CN111967697A - Online dynamic energy consumption intelligent early warning method, system, device and storage medium - Google Patents
Online dynamic energy consumption intelligent early warning method, system, device and storage medium Download PDFInfo
- Publication number
- CN111967697A CN111967697A CN202011142911.XA CN202011142911A CN111967697A CN 111967697 A CN111967697 A CN 111967697A CN 202011142911 A CN202011142911 A CN 202011142911A CN 111967697 A CN111967697 A CN 111967697A
- Authority
- CN
- China
- Prior art keywords
- energy consumption
- early warning
- value
- day
- threshold
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000005265 energy consumption Methods 0.000 title claims abstract description 749
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000008859 change Effects 0.000 claims abstract description 66
- 239000000126 substance Substances 0.000 claims description 15
- 238000007418 data mining Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 7
- 230000002354 daily effect Effects 0.000 description 57
- 201000004569 Blindness Diseases 0.000 description 10
- 238000004364 calculation method Methods 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 5
- 238000009825 accumulation Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000004134 energy conservation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 241000023813 Isia Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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 relates to an online dynamic energy consumption intelligent early warning method, a system, a device and a storage medium, which are used for acquiring historical energy consumption change trend data of an early warning object; determining an initial energy consumption early warning threshold value in an early warning period according to historical energy consumption change trend data; acquiring updated energy consumption change trend data in an early warning period, and dynamically updating an initial energy consumption early warning threshold value according to the updated energy consumption change trend data to obtain a real-time energy consumption early warning threshold value; acquiring a current energy consumption accumulated value and a future energy consumption predicted value in an early warning period; and judging the early warning event according to the current energy consumption accumulated value, the future energy consumption predicted value and the real-time energy consumption early warning threshold value, and sending out an early warning notice when the early warning event occurs. The invention can intelligently and automatically set the energy consumption early warning threshold value in the early warning period, dynamically update the threshold value on line in real time, and carry out trending and predictive advance early warning by combining the energy consumption accumulated value in the early warning period and the predicted value, thereby further achieving the purpose of energy saving.
Description
Technical Field
The invention relates to the technical field of energy management, in particular to an online dynamic energy consumption intelligent early warning method, system, device and storage medium.
Background
The energy consumption early warning is mainly used for helping a user to discover unreasonable energy consumption conditions in time, operation and maintenance personnel intervene in time by pushing early warning events or early warning messages, and conduct targeted troubleshooting, so that unreasonable energy consumption can be discovered and processed early, and energy conservation is achieved.
However, the existing energy consumption early warning method mainly sets a fixed energy consumption early warning threshold value by the manual experience of operation and maintenance personnel, and has the following problems:
1. operation and maintenance personnel do not know how much the energy consumption early warning threshold value is set properly, and when the user service changes, the original energy consumption early warning threshold value is not suitable any more, the energy consumption early warning threshold value needs to be set again, and time and labor are wasted;
2. only when the actual energy consumption accumulated value exceeds the energy consumption early warning threshold value, an alarm can be sent out, a user can only carry out post-processing on an alarm event, the unreasonable energy consumption condition can not be found in time in advance, namely, the unreasonable energy consumption condition can not be found in the first time, real early warning can not be achieved, the energy-saving effect is not obvious
Disclosure of Invention
The invention aims to solve the technical problem that the prior art is not enough, and provides an online dynamic energy consumption intelligent early warning method, a system, a device and a storage medium, which can realize intelligent automatic setting of an energy consumption early warning threshold value in an early warning period, online dynamic real-time updating of the threshold value and reduction of blindness, complexity and hysteresis of manual configuration of the energy consumption early warning threshold value; the energy consumption accumulated value in the early warning period and the early warning with the predicted value are combined to perform trending and predictive advance early warning, so that the effectiveness of energy consumption early warning is improved, a user is helped to find out unreasonable energy consumption in time, enough time is won to take relevant measures, and the purpose of saving energy is further achieved.
The technical scheme for solving the technical problems is as follows:
an online dynamic energy consumption intelligent early warning method comprises the following steps:
acquiring historical energy consumption change trend data of an early warning object;
determining an initial energy consumption early warning threshold value of the early warning object in an early warning period according to the historical energy consumption change trend data;
acquiring updated energy consumption change trend data of the early warning object in the early warning period, and dynamically updating the initial energy consumption early warning threshold value according to the updated energy consumption change trend data to obtain a real-time energy consumption early warning threshold value;
acquiring a current energy consumption accumulated value and a future energy consumption predicted value of the early warning object in the early warning period; and judging an early warning event according to the current energy consumption accumulated value, the future energy consumption predicted value and the real-time energy consumption early warning threshold value, and sending an early warning notice when the early warning event occurs.
According to another aspect of the invention, an online dynamic energy consumption intelligent early warning system is also provided, which is applied to the online dynamic energy consumption intelligent early warning method of the invention and comprises a data acquisition module, an initial energy consumption threshold value determination module, a dynamic update module, an early warning judgment module and an early warning notification module;
the data acquisition module is used for acquiring historical energy consumption change trend data of the early warning object;
the initial energy consumption threshold determining module is used for determining an initial energy consumption early warning threshold of the early warning object in an early warning period according to the historical energy consumption change trend data;
the data acquisition module is further used for acquiring the updated energy consumption change trend data of the early warning object in the early warning period;
the dynamic updating module is used for dynamically updating the initial energy consumption early warning threshold value according to the updated energy consumption change trend data to obtain a real-time energy consumption early warning threshold value;
the early warning judgment module is used for acquiring a current energy consumption accumulated value and a future energy consumption predicted value of the early warning object in the early warning period; judging an early warning event according to the current energy consumption accumulated value, the future energy consumption predicted value and the real-time energy consumption early warning threshold value;
and the early warning notification module is used for sending out early warning notification when an early warning event occurs.
According to another aspect of the present invention, an online dynamic energy consumption intelligent early warning device is further provided, which includes a processor, a memory, and a computer program stored in the memory and operable on the processor, where the computer program implements the steps of the online dynamic energy consumption intelligent early warning method in the present invention when running.
In accordance with another aspect of the present invention, there is provided a computer storage medium comprising: at least one instruction which, when executed, implements the steps of the online dynamic energy consumption intelligent warning method of the present invention.
The online dynamic energy consumption intelligent early warning method, the online dynamic energy consumption intelligent early warning system, the online dynamic energy consumption intelligent early warning device and the storage medium have the beneficial effects that: by acquiring historical energy consumption change trend data of the early warning object, an initial energy consumption early warning threshold value of the early warning object at the beginning of an early warning period can be determined, and powerful data support is provided for energy consumption early warning of the early warning object in the early warning period; the historical energy consumption change trend data can be energy consumption data of one month, one year or even more before the early warning period, and an initial energy consumption early warning threshold value is determined according to the energy consumption data by combining methods of big data analysis and data mining analysis, so that the accuracy and the reliability are high; when the initial energy consumption early warning threshold value is determined, the early warning object starts to generate energy in the early warning period, updated energy consumption change trend data is generated along with the advance of time in the early warning period, the initial energy consumption early warning threshold value is dynamically updated according to the updated energy consumption change trend data, the real-time energy consumption early warning threshold value in each updated time can be obtained, and the problems of blindness, complexity and hysteresis of manual setting of the energy consumption early warning threshold value are solved; meanwhile, in the dynamic updating process of the initial energy consumption early warning threshold, the current energy consumption accumulated value and the future energy consumption predicted value of the early warning object in the early warning period are obtained, the early warning event judgment is carried out according to the current energy consumption accumulated value, the future energy consumption predicted value and the real-time energy consumption early warning threshold, when the early warning event is judged to occur, an early warning notice is sent out, the early warning notice can be timely carried out on a certain future time point (for example, a certain future day or a certain future month) in the early warning period, the condition that the unreasonable energy consumption condition cannot be timely found out only aiming at the early warning event is avoided, and the early warning is really realized;
according to the online dynamic energy consumption intelligent early warning method, the online dynamic energy consumption intelligent early warning system, the online dynamic energy consumption intelligent early warning device and the storage medium, the intelligent automatic setting of the energy consumption early warning threshold value in the early warning period can be realized, the threshold value can be updated dynamically on line in real time, and the blindness, the complexity and the hysteresis of manually configuring the energy consumption early warning threshold value are reduced; the energy consumption accumulated value in the early warning period and the early warning with the predicted value are combined to perform trending and predictive advance early warning, so that the effectiveness of energy consumption early warning is improved, a user is helped to find out unreasonable energy consumption in time, enough time is won to take relevant measures, and the purpose of saving energy is further achieved.
Drawings
Fig. 1 is a schematic flow chart of an online dynamic energy consumption intelligent early warning method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an online dynamic energy consumption intelligent early warning system in the second embodiment of the present invention.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
The present invention will be described with reference to the accompanying drawings.
An embodiment of the first embodiment is shown in fig. 1, which is an online dynamic energy consumption intelligent early warning method, including the following steps:
s1: acquiring historical energy consumption change trend data of an early warning object;
s2: determining an initial energy consumption early warning threshold value of the early warning object in an early warning period according to the historical energy consumption change trend data;
s3: acquiring updated energy consumption change trend data of the early warning object in the early warning period, and dynamically updating the initial energy consumption early warning threshold value according to the updated energy consumption change trend data to obtain a real-time energy consumption early warning threshold value;
s4: acquiring a current energy consumption accumulated value and a future energy consumption predicted value of the early warning object in the early warning period; and judging an early warning event according to the current energy consumption accumulated value, the future energy consumption predicted value and the real-time energy consumption early warning threshold value, and sending an early warning notice when the early warning event occurs.
By acquiring historical energy consumption change trend data of the early warning object, an initial energy consumption early warning threshold value of the early warning object at the beginning of an early warning period can be determined, and powerful data support is provided for energy consumption early warning of the early warning object in the early warning period; the historical energy consumption change trend data can be energy consumption data of one month, one year or even more before the early warning period, and an initial energy consumption early warning threshold value is determined according to the energy consumption data by combining methods of big data analysis and data mining analysis, so that the accuracy and the reliability are high; when the initial energy consumption early warning threshold value is determined, the early warning object starts to generate energy in the early warning period, updated energy consumption change trend data is generated along with the advance of time in the early warning period, the initial energy consumption early warning threshold value is dynamically updated according to the updated energy consumption change trend data, the real-time energy consumption early warning threshold value in each updated time can be obtained, and the problems of blindness, complexity and hysteresis of manual setting of the energy consumption early warning threshold value are solved; meanwhile, in the dynamic updating process of the initial energy consumption early warning threshold, the current energy consumption accumulated value and the future energy consumption predicted value of the early warning object in the early warning period are obtained, the early warning event judgment is carried out according to the current energy consumption accumulated value, the future energy consumption predicted value and the real-time energy consumption early warning threshold, when the early warning event is judged to occur, an early warning notice is sent out, the early warning notice can be timely carried out on a certain future time point (for example, a certain future day or a certain future month) in the early warning period, the condition that the unreasonable energy consumption condition cannot be timely found out only aiming at the early warning event is avoided, and the early warning is really realized;
the online dynamic energy consumption intelligent early warning method can realize intelligent automatic setting of the energy consumption early warning threshold value in the early warning period and online dynamic real-time updating of the threshold value, and reduces blindness, complexity and hysteresis of manual configuration of the energy consumption early warning threshold value; the energy consumption accumulated value in the early warning period and the early warning with the predicted value are combined to perform trending and predictive advance early warning, so that the effectiveness of energy consumption early warning is improved, a user is helped to find out unreasonable energy consumption in time, enough time is won to take relevant measures, and the purpose of saving energy is further achieved.
Preferably, the initial energy consumption early warning threshold comprises a daily initial energy consumption threshold and/or a monthly initial energy consumption threshold;
s2 specifically includes:
and determining the daily initial energy consumption threshold and/or the monthly initial energy consumption threshold according to the historical energy consumption change trend data based on a k sigma principle.
The early warning period may be one day or one month, namely, the early warning judgment needs to be performed on the energy consumption generated by the early warning object in each day or in each month, when the early warning period is one day, the initial energy consumption early warning threshold value is a daily initial energy consumption threshold value, and the daily real-time energy consumption threshold value dynamically updated every day is conveniently obtained subsequently through the daily initial energy consumption threshold value, so that the early warning on the daily energy consumption is conveniently performed in advance; when the early warning period is one month, the initial energy consumption early warning threshold value is a monthly initial energy consumption threshold value, and a monthly real-time energy consumption threshold value dynamically updated every month is obtained through monthly initial energy consumption threshold value change, so that early warning on monthly energy consumption is facilitated; when the early warning requirement is high, early warning is needed to be carried out on energy consumption per month, and meanwhile, early warning is needed to be carried out on energy consumption per day in each month, and the initial energy consumption early warning threshold value comprises not only a monthly initial energy consumption threshold value but also a daily initial energy consumption threshold value, so that during the energy consumption early warning period in each month, daily energy consumption early warning in each month is also included, and the daily energy consumption value is compared with the daily real-time energy consumption threshold value; the method for determining the initial energy consumption early warning threshold value comprising the daily initial energy consumption threshold value and/or the monthly initial energy consumption threshold value can comprehensively early warn the energy consumption of the early warning object in the early warning period in advance, further improves the effect of energy consumption early warning, and has higher intelligent degree of online dynamic early warning.
The k sigma principle means that if data follows a normal distribution, an outlier is defined as one of a set of result values that deviates more than the mean valuekThe value of the multiple standard deviation; if the data do not follow a normal distribution, they may be far from the meankThe standard deviation is multiplied to describe the outliers. Therefore, according to the k sigma principle, a method for searching an abnormal value can be used as a method for determining the initial energy consumption early warning threshold value.
In particular, the initial energy consumption early warning threshold is determined according to the 3 sigma principle in the present embodiment, that is, the initial energy consumption early warning threshold is determinedkThe value was taken to be 3.
Preferably, when the initial energy consumption early warning threshold is specifically the day initial energy consumption threshold, where the day initial energy consumption threshold includes a working day initial energy consumption threshold and a rest day initial energy consumption threshold, S2 specifically includes:
taking any one day in the early warning period, and if the selected day is a working day, extracting a daily energy consumption value of at least 30 continuous working days before the early warning period from the historical energy consumption change trend data to serve as a first historical energy consumption data set;
respectively calculating a first average value and a first standard deviation of the first historical energy consumption data set;
based on a k sigma principle, calculating according to the first average value and the first standard deviation to obtain the initial energy consumption threshold of the working day;
the first formula for calculating the initial energy consumption threshold value of the working day is as follows:
wherein the content of the first and second substances,
for the initial energy consumption threshold for the working day,
is the first average value of the first average value,
for the purpose of the first standard deviation,kis a standard deviation multiple value set in the k sigma principle;
if the selected day is a rest day, extracting a daily energy consumption value of at least 30 continuous rest days before the early warning period from the historical energy consumption change trend data to serve as a second historical energy consumption data set;
respectively calculating a second average value and a second standard deviation of the second historical energy consumption data set;
calculating to obtain the initial energy consumption threshold value of the rest day according to the second average value and the second standard deviation based on the k sigma principle;
the second formula for calculating the initial energy consumption threshold value of the rest day is as follows:
wherein the content of the first and second substances,
an initial energy consumption threshold for the day of rest,
in order to be said second average value,
is the second standard deviation.
When the initial energy consumption early warning threshold is the daily initial energy consumption threshold, the early warning must be performed on the energy consumption of each day in the early warning period, and any day in the early warning period may be a working day or a rest day, and according to the common knowledge, the energy consumption of the working day is usually larger than that of the rest day; therefore, when an optional day in the early warning period is a working day, the initial energy consumption threshold of the working day needs to be determined according to historical energy consumption change trend data, that is, the initial energy consumption threshold of the working day needs to be used as the daily initial energy consumption early warning threshold corresponding to the selected day in the early warning period; similarly, when an optional day in the early warning period is a rest day, the initial energy consumption threshold value of the rest day needs to be used as the initial energy consumption early warning threshold value of the day degree of the selected day in the early warning period; by determining the initial energy consumption threshold of the working day or the initial energy consumption threshold of the rest day, the accuracy of the initial energy consumption threshold of the day can be further improved, and the early warning accuracy of the follow-up energy consumption early warning is further improved. The daily energy consumption values of at least 30 continuous working days or 30 rest days are extracted, and the accuracy and reliability of the initial energy consumption threshold value of the working days or the initial energy consumption threshold value of the rest days can be effectively guaranteed on the basis of the synchronization cycle ratio data.
Specifically, when the early warning period is 30 days and the current early warning day is a working day, the daily energy consumption values of at least 30 continuous working days before the working day are extracted as the first historical energy consumption data set, taking the daily energy consumption values of 30 continuous working days as the first historical energy consumption data set as an example, the average value and the standard deviation of the daily energy consumption values of the 30 working days, that is, the first average value, are calculated
And first standard deviation
Then, according to a first formula, calculating the initial energy consumption threshold value of the working day of the early warning period as
；
When the early warning period is 30 days and the current early warning day is a holiday (saturday or sunday or legal holiday), extracting the daily energy consumption values of at least 30 consecutive holidays before the holiday as a second historical energy consumption data set, taking the daily energy consumption values of 30 consecutive holidays as the second historical energy consumption data set as an example, and calculating the average value of the daily energy consumption values of the 30 holidaysAnd standard deviation, i.e. second mean value
And second standard deviation
Then, according to a second formula, calculating the initial energy consumption threshold value of the break day of the early warning period as
。
Preferably, when the initial energy consumption early warning threshold is specifically the monthly initial energy consumption threshold, then S2 specifically includes:
extracting a monthly energy consumption value of at least 13 continuous months before the early warning period from the historical energy consumption change trend data as a third historical energy consumption data set;
calculating a third standard deviation of the third historical energy consumption dataset;
based on the k sigma principle, calculating according to the third historical energy consumption data set and the third standard deviation to obtain the monthly initial energy consumption threshold;
the third formula for calculating the monthly initial energy consumption threshold is as follows:
wherein the content of the first and second substances,
for the monthly initial energy consumption threshold,
the last month energy consumption value in the third historical energy consumption dataset;
and
a 12 th month energy consumption value and a 11 th month energy consumption value, respectively, in the third historical energy consumption dataset prior to the last month energy consumption value,
is the third standard deviation.
When the initial energy consumption early warning threshold is the monthly initial energy consumption threshold, the early warning must be performed on the energy consumption of each month in the early warning period, and the early warning period can be months, a year or years; therefore, the monthly initial energy consumption threshold needs to be determined by extracting the monthly energy consumption values of at least 13 months before the early warning period according to the historical energy consumption change trend data, so as to improve the early warning accuracy of the subsequent energy consumption early warning. The monthly energy consumption value of at least 13 continuous months is extracted, and the accuracy and the reliability of the monthly initial energy consumption threshold value are effectively ensured by taking the synchronization cycle ratio data as the data basis.
Specifically, when the first month of the early warning period is the 2020 year 5 month, the month energy consumption value of at least 13 consecutive months before the 2020 year 5 month is extracted as the third history energy consumption dataset, taking the example of extracting the month energy consumption value of 13 consecutive months as the third history energy consumption dataset, the month energy consumption values of 13 months are respectively referred to as the 1 st month energy consumption value, the 2 nd month energy consumption value and the … … th month energy consumption value of the third history energy consumption dataset, and the month energy consumption values of 13 months respectively correspond to the 2019 year 4 month energy consumption value, the 2019 year 5 month energy consumption value, 2019 year 6 month energy consumption value, … … 2019 year 12 month energy consumption value, 2020 year 1 month energy consumption value, 2020 year 2 month energy consumption value, … … and the 2020 year 4 month energy consumption value; likewise, the standard deviation of the 13-month energy consumption values, i.e., the third standard deviation, was calculated, respectively
Then, the energy consumption value of the 1 st month (namely the energy consumption value of the 4 months and the 4 months in 2019), the energy consumption value of the 2 nd month (namely the energy consumption value of the 5 months and the 5 months in 2019) and the energy consumption value of the 13 th month (namely the energy consumption value of the 4 months and the 4 months in 2020) are taken,ktaking 3 and substituting into the third formula respectively to obtain 2020 th 5Monthly initial energy consumption threshold of a month.
Specifically, when the initial energy consumption early warning threshold includes both a daily initial energy consumption threshold and a monthly initial energy consumption threshold, for example, the first month of the early warning cycle is 2020-5 month, days 1 to 3 of the 2020-5 month are holidays (days 5 and 1 to 3 are legal holidays), and days 4 and 5 are workdays, the corresponding monthly initial energy consumption threshold is calculated according to the calculation method of the monthly initial energy consumption threshold, the corresponding holiday initial energy consumption threshold is calculated according to the calculation method of the holiday initial energy consumption threshold, and the corresponding workday initial energy consumption threshold is calculated according to the calculation method of the workday initial energy consumption threshold; then, in the subsequent dynamic updating, the initial energy consumption threshold value of the break day is used as the day degree initial energy consumption early warning threshold value in No. 5 month 1, the initial energy consumption threshold value of the break day is dynamically updated in No. 5 month 2, the updated initial energy consumption threshold value of the break day is updated again in No. 5 month 3, the initial energy consumption threshold value of the working day is used as the day degree initial energy consumption early warning threshold value in No. 5 month 4, and the initial energy consumption threshold value of the working day is dynamically updated in No. 5 month 5; by analogy with … …, the updated initial energy consumption threshold value of the holiday of No. 3 is updated again after 5 months and 9 months; by month 5 and 11, the initial energy consumption threshold is again updated on the weekday updated by month 5, … …, and so on.
And when the number 5 month 31 is finished and the number 6 month 1 is reached, dynamically updating the previously calculated monthly initial energy consumption threshold value, and taking the obtained monthly real-time energy consumption threshold value as the monthly initial energy consumption threshold value of the month 6.
Then, in the subsequent early warning event judgment, each dynamically updated daily real-time energy consumption threshold (including a working day real-time energy consumption threshold and a rest day real-time energy consumption threshold) and monthly real-time energy consumption threshold participate in the early warning judgment, the daily real-time energy consumption threshold participates in the judgment of the daily early warning event in the early warning period, and the monthly real-time energy consumption threshold participates in the judgment of the monthly early warning event in the early warning period.
Preferably, the real-time energy consumption early warning threshold comprises a daily real-time energy consumption threshold and/or a monthly real-time energy consumption threshold;
in S3, dynamically updating the initial energy consumption early warning threshold to obtain the real-time energy consumption early warning threshold, which specifically includes:
updating the day initial energy consumption early warning threshold once a day according to the updating of the date and the updating energy consumption change trend data in the early warning period to obtain the day real-time energy consumption threshold; and/or updating the monthly initial energy consumption early warning threshold once per month according to the updating of months and the updated energy consumption change trend data in the early warning period to obtain the monthly real-time energy consumption threshold.
Because the initial energy consumption early warning threshold comprises a daily initial energy consumption threshold and/or a monthly initial energy consumption threshold, in dynamic updating, the daily initial energy consumption threshold needs to be dynamically updated along with updating of a date to obtain each updated daily real-time energy consumption threshold, so that the daily initial energy consumption threshold is dynamically updated on line, the blindness, the complexity and the hysteresis of manually configuring the daily energy consumption early warning threshold are reduced, and the judgment of a subsequent daily early warning event is improved; in dynamic updating, with the updating of months, dynamic updating needs to be performed on each monthly initial energy consumption threshold to obtain each updated monthly real-time energy consumption threshold, so that the monthly initial energy consumption threshold is dynamically updated on line, the blindness, the complexity and the hysteresis of manually configuring the monthly energy consumption early warning threshold are reduced, and the judgment of subsequent monthly early warning events is improved; and for the condition with higher early warning requirement, dynamically updating each daily initial energy consumption threshold and each monthly initial energy consumption threshold at the same time, and respectively participating in the judgment of the daily early warning event and the monthly early warning event.
Specifically, when the initial energy consumption early warning threshold is a working day initial energy consumption threshold, for example, 5/4/2020/a corresponding day degree initial energy consumption threshold is a working day initial energy consumption threshold, the historical energy consumption change trend data extracted by calculating the working day initial energy consumption threshold is a daily energy consumption value of at least 30 consecutive working days before 5/4/a, similarly, taking the daily energy consumption value of 30 working days as an example for explanation, when the date is updated to 5/a, the working day initial energy consumption threshold needs to be updated, at this time, the updated energy consumption change trend data corresponding to 5/a 4/a is obtained, the first daily energy consumption value of the 30 working days extracted before is removed, the daily energy consumption values of 29 working days are left, the daily energy consumption value of 29 working days and the updated energy consumption change trend data corresponding to 5/a 4/a are taken together as the first historical energy consumption data set of 5/a, and calculating the corresponding working day initial energy consumption threshold value by adopting the method for calculating the first formula again, namely the working day initial energy consumption threshold value after dynamic updating, which is also called a day real-time energy consumption threshold value (more specifically, the working day real-time energy consumption threshold value).
When the initial energy consumption early warning threshold is the initial energy consumption threshold of the holiday, for example, No. 5/1 in 2020, the corresponding initial energy consumption threshold of the daytime is the initial energy consumption threshold of the holiday, the historical energy consumption change trend data extracted by calculating the initial energy consumption threshold of the holiday is the daily energy consumption data of at least 30 consecutive holidays before No. 5/1, similarly, the daily energy consumption values of 30 holidays are taken as an example for explanation, when the date is updated to No. 5/2, the initial energy consumption threshold of the holiday needs to be updated, the updated energy consumption change trend data corresponding to No. 5/1 in the current time is obtained, the first daily energy consumption value in the daily energy consumption values of 30 holidays extracted before is removed, the daily energy consumption values of 29 holidays are remained, the daily energy consumption value of the 29 holidays and the updated energy consumption change trend data corresponding to No. 5/1 are taken together as the second historical energy consumption data set of No. 5/2, and calculating the corresponding rest day initial energy consumption threshold value by adopting the method for calculating the second formula again, namely the dynamically updated rest day initial energy consumption threshold value, which is also called a day real-time energy consumption threshold value (more specifically, a rest day real-time energy consumption threshold value).
When the initial energy consumption early warning threshold is a monthly initial energy consumption threshold, for example, in 5 months in 2020, the historical energy consumption change trend data extracted in calculating the monthly initial energy consumption threshold is monthly energy consumption values of at least 13 consecutive months before 5 months in 2020, taking monthly energy consumption values of 13 consecutive months as an example for explanation, then with the updating of the months, when the 6 months in 2020 comes, the monthly initial energy consumption threshold needs to be updated, at this time, the updated energy consumption change trend data corresponding to 5 months in 2020 is obtained, the first monthly energy consumption value in the 13 months energy consumption values extracted before is removed, and the 12-month energy consumption value is remained, the 12-month daily energy consumption value and the updated energy consumption change trend data corresponding to 5 months in 2020 are taken together as a third historical energy consumption data set of 6 months in 2020, and the corresponding monthly initial energy consumption threshold is calculated again by adopting the method of calculating the third formula, namely, the dynamically updated monthly initial energy consumption threshold value is also called monthly real-time energy consumption threshold value.
Preferably, when the real-time energy consumption early warning threshold is a daily real-time energy consumption threshold, the current energy consumption accumulated value corresponds to a first actual energy consumption accumulated value at the current time of the day, and the future energy consumption predicted value includes a future time energy consumption predicted value corresponding to each future time at the current time of the day;
in S4, performing an early warning event judgment according to the current energy consumption accumulated value, the future energy consumption predicted value, and the real-time energy consumption early warning threshold value, and when an early warning event occurs, sending an early warning notification, specifically including:
acquiring the first actual energy consumption accumulated value at the current moment of the day, and sequentially acquiring the energy consumption predicted value at each future moment by adopting a data mining method according to the sequence of time from first to last;
according to the sequence of time from first to last, sequentially calculating to obtain the current-day energy consumption early warning value at each future moment according to the first actual energy consumption accumulated value and the energy consumption predicted value at each future moment;
the current time of day istAt the moment, then calculateiThe fourth formula of the energy consumption early warning value at the current day at the future moment is as follows:
wherein the content of the first and second substances,
is composed oftThe time corresponds to the secondiA Chinese character ofThe energy consumption early warning value of the current day at the coming moment,X t is composed oftThe first actual accumulated value of energy consumption at a time,x i is composed oftThe time corresponds to the secondiThe predicted value of the energy consumption at the future time,Tis composed oftThe number of hours of the future time corresponding to the time;
comparing the energy consumption early warning value of each day with the real-time energy consumption threshold value of the day degree one by one, and judging whether the energy consumption early warning value of each day is the first dayiWhen the energy consumption early warning value of the current day exceeds the real-time energy consumption threshold value of the current day, judging that an early warning event occurs, and sending that the current day of the current day is at the first momentiA first early warning notification corresponding to the future time.
When the real-time energy consumption early warning threshold value is the solar real-time energy consumption threshold value, energy consumption of each day needs to be early warned in advance, the current energy consumption accumulated value which needs to be obtained corresponds to a first actual energy consumption accumulated value at the solar current moment, namely, energy consumption used in an accumulated manner at the current time of the day is the current energy consumption value at the current time of the day, and the future energy consumption predicted value is the future time energy consumption predicted value which corresponds to each future time of the day one by one at the current time of the day; the energy consumption predicted value at each future moment can be sequentially obtained through a data mining method (such as Holt Winters, Prophet, wavelet transform forecast, ARIMA and other time sequence models, the data mining method is not an innovation point of the invention, and specific details are not described herein); then, the energy consumption early warning value of the current day at each future moment is calculated in turn according to a fourth formula, namely, the first actual energy consumption accumulated value is sequentially compared with the energy consumption predicted value at the 1 st future moment and the energy consumption predicted value at the 2 nd future moment … …TAccumulating the energy consumption predicted values at a future moment (for example, when the current moment of the day is 1 point, the number of hours at the future moment corresponding to the current moment of the day is 23) at the current day, when one of the accumulated energy consumption predicted values exceeds the real-time energy consumption threshold value of the day corresponding to the current day, the situation that the energy is excessive at the last future moment participating in the accumulation calculation is meant, namely, a daily energy consumption early warning event occurs, and sending a first early warning notice corresponding to the future moment so as to notify an operation and maintenance personThe personnel intervene in advance in time to achieve the aim of energy conservation.
Specifically, the current time of daytWhen the time is 1 point, the number of hours of the corresponding future time is 23, and the actual energy consumption integrated value which is already used when the first actual energy consumption integrated value is 1 point is set asX 1Predicting the predicted energy consumption values at the future time points of 23 future time points (2 point, 3 point and 4 point … … 24 point) of 1 point, wherein the predicted energy consumption values are respectivelyx 1、x 2、x 3、……x 23And the energy consumption early warning values of the day at 23 future moments obtained by sequentially calculating by adopting a fourth formula are respectively as follows:
when it comes toiThe day energy consumption early warning value at a future moment exceeds the day real-time energy consumption threshold value (set asQ d I.e. the degree of the day isdDay, corresponding todDay real-time energy consumption threshold of day), for example, the day energy consumption early warning value at the 11 th future time (i.e., 12 o' clock) exceeds the day real-time energy consumption threshold,
and then the day energy consumption early warning event is about to occur at the 11 th future moment (namely 12 points), and if the day energy consumption early warning event does not exist
And no early warning notification is sent out.
Preferably, when the real-time energy consumption early warning threshold is a monthly real-time energy consumption threshold, the current energy consumption accumulated value corresponds to a second actual energy consumption accumulated value on the current day of the month, and the future energy consumption predicted value includes a one-to-one future daily energy consumption predicted value on each future day of the current day of the month;
in S4, performing an early warning event judgment according to the current energy consumption accumulated value, the future energy consumption predicted value, and the real-time energy consumption early warning threshold value, and when an early warning event occurs, sending an early warning notification, specifically including:
acquiring the second actual energy consumption accumulated value of the monthly current day, and sequentially acquiring the energy consumption predicted value of each future day by adopting a data mining method according to the sequence of time from first to last;
according to the sequence of time from first to last, sequentially calculating to obtain the energy consumption early warning value in the current month in each future day according to the second actual energy consumption accumulated value and the energy consumption predicted value in each future day;
the month and day aredDay, then calculatejThe fifth formula of the energy consumption early warning value in the current month in the future day is as follows:
wherein the content of the first and second substances,
is composed ofdThe day corresponds tojThe energy consumption early warning value of the current month in the future,M d is composed ofdThe second accumulated actual energy consumption value for the day,n j is composed ofdThe day corresponds tojA future day energy consumption predicted value of a future day,Dis composed ofdThe number of days of the future day to which the day corresponds;
comparing the early warning value of the energy consumption of each month with the monthly real-time energy consumption threshold value one by one, and judging whether the early warning value of the energy consumption of each month is the first monthjWhen the energy consumption early warning value of the current month exceeds the monthly real-time energy consumption threshold value, judging that an early warning event occurs, and sending out the monthly current dayjA second warning notification corresponding to the future day.
The steps are judged for monthly early warning eventsWhen the real-time energy consumption early warning threshold is a monthly real-time energy consumption threshold, energy consumption of each month needs to be early warned in advance, and the current energy consumption accumulated value which needs to be obtained corresponds to a second actual energy consumption accumulated value on the current day of the month, namely, the energy consumption which is used in the current month is accumulated on the current day of the month, and the future energy consumption predicted value is a future day energy consumption predicted value which corresponds to each future day of the current month one by one on the current day of the month; the energy consumption predicted value of each future day can be sequentially obtained by a data mining method (the same as the energy consumption predicted value obtaining method at the future moment); then, according to a fifth formula, the monthly energy consumption early warning value of each future day is calculated in turn, namely, the second actual energy consumption accumulated value is sequentially compared with the 1 st future day energy consumption predicted value and the 2 nd future day energy consumption predicted value … …DAccumulating the energy consumption predicted value of the future day (for example, when the current month is No. 1, the number of days of the future day corresponding to the current month is 29 days in the current month, and the number is counted by 30 days in one month), and when one of the accumulated values exceeds the monthly real-time energy consumption threshold corresponding to the current month, the situation that the energy is excessive for the last future day participating in the sum accumulation calculation is about to occur, namely, a monthly energy consumption early warning event occurs, and sending a second early warning notice corresponding to the future day so as to notify the operation and maintenance personnel to intervene in advance in time, thereby achieving the purpose of energy saving.
Specifically, when the current date of the month is 1 day (i.e., No. 1), the number of days corresponding to the future day is 29 days, and the actual energy consumption integrated value that has been used when the second actual energy consumption integrated value is No. 1 is set as the actual energy consumption integrated valueM 1The predicted values of the energy consumption of the future days of 29 future days (No. 2, No. 3 and No. 4 … … 30) of No. 1 are predicted, and are respectivelyn 1、n 2、n 3、……n 29And the 29 current energy consumption early warning values in the future days obtained by sequentially calculating by adopting a fifth formula are respectively as follows:
when it comes tojThe early warning value of the energy consumption in the current month in the future day exceeds the real-time energy consumption threshold value of the month (set asQ m I.e. monthly ismMonth, corresponding tomMonthly real-time energy consumption threshold for a month), for example, the monthly energy consumption warning value on the 14 th future day (i.e., No. 15) exceeds the monthly real-time energy consumption threshold,
if the monthly energy consumption early warning event is not available, the 14 th future date (namely 15) is about to occur
And no early warning notification is sent out.
Based on the first embodiment, as shown in fig. 2, the second embodiment further discloses an online dynamic energy consumption intelligent early warning system, which is applied to the online dynamic energy consumption intelligent early warning method of the first embodiment, and comprises a data acquisition module, an initial energy consumption threshold determination module, a dynamic update module, an early warning judgment module and an early warning notification module;
the data acquisition module is used for acquiring historical energy consumption change trend data of the early warning object;
the initial energy consumption threshold determining module is used for determining an initial energy consumption early warning threshold of the early warning object in an early warning period according to the historical energy consumption change trend data;
the data acquisition module is further used for acquiring the updated energy consumption change trend data of the early warning object in the early warning period;
the dynamic updating module is used for dynamically updating the initial energy consumption early warning threshold value according to the updated energy consumption change trend data to obtain a real-time energy consumption early warning threshold value;
the early warning judgment module is used for acquiring a current energy consumption accumulated value and a future energy consumption predicted value of the early warning object in the early warning period; judging an early warning event according to the current energy consumption accumulated value, the future energy consumption predicted value and the real-time energy consumption early warning threshold value;
and the early warning notification module is used for sending out early warning notification when an early warning event occurs.
The online dynamic energy consumption intelligent early warning system in the embodiment can realize intelligent automatic setting of the energy consumption early warning threshold value in the early warning period and online dynamic real-time updating of the threshold value, and reduces blindness, complexity and hysteresis of manually configuring the energy consumption early warning threshold value; the energy consumption accumulated value in the early warning period and the early warning with the predicted value are combined to perform trending and predictive advance early warning, so that the effectiveness of energy consumption early warning is improved, a user is helped to find out unreasonable energy consumption in time, enough time is won to take relevant measures, and the purpose of saving energy is further achieved.
Preferably, the initial energy consumption early warning threshold comprises a daily initial energy consumption threshold and/or a monthly initial energy consumption threshold;
the initial energy consumption threshold determination module is specifically configured to:
and determining the daily initial energy consumption threshold and/or the monthly initial energy consumption threshold according to the historical energy consumption change trend data based on a k sigma principle.
Preferably, when the initial energy consumption early warning threshold is specifically the day initial energy consumption threshold, where the day initial energy consumption threshold includes a working day initial energy consumption threshold and a rest day initial energy consumption threshold, the initial energy consumption threshold determining module is specifically configured to:
taking any one day in the early warning period, and if the selected day is a working day, extracting a daily energy consumption value of a working day which is 30 days before the early warning period from the historical energy consumption change trend data to serve as a first historical energy consumption data set;
respectively calculating a first average value and a first standard deviation of the first historical energy consumption data set;
based on a k sigma principle, calculating according to the first average value and the first standard deviation to obtain the initial energy consumption threshold of the working day;
the first formula for calculating the initial energy consumption threshold value of the working day is as follows:
wherein the content of the first and second substances,
for the initial energy consumption threshold for the working day,
is the first average value of the first average value,
for the purpose of the first standard deviation,kis a standard deviation multiple value set in the k sigma principle;
if the selected day is a rest day, extracting a daily energy consumption value of a rest day of 30 continuous days before the early warning period from the historical energy consumption change trend data to serve as a second historical energy consumption data set;
respectively calculating a second average value and a second standard deviation of the second historical energy consumption data set;
calculating to obtain the initial energy consumption threshold value of the rest day according to the second average value and the second standard deviation based on the k sigma principle;
the second formula for calculating the initial energy consumption threshold value of the rest day is as follows:
wherein the content of the first and second substances,
an initial energy consumption threshold for the day of rest,
in order to be said second average value,
is the second standard deviation.
Preferably, when the initial energy consumption early warning threshold is specifically the monthly initial energy consumption threshold, the initial energy consumption early warning threshold is determined, and the initial energy consumption threshold determining module is specifically configured to:
extracting a monthly energy consumption value of 13 months before the early warning period from the historical energy consumption change trend data to serve as a third historical energy consumption data set;
calculating a third standard deviation of the third historical energy consumption dataset;
based on the k sigma principle, calculating according to the third historical energy consumption data set and the third standard deviation to obtain the monthly initial energy consumption threshold;
the third formula for calculating the monthly initial energy consumption threshold is as follows:
wherein the content of the first and second substances,
for the monthly initial energy consumption threshold,
the last month energy consumption value in the third historical energy consumption dataset;
and
a 12 th month energy consumption value and a 11 th month energy consumption value, respectively, in the third historical energy consumption dataset prior to the last month energy consumption value,
is the third standard deviation.
Preferably, the real-time energy consumption early warning threshold comprises a daily real-time energy consumption threshold and/or a monthly real-time energy consumption threshold;
the dynamic update module is specifically configured to:
updating the day initial energy consumption early warning threshold once a day according to the updating of the date and the updating energy consumption change trend data in the early warning period to obtain the day real-time energy consumption threshold; and/or updating the monthly initial energy consumption early warning threshold once per month according to the updating of months and the updated energy consumption change trend data in the early warning period to obtain the monthly real-time energy consumption threshold.
Preferably, when the real-time energy consumption early warning threshold is a daily real-time energy consumption threshold, the current energy consumption accumulated value corresponds to a first actual energy consumption accumulated value at the current time of the day, and the future energy consumption predicted value includes a future time energy consumption predicted value corresponding to each future time at the current time of the day;
the early warning judgment module is specifically configured to:
acquiring the first actual energy consumption accumulated value at the current moment of the day, and sequentially acquiring the energy consumption predicted value at each future moment by adopting a data mining method according to the sequence of time from first to last;
according to the sequence of time from first to last, sequentially calculating to obtain the current-day energy consumption early warning value at each future moment according to the first actual energy consumption accumulated value and the energy consumption predicted value at each future moment;
the current time of day istAt the moment, then calculateiThe fourth formula of the energy consumption early warning value at the current day at the future moment is as follows:
wherein the content of the first and second substances,
is composed oftThe time corresponds to the secondiThe energy consumption early warning value of the day at a future moment,X t is composed oftThe first actual accumulated value of energy consumption at a time,x i is composed oftThe time corresponds to the secondiThe predicted value of the energy consumption at the future time,Tis composed oftThe number of hours of the future time corresponding to the time;
comparing the energy consumption early warning value of each day with the real-time energy consumption threshold value of the day degree one by one, and judging whether the energy consumption early warning value of each day is the first dayiWhen the energy consumption early warning value of the current day exceeds the real-time energy consumption threshold value of the day degree, judging that an early warning event occurs;
the early warning notification module is specifically configured to:
the current time of the day of emission isiA first early warning notification corresponding to the future time.
Preferably, when the real-time energy consumption early warning threshold is a monthly real-time energy consumption threshold, the current energy consumption accumulated value corresponds to a second actual energy consumption accumulated value on the current day of the month, and the future energy consumption predicted value includes a one-to-one future daily energy consumption predicted value on each future day of the current day of the month;
the early warning judgment module is specifically configured to:
acquiring the second actual energy consumption accumulated value of the monthly current day, and sequentially acquiring the energy consumption predicted value of each future day by adopting a data mining method according to the sequence of time from first to last;
according to the sequence of time from first to last, sequentially calculating to obtain the energy consumption early warning value in the current month in each future day according to the second actual energy consumption accumulated value and the energy consumption predicted value in each future day;
the month and day aredDay, then calculatejThe fifth formula of the energy consumption early warning value in the current month in the future day is as follows:
wherein the content of the first and second substances,
is composed ofdThe day corresponds tojThe energy consumption early warning value of the current month in the future,M d is composed ofdThe second accumulated actual energy consumption value for the day,n j is composed ofdThe day corresponds tojA future day energy consumption predicted value of a future day,Dis composed ofdThe number of days of the future day to which the day corresponds;
comparing the early warning value of the energy consumption of each month with the monthly real-time energy consumption threshold value one by one, and judging whether the early warning value of the energy consumption of each month is the first monthjWhen the monthly energy consumption early warning value exceeds the monthly real-time energy consumption threshold value, judging that an early warning event occurs;
the early warning notification module is specifically configured to:
the day of the monthjA second warning notification corresponding to the future day.
Third embodiment, based on the first embodiment and the second embodiment, there is further provided an online dynamic energy consumption intelligent early warning device, including a processor, a memory, and a computer program stored in the memory and executable on the processor, where the computer program implements the method steps of S1 to S4 in the first embodiment of fig. 1 when running.
Through the computer program stored in the memory and running on the processor, the intelligent automatic setting of the energy consumption early warning threshold value in the early warning period and the online dynamic real-time updating of the threshold value can be realized, and the blindness, the complexity and the hysteresis of manually configuring the energy consumption early warning threshold value are reduced; the energy consumption accumulated value in the early warning period and the early warning with the predicted value are combined to perform trending and predictive advance early warning, so that the effectiveness of energy consumption early warning is improved, a user is helped to find out unreasonable energy consumption in time, enough time is won to take relevant measures, and the purpose of saving energy is further achieved.
The present embodiment also provides a computer storage medium having at least one instruction stored thereon, where the instruction when executed implements the method steps of S1-S4 in the first embodiment of fig. 1.
By executing a computer storage medium containing at least one instruction, the intelligent automatic setting of the energy consumption early warning threshold value in the early warning period and the online dynamic real-time updating of the threshold value can be realized, and the blindness, the complexity and the hysteresis of manually configuring the energy consumption early warning threshold value are reduced; the energy consumption accumulated value in the early warning period and the early warning with the predicted value are combined to perform trending and predictive advance early warning, so that the effectiveness of energy consumption early warning is improved, a user is helped to find out unreasonable energy consumption in time, enough time is won to take relevant measures, and the purpose of saving energy is further achieved.
Details of the embodiment are not described in detail in the first embodiment and the specific description of fig. 1, which are not repeated herein.
The reader should understand that in the description of this specification, reference to the description of the terms "one embodiment," "some embodiments," "an example," "a specific example" or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. An online dynamic energy consumption intelligent early warning method is characterized by comprising the following steps:
acquiring historical energy consumption change trend data of an early warning object;
determining an initial energy consumption early warning threshold value of the early warning object in an early warning period according to the historical energy consumption change trend data;
acquiring updated energy consumption change trend data of the early warning object in the early warning period, and dynamically updating the initial energy consumption early warning threshold value according to the updated energy consumption change trend data to obtain a real-time energy consumption early warning threshold value;
acquiring a current energy consumption accumulated value and a future energy consumption predicted value of the early warning object in the early warning period; and judging an early warning event according to the current energy consumption accumulated value, the future energy consumption predicted value and the real-time energy consumption early warning threshold value, and sending an early warning notice when the early warning event occurs.
2. The online dynamic energy consumption intelligent early warning method according to claim 1, wherein the initial energy consumption early warning threshold comprises a daily initial energy consumption threshold and/or a monthly initial energy consumption threshold;
determining the initial energy consumption early warning threshold value of the early warning object in the early warning period, specifically including:
and determining the daily initial energy consumption threshold and/or the monthly initial energy consumption threshold according to the historical energy consumption change trend data based on a k sigma principle.
3. The online dynamic energy consumption intelligent early warning method according to claim 2, wherein when the initial energy consumption early warning threshold is specifically the day initial energy consumption threshold, and the day initial energy consumption threshold includes a working day initial energy consumption threshold and a rest day initial energy consumption threshold, determining the initial energy consumption early warning threshold of the early warning object in the early warning period specifically includes:
taking any one day in the early warning period, and if the selected day is a working day, extracting a daily energy consumption value of at least 30 continuous working days before the early warning period from the historical energy consumption change trend data to serve as a first historical energy consumption data set;
respectively calculating a first average value and a first standard deviation of the first historical energy consumption data set;
based on a k sigma principle, calculating according to the first average value and the first standard deviation to obtain the initial energy consumption threshold of the working day;
the first formula for calculating the initial energy consumption threshold value of the working day is as follows:
wherein the content of the first and second substances,
for the initial energy consumption threshold for the working day,
is the first average value of the first average value,
for the purpose of the first standard deviation,kis a standard deviation multiple value set in the k sigma principle;
if the selected day is a rest day, extracting a daily energy consumption value of at least 30 continuous rest days before the early warning period from the historical energy consumption change trend data to serve as a second historical energy consumption data set;
respectively calculating a second average value and a second standard deviation of the second historical energy consumption data set;
calculating to obtain the initial energy consumption threshold value of the rest day according to the second average value and the second standard deviation based on the k sigma principle;
the second formula for calculating the initial energy consumption threshold value of the rest day is as follows:
wherein the content of the first and second substances,
an initial energy consumption threshold for the day of rest,
in order to be said second average value,
is the second standard deviation.
4. The online dynamic energy consumption intelligent early warning method according to claim 2, wherein when the initial energy consumption early warning threshold is specifically the monthly initial energy consumption threshold, determining the initial energy consumption early warning threshold of the early warning object in the early warning period specifically includes:
extracting a monthly energy consumption value of at least 13 continuous months before the early warning period from the historical energy consumption change trend data as a third historical energy consumption data set;
calculating a third standard deviation of the third historical energy consumption dataset;
based on the k sigma principle, calculating according to the third historical energy consumption data set and the third standard deviation to obtain the monthly initial energy consumption threshold;
the third formula for calculating the monthly initial energy consumption threshold is as follows:
wherein the content of the first and second substances,
for the monthly initial energy consumption threshold,
the last month energy consumption value in the third historical energy consumption dataset;
and
a 12 th month energy consumption value and a 11 th month energy consumption value, respectively, in the third historical energy consumption dataset prior to the last month energy consumption value,
is the third standard deviation.
5. The online dynamic energy consumption intelligent early warning method according to claim 2, wherein the real-time energy consumption early warning threshold comprises a daily real-time energy consumption threshold and/or a monthly real-time energy consumption threshold;
dynamically updating the initial energy consumption early warning threshold value to obtain the real-time energy consumption early warning threshold value, which specifically includes:
updating the day initial energy consumption early warning threshold once a day according to the updating of the date and the updating energy consumption change trend data in the early warning period to obtain the day real-time energy consumption threshold; and/or updating the monthly initial energy consumption early warning threshold once per month according to the updating of months and the updated energy consumption change trend data in the early warning period to obtain the monthly real-time energy consumption threshold.
6. The on-line dynamic energy consumption intelligent early warning method according to claim 5, wherein when the real-time energy consumption early warning threshold is a daily real-time energy consumption threshold, the current energy consumption accumulated value corresponds to a first actual energy consumption accumulated value at a current time of day, and the future energy consumption predicted value comprises a one-to-one future time energy consumption predicted value at each future time of the current time of day;
and judging an early warning event according to the current energy consumption accumulated value, the future energy consumption predicted value and the real-time energy consumption early warning threshold value, and sending an early warning notice when the early warning event occurs, wherein the early warning notice specifically comprises the following steps:
acquiring the first actual energy consumption accumulated value at the current moment of the day, and sequentially acquiring the energy consumption predicted value at each future moment by adopting a data mining method according to the sequence of time from first to last;
according to the sequence of time from first to last, sequentially calculating to obtain the current-day energy consumption early warning value at each future moment according to the first actual energy consumption accumulated value and the energy consumption predicted value at each future moment;
the current time of day istAt the moment, then calculateiThe fourth formula of the energy consumption early warning value at the current day at the future moment is as follows:
wherein the content of the first and second substances,
is composed oftThe time corresponds to the secondiThe energy consumption early warning value of the day at a future moment,X t is composed oftThe first actual accumulated value of energy consumption at a time,x i is composed oftThe time corresponds to the secondiThe predicted value of the energy consumption at the future time,Tis composed oftThe number of hours of the future time corresponding to the time;
comparing the energy consumption early warning value of each day with the real-time energy consumption threshold value of the day degree one by one, and judging whether the energy consumption early warning value of each day is the first dayiWhen the energy consumption early warning value of the current day exceeds the real-time energy consumption threshold value of the current day, judging that an early warning event occurs, and sending that the current day of the current day is at the first momentiA first early warning notification corresponding to the future time.
7. The on-line dynamic energy consumption intelligent warning method of claim 5, wherein when the real-time energy consumption warning threshold is a monthly real-time energy consumption threshold, the current energy consumption accumulated value corresponds to a second actual energy consumption accumulated value on the same day as a month, and the future energy consumption predicted value comprises a one-to-one future day energy consumption predicted value on each future day on the same day as a month;
and judging an early warning event according to the current energy consumption accumulated value, the future energy consumption predicted value and the real-time energy consumption early warning threshold value, and sending an early warning notice when the early warning event occurs, wherein the early warning notice specifically comprises the following steps:
acquiring the second actual energy consumption accumulated value of the monthly current day, and sequentially acquiring the energy consumption predicted value of each future day by adopting a data mining method according to the sequence of time from first to last;
according to the sequence of time from first to last, sequentially calculating to obtain the energy consumption early warning value in the current month in each future day according to the second actual energy consumption accumulated value and the energy consumption predicted value in each future day;
the month and day aredDay, then calculatejThe fifth formula of the energy consumption early warning value in the current month in the future day is as follows:
wherein the content of the first and second substances,
is composed ofdThe day corresponds tojThe energy consumption early warning value of the current month in the future,M d is composed ofdThe second accumulated actual energy consumption value for the day,n j is composed ofdThe day corresponds tojA future day energy consumption predicted value of a future day,Dis composed ofdThe number of days of the future day to which the day corresponds;
comparing the early warning value of the energy consumption of each month with the monthly real-time energy consumption threshold value one by one, and judging whether the early warning value of the energy consumption of each month is the first monthjWhen the energy consumption early warning value of the current month exceeds the monthly real-time energy consumption threshold value, judging that an early warning event occurs, and sending out the monthly current dayjA second warning notification corresponding to the future day.
8. An online dynamic energy consumption intelligent early warning system is characterized by being applied to the online dynamic energy consumption intelligent early warning method as claimed in any one of claims 1 to 7, and comprising a data acquisition module, an initial energy consumption threshold value determination module, a dynamic updating module, an early warning judgment module and an early warning notification module;
the data acquisition module is used for acquiring historical energy consumption change trend data of the early warning object;
the initial energy consumption threshold determining module is used for determining an initial energy consumption early warning threshold of the early warning object in an early warning period according to the historical energy consumption change trend data;
the data acquisition module is further used for acquiring the updated energy consumption change trend data of the early warning object in the early warning period;
the dynamic updating module is used for dynamically updating the initial energy consumption early warning threshold value according to the updated energy consumption change trend data to obtain a real-time energy consumption early warning threshold value;
the early warning judgment module is used for acquiring a current energy consumption accumulated value and a future energy consumption predicted value of the early warning object in the early warning period; judging an early warning event according to the current energy consumption accumulated value, the future energy consumption predicted value and the real-time energy consumption early warning threshold value;
and the early warning notification module is used for sending out early warning notification when an early warning event occurs.
9. An online dynamic energy consumption intelligent early warning device, which is characterized by comprising a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein the computer program realizes the steps of the online dynamic energy consumption intelligent early warning method according to any one of claims 1 to 7 when running.
10. A computer storage medium, the computer storage medium comprising: at least one instruction which, when executed, implements the steps of the online dynamic energy consumption intelligent warning method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011142911.XA CN111967697A (en) | 2020-10-23 | 2020-10-23 | Online dynamic energy consumption intelligent early warning method, system, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011142911.XA CN111967697A (en) | 2020-10-23 | 2020-10-23 | Online dynamic energy consumption intelligent early warning method, system, device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111967697A true CN111967697A (en) | 2020-11-20 |
Family
ID=73387177
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011142911.XA Pending CN111967697A (en) | 2020-10-23 | 2020-10-23 | Online dynamic energy consumption intelligent early warning method, system, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111967697A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112946231A (en) * | 2021-02-04 | 2021-06-11 | 成都秦川物联网科技股份有限公司 | Natural gas full-period energy metering system and method |
| CN113341774A (en) * | 2021-05-31 | 2021-09-03 | 浙江锐博科技工程有限公司 | Large-scale public building energy consumption monitoring system |
| CN114110434A (en) * | 2021-11-23 | 2022-03-01 | 中海石油气电集团有限责任公司 | Online digital energy-saving diagnosis and regulation and control method and system for LNG receiving station |
| CN115377975A (en) * | 2022-10-24 | 2022-11-22 | 国网浙江省电力有限公司宁波市北仑区供电公司 | Power distribution control method and power distribution control system |
| US11592323B2 (en) | 2021-02-04 | 2023-02-28 | Chengdu Qinchuan Iot Technology Co., Ltd. | Methods and systems for measuring energy of natural gas in a full cycle |
| CN115907494A (en) * | 2023-01-06 | 2023-04-04 | 碳管家智能云平台有限公司 | Energy consumption double-control management method, equipment and medium based on regional energy consumption budget |
| CN117873299A (en) * | 2024-01-02 | 2024-04-12 | 江苏锦花电子股份有限公司 | Equipment energy supply data monitoring method and system based on big data |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103329161A (en) * | 2011-07-13 | 2013-09-25 | 日东电工株式会社 | On-demand power control system, on-demand power control system program, and computer-readable recording medium recorded with said program |
| CN103853918A (en) * | 2014-02-21 | 2014-06-11 | 南京邮电大学 | Cloud computing server dispatching method based on idle time prediction |
| CN105204333A (en) * | 2015-08-26 | 2015-12-30 | 东北大学 | Energy consumption prediction method for improving energy utilization rate of iron and steel enterprise |
| CN105259847A (en) * | 2015-10-15 | 2016-01-20 | 深圳市万嘉明科技发展有限公司 | Energy management control method and system based on energy consumption historical data analysis |
| CN107464113A (en) * | 2017-07-27 | 2017-12-12 | 无锡雅座在线科技股份有限公司 | The risk of trading activity determines method and device |
| CN108429649A (en) * | 2018-03-23 | 2018-08-21 | 国家计算机网络与信息安全管理中心 | The system that synthesis based on multiple single type collection result judges extremely |
| CN110188932A (en) * | 2019-05-20 | 2019-08-30 | 国核电力规划设计研究院有限公司 | Consumption of data center prediction technique based on evaluation optimization |
| CN111275185A (en) * | 2020-01-16 | 2020-06-12 | 珠海格力电器股份有限公司 | Energy use state early warning method, device, equipment and storage medium |
-
2020
- 2020-10-23 CN CN202011142911.XA patent/CN111967697A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103329161A (en) * | 2011-07-13 | 2013-09-25 | 日东电工株式会社 | On-demand power control system, on-demand power control system program, and computer-readable recording medium recorded with said program |
| CN103853918A (en) * | 2014-02-21 | 2014-06-11 | 南京邮电大学 | Cloud computing server dispatching method based on idle time prediction |
| CN105204333A (en) * | 2015-08-26 | 2015-12-30 | 东北大学 | Energy consumption prediction method for improving energy utilization rate of iron and steel enterprise |
| CN105259847A (en) * | 2015-10-15 | 2016-01-20 | 深圳市万嘉明科技发展有限公司 | Energy management control method and system based on energy consumption historical data analysis |
| CN107464113A (en) * | 2017-07-27 | 2017-12-12 | 无锡雅座在线科技股份有限公司 | The risk of trading activity determines method and device |
| CN108429649A (en) * | 2018-03-23 | 2018-08-21 | 国家计算机网络与信息安全管理中心 | The system that synthesis based on multiple single type collection result judges extremely |
| CN110188932A (en) * | 2019-05-20 | 2019-08-30 | 国核电力规划设计研究院有限公司 | Consumption of data center prediction technique based on evaluation optimization |
| CN111275185A (en) * | 2020-01-16 | 2020-06-12 | 珠海格力电器股份有限公司 | Energy use state early warning method, device, equipment and storage medium |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112946231A (en) * | 2021-02-04 | 2021-06-11 | 成都秦川物联网科技股份有限公司 | Natural gas full-period energy metering system and method |
| US11592323B2 (en) | 2021-02-04 | 2023-02-28 | Chengdu Qinchuan Iot Technology Co., Ltd. | Methods and systems for measuring energy of natural gas in a full cycle |
| CN113341774A (en) * | 2021-05-31 | 2021-09-03 | 浙江锐博科技工程有限公司 | Large-scale public building energy consumption monitoring system |
| CN114110434A (en) * | 2021-11-23 | 2022-03-01 | 中海石油气电集团有限责任公司 | Online digital energy-saving diagnosis and regulation and control method and system for LNG receiving station |
| CN114110434B (en) * | 2021-11-23 | 2023-10-27 | 中海石油气电集团有限责任公司 | Online digital energy-saving diagnosis and regulation method and system for LNG receiving station |
| CN115377975A (en) * | 2022-10-24 | 2022-11-22 | 国网浙江省电力有限公司宁波市北仑区供电公司 | Power distribution control method and power distribution control system |
| CN115377975B (en) * | 2022-10-24 | 2023-04-18 | 国网浙江省电力有限公司宁波市北仑区供电公司 | Power distribution control method and power distribution control system |
| CN115907494A (en) * | 2023-01-06 | 2023-04-04 | 碳管家智能云平台有限公司 | Energy consumption double-control management method, equipment and medium based on regional energy consumption budget |
| CN117873299A (en) * | 2024-01-02 | 2024-04-12 | 江苏锦花电子股份有限公司 | Equipment energy supply data monitoring method and system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111967697A (en) | Online dynamic energy consumption intelligent early warning method, system, device and storage medium | |
| CN105279603B (en) | Dynamically configurable big data analysis system and method | |
| CN110297711A (en) | Batch data processing method, device, computer equipment and storage medium | |
| CN110909006B (en) | Method, device, computer equipment and storage medium for data synchronization | |
| CN112762576A (en) | Air conditioning system control method, temperature reaching time prediction model training method and equipment | |
| CN111143060B (en) | GPU resource scheduling method and device and GPU | |
| DE112012005419T5 (en) | System and method for efficient service-oriented energy management in the Internet of Things | |
| DE112011105886T5 (en) | Management of a plant | |
| CN109003107A (en) | Region partitioning method and device | |
| CN108876015A (en) | Gas station's product oil inventory's dynamic monitoring method for early warning under environment of internet of things based on scene | |
| TW201737084A (en) | Abnormality monitoring method and device | |
| CN111522864B (en) | Enterprise production mode recognition and transfer production early warning method based on electricity consumption data | |
| CN105652812A (en) | System for pre-scheduling special-batch cargos, and method | |
| CN111008727A (en) | Power distribution station load prediction method and device | |
| CN111142942A (en) | Window data processing method and device, server and storage medium | |
| CN111242602A (en) | Control method and device of payment equipment, computer readable storage medium and equipment | |
| CN112131081A (en) | Fault alarm parameter adjusting method and device, electronic equipment and storage medium | |
| CN109146134A (en) | Part amount prediction technique, system, equipment and storage medium are pulled in a kind of peak | |
| CN114756595A (en) | Data processing method for database and related device | |
| CN110570246A (en) | Internet marketing system flow segmentation method, system, equipment and medium | |
| CN111522845B (en) | Watermark issuing method of stream computing system based on time sequence prediction | |
| US10616153B2 (en) | Real-time communications system with intelligent presence indication | |
| CN113835626B (en) | Method and device for determining usable time length of disk | |
| CN112800089B (en) | Intermediate data storage level adjusting method, storage medium and computer equipment | |
| JP6427049B2 (en) | Peak power generation prediction apparatus and prediction method |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201120 |
|
| RJ01 | Rejection of invention patent application after publication |