CN110070203B - Water supply quantity prediction method, system, device and storage medium - Google Patents
Water supply quantity prediction method, system, device and storage medium Download PDFInfo
- Publication number
- CN110070203B CN110070203B CN201910139355.1A CN201910139355A CN110070203B CN 110070203 B CN110070203 B CN 110070203B CN 201910139355 A CN201910139355 A CN 201910139355A CN 110070203 B CN110070203 B CN 110070203B
- Authority
- CN
- China
- Prior art keywords
- interval
- temperature
- regression
- water supply
- intervals
- 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.)
- Active
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 129
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000012216 screening Methods 0.000 claims description 36
- 238000007477 logistic regression Methods 0.000 claims description 35
- 238000012417 linear regression Methods 0.000 claims description 23
- 230000008569 process Effects 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000001419 dependent effect Effects 0.000 claims description 5
- 230000001788 irregular Effects 0.000 claims description 5
- 238000012935 Averaging Methods 0.000 claims description 3
- 230000000875 corresponding effect Effects 0.000 description 70
- 230000002354 daily effect Effects 0.000 description 19
- 238000000611 regression analysis Methods 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 7
- 230000009286 beneficial effect Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000005192 partition Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000012163 sequencing technique Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000009172 bursting Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000013524 data verification Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- RAYLUPYCGGKXQO-UHFFFAOYSA-N n,n-dimethylacetamide;hydrate Chemical compound O.CN(C)C(C)=O RAYLUPYCGGKXQO-UHFFFAOYSA-N 0.000 description 1
- 230000001373 regressive effect Effects 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
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
- 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)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a water supply quantity prediction method, a system, a device and a storage medium, wherein the method comprises the following steps: carrying out service characteristic matching processing according to service characteristics to obtain a first interval corresponding to the service characteristics; performing temperature matching treatment according to the temperature to obtain a second interval corresponding to the temperature from the obtained first interval; and obtaining an interval algorithm model corresponding to the obtained second interval, and inputting the temperature and/or the meteorological factors into the obtained interval algorithm model, so as to calculate the predicted water supply amount. By using the method and the system, a more scientific and reasonable algorithm model can be obtained according to the service characteristics, so that the predicted water supply amount can be calculated easily, and the predicted water supply amount is more accurate. The water supply quantity prediction method, the system, the device and the storage medium can be widely applied to the field of computer-aided application.
Description
Technical Field
The present invention relates to the field of computer-aided application, and in particular, to a water supply amount prediction method, system, device, and storage medium.
Background
Generally, the hotter the weather, the more water is used and the colder the water is used. When a production department of a water supply enterprise makes a water supply plan, a daily scheduling scheme needs to predict the water quantity according to air temperature forecast, which is a common practice. In addition, other factors in the weather may have an effect on the water content. In addition to the prediction of the overall water volume of the scheduling scheme, in the zone metering DMA, if the calculated water volume is obviously inconsistent with the actual water volume, the water consumption of the zone is abnormal.
However, the relationship between the air temperature and the water quantity is not fixed, and through the data verification of the extreme cases, the two are not greatly correlated in general, but only have dependency correlation in case of exceeding certain extreme cases, so that a clear dependency relationship between the two should have a section. In addition, the dependency relationship is different among areas and partitions due to different demographics and city layouts. The problem is that a computer is used to perform the operation when the scheduling scheme is performed or the DMA water amount is evaluated every day, so that the dependence relationship can only be given to the extreme situation, and the operation is manually incorporated when the extreme situation is judged, which is not helpful for automatically realizing the calculation. There is therefore a need for a way to include both manual marking of special dates and specific data for the day (including temperature, weather factors, water supply, etc.), and then use the regression model inherent in this way to predict water supply. Even in special situations, such as spring festival, middle and long-term holidays, and special large activities occurring each year, the water supply amount may be associated with meteorological factors in these situations.
Regression analysis is the most common method of analyzing the relationship between meteorological factors and water usage. However, it is not known which regression analysis is best to use, since there are too many complications here. Therefore, the common method is generally to analyze in some typical local intervals, such as the case of the average temperature of 20 degrees or more in Shanghai city, the case of the exclusion of indoor heating in winter in western security city, and then select a regression model for analysis.
The existing regression analysis model mainly comprises: when the dependent variable is not the same (such as water volume increase/decrease is used as the dependent variable), adopting a logistic regression algorithm for analysis; when the variables show linear relation, adopting linear regression algorithm analysis; if the variables do not have a linear relation, but have a high-order characteristic (only two orders are generally calculated on the water quantity relation), a polynomial regression algorithm is adopted for analysis; for the combined action of multiple factors, stepwise regression algorithm analysis was employed. However, the existing means do not consider the influence of water supply business characteristics on the water supply amount, so that the prediction accuracy is low.
Disclosure of Invention
In order to solve the technical problems, an object of the present invention is to provide a water supply amount prediction method, a system, a device and a storage medium.
In one aspect, the present invention provides a water supply amount prediction method, comprising the steps of:
carrying out service characteristic matching processing according to service characteristics to obtain a first interval corresponding to the service characteristics;
performing temperature matching treatment according to the temperature to obtain a second interval corresponding to the temperature from the obtained first interval;
and obtaining an interval algorithm model corresponding to the obtained second interval, and inputting the temperature and/or the meteorological factors into the obtained interval algorithm model, so as to calculate the predicted water supply amount.
Further, the step of performing service characteristic matching processing according to the service characteristic to obtain a first interval corresponding to the service characteristic specifically includes:
according to the service characteristics, matching and screening first intervals corresponding to the service characteristics from a plurality of first intervals which are divided in advance;
the first intervals divided in advance are intervals divided in the time interval where the service characteristics of the historical water supply data are located, and the first intervals are in one-to-one correspondence with the service characteristics.
Further, the step of performing a temperature matching process according to a temperature to obtain a second interval corresponding to the temperature from the obtained first interval specifically includes:
obtaining a plurality of pre-divided second intervals from the obtained first intervals, wherein the plurality of second intervals are contained in the first intervals;
according to the temperature, matching and screening out a second interval in which the temperature falls from a plurality of obtained second intervals which are divided in advance;
the plurality of pre-divided second intervals are obtained by performing interval screening and dividing treatment according to the relation between the temperature and the water supply of the historical water supply data or the relation between the temperature and the weather factor and the water supply;
the step of the interval screening and dividing process specifically comprises the following steps: and respectively obtaining a temperature interval corresponding to each first interval, taking the temperature interval corresponding to the first interval as a logistic regression interval when the temperature interval corresponding to the first interval meets a logistic regression condition, and calculating to obtain a regression algorithm model corresponding to the logistic regression interval, wherein the logistic regression interval is included in the second interval.
Further, the step of the interval screening and dividing process further includes:
and selecting a temperature interval meeting the linear regression condition from the first temperature interval as a linear regression interval, and calculating to obtain a regression algorithm model corresponding to the linear regression interval, wherein the first temperature interval is the rest interval after the temperature interval corresponding to the first interval is selected, and the linear regression interval is included in the second interval.
Further, the step of the interval screening and dividing process further includes:
and selecting a temperature interval meeting a quadratic polynomial regression condition from the first temperature interval as a quadratic polynomial regression interval, and calculating to obtain a regression algorithm model corresponding to the quadratic polynomial regression interval, wherein the first temperature interval is the rest interval after the temperature interval corresponding to the first interval is screened, and the quadratic polynomial regression interval is contained in the second interval.
Further, the step of the interval screening and dividing process further includes:
screening a temperature interval meeting weather factor stepwise regression conditions from a first temperature interval as a stepwise regression interval, and calculating to obtain a regression algorithm model corresponding to the stepwise regression interval, wherein the first temperature interval is the rest interval of the temperature interval corresponding to the first interval after screening;
the historical water supply amount data in the stepwise regression interval satisfies a stepwise regression equation, the stepwise regression interval being included in the second interval, the stepwise regression equation being: the independent variable is temperature, the dependent variable is water supply, and the variables introduced one by one are weather factors;
and taking the remaining interval after the temperature interval corresponding to the historical water supply amount data is screened as an unpredictable interval, wherein the unpredictable interval is contained in the second interval.
Further, the step of obtaining the section algorithm model corresponding to the obtained second section, and inputting the temperature and/or the meteorological factor into the obtained section algorithm model, so as to calculate the predicted water supply amount, includes the following specific steps:
when the acquired second interval does not belong to the unpredictable interval, carrying out regression judgment processing;
the regression judgment process specifically comprises the following steps: judging whether the acquired second interval is a stepwise regression interval, if so, acquiring a regression algorithm model corresponding to the stepwise regression interval, and inputting the temperature and the relevant weather factors in the weather factors into the acquired regression algorithm model by combining the relevant weather factors related to the acquired regression algorithm model, so as to calculate and acquire the predicted water supply; otherwise, acquiring a regression algorithm model corresponding to the second interval, and inputting the temperature into the acquired regression algorithm model, so as to calculate and obtain the predicted water supply quantity.
In another aspect, the present invention provides a water supply amount prediction system, comprising:
the first interval acquisition module is used for carrying out service characteristic matching processing according to service characteristics to obtain a first interval corresponding to the service characteristics;
the second interval acquisition module is used for carrying out temperature matching processing according to the temperature so as to acquire a second interval corresponding to the temperature from the acquired first interval;
and the calculation module is used for obtaining the interval algorithm model corresponding to the obtained second interval and inputting the temperature and/or the meteorological factors into the obtained interval algorithm model so as to calculate the predicted water supply.
On the other hand, the invention also provides a water supply quantity prediction device, which comprises:
at least one processor;
at least one memory for storing at least one program;
when the at least one program is executed by the at least one processor, the at least one processor is caused to implement the one water supply amount prediction method.
In another aspect, the present invention also provides a storage medium having stored therein processor-executable instructions which, when executed by a processor, are for performing the one water supply amount prediction method.
The beneficial effects of the invention are as follows: according to the invention, the first interval corresponding to the service characteristic is matched according to the service characteristic, and the second interval corresponding to the temperature is obtained from the first interval according to the temperature, so that an interval algorithm model of the second interval is obtained, and finally the temperature and/or weather factors are input into the interval algorithm model for calculation, so that the predicted water supply quantity is finally obtained, the water supply quantity can be classified and predicted according to the service characteristic, and the method has the advantages of more pertinence and high accuracy.
Drawings
Fig. 1 is a flowchart showing steps of a water supply amount prediction method provided by an embodiment of the present invention;
fig. 2 is a block diagram showing a configuration of a water supply amount prediction system according to an embodiment of the present invention.
Detailed Description
The invention will now be described in further detail with reference to the drawings and to specific examples. The step numbers in the following embodiments are set for convenience of illustration only, and the order between the steps is not limited in any way, and the execution order of the steps in the embodiments may be adaptively adjusted according to the understanding of those skilled in the art.
As shown in fig. 1, an embodiment of the present invention provides a water supply amount prediction method including the steps of:
s101, carrying out service characteristic matching processing according to service characteristics to obtain a first interval corresponding to the service characteristics;
specifically, a first interval corresponding to the service characteristic is found out according to the service characteristic, wherein the service characteristic comprises: the date when the business problem occurs (for example, the meter fault data is wrong, the unauthorized water with large flow is found, etc.), the day when the irregular large-scale event occurs (for example, large-scale sports activities are held, the public (or regional) sanitary inspection is carried out, etc.), the day when the regular large-scale event occurs (for example, the pool washing and the yield is reduced in a water plant, large-scale pipe network engineering, pipe bursting or valve adjustment with large influence on the water supply pattern is carried out, etc.), holidays, double holidays and daily, wherein the first intervals are time intervals in days, namely, intervals in which the days are located, and each first interval is provided with a business characteristic label corresponding to the first interval.
S102, performing temperature matching processing according to the temperature to obtain a second interval corresponding to the temperature from the obtained first interval;
specifically, the second interval is a temperature interval, the temperature is a daily average temperature, each day has a daily average temperature and a date, so the first interval may include a plurality of second intervals (for example, the first interval corresponding to the business characteristics of daily life may include a plurality of intervals of 0-3 ℃, 3-7 ℃, 10-15 ℃, 20-26 ℃, wherein each interval is a second interval, and if the business characteristics of the day to be predicted are daily, the daily average temperature is 15 ℃, the matched second interval is the temperature interval of 10-15 ℃).
S103, obtaining an interval algorithm model corresponding to the obtained second interval, and inputting temperature and/or meteorological factors into the obtained interval algorithm model, so as to calculate predicted water supply quantity;
specifically, the second interval is a temperature interval, including: the method comprises the following steps of logic regression section, linear regression section, quadratic polynomial regression section, stepwise regression section, unpredictable section and the like, wherein the second sections of each type are different, and the second sections are different, and the corresponding section algorithms are possibly different, so that each second section has a corresponding section algorithm model, the section algorithm model is a regression function, and the regression function is a function of water supply quantity relative to temperature, and comprises: types such as a logistic regression algorithm model, a linear regression algorithm model, a quadratic polynomial regression algorithm model and a meteorological factor stepwise regression algorithm model (in the meteorological factor stepwise regression algorithm model, an independent variable is a temperature, an independent variable is a water supply amount, and variables which are introduced one by one are meteorological factors), etc., the predicted water supply amount can be obtained by inputting the temperature into the logistic regression algorithm model, the linear regression algorithm model and the quadratic polynomial regression algorithm model, and the predicted water supply amount can be obtained by inputting the temperature and the meteorological factors into the meteorological factor stepwise regression algorithm model, wherein the meteorological factors comprise: barometric pressure, humidity, climate, wind, etc.
According to the method, the water supply quantity can be classified and predicted according to the service characteristics, the relationship between the temperature and the water supply quantity is more regressive under the condition of the same service characteristics, and meanwhile, the influence of different service characteristics on the water supply quantity is eliminated, so that the prediction is more targeted, and the water supply quantity prediction is more accurate.
Further as a preferred embodiment of the present method, the step S101 of performing service characteristic matching processing according to a service characteristic to obtain a first interval corresponding to the service characteristic specifically includes:
s1011, according to service characteristics, matching and screening out first intervals corresponding to the service characteristics from a plurality of first intervals which are divided in advance;
s1012, dividing a plurality of first intervals into a plurality of intervals in a time interval in which the service characteristics of the historical water supply data are located, wherein the first intervals are in one-to-one correspondence with the service characteristics;
specifically, each first interval corresponds to a service characteristic, for example: the first interval corresponding to the business attribute of holidays comprises a time interval of 2 months, 4 days, 2 months and 10 days, the first interval corresponding to the business attribute of holidays comprises time intervals of 2 months, 16 days, 2 months, 17 days, 2 months, 23 days, 2 months, 24 days, 3 months, 2 days, 3 days, and if the predicted day is 3 months, the first interval can be obtained according to the business characteristics of holidays. Different business characteristics cannot be mixed together to perform regression analysis, and even if the regression analysis is performed, the rule is obviously wrong. The sequential logic that divides the first interval may be: firstly, dividing a first interval corresponding to a business characteristic of a date generating a business problem, wherein when the business problem occurs, no matter whether the business problem is a subsequent condition or not, the water consumption of the date can be greatly and sporadically influenced, so the classification is mainly to exclude regressible cases because analysis is not meaningful (for example, the data of a certain DMA (partition metering) partition on the same day is not included in calculation); then dividing a first interval corresponding to the business characteristic of the occurrence day of the irregular large-scale event, wherein the water quantity is greatly influenced by the irregular large-scale event, and the situation is possibly similar to the occurrence of the event in the future as a quantifiable influence; then dividing a first interval corresponding to the service characteristic of the occurrence day of the conventional large event, wherein the conventional large event has reference significance, because the events such as engineering, pipe explosion and the like are frequently occurred, the water quantity change can be predicted in the occurrence day of the events; then dividing the holiday, wherein the holiday usually comprises a double holiday, so that the holiday is divided firstly, and the continuity relationship between the double holiday and the holiday is eliminated; then dividing a first interval corresponding to the business characteristic of double holidays, wherein the water consumption of the double holidays has obvious difference in area, so that the analysis cannot be performed as a daily condition; the first interval corresponding to the last remaining date corresponds to the daily business characteristic.
By the method, the first interval and the service characteristic can be in one-to-one correspondence, so that the prediction is more targeted, scientific and reasonable, and practical significance is achieved.
Further as a preferred embodiment of the method, the step S102 of performing a temperature matching process according to a temperature to obtain a second interval corresponding to the temperature from the obtained first interval specifically includes:
s1021, obtaining a plurality of pre-divided second sections from the obtained first sections, wherein the plurality of second sections are contained in the first section;
s1022, according to the temperature, matching and screening out a second interval in which the temperature falls from a plurality of obtained second intervals which are divided in advance;
specifically, for example, the business characteristics are that three second intervals of 3-10 ℃, 10-15 ℃ and 15-18 ℃ exist in a first interval of daily life, the business characteristics of the prediction day are that the temperature is 12 ℃, the judgment shows that 12 is more than 10 and less than 15, the second interval in which 12 falls is 10-15 ℃, and the temperatures are all daily average temperatures.
S1023, the plurality of pre-divided second sections are a plurality of sections obtained by section screening and dividing treatment according to the relation between the temperature and the water supply of the historical water supply data or the relation between the temperature and the weather factor and the water supply;
specifically, the division manner adopted when dividing the logistic regression interval, the linear regression interval and the quadratic polynomial regression interval is as follows: different sections are divided according to the relation between the daily average temperature of the historical water supply data and the water supply, and the dividing mode adopted when dividing stepwise regression sections is to divide sections capable of performing stepwise regression analysis of meteorological factors according to the relation between the daily average temperature of the historical water supply data and the water supply and the meteorological factors.
The step S1023 of the interval screening and dividing process specifically includes:
s10231, respectively obtaining a temperature interval corresponding to each first interval, taking the temperature interval corresponding to the first interval as a logistic regression interval when the temperature interval corresponding to the first interval meets a logistic regression condition, and calculating to obtain a regression algorithm model corresponding to the logistic regression interval, wherein the logistic regression interval is included in a second interval;
specifically, logistic regression screening is performed on the first interval, and whether the temperature interval corresponding to the first interval can be logistic regression is judged, which may be specifically: a1, averaging the water supply amount of the historical water supply amount data in the first interval; a2, dividing the data into two parts according to the water supply quantity which is larger than the average value and smaller than the average value; a3, calculating the ratio (standard deviation coefficient) of the standard deviation to the mean value in the two parts respectively; and a4, if the ratio is smaller than a certain threshold (for example, 5%, the specific numerical value can be adjusted according to the actual situation), the part can be subjected to logistic regression, the temperature interval corresponding to the part is used as a logistic regression interval, and otherwise, the logistic regression is not suitable.
Further as a preferred embodiment of the method, the section filtering and dividing process S1023 further includes:
s10232, screening a temperature interval meeting a linear regression condition from a first temperature interval as a linear regression interval, and calculating to obtain a regression algorithm model corresponding to the linear regression interval, wherein the first temperature interval is a residual interval after the temperature interval corresponding to the first interval is screened, and the linear regression interval is contained in a second interval;
specifically, linear regression screening is performed on the first section after screening, and whether the temperature section corresponding to the first section at this time meets the linear regression condition is judged, which may be specifically: b1, sequencing the first intervals at the moment according to the temperature, and sequentially and continuously taking the number of the sequenced first intervals by using a window with the width of 5; b2, calculating a correlation coefficient of the temperature and the water supply amount of the data in the window; b3, if the absolute value of the correlation coefficient is smaller than the standard correlation coefficient (for example, 0.85), shifting the window by one bit until the absolute value of the calculated correlation coefficient is larger than the standard correlation coefficient; b4, if the first partition is not found all the time, the first partition is not suitable for linear regression; b5, if the absolute value of the correlation coefficient is larger than the standard correlation coefficient, expanding the window by 1 bit backwards, and calculating the correlation coefficient of the window; b6, if the absolute value of the correlation coefficient is larger than the standard correlation coefficient, continuing to expand the window until the absolute value of the correlation coefficient is smaller than the standard correlation coefficient, retracting the window by 1 bit at the moment, and setting the window as a second interval serving as a linear regression interval; and b7, creating a window with the width of 5 from the lower boundary of the interval, and continuing the steps b2-b7 until the end of the first interval (wherein the specific values of the window width and the standard correlation coefficient can be adjusted according to actual conditions), and the temperatures are all daily average temperatures.
By the method, the second interval can be divided again on the basis of the first interval, so that the interval division is more reasonable and has practical significance.
Further as a preferred embodiment of the method, the section filtering and dividing process S1023 further includes:
s10233, selecting a temperature interval meeting a quadratic polynomial regression condition from a first temperature interval as a quadratic polynomial regression interval, and calculating to obtain a regression algorithm model corresponding to the quadratic polynomial regression interval, wherein the first temperature interval is a residual interval after the temperature interval corresponding to the first interval is screened, and the quadratic polynomial regression interval is contained in a second interval;
specifically, a second polynomial regression screening is performed on the first section after the screening, and whether the temperature section corresponding to the first section at this time meets the second polynomial regression condition is determined, which may be specifically: c1, sequencing the first interval at the moment according to the temperature; c2, if the width of the first interval is smaller than 5, performing quadratic polynomial regression on the whole interval, and calculating a standard deviation coefficient; if the standard deviation coefficient is smaller than the standard deviation coefficient threshold (such as 10%), the temperature interval corresponding to the first interval at the moment is a second interval serving as a quadratic polynomial regression interval; c4, if the width of the first interval is larger than 5, creating a window with the width of 5, performing quadratic polynomial regression in the window, and calculating a standard deviation coefficient; c5, if the standard deviation coefficient is larger than the standard deviation coefficient threshold, moving the window backwards by 1 bit, returning again, and calculating the standard deviation coefficient until the standard deviation coefficient is smaller than the standard deviation coefficient threshold; c6, when the standard deviation coefficient is smaller than the standard deviation coefficient threshold, expanding the window backwards by 1 bit, carrying out quadratic polynomial regression and calculating the standard deviation coefficient until the standard deviation coefficient is larger than the standard deviation coefficient threshold, retracting the window by 1 bit, and enabling the range of the window to be suitable for the interval of quadratic polynomial regression; and c7, starting from the lower boundary of the window, if the width of the subsequent interval is smaller than 5, executing the steps c1-c3, and if the width of the subsequent interval is larger than 5, executing the steps c4-c7, and repeating until the end of the first interval (wherein specific values of the window width and the standard deviation coefficient threshold value can be adjusted according to actual conditions), wherein the temperatures are all daily average temperatures. The regression analysis can be more detailed and specific by adding the quadratic polynomial regression interval, and the method has more practical significance.
Further as a preferred embodiment of the method, the section filtering and dividing process S1023 further includes:
s10234, screening a temperature interval meeting weather factor stepwise regression conditions from a first temperature interval as a stepwise regression interval, and calculating to obtain a regression algorithm model corresponding to the stepwise regression interval, wherein the first temperature interval is the rest interval of the screened temperature interval corresponding to the first interval;
specifically, weather factor stepwise regression screening is performed on the first section after screening, and whether the temperature section corresponding to the first section at this time meets the weather factor stepwise regression condition is judged, which may be specifically: d1, sequencing the first interval at the moment according to the temperature; d2, if the width of the first interval is smaller than 5, gradually regressing meteorological factors on the whole interval, and calculating a standard deviation coefficient; d3, if the standard deviation coefficient is smaller than the standard deviation coefficient threshold (such as 10%), the temperature interval corresponding to the first interval at the moment is a second interval which is a weather factor stepwise regression interval; d4, if the width of the first interval is larger than 5, creating a window with the width of 5, performing weather factor stepwise regression in the window, and calculating a standard deviation coefficient; d5, if the standard deviation coefficient is larger than the standard deviation coefficient threshold, moving the window backwards by 1 bit, performing weather factor stepwise regression again, and calculating the standard deviation coefficient until the standard deviation coefficient is smaller than the standard deviation coefficient threshold; d6, when the standard deviation coefficient is smaller than the standard deviation coefficient threshold, expanding the window backwards by 1 bit, carrying out stepwise regression on the meteorological factors, and calculating the standard deviation coefficient until the standard deviation coefficient is larger than the standard deviation coefficient threshold, retracting the window by 1 bit, wherein the window range is suitable for the stepwise regression interval of the meteorological factors; d7, starting from the lower boundary of the window, if the width of the subsequent interval is smaller than 5, executing the steps d1-d3, if the width of the subsequent interval is larger than 5, executing the steps d4-d7, and repeating until the end of the first interval (wherein, the specific values of the window width and the standard deviation coefficient threshold value can be adjusted according to actual conditions), wherein the temperatures are all daily average temperatures.
Wherein the historical water supply amount data in the stepwise regression section satisfies a stepwise regression equation, the stepwise regression section being included in the second section, the stepwise regression equation being: the independent variable is temperature, the dependent variable is water supply, and the variables introduced one by one are weather factors;
specifically, the weather factor herein is not fixed and may be selected based on regression.
S10235, taking the remaining interval after the temperature interval corresponding to the historical water supply amount data is screened as an unpredictable interval, wherein the unpredictable interval is contained in the second interval;
specifically, when the second section to which the predicted date belongs is an unpredictable section, unpredictable information may be returned, or the prediction may be directly ended, or 0 may be returned (indicating that the date to be measured cannot be predicted).
From the above, the beneficial effects brought by the embodiment of the invention are as follows: the weather factor stepwise regression interval is added as an alternative scheme, so that regression analysis is more scientific and reasonable, and division of intervals is more detailed and specific and has practical significance
Further as a preferred embodiment of the method, the step of obtaining the section algorithm model corresponding to the obtained second section and inputting the temperature and/or the weather factor into the obtained section algorithm model to calculate the predicted water supply amount specifically includes:
s1031, performing regression judgment processing when the acquired second interval does not belong to the unpredictable interval;
the regression judgment process specifically comprises the following steps:
judging whether the acquired second interval is a stepwise regression interval, if so, acquiring a regression algorithm model corresponding to the stepwise regression interval, and inputting the temperature and the relevant weather factors in the weather factors into the acquired regression algorithm model by combining the relevant weather factors related to the acquired regression algorithm model, so as to calculate and acquire the predicted water supply;
specifically, the number of relevant weather factors can be multiple or one, the independent variables related to the stepwise regression algorithm model can be obtained after the stepwise regression algorithm model is obtained, then the independent variables are input into the stepwise regression algorithm model according to the parameters corresponding to the predicted date, and the predicted water supply is calculated and obtained. For example: the obtained stepwise regression algorithm model is as follows: if the predicted water supply amount (unit: ton) =20×temperature (unit: °c) +20×humidity+1.5×wind intensity+20, the final predicted water supply amount is 275 tons, which are all daily average temperatures, based on the predicted date temperature (12 ℃), humidity (30%) and wind intensity (6).
Otherwise, acquiring a regression algorithm model corresponding to the second interval, and inputting the temperature into the acquired regression algorithm model, so as to calculate and obtain the predicted water supply quantity;
specifically, different intervals correspond to different interval algorithm models, such as: the service characteristic of the predicted day is daily, the temperature is 15 ℃, the matched second interval is 10-16 ℃, the algorithm model corresponding to the second interval is the predicted water supply quantity (unit: ton) =15×temperature (unit: DEG C) +7, and then the water supply quantity can be calculated to be 232 tons; also for example: the service characteristic of the predicted day is double holidays, the temperature is 15 ℃, the matched second interval is 12-18 ℃, at this time, the algorithm model corresponding to the second interval is the predicted water supply quantity (unit: ton) =2×temperature (unit:. Degree. C.) 2-35, and the calculated water supply quantity is 415 tons (for example, only reference), and the temperatures are all average daily temperatures.
From the above, the beneficial effects brought by the embodiment of the invention are as follows: the predicted water supply amount can be obtained by inputting different values according to different interval algorithms, and the prediction has more practical significance.
As shown in fig. 2, an embodiment of the present invention further provides a water supply amount prediction system, including:
the first interval obtaining module 201 is configured to perform service characteristic matching processing according to a service characteristic, and obtain a first interval corresponding to the service characteristic.
The second interval obtaining module 202 is configured to perform a temperature matching process according to a temperature, so as to obtain a second interval corresponding to the temperature from the obtained first interval.
And the calculating module 203 is configured to obtain an interval algorithm model corresponding to the obtained second interval, and input the temperature and/or the meteorological factor into the obtained interval algorithm model, so as to calculate the predicted water supply amount.
The content in the method embodiment is applicable to the system embodiment, the functions specifically realized by the system embodiment are the same as those of the method embodiment, and the achieved beneficial effects are the same as those of the method embodiment.
Based on the water supply amount prediction method shown in fig. 1, an embodiment of the present invention further provides a water supply amount prediction apparatus, including:
at least one processor;
at least one memory for storing at least one program;
when the at least one program is executed by the at least one processor, the at least one processor is caused to implement the above-described one water supply amount prediction method.
The content in the method embodiment is applicable to the embodiment of the device, and the functions specifically realized by the embodiment of the device are the same as those of the method embodiment, and the obtained beneficial effects are the same as those of the method embodiment.
In addition, an embodiment of the present invention also provides a storage medium in which processor-executable instructions for performing any one of the water supply amount prediction methods described above when executed by a processor are stored.
While the preferred embodiment of the present invention has been described in detail, the invention is not limited to the embodiment, and various equivalent modifications and substitutions can be made by those skilled in the art without departing from the spirit of the invention, and these modifications and substitutions are intended to be included in the scope of the present invention as defined in the appended claims.
Claims (8)
1. A water supply amount prediction method, characterized by: the method comprises the following steps:
according to the service characteristics, first intervals corresponding to the service characteristics are screened out in a matching mode from a plurality of first intervals which are divided in advance, wherein the first intervals are divided in a time interval where the service characteristics of historical water supply data are located, the first intervals are in one-to-one correspondence with the service characteristics, the first intervals are divided according to a preset service characteristic sequence, and the preset service characteristic sequence is date, irregular large-scale event occurrence date, regular large-scale event occurrence date, holiday, double holiday and daily;
obtaining a plurality of pre-divided second intervals from the obtained first intervals, wherein the plurality of second intervals are contained in the first intervals;
according to the temperature, matching and screening out a second interval in which the temperature falls from a plurality of obtained second intervals which are divided in advance;
the plurality of pre-divided second intervals are obtained by performing interval screening and dividing treatment according to the relation between the temperature and the water supply of the historical water supply data or the relation between the temperature and the weather factor and the water supply;
the step of the interval screening and dividing process specifically comprises the following steps: respectively obtaining a temperature interval corresponding to each first interval, taking the temperature interval corresponding to the first interval as a logistic regression interval when the temperature interval corresponding to the first interval meets a logistic regression condition, and calculating to obtain a regression algorithm model corresponding to the logistic regression interval, wherein the logistic regression interval is included in a second interval, and the second interval is a temperature interval and further comprises: linear regression intervals, quadratic polynomial regression intervals, stepwise regression intervals and unpredictable intervals;
obtaining an interval algorithm model corresponding to the obtained second interval, and inputting the temperature and/or the meteorological factors into the obtained interval algorithm model, so as to calculate the predicted water supply quantity;
the logistic regression screening is performed on the first interval, and whether the temperature interval corresponding to the first interval can be logistic regression is judged, which comprises the following steps: a1, averaging the water supply amount of the historical water supply amount data in the first interval; a2, dividing the data into two parts according to the water supply quantity which is larger than the average value and smaller than the average value; a3, calculating the ratio of the standard deviation to the mean value in the two parts respectively; and a4, if the ratio is smaller than a certain threshold value, the part can be subjected to logistic regression, the temperature interval corresponding to the part is used as a logistic regression interval, and otherwise, the logistic regression is not suitable.
2. The water supply amount prediction method according to claim 1, wherein: the step of interval screening and dividing processing further comprises the following steps:
and selecting a temperature interval meeting the linear regression condition from the first temperature interval as a linear regression interval, and calculating to obtain a regression algorithm model corresponding to the linear regression interval, wherein the first temperature interval is the rest interval after the temperature interval corresponding to the first interval is selected, and the linear regression interval is included in the second interval.
3. The water supply amount prediction method according to claim 1, wherein: the step of interval screening and dividing processing further comprises the following steps:
and selecting a temperature interval meeting a quadratic polynomial regression condition from the first temperature interval as a quadratic polynomial regression interval, and calculating to obtain a regression algorithm model corresponding to the quadratic polynomial regression interval, wherein the first temperature interval is the rest interval after the temperature interval corresponding to the first interval is screened, and the quadratic polynomial regression interval is contained in the second interval.
4. The water supply amount prediction method according to claim 1, wherein: the step of interval screening and dividing processing further comprises the following steps:
screening a temperature interval meeting weather factor stepwise regression conditions from a first temperature interval as a stepwise regression interval, and calculating to obtain a regression algorithm model corresponding to the stepwise regression interval, wherein the first temperature interval is the rest interval of the temperature interval corresponding to the first interval after screening;
the historical water supply amount data in the stepwise regression interval satisfies a stepwise regression equation, the stepwise regression interval being included in the second interval, the stepwise regression equation being: the independent variable is temperature, the dependent variable is water supply, and the variables introduced one by one are weather factors;
and taking the remaining interval after the temperature interval corresponding to the historical water supply amount data is screened as an unpredictable interval, wherein the unpredictable interval is contained in the second interval.
5. The water supply amount prediction method according to claim 4, wherein: the step of obtaining an interval algorithm model corresponding to the obtained second interval, and inputting the temperature and/or the meteorological factors into the obtained interval algorithm model so as to calculate the predicted water supply amount, which specifically comprises the following steps:
when the acquired second interval does not belong to the unpredictable interval, carrying out regression judgment processing;
the regression judgment process specifically comprises the following steps: judging whether the acquired second interval is a stepwise regression interval, if so, acquiring a regression algorithm model corresponding to the stepwise regression interval, and inputting the temperature and the relevant weather factors in the weather factors into the acquired regression algorithm model by combining the relevant weather factors related to the acquired regression algorithm model, so as to calculate and acquire the predicted water supply; otherwise, acquiring a regression algorithm model corresponding to the second interval, and inputting the temperature into the acquired regression algorithm model, so as to calculate and obtain the predicted water supply quantity.
6. A water supply quantity prediction system, characterized in that: comprising the following steps:
the first interval acquisition module is used for matching and screening a first interval corresponding to the service characteristic from a plurality of first intervals which are divided in advance according to the service characteristic, wherein the first intervals are a plurality of intervals which are divided in a time interval where the service characteristic of historical water supply data is located, the first intervals are in one-to-one correspondence with the service characteristic, the first intervals are divided according to a preset service characteristic sequence, and the preset service characteristic sequence is date, irregular large-scale event occurrence date, regular large-scale event occurrence date, holiday, double holiday and daily;
the second interval acquisition module is used for obtaining a plurality of pre-divided second intervals from the obtained first intervals, wherein the plurality of second intervals are contained in the first intervals; according to the temperature, matching and screening out a second interval in which the temperature falls from a plurality of obtained second intervals which are divided in advance; the plurality of pre-divided second intervals are obtained by performing interval screening and dividing treatment according to the relation between the temperature and the water supply of the historical water supply data or the relation between the temperature and the weather factor and the water supply; the step of the interval screening and dividing process specifically comprises the following steps: respectively obtaining a temperature interval corresponding to each first interval, taking the temperature interval corresponding to the first interval as a logistic regression interval when the temperature interval corresponding to the first interval meets a logistic regression condition, and calculating to obtain a regression algorithm model corresponding to the logistic regression interval, wherein the logistic regression interval is included in a second interval, and the second interval is a temperature interval and further comprises:
linear regression intervals, quadratic polynomial regression intervals, stepwise regression intervals and unpredictable intervals;
the calculation module is used for obtaining an interval algorithm model corresponding to the obtained second interval and inputting the temperature and/or the meteorological factors into the obtained interval algorithm model so as to calculate the predicted water supply quantity;
the logistic regression screening is performed on the first interval, and whether the temperature interval corresponding to the first interval can be logistic regression is judged, which comprises the following steps: a1, averaging the water supply amount of the historical water supply amount data in the first interval; a2, dividing the data into two parts according to the water supply quantity which is larger than the average value and smaller than the average value; a3, calculating the ratio of the standard deviation to the mean value in the two parts respectively; and a4, if the ratio is smaller than a certain threshold value, the part can be subjected to logistic regression, the temperature interval corresponding to the part is used as a logistic regression interval, and otherwise, the logistic regression is not suitable.
7. A water supply amount prediction apparatus, characterized in that: comprising the following steps:
at least one processor;
at least one memory for storing at least one program;
when the at least one program is executed by the at least one processor, the at least one processor is caused to implement a water supply amount prediction method as set forth in any one of claims 1 to 5.
8. A storage medium having stored therein instructions executable by a processor, characterized by: the processor-executable instructions, when executed by the processor, are for performing a water supply amount prediction method as claimed in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910139355.1A CN110070203B (en) | 2019-02-25 | 2019-02-25 | Water supply quantity prediction method, system, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910139355.1A CN110070203B (en) | 2019-02-25 | 2019-02-25 | Water supply quantity prediction method, system, device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110070203A CN110070203A (en) | 2019-07-30 |
| CN110070203B true CN110070203B (en) | 2023-12-26 |
Family
ID=67366005
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910139355.1A Active CN110070203B (en) | 2019-02-25 | 2019-02-25 | Water supply quantity prediction method, system, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110070203B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115169771B (en) * | 2022-01-18 | 2022-12-30 | 长安大学 | Method for quickly evaluating efficiency damage of traffic network under influence of flood disasters |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105956690A (en) * | 2016-04-25 | 2016-09-21 | 广州东芝白云自动化系统有限公司 | Water supply prediction method and water supply prediction system |
| CN107273998A (en) * | 2016-06-30 | 2017-10-20 | 国网江苏省电力公司南通供电公司 | A kind of Temperature correction method predicted for platform area daily power consumption |
| CN107909195A (en) * | 2017-11-08 | 2018-04-13 | 吴江华衍水务有限公司 | A kind of design for commodities method |
| CN108133283A (en) * | 2017-12-11 | 2018-06-08 | 中国水利水电科学研究院 | Urban water system and the joint response regulation and control method of energy resource system reply climate change |
| CN109002937A (en) * | 2018-09-07 | 2018-12-14 | 深圳供电局有限公司 | Load Forecasting, device, computer equipment and storage medium |
-
2019
- 2019-02-25 CN CN201910139355.1A patent/CN110070203B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105956690A (en) * | 2016-04-25 | 2016-09-21 | 广州东芝白云自动化系统有限公司 | Water supply prediction method and water supply prediction system |
| CN107273998A (en) * | 2016-06-30 | 2017-10-20 | 国网江苏省电力公司南通供电公司 | A kind of Temperature correction method predicted for platform area daily power consumption |
| CN107909195A (en) * | 2017-11-08 | 2018-04-13 | 吴江华衍水务有限公司 | A kind of design for commodities method |
| CN108133283A (en) * | 2017-12-11 | 2018-06-08 | 中国水利水电科学研究院 | Urban water system and the joint response regulation and control method of energy resource system reply climate change |
| CN109002937A (en) * | 2018-09-07 | 2018-12-14 | 深圳供电局有限公司 | Load Forecasting, device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110070203A (en) | 2019-07-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Miller et al. | Automated daily pattern filtering of measured building performance data | |
| US10325331B2 (en) | Systems and methods for measuring and verifying energy usage in a building | |
| CN104966141B (en) | Method and system for updating a model used to generate an industrial asset health profile | |
| Wang et al. | A hierarchical Bayesian regression model for predicting summer residential electricity demand across the USA | |
| US7769568B2 (en) | Employing a dynamic lifecycle condition index (CI) to accommodate for changes in the expected service life of an item based on observance of the item and select extrinsic factors | |
| CN115293667B (en) | Management method of project progress and cost management system | |
| US7430494B2 (en) | Dynamic data stream histograms for no loss of information | |
| CN109116444B (en) | PCA-kNN-based air quality model PM2.5Forecasting method | |
| BRPI1101199A2 (en) | computerized method and system for monitoring a water distribution network, and computerized method for managing a water distribution network | |
| US20210110413A1 (en) | Systems and methods for dynamic demand sensing | |
| Cherkaoui et al. | Quantitative assessments of performance and robustness of maintenance policies for stochastically deteriorating production systems | |
| JP7292076B2 (en) | Deterioration estimation device, learning device, deterioration estimation method, learning method, deterioration estimation program, and learning program | |
| AU2016201794B1 (en) | Analyzing equipment degradation for maintaining equipment | |
| US20150371243A1 (en) | Systems and methods for parts forecasting | |
| US20180225779A1 (en) | System and method for determining power production in an electrical power grid | |
| Kacar et al. | A comparison of multiple linear regression approaches for fitting clearing functions to empirical data | |
| JP7422272B2 (en) | Method and apparatus for facilitating storage of data from industrial automation control systems or power systems | |
| CN110070203B (en) | Water supply quantity prediction method, system, device and storage medium | |
| Sha et al. | Development of a key-variable-based parallel HVAC energy predictive model | |
| Niaz et al. | A new comprehensive approach for regional drought monitoring | |
| Schwartz | Labor market dynamics over the business cycle: evidence from Markov switching models | |
| CN112686442A (en) | Air conditioner tail end energy consumption prediction method and system based on operation diversity | |
| van Summeren et al. | Influence of temperature, network diagnostics, and demographic factors on discoloration-related customer reports | |
| Bjerregaard et al. | The influence of electricity prices on saving electricity in production: Automated multivariate time-series analyses for 99 Danish trades and industries | |
| Rit et al. | Calibration method for an open source model to simulate building energy at territorial scale |
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 | ||
| CB02 | Change of applicant information |
Address after: 510660 No.12 Zhongshan 1st Road, Yuexiu District, Guangzhou, Guangdong Province Applicant after: Guangzhou Water Supply Co.,Ltd. Address before: 510600, No. 12, Zhongshan Road, Yuexiu District, Guangdong, Guangzhou Applicant before: GUANGZHOU WATER SUPPLY CO. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |