Intelligent power distribution electrical energy monitoring system and working methodTechnical field
The present invention relates to intelligent power distribution field, belong to a kind of intelligent power distribution electrical energy monitoring system and working method.
Background technique
Attention with country to energy-saving and emission-reduction, energy management systems at different levels and reducing energy consumption project start successively, are skillEnergy emission reduction provides data support and system service.But for the metering object of different type, different industries, different geographical,How to judge that it, with that can be mutated, is a relatively difficult problem.
Currently, in existing energy consumption management system at different levels, for the judgement of uprushing with energy, substantially using simpleAbsolute value or relative value judgment mode, this mode is for measuring the historical data of object using insufficient, and for meterThe habitual variation of amount object energy cannot be considered in terms of.
Summary of the invention
The purpose of the present invention is to provide a kind of intelligent power distribution electrical energy monitoring system and working methods, can be towards differentWith object can be measured, energy consumption abrupt information is obtained with energy data in conjunction with history, more efficiently and accurately identifies energy consumption mutation.
In order to achieve the above objectives, the invention provides the following technical scheme:
A kind of intelligent power distribution electrical energy monitoring system, be suitable for needing to carry out energy consumption mutation judgement uses energy object, the intelligenceEnergy power-distribution electric energy monitoring system includes acquisition device, processing unit, prior-warning device；
The acquisition device is electrically connected with processing unit, is configured to use energy according to the frequency acquisition of a setting to acquireValue；
The frequency acquisition of the setting refers to,
As unit of one day, several each use with energy object judged with energy period, acquisition were divided by one dayThe use of energy period can be worth；
The processing unit is based on Fuzzy Pattern Recognition Theory, comprehensive to obtain according to historical data using following formulaBy the statistical indicator K (n) of judge object n-th of use energy period on the day of:
K (n)=(X (n)/X (n-1)) * (Y (n-1)/Y (n))
+(X(n)/X(day_n-1))*(Y(day_n-1)/Y(n))
+(X(n)/X(month_day_n-1))*(Y(month_day_n-1)/Y(n))
+(X(n)/X(year_month_day_n-1))*(Y(year_month_day_n-1)/Y(n))
Wherein, X (n) indicate the same day n-th with can the period use can be worth, X (n-1) indicate the same day (n-1) it is a use energy whenThe use of section can be worth；
Y (n) indicate n-th of same day with can the period with can statistical indicator, Y (n-1) indicates the same day the (n-1) is a to use energyUsing for period can statistical indicator；
X (day_n-1) indicates that a use of energy period of (n-1) of the previous day can be worth, and Y (day_n-1) indicates the previous day(n-1) it is a with can period with can statistical indicator；
X (month_day_n-1) indicates that a use of energy period of (n-1) of the same day of the previous moon can be worth, Y(month_day_n-1) indicating that (n-1) of the same day of the previous moon is a uses using for energy period can statistical indicator；
The processing unit is electrically connected with prior-warning device, is configured to set in response to the statistical indicator K (n) of acquisition beyond oneDetermine threshold value, generates an alarm command and be sent to prior-warning device；
The prior-warning device sends a warning information to a setting user terminal in response to alarm command.
System is monitored based on aforementioned intelligent power-distribution electric energy, the present invention further mentions a kind of work of intelligent power distribution electrical energy monitoring systemMake method, comprising:
Step 1 was divided into several with the energy period for one day；
Step 2, acquisition one can be worth by each of judge object use of energy period；
Step 3 is based on Fuzzy Pattern Recognition Theory, calculates by judge object on the day of n-th with energy according to following formulaThe statistical indicator K (n) of period:
K (n)=(X (n)/X (n-1)) * (Y (n-1)/Y (n))
+(X(n)/X(day_n-1))*(Y(day_n-1)/Y(n))
+(X(n)/X(month_day_n-1))*(Y(month_day_n-1)/Y(n))
+(X(n)/X(year_month_day_n-1))*(Y(year_month_day_n-1)/Y(n))
Wherein, X (n) indicate the same day n-th with can the period use can be worth, X (n-1) indicate the same day (n-1) it is a use energy whenThe use of section can be worth；
Y (n) indicate n-th of same day with can the period with can statistical indicator, Y (n-1) indicates the same day the (n-1) is a to use energyUsing for period can statistical indicator；
X (day_n-1) indicates that a use of energy period of (n-1) of the previous day can be worth, and Y (day_n-1) indicates the previous day(n-1) it is a with can period with can statistical indicator；
X (month_day_n-1) indicates that a use of energy period of (n-1) of the same day of the previous moon can be worth, Y(month_day_n-1) indicating that (n-1) of the same day of the previous moon is a uses using for energy period can statistical indicator；
Step 4, using Theory of Fuzzy Comprehensive, judge rank according to the historical data of statistical indicator K (n) is comprehensive to obtainLadder.
Further, in step 4, using expert's aid decision, rank is judged with that can be accustomed to obtain according to judge objectLadder.
Further, in step 4, using historical data self-learning algorithm, ladder codomain is determined, to obtain judge ladder.
Further, in step 4, by adjusting time granularity, to adjust the judgment basis of Theory of Fuzzy Comprehensive.
Further, in step 3, the energy statistical indicator refers to, in the setting time depth before the period, leads toThe statistical value that counts that historical data self-learning algorithm is crossed to obtain.
Further, the historical data self-learning algorithm includes normal distribution algorithm, trend analysis algorithm, linear regressionAlgorithm.
The beneficial effects of the present invention are:
1) value for sufficiently excavating historical data, according to the historical data of each metering object, to correct its calculation formula,Give full play to the effect that historical data calculates mutation analysis.
It 2), should be the result is that a design factor, so that different meters using abstract calculated result as mutation judgment basisThe objective difference (can be such as accustomed to energy scale, use) for calculating object, no longer influences mutation judgement, the normalization with realization to resultProcessing.
3) for calculated result, the ability of mining again and analysis is provided, is allowed in the range of more wide area,The data of different type equipment are collected, and to analysis result perpendicular evaluation energy catastrophe.
The above description is only an overview of the technical scheme of the present invention, in order to better understand the technical means of the present invention,And can be implemented in accordance with the contents of the specification, the following is a detailed description of the preferred embodiments of the present invention and the accompanying drawings.
Detailed description of the invention
Fig. 1 is the structure chart of intelligent power distribution electrical energy monitoring system of the invention.
Fig. 2 is the evaluation method flow chart of intelligent power distribution electrical energy monitoring system of the invention.
Specific embodiment
With reference to the accompanying drawings and examples, specific embodiments of the present invention will be described in further detail.Implement belowExample is not intended to limit the scope of the invention for illustrating the present invention.
In conjunction with Fig. 1, Fig. 2, the present invention refers to a kind of intelligent power distribution electrical energy monitoring system, is suitable for needing to carry out energy consumption mutationEnergy object is used in judgement, and the intelligent power distribution electrical energy monitoring system includes acquisition device 10, processing unit 20, prior-warning device 30.
The acquisition device 10 is electrically connected with processing unit 20, is configured to the frequency acquisition according to a setting to acquire useIt can value.
The frequency acquisition of the setting refers to,
As unit of one day, several each use with energy object judged with energy period, acquisition were divided by one dayThe use of energy period can be worth.
Division uses the energy period more, and obtained evaluation result is more accurate.
The processing unit is based on Fuzzy Pattern Recognition Theory, comprehensive to obtain according to historical data using following formulaBy the statistical indicator K (n) of judge object n-th of use energy period on the day of:
K (n)=(X (n)/X (n-1)) * (Y (n-1)/Y (n))
+(X(n)/X(day_n-1))*(Y(day_n-1)/Y(n))
+(X(n)/X(month_day_n-1))*(Y(month_day_n-1)/Y(n))
+(X(n)/X(year_month_day_n-1))*(Y(year_month_day_n-1)/Y(n))
Wherein, X (n) indicate the same day n-th with can the period use can be worth, X (n-1) indicate the same day (n-1) it is a use energy whenThe use of section can be worth.
Y (n) indicate n-th of same day with can the period with can statistical indicator, Y (n-1) indicates the same day the (n-1) is a to use energyUsing for period can statistical indicator.
X (day_n-1) indicates that a use of energy period of (n-1) of the previous day can be worth, and Y (day_n-1) indicates the previous day(n-1) it is a with can period with can statistical indicator.
X (month_day_n-1) indicates that a use of energy period of (n-1) of the same day of the previous moon can be worth, Y(month_day_n-1) indicating that (n-1) of the same day of the previous moon is a uses using for energy period can statistical indicator.
The processing unit 20 is electrically connected with prior-warning device 30, is configured to surpass in response to the statistical indicator K (n) of acquisitionA given threshold out generates an alarm command and is sent to prior-warning device 30.
The prior-warning device 30 sends a warning information to a setting user terminal, such as mobile phone, pc in response to alarm commandEnd, tablet computer etc., the warning information of transmission can preset content, be also possible to the statistical indicator beyond given thresholdK (n) information.
System is monitored based on aforementioned intelligent power-distribution electric energy, the present invention further mentions a kind of work of intelligent power distribution electrical energy monitoring systemMake method, comprising:
Step 1 was divided into several with the energy period for one day.
Step 2, acquisition one can be worth by each of judge object use of energy period.
Step 3 is based on Fuzzy Pattern Recognition Theory, calculates by judge object on the day of n-th with energy according to following formulaThe statistical indicator K (n) of period:
K (n)=(X (n)/X (n-1)) * (Y (n-1)/Y (n))
+(X(n)/X(day_n-1))*(Y(day_n-1)/Y(n))
+(X(n)/X(month_day_n-1))*(Y(month_day_n-1)/Y(n))
+(X(n)/X(year_month_day_n-1))*(Y(year_month_day_n-1)/Y(n))
Wherein, X (n) indicate the same day n-th with can the period use can be worth, X (n-1) indicate the same day (n-1) it is a use energy whenThe use of section can be worth.
Y (n) indicate n-th of same day with can the period with can statistical indicator, Y (n-1) indicates the same day the (n-1) is a to use energyUsing for period can statistical indicator.
X (day_n-1) indicates that a use of energy period of (n-1) of the previous day can be worth, and Y (day_n-1) indicates the previous day(n-1) it is a with can period with can statistical indicator.
X (month_day_n-1) indicates that a use of energy period of (n-1) of the same day of the previous moon can be worth, Y(month_day_n-1) indicating that (n-1) of the same day of the previous moon is a uses using for energy period can statistical indicator.
Preferably, the energy statistical indicator refers to, in the setting time depth before the period, passes through historical dataCount statistical value of the self-learning algorithm to obtain.
The historical data self-learning algorithm includes normal distribution algorithm, trend analysis algorithm, linear regression algorithm.
Step 4, using Theory of Fuzzy Comprehensive, judge rank according to the historical data of statistical indicator K (n) is comprehensive to obtainLadder.
In some instances, using expert's aid decision as Theory of Fuzzy Comprehensive, energy is used according to judge objectHabit is to obtain judge ladder.
In other examples, using historical data self-learning algorithm as Theory of Fuzzy Comprehensive, step values are determinedDomain, to obtain judge ladder.
Further, by adjusting time granularity, to adjust the judgment basis of Theory of Fuzzy Comprehensive, to adapt to notSame use, which can be worth, judges accuracy requirement.
Each technical characteristic of embodiment described above can be combined arbitrarily, for simplicity of description, not to above-mentioned realityIt applies all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not depositedIn contradiction, all should be considered as described in this specification.
The embodiments described above only express several embodiments of the present invention, and the description thereof is more specific and detailed, but simultaneouslyIt cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the artIt says, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to protection of the inventionRange.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.