CN111429180A - Liquefied natural gas demand prediction method and device - Google Patents
Liquefied natural gas demand prediction method and device Download PDFInfo
- Publication number
- CN111429180A CN111429180A CN202010211666.7A CN202010211666A CN111429180A CN 111429180 A CN111429180 A CN 111429180A CN 202010211666 A CN202010211666 A CN 202010211666A CN 111429180 A CN111429180 A CN 111429180A
- Authority
- CN
- China
- Prior art keywords
- natural gas
- liquefied natural
- regional
- demand
- fitting
- 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
- 239000003949 liquefied natural gas Substances 0.000 title claims abstract description 211
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 47
- 238000005457 optimization Methods 0.000 claims abstract description 26
- 238000003860 storage Methods 0.000 claims abstract description 17
- 230000001932 seasonal effect Effects 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 3
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 abstract description 20
- 239000003345 natural gas Substances 0.000 abstract description 10
- 238000010276 construction Methods 0.000 abstract description 5
- 238000011161 development Methods 0.000 abstract description 5
- 238000013468 resource allocation Methods 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 55
- 238000010586 diagram Methods 0.000 description 17
- 238000012545 processing Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 230000000737 periodic effect Effects 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 3
- 238000011179 visual inspection Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 230000003442 weekly effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- 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
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Filling Or Discharging Of Gas Storage Vessels (AREA)
Abstract
The application discloses a liquefied natural gas demand prediction method and device, electronic equipment and a readable storage medium. The method comprises the following steps: acquiring daily consumption data of regional liquefied natural gas; inputting the daily consumption data of the regional liquefied natural gas into a preset time sequence algorithm for fitting so as to establish a time sequence model; optimizing the parameters of the time series model by adopting a preset parameter optimization algorithm; and outputting a liquefied natural gas demand prediction model according to the optimization result so as to predict the liquefied natural gas demand of the region according to the liquefied natural gas demand prediction model. The method and the device solve the problems that in the related art, due to the fact that scientific resource allocation cannot be carried out on the liquefied natural gas, the liquefied natural gas transportation efficiency is low, and the development of the natural gas is restricted due to insufficient pipeline coverage, limited pipe network interconnection and intercommunication degree and slow construction progress. Through this application, allotment resource that can be more scientific, the confession is protected to helping hand natural gas, promotes liquefied natural gas's conveying efficiency.
Description
Technical Field
The application relates to the field of demand prediction of liquefied natural gas, in particular to a demand prediction method and device of liquefied natural gas, electronic equipment and a readable storage medium.
Background
Under the influence of the rapid expansion of the downstream demand of liquefied natural gas (L NG), the domestic supply is becoming tight, the pipeline gas frequency is limited, and diversified consumption demands need to be matched with diversified transportation modes, wherein the highway transportation is responsible for transporting the liquefied natural gas of natural gas liquefaction plants and receiving stations to various use points.
Highway transportation of lng is an important part of the lng supply chain. Therefore, the demand prediction for the liquefied natural gas can allocate resources more scientifically, the natural gas conservation and supply assistance can be realized, the transportation efficiency of the liquefied natural gas is improved, and the restriction on the development of the natural gas caused by insufficient pipeline coverage, limited degree of interconnection and intercommunication of a pipe network and slow construction progress can be quickly compensated.
Aiming at the problems that the transportation efficiency of the liquefied natural gas is low due to the fact that scientific resource allocation can not be carried out on the liquefied natural gas in the related technology, and the development of the natural gas is restricted due to the fact that the pipeline coverage is insufficient, the degree of interconnection and intercommunication of a pipe network is limited, and the construction progress is slow, an effective solution scheme is not provided at present.
Disclosure of Invention
The present application is directed to a method and an apparatus for demand prediction of liquefied natural gas, an electronic device and a readable storage medium, for solving the above-mentioned problems in the related art.
In order to achieve the above object, according to a first aspect of the present application, a demand prediction method for liquefied natural gas is provided.
The liquefied natural gas demand prediction method comprises the following steps: acquiring daily consumption data of regional liquefied natural gas; inputting the daily consumption data of the regional liquefied natural gas into a preset time sequence algorithm for fitting so as to establish a time sequence model; optimizing the parameters of the time series model by adopting a preset parameter optimization algorithm; and outputting a liquefied natural gas demand prediction model according to the optimization result so as to predict the liquefied natural gas demand of the region according to the liquefied natural gas demand prediction model.
Further, the acquiring of the daily data of the regional liquefied natural gas includes: acquiring liquefied natural gas road transportation track data; extracting regional liquefied natural gas supply and demand data according to the liquefied natural gas road transportation track data; and calculating the daily consumption data of the regional liquefied natural gas according to the supply and demand data of the liquefied natural gas.
Further, the preset time series algorithm comprises a plurality of sub-functions, and the inputting the data of the daily consumption of the regional liquefied natural gas into the preset time series algorithm for fitting to establish the time series model comprises: respectively inputting the daily consumption data of the regional liquefied natural gas into a plurality of the subfunctions for fitting so as to obtain a plurality of fitting results; and superposing the fitting results to obtain the time series model.
Further, the preset time series algorithm comprises a trend function, a seasonal function and a holiday function, and the step of inputting the daily data of the regional liquefied natural gas into the preset time series algorithm for fitting to establish the time series model comprises the following steps: inputting the daily consumption data of the regional liquefied natural gas into the trend function to obtain a first fitting result; inputting the daily consumption data of the regional liquefied natural gas into the seasonal function to obtain a second fitting result; inputting the daily consumption data of the regional liquefied natural gas into the holiday function to obtain a third fitting result; and superposing the first fitting result, the second fitting result and the third fitting result to obtain the time series model.
Further, the outputting a liquefied natural gas demand prediction model according to the optimization result, so as to predict the liquefied natural gas demand of the region according to the liquefied natural gas demand prediction model, then includes: obtaining a demand forecast request for liquefied natural gas, wherein the demand forecast request for liquefied natural gas includes a region and a date; calling a corresponding liquefied natural gas demand prediction model according to the region; inputting the date into the liquefied natural gas demand prediction model to output the liquefied natural gas demand of the region on the date.
In order to achieve the above object, according to a second aspect of the present application, there is provided a liquefied natural gas demand prediction apparatus.
The liquefied natural gas demand prediction device according to the present application includes: the first acquisition module is used for acquiring daily consumption data of regional liquefied natural gas; the input module is used for inputting the daily consumption data of the regional liquefied natural gas into a preset time series algorithm for fitting so as to establish a time series model; the optimization module is used for optimizing the parameters of the time series model by adopting a preset parameter optimization algorithm; and the output module is used for outputting the liquefied natural gas demand prediction model according to the optimization result so as to predict the liquefied natural gas demand of the region according to the liquefied natural gas demand prediction model.
Further, the first obtaining module comprises: the acquisition unit is used for acquiring liquefied natural gas road transportation track data; the extraction unit is used for extracting regional liquefied natural gas supply and demand data according to the liquefied natural gas highway transportation track data; and the calculating unit is used for calculating the daily consumption data of the regional liquefied natural gas according to the supply and demand data of the liquefied natural gas.
Further, the preset time series algorithm includes a plurality of sub-functions, and the input module includes: the first input unit is used for inputting the daily consumption data of the regional liquefied natural gas into the plurality of subfunctions respectively for fitting so as to obtain a plurality of fitting results; and the first superposition unit is used for superposing the fitting results to obtain the time series model.
In order to achieve the above object, according to a third aspect of the present application, there is provided an electronic apparatus comprising: one or more processors; storage means for storing one or more programs; the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of the preceding claims.
To achieve the above object, according to a fourth aspect of the present application, there is provided a non-transitory readable storage medium having stored thereon computer instructions which, when executed by a processor, implement the steps of the method according to any of the preceding claims.
In the embodiment of the application, the method comprises the steps of acquiring daily consumption data of regional liquefied natural gas; inputting the daily consumption data of the regional liquefied natural gas into a preset time sequence algorithm for fitting so as to establish a time sequence model; the method for optimizing the parameters of the time series model by adopting the preset parameter optimization algorithm achieves the aim of accurately predicting the demand of the liquefied natural gas in the region according to the demand prediction model of the liquefied natural gas by outputting the demand prediction model of the liquefied natural gas according to the optimization result, so that resources can be allocated more scientifically, the natural gas supply can be assisted, the transportation efficiency of the liquefied natural gas is improved, and the restriction of the natural gas development caused by insufficient pipeline coverage, limited degree of interconnection and intercommunication of a pipe network and slow construction progress can be rapidly compensated.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, serve to provide a further understanding of the application and to enable other features, objects, and advantages of the application to be more apparent. The drawings and their description illustrate the embodiments of the invention and do not limit it. In the drawings:
FIG. 1 is a schematic flow diagram of a method for demand prediction of liquefied natural gas according to a first embodiment of the present application;
FIG. 2 is a schematic flow diagram of a method for demand prediction of liquefied natural gas according to a second embodiment of the present application;
FIG. 3 is a schematic flow diagram of a method for demand prediction of liquefied natural gas according to a third embodiment of the present application;
FIG. 4 is a schematic flow chart of a method for demand prediction of liquefied natural gas according to a fourth embodiment of the present application;
FIG. 5 is a schematic flow chart of a method for demand prediction of liquefied natural gas according to a fifth embodiment of the present application;
FIG. 6 is a schematic diagram of a fitting result of a prediction model of demand for liquefied natural gas according to an embodiment of the application;
FIG. 7 is a graphical illustration of trend, weekly, and annual effects in a prediction of demand for liquefied natural gas according to an embodiment of the application;
FIG. 8 is a schematic diagram of a schematic block diagram of an LNG demand prediction apparatus according to an embodiment of the present application; and
fig. 9 is a schematic diagram of a composition structure of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all 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 application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. 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 noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
According to an embodiment of the present invention, there is provided a demand prediction method for liquefied natural gas, as shown in fig. 1, the method includes steps S101 to S104 as follows:
and step S101, acquiring daily consumption data of the regional liquefied natural gas.
In specific implementation, before a model for predicting demand of liquefied natural gas is constructed, daily consumption data of liquefied natural gas (L NG) of each region, that is, consumption of liquefied natural gas per day of each region, needs to be obtained, where the daily consumption data specifically includes a date field ds (date, datetime data type) and a L NG daily consumption field y (consumption value variable, float data type).
And S102, inputting the daily consumption data of the regional liquefied natural gas into a preset time series algorithm for fitting so as to establish a time series model.
In specific implementation, the method adopts a Prophet algorithm to construct a liquefied natural gas demand time series model, the Prophet algorithm mainly uses daily observation data to analyze a time series, and a Prophet overall framework comprises the following four parts: modeling, Forecast Evaluation, Surface profiles, and visual inspection profiles. On the whole, the method is a loop structure, and the structure can be divided into a Modeling + visual inspection methods and an automation part (Forecast Evaluation + surface schemes), so that the whole process is a loop system combining an analyst and an automation process and is a process combining problem background knowledge and statistical analysis, the application range of the model is greatly increased through combination, and the accuracy of the model is improved. According to the four parts, the prediction process of the Prophet algorithm is as follows: 1) modeling: and establishing a time series model, and selecting a proper model according to the background of the prediction problem. 2) Forecast Evaluation: and (6) evaluating the model. The historical data is simulated according to the model, various attempts can be made under the condition that the parameters of the model are uncertain, and which model is more suitable is evaluated according to the corresponding simulation effect. 3) Surface profiles: presenting a problem. If the model is not fully functional after the various parameters are tried, the analyst may be presented with a potential cause of the large error. 4) VisuallyInspects forms: and feeding back the whole prediction result in a visual mode. After the questions are fed back to the analyst, the analyst considers whether to further tune and build the model.
The obtained daily consumption data of the regional liquefied natural gas are input into a Prophet algorithm for fitting, and then a preliminary time series model is obtained.
And S103, optimizing the parameters of the time series model by adopting a preset parameter optimization algorithm.
In particular, L-BGFS may be used to obtain maximum A posteriori estimates of the various parameters of the time series model. L-BFGS solves the unconstrained minimization problem, e.g., minimizing F (x), x (x1, x 2.., xN), only when the objective function F (x) and its gradient function G (x) are calculable.
And step S104, outputting a liquefied natural gas demand prediction model according to the optimization result, and predicting the liquefied natural gas demand of the region according to the liquefied natural gas demand prediction model.
In specific implementation, after the parameters of the time series model are optimized through the preset parameter optimization algorithm, a final liquefied natural gas demand prediction model is obtained, and the liquefied natural gas demand condition of any region can be predicted according to the liquefied natural gas demand prediction model.
According to the embodiment of the application, the demand condition of the liquefied natural gas in each region can be accurately predicted through the demand prediction model of the liquefied natural gas constructed in the way, more scientific resource allocation can be carried out on the road transportation of the liquefied natural gas according to the prediction result, and the transportation efficiency of the liquefied natural gas is further improved.
As a preferred implementation manner of the embodiment of the present application, as shown in fig. 2, the acquiring of the daily consumption data of the regional liquefied natural gas includes steps S201 to S203 as follows:
step S201, acquiring liquefied natural gas road transportation track data.
In specific implementation, when acquiring daily consumption data of local liquefied natural gas, firstly, road transportation track data of the liquefied natural gas needs to be acquired, and the road transportation track data may include a driving route, a vehicle stop, stop time and the like. The existing liquefied natural gas transport vehicles are generally provided with positioning terminals, and the positioning terminals upload vehicle position data at a certain frequency so as to form track data of the vehicles.
And S202, extracting regional liquefied natural gas supply and demand data according to the liquefied natural gas road transportation track data.
In specific implementation, based on the obtained road transportation track data of the liquefied natural gas, liquefied natural gas trade data of corresponding regions, namely supply and demand data of the liquefied natural gas, are extracted.
And S203, calculating the daily consumption data of the regional liquefied natural gas according to the supply and demand data of the liquefied natural gas.
In specific implementation, after the supply and demand data of the liquefied natural gas in the region is obtained, L NG daily consumption of the region is counted according to the supply and demand data of the region, and the daily consumption comprises a date field ds (date data type) and a L NG consumption field y (consumption value variable, float data type).
As a preferred implementation manner of the embodiment of the present application, as shown in fig. 3, the preset time series algorithm includes a plurality of sub-functions, and the inputting the data of the daily consumption of the regional lng into the preset time series algorithm for fitting to establish the time series model includes the following steps S301 to S302:
and S301, inputting the daily consumption data of the regional liquefied natural gas into a plurality of the subfunctions respectively for fitting to obtain a plurality of fitting results.
In specific implementation, the preset time sequence algorithm adopted in the embodiment of the application is a Prophet algorithm, and the Prophet algorithm may include a plurality of sub-functions, so that data with different trends in the daily consumption data of the regional liquefied natural gas are respectively fitted through the plurality of sub-functions, and then a plurality of fitting results are obtained.
And S302, overlapping the fitting results to obtain the time series model.
In specific implementation, the number of the sub-functions in the embodiment of the present application may be three, for example, g (t), s (t), and h (t), respectively. And adding the fitting results of the sub-functions to obtain a final time series model y (t), which is shown as the following formula:
y(t)＝g(t)+s(t)+h(t)+∈， (1)
wherein g (t) is a trend (trend) function for analyzing aperiodic changes in the time series, s (t) represents periodic changes, such as the periodicity of a week or a year, h (t) represents the influence caused by occasional days or days such as holidays, ∈ is an error term representing the influence of the remaining errors which are not considered.
As a preferred implementation manner of the embodiment of the present application, as shown in fig. 4, the preset time-series algorithm includes a trend function, a seasonal function, and a holiday function, and the inputting the daily data of the regional lng into the preset time-series algorithm for fitting to establish the time-series model includes steps S401 to S404 as follows:
step S401, inputting the daily consumption data of the regional liquefied natural gas into the trend function to obtain a first fitting result.
In specific implementation, the preset time series algorithm adopted in the embodiment of the application is a Prophet algorithm, the algorithm comprises three functions, the first function is a trend function g (t), the trend function g (t) represents how the whole time series is considered to be increased or changed and how the whole time series is expected to be increased or changed in future time, and the fitting result of the trend function is obtained by inputting the daily consumption data of the regional liquefied natural gas into the trend function g (t). Specifically, the formula of the trend function is obtained as follows:
we define the growth term g (t) as a logical function:
this function is actually analogous to a population growth function, where C is population size, k is growth rate, and b is offset. It is clear that with increasing time t, the more C is approached by g (t), and the higher k is, the faster the growth rate is.
However, if only this model is used, it is not sufficient, because the growth rate may change with time, so we can set a change point to represent the time node of the growth rate k change, when t > sjIs a turning point.
Due to the occurrence of change point, in order to make the function continuous, some processing is required:
let C also vary with time, and use C (t) to represent the upper limit of growth:
C(t)＝K
C(t)＝Mt+K， (5)
the final formula for the trend function can then be found as:
in addition, we can also use a linear growth function:
g(t)＝(k+a(t)τ)+(b+a(t)τγ)， (7)
where k is the growth rate, is the adaptation rate, b is the offset parameter, and γ is set to-sj jThe purpose is to make the function continuous.
And S402, inputting the daily consumption data of the regional liquefied natural gas into the seasonal function to obtain a second fitting result.
In specific implementation, the second function related to the Prophet algorithm is a seasonal function or a periodic function s (t), and the fitting result of the seasonal function is obtained by inputting the daily consumption data of the regional liquefied natural gas into the seasonal function s (t). Specifically, since the time series may include seasonal trends of various cycle types, a fourier series may be used to approximately express the cycle attribute, and the specific formula is as follows:
wherein, P is the time period, when P is 7, the drawing is the cycle, and when P is 365.25, the cycle is the year. a isnAnd bnAre parameters that need to be learned. As is clear from the properties of the fourier series, as N increases, a periodic pattern that changes more frequently is drawn, and as a default, N is 10 for a periodic change in the unit of year, and N is 3 for a periodic change in the unit of week.
And S403, inputting the daily consumption data of the regional liquefied natural gas into the holiday function to obtain a third fitting result.
In specific implementation, the third function related to the Prophet algorithm is a holiday function h (t), and many practical experiences show that holidays or some major events have great influence on a time sequence, and the time points often have no periodicity. Analysis of these points is extremely necessary, even though sometimes it is of far greater importance than the usual points. And inputting the daily consumption data of the regional liquefied natural gas into the holiday function h (t) so as to obtain a fitting result of the holiday function. The formula of the holiday function adopted in the embodiment of the application is as follows:
Z(t)＝[1(t∈D1)，…，1(t∈DL)]
z (t) represents the length of a holiday, wherein the holiday model treats the effects of different holidays at different points in time as independent models, given that the date and degree of effect of each holiday (or some known major event) differ. A time window is set for each model at the same time, which mainly takes into account that the influence of holidays has a window period (e.g. the first few days and the last few days of mid-autumn festival), and the model sets the influence in the same window period to the same value. Wherein D isLAnd the time t contained in the window period is shown, and K shows the influence of the holiday in the window period on the predicted value.
And S404, superposing the first fitting result, the second fitting result and the third fitting result to obtain the time series model.
In specific implementation, fitting results of the trend function, the seasonal function and the holiday function are superposed according to the following formula, and then a final time series model is obtained.
y(t)＝g(t)+s(t)+h(t)+∈。
As a preferred implementation manner of the embodiment of the present application, as shown in fig. 5, after the outputting a liquefied natural gas demand prediction model according to an optimization result to predict the demand of liquefied natural gas in a region according to the liquefied natural gas demand prediction model, the method includes the following steps 501 to S503:
step S501, obtaining a demand forecast request of liquefied natural gas, wherein the demand forecast request of liquefied natural gas comprises a region and a date.
In specific implementation, when a relevant department or person needs to predict the demand of the liquefied natural gas in a certain area at a future time or a certain time, a request for predicting the demand of the liquefied natural gas can be initiated, so that the request for predicting the demand of the liquefied natural gas needs to be obtained first, wherein the request comprises the area to be predicted and the predicted time.
And step S502, calling a corresponding liquefied natural gas demand prediction model according to the region.
In specific implementation, the liquefied natural gas demand prediction models corresponding to different regions are different, so that the corresponding liquefied natural gas demand prediction models need to be called according to the regions to predict the liquefied natural gas demand of the regions.
Step S503, inputting the date into the liquefied natural gas demand forecasting model so as to output the liquefied natural gas demand of the region on the date.
In specific implementation, the demand prediction model is related to date, and the demand of the liquefied natural gas at the date can be predicted by inputting the date needing prediction into the model. Specifically, the prediction result includes a date ds, a required liquefied natural gas quantity yhat, a lower limit of the required liquefied natural gas quantity yhat _ lower, and an upper limit of the required liquefied natural gas quantity yhat _ upper, which is a confidence interval of the change of the demand prediction result of the liquefied natural gas.
Fig. 6 is a schematic diagram of the fitting result of the lng demand prediction model according to the embodiment of the present application, where black dots represent L NG usage amount of real data, solid lines represent the line fitted to the prediction result, and shaded areas represent confidence intervals given for upper and lower prediction limits.
Fig. 7 is a schematic diagram illustrating a trend effect, a week effect, and an annual effect in the prediction result of the demand for liquefied natural gas according to the embodiment of the present application.
From the above description, it can be seen that the present invention achieves the following technical effects: acquiring daily consumption data of regional liquefied natural gas; inputting the daily consumption data of the regional liquefied natural gas into a preset time sequence algorithm for fitting so as to establish a time sequence model; the method for optimizing the parameters of the time series model by adopting the preset parameter optimization algorithm achieves the aim of accurately predicting the demand of the liquefied natural gas in the region according to the demand prediction model of the liquefied natural gas by outputting the demand prediction model of the liquefied natural gas according to the optimization result, so that resources can be allocated more scientifically, the natural gas supply can be assisted, the transportation efficiency of the liquefied natural gas is improved, and the restriction of the natural gas development caused by insufficient pipeline coverage, limited degree of interconnection and intercommunication of a pipe network and slow construction progress can be rapidly compensated.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
According to an embodiment of the present invention, there is also provided an apparatus for implementing the method for predicting demand for liquefied natural gas, as shown in fig. 8, the apparatus including: the device comprises a first acquisition module 1, an input module 2, an optimization module 3 and an output module 4. The first obtaining module 1 of the embodiment of the application is used for obtaining daily consumption data of regional liquefied natural gas; the input module 2 of the embodiment of the application is used for inputting the daily consumption data of the regional liquefied natural gas into a preset time series algorithm for fitting so as to establish a time series model; the optimization module 3 of the embodiment of the application is configured to optimize parameters of the time series model by using a preset parameter optimization algorithm; the output module 4 of the embodiment of the application is used for outputting the liquefied natural gas demand prediction model according to the optimization result so as to predict the liquefied natural gas demand of the region according to the liquefied natural gas demand prediction model.
As a preferred implementation manner of the embodiment of the present application, the first obtaining module includes: the acquisition unit is used for acquiring liquefied natural gas road transportation track data; the extraction unit is used for extracting regional liquefied natural gas supply and demand data according to the liquefied natural gas highway transportation track data; and the calculating unit is used for calculating the daily consumption data of the regional liquefied natural gas according to the supply and demand data of the liquefied natural gas.
As a preferred implementation manner of the embodiment of the present application, the preset time series algorithm includes a plurality of sub-functions, and the input module includes: the first input unit is used for inputting the daily consumption data of the regional liquefied natural gas into the plurality of subfunctions respectively for fitting so as to obtain a plurality of fitting results; and the first superposition unit is used for superposing the fitting results to obtain the time series model.
As a preferred implementation manner of the embodiment of the present application, the preset time series algorithm includes a trend function, a seasonal function, and a holiday function, and the input module includes: the second input unit is used for inputting the daily consumption data of the regional liquefied natural gas into the trend function to obtain a first fitting result; the third input unit is used for inputting the daily consumption data of the regional liquefied natural gas into the seasonal function to obtain a second fitting result; the fourth input unit is used for inputting the daily consumption data of the regional liquefied natural gas into the holiday function to obtain a third fitting result; and the second superposition unit is used for superposing the first fitting result, the second fitting result and the third fitting result to obtain the time series model.
As a preferred implementation of the embodiment of the present application, the apparatus further includes: the second obtaining module is used for obtaining a demand prediction request of the liquefied natural gas, wherein the demand prediction request of the liquefied natural gas comprises a region and a date; the calling module is used for calling a corresponding liquefied natural gas demand prediction model according to the region; and the prediction module is used for inputting the date into the liquefied natural gas demand prediction model so as to output the liquefied natural gas demand of the region on the date.
For the specific connection relationship between the modules and the units and the functions performed, please refer to the detailed description of the method, which is not repeated herein.
According to an embodiment of the present invention, there is also provided a computer apparatus including: one or more processors; storage means for storing one or more programs; the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method as previously described.
There is also provided, in accordance with an embodiment of the present invention, a computer-readable storage medium having stored thereon computer instructions, which when executed by a processor, implement the steps of the method as previously described.
As shown in fig. 9, the electronic device includes one or more processors 31 and a memory 32, and one processor 31 is taken as an example in fig. 9.
The control unit may further include: an input device 33 and an output device 34.
The processor 31, the memory 32, the input device 33 and the output device 34 may be connected by a bus or other means, and the bus connection is exemplified in fig. 9.
The processor 31 may be a Central Processing Unit (CPU). The Processor 31 may also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, or combinations thereof. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 32, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules. The processor 31 executes various functional applications of the server and data processing by running non-transitory software programs, instructions and modules stored in the memory 32, so as to implement the liquefied natural gas demand prediction method of the above method embodiment.
The memory 32 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of a processing device operated by the server, and the like. Further, the memory 32 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 32 may optionally include memory located remotely from the processor 31, which may be connected to a network connection device via 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 input device 33 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the processing device of the server. The output device 34 may include a display device such as a display screen.
One or more modules are stored in the memory 32, which when executed by the one or more processors 31 perform the methods as previously described.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein. Computer instructions are used to cause the computer to perform the above-described lng demand prediction method.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, the principle and the implementation of the present invention are explained by applying the specific embodiments in the present invention, and the above description of the embodiments is only used to help understanding the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. A demand prediction method for Liquefied Natural Gas (LNG), comprising:
acquiring daily consumption data of regional liquefied natural gas;
inputting the daily consumption data of the regional liquefied natural gas into a preset time sequence algorithm for fitting so as to establish a time sequence model;
optimizing the parameters of the time series model by adopting a preset parameter optimization algorithm;
and outputting a liquefied natural gas demand prediction model according to the optimization result so as to predict the liquefied natural gas demand of the region according to the liquefied natural gas demand prediction model.
2. The method of predicting demand for liquefied natural gas according to claim 1, wherein the obtaining of data on daily consumption of regional liquefied natural gas comprises:
acquiring liquefied natural gas road transportation track data;
extracting regional liquefied natural gas supply and demand data according to the liquefied natural gas road transportation track data;
and calculating the daily consumption data of the regional liquefied natural gas according to the supply and demand data of the liquefied natural gas.
3. The lng demand prediction method of claim 1, wherein the predetermined time series algorithm comprises a plurality of sub-functions, and the inputting the regional lng daily data into the predetermined time series algorithm for fitting to establish the time series model comprises:
respectively inputting the daily consumption data of the regional liquefied natural gas into a plurality of the subfunctions for fitting so as to obtain a plurality of fitting results;
and superposing the fitting results to obtain the time series model.
4. The method of predicting demand for liquefied natural gas according to claim 1, wherein the predetermined time-series algorithm includes a trend function, a seasonal function, and a holiday function, and the inputting the regional daily liquefied natural gas data into the predetermined time-series algorithm for fitting to establish the time-series model includes:
inputting the daily consumption data of the regional liquefied natural gas into the trend function to obtain a first fitting result;
inputting the daily consumption data of the regional liquefied natural gas into the seasonal function to obtain a second fitting result;
inputting the daily consumption data of the regional liquefied natural gas into the holiday function to obtain a third fitting result;
and superposing the first fitting result, the second fitting result and the third fitting result to obtain the time series model.
5. The method of predicting demand for liquefied natural gas according to claim 1, wherein outputting a liquefied natural gas demand prediction model according to the optimization result to predict demand for liquefied natural gas in the area according to the liquefied natural gas demand prediction model comprises:
obtaining a demand forecast request for liquefied natural gas, wherein the demand forecast request for liquefied natural gas includes a region and a date;
calling a corresponding liquefied natural gas demand prediction model according to the region;
inputting the date into the liquefied natural gas demand prediction model to output the liquefied natural gas demand of the region on the date.
6. A liquefied natural gas demand prediction apparatus, comprising:
the first acquisition module is used for acquiring daily consumption data of regional liquefied natural gas;
the input module is used for inputting the daily consumption data of the regional liquefied natural gas into a preset time series algorithm for fitting so as to establish a time series model;
the optimization module is used for optimizing the parameters of the time series model by adopting a preset parameter optimization algorithm;
and the output module is used for outputting the liquefied natural gas demand prediction model according to the optimization result so as to predict the liquefied natural gas demand of the region according to the liquefied natural gas demand prediction model.
7. The lng demand prediction device of claim 6, wherein the first acquisition module comprises:
the acquisition unit is used for acquiring liquefied natural gas road transportation track data;
the extraction unit is used for extracting regional liquefied natural gas supply and demand data according to the liquefied natural gas highway transportation track data;
and the calculating unit is used for calculating the daily consumption data of the regional liquefied natural gas according to the supply and demand data of the liquefied natural gas.
8. The lng demand prediction device of claim 6, wherein the predetermined time series algorithm comprises a plurality of sub-functions, and the input module comprises:
the first input unit is used for inputting the daily consumption data of the regional liquefied natural gas into the plurality of subfunctions respectively for fitting so as to obtain a plurality of fitting results;
and the first superposition unit is used for superposing the fitting results to obtain the time series model.
9. An electronic device, comprising:
one or more processors;
storage means for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-5.
10. A non-transitory readable storage medium having stored thereon computer instructions which, when executed by a processor, implement the steps of the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010211666.7A CN111429180A (en) | 2020-03-23 | 2020-03-23 | Liquefied natural gas demand prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010211666.7A CN111429180A (en) | 2020-03-23 | 2020-03-23 | Liquefied natural gas demand prediction method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111429180A true CN111429180A (en) | 2020-07-17 |
Family
ID=71548741
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010211666.7A Pending CN111429180A (en) | 2020-03-23 | 2020-03-23 | Liquefied natural gas demand prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111429180A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112465216A (en) * | 2020-11-24 | 2021-03-09 | 中国人民解放军空军预警学院 | Flight data analysis method and device based on Prophet model and computer equipment |
| CN116386808A (en) * | 2023-01-19 | 2023-07-04 | 南京玛瑜信息科技有限公司 | Internet medicine-opening resource dynamic allocation system |
| CN118408302A (en) * | 2024-06-28 | 2024-07-30 | 浙江城建煤气热电设计院股份有限公司 | Natural gas distributed comprehensive energy system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105894113A (en) * | 2016-03-31 | 2016-08-24 | 中国石油天然气股份有限公司规划总院 | Natural gas short-period demand prediction method |
| CN109359778A (en) * | 2018-11-13 | 2019-02-19 | 中石化石油工程技术服务有限公司 | Short-term Forecast of Natural Gas Load method based on Optimization Experience mode decomposition |
| CN109495318A (en) * | 2018-12-17 | 2019-03-19 | 广东宜通世纪科技股份有限公司 | A kind of mobile communications network method for predicting, device and readable storage medium storing program for executing |
| CN109559046A (en) * | 2018-11-30 | 2019-04-02 | 北京市燃气集团有限责任公司 | A kind of natural gas development influence factor appraisal procedure and assessment system |
| CN109657831A (en) * | 2017-10-11 | 2019-04-19 | 顺丰科技有限公司 | A kind of Traffic prediction method, apparatus, equipment, storage medium |
| CN109993364A (en) * | 2019-04-01 | 2019-07-09 | 北京恒华龙信数据科技有限公司 | A kind of prediction technique and device of natural gas gas consumption |
| KR20190084750A (en) * | 2018-01-09 | 2019-07-17 | 주식회사 포스코건설 | Cost estimating system of lng income terminal and estimating method using it |
-
2020
- 2020-03-23 CN CN202010211666.7A patent/CN111429180A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105894113A (en) * | 2016-03-31 | 2016-08-24 | 中国石油天然气股份有限公司规划总院 | Natural gas short-period demand prediction method |
| CN109657831A (en) * | 2017-10-11 | 2019-04-19 | 顺丰科技有限公司 | A kind of Traffic prediction method, apparatus, equipment, storage medium |
| KR20190084750A (en) * | 2018-01-09 | 2019-07-17 | 주식회사 포스코건설 | Cost estimating system of lng income terminal and estimating method using it |
| CN109359778A (en) * | 2018-11-13 | 2019-02-19 | 中石化石油工程技术服务有限公司 | Short-term Forecast of Natural Gas Load method based on Optimization Experience mode decomposition |
| CN109559046A (en) * | 2018-11-30 | 2019-04-02 | 北京市燃气集团有限责任公司 | A kind of natural gas development influence factor appraisal procedure and assessment system |
| CN109495318A (en) * | 2018-12-17 | 2019-03-19 | 广东宜通世纪科技股份有限公司 | A kind of mobile communications network method for predicting, device and readable storage medium storing program for executing |
| CN109993364A (en) * | 2019-04-01 | 2019-07-09 | 北京恒华龙信数据科技有限公司 | A kind of prediction technique and device of natural gas gas consumption |
Non-Patent Citations (3)
| Title |
|---|
| 周家萱 等: "基于特殊任务 Prophet 模的航材消耗需求预测模型" * |
| 舒漫;刘夏兰;徐婷;谢雯娟;何斌;: "城市天然气短期日需求量预测新模型" * |
| 鲁德宏: "天然气用户需求特点及需求预测方法" * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112465216A (en) * | 2020-11-24 | 2021-03-09 | 中国人民解放军空军预警学院 | Flight data analysis method and device based on Prophet model and computer equipment |
| CN116386808A (en) * | 2023-01-19 | 2023-07-04 | 南京玛瑜信息科技有限公司 | Internet medicine-opening resource dynamic allocation system |
| CN116386808B (en) * | 2023-01-19 | 2023-11-14 | 北京智胜远景科技有限公司 | Internet medicine-opening resource dynamic allocation system |
| CN118408302A (en) * | 2024-06-28 | 2024-07-30 | 浙江城建煤气热电设计院股份有限公司 | Natural gas distributed comprehensive energy system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111429180A (en) | Liquefied natural gas demand prediction method and device | |
| CN110019401B (en) | Method, device, equipment and storage medium for predicting part quantity | |
| CN108038040B (en) | Computer cluster performance index detection method, electronic equipment and storage medium | |
| CN110400021B (en) | Bank branch cash usage prediction method and device | |
| Xu et al. | Strategic robust mixed model assembly line balancing based on scenario planning | |
| Salomons et al. | Practical real-time optimization for energy efficient water distribution systems operation | |
| US10332014B2 (en) | Concise state model for operational optimization of wastewater treatment unit(s) | |
| MX2013006155A (en) | Systems and methods for reducing reservoir simulator model run time. | |
| Osorio et al. | On the analytical approximation of joint aggregate queue-length distributions for traffic networks: A stationary finite capacity Markovian network approach | |
| US20230252490A1 (en) | Methods for determining smart gas inspection plans and internet of things systems thereof | |
| Ni et al. | Cordon control with spatially-varying metering rates: A reinforcement learning approach | |
| Wu et al. | High fidelity digital twin-based anomaly detection and localization for smart water grid operation management | |
| Wang et al. | Porter effect test for construction land reduction | |
| Peñuela et al. | Assessing the value of seasonal hydrological forecasts for improving water resource management: insights from a pilot application in the UK | |
| CN110836683A (en) | River channel management method, river channel management device and terminal | |
| CN113379168B (en) | Time series prediction processing method, device and equipment | |
| Mohammadi et al. | Solving a stochastic berth allocation problem using a hybrid sequence pair-based simulated annealing algorithm | |
| CN111738507A (en) | Bank clearing position fund payment amount prediction method, device, equipment and medium | |
| CN112365156B (en) | Data processing method, data processing device, terminal and storage medium | |
| Song et al. | Virtual shop model for experimental planning of steel fabrication projects | |
| Menezes et al. | Phenomenological decomposition heuristic for process design synthesis of oil-refinery Units | |
| US10445399B2 (en) | Forecast-model-aware data storage for time series data | |
| CN116562772A (en) | Method, apparatus, device, medium and program product for generating article replenishment information | |
| Hernandez | Flex scheduling for bus arrival time prediction | |
| CN114792258B (en) | Information generation method and device, electronic equipment and computer readable medium |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220627 Address after: 201306 C Building, 888 Huanhu West Second Road, Pudong New Area, Shanghai Applicant after: Zhonghaifu Information Technology Co.,Ltd. Address before: 200131 room 8-26, floor 8, building 2, No. 115, futexi 1st Road, China (Shanghai) pilot Free Trade Zone, Pudong New Area, Shanghai Applicant before: Shanghai Zhonghuan Energy Technology Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200717 |