CN116011647A - 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
- CN116011647A CN116011647A CN202310011399.2A CN202310011399A CN116011647A CN 116011647 A CN116011647 A CN 116011647A CN 202310011399 A CN202310011399 A CN 202310011399A CN 116011647 A CN116011647 A CN 116011647A
- Authority
- CN
- China
- Prior art keywords
- gas load
- load data
- data
- target
- prediction
- 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
Images
Classifications
-
- 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
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application provides a gas load prediction method and device, electronic equipment and a storage medium, and belongs to the technical field of artificial intelligence. The method comprises the following steps: acquiring initial historical gas load data; denoising the initial historical gas load data to obtain target historical gas load data; performing phase space reconstruction processing on the target historical gas load data to obtain target reconstructed gas load data; and carrying out gas load prediction on the target reconstructed gas load data through a preset target prediction model to obtain target load prediction data. According to the embodiment of the application, the accuracy of the gas load can be improved.
Description
Technical Field
The present disclosure relates to the field of artificial intelligence technologies, and in particular, to a method and an apparatus for predicting a gas load, an electronic device, and a storage medium.
Background
At present, short-term gas load prediction is carried out, so that a gas company can flexibly schedule gas according to a prediction result and reasonably plan gas use. In the related art, the gas load prediction method includes a multivariate time series analysis method and a single time series analysis method. The multivariate time series analysis method uses key information related to gas load such as seasons, climates, humiture and the like as input data of a prediction model, but is not capable of acquiring sufficient key information due to the influence of regional conditions, technical limitations and the like in practical application. In addition, the gas load has the characteristics of non-stability, fluctuation and the like, so that the accuracy of a single time series analysis method is influenced. Therefore, how to improve the accuracy of gas load prediction is a technical problem to be solved.
Disclosure of Invention
The embodiment of the application mainly aims to provide a gas load prediction method and device, electronic equipment and storage medium, and aims to improve the accuracy of gas load prediction.
To achieve the above object, a first aspect of an embodiment of the present application proposes a gas load prediction method, including:
acquiring initial historical gas load data;
denoising the initial historical gas load data to obtain target historical gas load data;
performing phase space reconstruction processing on the target historical gas load data to obtain target reconstructed gas load data;
and carrying out gas load prediction on the target reconstructed gas load data through a preset target prediction model to obtain target load prediction data.
In some embodiments, before the gas load prediction is performed on the target reconstructed gas load data through a preset prediction model to obtain target load prediction data, the method further includes training the target prediction model, and specifically includes:
acquiring original historical gas load data;
denoising the original historical gas load data to obtain sample historical gas load data;
Carrying out phase space reconstruction processing on the sample historical gas load data to obtain sample reconstruction gas load data;
obtaining sample gas data and sample prediction data according to the sample reconstruction gas load data;
carrying out gas load prediction on the sample gas data through a preset initial prediction model to obtain sample load prediction data;
and carrying out parameter adjustment on the initial prediction model according to the sample prediction data and the sample load prediction data to obtain the target prediction model.
In some embodiments, the denoising processing is performed on the original historical gas load data to obtain sample historical gas load data, including:
performing modal decomposition processing on the original historical gas load data to obtain initial decomposed gas load data;
acquiring the original center frequency of the initial decomposed gas load data;
updating the initial decomposed gas load data according to preset constraint data and the original center frequency to obtain target decomposed gas load data;
performing correlation calculation on the target decomposed gas load data and the original historical gas load data to obtain a correlation coefficient;
And obtaining the sample historical gas load data according to the correlation coefficient and the target decomposed gas load data.
In some embodiments, the performing phase space reconstruction processing on the sample historical gas load data to obtain sample reconstructed gas load data includes:
performing mutual information calculation on the sample historical gas load data to obtain a mutual information value;
determining a target delay time according to the mutual information value;
determining the data quantity of the neighbor data according to the target delay time and the sample historical gas load data to obtain a target quantity;
determining a target space dimension according to the target number and a preset occupation ratio;
and carrying out phase space reconstruction processing on the sample historical gas load data according to the target space dimension and the target delay time to obtain the sample reconstruction gas load data.
In some embodiments, the denoising processing is performed on the initial historical gas load data to obtain target historical gas load data, including:
and carrying out Gaussian filtering processing on the initial historical gas load data to obtain the target historical gas load data.
In some embodiments, the target prediction model comprises a blurring layer, a rule layer, a normalization layer, a defuzzification layer, an output layer;
The gas load prediction is performed on the target reconstructed gas load data through a preset target prediction model to obtain target load prediction data, and the method comprises the following steps:
fuzzification processing is carried out on the target reconstructed gas load data through the fuzzification layer, so that gas load membership is obtained;
carrying out fuzzy rule calculation on the gas load membership degree through the rule layer to obtain rule applicability degree;
normalizing the rule applicability through the normalization layer to obtain applicability probability;
deblurring the applicable probability and the target reconstructed gas load data through the deblurring layer to obtain key reconstructed gas load data;
and mapping and outputting the key reconstructed gas load data through the output layer to obtain the target load prediction data.
To achieve the above object, a second aspect of the embodiments of the present application proposes a gas load prediction apparatus, the apparatus including:
the data acquisition module is used for acquiring initial historical gas load data;
the denoising module is used for denoising the initial historical gas load data to obtain target historical gas load data;
The phase space reconstruction module is used for carrying out phase space reconstruction processing on the target historical gas load data to obtain target reconstructed gas load data;
and the fuel gas load prediction module is used for carrying out fuel gas load prediction on the target reconstructed fuel gas load data through a preset target prediction model to obtain target load prediction data.
To achieve the above object, a third aspect of the embodiments of the present application proposes an electronic device, which includes a memory and a processor, the memory storing a computer program, the processor implementing the method according to the first aspect when executing the computer program.
To achieve the above object, a fourth aspect of the embodiments of the present application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method of the first aspect.
According to the gas load prediction method and device, the electronic equipment and the storage medium, the target historical gas load data are obtained through denoising the initial historical gas load data. And performing phase space reconstruction processing on the target historical gas load data to obtain target reconstructed gas load data, thereby solving the problem that the accuracy of a single time sequence analysis method is affected due to the characteristics of non-stationarity, fluctuation and the like of the gas load data in the related technology. Therefore, when the gas load prediction is performed on the target reconstructed gas load data through the preset target prediction model, the accuracy of the gas load prediction can be improved.
Drawings
FIG. 1 is a flow chart of a fuel gas load prediction method according to an embodiment of the present application;
FIG. 2 is another flow chart of a gas load prediction method of an embodiment of the present application;
FIG. 3 is another flow chart of a gas load prediction method of an embodiment of the present application;
FIG. 4 is another flow chart of a gas load prediction method of an embodiment of the present application;
FIG. 5 is another flow chart of a gas load prediction method of an embodiment of the present application;
FIG. 6 is a schematic view of the structure of a gas load device according to an embodiment of the present application;
fig. 7 is a schematic hardware structure of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
It should be noted that although functional block division is performed in a device diagram and a logic sequence is shown in a flowchart, in some cases, the steps shown or described may be performed in a different order than the block division in the device, or in the flowchart. The terms first, second and the like in the description and in the claims and in the above-described figures, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the present application only and is not intended to be limiting of the present application.
First, several nouns referred to in this application are parsed:
artificial intelligence (artificial intelligence, AI): is a new technical science for researching and developing theories, methods, technologies and application systems for simulating, extending and expanding the intelligence of people; artificial intelligence is a branch of computer science that attempts to understand the nature of intelligence and to produce a new intelligent machine that can react in a manner similar to human intelligence, research in this field including robotics, language recognition, image recognition, natural language processing, and expert systems. Artificial intelligence can simulate the information process of consciousness and thinking of people. Artificial intelligence is also a theory, method, technique, and application system that utilizes a digital computer or digital computer-controlled machine to simulate, extend, and expand human intelligence, sense the environment, acquire knowledge, and use knowledge to obtain optimal results.
Phase Space Reconstruction (PSR): the basic idea of phase space reconstruction is that the evolution of any one element in the system is determined by the other elements with which it interacts, so that the information of these relevant elements is implicit in the development of any element. It follows that the purpose of the phase space reconstruction is to mine more information of the whole time sequence, find another system equivalent to the original system in a sense, to obtain hidden information of the original system from the other system.
Variational modal decomposition (Variational mode decomposition, VMD): is a method of adaptive, completely non-recursive modal variation and signal processing. According to the method, the frequency center and the bandwidth of each component are determined by iteratively searching the optimal solution of the variation model in the process of obtaining the decomposition components, so that signal frequency domain subdivision and effective separation of each component can be adaptively realized. The VMD can decompose a plurality of sub-signals constituting one noise-containing signal, and then reconstruct the original signal using the sub-signals, thereby realizing a noise reduction function.
The fuzzy inference system (Adaptive-Network-Based Fuzzy Inference Sysrem, ANFIS) is composed of five functional modules: first, a rule base containing a number of fuzzy if-then rules; second, define a database of membership functions for fuzzy sets using fuzzy if-then rules; third, a decision unit on rules that performs reasoning operations; fourth, converting the explicit input into a fuzzy interface that matches the degree of language value; fifth, the fuzzy result from reasoning is converted into a clearly output deblurring interface. The ANFIS realizes three basic processes of fuzzification, fuzzy reasoning and anti-fuzzification of the fuzzy control by using a neural network structure, and automatically extracts rules from input and output sample data by using a learning mechanism of the neural network to form the self-adaptive neural fuzzy controller.
At present, short-term gas load prediction is carried out, so that a gas company can flexibly schedule gas according to a prediction result and reasonably plan gas use. In the related art, the gas load prediction method includes a multivariate time series analysis method and a single time series analysis method. The multivariate time series analysis method uses key information related to gas load such as seasons, climates, humiture and the like as input data of a prediction model, but is not capable of acquiring sufficient key information due to the influence of regional conditions, technical limitations and the like in practical application. In addition, the gas load has the characteristics of non-stability, fluctuation and the like, so that the accuracy of a single time series analysis method is influenced. Therefore, how to improve the accuracy of gas load prediction is a technical problem to be solved.
Based on the above, the embodiment of the application provides a gas load prediction method and device, electronic equipment and storage medium, and aims to improve the accuracy of gas load prediction.
The method and device for predicting the gas load, the electronic device and the storage medium provided by the embodiment of the application are specifically described through the following embodiments, and the method for predicting the gas load in the embodiment of the application is described first.
The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.
Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.
The embodiment of the application provides a gas load prediction method, and relates to the technical field of artificial intelligence. The fuel gas load prediction method provided by the embodiment of the application can be applied to a terminal, a server side and software running in the terminal or the server side. In some embodiments, the terminal may be a smart phone, tablet, notebook, desktop, etc.; the server side can be configured as an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, and a cloud server for providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs, basic cloud computing services such as big data and artificial intelligent platforms and the like; the software may be an application or the like for realizing the gas load prediction method, but is not limited to the above form.
The subject application is operational with numerous general purpose or special purpose computer system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like. The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
Fig. 1 is an optional flowchart of a gas load prediction method provided in an embodiment of the present application, where the method in fig. 1 may include, but is not limited to, steps S101 to S104.
S101, acquiring initial historical gas load data;
step S102, denoising the initial historical gas load data to obtain target historical gas load data;
step S103, performing phase space reconstruction processing on the target historical gas load data to obtain target reconstructed gas load data;
and step S104, carrying out gas load prediction on the target reconstructed gas load data through a preset target prediction model to obtain target load prediction data.
In the steps S101 to S104 illustrated in the embodiment of the present application, the target historical gas load data is obtained by denoising the initial historical gas load data. And performing phase space reconstruction processing on the target historical gas load data to obtain target reconstructed gas load data, thereby solving the problem that the accuracy of a single time sequence analysis method is affected due to the characteristics of non-stationarity, fluctuation and the like of the gas load data in the related technology. Therefore, when the gas load prediction is performed on the target reconstructed gas load data through the preset target prediction model, the accuracy of the gas load prediction can be improved.
In step S101 of some embodiments, daily gas load data of the region to be measured in a historical period of time is obtained through a related application programming interface (Application Programming Interface, API) and other modes, so as to obtain initial gas load data. It will be appreciated that the predicted target load prediction data is used to characterize the condition of the gas load in the region under test in a future period of time, and therefore, the historical period of time and the future period of time should be two adjacent periods of time, or two periods of time with a time interval within a preset threshold. For example, in order to predict the gas load condition of the region to be measured 2022 for 3 to 4 months, initial historical gas load data of the region to be measured for 2022 for 1 to 2 months should be obtained. Alternatively, in order to predict the gas load condition of the region 2022 under test for 11 months to 12 months, since the gas load condition is greatly different from the gas load condition in the other three seasons because the region 2022 under test for 11 months to 12 months is winter, the gas load data of the region 2021 under test for 11 months to 12 months may be selected as the initial historical gas load data. The preset threshold range is one year at this time. In addition, the time length of the historical period of time may be the same as or different from the time length of the future period of time, and the embodiment of the present application is not particularly limited. However, in order to improve the accuracy of the gas load prediction, it should be ensured that the amount of data input to the target prediction model is sufficient, and at this time, the time length of the historical period of time may be set to be greater than or equal to the time length of the future period of time.
In step S102 of some embodiments, since abnormal gas load data may exist in the initial historical gas load data, in order to improve accuracy of subsequent gas load prediction, denoising processing needs to be performed on the initial historical gas load data, that is, abnormal gas load data is filtered, so as to obtain target historical gas load data. It can be appreciated that any mode of mean filtering, median filtering, gaussian filtering, VMD and the like can be used to denoise the initial historical gas load data, and the embodiment of the application is not particularly limited.
In some embodiments, the initial gas load data is denoised using gaussian filtering to enable smoother target historical gas load data.
In step S103 of some embodiments, phase space reconstruction processing is performed on the target historical gas load data, so as to perform multidimensional expansion on the target historical gas load data of a single sequence, and obtain target reconstructed gas load data with chaos characteristics, so that more hidden information in the target historical gas load data can be obtained through excavation. Wherein the hidden information includes, but is not limited to, potential laws of gas load data changes, etc.
Referring to fig. 2, in some embodiments, before step S104, the gas load prediction method provided in the embodiments of the present application further includes training a target prediction model, specifically including, but not limited to, steps S201 to S206.
Step S201, acquiring original historical gas load data;
step S202, denoising the original historical gas load data to obtain sample historical gas load data;
step S203, carrying out phase space reconstruction processing on the sample historical gas load data to obtain sample reconstructed gas load data;
step S204, sample gas data and sample prediction data are obtained according to the sample reconstruction gas load data;
step S205, carrying out gas load prediction on sample gas data through a preset initial prediction model to obtain sample load prediction data;
and S206, carrying out parameter adjustment on the initial prediction model according to the sample prediction data and the sample load prediction data to obtain a target prediction model.
In step S201 of some embodiments, gas load data of a sample region in a sample time is acquired to obtain original historical gas load data X1 (t) = (X) 1 ,x 2 ,...,x n ). It will be appreciated that in order to improve the accuracy of the gas load prediction in the region to be predicted, the sample region and the region to be predicted should be the same region. Second, since the tag data for loss calculation is acquired from the original historical gas load data at the time of the subsequent model training, the time span of the sample time should be long enough, for example, the sample time is 2017, 1, to 2021, 12, 31.
In step S202 of some embodiments, since abnormal gas load data may exist in the original historical gas load data, in order to improve accuracy of subsequent model training, denoising processing needs to be performed on the original historical gas load data, that is, abnormal gas load data is filtered out, so as to obtain sample historical gas load data X2 (t). It can be appreciated that any mode of mean filtering, median filtering, gaussian filtering, VMD and the like can be used to denoise the original historical gas load data, and the embodiment of the application is not particularly limited.
Referring to fig. 3, in some embodiments, step S202 includes, but is not limited to including, step S301 to step S305.
Step S301, performing modal decomposition processing on original historical gas load data to obtain initial decomposed gas load data;
step S302, obtaining the original center frequency of the initial decomposed gas load data;
step S303, updating the initial decomposed gas load data according to preset constraint data and original center frequency to obtain target decomposed gas load data;
step S304, performing correlation calculation on target decomposed gas load data and original historical gas load data to obtain a correlation coefficient;
And step S305, obtaining sample historical gas load data according to the correlation coefficient and the target decomposed gas load data.
It should be noted that, the gas load data has non-stationarity and random fluctuation due to the influence of weather, date and the like, so the embodiment of the application performs denoising and smoothing treatment on the original gas load by the VMD method. The VMD method extracts the characteristic information of the non-stationary signal by adopting a non-recursive signal processing mode so as to solve the problems of randomness and nonlinearity of the gas load data.
In step S301 of some embodiments, the original historical gas load data X1 (t) is decomposed to obtain K modal components with specific bandwidths, and initial decomposed gas load data u is obtained k ＝{u 1 ，u 2 ，…，u K }。
It is understood that in the decomposition process, constraint variation conditions shown in the following formulas (1) and (2) are satisfied:
wherein, the liquid crystal display device comprises a liquid crystal display device,
the time bias is represented, and delta (t) is a unit pulse function.
In step S302 of some embodiments, the center frequencies of the modal components are obtained to obtain the original center frequency ω k ＝{ω 1 ，ω 2 ，…，ω K }。
In step S303 of some embodiments, in order to solve the above-described constraint optimization problem, the constraint variation problem is converted into a non-constraint variation problem according to preset constraint data (including a quadratic penalty term α and a lagrangian λ), as shown in the following formula (3).
Specifically, n=0, k=1 is initialized, and iterative updating is performed according to n=n+1, k=k+1, the following formulas (4) to (6), and the alternate direction multiplier algorithm:
where γ is the noise tolerance of the signal. And repeating iterative updating until the convergence condition is met or the maximum iterative times are reached. The convergence condition is shown in the following formula (7), and both γ and ε are constants and larger than zero.
According to the iterative updating, obtaining the optimal solution of the unconstrained variation problem, namely obtaining target decomposed gas load data u k ′。
In step S304 of some embodiments, the targets are divided intoGas load data u k And carrying out correlation calculation on each modal component in' and the original historical gas load data X1 (t), and obtaining the correlation coefficient of each modal component. It is to be appreciated that the pearson (Pearson Correlation Coefficient) correlation coefficient or other correlation coefficient may be used for correlation calculation, and embodiments of the present application are not particularly limited.
In step S305 of some embodiments, the gas load data u is decomposed for the target according to the correlation coefficient of each modal component k Screening to obtain modal components with correlation coefficient greater than preset threshold, i.e. target decomposed gas load data u k A modal component with consistent main trend in' the model. Will decompose the gas load data u from the target k And reconstructing the mode components screened in the' to obtain sample historical gas load data X2 (t).
In step S203 of some embodiments, phase space reconstruction processing is performed on the sample historical gas load data, so as to perform multidimensional expansion on the sample historical gas load data of a single sequence, so as to obtain sample reconstructed gas load data with chaos characteristics, thereby being capable of mining more hidden information in the sample historical gas load data. Wherein the hidden information includes, but is not limited to, potential laws of gas load data changes, etc.
Specifically, as shown in the following equation (8), the phase space reconstruction processing is performed by embedding the space dimension m and the delay time τ, and the sample reconstruction gas load data N is obtained.
For example, when the embedding space dimension m=3 and the delay time τ=2, the sample reconstruction gas load data N is represented by the following expression (9).
Referring to fig. 4, in some embodiments, step S203 includes, but is not limited to, including steps S401 through S405.
S401, performing mutual information calculation on sample historical gas load data to obtain a mutual information value;
Step S402, determining target delay time according to the mutual information value;
step S403, determining the data quantity of the neighbor data according to the target delay time and the sample historical gas load data to obtain the target quantity;
step S404, determining the dimension of the target space according to the target number and the preset occupation ratio;
and step S405, carrying out phase space reconstruction processing on the sample historical gas load data according to the target space dimension and the target delay time to obtain sample reconstruction gas load data.
It should be noted that, in the embodiment of the present application, the sample historical gas load data is processed by a phase space reconstruction technique, so as to deeply mine the intrinsic structural characteristics and potential rules of the sample historical gas load data in the chaotic time sequence. It will be appreciated that the main idea of phase space reconstruction is to map the sample historical gas load data X2 (t) to a high dimensional space so that the mapped data more closely matches the actual gas load variations.
In steps S401 to S402 of some embodiments, mutual information calculation shown in the following formula (10) is performed on the sample historical gas load data X2 (t) to measure the sample historical gas load data X2 (t) to obtain a mutual information value. Specifically, as shown in the following formula (10), the mutual information value I (τ') is calculated.
Wherein, it is assumed that the sample historical gas load data X2 (t) = { X 1 ，x 2 ，...，x N P (x) t ) Representing gas load data x t Corresponding value is { x } 1 ,x 2 ,...x N Probability of occurrence in }; p (x) t+τ′ ) Representing gas load data x t+τ′ Corresponding toThe numerical value is { x 1+τ′ ,x 2+τ′ ,...,x N+τ′ Probability of occurrence in }; p (x) t ,x t+τ ) Representing P (x) t ) And P (x) t+τ′ ) The corresponding values are in the sequence { x }, respectively 1 ,x 2 ,...x N Sum { x } 1+τ′ ,x 2+τ′ ,...,x N+τ′ Joint probabilities of simultaneous occurrence in }. When I (τ') is a minimum value, it indicates that x at this time t And x t+τ′ With the greatest possible uncorrelation. Since the chaotic system has a nonlinear characteristic, i.e., has an uncorrelation, a first minimum value I (τ ') obtained from a preset τ' is taken as an optimal delay time τ, i.e., a target delay time, when the phase space is reconstructed.
In steps S403 to S404 of some embodiments, the best embedding space dimension m at the time of phase space reconstruction, i.e., the target space dimension, is determined using pseudo-neighbor method. Specifically, for any phase point (i.e., vector) in m-dimensional space
All have nearest neighbors +>
The phase point and the nearest neighbor point +.>
There is a distance +.>
Wherein the phase point and the nearest neighbor point when the dimension of the embedded space is increased to m+1
The distance of (2) is changed to be a distance +. >
It will be appreciated that when distance
Distance->
When the difference value is larger than a preset threshold value, the point is changed into a pseudo adjacent point when two non-adjacent points in the high-dimensional space are projected to the low-dimensional space. Namely when the distance is according to the following formula (13)
And distance->
When the ratio is calculated, if the obtained ratio S m < preset ratio S 0 Description of->
Is F t Is a pseudo-nearest neighbor of (c). According to the method, the number of samples of the pseudo nearest neighbors in the sample historical gas load data X2 (t) under the current embedded space dimension m is determined. And determining the current sample occupation value of the pseudo nearest neighbor according to the number of the samples.
If the current sample occupation ratio is smaller than the preset occupation ratio, the fact that the internal structure and the characteristics in the sample historical gas load data X2 (t) can be displayed completely under the current embedded space dimension m is indicated, and therefore the current embedded space dimension m is taken as the target space dimension. If the obtained ratio S m Not less than a preset ratio S 0 The current embedded spatial dimension m is updated. And (3) recalculating new sample numbers of the pseudo nearest neighbors in the sample historical gas load data X2 (t) according to the updated embedded space dimension, and obtaining new sample occupation ratios according to the new sample numbers. It may be appreciated that in some embodiments, when the current sample occupation ratio is equal to the new sample occupation ratio, the embedded space dimension corresponding to the current sample occupation ratio may also be set as the target space dimension, which is not specifically limited in this embodiment of the present application.
In step S405 of some embodiments, phase space reconstruction processing is performed on the sample historical gas load data X2 (t) according to the target space dimension and the target delay time, so as to obtain sample reconstructed gas load data N. For example, when it is determined that the target space dimension is equal to 3 and the delay time is equal to 2, the sample reconstructed gas load data N shown in the above formula (9) is obtained.
In step S204 of some embodiments, the sample reconstructed gas load data is classified to construct sample gas data and sample prediction data. It can be understood that the sample gas data is predicted to obtain sample prediction data according to the sample gas data before the sample prediction data, that is, the sample prediction data is used as tag data of the sample gas data. For example, the sample gas load data N according to the sample reconstruction shown in the formula (9) may be constructed to obtain the sample gas data J shown in the following formula (14) and the sample prediction data L shown in the following formula (15).
It will be appreciated that the gas load data x 6 Is the number of tags corresponding to the gas load data { x1, x3, x5}According to the above.
In step S205 of some embodiments, an initial prediction model with an ANFIS as a model structure is constructed in advance, and sample gas data J is used as input data of the initial prediction model to obtain prediction data of the initial prediction model, that is, sample load prediction data.
In step S206 of some embodiments, loss calculation is performed on the sample load prediction data and the sample prediction data L according to a preset loss function, and parameter adjustment is performed on the initial prediction model according to the calculated loss value, so as to improve the prediction capability of the initial prediction model, and obtain the target prediction model.
In step S104 of some embodiments, target load prediction data for characterizing the gas load situation in a future period of time is obtained using the target reconstructed gas load data as input data to a target prediction model. It is understood that the target prediction model is a model that is pre-trained based on the ANFIS model structure.
Referring to fig. 5, in some embodiments, the target prediction model includes a blurring layer, a rule layer, a normalization layer, a defuzzification layer, and an output layer. Step S104 includes, but is not limited to, steps S501 to S505.
Step S501, carrying out fuzzification processing on target reconstructed gas load data through a fuzzification layer to obtain gas load membership;
step S502, carrying out fuzzy rule calculation on the gas load membership degree through a rule layer to obtain rule applicability degree;
step S503, carrying out normalization processing on rule applicability through a normalization layer to obtain applicability probability;
Step S504, performing deblurring treatment on the applicable probability and the target reconstructed gas load data through a deblurring layer to obtain key reconstructed gas load data;
and step S505, mapping and outputting the key reconstructed gas load data through an output layer to obtain target load prediction data.
In step S501 of some embodiments, it is assumed that the target reconstructed gas load data P is represented by the following formula (16), and the target reconstructed gas load data is used as input data of a blurring layer, so that blurring processing is performed on the target reconstructed gas load data through the blurring layer, and a gas load membership degree is obtained.
For example, for input data
And (3) after the blurring processing is carried out by the blurring layer, obtaining output data of the blurring layer as shown in a formula (17), namely the gas load membership degree. />
Wherein mu Ai (x 1 ') is corresponding to the input data x 1 ' gas load membership; mu (mu) Bj (x′ 3 ) To correspond to the input data x 3 ' gas load membership; mu (mu) Ck (x′ 5 ) To correspond to the input data x 5 ' gas load membership. As can be appreciated, μ Ai (x 1 ′)、μ Bj (x′ 3 )、μ Ck (x′ 5 ) The specific calculation formulas are shown in formulas (18) to (20) and are calculated according to a preset bell membership function.
Wherein a is z 、b z 、c z (z＝A i ,B j ,C k ) Are all advance parameters.
In step S502 of some embodiments, the rule layer calculates the applicability of each fuzzy if-then rule in the preset rule base to obtain the rule applicability O 2,u I.e. the trigger strength of each rule. Specifically, the rule fitness O is calculated with reference to the following formula (21) 2,u 。
O 2 ， u ＝W u ＝μ Ai (x′ 1 )·μ Bj (x′ 3 )·μC k (x′ 5 ) U=1, 2,3. Once again, the combination (21)
In step S503 of some embodiments, the rule fitness of each rule is normalized by the normalization layer to obtain an applicable probability, so as to determine the triggering proportion of the corresponding rule in the whole rule base, that is, the probability of using the rule in the whole prediction process. Specifically, the probability of applicability O is calculated according to the following formula (22) 3,u 。
In step S504 of some embodiments, the key reconstructed gas load data is obtained by calculating, by the defuzzification layer, the prediction results corresponding to the predictions using the respective rules. Specifically, the key reconstruction gas load data O is calculated according to the following formula (23) 4,u 。
Wherein p is u 、q u 、r u 、s u Is a preset conclusion parameter; f (f) u Is a linear combination of conclusion parameters used to represent fuzzy rules.
In step S505 of some embodiments, target reconstructed gas load data is obtained through the output layer
I.e. the target load prediction data. Specifically, the target load prediction data O is calculated according to the following formula (24) 5 。
According to the gas load prediction method, the target historical gas load data is obtained through denoising processing of the initial historical gas load data. And performing phase space reconstruction processing on the target historical gas load data to obtain target reconstructed gas load data, thereby solving the problem that the accuracy of a single time sequence analysis method is affected due to the characteristics of non-stationarity, fluctuation and the like of the gas load data in the related technology. Therefore, when the gas load prediction is performed on the target reconstructed gas load data through the preset target prediction model, the accuracy of the gas load prediction can be improved.
Referring to fig. 6, an embodiment of the present application further provides a gas load prediction apparatus, which may implement the gas load prediction method, where the apparatus includes:
the data acquisition module 601 is configured to acquire initial historical gas load data;
the denoising module 602 is configured to denoise the initial historical gas load data to obtain target historical gas load data;
the phase space reconstruction module 603 is configured to perform phase space reconstruction processing on the target historical gas load data to obtain target reconstructed gas load data;
The gas load prediction module 604 is configured to perform gas load prediction on the target reconstructed gas load data through a preset target prediction model, so as to obtain target load prediction data.
The specific embodiment of the gas load prediction device is basically the same as the specific embodiment of the gas load prediction method, and will not be described herein.
The embodiment of the application also provides electronic equipment, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the gas load prediction method when executing the computer program. The electronic equipment can be any intelligent terminal including a tablet personal computer, a vehicle-mounted computer and the like.
Referring to fig. 7, fig. 7 illustrates a hardware structure of an electronic device according to another embodiment, the electronic device includes:
the processor 701 may be implemented by a general-purpose CPU (central processing unit), a microprocessor, an application-specific integrated circuit (ApplicationSpecificIntegratedCircuit, ASIC), or one or more integrated circuits, etc. for executing related programs to implement the technical solutions provided by the embodiments of the present application;
the memory 702 may be implemented in the form of read-only memory (ReadOnlyMemory, ROM), static storage, dynamic storage, or random access memory (RandomAccessMemory, RAM). The memory 702 may store an operating system and other application programs, and when the technical solutions provided in the embodiments of the present application are implemented by software or firmware, relevant program codes are stored in the memory 702, and the processor 701 invokes the method for predicting gas load to execute the embodiments of the present application;
An input/output interface 703 for implementing information input and output;
the communication interface 704 is configured to implement communication interaction between the device and other devices, and may implement communication in a wired manner (e.g. USB, network cable, etc.), or may implement communication in a wireless manner (e.g. mobile network, WIFI, bluetooth, etc.);
a bus 705 for transferring information between various components of the device (e.g., the processor 701, memory 702, input/output interfaces 703, and communication interfaces 704);
wherein the processor 701, the memory 702, the input/output interface 703 and the communication interface 704 are in communication connection with each other inside the device via a bus 705.
The embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program realizes the fuel gas load prediction method when being executed by a processor.
The memory, as a non-transitory computer readable storage medium, may be used to store non-transitory software programs as well as non-transitory computer executable programs. In addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory remotely located relative to the processor, the remote memory being connectable to the processor through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The embodiments described in the embodiments of the present application are for more clearly describing the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application, and as those skilled in the art can know that, with the evolution of technology and the appearance of new application scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.
It will be appreciated by those skilled in the art that the technical solutions shown in the figures do not constitute limitations of the embodiments of the present application, and may include more or fewer steps than shown, or may combine certain steps, or different steps.
The above described apparatus embodiments are merely illustrative, wherein the units illustrated as separate components may or may not be physically separate, i.e. may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
Those of ordinary skill in the art will appreciate that all or some of the steps of the methods, systems, functional modules/units in the devices disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof.
The terms "first," "second," "third," "fourth," and the like in the description of the present application and in the above-described figures, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that in this application, "at least one" means one or more, and "a plurality" means two or more. "and/or" for describing the association relationship of the association object, the representation may have three relationships, for example, "a and/or B" may represent: only a, only B and both a and B are present, wherein a, B may be singular or plural. The character "/" generally indicates that the context-dependent object is an "or" relationship. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b or c may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the above-described division of units is merely a logical function division, and there may be another division manner in actual implementation, for example, a plurality of units or components may be combined or may be 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 with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described above as separate components may or may not be physically separate, and components 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 application 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 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 technical solution of the present application may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including multiple instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of the various embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing a program.
Preferred embodiments of the present application are described above with reference to the accompanying drawings, and thus do not limit the scope of the claims of the embodiments of the present application. Any modifications, equivalent substitutions and improvements made by those skilled in the art without departing from the scope and spirit of the embodiments of the present application shall fall within the scope of the claims of the embodiments of the present application.
Claims (9)
1. A method of gas load prediction, the method comprising:
acquiring initial historical gas load data;
denoising the initial historical gas load data to obtain target historical gas load data;
performing phase space reconstruction processing on the target historical gas load data to obtain target reconstructed gas load data;
and carrying out gas load prediction on the target reconstructed gas load data through a preset target prediction model to obtain target load prediction data.
2. The method according to claim 1, wherein before the gas load prediction is performed on the target reconstructed gas load data by a preset prediction model to obtain target load prediction data, the method further comprises training the target prediction model, specifically comprising:
acquiring original historical gas load data;
denoising the original historical gas load data to obtain sample historical gas load data;
carrying out phase space reconstruction processing on the sample historical gas load data to obtain sample reconstruction gas load data;
obtaining sample gas data and sample prediction data according to the sample reconstruction gas load data;
Carrying out gas load prediction on the sample gas data through a preset initial prediction model to obtain sample load prediction data;
and carrying out parameter adjustment on the initial prediction model according to the sample prediction data and the sample load prediction data to obtain the target prediction model.
3. The method of claim 2, wherein denoising the raw historical gas load data to obtain sample historical gas load data comprises:
performing modal decomposition processing on the original historical gas load data to obtain initial decomposed gas load data;
acquiring the original center frequency of the initial decomposed gas load data;
updating the initial decomposed gas load data according to preset constraint data and the original center frequency to obtain target decomposed gas load data;
performing correlation calculation on the target decomposed gas load data and the original historical gas load data to obtain a correlation coefficient;
and obtaining the sample historical gas load data according to the correlation coefficient and the target decomposed gas load data.
4. The method of claim 3, wherein performing a phase space reconstruction process on the sample historical gas load data to obtain sample reconstructed gas load data comprises:
Performing mutual information calculation on the sample historical gas load data to obtain a mutual information value;
determining a target delay time according to the mutual information value;
determining the data quantity of the neighbor data according to the target delay time and the sample historical gas load data to obtain a target quantity;
determining a target space dimension according to the target number and a preset occupation ratio;
and carrying out phase space reconstruction processing on the sample historical gas load data according to the target space dimension and the target delay time to obtain the sample reconstruction gas load data.
5. The method according to any one of claims 1 to 4, wherein denoising the initial historical gas load data to obtain target historical gas load data comprises:
and carrying out Gaussian filtering processing on the initial historical gas load data to obtain the target historical gas load data.
6. The method of any one of claims 1 to 4, wherein the target prediction model comprises a blurring layer, a rule layer, a normalization layer, a defuzzification layer, an output layer;
the gas load prediction is performed on the target reconstructed gas load data through a preset target prediction model to obtain target load prediction data, and the method comprises the following steps:
Fuzzification processing is carried out on the target reconstructed gas load data through the fuzzification layer, so that gas load membership is obtained;
carrying out fuzzy rule calculation on the gas load membership degree through the rule layer to obtain rule applicability degree;
normalizing the rule applicability through the normalization layer to obtain applicability probability;
deblurring the applicable probability and the target reconstructed gas load data through the deblurring layer to obtain key reconstructed gas load data;
and mapping and outputting the key reconstructed gas load data through the output layer to obtain the target load prediction data.
7. A gas load prediction apparatus, the apparatus comprising:
the data acquisition module is used for acquiring initial historical gas load data;
the denoising module is used for denoising the initial historical gas load data to obtain target historical gas load data;
the phase space reconstruction module is used for carrying out phase space reconstruction processing on the target historical gas load data to obtain target reconstructed gas load data;
and the fuel gas load prediction module is used for carrying out fuel gas load prediction on the target reconstructed fuel gas load data through a preset target prediction model to obtain target load prediction data.
8. An electronic device comprising a memory storing a computer program and a processor that when executing the computer program implements the gas load prediction method of any one of claims 1 to 6.
9. A computer-readable storage medium storing a computer program, characterized in that the computer program, when executed by a processor, implements the gas load prediction method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310011399.2A CN116011647A (en) | 2023-01-05 | 2023-01-05 | Gas load prediction method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310011399.2A CN116011647A (en) | 2023-01-05 | 2023-01-05 | Gas load prediction method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116011647A true CN116011647A (en) | 2023-04-25 |
Family
ID=86024451
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310011399.2A Pending CN116011647A (en) | 2023-01-05 | 2023-01-05 | Gas load prediction method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116011647A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116257745A (en) * | 2023-05-10 | 2023-06-13 | 杭州致成电子科技有限公司 | Load current extreme abnormality data processing method and device |
| CN116737804A (en) * | 2023-08-15 | 2023-09-12 | 成都秦川物联网科技股份有限公司 | Gas data hierarchical processing method and system based on intelligent gas Internet of things |
-
2023
- 2023-01-05 CN CN202310011399.2A patent/CN116011647A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116257745A (en) * | 2023-05-10 | 2023-06-13 | 杭州致成电子科技有限公司 | Load current extreme abnormality data processing method and device |
| CN116257745B (en) * | 2023-05-10 | 2023-08-15 | 杭州致成电子科技有限公司 | Load current extreme abnormality data processing method and device |
| CN116737804A (en) * | 2023-08-15 | 2023-09-12 | 成都秦川物联网科技股份有限公司 | Gas data hierarchical processing method and system based on intelligent gas Internet of things |
| CN116737804B (en) * | 2023-08-15 | 2023-11-10 | 成都秦川物联网科技股份有限公司 | Gas data hierarchical processing method and system based on intelligent gas Internet of things |
| US12009992B2 (en) | 2023-08-15 | 2024-06-11 | Chengdu Qinchuan Iot Technology Co., Ltd. | Methods and systems for hierarchical processing of gas data based on smart gas internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116011647A (en) | Gas load prediction method and device, electronic equipment and storage medium | |
| Sandryhaila et al. | Big data analysis with signal processing on graphs: Representation and processing of massive data sets with irregular structure | |
| Tax | Human activity prediction in smart home environments with LSTM neural networks | |
| US11340603B2 (en) | Behavior monitoring using convolutional data modeling | |
| Zozor et al. | General entropy-like uncertainty relations in finite dimensions | |
| Shin et al. | Optimal signal multi-resolution by genetic algorithms to support artificial neural networks for exchange-rate forecasting | |
| Njitacke et al. | Nonlinear dynamics of three-neurons-based Hopfield neural networks (HNNs): Remerging Feigenbaum trees, coexisting bifurcations and multiple attractors | |
| Liu et al. | Sensor faults classification for SHM systems using deep learning-based method with Tsfresh features | |
| Hyvärinen | Statistical models of natural images and cortical visual representation | |
| Zhang et al. | LightGBM‐based model for metro passenger volume forecasting | |
| Rao et al. | Comparison of fuzzy and neuro fuzzy image fusion techniques and its applications | |
| Stocchi et al. | Fast wavelet transform assisted predictors of streaming time series | |
| CN111343143B (en) | Data identification method, device and storage medium | |
| Chen et al. | A fuzzy intelligent decision support system for typhoon disaster management | |
| Holmes et al. | Introduction to Bayesian networks | |
| Castro-Camilo et al. | Bayesian space-time gap filling for inference on extreme hot-spots: an application to Red Sea surface temperatures | |
| Liu et al. | Approximation of stochastic processes by T–S fuzzy systems | |
| CN116701875A (en) | Audible noise probability prediction method and system for extra-high voltage alternating current transmission line | |
| RU2600099C1 (en) | Method of neural network forecasting of change of values of function with its complementary wavelet processing and device for its implementation | |
| CN114912354B (en) | Method, device and medium for predicting mosquito vector infectious disease risk | |
| CN115169747A (en) | Method and device for predicting non-stationary time sequence of power load and related equipment | |
| Szmoski et al. | Effective dynamics for chaos synchronization in networks with time-varying topology | |
| CN113762648A (en) | Public defense black swan event prediction method, device, equipment and medium | |
| Salah et al. | A modified ARIMA model for forecasting chemical sales in the USA | |
| Pereira et al. | Time series forecasting by using a neural arima model based on wavelet decomposition |
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 |