CN109785184A - Normal energy consumption interval computation method, abnormal energy consumption data detection method and device - Google Patents
Normal energy consumption interval computation method, abnormal energy consumption data detection method and device Download PDFInfo
- Publication number
- CN109785184A CN109785184A CN201811627185.3A CN201811627185A CN109785184A CN 109785184 A CN109785184 A CN 109785184A CN 201811627185 A CN201811627185 A CN 201811627185A CN 109785184 A CN109785184 A CN 109785184A
- Authority
- CN
- China
- Prior art keywords
- energy consumption
- data
- mode
- normal
- detected
- 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 277
- 238000000034 method Methods 0.000 title claims abstract description 54
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 49
- 238000001514 detection method Methods 0.000 title claims abstract description 38
- 241001269238 Data Species 0.000 claims abstract description 16
- 230000015654 memory Effects 0.000 claims description 20
- 230000002123 temporal effect Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 2
- 230000001052 transient effect Effects 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000012360 testing method Methods 0.000 description 4
- 238000013450 outlier detection Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003116 impacting effect Effects 0.000 description 1
- 238000005057 refrigeration Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of normal energy consumption interval computation method, abnormal energy consumption data detection method and device, which includes: to obtain several energy consumption sample datas, and obtain the corresponding acquisition parameter information of each energy consumption sample data；Energy consumption sample data is assigned under several predetermined power consumption modes according to acquisition parameter information；The normal energy consumption section under each predetermined power consumption mode is calculated according to the energy consumption sample data under each predetermined power consumption mode.By based on the energy consumption sample data got and the corresponding acquisition parameter information of energy consumption sample data, energy consumption sample data is assigned under several predetermined power consumption modes, and calculate the normal energy consumption section under each predetermined power consumption mode, when making subsequent energy consumption data detection abnormal based on the progress of normal energy consumption section, the normal energy consumption section under corresponding predetermined power consumption mode can be chosen, according to the acquisition parameter information of energy consumption data to be detected so as to improve the detection accuracy of abnormal energy consumption number detection.
Description
Technical field
The present invention relates to data monitoring technical field more particularly to a kind of normal energy consumption interval computation methods, offline view
Detection and analysis device, electronic equipment and the computer readable storage medium of frequency.
Background technique
In building energy management system, need acquire and transmit data volume it is very big, but due to current instrumentation,
The reasons such as error in the reason of equipment such as data collector itself and network transmission process cause in data acquisition, are transmitted across
Phenomena such as inevitably will appear leak source, misinformation in journey, so that some sampled data missings, zero data and apparent abnormal number can be generated
According to, and the authenticity of data directly affects the reliability, accuracy and positioning problems of application layer analysis, therefore should cause enough
Pay attention to.
Currently, to solve the above-mentioned problems, many companies or producer also grind in the correlation for actively doing data exception detection
Study carefully, wherein relatively common is that data monitoring is carried out using quota method, and this method for judging abnormal energy consumption data is substantially
Dependent on experience (expert or user observe for a long time), and industry index is referred to, fixed threshold value is set, when energy consumption data is super
It is judged as abnormal data when quota out.But due in practical application scene with can situation also by weather, time etc. because
The influence of element, and when factor generates variation, the fluctuation with energy data is more obvious, therefore, (just using single quotum of data
Normal energy consumption section) carry out energy consumption data whether Yi Chang judgement, it is likely that will appear and normal data is determined as abnormal data, or
The mode of the case where abnormal data is determined as normal data by person, i.e., the existing single normal energy consumption section of determination can make determination
The reasonability in normal energy consumption section is poor, to make subsequent based on the single normal abnormal energy consumption data detection of energy consumption section progress
The accuracy of obtained testing result is lower.
Summary of the invention
In view of this, the embodiment of the invention provides a kind of normal energy consumption interval computation methods, abnormal energy consumption data detection
Method and device can make the reasonable of determining normal energy consumption section in a manner of solving the single normal energy consumption section of existing determination
Property it is poor, subsequent testing result when carrying out abnormal energy consumption data detection based on the single normal energy consumption section, obtained it is accurate
The lower problem of property.
According in a first aspect, including the following steps: the embodiment of the invention provides a kind of normal energy consumption interval computation method
Several energy consumption sample datas are obtained, and obtain the corresponding acquisition parameter information of each energy consumption sample data；Believed according to acquisition parameter
Energy consumption sample data is assigned under several predetermined power consumption modes by breath；According to the energy consumption sample number under each predetermined power consumption mode
According to the normal energy consumption section calculated under each predetermined power consumption mode.
By based on the energy consumption sample data got and the corresponding acquisition parameter information of energy consumption sample data, by energy consumption
Sample data is assigned under several predetermined power consumption modes, and calculates the normal energy consumption section under each predetermined power consumption mode, is made
When subsequent energy consumption data detection abnormal based on the progress of normal energy consumption section, it can be believed according to the acquisition parameter of energy consumption data to be detected
Breath chooses the normal energy consumption section under corresponding predetermined power consumption mode, based on examining for the acquisition parameter information to influence energy situation
Amount keeps determining normal energy consumption section more reasonable, so as to improve the detection accuracy of abnormal energy consumption number detection.
With reference to first aspect, in first aspect first embodiment, several energy consumption sample datas are obtained, and are obtained each
The step of energy consumption sample data corresponding acquisition parameter information, comprising: all historical energy consumption datas in predetermined amount of time are obtained,
And obtain the corresponding acquisition parameter information of each historical energy consumption data；The data incomplete in historical energy consumption data is rejected, is obtained several
A intermediate sample data；Intermediate sample data is detected using abnormal point method of determining and calculating；It rejects by abnormal point method of determining and calculating
Abnormal intermediate sample data are detected as, several energy consumption sample datas and its corresponding acquisition parameter information are obtained.
It is different by being rejected after the historical energy consumption data progress data incomplete rejecting and Outlier Detection Algorithm detection to acquisition
The validity of the pretreatment often put, the energy consumption sample data made improves, so as to prevent exceptional sample data to calculating
The reasonability in obtained normal energy consumption section impacts, and the method based on the embodiment of the present invention that further increases obtains normal
Energy consumption section carries out detection accuracy when abnormal energy consumption number detection.
With reference to first aspect or first aspect first embodiment, in first aspect second embodiment, acquisition parameter
Information includes the acquisition time information of data, and predetermined power consumption mode includes working day mode and nonworkdays mode.
With reference to first aspect or first aspect first embodiment, in first aspect third embodiment, acquisition parameter
Information includes the acquisition time information of data, and predetermined power consumption mode includes work hours on working day mode, quitting time on working day
Mode and nonworkdays mode.
With reference to first aspect or first aspect first embodiment, in the 4th embodiment of first aspect, acquisition parameter
Information includes the acquisition time information and temperature collection information of data, and predetermined power consumption mode includes on the first temperature range working day
Class time mode, second temperature range work hours on working day mode, third temperature range work hours on working day mode, first
Temperature range quitting time on working day mode, second temperature range quitting time on working day mode, third temperature range working day
Quitting time mode and nonworkdays mode.
According to second aspect, the embodiment of the invention provides a kind of abnormal energy consumption data detection methods, include the following steps:
Obtain the acquisition parameter information of energy consumption data to be detected and energy consumption data to be detected；According to acquisition parameter acquisition of information with it is to be detected
Normal energy consumption section under the corresponding predetermined power consumption mode of energy consumption data；Normal energy consumption section is to use first aspect or first
Normal energy consumption interval computation method described in any one embodiment of aspect is calculated；Judging energy consumption data to be detected is
It is no to fall into the range of normal energy consumption section；When energy consumption data to be detected is not fallen in the range of normal energy consumption section, determine
Energy consumption data to be detected is abnormal data.
By the acquisition parameter acquisition of information based on energy consumption data to be detected it is corresponding with energy consumption data to be detected it is pre- surely
Normal energy consumption section under consumption mode, and energy consumption data to be detected is made whether abnormal to sentence based on the normal energy consumption section
It is disconnected, be able to solve the testing result accuracy of the existing abnormal energy consumption data detection method based on single normal energy consumption section compared with
Low problem.
In conjunction with second aspect, in second aspect first embodiment, acquisition parameter information includes the acquisition time of data
Information, predetermined power consumption mode include working day mode and nonworkdays mode.
In conjunction with second aspect, in second aspect second embodiment, acquisition parameter information includes the acquisition time of data
Information, predetermined power consumption mode include work hours on working day mode, quitting time on working day mode and nonworkdays mode.
In conjunction with second aspect, in second aspect third embodiment, acquisition parameter information includes the acquisition time of data
Information and temperature collection information, predetermined power consumption mode include the first temperature range work hours on working day mode, second temperature model
Enclose work hours on working day mode, third temperature range work hours on working day mode, the first temperature range working day come off duty when
Between mode, second temperature range quitting time on working day mode, third temperature range quitting time on working day mode and inoperative
Day mode.
According to the third aspect, the embodiment of the invention provides a kind of normal energy consumption interval computation devices, comprising: sample data
Module is obtained, for obtaining several energy consumption sample datas, and obtains the corresponding acquisition parameter information of each energy consumption sample data；Mould
Formula distribution module, for energy consumption sample data to be assigned under several predetermined power consumption modes according to acquisition parameter information；Section
Computing module, for calculating the normal energy consumption area of predetermined power consumption mode according to the energy consumption sample data under each predetermined power consumption mode
Between.
According to fourth aspect, the embodiment of the invention provides a kind of abnormal energy consumption data detection devices, comprising: number to be detected
According to module is obtained, for obtaining the acquisition parameter information of energy consumption data to be detected and energy consumption data to be detected；Section obtains module,
For according to the normal energy consumption section under acquisition parameter acquisition of information predetermined power consumption mode corresponding with energy consumption data to be detected；Just
Normal energy consumption section is to use normal energy consumption interval computation described in any one of first aspect or first aspect embodiment
Method is calculated；Judgment module, for judging whether energy consumption data to be detected falls into the range of normal energy consumption section；As a result
Determining module, for determining energy consumption data to be detected when energy consumption data to be detected is not fallen in the range of normal energy consumption section
For abnormal data.
According to the 5th aspect, the embodiment of the invention provides a kind of electronic equipment, comprising: at least one processor；And
The memory being connect at least one processor communication；Computer instruction is stored in memory, processor is by executing calculating
Machine instruction, thereby executing any of any one embodiment of first aspect, first aspect, second aspect or second aspect
A kind of method described in embodiment.
According to the 6th aspect, the embodiment of the invention provides a kind of computer readable storage medium, computer-readable storage
Medium storing computer instruction, any one implementation that computer instruction is used to that computer to be made to execute first aspect, first aspect
Method described in any one embodiment of mode, second aspect or second aspect.
Detailed description of the invention
It, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution in the prior art
Embodiment or attached drawing needed to be used in the description of the prior art be briefly described, it should be apparent that, it is described below
Attached drawing is some embodiments of the present invention, for those of ordinary skill in the art, before not making the creative labor
It puts, is also possible to obtain other drawings based on these drawings.
Fig. 1 is the flow chart of the normal energy consumption interval computation method in the embodiment of the present invention 1；
Fig. 2 is the specific steps flow chart of the S101 provided in the embodiment of the present invention 1；
Fig. 3 is another flow chart of the normal energy consumption interval computation method in the embodiment of the present invention 1；
Fig. 4 is the flow chart of the abnormal energy consumption data detection method in the embodiment of the present invention 2；
Fig. 5 is the functional block diagram of the normal energy consumption interval computation device in the embodiment of the present invention 3；
Fig. 6 is the functional block diagram of the abnormal energy consumption data detection device in the embodiment of the present invention 3；
Fig. 7 is the hardware structural diagram of the electronic equipment in the embodiment of the present invention 3.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those skilled in the art are not having
Every other embodiment obtained under the premise of creative work is made, shall fall within the protection scope of the present invention.
In the description of the present invention, it should be noted that term " first ", " second ", " third " are used for description purposes only,
It is not understood to indicate or imply relative importance.
Embodiment 1
Fig. 1 shows the flow chart of the normal energy consumption interval computation method of the embodiment of the present invention, as shown in Figure 1, this method can
To include the following steps:
S101 obtains several energy consumption sample datas, and obtains the corresponding acquisition parameter information of each energy consumption sample data.?
Here, acquisition parameter information can adopt to acquire the temporal information (hereinafter referred to as acquisition time information) when energy consumption sample data
Temperature information (hereinafter referred to as temperature collection information) etc. when collecting energy consumption sample data can influence the information with energy situation,
In, acquisition time information can also include acquisition time information and acquisition date information.
Energy consumption sample data is assigned under several predetermined power consumption modes by S102 according to acquisition parameter information.
S103 is calculated normal under each predetermined power consumption mode according to the energy consumption sample data under each predetermined power consumption mode
Energy consumption section.Herein, it can be calculated respectively by way of the threshold value of energy consumption sample data under each predetermined power consumption mode obtaining
The normal energy consumption section of a predetermined power consumption mode, normal energy consumption section at this time refer to the maximum of energy consumption sample data and minimum
Section (including maximum and minimum) between value；It is of course also possible to be calculated each predetermined by based on given confidence level
The confidence interval of energy consumption sample data under power consumption mode, and using confidence interval as the mode in normal energy consumption section, it calculates each
The normal energy consumption section of predetermined power consumption mode.
Specifically, for calculating normal energy consumption section by way of calculating confidence interval, in the embodiment of the present invention
Step S103 may include:
Step A calculates the average value of all energy consumption sample datas under a predetermined power consumption mode
Herein,Wherein, xiRefer to i-th of energy consumption sample data, n refers to a predetermined power consumption mode
Under energy consumption sample data sum.
Step B calculates the mean square deviation S of all energy consumption sample datas under a predetermined power consumption mode.
Herein, Refer to the average value of above-mentioned energy consumption sample data, xiRefer to i-th
Energy consumption sample data, n refer to the energy consumption sample data sum under a predetermined power consumption mode.
Step C is obtained specified confidence level (1- α), and based on all under specified one predetermined power consumption mode of confidence calculations
The confidence interval of energy consumption sample data.
Herein, confidence interval isWherein,Refer to energy
The average value of sample data is consumed, S refers to the mean square deviation of energy consumption sample data, and n refers to energy consumption sample data sum.Wherein, tα/2
(n-1) it can be obtained by inquiring t distribution table.
Step D, using above-mentioned confidence interval as the normal energy consumption section under corresponding predetermined power consumption mode.
The normal energy consumption interval computation method of the embodiment of the present invention, by based on the energy consumption sample data got and energy
The corresponding acquisition parameter information of sample data is consumed, energy consumption sample data is assigned under several predetermined power consumption modes, and is calculated
Normal energy consumption section under each predetermined power consumption mode makes subsequent based on the abnormal energy consumption data detection of normal energy consumption section progress
When, the normal energy consumption area under corresponding predetermined power consumption mode can be chosen according to the acquisition parameter information of energy consumption data to be detected
Between, based on considering for the acquisition parameter information to influence energy situation, keep determining normal energy consumption section more reasonable, so as to
Enough detection accuracies for improving abnormal energy consumption number detection.
As a kind of optional embodiment of the present embodiment, as shown in Fig. 2, S101 may include steps of:
S201 obtains all historical energy consumption datas in predetermined amount of time, and obtains that each historical energy consumption data is corresponding to adopt
Collect parameter information.Herein, the length of preset time period can according to the corresponding time segment length of each historical energy consumption data with
And the case where practical application scenes such as the computational accuracy requirement in normal energy consumption section, is specifically arranged.For example, if one is gone through
The corresponding time segment length of history energy consumption data is a hour, then can set predetermined amount of time to 60 days；If one is gone through
The corresponding time segment length of history energy consumption data is two hours, then can set predetermined amount of time to 120 days；If one is gone through
The corresponding time segment length of history energy consumption data is 1 day, then can set predetermined amount of time to 1 year.Certainly, above-mentioned specific example
The example only lifted convenient for those skilled in the art to the understanding of the embodiment of the present invention should not be constituted to of the invention real
Apply any restrictions of example.
S202 rejects the data incomplete in historical energy consumption data, obtains several intermediate sample data.Herein, defect
Data can be the obvious abnormal datas such as null value data or negative valued data in historical energy consumption data.
S203 detects intermediate sample data using abnormal point method of determining and calculating.Herein, k-means can be based on
Clustering algorithm, difference algorithm, outlier detection algorithm (Local Outlier Factor, LOF) or based on neural network into
Line number it is predicted that the methods of intermediate sample data is detected.
S204, rejecting are detected as abnormal intermediate sample data by abnormal point method of determining and calculating, obtain several energy consumption samples
Data.
The normal energy consumption interval computation method of the embodiment of the present invention, by carrying out defect number to the historical energy consumption data of acquisition
According to the pretreatment of rejecting abnormalities point after rejecting and Outlier Detection Algorithm detection, the validity of the energy consumption sample data made is mentioned
Height further mentions so as to prevent exceptional sample data from impacting to the reasonability in the normal energy consumption section being calculated
Height carries out detection accuracy when abnormal energy consumption number detection based on the normal energy consumption section that the method for the embodiment of the present invention obtains.
Fig. 3 shows the flow chart of the normal energy consumption interval computation method of another embodiment of the present invention, in the present embodiment,
The normal energy consumption of the embodiment of the present invention is described so that acquisition parameter information includes the acquisition time information of energy consumption sample data as an example
Interval computation method.As shown in figure 3, this method may include:
S301 obtains several energy consumption sample datas, and obtains the corresponding acquisition time information of each energy consumption sample data.
Energy consumption sample data is assigned to working day mode or nonworkdays mode according to acquisition time information by S302
Under.Herein, acquisition time information refers to the acquisition date information of sample data, specifically, when the acquisition of energy consumption sample data
When date is working day, which is assigned under working day mode, is when the acquisition date of energy consumption sample data
When nonworkdays, which is assigned under nonworkdays mode.It should be noted that, although conventional working day
For Mon-Fri, nonworkdays is Saturday and Sunday, and still, the division on working day and nonworkdays herein can also basis
Practical application scene is adjusted, for example, Monday to Saturday can be divided into working day, will be divided into nonworkdays on Sunday
Deng.
S303 calculates the normal energy consumption section under working day mode according to the energy consumption sample data under working day mode, and
The normal energy consumption section under nonworkdays mode is calculated according to the energy consumption sample data under nonworkdays mode.
In some other embodiment of the invention, acquisition parameter information includes the acquisition time letter of energy consumption sample data
Breath, predetermined power consumption mode can also include work hours on working day mode, quitting time on working day mode and nonworkdays mode.
Herein, acquisition time information includes that the acquisition time information of energy consumption sample data and acquisition date information specifically work as energy consumption
When the acquisition time of sample data is the workaday work hours, which is assigned to work hours on working day mould
Under formula, when the acquisition time of energy consumption sample data is the workaday quitting time, which is assigned to work
Under day quitting time mode, when the acquisition time of energy consumption sample data is nonworkdays, which is assigned to
Under nonworkdays mode, specifically, referring to step S302, the division on working day and nonworkdays herein and work hours
Division with the quitting time also can be adjusted according to practical application scene.
The particular content of the normal energy consumption interval computation method of the embodiment of the present invention is referred to S301-S303 to understand,
Details are not described herein.
In some other embodiment of the invention, acquisition parameter information includes the acquisition time letter of energy consumption sample data
Breath, when predetermined power consumption mode can also include work hours on working day mode, quitting time on working day mode, nonworkdays working
Between mode and nonworkdays quitting time mode.
In some other embodiment of the invention, acquisition parameter information includes the acquisition time information of energy consumption sample data
With temperature collection information, predetermined power consumption mode includes the first temperature range work hours on working day mode, second temperature range work
Make work hours day mode, third temperature range work hours on working day mode, the first temperature range quitting time on working day mould
Formula, second temperature range quitting time on working day mode, third temperature range quitting time on working day mode and nonworkdays mould
Formula.Herein, the first temperature range, second temperature range and third temperature range can according under different application scene to energy
Situation causes the temperature changed to be divided, and such as according to the temperature for starting heating under different application scene and can start to freeze
Temperature be adjusted, specifically, by taking Jiangsu as an example, the first temperature range can be set to 30 degrees Celsius or more (refrigeration
Temperature range), second temperature range is set as in 10 degrees Celsius to 30 degrees Celsius (normal temperature sections), the setting of third temperature range
For 10 degrees Celsius or less (heating temperature sections).
The particular content of the normal energy consumption interval computation method of the embodiment of the present invention is referred to S301-S303 to understand,
Details are not described herein.
In some other embodiment of the invention, when acquisition parameter information includes the acquisition time letter of energy consumption sample data
When breath and temperature collection information, predetermined power consumption mode can also include the first temperature range work hours on working day mode, second
Temperature range work hours on working day mode, third temperature range work hours on working day mode, the first temperature range working day
Quitting time mode, second temperature range quitting time on working day mode, third temperature range quitting time on working day mode and
Including the first temperature range nonworkdays work hours mode, second temperature range nonworkdays work hours mode, third temperature
Spend range nonworkdays work hours mode, the first temperature range nonworkdays quitting time mode, the non-work of second temperature range
Make quitting time day mode, third temperature range nonworkdays quitting time mode.
Embodiment 2
Fig. 4 shows the flow chart of the abnormal energy consumption data detection method of the embodiment of the present invention, as shown in figure 4, this method can
To include:
S401 obtains the acquisition parameter information of energy consumption data to be detected and energy consumption data to be detected.Herein, acquisition parameter
Information can acquire energy consumption to be detected to acquire the temporal information (hereinafter referred to as acquisition time information) when energy consumption data to be detected
Temperature information (hereinafter referred to as temperature collection information) when data etc. can influence the information with energy situation, wherein acquisition time
Information can also include acquisition time information and acquisition date information.
S402, according to the normal energy under acquisition parameter acquisition of information predetermined power consumption mode corresponding with energy consumption data to be detected
Consume section.Herein, it is root that energy consumption data to be detected and embodiment 1, which are used to calculate the energy consumption sample data in normal energy consumption section,
According to the data that identical collection period acquires, the normal energy consumption section under predetermined power consumption mode is to use any reality in embodiment 1
Normal energy consumption interval computation method described in mode is applied to be calculated.
S403, judges whether energy consumption data to be detected falls into the range of normal energy consumption section.
S404 determines energy consumption data to be detected when energy consumption data to be detected is not fallen in the range of normal energy consumption section
For abnormal data.
The normal energy consumption interval computation method of the embodiment of the present invention is believed by the acquisition parameter based on energy consumption data to be detected
Breath obtains the normal energy consumption section under predetermined power consumption mode corresponding with energy consumption data to be detected, and is based on the normal energy consumption section
It is made whether abnormal judgement to energy consumption data to be detected, is able to solve the existing abnormal energy based on single normal energy consumption section
Consume the lower problem of the testing result accuracy of data detection method.
In some other embodiment of the invention, when acquisition parameter information includes the acquisition time information of data, make a reservation for
Power consumption mode can also include working day mode and nonworkdays mode.Specifically, it is determined that the corresponding mould of energy consumption data to be detected
Formula is the particular content that working day mode is still nonworkdays mode, is referred to embodiment 1 to understand, no longer goes to live in the household of one's in-laws on getting married herein
It states.
In some other embodiment of the invention, when acquisition parameter information includes the acquisition time information of data, make a reservation for
Power consumption mode can also include work hours on working day mode, quitting time on working day mode and nonworkdays mode.Specifically,
Determine that the corresponding mode of energy consumption data to be detected is work hours on working day mode, quitting time on working day mode or inoperative
The particular content of day mode, is referred to embodiment 1 to understand, details are not described herein.
In some other embodiment of the invention, acquisition parameter information includes the acquisition time letter of energy consumption sample data
Breath, when predetermined power consumption mode can also include work hours on working day mode, quitting time on working day mode, nonworkdays working
Between mode and nonworkdays quitting time mode.
In some other embodiment of the invention, acquisition parameter information includes acquisition time information and temperature collection letter
Breath, predetermined power consumption mode include the first temperature range work hours on working day mode, second temperature range work hours on working day
Mode, third temperature range work hours on working day mode, the first temperature range quitting time on working day mode, second temperature model
Enclose quitting time on working day mode, third temperature range quitting time on working day mode and nonworkdays mode.Specifically, it is determined that
The particular content of the corresponding mode of energy consumption data to be detected, is referred to embodiment 1 to understand, details are not described herein.
In some other embodiment of the invention, when acquisition parameter information includes the acquisition time letter of energy consumption sample data
When breath and temperature collection information, predetermined power consumption mode can also include the first temperature range work hours on working day mode, second
Temperature range work hours on working day mode, third temperature range work hours on working day mode, the first temperature range working day
Quitting time mode, second temperature range quitting time on working day mode, third temperature range quitting time on working day mode and
Including the first temperature range nonworkdays work hours mode, second temperature range nonworkdays work hours mode, third temperature
Spend range nonworkdays work hours mode, the first temperature range nonworkdays quitting time mode, the non-work of second temperature range
Make quitting time day mode, third temperature range nonworkdays quitting time mode.
Embodiment 3
Fig. 5 shows a kind of functional block diagram of normal energy consumption interval computation device according to an embodiment of the present invention, the device
It can be used to implement normal energy consumption interval computation method described in embodiment 1 or its any optional embodiment.Such as Fig. 5 institute
Show, which includes that sample data obtains module 10, mode classification module 20 and interval computation module 30.
Sample data obtains module 10 and corresponds to for obtaining several energy consumption sample datas and obtaining each energy consumption sample data
Acquisition parameter information.
Mode classification module 20 is used to that energy consumption sample data to be assigned to several predetermined energy consumptions according to acquisition parameter information
Under mode.
Interval computation module 30 is used to calculate predetermined energy consumption mould according to the energy consumption sample data under each predetermined power consumption mode
The normal energy consumption section of formula.
Fig. 6 shows a kind of functional block diagram of abnormal energy consumption data detection device according to an embodiment of the present invention, the device
It can be used to implement abnormal energy consumption data detection method described in embodiment 2 or its any optional embodiment.Such as Fig. 6 institute
Show, which includes that data to be tested obtain module 40, section obtains module 50 and judgment module 60 and result determining module 70.
Data to be tested obtain the acquisition parameter that module 40 is used to obtain energy consumption data to be detected and energy consumption data to be detected
Information.
Section obtains module 50 and is used for according to acquisition parameter acquisition of information predetermined energy consumption corresponding with energy consumption data to be detected
Normal energy consumption section under mode.Herein, normal energy consumption section is using above-described embodiment 1 or its any optional embodiment party
Normal energy consumption interval computation method described in formula is calculated.
Judgment module 60 is for judging whether energy consumption data to be detected falls into the range of normal energy consumption section.
As a result determining module 70 be used for when energy consumption data to be detected is not fallen in the range of normal energy consumption section, determine to
Detection energy consumption data is abnormal data.
The embodiment of the invention also provides a kind of electronic equipment, as shown in fig. 7, the electronic equipment may include processor 71
With memory 72, wherein processor 71 can be connected with memory 72 by bus or other modes, to pass through bus in Fig. 7
For connection.
Processor 71 can be central processing unit (Central Processing Unit, CPU).Processor 71 can be with
For other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
The combination of the chips such as discrete hardware components or above-mentioned all kinds of chips.
Memory 72 is used as a kind of non-transient computer readable storage medium, can be used for storing non-transient software program, non-
Transient computer executable program and module, such as the normal energy consumption interval computation method or abnormal energy consumption in the embodiment of the present invention
Corresponding program instruction/the module of data detection method is (for example, the sample data shown in Fig. 5 obtains module 10, mode classification module
20 and the interval computation module 30 or data to be tested shown in Fig. 6 obtain module 40, section obtains module 50 and judgment module
60 and result determining module 70).Processor 71 by operation be stored in memory 72 non-transient software program, instruction and
Module, thereby executing the various function application and data processing of processor, i.e. normal energy in realization above method embodiment
Consume interval computation method or abnormal energy consumption data detection method.
Memory 72 may include storing program area and storage data area, wherein storing program area can storage program area,
Application program required at least one function；It storage data area can the data etc. that are created of storage processor 71.In addition, storage
Device 72 may include high-speed random access memory, can also include non-transient memory, for example, at least a magnetic disk storage
Part, flush memory device or other non-transient solid-state memories.In some embodiments, it includes relative to place that memory 72 is optional
The remotely located memory of device 71 is managed, these remote memories can pass through network connection to processor 71.The reality of above-mentioned network
Example includes but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
One or more of modules are stored in the memory 72, when being executed by the processor 71, are executed
Normal energy consumption interval computation method in embodiment as shown in Figs. 1-3, or execute the abnormal energy consumption in embodiment as shown in Figure 4
Data detection method.
Above-mentioned electronic equipment detail can correspond to corresponding associated description in embodiment referring to FIG. 1 to 4
Understood with effect, details are not described herein again.
It is that can lead to it will be understood by those skilled in the art that realizing all or part of the process in above-described embodiment method
Computer program is crossed to instruct relevant hardware and complete, the program can be stored in a computer-readable storage medium
In, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, the storage medium can for magnetic disk,
CD, read-only memory (Read-Only Memory, ROM), random access memory (Random Access
Memory, RAM), flash memory (Flash Memory), hard disk (Hard Disk Drive, abbreviation: HDD) or solid state hard disk
(Solid-State Drive, SSD) etc.；The storage medium can also include the combination of the memory of mentioned kind.
Obviously, the above embodiments are merely examples for clarifying the description, and does not limit the embodiments.It is right
For those of ordinary skill in the art, can also make on the basis of the above description it is other it is various forms of variation or
It changes.There is no necessity and possibility to exhaust all the enbodiments.And it is extended from this it is obvious variation or
It changes still within the protection scope of the invention.
Claims (10)
1. a kind of normal energy consumption interval computation method, which comprises the steps of:
Several energy consumption sample datas are obtained, and obtain the corresponding acquisition parameter information of each energy consumption sample data；
The energy consumption sample data is assigned under several predetermined power consumption modes according to the acquisition parameter information；
It is calculated according to the energy consumption sample data under each predetermined power consumption mode normal under each predetermined power consumption mode
Energy consumption section.
2. normal energy consumption interval computation method according to claim 1, which is characterized in that described several energy consumption samples of acquisition
Notebook data, and the step of obtaining each energy consumption sample data corresponding acquisition parameter information, comprising:
All historical energy consumption datas in predetermined amount of time are obtained, and obtain the corresponding acquisition parameter of each historical energy consumption data
Information；
The data incomplete in the historical energy consumption data is rejected, several intermediate sample data are obtained；
The intermediate sample data are detected using abnormal point method of determining and calculating；
Rejecting is detected as abnormal intermediate sample data by the abnormal point method of determining and calculating, obtains several described energy consumption sample numbers
According to and its corresponding acquisition parameter information.
3. a kind of exception energy consumption data detection method, which comprises the steps of:
Obtain the acquisition parameter information of energy consumption data to be detected and the energy consumption data to be detected；
According to the normal energy under the acquisition parameter acquisition of information predetermined power consumption mode corresponding with the energy consumption data to be detected
Consume section；The normal energy consumption section is to be calculated using normal energy consumption interval computation method described in as claimed in claim 1 or 22；
Judge whether the energy consumption data to be detected falls into the range of the normal energy consumption section；
When the energy consumption data to be detected is not fallen in the range of the normal energy consumption section, the energy consumption number to be detected is determined
According to for abnormal data.
4. method according to claim 1-3, which is characterized in that the acquisition parameter information includes adopting for data
Collect temporal information, the predetermined power consumption mode includes working day mode and nonworkdays mode.
5. method according to claim 1-3, which is characterized in that the acquisition parameter information includes adopting for data
Collect temporal information, the predetermined power consumption mode includes work hours on working day mode, quitting time on working day mode and inoperative
Day mode.
6. method according to claim 1-3, which is characterized in that the acquisition parameter information includes adopting for data
Collect temporal information and temperature collection information, the predetermined power consumption mode include the first temperature range work hours on working day mode,
Second temperature range work hours on working day mode, third temperature range work hours on working day mode, the first temperature range work
Make quitting time day mode, second temperature range quitting time on working day mode, third temperature range quitting time on working day mould
Formula and nonworkdays mode.
7. a kind of normal energy consumption interval computation device characterized by comprising
Sample data obtains module, and for obtaining several energy consumption sample datas, and it is corresponding to obtain each energy consumption sample data
Acquisition parameter information；
Mode classification module, it is pre- surely for the energy consumption sample data to be assigned to several according to the acquisition parameter information
Under consumption mode；
Interval computation module, for calculating the predetermined power consumption mode according to the energy consumption sample data under each predetermined power consumption mode
Normal energy consumption section.
8. a kind of exception energy consumption data detection device characterized by comprising
Data to be tested obtain module, and the acquisition parameter for obtaining energy consumption data to be detected and the energy consumption data to be detected is believed
Breath；
Section obtains module, for according to the acquisition parameter acquisition of information it is corresponding with the energy consumption data to be detected it is pre- surely
Normal energy consumption section under consumption mode；The normal energy consumption section is to be counted using normal energy consumption section described in as claimed in claim 1 or 22
Calculation method is calculated；
Judgment module, for judging whether the energy consumption data to be detected falls into the range of the normal energy consumption section；
As a result determining module, for when the energy consumption data to be detected is not fallen in the range of the normal energy consumption section, really
The fixed energy consumption data to be detected is abnormal data.
9. a kind of electronic equipment characterized by comprising at least one processor；And it is logical at least one described processor
Believe the memory of connection；Wherein, the memory is stored with the instruction that can be executed by one processor, and described instruction is by institute
The execution of at least one processor is stated, so that at least one described processor executes such as method as claimed in any one of claims 1 to 6.
10. a kind of computer readable storage medium, is stored thereon with computer instruction, which is characterized in that the instruction is by processor
The step of any the method in such as claim 1-6 is realized when execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811627185.3A CN109785184A (en) | 2018-12-28 | 2018-12-28 | Normal energy consumption interval computation method, abnormal energy consumption data detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811627185.3A CN109785184A (en) | 2018-12-28 | 2018-12-28 | Normal energy consumption interval computation method, abnormal energy consumption data detection method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109785184A true CN109785184A (en) | 2019-05-21 |
Family
ID=66498834
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811627185.3A Pending CN109785184A (en) | 2018-12-28 | 2018-12-28 | Normal energy consumption interval computation method, abnormal energy consumption data detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109785184A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102289585A (en) * | 2011-08-15 | 2011-12-21 | 重庆大学 | Real-time monitoring method for energy consumption of public building based on data mining |
| CN106250905A (en) * | 2016-07-08 | 2016-12-21 | 复旦大学 | A kind of real time energy consumption method for detecting abnormality of combination colleges and universities building structure feature |
| CN107944464A (en) * | 2017-10-12 | 2018-04-20 | 华南理工大学 | A kind of office building by when energy consumption abnormal data online recognition and complementing method |
| CN108932217A (en) * | 2017-05-27 | 2018-12-04 | 深圳市中电电力技术股份有限公司 | The method and device of energy consumption statistic |
-
2018
- 2018-12-28 CN CN201811627185.3A patent/CN109785184A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102289585A (en) * | 2011-08-15 | 2011-12-21 | 重庆大学 | Real-time monitoring method for energy consumption of public building based on data mining |
| CN106250905A (en) * | 2016-07-08 | 2016-12-21 | 复旦大学 | A kind of real time energy consumption method for detecting abnormality of combination colleges and universities building structure feature |
| CN108932217A (en) * | 2017-05-27 | 2018-12-04 | 深圳市中电电力技术股份有限公司 | The method and device of energy consumption statistic |
| CN107944464A (en) * | 2017-10-12 | 2018-04-20 | 华南理工大学 | A kind of office building by when energy consumption abnormal data online recognition and complementing method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109495502B (en) | Industrial control network security and health index evaluation method and device | |
| CN105956734A (en) | Method and system for dynamically setting performance index threshold of IT equipment | |
| JP2014021555A (en) | Natural energy amount prediction device | |
| US20140122181A1 (en) | Demand response load forecaster | |
| WO2021082478A1 (en) | Energy consumption prediction method and device for air conditioning system | |
| CN112597263B (en) | Pipe network detection data abnormity judgment method and system | |
| WO2019085754A1 (en) | Application cleaning method and apparatus, and storage medium and electronic device | |
| CN115219903A (en) | Battery self-discharge rate abnormity judgment method and device based on Internet of vehicles data analysis | |
| CN110298765B (en) | Power distribution network power consumption abnormality detection method based on objective correlation factors | |
| CN111200864A (en) | Data processing method, device, equipment and storage medium | |
| Yang et al. | An efficient and robust method for lithium-ion battery capacity estimation using constant-voltage charging time | |
| CN117093943A (en) | Power consumption monitoring and early warning method and device | |
| CN109785184A (en) | Normal energy consumption interval computation method, abnormal energy consumption data detection method and device | |
| CN115951123B (en) | Electric energy metering method and system based on wireless communication | |
| CN116867038A (en) | Management system and method for low-power consumption microclimate sensor | |
| CN112116176A (en) | Meteorological factor-based regional insulator group pollution flashover risk assessment method and system | |
| CN108765192A (en) | A kind of transformer upper layer oil temperature prediction technique, system and equipment based on big data | |
| CN112747413B (en) | Air conditioning system load prediction method and device | |
| CN108830476B (en) | Method for evaluating cognitive testability information flow and terminal equipment | |
| CN102486502B (en) | Power feature identification device and method | |
| CN115291111B (en) | Training method of battery rest time prediction model and rest time prediction method | |
| CN114885231B (en) | Communication protocol self-adaptive signal acquisition method, system, terminal and medium | |
| CN116303124B (en) | Data searching method and device, electronic equipment and storage medium | |
| Dadi et al. | Estimation of transmission reliability margin using statistical methods and intelligent techniques | |
| CN106779265B (en) | Online state safety detection method based on electric power intelligent mobile terminal |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190521 |