CN113536668A - Gas supply load prediction method and device for gas system, terminal equipment and storage medium - Google Patents
Gas supply load prediction method and device for gas system, terminal equipment and storage medium Download PDFInfo
- Publication number
- CN113536668A CN113536668A CN202110720808.7A CN202110720808A CN113536668A CN 113536668 A CN113536668 A CN 113536668A CN 202110720808 A CN202110720808 A CN 202110720808A CN 113536668 A CN113536668 A CN 113536668A
- Authority
- CN
- China
- Prior art keywords
- sample
- supply load
- load prediction
- gas supply
- input
- 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 49
- 239000011159 matrix material Substances 0.000 claims abstract description 47
- 238000012549 training Methods 0.000 claims abstract description 35
- 230000008569 process Effects 0.000 claims abstract description 18
- 239000013598 vector Substances 0.000 claims abstract description 17
- 238000004590 computer program Methods 0.000 claims description 21
- 230000006870 function Effects 0.000 claims description 17
- 238000013139 quantization Methods 0.000 claims description 16
- 238000005314 correlation function Methods 0.000 claims description 5
- 238000011002 quantification Methods 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 3
- 230000000875 corresponding effect Effects 0.000 description 16
- 238000004891 communication Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 208000011231 Crohn disease Diseases 0.000 description 1
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 description 1
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—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
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Computer Hardware Design (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of load prediction, and discloses a method and a device for predicting gas supply load of a gas system, terminal equipment and a storage medium, wherein the method comprises the following steps: acquiring an input sample and an output sample for training an air supply load prediction model; the input sample is a multidimensional vector comprising historical air temperature and historical weather types, and the output sample is a gas supply load of a gas system corresponding to the input sample; performing Gaussian process regression training according to the input samples and the output samples, and establishing a correlation matrix among a plurality of input samples; establishing an air supply load prediction model according to the correlation matrix, and predicting a sample to be predicted to obtain a corresponding air supply load prediction value; wherein, the sample to be predicted is a multidimensional vector comprising future air temperature and future weather type. The method can establish the air supply load prediction model and improve the accuracy of air supply load prediction.
Description
Technical Field
The invention relates to the technical field of load prediction, in particular to a gas supply load prediction method and device for a gas system, terminal equipment and a storage medium.
Background
At present, the prediction of gas supply load is an important basis for operation and scheduling of a gas supply system, and the gas storage amount is reduced as much as possible and the gas storage cost is reduced under the condition of meeting the gas demand of a user.
The air supply load is easily influenced by various factors such as air temperature, weather conditions and the like, so that the obvious nonlinear characteristic is presented, and the difficulty is brought to the air supply load prediction work. In actual use, if the air supply load is predicted only by experience, the prediction result has a large deviation, so that the prediction result is not accurate enough, and the requirement of system operation scheduling cannot be met.
Disclosure of Invention
The invention provides a gas supply load prediction method and device for a gas system, terminal equipment and a storage medium, and aims to establish a gas supply load prediction model and improve the accuracy of gas supply load prediction of the gas system.
In a first aspect, an embodiment of the present invention provides a gas supply load prediction method for a gas system, including the following steps:
acquiring an input sample and an output sample for training an air supply load prediction model; the input sample is a multidimensional vector comprising historical air temperature and historical weather types, and the output sample is a gas supply load of a gas system corresponding to the input sample;
performing Gaussian process regression training according to the input samples and the output samples, and establishing a correlation matrix among a plurality of input samples;
establishing an air supply load prediction model according to the correlation matrix, and predicting a sample to be predicted to obtain a corresponding air supply load prediction value; wherein, the sample to be predicted is a multidimensional vector comprising future air temperature and future weather type.
Optionally, after establishing an air supply load prediction model according to the correlation matrix and predicting a sample to be predicted to obtain a corresponding air supply load prediction value, the method further includes:
and controlling the gas supply scheduling work of the gas system according to the gas supply load predicted value.
Optionally, after obtaining the input samples and the output samples for training the air supply load prediction model, the method further includes:
distinguishing load influence factors according to different types; wherein the load influence factors comprise air temperature and weather type;
quantizing the input sample according to the influence degree of different types of load influence factors on the air supply load to obtain a quantized value of the sample data;
and establishing a training sample database according to the sample data quantization value.
Optionally, the performing the gaussian process regression training according to the input samples and the output samples, and establishing a correlation matrix between a plurality of input samples specifically includes:
evaluating the correlation between any two input samples according to the covariance function;
and establishing a correlation matrix among a plurality of input samples according to the evaluation result.
Optionally, the establishing a gas supply load prediction model according to the correlation matrix and predicting a sample to be predicted to obtain a corresponding gas supply load prediction value includes:
obtaining Gaussian distribution obeyed by an air supply load predicted value according to the input sample, the output sample, the sample to be predicted and the correlation matrix;
taking the Gaussian distribution as a gas supply load prediction model;
and obtaining a predicted value of the gas supply load according to the gas supply load prediction model.
Optionally, the gaussian distribution is:
wherein, y*For the supply air load prediction, x is the input sample, y is the output sample, x*For the sample to be predicted, K is the correlation matrix, K-1Representing the inverse matrix of K, K*＝[k(x*,x1)k(x*,x2)…k(x*,xN)]，
Representation matrix K*Transposed matrix of, K**＝k(x*,x*)，k(xi,xj) Is the correlation function.
In a second aspect, an embodiment of the present invention provides a gas supply load prediction apparatus for a gas system, including:
the system comprises an acquisition module, a prediction module and a prediction module, wherein the acquisition module is used for acquiring input samples and output samples for training an air supply load prediction model; the input sample is a multidimensional vector comprising historical air temperature and historical weather types, and the output sample is a gas supply load of a gas system corresponding to the input sample;
the training module is used for carrying out Gaussian process regression training according to the input samples and the output samples and establishing a correlation matrix among a plurality of input samples;
the prediction module is used for establishing a gas supply load prediction model according to the correlation matrix and predicting a sample to be predicted to obtain a corresponding gas supply load prediction value; wherein, the sample to be predicted is a multidimensional vector comprising future air temperature and future weather type.
Optionally, the apparatus further includes a quantization module, where the quantization module specifically includes:
the distinguishing unit is used for distinguishing the load influence factors according to different types; wherein the load influence factors comprise air temperature and weather type;
the quantization unit is used for quantizing the input sample according to the influence degree of different types of load influence factors on the air supply load to obtain a sample data quantization value;
and the sample unit is used for establishing a training sample database according to the sample data quantized value.
In a third aspect, an embodiment of the present invention further provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, the method for predicting a gas supply load of a gas system described in any one of the above is implemented.
In a fourth aspect, the embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program, where when the computer program runs, the apparatus where the computer-readable storage medium is located is controlled to execute the gas supply load prediction method for the gas system according to any one of the above.
The invention provides a method and a device for predicting gas supply load of a gas system, terminal equipment and a storage medium, wherein one embodiment of the method has the following beneficial effects:
1. establishing a sample database according to data such as historical air supply load, air temperature, weather type and the like, training the sample data by adopting a Gaussian process regression algorithm, establishing a correlation matrix among a plurality of input samples, predicting the sample to be predicted according to an air supply load prediction model, and further obtaining a corresponding air supply load prediction value. The method can realize the prediction of the gas supply load, improves the accuracy of the gas supply load prediction, and the simulation result shows that the prediction error is 4.85 percent, meets the requirement of system operation scheduling, and provides a basis for the operation scheduling of the urban gas pipe network.
2. After the input sample is obtained, the sample data is quantized, and the influence of different types in each load influence factor on the air supply load can be distinguished; meanwhile, the quantized data is more concise and regular, and analysis and Gaussian process regression training are facilitated.
3. And evaluating each sample through a covariance function so as to establish a correlation matrix between the input samples, and then determining the Gaussian distribution obeyed by the air supply load according to the correlation matrix, so that the obtained Gaussian distribution is more accurate, and the accuracy of air supply load prediction is further improved.
Drawings
FIG. 1 is a schematic flow chart of a gas supply load prediction method for a gas system according to a first embodiment of the present invention;
FIG. 2 is a graph comparing predicted results with actual results;
fig. 3 is a schematic structural diagram of a gas supply load prediction device of a gas system according to a second embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a first embodiment of the present invention provides a supply air load prediction method, including the steps of:
s11, obtaining an input sample and an output sample for training an air supply load prediction model; the input sample is a multidimensional vector comprising historical air temperature and historical weather types, and the output sample is a gas supply load of a gas system corresponding to the input sample.
And S12, performing Gaussian process regression training according to the input samples and the output samples, and establishing a correlation matrix among a plurality of input samples.
S13, establishing a gas supply load prediction model according to the correlation matrix, and predicting a sample to be predicted to obtain a corresponding gas supply load prediction value; wherein, the sample to be predicted is a multidimensional vector comprising future air temperature and future weather type.
In step S11, the input sample is a multidimensional vector including a historical air temperature and a historical weather type, the output sample is an air supply load corresponding to the input sample, and the historical data is collected as sample data.
In one implementation, in order to facilitate analysis, after an input sample and an output sample used for training the air supply load prediction model are obtained, the sample data may be quantized to obtain a sample data quantized value, which specifically includes:
s21, distinguishing the load influence factors according to different types; wherein the load influence factors comprise air temperature and weather type;
s22, quantizing the input sample according to the influence degree of different types of load influence factors on the air supply load to obtain the quantized value of the sample data;
and S23, establishing a training sample database according to the sample data quantization value.
In step S21, different types of load influencing factors need to be distinguished. In this embodiment, the temperature, the weather type, the week type, and the holiday type are selected as sample data, and in other embodiments, other factors affecting the air supply load may also be selected as sample data, which is not limited in the present invention.
In step S22, sample data is quantized, wherein the influence degree of each load influence factor on the air supply load is different for different categories. For example, the weather types may be classified into various categories such as heavy rain, thunderstorm, light rain, and others (cloudy, clear, and cloudy), and the magnitude of the influence on the air supply load may be quantified, and the quantified values of heavy rain and heavy rain may be set to 1, the quantified values of thunderstorm and medium rain may be set to 0.9, the quantified value of light rain may be set to 0.8, and the other categories may be set to 0.7, and the results of the quantification may be shown in table 1.
| Weather type | Heavy/heavy rain | Thunderstorm/rain | Light rain | Others |
| Quantized value | 1.0 | 0.9 | 0.8 | 0.7 |
TABLE 1 weather type quantization Table
The week type and holiday type can also be quantified as described above, and the quantification results are shown in tables 2 and 3.
| Week | (Sunday) | Saturday wine | Working day |
| Quantized value | 1.0 | 0.9 | 0.8 |
TABLE 2 week-type quantization table
| Festival | Spring festival | National Day | Five one | At ordinary times |
| Quantized value | 1.0 | 0.9 | 0.8 | 0.7 |
TABLE 3 holiday type quantization table
After the quantized value of the sample data is obtained, a training sample database is built according to the quantized value of the sample data, that is, the contents in step S23. In the sample database, the daily air supply load is associated with the air temperature, the weather type, the week type and the holiday type of the day, and an input sample and an output sample are obtained, and the established training sample database is shown in table 4.
Table 4 training sample database
As can be seen from table 4, the input samples are multidimensional vectors including air temperature, weather type, week type, and holiday type, and the output samples are air supply loads corresponding to the input samples. Input samples are quantized, so that the input samples are simpler and more regular, and analysis and subsequent Gaussian process regression training are facilitated.
In step S12, a gaussian process regression training is performed on the input samples and the output samples to establish a correlation matrix between a plurality of input samples. Specifically, the correlation between any two input samples may be evaluated according to the covariance function, and a correlation matrix between a plurality of input samples may be established according to the evaluation result.
It should be noted here that the following mathematical model is satisfied between the input samples and the output samples:
yi＝f(xi)+ε(1)
wherein x isiIs an input sample, yiIs the sample to be predicted, is the measurement error,
f represents a Gaussian process function with a function value obeying a mean of 0 and a variance of
The distribution of the gaussian component of (a) is,
representing the variance of the output sample y.
In the Gaussian process, any two input samples xiAnd xjAre correlated, and the correlation degree can be determined by a covariance function k (x)i,xj) To describe, a gaussian kernel function can be generally adopted as the covariance function:
parameter in the formula
Is the maximum covariance, | x, between two input samplesi-xjI represents the Euclidean distance between two input samples, when xiAnd xjThe closer they are, the greater the correlation between them. The parameter l may be used to control the magnitude of the distance effect on the correlation. Taking into account the effect of measurement errors, the correlation function between two input samples can be expressedComprises the following steps:
wherein, δ (x)i,xj) Is a function of Crohn's function when xi＝xjWhen, delta (x)i,xj) 0; when x isi≠xjWhen, delta (x)i,xj) 1. According to equation (3), a correlation matrix between a plurality of input samples is established as follows:
the correlation matrix K covers N input samples, each sample is evaluated, and then a Gaussian process regression model is determined, so that the obtained Gaussian distribution is more accurate, and the accuracy of gas supply load prediction is further improved.
In step S13, an air supply load prediction model is established according to the correlation matrix, and a sample to be predicted is predicted to obtain a corresponding air supply load prediction value; wherein, the sample to be predicted is a multidimensional vector comprising future air temperature and future weather type.
Firstly, obtaining Gaussian distribution obeyed by an air supply load predicted value according to an input sample, an output sample, a sample to be predicted, a correlation function and a correlation matrix, and obtaining the air supply load predicted value according to the Gaussian distribution.
Under the condition of knowing input sample x and output sample y, for sample x to be predicted*Its corresponding air supply load predicted value y*Obey mean value of K*K-1y, variance of
Gaussian distribution of (a):
wherein, y*For the supply air load prediction, x is the input sample, y is the output sample, x*For the sample to be predicted, K is the correlation matrix, K-1Representing the inverse matrix of K, K*＝[k(x*,x1)k(x*,x2)…k(x*,xN)]，
Representation matrix K*Transposed matrix of, K**＝k(x*,x*)，k(xi,xj) Is the correlation function.
And secondly, after the Gaussian distribution is obtained, the Gaussian distribution is used as a gas supply load prediction model, and a gas supply load prediction value is obtained according to the gas supply load prediction model.
The method can realize the prediction of the air supply load and improve the accuracy of the prediction of the air supply load. As shown in FIG. 2, the annual load prediction result of a certain gas company is compared with the actual result according to the obtained sample data, and the root mean square error RMSE is 7.36X 104The average absolute percentage error MAPE is 4.85 percent in cubic meter, the requirement of system operation scheduling is met, and a basis can be provided for operation scheduling of the urban gas pipe network.
Referring to fig. 3, a second embodiment of the present invention provides a gas supply load prediction apparatus for a gas system, including:
the system comprises an acquisition module, a prediction module and a prediction module, wherein the acquisition module is used for acquiring input samples and output samples for training an air supply load prediction model; the input sample is a multidimensional vector comprising historical air temperature and historical weather types, and the output sample is a gas supply load of a gas system corresponding to the input sample;
the training module is used for carrying out Gaussian process regression training according to the input samples and the output samples and establishing a correlation matrix among a plurality of input samples;
the prediction module is used for establishing a gas supply load prediction model according to the correlation matrix and predicting a sample to be predicted to obtain a corresponding gas supply load prediction value; wherein, the sample to be predicted is a multidimensional vector comprising future air temperature and future weather type.
Preferably, the apparatus further comprises a quantization module, and the quantization module specifically includes:
the distinguishing unit is used for distinguishing the load influence factors according to different types; wherein the load influence factors comprise air temperature and weather type;
the quantization unit is used for quantizing the input sample according to the influence degree of different types of load influence factors on the air supply load to obtain a sample data quantization value;
and the sample unit is used for establishing a training sample database according to the sample data quantized value.
By adopting the device, a sample database can be established according to data such as historical air supply load, air temperature, weather types and the like, then the Gaussian process regression algorithm is adopted to train the sample data, a correlation matrix among a plurality of input samples is established, then the samples to be predicted are predicted according to the correlation matrix, and then the corresponding air supply load predicted value is obtained. The device can realize the prediction of the gas supply load, improves the accuracy of the gas supply load prediction, and the simulation result shows that the prediction error is 4.85 percent, meets the requirement of system operation scheduling, and provides a basis for the operation scheduling of the urban gas pipe network.
The embodiment of the invention also provides the terminal equipment. The terminal device includes: a processor, a memory and a computer program, such as a gas supply load prediction method program, stored in the memory and executable on the processor. The processor, when executing the computer program, implements the steps in each of the gas system supply air load prediction method embodiments described above, such as step S11 shown in fig. 1. Alternatively, the processor, when executing the computer program, implements the functions of the modules/units in the above device embodiments, such as the acquisition module.
Illustratively, the computer program may be partitioned into one or more modules/units that are stored in the memory and executed by the processor to implement the invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used for describing the execution process of the computer program in the terminal device.
The terminal device can be a desktop computer, a notebook, a palm computer, an intelligent tablet and other computing devices. The terminal device may include, but is not limited to, a processor, a memory. It will be appreciated by those skilled in the art that the above components are merely examples of a terminal device and do not constitute a limitation of a terminal device, and that more or fewer components than those described above may be included, or certain components may be combined, or different components may be included, for example, the terminal device may also include input output devices, network access devices, buses, etc.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is the control center of the terminal device and connects the various parts of the whole terminal device using various interfaces and lines.
The memory may be used for storing the computer programs and/or modules, and the processor may implement various functions of the terminal device by executing or executing the computer programs and/or modules stored in the memory and calling data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
Wherein, the terminal device integrated module/unit can be stored in a computer readable storage medium if it is implemented in the form of software functional unit and sold or used as a stand-alone product. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
It should be noted that the above-described device embodiments are merely illustrative, where the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. In addition, in the drawings of the embodiment of the apparatus provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, and may be specifically implemented as one or more communication buses or signal lines. One of ordinary skill in the art can understand and implement it without inventive effort.
The above-mentioned embodiments are provided to further explain the objects, technical solutions and advantages of the present invention in detail, and it should be understood that the above-mentioned embodiments are only examples of the present invention and are not intended to limit the scope of the present invention. It should be understood that any modifications, equivalents, improvements and the like, which come within the spirit and principle of the invention, may occur to those skilled in the art and are intended to be included within the scope of the invention.
Claims (10)
1. A gas supply load prediction method for a gas system is characterized by comprising the following steps:
acquiring an input sample and an output sample for training an air supply load prediction model; the input sample is a multidimensional vector comprising historical air temperature and historical weather types, and the output sample is the historical gas system gas supply load corresponding to the input sample;
performing Gaussian process regression training according to the input samples and the output samples, and establishing a correlation matrix among a plurality of input samples;
establishing an air supply load prediction model according to the correlation matrix, and predicting a sample to be predicted to obtain a corresponding air supply load prediction value; wherein, the sample to be predicted is a multidimensional vector comprising future air temperature and future weather type.
2. The gas system gas supply load prediction method according to claim 1, wherein after establishing a gas supply load prediction model according to the correlation matrix and predicting a sample to be predicted to obtain a corresponding gas supply load prediction value, the method further comprises:
and controlling the gas supply scheduling work of the gas system according to the gas supply load predicted value.
3. The gas system gas supply load prediction method according to claim 1, wherein after obtaining input samples and output samples for training a gas supply load prediction model, the method further comprises:
distinguishing load influence factors according to different types; wherein the load influence factors comprise air temperature and weather type;
quantizing the input sample according to the influence degree of different types of load influence factors on the air supply load to obtain a quantized value of the sample data;
and establishing a training sample database according to the sample data quantization value.
4. The gas supply load prediction method for a gas system according to claim 1, wherein the performing a gaussian process regression training according to the input samples and the output samples to establish a correlation matrix between a plurality of input samples specifically comprises:
evaluating the correlation between any two input samples according to the covariance function;
and establishing a correlation matrix among a plurality of input samples according to the evaluation result.
5. The gas system gas supply load prediction method according to claim 1, wherein the establishing a gas supply load prediction model according to the correlation matrix and predicting a sample to be predicted to obtain a corresponding gas supply load prediction value comprises:
obtaining Gaussian distribution obeyed by an air supply load predicted value according to the input sample, the output sample, the sample to be predicted and the correlation matrix;
taking the Gaussian distribution as a gas supply load prediction model;
and obtaining a predicted value of the gas supply load according to the gas supply load prediction model.
6. The gas system gas supply load prediction method of claim 5, wherein the Gaussian distribution is:
wherein, y*For the supply air load prediction, x is the input sample, y is the output sample, x*For the sample to be predicted, K is the correlation matrix, K-1Representing the inverse matrix of K, K*＝[k(x*，x1)k(x*，x2)…k(x*，xN)]，
Representation matrix K*Transposed matrix of, K**＝k(x*，x*)，k(xi，xj) Is the correlation function.
7. A gas supply load prediction device for a gas system, comprising:
the system comprises an acquisition module, a prediction module and a prediction module, wherein the acquisition module is used for acquiring input samples and output samples for training an air supply load prediction model; the input samples are multidimensional vectors comprising air temperature and weather types, and the output samples are corresponding gas supply loads of a gas system;
the training module is used for carrying out Gaussian process regression training according to the input samples and the output samples and establishing a correlation matrix among a plurality of input samples;
the prediction module is used for establishing a gas supply load prediction model according to the correlation matrix and predicting a sample to be predicted to obtain a corresponding gas supply load prediction value; and the samples to be predicted are multidimensional vectors comprising air temperature and weather types.
8. The gas system gas supply load prediction device according to claim 7, further comprising a quantification module, the quantification module specifically comprising:
the distinguishing unit is used for distinguishing the load influence factors according to different types; wherein the load influence factors comprise air temperature and weather type;
the quantization unit is used for quantizing the input sample according to the influence degree of different types of load influence factors on the air supply load to obtain a sample data quantization value;
and the sample unit is used for establishing a training sample database according to the sample data quantized value.
9. A terminal device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the gas system supply air load prediction method according to any one of claims 1 to 6 when executing the computer program.
10. A computer-readable storage medium, comprising a stored computer program, wherein when the computer program is run, the computer-readable storage medium controls a device to execute the gas system supply air load prediction method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110720808.7A CN113536668A (en) | 2021-06-28 | 2021-06-28 | Gas supply load prediction method and device for gas system, terminal equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110720808.7A CN113536668A (en) | 2021-06-28 | 2021-06-28 | Gas supply load prediction method and device for gas system, terminal equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113536668A true CN113536668A (en) | 2021-10-22 |
Family
ID=78126009
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110720808.7A Pending CN113536668A (en) | 2021-06-28 | 2021-06-28 | Gas supply load prediction method and device for gas system, terminal equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113536668A (en) |
-
2021
- 2021-06-28 CN CN202110720808.7A patent/CN113536668A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109858740B (en) | Enterprise risk assessment method and device, computer equipment and storage medium | |
| CN108446795B (en) | Power system load fluctuation analysis method and device and readable storage medium | |
| CN113239314A (en) | Method, device, terminal and computer-readable storage medium for carbon emission prediction | |
| CN109636010B (en) | Provincial power grid short-term load prediction method and system based on correlation factor matrix | |
| Yvette Zhang | A density‐ratio model of crop yield distributions | |
| CN106452934B (en) | Method and device for analyzing network performance index change trend | |
| CN114414935A (en) | Automatic positioning method and system for feeder fault area of power distribution network based on big data | |
| CN112508299A (en) | Power load prediction method and device, terminal equipment and storage medium | |
| CN113743673A (en) | Power load prediction method during typhoon | |
| CN113743650B (en) | Power load prediction method, device, equipment and storage medium | |
| CN110232150B (en) | User data analysis method and device, readable storage medium and terminal equipment | |
| CN111598460A (en) | Method, device and equipment for monitoring heavy metal content in soil and storage medium | |
| CN113536668A (en) | Gas supply load prediction method and device for gas system, terminal equipment and storage medium | |
| CN111581499A (en) | Data normalization method, device and equipment and readable storage medium | |
| CN110751400A (en) | Risk assessment method and device | |
| CN113190429A (en) | Server performance prediction method and device and terminal equipment | |
| CN113139673A (en) | Method, device, terminal and storage medium for predicting air quality | |
| CN113887802A (en) | Power load influence factor weighting dimensionalization processing method based on characteristic correlation | |
| CN113705929A (en) | Spring festival holiday load prediction method based on load characteristic curve and typical characteristic value fusion | |
| CN112561732A (en) | Method and device for optimizing active power scheduling of power system and readable storage medium | |
| CN112818067A (en) | Big data and multidimensional feature combined data tracing method and big data cloud server | |
| CN113486225B (en) | Enterprise image display method and system based on big data | |
| CN110852767A (en) | Passenger flow volume clustering method and terminal equipment | |
| WO2022156743A1 (en) | Feature construction method and apparatus, model training method and apparatus, and device and medium | |
| Wang et al. | Research on the Impact of Digital Technology Development on the Efficiency of Chinese Market Transactions |
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 |