and determining the gas load predicted value according to the first predicted value and the pipe gas predicted value. The method solves the problem of accurately predicting the use amount of the natural gas.
Description
Technical Field
The disclosure relates to the technical field of artificial intelligence, and in particular relates to a gas load prediction method, a device, electronic equipment and a storage medium.
Background
The natural gas industry rapidly develops, the dispatching management, planning operation and operation optimization of the natural gas pipeline are all dependent on an accurate load prediction technology, and the more accurate prediction of the natural gas consumption is of great significance to the future optimized dispatching of connecting the natural gas pipe networks of all cities, the reasonable planning of the gas consumption of gas companies and the optimized operation of the urban gas pipe networks.
The existing gas load prediction method predicts the gas load according to weather influence factors and the natural gas consumption, but in a real natural gas application scene, factors such as holidays, heating periods and the like can greatly influence the natural gas consumption; in addition, because the natural gas is transported by a long-distance pipeline, natural gas residues exist in the pipeline, and the content of the residual natural gas cannot be ignored in the prediction process. Therefore, the existing prediction method cannot be combined with a real natural gas use scene to accurately predict the use amount of the natural gas.
Disclosure of Invention
In view of the above, embodiments of the present disclosure provide a method, an apparatus, an electronic device, and a storage medium for predicting a gas load, so as to solve the problem that a prediction method in the prior art cannot combine with a real natural gas usage scenario to accurately predict a usage amount of natural gas.
In a first aspect of an embodiment of the present disclosure, there is provided a gas load prediction method, including:
acquiring historical original data in a target area, wherein the historical original data comprises historical actual use data of natural gas and historical management data of the natural gas;
extracting features of the historical original data to obtain data features of the historical original data;
determining appointed influence factor data related to the data characteristics of the historical original data according to the data characteristics of the historical original data;
comparing the appointed influence factor data with the historical actual influence factor data to obtain variation data of the influence factor data;
training and predicting variable data of sample data and influence factor data by using a gas load prediction model to determine a first predicted value of the gas load, wherein the gas load prediction model is a neural network model based on a knowledge distillation frame;
collecting pipeline pressure data in a target area, calling a pipeline storage data prediction model to train the pipeline pressure data, and determining a predicted value of the pipeline storage gas;
and determining the gas load predicted value according to the first predicted value and the pipe gas predicted value.
In a second aspect of the embodiments of the present disclosure, there is provided a gas load prediction apparatus including:
The data acquisition module is configured to acquire historical original data in the target area, wherein the historical original data comprises historical actual use data of the natural gas and historical management data of the natural gas;
the feature extraction module is configured to perform feature extraction on the historical original data to obtain data features of the historical original data;
the characteristic determining module is configured to determine specified influence factor data related to the data characteristics of the historical original data according to the data characteristics of the historical original data;
the data comparison module is configured to compare the appointed influence factor data with the historical actual influence factor data so as to obtain variation data of the influence factor data;
the determining module is configured to train and predict variable data of sample data and influence factor data by using a gas load prediction model to determine a first predicted value of the gas load, wherein the gas load prediction model is a neural network model based on a knowledge distillation frame; collecting pipeline pressure data in a target area, calling a pipeline storage data prediction model to train the pipeline pressure data, and determining a predicted value of the pipeline storage gas; and determining the gas load predicted value according to the first predicted value and the pipe gas predicted value.
In a third aspect of the disclosed embodiments, an electronic device is provided, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the above method when executing the computer program.
In a fourth aspect of the disclosed embodiments, a computer-readable storage medium is provided, which stores a computer program which, when executed by a processor, implements the steps of the above-described method.
Compared with the prior art, the embodiment of the disclosure has the beneficial effects that: the residual data in the natural gas pipeline is taken as a part of the historical original data of the target area in combination with the use scene of the natural gas, so that the data characteristics of the actual gas and the data characteristics of the pipeline residual are obtained, and the use condition of the actual natural gas can be reflected more accurately and comprehensively; and analyzing the historical original data to obtain appointed influence factor data, comparing the influence factor data with actual influence factor data to obtain the variation of the influence factor, further accurately processing the influence factor, obtaining a first predicted value according to the sample data and the variation of the influence factor, obtaining a pipe gas storage predicted value according to the pipeline pressure value, and obtaining a final gas load predicted value by combining the first predicted value and the pipe gas storage predicted value to realize accurate prediction.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings that are required for the embodiments or the description of the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and other drawings may be obtained according to these drawings without inventive effort for a person of ordinary skill in the art.
FIG. 1 is a schematic diagram of a joint learning architecture according to an embodiment of the present disclosure;
FIG. 2 is a schematic flow chart of a method for gas load prediction provided by an embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a prediction flow of a gas load prediction model according to an embodiment of the present disclosure;
FIG. 4 is a schematic diagram of a gas load prediction apparatus according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system configurations, techniques, etc. in order to provide a thorough understanding of the disclosed embodiments. However, it will be apparent to one skilled in the art that the present disclosure may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present disclosure with unnecessary detail.
The joint learning refers to comprehensively utilizing a plurality of AI (Artificial Intelligence ) technologies on the premise of ensuring data safety and user privacy, jointly excavating data value by combining multiparty cooperation, and promoting new intelligent business states and modes based on joint modeling. The joint learning has at least the following characteristics:
(1) The participating nodes control the weak centralized joint training mode of the own data, so that the data privacy safety in the co-creation intelligent process is ensured.
(2) Under different application scenes, a plurality of model aggregation optimization strategies are established by utilizing screening and/or combination of an AI algorithm and privacy protection calculation so as to obtain a high-level and high-quality model.
(3) On the premise of ensuring data safety and user privacy, a method for improving the efficiency of the joint learning engine is obtained based on a plurality of model aggregation optimization strategies, wherein the efficiency method can be used for improving the overall efficiency of the joint learning engine by solving the problems of information interaction, intelligent perception, exception handling mechanisms and the like under a large-scale cross-domain network with parallel computing architecture.
(4) The requirements of multiparty users in all scenes are acquired, the real contribution degree of all joint participants is determined and reasonably evaluated through a mutual trust mechanism, and distribution excitation is carried out.
Based on the mode, AI technical ecology based on joint learning can be established, the industry data value is fully exerted, and the scene of the vertical field is promoted to fall to the ground.
A method and apparatus for predicting a gas load according to an embodiment of the present disclosure will be described in detail with reference to the accompanying drawings.
Fig. 1 is a schematic diagram of a joint learning architecture according to an embodiment of the present disclosure. As shown in fig. 1, the architecture of joint learning may include a server (central node) 101, as well as participants 102, 103, and 104.
In the joint learning process, a basic model may be established by the server 101, and the server 101 transmits the model to the participants 102, 103, and 104 with which a communication connection is established. The basic model may also be uploaded to the server 101 after any party has established, and the server 101 sends the model to the other parties with whom it has established a communication connection. The participants 102, 103 and 104 construct a model according to the downloaded basic structure and model parameters, perform model training using local data, obtain updated model parameters, and encrypt and upload the updated model parameters to the server 101. Server 101 aggregates the model parameters sent by participants 102, 103, and 104 to obtain global model parameters, and transmits the global model parameters back to participants 102, 103, and 104. Participant 102, participant 103 and participant 104 iterate the respective models according to the received global model parameters until the models eventually converge, thereby enabling training of the models. In the joint learning process, the data uploaded by the participants 102, 103 and 104 are model parameters, local data is not uploaded to the server 101, and all the participants can share final model parameters, so that common modeling can be realized on the basis of ensuring data privacy. It should be noted that the number of participants is not limited to three as described above, but may be set as needed, and the embodiment of the present disclosure is not limited thereto.
Fig. 2 is a schematic flow chart of a gas load prediction method according to an embodiment of the disclosure. The air load prediction method of fig. 2 may be performed by the server or the participants of fig. 1. As shown in fig. 2, the gas load prediction method includes:
s201, acquiring historical original data in a target area, wherein the historical original data comprises historical actual use data of natural gas and historical management data of the natural gas;
the historical actual use data is the natural gas use amount in the target area, and the historical pipe storage data is the residual data of the natural gas pipeline in the target area.
S202, extracting features of the historical original data to obtain data features of the historical original data;
the data characteristics of the historical original data are used for representing the data characteristics of the natural gas usage in the target area and the data characteristics of the natural gas pipeline residues in the target area.
S203, determining appointed influence factor data related to the data characteristics of the historical original data according to the data characteristics of the historical original data;
specifically, the specified influence factor data related to the data characteristics of the historical original data can be determined through a preset data analysis method, wherein the specified influence factor data comprises any one or more of weather data, heating period data and holiday data.
S204, comparing the appointed influence factor data with the historical actual influence factor data to obtain variation data of the influence factor data;
specifically, the specified influence factor data is compared with the historical actual influence factor data, and the change amount of the influence factor data is determined.
S205, training and predicting variable data of sample data and influence factor data by using a gas load prediction model, and determining a first predicted value of the gas load;
the gas load prediction model is a neural network model based on a knowledge distillation frame;
specifically, the predicted sample data and the variation are input into a pre-trained air load prediction model, and a first predicted value of the air load is determined, wherein the air load prediction model is a neural network model based on a knowledge distillation frame.
S206, collecting pipeline pressure data in the target area, calling pipeline pressure data of the pipeline storage data prediction model training pipeline pressure data, and determining a predicted value of the pipeline storage gas.
S207, determining a gas load predicted value according to the first predicted value and the pipe gas predicted value.
Specifically, in order to combine the actual use scene of the natural gas, obtain accurate and comprehensive gas load prediction data, in a historical data acquisition stage, the actual use amount of the natural gas in a target area is acquired through electronic equipment and used as historical actual use data. Because of the specificity of the natural gas transportation scene, the residual natural gas data in the natural gas pipeline data in the target area is also collected, and the residual data in the natural gas pipeline is used as historical pipe storage data.
Specifically, the characteristic extraction is carried out on the historical original data, missing value filling can be carried out on the historical original data, and abnormal value detection is carried out on the filled actual gas data and the filled historical management data in a specified mode; according to the detection result, carrying out outlier replacement on the filled history actual gas data and the filled history management data to obtain preprocessed history original data; extracting a first data feature group in the preprocessed historical original data according to a preset feature extraction algorithm;
performing cluster analysis on the preprocessed historical original data, and dividing the preprocessed historical original data into a plurality of data groups; performing feature analysis on the data in each data group to determine common features in the groups, and performing feature analysis on a plurality of data groups to determine inter-group difference features; determining a second data feature set according to the intra-group common features and the inter-group differential features; and determining the data characteristics of the historical original data according to the first data characteristic group and the second data characteristic group.
It should be noted that, feature extraction refers to performing a series of processes on the historical original data, and refining the historical original data into data features in combination with an actual application scenario, so as to facilitate the subsequent related computation through an algorithm and a model. The data characteristics of the historical raw data are used for expressing the data characteristics of the natural gas usage in the target area and the data characteristics of the natural gas pipeline residues.
Specifically, according to the data characteristics of the historical original data, determining the appointed influence factor data related to the data characteristics of the historical original data, wherein the influence factor data corresponding to the historical original data can be obtained in the target area; performing dimensionless treatment on the historical original data and the influence factor data respectively, taking the treated historical original data as a comparison sequence, and taking the treated influence factor data as a comparison sequence; calculating the association coefficient of the comparison number sequence and the comparison number sequence, and determining the association degree of the influence factor data and the historical original data according to the association coefficient; and sequencing the association degrees according to a preset rule, and taking the influence factor data with the association degrees higher than a preset threshold value as the appointed influence factor data.
Further, through a preset data analysis method, data characteristics of the historical original data are analyzed, specified influence factor characteristics related to the historical original data are determined, and specified influence factor data are determined according to the specified influence factor characteristics. That is, the influence factor data influencing the natural gas usage amount is extracted from the data characteristics of the historical raw data. Since the natural gas usage is closely related to weather conditions, heating period conditions, holidays, and the like, for example, the natural gas usage is smaller in sunny weather than in overcast and rainy weather, and is also greatly different from the natural gas usage in non-heating period during heating, the natural gas usage is drastically reduced when in specific holidays such as national holidays, spring festival, and the like. Therefore, by analyzing the historical original data of the natural gas, the influence factor data influencing the historical original data is obtained, and the appointed influence factor data obtained by the method can more accurately represent the influence of the specific influence factor data on the natural gas usage.
Specifically, the real influence factor data corresponding to the historical original data in the time is obtained, the real influence factor data corresponding to the historical time is compared with the appointed influence factor data, and the change amount of the influence factor is obtained, for example, the obtained appointed influence factor data is the air temperature of 20 degrees in the weather data, the air temperature of 25 degrees in the real weather data in the corresponding time, and then the change amount of the weather data is 5 degrees. That is, the embodiments of the present disclosure consider the variation situation of the actual factors, so that a more accurate data range of the influence factor data can be obtained.
Specifically, the first predicted value of the air load is determined by training and predicting variable data of sample data and influence factor data by using an air load prediction model, and a data set of historical air data and influence factor data can be collected; invoking data in a data set of pre-constructed training influence factor data of a knowledge distillation teacher model, and determining historical gas data as output soft targets and/or output prediction gas data; modifying a loss function of the teacher model according to the output soft target, and training the teacher model; inputting data in a data set of influence factor data into a pre-constructed knowledge distillation student model, taking the prediction gas data as a target value of the student model, and training the student model to obtain a gas load prediction model meeting the requirements.
Further, the predicted sample data and the variation are input into a pre-trained gas load prediction model together, and a first predicted value of the gas load is determined. The gas load prediction model is a neural network model based on a knowledge distillation framework. It should be noted that the knowledge distillation framework mainly teaches a smaller network exactly what to do by using a larger already trained network step by step, and then the small network is trained to learn the exact behavior of the large network by trying to replicate the output of the large network at each layer. The framework mainly consists of a Teacher model and a Student model. According to the Teacher model, the problem that the acquisition frequencies of the air consumption data and the weather and other influence factor data in air consumption prediction are different is solved through the deep learning network, and the data model of the influence factor data in the hour level can be simulated. The Student model realizes the hour-level real-time prediction of gas consumption data through a random forest. The predicted sample data and the sample data variable quantity are input into the model together, the change condition of the influence factors is considered, and a more accurate first predicted value can be obtained.
Specifically, in an actual application scenario, part of natural gas also exists in the natural gas pipeline, and when the use condition of the front gas is predicted, the residual quantity in the natural gas pipeline is usually ignored. Thus, in embodiments of the present disclosure, a pipeline pressure value within a target area is collected, the pipeline pressure value is input into a pre-trained pipeline storage data prediction model, and a pipeline storage gas prediction value is determined from the pipeline pressure value.
Specifically, the gas load predicted value is determined based on the first predicted value and the pipe gas predicted value.
According to the technical scheme provided by the embodiment of the disclosure, by combining the use scene of the natural gas, the residual data in the natural gas pipeline is used as a part of the historical original data of the target area, so that the data characteristics of the actual gas and the data characteristics of the residual pipeline are obtained, and the use condition of the actual natural gas can be reflected more accurately and comprehensively; and analyzing the historical original data to obtain appointed influence factor data, comparing the influence factor data with actual influence factor data to obtain the variation of the influence factor, further accurately processing the influence factor, obtaining a first predicted value according to the sample data and the variation of the influence factor, obtaining a pipe gas storage predicted value according to the pipeline pressure value, and obtaining a final gas load predicted value by combining the first predicted value and the pipe gas storage predicted value to realize accurate prediction.
In some embodiments, feature extraction is performed on the historical original data to obtain data features of the historical original data, which specifically includes: filling missing values of the historical original data, and detecting abnormal values of the filled actual gas data and the filled historical management data in a specified mode; according to the detection result, carrying out outlier replacement on the filled history actual gas data and the filled history management data to obtain preprocessed history original data; extracting a first data feature group in the preprocessed historical original data according to a preset feature extraction algorithm; performing cluster analysis on the preprocessed historical original data, and dividing the preprocessed historical original data into a plurality of data groups; performing feature analysis on the data in each data group to determine common features in the groups, and performing feature analysis on a plurality of data groups to determine inter-group difference features; determining a second data feature set according to the intra-group common features and the inter-group differential features; and determining the data characteristics of the historical original data according to the first data characteristic group and the second data characteristic group.
Specifically, since the obtained source of the history raw data of the obtained natural gas is different, abnormal data may exist in the history raw data, and thus, the history raw data needs to be preprocessed in advance. The actual natural gas historical original data is small in number due to the specificity of the data, so that each piece of data needs to be processed as useful data, missing value filling can be carried out on the historical original data, and the filling data can be determined according to average data in similar time or can be set by combining experience. After filling the missing value of the historical original data, detecting the abnormal value of the filled data, and replacing the detected abnormal value with a normal value, wherein the abnormal value detection method can be a simple statistical method or other detection methods, and is not particularly limited.
And after preprocessing the historical original data, extracting characteristic data of the preprocessed historical original data. Firstly, extracting features of the preprocessed historical original data to obtain a first data feature group of the historical original data, wherein the first data feature group is used for representing data features shared by the historical original data, and the extraction algorithm can be a principal component analysis algorithm or an independent component analysis algorithm. And then, carrying out cluster analysis on the preprocessed historical original data, and dividing the data into a plurality of data groups. And carrying out feature analysis on the data in each data group in each group, counting the value frequency of each data variable in the corresponding data group, taking the distribution condition of the value frequency as the intra-group common feature of the data group, and taking the intra-group common feature as the intra-group common feature.
And carrying out characteristic analysis on the plurality of data groups, taking the data variable with obvious difference of the value frequency numbers in the two different data groups as the inter-group difference characteristic between the two data groups, and determining the inter-group difference characteristic. The intra-group common features and inter-group differential features are grouped into a second set of data features. The second set of data features is used to represent data features of finer historical raw data. And taking the data characteristics in the first data characteristic group and the data characteristics in the second data characteristic group as the data characteristics of the historical original data.
According to the technical scheme provided by the embodiment of the disclosure, the historical original data is preprocessed, the influence of the missing value and the abnormal value existing in the data on the feature extraction effect is avoided, and the accuracy and the comprehensiveness of the data features of the historical original data can be effectively ensured by carrying out integral feature extraction on the historical original data and feature extraction on the packet data and combining the two feature extraction methods to obtain the data features.
In some embodiments, determining the specified influencing factor data related to the feature vector of the historical original data through a specified data analysis method specifically comprises: acquiring influence factor data corresponding to historical original data in a target area; performing dimensionless treatment on the historical original data and the influence factor data respectively, taking the treated historical original data as a comparison sequence, and taking the treated influence factor data as a comparison sequence; calculating the association coefficient of the comparison number sequence and the comparison number sequence, and determining the association degree of the influence factor data and the historical original data according to the association coefficient; and sequencing the association degrees according to a preset rule, and taking the influence factor data with the association degrees higher than a preset threshold value as the appointed influence factor data.
Specifically, according to the corresponding time of the historical original data, the influence factor data of the same time in the target area is obtained, for example, weather data in the corresponding time period, whether the corresponding time period is a heating period and whether the corresponding time period is a holiday, and dimensionless processing is performed on the influence factor data and the historical original data respectively, so that comparison calculation can be performed between the influence factor data and the historical original data. The method comprises the steps of taking processed historical original data as a comparison sequence, taking processed influence factor data as a comparison sequence, calculating the association coefficient of the comparison sequence and the comparison sequence, and determining the association degree of the influence factor data and the historical original data according to the association coefficient. And sequencing the association degrees according to the numerical values, and taking the influence factor data with the association degrees higher than a preset threshold value as the appointed influence factor data. It should be noted that, the preset threshold value herein may be determined according to the actual situation of the user, and when the requirement on the influencing factor is strict, the data ranked in the top 70% and having the association degree greater than the specified value may be selected.
According to the technical scheme provided by the embodiment of the disclosure, through dimensionless processing of the historical original data and the influence factor data, comparison calculation can be performed between the two types of data, and through relevance calculation, the influence degree of the influence factor on the use condition of the natural gas is quantitatively displayed, so that more accurate influence factor types can be obtained.
In some embodiments, a dataset of historical gas data and influencing factor data is collected; invoking data in a data set of pre-constructed training influence factor data of a knowledge distillation teacher model, and determining historical gas data as output soft targets and/or output prediction gas data; modifying a loss function of the teacher model according to the output soft target, and training the teacher model; inputting the data in the data set of the influence factor data into a pre-constructed knowledge distillation student model, taking the prediction gas data as a target value of the student model, and training the student model to obtain a gas load prediction model meeting the requirements.
Specifically, a teacher model of the multilayer feedforward neural network is constructed, the teacher model comprises an input layer, two hidden layers and an output layer, the input variable dimension of the input layer is 32 dimensions, the number of neurons of the two hidden layers is 512 and 256 respectively, and the output layer is used for outputting predicted values of gas data; and the ReLU function is selected as an activation function, so that the model training speed and efficiency can be improved. A student model is built by adopting a random forest algorithm Xgboost, and each round of Xgboost trains a tree, so that a loss function can be minimized, the loss function not only measures the fitting error of the model, but also adds a regularization term, namely a penalty term for the complexity of each tree, so as to prevent over-fitting.
And constructing a data set of the historical gas data and the influence factor data, inputting the influence factor data into a pre-constructed teacher model, taking the historical gas data as an output soft target, and outputting the prediction gas data. And modifying the loss function of the teacher model according to the output soft target, and training the teacher model. The method comprises the steps of inputting influence factor data into a pre-constructed student model, taking prediction gas data as a target value of the student model, training the student model to obtain a gas load prediction model meeting requirements, and as shown in fig. 3, fig. 3 is a prediction flow of the gas load prediction model provided by the embodiment of the disclosure, inputting the influence factor data and natural gas use data in sample data into a teacher model and the student model respectively, outputting hour-level prediction gas data in the teacher model, taking the data as a soft target, taking the data as the target value of the student model, and obtaining a final prediction result through the student model.
According to the technical scheme provided by the embodiment of the disclosure, the problem that the collection frequency of the gas consumption data and the collection frequency of the influence factor data in the gas consumption prediction are different is solved through the Teacher according to the deep learning network, a data model of the influence factor data of an hour level can be simulated, and the hour level real-time prediction of the gas consumption data is realized through a random forest algorithm of the Student model.
In some embodiments, determining the gas load predicted value according to the first predicted value and the stored gas predicted value specifically includes: calculating the ratio of the pipe stored gas predicted value to the first predicted value to obtain a first ratio; calculating the ratio of the historical pipe storage data to the historical actual gas data to obtain a second ratio; and if the difference value of the first ratio and the second ratio is larger than a preset threshold value, carrying out weighted calculation on the first predicted value and the pipe gas predicted value to obtain the gas load predicted value.
Specifically, in combination with an actual natural gas application scene, in a metropolitan area, natural gas is mostly transmitted by using long-distance pipelines, and the content of the residual natural gas in the long-distance pipelines cannot be ignored and also belongs to a part of natural gas scheduling links. But in smaller areas the residue in the natural gas pipeline is less and negligible. Thus, it may be determined whether the pipeline data needs to be added to the final predicted value by the ratio of pipeline inventory to actual usage. And calculating the ratio of the pipe gas storage predicted value to the first predicted value, wherein the first ratio is used for representing the predicted data duty ratio. Calculating the ratio of the historical pipe storage data to the historical actual gas utilization data as a second ratio, wherein the second ratio is used for representing the actual ratio situation of the historical pipe storage data in the target area, and judging whether the situation of the first ratio needs to be added with the pipe storage data or not according to the second ratio. And carrying out weighted calculation on the pipe stored gas predicted value and the first predicted value to obtain a final gas load predicted value.
According to the technical scheme provided by the embodiment of the disclosure, the gas load prediction data is obtained by combining the actual natural gas application scene, the prediction data is closer to the actual scene, and the accuracy of the prediction data is improved.
In some embodiments, inputting pipeline pressure values into a pre-trained pipe storage data prediction model, determining pipe storage gas prediction values, and constructing a pipe storage data set according to historical pipeline pressure values and historical pipe storage data before; the historical pipeline pressure values in the management data set are input into a pre-built neural network model, the historical management data are used as output targets of the neural network model, model parameters are adjusted, and the model is trained so as to determine a management data prediction model meeting requirements.
Specifically, a neural network model is built in advance, the neural network model is trained through the historical pipeline pressure value and the historical management data, model parameters are adjusted according to the historical management data, and a management data prediction model meeting the requirements is determined.
According to the technical scheme provided by the embodiment of the disclosure, the management data prediction model is used for obtaining the management data, so that the calculation time is saved, and the accuracy of the management data is further enhanced.
In some embodiments, the gas load is used to represent the natural gas usage in the target zone.
Any combination of the above optional solutions may be adopted to form an optional embodiment of the present application, which is not described herein in detail.
The following are device embodiments of the present disclosure that may be used to perform method embodiments of the present disclosure. For details not disclosed in the embodiments of the apparatus of the present disclosure, please refer to the embodiments of the method of the present disclosure.
Fig. 4 is a schematic diagram of a gas load prediction apparatus according to an embodiment of the present disclosure. As shown in fig. 4, the gas load prediction apparatus includes:
the data acquisition module 401 is configured to acquire historical raw data in the target area, where the historical raw data includes historical actual usage data of the natural gas and historical management data of the natural gas, and the historical actual usage data is an amount of natural gas usage in the target area, and the historical management data is residual data of a natural gas pipeline in the target area.
The feature extraction module 402 is configured to perform feature extraction on the historical original data to obtain data features of the historical original data, where the data features of the historical original data are used for representing data features of natural gas usage in the target area and data features of natural gas pipeline residues in the target area.
The feature determining module 403 is configured to determine specified influence factor data related to the data features of the historical raw data according to the data features of the historical raw data, wherein the specified influence factor data includes any one or more of weather data, heating period data, and holiday data.
The data comparison module 404 is configured to compare the specified influence factor data with the historical actual influence factor data to obtain variation data of the influence factor data.
A determining module 405 configured to determine a first predicted value of the air load by using variable data of the air load prediction model training prediction sample data and the influence factor data, wherein the air load prediction model is a neural network model based on a knowledge distillation frame; collecting pipeline pressure data in a target area, calling a pipeline storage data prediction model to train the pipeline pressure data, and determining a predicted value of the pipeline storage gas; and determining the gas load predicted value according to the first predicted value and the pipe gas predicted value.
According to the technical scheme provided by the embodiment of the disclosure, the residual data in the natural gas pipeline is taken as a part of the historical original data of the target area in combination with the use scene of the natural gas, so that the data characteristics of the actual gas and the data characteristics of the pipeline residual are obtained, and the use situation of the actual natural gas can be reflected more accurately and comprehensively; and analyzing the historical original data to obtain appointed influence factor data, comparing the influence factor data with actual influence factor data to obtain the variation of the influence factor, further accurately processing the influence factor, obtaining a first predicted value according to the sample data and the variation of the influence factor, obtaining a pipe gas storage predicted value according to the pipeline pressure value, and obtaining a final gas load predicted value by combining the first predicted value and the pipe gas storage predicted value to realize accurate prediction.
In some embodiments, the feature extraction module 402 is further configured to perform missing value filling on the historical raw data, and perform outlier detection on the filled actual gas data and the filled historical management data in a specified manner; according to the detection result, carrying out outlier replacement on the filled history actual gas data and the filled history management data to obtain preprocessed history original data; extracting a first data feature group in the preprocessed historical original data according to a preset feature extraction algorithm; performing cluster analysis on the preprocessed historical original data, and dividing the preprocessed historical original data into a plurality of data groups; performing feature analysis on the data in each data group to determine common features in the groups, and performing feature analysis on a plurality of data groups to determine inter-group difference features; determining a second data feature set according to the intra-group common features and the inter-group differential features; and determining the data characteristics of the historical original data according to the first data characteristic group and the second data characteristic group.
In some embodiments, the feature determining module 403 is further configured to obtain, in the target area, influence factor data corresponding to the historical raw data; performing dimensionless treatment on the historical original data and the influence factor data respectively, taking the treated historical original data as a comparison sequence, and taking the treated influence factor data as a comparison sequence; calculating the association coefficient of the comparison number sequence and the comparison number sequence, and determining the association degree of the influence factor data and the historical original data according to the association coefficient; and sequencing the association degrees according to a preset rule, and taking the influence factor data with the association degrees higher than a preset threshold value as the appointed influence factor data.
In some embodiments, further comprising a model determination module 406 configured to collect a dataset of historical gas data and influencing factor data; invoking data in a data set of pre-constructed training influence factor data of a knowledge distillation teacher model, and determining historical gas data as output soft targets and/or output prediction gas data; modifying a loss function of the teacher model according to the output soft target, and training the teacher model; inputting data in a data set of influence factor data into a pre-constructed knowledge distillation student model, taking the prediction gas data as a target value of the student model, and training the student model to obtain a gas load prediction model meeting the requirements.
In some embodiments, the determining module 405 is further configured to calculate a ratio of the stored gas prediction value to the first prediction value, resulting in a first ratio; calculating the ratio of the historical pipe storage data to the historical actual gas data to obtain a second ratio; and if the difference value of the first ratio and the second ratio is larger than a preset threshold value, carrying out weighted calculation on the first predicted value and the pipe gas predicted value to obtain the gas load predicted value.
In some embodiments, model determination module 406 is further configured to construct a tube store data set from the historical tube pressure values and the historical tube store data; the historical pipeline pressure values in the management data set are input into a pre-built neural network model, the historical management data are used as output targets of the neural network model, model parameters are adjusted, and the model is trained so as to determine a management data prediction model meeting requirements.
In some embodiments, the gas load is used to represent the natural gas usage in the target zone.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic of each process, and should not constitute any limitation on the implementation process of the embodiments of the disclosure.
Fig. 5 is a schematic diagram of an electronic device 5 provided by an embodiment of the present disclosure. As shown in fig. 5, the electronic apparatus 5 of this embodiment includes: a processor 501, a memory 502 and a computer program 503 stored in the memory 502 and executable on the processor 501. The steps of the various method embodiments described above are implemented by processor 501 when executing computer program 503. Alternatively, the processor 501, when executing the computer program 503, performs the functions of the modules/units in the above-described apparatus embodiments.
Illustratively, the computer program 503 may be partitioned into one or more modules/units, which are stored in the memory 502 and executed by the processor 501 to complete the present disclosure. One or more of the modules/units may be a series of computer program instruction segments capable of performing a specific function for describing the execution of the computer program 503 in the electronic device 5.
The electronic device 5 may be a desktop computer, a notebook computer, a palm computer, a cloud server, or the like. The electronic device 5 may include, but is not limited to, a processor 501 and a memory 502. It will be appreciated by those skilled in the art that fig. 5 is merely an example of the electronic device 5 and is not meant to be limiting as the electronic device 5 may include more or fewer components than shown, or may combine certain components, or different components, e.g., the electronic device may further include an input-output device, a network access device, a bus, etc.
The processor 501 may be a central processing unit (Central Processing Unit, CPU) or other general purpose processor, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 502 may be an internal storage unit of the electronic device 5, for example, a hard disk or a memory of the electronic device 5. The memory 502 may also be an external storage device of the electronic device 5, for example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like, which are provided on the electronic device 5. Further, the memory 502 may also include both internal storage units and external storage devices of the electronic device 5. The memory 502 is used to store computer programs and other programs and data required by the electronic device. The memory 502 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.
In the embodiments provided in the present disclosure, it should be understood that the disclosed apparatus/electronic device and method may be implemented in other manners. For example, the apparatus/electronic device embodiments described above are merely illustrative, e.g., the division of modules or elements is merely a logical functional division, and there may be additional divisions of actual implementations, multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present disclosure may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present disclosure may implement all or part of the flow of the method of the above-described embodiments, or may be implemented by a computer program to instruct related hardware, and the computer program may be stored in a computer readable storage medium, where the computer program, when executed by a processor, may implement the steps of the method embodiments described above. The computer program may comprise computer program code, which may be in source code form, object code form, executable file or in some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the content of the computer readable medium can be appropriately increased or decreased according to the requirements of the jurisdiction's jurisdiction and the patent practice, for example, in some jurisdictions, the computer readable medium does not include electrical carrier signals and telecommunication signals according to the jurisdiction and the patent practice.
The above embodiments are merely for illustrating the technical solution of the present disclosure, and are not limiting thereof; although the present disclosure has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the disclosure, and are intended to be included in the scope of the present disclosure.
Claims (10)
1. A method for predicting gas load, comprising:
acquiring historical original data in a target area, wherein the historical original data comprises historical actual use data of natural gas and historical management data of the natural gas;
extracting features of the historical original data to obtain data features of the historical original data;
determining appointed influence factor data related to the data characteristics of the historical original data according to the data characteristics of the historical original data;
comparing the appointed influence factor data with the historical actual influence factor data to obtain variation data of the influence factor data;
Training and predicting variable data of sample data and influence factor data by using a gas load prediction model to determine a first predicted value of the gas load, wherein the gas load prediction model is a neural network model based on a knowledge distillation frame;
collecting pipeline pressure data in the target area, calling a pipeline storage data prediction model to train the pipeline pressure data, and determining a pipeline storage gas prediction value;
and determining a gas load predicted value according to the first predicted value and the pipe stored gas predicted value.
2. The method of claim 1, wherein the feature extraction is performed on the historical raw data to obtain the data feature of the historical raw data, and specifically includes:
filling the missing value of the historical original data, and detecting the abnormal value of the filled actual gas data and the filled historical management data in a specified mode;
according to the detection result, carrying out abnormal value replacement on the filled history actual gas data and the filled history management data to obtain preprocessed history original data;
extracting a first data feature group in the preprocessed historical original data according to a preset feature extraction algorithm;
Performing cluster analysis on the preprocessed historical original data, and dividing the preprocessed historical original data into a plurality of data groups; performing feature analysis on the data in each data group to determine common features in the groups, and performing feature analysis on the plurality of data groups to determine inter-group difference features;
determining a second set of data features based on the intra-set common features and the inter-set differential features;
and determining the data characteristics of the historical original data according to the first data characteristic group and the second data characteristic group.
3. The method according to claim 1, wherein determining the specified influencing factor data related to the data characteristics of the historical original data according to the data characteristics of the historical original data specifically comprises:
acquiring influence factor data corresponding to the historical original data in a target area;
performing dimensionless processing on the historical original data and the influence factor data respectively, taking the processed historical original data as a comparison sequence, and taking the processed influence factor data as a comparison sequence;
calculating a correlation coefficient of the comparison number sequence and the comparison number sequence, and determining the correlation of the influence factor data and the historical original data according to the correlation coefficient;
And sequencing the association degrees according to a preset rule, and taking the influence factor data with the association degrees higher than a preset threshold value as the appointed influence factor data.
4. The method of claim 1, wherein determining the first predicted value of the air load using the variance data of the training predicted sample data and the influencing factor data using the air load prediction model comprises:
collecting a data set of historical gas data and influence factor data;
invoking a pre-constructed knowledge distillation teacher model to train the data in the data set of the influence factor data, and determining the historical gas data as output soft targets and/or output prediction gas data;
modifying a loss function of the teacher model according to the output soft target, and training the teacher model;
inputting the data in the data set of the influence factor data into a pre-constructed knowledge distillation student model, taking the prediction gas data as a target value of the student model, and training the student model to obtain a gas load prediction model meeting the requirements.
5. The method according to claim 1, wherein determining the gas load predicted value according to the first predicted value and the pipe gas predicted value comprises:
Calculating the ratio of the pipe stored gas predicted value to the first predicted value to obtain a first ratio;
calculating the ratio of the historical pipe storage data to the historical actual gas data to obtain a second ratio;
and if the difference value of the first ratio and the second ratio is larger than a preset threshold value, carrying out weighted calculation on the first predicted value and the pipe stored gas predicted value to obtain the gas load predicted value.
6. The method of claim 1, wherein the acquiring the pipeline pressure data within the target area, retrieving a pipeline storage data prediction model training the pipeline pressure data, and determining a pipeline storage gas prediction value comprises:
constructing a pipe memory data set according to the historical pipeline pressure value and the historical pipe memory data;
and inputting the historical pipeline pressure values in the management data set into a pre-constructed neural network model, taking the historical management data as an output target of the neural network model, adjusting model parameters, and training the model so as to determine a management data prediction model meeting the requirements.
7. The method of any one of claims 1 to 6, wherein the gas load is used to represent natural gas usage in a target area.
8. A gas load prediction apparatus, the apparatus comprising:
the system comprises a data acquisition module, a storage module and a storage module, wherein the data acquisition module is configured to acquire historical original data in a target area, and the historical original data comprises historical actual use data of natural gas and historical management data of the natural gas;
the feature extraction module is configured to perform feature extraction on the historical original data to obtain data features of the historical original data;
the characteristic determining module is configured to determine specified influence factor data related to the data characteristics of the historical original data according to the data characteristics of the historical original data;
the data comparison module is configured to compare the appointed influence factor data with the historical actual influence factor data so as to obtain variation data of the influence factor data;
the determining module is configured to train and predict variable data of sample data and influence factor data by using a gas load prediction model to determine a first predicted value of the gas load, wherein the gas load prediction model is a neural network model based on a knowledge distillation frame; collecting pipeline pressure data in the target area, calling a pipeline storage data prediction model to train the pipeline pressure data, and determining a pipeline storage gas prediction value; and determining a gas load predicted value according to the first predicted value and the pipe stored gas predicted value.
9. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111530673.4A CN116341152A (en) | 2021-12-14 | 2021-12-14 | Gas load prediction method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111530673.4A CN116341152A (en) | 2021-12-14 | 2021-12-14 | Gas load prediction method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116341152A true CN116341152A (en) | 2023-06-27 |
Family
ID=86882721
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111530673.4A Pending CN116341152A (en) | 2021-12-14 | 2021-12-14 | Gas load prediction method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116341152A (en) |
-
2021
- 2021-12-14 CN CN202111530673.4A patent/CN116341152A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109508360B (en) | Geographical multivariate stream data space-time autocorrelation analysis method based on cellular automaton | |
| Thai-Nghe et al. | Deep learning approach for forecasting water quality in IoT systems | |
| CN106097043B (en) | The processing method and server of a kind of credit data | |
| CN101963983A (en) | Data mining method of rough set and optimization neural network | |
| Feng et al. | [Retracted] Design and Simulation of Human Resource Allocation Model Based on Double‐Cycle Neural Network | |
| WO2017071369A1 (en) | Method and device for predicting user unsubscription | |
| CN112580902B (en) | Object data processing method and device, computer equipment and storage medium | |
| Awad et al. | Prediction of water demand using artificial neural networks models and statistical model | |
| CN113222560A (en) | Enterprise service system based on AI consultation and construction method thereof | |
| CN111754370B (en) | Artificial intelligence-based online education course management method and system | |
| Praynlin et al. | Performance analysis of software effort estimation models using neural networks | |
| CN115249081A (en) | Object type prediction method and device, computer equipment and storage medium | |
| CN115049397A (en) | Method and device for identifying risk account in social network | |
| CN116578858A (en) | Air compressor fault prediction and health degree evaluation method and system based on graphic neural network | |
| CN114154415A (en) | Equipment life prediction method and device | |
| CN116341152A (en) | Gas load prediction method and device, electronic equipment and storage medium | |
| CN114970357A (en) | Energy-saving effect evaluation method, system, device and storage medium | |
| CN114118275A (en) | Joint learning training method and device | |
| CN116050557A (en) | Power load prediction method, device, computer equipment and medium | |
| CN114118543A (en) | Flue gas oxygen content load prediction method and device based on joint learning | |
| CN113487087A (en) | Method and device for predicting service life of equipment, computer equipment and computer-readable storage medium | |
| CN109447498B (en) | Rail transit system cost association multi-domain influence element big data driving analysis method | |
| Zha et al. | Container throughput time series forecasting using a hybrid approach | |
| Shousong et al. | Notice of Violation of IEEE Publication Principles: Research on Urban Land Price Assessment Based on Artificial Neural Network Model | |
| CN114118540A (en) | Flue gas oxygen content load prediction method and device based on sample migration |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |