CN110070225A - It is a kind of that Prediction of Coal Price method is lauched based on relation between supply and demand big data - Google Patents
It is a kind of that Prediction of Coal Price method is lauched based on relation between supply and demand big data Download PDFInfo
- Publication number
- CN110070225A CN110070225A CN201910323587.2A CN201910323587A CN110070225A CN 110070225 A CN110070225 A CN 110070225A CN 201910323587 A CN201910323587 A CN 201910323587A CN 110070225 A CN110070225 A CN 110070225A
- Authority
- CN
- China
- Prior art keywords
- coal
- supply
- demand
- data
- consumption
- 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.)
- Granted
Links
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
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0283—Price estimation or determination
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A20/00—Water conservation; Efficient water supply; Efficient water use
- Y02A20/20—Controlling water pollution; Waste water treatment
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S50/00—Market activities related to the operation of systems integrating technologies related to power network operation or related to communication or information technologies
- Y04S50/14—Marketing, i.e. market research and analysis, surveying, promotions, advertising, buyer profiling, customer management or rewards
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Entrepreneurship & Innovation (AREA)
- Finance (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Operations Research (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Prediction of Coal Price method is lauched based on relation between supply and demand big data the invention discloses a kind of, the following steps are included: step S1, obtain coal supply data and coal demand data, wherein, it includes coal production and coal import volume that coal, which supplies data, and coal demand data include macro-performance indicator, generated energy and coal consumption；Step S2 supplies data according to coal and coal demand data calculates monthly overall supplies and monthly total coal consumption, generates the monthly supply and demand difference table of coal；Step S3 extracts the linked character rule between monthly supply and demand difference table and coal price tendency using the method for correlation rule, generates Association Rules, and the tendency of coal market price is lauched according to Association Rules prediction.Compared with prior art, the present invention can carry out Accurate Prediction to the subsequent tendency for being lauched coal market price, and then more effectively optimize Coal Procurement opportunity and adjusted to greatest extent into texture of coal, reduce purchase cost.
Description
Technical field
Prediction of Coal Price method is lauched based on relation between supply and demand big data the present invention relates to a kind of, belongs to Prediction of Coal Price technology neck
Domain.
Background technique
With the iterative method of electricity marketization in recent years, fuel cost and the low electricity power enterprise of cost of electricity-generating are in electric power city
Just there is stronger competitiveness on field, thus the importance of fuel cost more highlights.Research influences the factor of coal price tendency, grasps
Coal market Fluctuation, it is lucrative for thermal power plant and fully develop talents.Therefore, only to subsequent coal price tendency
Accurate anticipation, could more effectively optimize Coal Procurement opportunity and be adjusted to greatest extent into texture of coal, reduce purchase cost.
Currently, be not to the prediction technique for being lauched coal market price it is very much, mainly predicted with macro-performance indicator or with
The Short Term of Microscopic Indexes prediction coal price.Wherein, macro-performance indicator can only probably predict coal price, be inaccurate,
Without the meaning for actually instructing procurement work；For example the index of Macro-economic situation starts downlink, using trade war as representative
Anticipated impact, supply side reform comes to an end, high-quality coal production capacity starts release etc., can predict that annual supply and demand improves, coal price
Median compared with last year decline be exactly Great possibility, but this prediction cannot direct concretely party in request divide moon or timesharing between
The buying of section.And Microscopic Indexes are too small, are generally only to carry out problem analysis from an angle, it is not necessarily comprehensively accurate, and by city
Field psychological impact is big, and short-term coal price tendency may deviate with practical coal price.As it can be seen that existing Prediction of Coal Price method can not be accurate
Accurate Prediction is carried out to the tendency for being lauched coal market price, thus can not effectively optimize Coal Procurement opportunity and adjust to greatest extent
It is whole into texture of coal, purchase cost can not be reduced.
Summary of the invention
Prediction of Coal Price method is lauched based on relation between supply and demand big data the object of the present invention is to provide a kind of, it can be down to
One of above-mentioned technical problem is solved less.
In order to solve the above technical problems, the present invention adopts the following technical scheme that:
It is a kind of that Prediction of Coal Price method is lauched based on relation between supply and demand big data, comprising: step S1 obtains coal and supplies data
With coal demand data, wherein the coal supply data include coal production and coal import volume, the coal demand data
Including generated energy and coal consumption；Step S2 supplies data according to the coal and the coal demand data calculates monthly total confession
Should measure with monthly total coal consumption, generate the monthly supply and demand difference table of coal；Step S3 extracts institute using the method for correlation rule
The linked character rule between monthly supply and demand difference table and coal price tendency is stated, generates Association Rules, and advise according to the association
Then collect the tendency that prediction is lauched coal market price.
Being lauched in Prediction of Coal Price method based on relation between supply and demand big data above-mentioned, before the step S2, further includes:
Step S4 obtains supply-demand connection data, and judges whether the supply-demand connection data are abnormal, if otherwise continuing to execute the step
S2；Wherein, the supply-demand connection data include Shipping amount and total volume of railway freight.
Being lauched in Prediction of Coal Price method based on relation between supply and demand big data above-mentioned judges the supply and demand in the step S4
If linking data whether include: extremely Coal Transport total amount same when ring than decline no more than 10% or Coal Transport it is total
Year-on-year, the sequential growth rate of amount then determine that the supply-demand connection data without exception, otherwise determine that the supply-demand connection data are different
Often.
Being lauched in Prediction of Coal Price method based on relation between supply and demand big data above-mentioned, the step S2 are specifically included: step
Coal production monthly is added by S21 with coal import volume respectively, and the monthly overall supplies is calculated；Step S22, point
Thermal coal consumption, coking coal consumption monthly is not added with lump coal consumption, monthly total coal consumption is calculated；Step
The monthly overall supplies is subtracted monthly total coal consumption, obtains supply and demand difference monthly, generate the moon of coal by rapid S23
Spend supply and demand difference table.
Being lauched in Prediction of Coal Price method based on relation between supply and demand big data above-mentioned, if can not obtain within a preset time
Month thermal coal consumption, coking coal consumption and lump coal consumption data, to calculate total coal consumption of last month, then the step
S22 further include: step S221 converts the thermal power output monthly before this month respectively according to conversion factor, worked as
Thermoelectricity coal consumption monthly before month；Step S222, according to the thermoelectricity coal consumption and total coal consumption monthly before last month, respectively
The ratio of the total coal consumption of thermoelectricity coal consumption Zhan monthly before last month is calculated, using simple regression function to the thermoelectricity of last month
The ratio of the total coal consumption of coal consumption Zhan is predicted；Step S223 is consumed according to the thermoelectricity coal consumption of last month and the thermoelectricity of last month
Total coal consumption of last month is calculated in the ratio of the total coal consumption of coal amount Zhan.
Being lauched in Prediction of Coal Price method based on relation between supply and demand big data above-mentioned is also wrapped before the step S223
Include: step S224, according to the power industry coal consumption and total coal consumption monthly before last month, before calculating separately last month monthly
Power industry coal consumption accounts for the ratio of coal total flow, and is accounted for using power industry coal consumption of the simple regression function to last month
Always the ratio of coal consumption is predicted, the power industry coal consumption accounting chart before generating this month；Step S225, before generating this month
Thermoelectricity coal consumption accounting chart；Step S226 accounts for the power industry coal consumption accounting chart and the thermoelectricity coal consumption
It is compared than chart, if the ratio of the ratio of the total coal consumption of power industry coal consumption Zhan and the total coal consumption of thermoelectricity coal consumption Zhan
Variation tendency is consistent, then checks success, continues to execute the step S223.
Being lauched in Prediction of Coal Price method based on relation between supply and demand big data above-mentioned, the step S3 are specifically included: being calculated
Confidence coefficient between supply and demand difference data and coal price will be between supply and demand difference data and coal price if confidence coefficient is greater than 0.8
Changing rule be determined as a correlation rule；When supply and demand difference is positive value, coal price drop, and numerical value longer on the occasion of the time is more
Greatly, drop-off range is bigger, the drop time is longer；When supply and demand difference is negative value, coal price goes up, the negative value time is longer and numerical value more
Greatly, rising range is bigger, the time of going up is longer；When supply and demand difference fluctuates near 0, the equilibrium of supply and demand, coal price is steady；Supply and demand is poor
There are 1-2 months time lags between value and the variation of coal price, the variation of coal price is later than the variation of supply and demand difference.
Being lauched in Prediction of Coal Price method based on relation between supply and demand big data above-mentioned, the step S3 further include: in conjunction with auxiliary
Factor is helped to predict the tendency for being lauched coal market price, wherein the cofactor includes manually pre- to short-term market psychology
Phase, forward market tendency and monthly long association's valence tendency.
Being lauched in Prediction of Coal Price method based on relation between supply and demand big data above-mentioned, the coal supply data further include coal
Charcoal quantity in stock, after the step S3, further includes: step S5 by each coal inventory figureofmerit and is lauched coal market price index
It compares, the correlation rule for forming each coal inventory figureofmerit and being lauched between coal market price index, according to the correlation rule
The tendency for being lauched coal market price of prediction is verified.
Compared with prior art, the present invention passes through the pricing model for coal price at this stage, from the angle of relation between supply and demand
Degree is started with, and combing influences the index of supply, demand, is collected corresponding historical data relevant to supply and demand, is utilized correlation rule, unitary
Three kinds of methods of regression function and supply and demand differential analysis carry out comprehensive analysis to the data of all kinds of supply and demand indexs, in conjunction with short-term market
The other factors such as in-mind anticipation, forward market tendency carry out Accurate Prediction to the subsequent tendency for being lauched coal market price, and then more have
The optimization Coal Procurement opportunity of effect adjusts with maximum into texture of coal, reduces purchase cost；The present invention is looked forward to from thermal power generation
The actual demand of industry is set out, and all kinds of main macroscopics, Microscopic Indexes needed for network analysis is used, using data collection as base
Plinth searches out the changing rule between some data and coal price, procurement work is instructed to practice using mathematical analysis as means.
Detailed description of the invention
Fig. 1, Fig. 2, Fig. 3, Fig. 6 are method flow diagram provided in an embodiment of the present invention；
Fig. 4 is supply and demand difference table provided in an embodiment of the present invention；
Fig. 5 is history coal price trend graph provided in an embodiment of the present invention.
The present invention is further illustrated with reference to the accompanying drawings and detailed description.
Specific embodiment
The embodiment of the present invention provide it is a kind of Prediction of Coal Price method is lauched based on relation between supply and demand big data, as shown in Figure 1, main
Want the following steps are included:
Step S1 obtains coal supply data and coal demand data, wherein coal supply data include coal production and
Coal import volume, coal demand data include generated energy and coal consumption；
Start with from relation between supply and demand, collects the influence factor and historical data of coal supply, demand.Wherein, coal supplies number
It is coal production according to first part, including production capacity situation, the production of monthly coal are not built up in coal totality production capacity situation, approval at this stage
Amount, every profession and trade thermal coal supply amount；Second part is coal import volume, including monthly coal import volume, international market coal price are (extensively
State port Import Coal C.I.F. etc.), import coal control policy.Coal demand data first part is target generated output, including fire
Power, waterpower, wind-force, photovoltaic, nuclear power target generated output；Second part be coal consumption index, including thermal coal divide electric power, building materials,
Chemical industry, metallurgy, heat supply, other etc. every profession and trades consumption data, coastal six big electric day consumption, national emphasis power plant day consumption.Optionally, coal
Charcoal demand data can also include macro-performance indicator, including manufacturing industry Purchase Management Index, the index numbers of industrial production, be used for coal
The assistant analysis of valence forward prediction.
Step S2 supplies data according to coal and coal demand data calculates monthly overall supplies and monthly total coal consumption,
Generate the monthly supply and demand difference table of coal；
As shown in Fig. 2, step S2 is specifically included:
Coal production monthly is added with coal import volume respectively, monthly overall supplies is calculated by step S21；
Thermal coal consumption, coking coal consumption monthly is added with lump coal consumption respectively, is calculated by step S22
Monthly total coal consumption；
Monthly overall supplies is subtracted monthly total coal consumption, obtains supply and demand difference monthly, generate coal by step S23
Monthly supply and demand difference table.
It should be noted that the no sequencing of execution of step S21 and step S22, as long as step S21, step S22 are equal
It is executed before step S23.
Thermal coal consumption, coking coal consumption and lump coal consumption data due to calculating total coal consumption generally want late one
Go out within more months, therefore, total coal consumption of last month can not be obtained by calculation, pre- in order to carry out in time to subsequent coal price tendency
It surveys, needs to predict total coal consumption of last month at this time, so, when within a preset time (such as before the of that month last ten-days period) can not
When obtaining the total coal consumption of thermal coal consumption, coking coal consumption and the lump coal consumption data of last month to calculate last month, step
S22 can also include (as shown in Figure 3):
Step S221 rolls over respectively according to thermal power output monthly of the conversion factor to (not including this month) before this month
It calculates, the thermoelectricity coal consumption monthly before obtaining this month；
In step S221, conversion factor is between 4.1 to 4.3.Preferably, coal 310g/kwh is marked by whole nation power supply, enters factory
4800 kilocalorie of coal mean calorie/kilogram, the two numerical value are basically unchanged in a short time, see net coal consumption rate with technological progress gradually for a long time
Decline, calorific value are influenced by Environmental Factors, consumption coal overall control factor, are gradually increasing, 310/4800*7000=4.52, conversion system
Number is 4.52.Conversion factor is annual per year gradually slightly to be reduced, and is increased with LNG rise in price, Load in Summer height is also to omit
There is increase, coefficient is adjusted within the scope of 4.1-4.3 depending on year, seasonal factor and LNG import price.
Step S222 is counted respectively according to the thermoelectricity coal consumption and total coal consumption monthly of (not including last month) before last month
Calculation obtains the ratio of the total coal consumption of thermoelectricity coal consumption Zhan monthly before last month, is consumed using thermoelectricity of the simple regression function to last month
The ratio of the total coal consumption of coal amount Zhan is predicted；
Step S223, according to the thermoelectricity coal consumption of last month and the ratio of the total coal consumption of thermoelectricity coal consumption Zhan of last month, meter
Calculation obtains total coal consumption of last month.
Optionally, the ratio of the total coal consumption of thermoelectricity coal consumption Zhan of the last month using prediction to total coal consumption of last month into
Before row prediction, needs the ratio to the total coal consumption of thermoelectricity coal consumption Zhan of the last month of prediction to check, only checks successfully,
Total coal consumption could be predicted, just can guarantee the accuracy to subsequent coal price forward prediction in this way, therefore, as shown in figure 3,
Before step S223, further includes:
Step S224, according to the power industry coal consumption and total coal consumption monthly of (not including last month) before last month, respectively
Power industry coal consumption monthly before calculating last month accounts for the ratio of coal total flow, and using simple regression function to last month
The ratio of the total coal consumption of power industry coal consumption Zhan predicted, generate it is of that month before the power industry of (not including this month) consume coal
Measure accounting chart；
Step S225 generates the thermoelectricity coal consumption accounting chart of (not including this month) before this month；
Step S226 compares power industry coal consumption accounting chart and thermoelectricity coal consumption accounting chart, if electric power
The variation tendency of the ratio of the ratio and total coal consumption of thermoelectricity coal consumption Zhan of the total coal consumption of industry coal consumption Zhan is consistent, then check at
Function continues to execute step S223.
It should be noted that the no sequencing of execution of step S224 and step S225, as long as step S224, step
S225 is executed before step S223.
Such as: thermal coal consumption, coking coal consumption and the lump coal consumption data in March, 2019 are generally in April
Last ten-days period publication, when predicting before the last ten-days period in April the following coal price tendency, can not calculate total coal consumption in March, therefore,
Need first to calculate the thermoelectricity coal consumption of (not including April) monthly before in April, 2019, then calculate in March, 2019 with
Before the total coal consumption of thermoelectricity coal consumption Zhan of (not including March) monthly ratio, it is total according to the thermoelectricity coal consumption Zhan calculated
The ratio of coal consumption establishes simple regression function, and according to simple regression function to the total coal consumption of thermoelectricity coal consumption Zhan in March
Ratio predicted, coal is always consumed according to the thermoelectricity coal consumption Zhan in the thermoelectricity coal consumption in the March of calculating and the March of prediction
Total coal consumption in March is calculated in the ratio of amount.In the ratio of the total coal consumption of thermoelectricity coal consumption Zhan in the March using prediction
Before example calculates total coal consumption in March, the power industry consumption coal monthly of (not including March) before March is also calculated
Amount accounts for the ratio of coal total flow, also with simple regression function to the total coal consumption of power industry coal consumption Zhan in March
Ratio predicted, and generate by the end of in March, 2019 power industry coal consumption accounting chart and thermoelectricity coal consumption
Accounting chart compares the variation tendency of the two charts, if consistent just check the thermoelectricity that successfully can use the March of prediction
The ratio of the total coal consumption of coal consumption Zhan predicts total coal consumption in March.
Step S3 extracts the linked character between monthly supply and demand difference table and coal price tendency using the method for correlation rule
Rule generates Association Rules, and the tendency of coal market price is lauched according to Association Rules prediction.
Fig. 4 shows the supply and demand difference table from January, 2015 in March, 2019, and Fig. 5 is shown from 2015 1
Month the trend graph for being lauched coal market price in April, 2019.As shown in Figure 4, Figure 5, step S3 is specifically included: calculating supply and demand
Confidence coefficient between difference data and coal price, if confidence coefficient is greater than 0.8, by the change between supply and demand difference data and coal price
Law is determined as a correlation rule；When supply and demand difference is positive value, coal price drop, the positive value time is longer and numerical value is bigger,
Drop-off range is bigger, the drop time is longer；When supply and demand difference is negative value, coal price goes up, and the negative value time is longer and numerical value is bigger,
Rising range is bigger, the time of going up is longer；When supply and demand difference fluctuates near 0, the equilibrium of supply and demand, coal price is steady；Supply and demand difference
There are 1-2 months time lags between the variation of coal price, the variation of coal price is later than the variation of supply and demand difference；In long-term confession
Need it is unbalance under the premise of, the of short duration equilibrium of supply and demand to unbalance situation improve less, to alleviate coal price extreme case effect can neglect
Slightly disregard.
Optionally, step S3 can also include: to predict in conjunction with cofactor the tendency for being lauched coal market price,
In, cofactor includes manually to short-term market in-mind anticipation, forward market tendency and monthly long association's valence tendency.Wherein, psychological
It is expected that the mainly guidance by events such as some emergency event such as mine disasters for influencing supply and demand in the market, peace green audit rectifications, such as
1.12 Yulin mine disasters, the mine disaster of 2.23 Inner Mongol Xilinguole League can influence the reduction of yield in a short time, lead to market in-mind anticipation valence
Lattice go up, on the restrictive policy of Import Coal also can a degree of influence aggregate supply, cause market generate endure valence psychology；Phase
The tendency in goods market has directive significance to spot price, more closes on prompt day, and futures, spot price more reach unanimity；The beginning of each month
The ups and downs of monthly long association's valence of publication have certain directive significance to market price.
As a kind of optional embodiment of the present embodiment, as shown in fig. 6, can also include: step before step S2
S4, obtains the historical data of supply-demand connection data, and whether judge supply-demand connection data abnormal, if otherwise illustrating, coal supplies number
According to effective, then step S2 can be continued to execute；Wherein, supply-demand connection data first part is Shipping, including coastal coal
Freight index, Huanghua-Shanghai (3-4WDT) freight index；Second part is Automobile Transportation, including Automobile Transportation safety inspection, limit
The policies such as vapour order；Part III is railway transportation, including the main coal railway transporting amount data in the whole nation, maintenance situation.
In this optional embodiment, as long as supply-demand connection data, that is, coal transportation quantity does not have sharp fall, so that it may
Assert that supply-demand connection data are normal, signature coal supply data are effective, can be used for subsequent coal price forward prediction.Such as: if
The same when ring of Coal Transport total amount is no more than year-on-year, the sequential growth rate of 10% or Coal Transport total amount than declining, then sentences
Otherwise the fixed supply-demand connection data determine the supply-demand connection data exception without exception.
As a kind of optional embodiment of the present embodiment, it further includes coal quantity in stock that coal, which supplies data, such as Fig. 6 institute
Show, after step s 3, further includes: step S5 compares each coal inventory figureofmerit with coal market price index is lauched, shape
At each coal inventory figureofmerit and the correlation rule being lauched between coal market price index, prediction is lauched according to the correlation rule
The tendency of coal market price is verified.Specifically, by (coastal, riverine) the total and market price CCI5500 index pair of harbour inventory
Than；Circum-Bohai Sea major port inventory and market price CCI5500 index are compared；By Circum-Bohai Sea major port anchorage ships quantity with
The comparison of market price CCI5500 index；By six big Power Groups (power on, Guangdong electricity, Zhejiang electricity, Huaneng Group, state's electricity, Datang Coastal Power Station)
Field deposit, day consumption, can with number of days and market price CCI5500 index comparison；By national emphasis power plant inventory and market price CCI5500
Index comparison；National emphasis power plant day consumption is compared with thermal power generation figureofmerit；It can be concluded that above data compares to be formed
Data between correlation rule (such as inventory is higher, and rise in price probability is smaller), prediction is lauched further according to the correlation rule
The correctness of the tendency of coal market price is verified.In this optional embodiment, each coal inventory figureofmerit be the place of production, harbour,
The quantity in stock in power plant downstream, including it is Circum-Bohai Sea harbour quantity in stock, riverine harbour quantity in stock, the South China coastal harbour quantity in stock, coastal
The field storage of six big electricity, national emphasis power plant quantity in stock, national some importance coal mine output, emphasis coal mining enterprise yield, emphasis
Region yield, national mining listed corporations inventory, State owned coal mine inventory, the safe and environment-friendly inspection in main producing region etc. influence yield
Or the policy situation of inventory.
In the present embodiment, the executing subject of above steps is the device with computing capability, such as PC machine, mobile phone, flat
Plate computer etc. is not specifically limited this present embodiment.Coal supply data, coal demand data, supply-demand connection data etc. are gone through
The acquisition modes of history data can be directly from network, database downloading, be also possible to carry out by modes such as keyboard, touch screens defeated
Enter, can also be that wirelessly (such as bluetooth, infrared etc.) carries out data transmission, and does not do specific limit to this present embodiment
It is fixed.
Principle based on the demand-supply relation, relation between supply and demand are to influence the main and most direct factor of coal price.?
In the method for predicting following coal price tendency by the relationship of analysis supply and demand data and coal price index, various Supply and Demands
Data target is the basis of research prediction coal price tendency at all, and algorithm and mathematical model are means, for screening valid data
And verify the correlation degree of itself and coal price variation.On the one hand, with the continuous application of information technology and big data technology, coal is influenced
The index and coal price index Various types of data of charcoal supply and demand can be obtained by internet or other channels, the accuracy of data source and
Therefore reliability also available guarantee is to have data base carrying out the research of Prediction of Coal Price at this stage from the point of view of data source
Plinth.On the other hand, feature selecting and association rule mining can be carried out to data, obtained by some simple mathematical models
The correlation rule of coal price must be influenced, therefore, from the point of view of analyzing from data, carrying out prediction to coal price using suitable model is to have
Fundamentals of Mathematics.At this stage by the Association Rule Analysis to data, it can be found that between some data variations and coal price variation
Rule.And by the continuous screening to numerous historical datas, it can be found that more suchlike correlation rules, thus comprehensive
Close influence of the analysis to coal price trend.It is this to carry out systematic prediction from the various main indicators of relation between supply and demand, particularly with the addition of
The prediction of supply and demand index Future Data, then coal price is analyzed, there is not correlative study also.
The present embodiment the method collects coal supply, the influence of demand and supply-demand connection by starting with from relation between supply and demand
Factor and historical data；The data of collection are analyzed and processed using three kinds of Mathematical Methods, first is that comparison different data
Tendency, extract data between correlation rule；Second is that using simple regression function, according to historical data to various generated energy,
The successor value that monthly coal production, monthly import series, thermal power output account for the data such as the ratio of coal total flow is predicted；
Third is that calculating the monthly overall supplies of coal and total coal consumption, the supply and demand difference table of coal is formed；Using the method for correlation rule, mention
Take the linked character rule between the supply and demand difference table and coal price tendency；The linked character extracted using difference table, in conjunction with it
The predicted value of Association Rules, simple regression function that his data are extracted, then manually to emergency event such as mine disaster, peace green audit
Rectify etc. can influence guidance of the event to short-term market in-mind anticipation of supply and demand, forward market tendency, monthly long association's valence tendency add
With assistant analysis, the subsequent forward prediction for being lauched coal market price is obtained.This method is directed to the pricing model of coal price at this stage,
Start with from the angle of relation between supply and demand, combing influences the index of supply, demand, collects corresponding historical data, utilizes correlation rule, one
Three kinds of methods of first regression function and supply and demand differential analysis carry out comprehensive analysis to the data of all kinds of supply and demand indexs, in conjunction with short-term city
The other factors such as field in-mind anticipation, forward market tendency carry out Accurate Prediction, Jin Ergeng to the subsequent tendency for being lauched coal market price
Effective optimization Coal Procurement opportunity adjusts with maximum into texture of coal, reduces purchase cost.
These are only the preferred embodiment of the present invention, is not intended to restrict the invention, for those skilled in the art
For member, the invention may be variously modified and varied.It is all within creativeness spirit of the invention and principle, it is made any
Modification, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (9)
1. a kind of be lauched Prediction of Coal Price method based on relation between supply and demand big data, which comprises the following steps:
Step S1 obtains coal supply data and coal demand data, wherein the coal supply data include coal production and
Coal import volume, the coal demand data include generated energy and coal consumption；
Step S2 supplies data according to the coal and the coal demand data calculates monthly overall supplies and monthly total consumption coal
Amount, generates the monthly supply and demand difference table of coal；
Step S3 extracts the linked character between the monthly supply and demand difference table and coal price tendency using the method for correlation rule
Rule generates Association Rules, and the tendency of coal market price is lauched according to Association Rules prediction.
2. according to claim 1 be lauched Prediction of Coal Price method based on relation between supply and demand big data, which is characterized in that in institute
Before stating step S2, further includes:
Step S4 obtains supply-demand connection data, and whether judge the supply-demand connection data abnormal, if otherwise continuing to execute described
Step S2；Wherein, the supply-demand connection data include Shipping amount and total volume of railway freight.
3. according to claim 2 be lauched Prediction of Coal Price method based on relation between supply and demand big data, which is characterized in that described
Judge in step S4 the supply-demand connection data whether include: extremely
If the same when ring of Coal Transport total amount is no more than 10% or the year-on-year of Coal Transport total amount, ring ratio increasing than declining
It is long, then determine that the supply-demand connection data without exception, otherwise determine the supply-demand connection data exception.
4. according to any one of claims 1 to 3 be lauched Prediction of Coal Price method, feature based on relation between supply and demand big data
It is, the step S2 is specifically included:
Coal production monthly is added by step S21 with coal import volume respectively, and the monthly overall supplies is calculated；
Thermal coal consumption, coking coal consumption monthly is added with lump coal consumption by step S22 respectively, is calculated described
Monthly total coal consumption；
The monthly overall supplies is subtracted monthly total coal consumption by step S23, obtains supply and demand difference monthly, generates coal
The monthly supply and demand difference table of charcoal.
5. according to claim 4 be lauched Prediction of Coal Price method based on relation between supply and demand big data, which is characterized in that if
The thermal coal consumption, coking coal consumption and lump coal consumption data of last month can not be obtained in preset time, to calculate last month
Total coal consumption, then the step S22 further include:
Step S221 converts the thermal power output monthly before this month according to conversion factor, respectively before obtaining this month
Thermoelectricity coal consumption monthly；
Step S222, it is every before calculating separately to obtain last month according to the thermoelectricity coal consumption and total coal consumption monthly before last month
Month the total coal consumption of thermoelectricity coal consumption Zhan ratio, using simple regression function to the total coal consumption of thermoelectricity coal consumption Zhan of last month
Ratio is predicted；
Step S223 is calculated according to the thermoelectricity coal consumption of last month and the ratio of the total coal consumption of thermoelectricity coal consumption Zhan of last month
To total coal consumption of last month.
6. according to claim 5 be lauched Prediction of Coal Price method based on relation between supply and demand big data, which is characterized in that in institute
Before stating step S223, further includes:
Step S224 was calculated separately before last month monthly according to the power industry coal consumption and total coal consumption monthly before last month
Power industry coal consumption account for the ratio of coal total flow, and using simple regression function to the power industry coal consumption of last month
The ratio of the total coal consumption of Zhan predicted, generate it is of that month before power industry coal consumption accounting chart；
Step S225, the thermoelectricity coal consumption accounting chart before generating this month；
Step S226 compares the power industry coal consumption accounting chart and the thermoelectricity coal consumption accounting chart, if
The variation tendency of the ratio of the ratio and total coal consumption of thermoelectricity coal consumption Zhan of the total coal consumption of power industry coal consumption Zhan is consistent, then school
Core success, continues to execute the step S223.
7. according to any one of claims 1 to 6 be lauched Prediction of Coal Price method, feature based on relation between supply and demand big data
It is, the step S3 is specifically included: the confidence coefficient between supply and demand difference data and coal price is calculated, if confidence coefficient is greater than
0.8, then the changing rule between supply and demand difference data and coal price is determined as a correlation rule；When supply and demand difference is positive value
When, coal price drop, the positive value time is longer and numerical value is bigger, and drop-off range is bigger, the drop time is longer；When supply and demand difference is negative value
When, coal price goes up, and the negative value time is longer and numerical value is bigger, and rising range is bigger, the time of going up is longer；Supply and demand difference and coal price
There are 1-2 months time lags between variation, the variation of coal price is later than the variation of supply and demand difference.
8. according to any one of claims 1 to 7 be lauched Prediction of Coal Price method, feature based on relation between supply and demand big data
It is, the step S3 further include: the tendency for being lauched coal market price is predicted in conjunction with cofactor, wherein the auxiliary
Factor includes manually to short-term market in-mind anticipation, forward market tendency and monthly long association's valence tendency.
9. according to any one of claims 1 to 8 be lauched Prediction of Coal Price method, feature based on relation between supply and demand big data
It is, the coal supply data further include that the coal quantity in stock of entrepot and power plant also wraps after the step S3
It includes:
Step S5, by Circum-Bohai Sea harbour quantity in stock, coastal riverine harbour inventory figureofmerit, national emphasis power plant inventory, coastal six
Big electric field is deposited index and is compared with coal market price index is lauched, and forms each coal inventory figureofmerit and is lauched coal market price index
Between correlation rule, verified according to the tendency that is lauched coal market price of the correlation rule to prediction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910323587.2A CN110070225B (en) | 2019-04-22 | 2019-04-22 | Launching coal price prediction method based on big data of supply and demand relationship |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910323587.2A CN110070225B (en) | 2019-04-22 | 2019-04-22 | Launching coal price prediction method based on big data of supply and demand relationship |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110070225A true CN110070225A (en) | 2019-07-30 |
| CN110070225B CN110070225B (en) | 2021-05-18 |
Family
ID=67368399
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910323587.2A Expired - Fee Related CN110070225B (en) | 2019-04-22 | 2019-04-22 | Launching coal price prediction method based on big data of supply and demand relationship |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110070225B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111563774A (en) * | 2020-05-08 | 2020-08-21 | 上海腾暨物联网科技有限公司 | Method and system for constructing coal price index prediction and supply-demand relation index |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104200285A (en) * | 2014-09-09 | 2014-12-10 | 国家电网公司 | Optimization method for mixed fire coal blending in power plant |
| CN107301477A (en) * | 2017-06-22 | 2017-10-27 | 湖南华润电力鲤鱼江有限公司 | A kind of coal-fired procurement decisions method based on many coal coal mixing combustion optimizing models |
| CN107808233A (en) * | 2017-09-29 | 2018-03-16 | 广东电力交易中心有限责任公司 | Long-term cost benefit measuring method in generating set under the environment of spot market |
| US10127568B2 (en) * | 2011-04-04 | 2018-11-13 | The Catholic University Of America | Systems and methods for improving the accuracy of day-ahead load forecasts on an electric utility grid |
-
2019
- 2019-04-22 CN CN201910323587.2A patent/CN110070225B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10127568B2 (en) * | 2011-04-04 | 2018-11-13 | The Catholic University Of America | Systems and methods for improving the accuracy of day-ahead load forecasts on an electric utility grid |
| CN104200285A (en) * | 2014-09-09 | 2014-12-10 | 国家电网公司 | Optimization method for mixed fire coal blending in power plant |
| CN107301477A (en) * | 2017-06-22 | 2017-10-27 | 湖南华润电力鲤鱼江有限公司 | A kind of coal-fired procurement decisions method based on many coal coal mixing combustion optimizing models |
| CN107808233A (en) * | 2017-09-29 | 2018-03-16 | 广东电力交易中心有限责任公司 | Long-term cost benefit measuring method in generating set under the environment of spot market |
Non-Patent Citations (1)
| Title |
|---|
| 赵卫: "电煤价格影响因素及预测分析", 《发电技术》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111563774A (en) * | 2020-05-08 | 2020-08-21 | 上海腾暨物联网科技有限公司 | Method and system for constructing coal price index prediction and supply-demand relation index |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110070225B (en) | 2021-05-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Nikoobakht et al. | Assessing increased flexibility of energy storage and demand response to accommodate a high penetration of renewable energy sources | |
| Hilorme et al. | Smart grid concept as a perspective for the development of Ukrainian energy platform | |
| Muneer et al. | Large-scale solar PV investment models, tools, and analysis: The Ontario case | |
| Henriques et al. | Employment impact assessment of renewable energy targets for electricity generation by 2020—An IO LCA approach | |
| Wu et al. | Optimal investment selection of industrial and commercial rooftop distributed PV project based on combination weights and cloud-TODIM model from SMEs’ perspectives | |
| JP4435101B2 (en) | Design evaluation method for small-scale power system | |
| Vykhodtsev et al. | A review of modelling approaches to characterize lithium-ion battery energy storage systems in techno-economic analyses of power systems | |
| JP5248372B2 (en) | Power generation plan creation method, device, program, and storage device | |
| Vonsien et al. | Li-ion battery storage in private households with PV systems: Analyzing the economic impacts of battery aging and pooling | |
| CN109193748B (en) | Evaluation method and computing device for photovoltaic absorption capacity | |
| Wilkerson et al. | Survey of Western US electric utility resource plans | |
| WO2009103020A2 (en) | Renewable energy delivery systems and methods | |
| Sauhats et al. | Optimal investment and operational planning of a storage power plant | |
| Matute et al. | Optimal dispatch model for PV-electrolysis plants in self-consumption regime to produce green hydrogen: A Spanish case study | |
| CN104091293B (en) | The power network long-term load characteristic prediction method changed based on power structure | |
| Di Cosmo et al. | Wind, storage, interconnection and the cost of electricity generation | |
| Yang et al. | Intertemporal optimization of the coal production capacity in China in terms of uncertain demand, economy, environment, and energy security | |
| US20110137574A1 (en) | Graphical Technique for Visualizing Effects of Environmental Emission Reductions | |
| Emblemsvåg | On the levelised cost of energy of solar photovoltaics | |
| CN110070225A (en) | It is a kind of that Prediction of Coal Price method is lauched based on relation between supply and demand big data | |
| Helman et al. | Development of long-duration energy storage projects in electric power systems in the United States: A survey of factors which are shaping the market | |
| Xu et al. | CVaR‐based method for optimizing the contract bidding strategy of PV power stations | |
| CN116823008A (en) | Park energy utilization efficiency evaluation method, system, equipment and storage medium | |
| JP2020058141A (en) | Power storage facility management device and power storage facility management method | |
| Busch et al. | Estimation of avoided costs for electric utility demand-side planning |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210518 |