CN116755641B - Distribution box operation data optimization acquisition and storage method - Google Patents
Distribution box operation data optimization acquisition and storage method Download PDFInfo
- Publication number
- CN116755641B CN116755641B CN202311056201.9A CN202311056201A CN116755641B CN 116755641 B CN116755641 B CN 116755641B CN 202311056201 A CN202311056201 A CN 202311056201A CN 116755641 B CN116755641 B CN 116755641B
- Authority
- CN
- China
- Prior art keywords
- sequence
- component
- similarity
- data
- sequences
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000009826 distribution Methods 0.000 title claims abstract description 25
- 238000003860 storage Methods 0.000 title claims abstract description 20
- 238000005457 optimization Methods 0.000 title abstract description 4
- 230000005611 electricity Effects 0.000 claims abstract description 102
- 230000005856 abnormality Effects 0.000 claims abstract description 28
- 230000002159 abnormal effect Effects 0.000 claims description 30
- 230000008569 process Effects 0.000 claims description 15
- 230000000737 periodic effect Effects 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 3
- 230000001131 transforming effect Effects 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 7
- 238000004458 analytical method Methods 0.000 description 13
- 238000000354 decomposition reaction Methods 0.000 description 5
- 238000012216 screening Methods 0.000 description 4
- 238000012935 Averaging Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000012300 Sequence Analysis Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- 230000003313 weakening effect Effects 0.000 description 1
- 238000003466 welding Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/0608—Saving storage space on storage systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/0614—Improving the reliability of storage systems
- G06F3/0619—Improving the reliability of storage systems in relation to data integrity, e.g. data losses, bit errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0638—Organizing or formatting or addressing of data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The application relates to the field of data processing, in particular to a distribution box operation data optimization acquisition and storage method, which comprises the following steps: obtaining a power consumption load sequence; setting component splitting control conditions according to the power load sequence, and obtaining a plurality of IMF component sequences according to the component splitting control conditions; calculating the similarity of each IMF component sequence, and obtaining a similarity component sequence according to the similarity; calculating the contribution degree of each similarity component sequence, and obtaining a plurality of strong contribution component sequences and a plurality of weak contribution component sequences according to the contribution degree and the similarity; and obtaining electricity consumption abnormality judgment conditions according to the strong contribution component sequences and the weak contribution component sequences, and performing storage control on the electricity consumption load sequences according to the electricity consumption abnormality judgment conditions, so that the storage space is reduced, and meanwhile, important data can be reserved.
Description
Technical Field
The application relates to the field of data processing, in particular to an optimized acquisition and storage method for operation data of a distribution box.
Background
Along with the continuous expansion of the fields of intelligence and informatization, various traditional devices start to be intelligent, and a large amount of data is generated. The intelligent distribution box can be used for power management of houses, and energy conservation, safety and convenient power consumption experience are realized through monitoring and control of household power consumption conditions. Meanwhile, through monitoring and controlling the electricity consumption condition, the electricity consumption is finely managed, the waste of energy sources is reduced, the carbon emission is reduced, the safety problems of circuit overload, short circuit and the like are avoided, and the electric power safety of a user is ensured. How to analyze and store the collected data, reasonably and efficiently utilize the data, and not generate redundancy of the data is a problem to be solved urgently.
The power consumption load data has abnormal data and normal data, wherein the abnormal data and the normal data have different influences on power consumption analysis, so that the data are required to be stored and managed differently according to the normal and abnormal conditions of the data. In order to realize better storage management of electricity consumption data, the normal and abnormal conditions of the electricity consumption load data are required to be accurately judged, and the existing data judging method comprises a time sequence analysis method which is used for analyzing the time sequence of the electricity consumption load data to obtain an electricity consumption trend graph and further obtain the normal and abnormal analysis conclusion of each piece of electricity consumption load data. However, the data analysis method cannot decompose independent data characteristics due to poor fineness of data splitting, so that analysis conclusion obtained by utilizing each component data is poor in accuracy, and meanwhile, when the data is analyzed, the condition that the variation characteristics in the power utilization load sequence are unchanged and the abnormality judgment conditions set by the unchanged characteristics are not considered to be inaccurate is not considered, so that the abnormality judgment precision of the power utilization load data is affected.
Disclosure of Invention
In order to solve the technical problems, the application provides a distribution box operation data optimization acquisition and storage method, which comprises the following steps:
obtaining a power consumption load sequence;
setting a component splitting control condition according to the electric load sequence, and splitting the electric load sequence according to the component splitting control condition to obtain a plurality of IMF component sequences and a residual sequence;
calculating the similarity of each IMF component sequence and the power utilization load sequence, and obtaining a plurality of similarity component sequences according to the similarity of all the IMF component sequences and the power utilization load sequence;
acquiring a plurality of periodic segments of each similarity component sequence and a plurality of periodic segments of the power utilization load sequence, obtaining the contribution degree of each similarity component sequence according to each similarity component sequence and the periodic segments of the power utilization load sequence, and obtaining a plurality of strong contribution component sequences and a plurality of weak contribution component sequences according to the contribution degree of all the similarity component sequences and the similarity of all the IMF component sequences and the power utilization load sequence;
and obtaining electricity consumption abnormality judgment conditions according to the strong contribution component sequence, the weak contribution component sequence and the residual sequence, and performing storage control on the electricity consumption load sequence according to the electricity consumption abnormality judgment conditions.
Preferably, the setting of the component splitting control condition includes the specific steps of:
acquiring an analog component sequence of each IMF component sequence in the splitting process of each IMF component sequence;
the component splitting control condition includes a second condition and a first condition;
setting a second condition of each analog component sequence of each IMF component sequence according to each analog component sequence of each IMF component sequence;
the first condition of each analog component sequence of each IMF component sequence is calculated by:
；
；
wherein ,representing +_for threshold value>Is also the first condition of the j-th analog component sequence of the i-th IMF component sequence, +.>Threshold value of the j-th analog component sequence representing the i-th IMF component sequence, +_>The t-th element in the j-th analog component sequence representing the i-th IMF component sequence,/-th element>The t-th element in the j-1 th analog component sequence representing the i-th IMF component sequence,/and->Representing the number of elements in the j-th analog component sequence of the i-th IMF component sequence.
Preferably, the setting the second condition of each analog component sequence of each IMF component sequence according to each analog component sequence of each IMF component sequence includes the specific steps of:
transforming each analog component sequence to obtain a plurality of instantaneous frequencies and a plurality of instantaneous amplitudes, taking the average value of the instantaneous frequencies as the integral frequency of each analog component sequence of each IMF component sequence, and taking the average value of the instantaneous amplitudes as the integral amplitude of each analog component sequence of each IMF component sequence;
each analog component sequence of each IMF component sequence second condition:
；
wherein ,second conditions of the jth analog component sequence representing the ith IMF component sequence；/>Representing the overall amplitude of the jth analog component sequence of the ith IMF component sequence, +.>Representing the overall frequency of the jth analog component sequence of the ith IMF component sequence, +.>Representing the overall magnitude of the j-1 st analog component sequence of the i-th IMF component sequence,representing the overall frequency of the j-1 st analog component sequence of the i-th IMF component sequence.
Preferably, the calculating the similarity of each IMF component sequence includes the specific steps of:
the similarity calculation method of the ith IMF component sequence comprises the following steps:
；
wherein ,represents the t-th element in the ith IMF component sequence,>represents the T-th element in the electrical load sequence, T represents the length of the electrical load sequence,/->The similarity of the ith IMF component sequence to the electrical load sequence is represented.
Preferably, the obtaining the similarity component sequence according to the similarity of the IMF component sequence includes the following specific steps:
obtaining the minimum similarity value of all IMF component sequences, obtaining a similarity threshold value according to the minimum similarity value of the IMF component sequences, and taking the IMF component sequences with the similarity greater than the similarity threshold value with the power load sequences as the similarity component sequences.
Preferably, the step of acquiring the plurality of period segments of each similarity component sequence and the plurality of period segments of the electrical load sequence includes the specific steps of:
extracting all local maximum points of the power utilization load sequence, and enabling the sequence between the two maximum points to be called a period segment to obtain a plurality of period segments of the power utilization load sequence;
a plurality of periodic segments of each sequence of similarity components is acquired.
Preferably, the contribution degree of each similarity component sequence is obtained according to each similarity component sequence and the period section of the electric load sequence, and the specific steps include:
the method for acquiring the set formed by the energy densities of all the period sections of the ith similarity component sequence comprises the following steps:
；
；
wherein ,a set of energy densities of all period segments representing the ith sequence of similarity components, +.>Energy density of the jth period representing the ith sequence of similarity components, +.>A length of a jth period segment representing an ith sequence of similarity components; />A t-th element representing a j-th period segment of the i-th sequence of similarity components;
acquiring a set of energy densities of all periodic segments of the electrical load sequence;
；
variance of energy density representing all period segments of the electrical load sequence, +.>Variance of energy density of all period segments representing the ith similarity component sequence, +.>A set of energy densities of all period segments representing the ith sequence of similarity components, +.>Representing the set of energy densities of all periodic segments of the electrical load sequence,indicating the degree of contribution of the ith sequence of similarity components.
Preferably, the method for obtaining a plurality of strong contribution component sequences and a plurality of weak contribution component sequences according to the contribution degree and the similarity includes the following specific steps:
and acquiring a third quartile of a set formed by the contribution degrees of the similarity component sequences, dividing the similarity component sequences with the contribution degrees larger than the third quartile into strong contribution component sequences, dividing the similarity component sequences with the contribution degrees smaller than the third quartile into weak contribution component sequences, and dividing the IMF component sequences with the similarity smaller than the similarity threshold into weak contribution component sequences.
Preferably, the obtaining the power consumption abnormality determination condition according to the strong contribution component sequence, the weak contribution component sequence and the residual sequence includes the specific steps of:
accumulating all the strong contribution component sequences to obtain a first accumulated sum sequence, and accumulating the first accumulated sum sequence and the residual sequence to obtain an electricity load reference sequence; accumulating all weak contribution component sequences to obtain a power consumption load deviation sequence;
the electricity consumption abnormality judgment condition calculation method comprises the following steps:
；
；
wherein ,representing the electrical load reference sequence,/->Representing preset correction parameters->Representing the sequence of the power load deviations,/->Representing the lower bias sequence, +.>Representing the upper run sequence.
Preferably, the storage control of the electricity load sequence according to the electricity abnormality determination condition includes the specific steps of:
the method comprises the steps of taking data at any moment in an electricity load sequence as target data, obtaining data at the same moment as the target data in an upper deviation sequence as upper reference data, obtaining data at the same moment as the target data in a lower deviation data sequence as lower reference data, judging the target data as normal electricity utilization data when the target data belongs to the data between the upper reference data and the lower reference data, and judging the target data as abnormal electricity utilization data when the target data does not belong to the data between the upper reference data and the lower reference data;
and compressing and storing normal data, and not compressing and storing abnormal data.
The embodiment of the application has at least the following beneficial effects: the abnormal data in the electricity load data has a large influence on electricity analysis, the electricity load data is required to be compressed and stored according to the abnormal condition of the electricity load data, and when the abnormal condition of the electricity load data is analyzed, compared with the traditional abnormal analysis method, the abnormal judgment condition can be adaptively set.
When the abnormal judgment condition is set, the power consumption load data is subjected to data splitting in consideration of the fact that the power consumption load data contains various data characteristics, and when the power consumption load data is subjected to data splitting, the situation that signal aliasing exists in components split by a traditional EMD method is considered, so that component splitting control conditions are newly added on the basis of the traditional EMD method, and an IMF component sequence is accurately split.
When an abnormal judgment condition is set in a self-adaptive mode, the similarity and contribution degree conditions of each IMF component sequence and the power load sequence are considered to complete classification of the IMF component sequences, and a strong contribution component sequence and a weak contribution component sequence are obtained, so that the IMF component sequences describing conventional data features and the IMF component sequences describing variant features are separated; and then obtaining an electricity load reference sequence according to the strong contribution component sequence, obtaining an electricity load deviation sequence according to the weak contribution sequence, and obtaining electricity abnormality judgment conditions according to the electricity load reference sequence and the deviation sequence, thereby accurately obtaining the abnormality judgment conditions.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the application, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for optimizing, collecting and storing operation data of a distribution box.
Detailed Description
In order to further describe the technical means and effects adopted by the application to achieve the preset aim, the following description refers to the specific implementation, structure, characteristics and effects of the optimized acquisition and storage method for the operation data of the distribution box according to the application by combining the attached drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
The application provides a specific scheme of the optimized acquisition and storage method for the operation data of the distribution box, which is specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of steps of a method for optimizing collection and storage of operation data of a distribution box according to an embodiment of the present application is shown, where the method includes the following steps:
step S001, acquiring an electric load sequence.
In real life, abnormal electricity consumption conditions exist, wherein the abnormal electricity consumption data has a large influence on electricity consumption analysis, so that the abnormal electricity consumption data cannot be subjected to data loss in the storage process, and the original data needs to be reserved. Thus, normal electricity data has relatively little impact on electricity analysis, and appropriate losses may be accepted during storage to save storage costs. Therefore, before the electricity consumption data is stored, the electricity consumption data is required to be analyzed, and abnormal data and normal data in the electricity consumption data are judged.
And acquiring the electricity utilization coincidence data before discriminating the electricity utilization data. The intelligent distribution box is provided with electric energy meters, current transformers and other devices, the devices can monitor the operation data of the intelligent distribution box in real time, and the power load data are obtained by collecting the operation data of the devices.
And collecting electricity load data at one moment every hour, collecting T times of data, and collecting the electricity load data at the T moments.
The power load data is used as a vector formed by the base power consumption data, the branch power consumption data and the event data, wherein the base power consumption data comprises data such as current, voltage, power and electric energy of a total line, and the branch power consumption data comprises data such as circuit, voltage, power and electric energy of each branch.
Because the electricity load data at each moment is high-dimensional data, the electricity load data needs to be subjected to dimension reduction processing for the convenience of analysis, and the method specifically comprises the following steps: and performing dimension reduction processing on the T pieces of electricity load data by using a PCA algorithm to obtain T pieces of 1-dimension electricity load data, wherein the electricity load data after dimension reduction is still recorded as electricity load data for convenience of description.
Arranging all the electricity load data in time sequence to obtain an electricity load sequence with the length of T, and recording the electricity load sequence as。/>And (5) indicating electricity load data at the T-th time.
In step S002, in the EMD decomposition process, component splitting control conditions are set, and the load sequence is split and controlled by using the component splitting control conditions to obtain a plurality of IMF component sequences and a residual sequence.
The electricity consumption data can be interfered by random factors such as human activities, weather and the like, so that the judgment of abnormal electricity consumption is affected. The conventional power consumption abnormality determination method has poor capability of processing the power consumption data under the random factor interference, so the following operations are performed in order to realize accurate power consumption abnormality analysis.
The power utilization load sequence contains various power utilization characteristic information, and in order to better utilize the power utilization characteristic information to judge power utilization abnormality, the power utilization load sequence needs to be split into a plurality of component sequences with independent power utilization characteristics.
Because the component sequences obtained by traditional EMD decomposition have the phenomenon of modal aliasing, the modal aliasing means that the component sequences obtained by the decomposition have wider scale distribution, and various signals exist, namely, information of other components are mixed in one component sequence. Therefore, the component sequence with modal aliasing is difficult to accurately reflect the characteristics of the power consumption signal, and the subsequent signal analysis is affected; at the same time, modal aliasing can cause uneven energy distribution of component sequences, resulting in masking or weakening peaks or peaks and valleys of some component sequences, thereby affecting analysis and understanding of signal characteristics. In order to solve the problem of modal aliasing, the conventional EMD method needs to be improved, and the difference between the method in this embodiment and the conventional EMD method is that the component splitting control conditions are set, and the specific operation is as follows:
1. the existing EMD decomposition process:
(1) Setting a blank residual sequence, and setting the first residual sequenceSet to the electrical load sequence C, obtain the remaining sequence +.>All local extremum points;
(2) Construction of the remaining sequenceUpper envelope and lower envelope of (a) are +.> and />；
(3) Averaging the two envelopes to obtain an envelope average sequenceThe specific formula is as follows: />；
(4) The power load sequence C and the envelope mean value sequenceThe difference results in a sequence of analog components:；
(5) When (when)When the component splitting control condition is satisfied, the analog component sequence +.>As an IMF component sequence, it is noted +.>. When the component splitting control conditions are not satisfied, the method is executed according to the satisfaction of each of the component splitting control conditions, and the specific execution method refers to the process 3. Until the obtained analog component sequence meets the component splitting control condition, obtaining IMF component sequence +.>。
(6) The remaining sequenceAnd IMF component sequences->Making difference to obtain the remaining sequence->Substitution of the remaining sequence->The remaining sequence->Continuing to repeat the processes (1) (2) (3) (4) (5) until all IMF component sequences are isolated, and marking the ith IMF component sequence as +.>. Wherein the IMF component sequence and the electrical loadThe sequences satisfy the following relationship:
；
wherein ,an ith IMF component sequence representing a power load signal, N representing the number of IMF component sequences, +.>Representing the residual sequence, C represents the electrical load sequence.
It should be noted that J analog component sequences are generated during the splitting process of each IMF component sequence, wherein the ith IMF component sequence isThe j-th analog component sequence called the i-th IMF component sequence in the splitting process is marked as +.>。
The above process is a brief description of the existing EMD decomposition process, and this embodiment is not further described or analyzed.
2. Setting component splitting control conditions:
the component splitting control condition is a main factor for controlling splitting, so that the mode superposition problem is solved, the component splitting control condition of the traditional EMD is required to be adjusted, and the specific method is as follows:
and carrying out conversion processing on each analog component sequence by using Hilbert transformation to obtain a plurality of instantaneous frequencies and a plurality of instantaneous amplitudes of each analog component sequence, averaging all the instantaneous frequencies of each analog component sequence to obtain the overall frequency of each analog component sequence, and averaging all the instantaneous amplitudes of each analog component sequence to obtain the overall amplitude of each analog component sequence. The spectrum data set formed by the integral frequency and integral amplitude of the jth analog component sequence of the ith IMF component sequence is recorded as, wherein />、/>The overall amplitude and overall frequency of the j-th analog component sequence of the i-th IMF component sequence are represented, respectively.
For the jth analog component sequence of the ith IMF component sequence, obtaining component splitting control, wherein the component splitting control comprises a first condition and a second condition, and the specific obtaining method comprises the following steps:
；
；
；
representing +_for threshold value>Is marked as a first condition which is an existing condition of the conventional EMD method, < ->Threshold value of the j-th analog component sequence representing the i-th IMF component sequence, +_>The t-th element in the j-th analog component sequence representing the i-th IMF component sequence,/-th element>Representing the ith IMF component sequenceThe t element in the j-1 th analog component sequence,>representing the number of elements in the j-1 st analog component sequence of the i-th IMF component sequence.
A second condition is noted as a determination function for representing the overall amplitude and overall frequency of the jth analog component sequence of the ith IMF component sequence, which is a newly added condition proposed in the present embodiment; />Representing the overall amplitude of the jth analog component sequence of the ith IMF component sequence, +.>Representing the overall frequency of the jth analog component sequence of the ith IMF component sequence, +.>Representing the overall amplitude of the j-1 th analog component sequence of the i-th IMF component sequence,/->Representing the overall frequency of the j-1 th analog component sequence of the i-th IMF component sequence;
the reason why the modal aliasing problem can be solved well through the second condition is that: the modal aliasing refers to that information aliasing exists between IMF component sequences, namely, characteristic information of other IMF component sequences contained in one IMF component sequence; and when the information in the newly decomposed IMF component sequence is obviously different from the information in the last analog component sequence, the information in other IMF component sequences in the newly decomposed IMF component sequence is less likely to be aliased. Meanwhile, the frequency and the amplitude can better measure the information difference, namely, the information difference is measured through the frequency and the amplitude difference; formulas in the second condition in the present embodimentCan be arranged into->, wherein />Reflecting the frequency difference between the newly decomposed analog component and the analog component at the previous time, ++>Reflecting the difference in amplitude between the newly decomposed analog component and the analog component at the previous time, ++>The frequency and amplitude difference between the newly decomposed analog component and the analog component at the previous moment is described to meet the set condition, so that the problem of information aliasing can be well solved by utilizing the second condition.
3. The method comprises the steps of carrying out split control on a load sequence by utilizing a component split control condition to obtain a plurality of IMF component sequences and a residual sequence:
when the first condition of the decomposed analog component sequence is equal to 1 and the second condition is equal to 1, the decomposed analog component sequence is represented to meet the component splitting control condition, and the analog component sequence is taken as an IMF component sequence; repeating the processes (1) - (4) in step 1 to split the next analog component as long as the first condition is equal to 0; only when the second condition is equal to 0, gaussian white noise with the mean value of 0 and the variance of 1 is added to the decomposed analog component sequence, and the component splitting control condition is used for re-judging the analog component sequence added with the Gaussian noise.
Based on the component splitting control condition, the EMD component splitting process in step 1 is performed to obtain a plurality of IMF component sequences and a residual sequence R.
Thus, the component splitting is completed to obtain a plurality of IMF component sequences and a residual sequence R, the signal aliasing problem is considered in the component splitting process, and a second condition is newly added on the basis of the control condition of the original EMD method, so that the signal aliasing problem among the components is reduced.
Step S003, calculating the similarity of each IMF component sequence and the electricity load sequence, and obtaining a plurality of similar component sequences according to the similarity of each IMF component sequence and the electricity load sequence.
In order to determine the abnormal electricity consumption in the electricity load sequence, it is necessary to set an appropriate determination condition, and further to perform the abnormal electricity consumption determination using the appropriate determination condition.
When the judging conditions are set, the contribution degree of each IMF component sequence to the power utilization load sequence is analyzed, and the IMF component sequences are classified according to the contribution degree, so that the judging conditions are set by using the IMF component sequences of each class, and further the power utilization abnormality analysis is realized.
In classifying the IMF component sequences, the IMF component sequences are considered normal, wherein the normal IMF component sequences should be more consistent with the data characteristics of the electrical load sequences.
The similarity can reflect the matching degree of each IMF component sequence and the electricity load sequence, and the fluctuation condition and the change trend capturing condition of each IMF component sequence on the electricity load sequence. Therefore, similarity can be used as an evaluation standard to perform primary screening on the component signals, wherein IMF component sequences with high similarity contain IMF component information with high similarity, which can better describe the condition of electricity consumption, so that the IMF component information with high similarity needs to be screened out.
The specific calculation method for obtaining a plurality of similar component sequences by analyzing the similarity of each IMF component sequence and the power utilization load sequence comprises the following steps:
；
；
；
wherein ,represents the t-th element in the ith IMF component sequence,>represents the T-th element in the electrical load sequence, T represents the length of the electrical load sequence,/->Representing the similarity of the ith IMF component sequence to the electrical load sequence,function representing the minimum value taken, +.>Representing similarity threshold, ++>A screening flag value representing the ith IMF component sequence.
And taking the IMF component sequence with the screening flag value equal to 1 as a similarity component sequence to obtain a plurality of similarity component sequences.
Step S004, calculating the contribution degree of each similarity component sequence, and obtaining a strong contribution component sequence and a weak contribution component sequence according to the contribution degree.
In the above steps, a round of rough screening is performed on the IMF component sequences through the similarity to obtain the similarity component sequences, so that in order to more accurately screen out better IMF component sequences, the contribution condition of the similarity component sequences to the power utilization load sequences needs to be continuously analyzed, and the specific operation is as follows:
1. calculating the contribution degree of the similarity component sequence:
(1) Performing period segmentation to obtain a plurality of period sequences:
the degree of contribution of the similarity component sequence is reflected by the energy density distribution of the similarity component sequence, and in order to calculate the energy density distribution of the components, it is necessary to acquire the periods of the power load sequence and the similarity component sequence first. The acquisition cycle is as follows:
firstly, all local maximum points of an electric load sequence are extracted, a period of time between every two maximum points is defined as a period, a sequence between the two maximum points is called a period, a plurality of period are obtained, all period are arranged in time sequence to obtain a period sequence, and the period sequence of the electric load sequence is obtained.
And the same applies to the periodic sequence of each similarity component sequence.
(2) Calculating the contribution degree of the similarity component sequence to the electricity load sequence:
the method comprises the steps of obtaining a set formed by energy densities of all period segments of a similarity sequence, wherein the set comprises the following concrete steps:
；
；
wherein ,a set of energy densities of all period segments representing the ith sequence of similarity components, +.>An energy density representing a jth period of the ith sequence of similarity components; />A length of a jth period segment representing an ith sequence of similarity components; />A t-th element representing a j-th period segment of the i-th sequence of similarity components.
The set of energy densities of all the period segments of the i-th similarity component sequence is thus obtained, and the set of energy densities of all the period segments of the electrical load sequence is similarly obtained.
Calculating the contribution degree of the similarity component sequence according to the set formed by the energy densities of all the period sections of the ith similarity component sequence and the set formed by the energy densities of all the period sections of the electricity load sequence, wherein the contribution degree is specifically as follows:
；
wherein ,representing the set of energy densities of all period segments of the electrical load sequence, +.>Representing the variance of the energy density of all periodic segments of the electrical load sequence, by which value the fluctuation of the electrical load sequence is reflected,/o>A set of energy densities of all period segments representing the ith sequence of similarity components, +.>Representing the variance of the energy density of all periodic segments of the ith similarity component sequence, by which value the fluctuation situation of the similarity component sequence is reflected, +.>Reflects the fluctuation consistency of the ith similarity component sequence and the electricity load sequence, < ->Indicating the degree of contribution of the ith sequence of similarity components. Obtaining a strong contribution component sequence and a weak contribution component sequence according to the contribution degree:
the third quartile of the set of contribution degrees of the similarity component sequences is obtained, and is a prior art, and will not be described in detail here.
The similarity component sequences with the contribution degree larger than the third quartile are divided into strong contribution component sequences, the similarity component sequences with the contribution degree smaller than the third quartile are divided into weak contribution component sequences, and the IMF component sequences with the similarity smaller than the similarity threshold value with the electricity load sequences are also marked as weak contribution component sequences.
So far, a strong contribution component sequence and a weak contribution component sequence are obtained, when the strong contribution component sequence and the weak contribution component sequence are obtained, the similarity situation of each IMF component sequence and the electricity load sequence is considered to obtain a similarity component sequence, then the contribution degree of each similarity component sequence is obtained according to the contribution situation of the similarity component sequence to the electricity load sequence, and further the strong contribution component sequence and the weak contribution component sequence are obtained according to the contribution degree.
And step S005, obtaining electricity consumption abnormality judgment conditions according to the strong contribution component sequences and the weak contribution component sequences, and performing storage control on electricity consumption load data according to the electricity consumption abnormality judgment conditions.
1. Setting an electricity consumption abnormality determination condition:
(1) Obtaining a power consumption load reference sequence:
since the data characteristics of the strong contribution component sequence are more consistent with the overall characteristics of the electrical load sequence, the probability that the strong contribution component sequence describes normal data is higher, and thus the electrical load reference sequence can be obtained by using the strong contribution component sequence:
accumulating all the strong contribution component sequences to obtain a first accumulated sum sequence, accumulating the first accumulated sum sequence and the residual sequence to obtain an electricity load reference sequence, and marking the electricity load reference sequence asThe sequence is derived from a strongly contributing data sequence that is characteristic of normal data, so that the sequence can serve as a reference for the normal data, which thus fluctuates around the sequence to a certain extent.
(2) Obtaining a power consumption load deviation sequence:
and accumulating all weak contribution component sequences to obtain a power consumption load deviation sequence, and marking the power consumption load deviation sequence as C2, wherein the power consumption load deviation sequence is obtained by a weak data sequence which does not accord with normal data characteristics, and the weak data sequence can reflect the mutation condition of data, so that the deviation range can be set by utilizing the data.
(3) Setting an electricity consumption abnormality determination condition:
obtaining electricity consumption abnormality determination conditions according to the electricity consumption load reference sequence and the electricity consumption load deviation sequence:
；
；
wherein ,representing an electricity load reference sequence reflecting the overall distribution characteristics of normal electricity consumption data, which fluctuates around the sequence within a certain range, ++>Representing preset correction parameters, in this embodiment +.>Taking 0.3 as an example, other embodiments may be set to other values, and the present embodiment is not particularly limited. />Represents a power consumption load deviation sequence reflecting the mutation of power consumption data, by which the fluctuation range is set. />A sequence of lower deviations is indicated and,representing the upper run sequence.
2. And carrying out storage control on the electricity load data according to the electricity abnormality judgment condition:
and taking the data at any moment in the electricity load sequence as target data, acquiring the data at the same moment as the target data in the upper deviation sequence as upper reference data, acquiring the data at the same moment as the target data in the lower deviation data sequence as lower reference data, judging the target data as normal electricity utilization data when the target data belongs to the data between the upper reference data and the lower reference data, and judging the target data as abnormal electricity utilization data when the target data does not belong to the data between the upper reference data and the lower reference data. It should be noted that the data between the upper and lower reference data includes the upper and lower reference data.
And similarly, judging all data in the power load sequence to obtain all abnormal data and normal data.
And (3) compressing and storing normal data, not compressing abnormal data, and keeping an original value.
In summary, the embodiment of the application provides an intelligent detection method for welding defects of a sheet metal part based on image data, which has a large influence on electricity analysis by abnormal data in electricity load data, and needs to compress and store the electricity load data according to the abnormal condition of the electricity load data.
When the abnormal judgment condition is set, the power consumption load data is subjected to data splitting in consideration of the fact that the power consumption load data contains various data characteristics, and when the power consumption load data is subjected to data splitting, the situation that signal aliasing exists in components split by a traditional EMD method is considered, so that component splitting control conditions are newly added on the basis of the traditional EMD method, and an IMF component sequence is accurately split.
When an abnormal judgment condition is set in a self-adaptive mode, the similarity and contribution degree conditions of each IMF component sequence and the power load sequence are considered to complete classification of the IMF component sequences, and a strong contribution component sequence and a weak contribution component sequence are obtained, so that the IMF component sequences describing conventional data features and the IMF component sequences describing variant features are separated; and then obtaining an electricity load reference sequence according to the strong contribution component sequence, obtaining an electricity load deviation sequence according to the weak contribution sequence, and obtaining electricity abnormality judgment conditions according to the electricity load reference sequence and the deviation sequence, thereby accurately obtaining the abnormality judgment conditions.
It should be noted that: the sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
The foregoing description of the preferred embodiments of the present application is not intended to be limiting, but rather, any modifications, equivalents, improvements, etc. that fall within the principles of the present application are intended to be included within the scope of the present application.
Claims (8)
1. An optimized acquisition and storage method for operation data of a distribution box is characterized by comprising the following steps:
obtaining a power consumption load sequence;
setting a component splitting control condition according to the electric load sequence, and splitting the electric load sequence according to the component splitting control condition to obtain a plurality of IMF component sequences and a residual sequence;
calculating the similarity of each IMF component sequence and the power utilization load sequence, and obtaining a plurality of similarity component sequences according to the similarity of all the IMF component sequences and the power utilization load sequence;
acquiring a plurality of periodic segments of each similarity component sequence and a plurality of periodic segments of the power utilization load sequence, obtaining the contribution degree of each similarity component sequence according to each similarity component sequence and the periodic segments of the power utilization load sequence, and obtaining a plurality of strong contribution component sequences and a plurality of weak contribution component sequences according to the contribution degree of all the similarity component sequences and the similarity of all the IMF component sequences and the power utilization load sequence;
obtaining electricity consumption abnormality judgment conditions according to the strong contribution component sequence, the weak contribution component sequence and the residual sequence, and performing storage control on the electricity consumption load sequence according to the electricity consumption abnormality judgment conditions;
the setting of the component splitting control conditions comprises the following specific steps:
acquiring an analog component sequence of each IMF component sequence in the splitting process of each IMF component sequence;
the component splitting control condition includes a second condition and a first condition;
setting a second condition of each analog component sequence of each IMF component sequence according to each analog component sequence of each IMF component sequence;
the first condition of each analog component sequence of each IMF component sequence is calculated by:
wherein ,representing +_for threshold value>Is also the first condition of the j-th analog component sequence of the i-th IMF component sequence, +.>Threshold value of the j-th analog component sequence representing the i-th IMF component sequence, +_>The jth analog component representing the ith IMF component sequenceThe t element in the quantitative sequence, +.>The t-th element in the j-1 th analog component sequence representing the i-th IMF component sequence,/and->Representing the number of elements in the j-th analog component sequence of the i-th IMF component sequence;
the method for calculating the similarity of each IMF component sequence and the power utilization load sequence comprises the following specific steps:
the similarity calculation method of the ith IMF component sequence comprises the following steps:
wherein ,represents the t-th element in the ith IMF component sequence,>represents the T-th element in the electrical load sequence, T represents the length of the electrical load sequence,/->The similarity of the ith IMF component sequence to the electrical load sequence is represented.
2. The method for optimally collecting and storing operation data of a distribution box according to claim 1, wherein the step of setting the second condition of each analog component sequence of each IMF component sequence according to each analog component sequence of each IMF component sequence comprises the following specific steps:
transforming each analog component sequence to obtain a plurality of instantaneous frequencies and a plurality of instantaneous amplitudes, taking the average value of the instantaneous frequencies as the integral frequency of each analog component sequence of each IMF component sequence, and taking the average value of the instantaneous amplitudes as the integral amplitude of each analog component sequence of each IMF component sequence;
each analog component sequence of each IMF component sequence second condition:
wherein ,a second condition representing a jth analog component sequence of the ith IMF component sequence; />Representing the overall amplitude of the jth analog component sequence of the ith IMF component sequence, +.>Representing the overall frequency of the jth analog component sequence of the ith IMF component sequence, +.>Representing the overall amplitude of the j-1 th analog component sequence of the i-th IMF component sequence,/->Representing the overall frequency of the j-1 st analog component sequence of the i-th IMF component sequence.
3. The method for optimally collecting and storing the operation data of the distribution box according to claim 1, wherein the step of obtaining a plurality of similarity component sequences according to the similarity between all the IMF component sequences and the electricity load sequences comprises the following specific steps:
obtaining the minimum similarity value of all IMF component sequences, obtaining a similarity threshold value according to the minimum similarity value of the IMF component sequences, and taking the IMF component sequences with the similarity greater than the similarity threshold value with the power load sequences as the similarity component sequences.
4. The method for optimally collecting and storing the operation data of the distribution box according to claim 1, wherein the steps of obtaining a plurality of period segments of each similarity component sequence and a plurality of period segments of the power load sequence comprise the following specific steps:
extracting all local maximum points of the power utilization load sequence, and enabling the sequence between the two maximum points to be called a period segment to obtain a plurality of period segments of the power utilization load sequence;
a plurality of periodic segments of each sequence of similarity components is acquired.
5. The method for optimally collecting and storing the operation data of the distribution box according to claim 1, wherein the contribution degree of each similarity component sequence is obtained according to each similarity component sequence and the period section of the power load sequence, and the method comprises the following specific steps:
the method for acquiring the set formed by the energy densities of all the period sections of the ith similarity component sequence comprises the following steps:
wherein ,a set of energy densities of all period segments representing the ith sequence of similarity components, +.>Energy density of the jth period representing the ith sequence of similarity components, +.>Represents the ithThe length of the jth period of the sequence of individual similarity components; />A t-th element representing a j-th period segment of the i-th sequence of similarity components;
acquiring a set of energy densities of all periodic segments of the electrical load sequence;
variance of energy density representing all period segments of the electrical load sequence, +.>Variance of energy density of all period segments representing the ith similarity component sequence, +.>A set of energy densities of all period segments representing the ith sequence of similarity components, +.>Representing the set of energy densities of all period segments of the electrical load sequence, +.>Indicating the degree of contribution of the ith sequence of similarity components.
6. The method for optimally collecting and storing the operation data of the distribution box according to claim 1, wherein the steps of obtaining a plurality of strong contribution component sequences and a plurality of weak contribution component sequences according to the contribution degree of all the similarity component sequences and the similarity of all the IMF component sequences and the power utilization load sequences comprise the following specific steps:
and acquiring a third quartile of a set formed by the contribution degrees of the similarity component sequences, dividing the similarity component sequences with the contribution degrees larger than the third quartile into strong contribution component sequences, dividing the similarity component sequences with the contribution degrees smaller than the third quartile into weak contribution component sequences, and dividing the IMF component sequences with the similarity smaller than the similarity threshold into weak contribution component sequences.
7. The method for optimally collecting and storing the operation data of the distribution box according to claim 1, wherein the power consumption abnormality judgment condition is obtained according to the strong contribution component sequence, the weak contribution component sequence and the residual sequence, and the method comprises the following specific steps:
accumulating all the strong contribution component sequences to obtain a first accumulated sum sequence, and accumulating the first accumulated sum sequence and the residual sequence to obtain an electricity load reference sequence; accumulating all weak contribution component sequences to obtain a power consumption load deviation sequence;
the electricity consumption abnormality judgment condition calculation method comprises the following steps:
wherein ,representing the electrical load reference sequence,/->Representing preset correction parameters->A sequence of electrical load deviations is indicated,representing the lower bias sequence, +.>Representing the upper run sequence.
8. The method for optimally collecting and storing the operation data of the distribution box according to claim 1, wherein the step of storing and controlling the electric load sequence according to the electric abnormality judgment condition comprises the following specific steps:
the method comprises the steps of taking data at any moment in an electricity load sequence as target data, obtaining data at the same moment as the target data in an upper deviation sequence as upper reference data, obtaining data at the same moment as the target data in a lower deviation data sequence as lower reference data, judging the target data as normal electricity utilization data when the target data belongs to the data between the upper reference data and the lower reference data, and judging the target data as abnormal electricity utilization data when the target data does not belong to the data between the upper reference data and the lower reference data;
and compressing and storing normal data, and not compressing and storing abnormal data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311056201.9A CN116755641B (en) | 2023-08-22 | 2023-08-22 | Distribution box operation data optimization acquisition and storage method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311056201.9A CN116755641B (en) | 2023-08-22 | 2023-08-22 | Distribution box operation data optimization acquisition and storage method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116755641A CN116755641A (en) | 2023-09-15 |
| CN116755641B true CN116755641B (en) | 2023-10-24 |
Family
ID=87950121
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311056201.9A Active CN116755641B (en) | 2023-08-22 | 2023-08-22 | Distribution box operation data optimization acquisition and storage method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116755641B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117370898B (en) * | 2023-12-08 | 2024-03-12 | 钛合联(深圳)科技有限公司 | Electronic data safety control system |
| CN117421686B (en) * | 2023-12-18 | 2024-03-05 | 山东金诺种业有限公司 | Water and fertilizer integrated irrigation dosage data collection method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20160064447A (en) * | 2014-11-28 | 2016-06-08 | 이종찬 | A recommendation method for new users by using preference prediction based on collaborative filtering algorithm |
| CN109063902A (en) * | 2018-07-17 | 2018-12-21 | 广东工业大学 | A kind of short-term load forecasting method, device, equipment and storage medium |
| CN114139820A (en) * | 2021-12-07 | 2022-03-04 | 国网江苏省电力有限公司扬州供电分公司 | Improved modal decomposition method for non-invasive electric energy load prediction |
| US11429311B1 (en) * | 2021-03-26 | 2022-08-30 | Anaplan, Inc. | Method and system for managing requests in a distributed system |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10235399B2 (en) * | 2014-11-05 | 2019-03-19 | Hewlett Packard Enterprise Development Lp | Methods and systems for determining hardware sizing for storage array systems |
| US9959923B2 (en) * | 2015-04-16 | 2018-05-01 | Micron Technology, Inc. | Apparatuses and methods to reverse data stored in memory |
| US10372620B2 (en) * | 2016-12-30 | 2019-08-06 | Intel Corporation | Devices, systems, and methods having high data deduplication and low read latencies |
| US11366606B2 (en) * | 2020-10-01 | 2022-06-21 | Dell Products, L.P. | Smarter performance alerting mechanism combining thresholds and historical seasonality |
-
2023
- 2023-08-22 CN CN202311056201.9A patent/CN116755641B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20160064447A (en) * | 2014-11-28 | 2016-06-08 | 이종찬 | A recommendation method for new users by using preference prediction based on collaborative filtering algorithm |
| CN109063902A (en) * | 2018-07-17 | 2018-12-21 | 广东工业大学 | A kind of short-term load forecasting method, device, equipment and storage medium |
| US11429311B1 (en) * | 2021-03-26 | 2022-08-30 | Anaplan, Inc. | Method and system for managing requests in a distributed system |
| CN114139820A (en) * | 2021-12-07 | 2022-03-04 | 国网江苏省电力有限公司扬州供电分公司 | Improved modal decomposition method for non-invasive electric energy load prediction |
Non-Patent Citations (6)
| Title |
|---|
| "Short-Term Prediction of Power Load for Urban Residents Based on VMD-SVR-PSO Model";R Zhang et al.;《2022 3rd International Conference on Electronic Communication and Artificial Intelligence (IWECAI)》;第519-524页 * |
| "Short-Term Prediction of Power Load for Urban Residents Based on VMD-SVR-PSO Model";R Zhang et al.;《2022 3rd International Conference on Electronic Communication and Artificial Intelligence》;第519-524页 * |
| "基于CEEMDAN-LSTM-CNN网络的短期电力负荷预测";简定辉 等;《电工电气》(第6期);第1-6页 * |
| "基于多层全连接神经网络的漏电流容性分量补偿方法研究";周星雨 等;《电器与能效管理技术》(第3期);第54-61页 * |
| "基于局域波与近似熵的负荷分析方法";栗然;陆凤怡;徐宏锐;张烈勇;;《中国电机工程学报》;第30卷(第25期);第51-58页 * |
| "经验模态分析综合法在负荷预测中的应用";余林;舒勤;马哲;;《四川电力技术》(第02期);第48-52页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116755641A (en) | 2023-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116755641B (en) | Distribution box operation data optimization acquisition and storage method | |
| Greaves et al. | Temporal forecast uncertainty for ramp events | |
| CN116089846B (en) | New energy settlement data anomaly detection and early warning method based on data clustering | |
| JP2000512766A (en) | Statistical pattern analysis method for partial discharge measurement in high voltage insulation | |
| CN116559598B (en) | Smart distribution network fault positioning method and system | |
| CN105740635B (en) | A kind of cloud ideal solution evaluation method of transformer electromagnetic design scheme | |
| CN111177216B (en) | Association rule generation method and device for comprehensive energy consumer behavior characteristics | |
| CN112182720B (en) | Building energy consumption model evaluation method based on building energy management application scene | |
| CN112433907A (en) | Method and device for processing host operation parameter data of uninterruptible power supply and electronic device | |
| CN112085111A (en) | Load identification method and device | |
| CN109921462B (en) | New energy consumption capability assessment method and system based on LSTM | |
| CN116681186B (en) | Power quality analysis method and device based on intelligent terminal | |
| CN117200394A (en) | BMS battery management method and system based on BIM model | |
| CN116561569A (en) | Industrial power load identification method based on EO feature selection and AdaBoost algorithm | |
| CN116881661A (en) | Performance automatic analysis method and system based on low-voltage power capacitor | |
| Yang et al. | Non-Intrusive Load Classification and Recognition Using Soft-Voting Ensemble Learning Algorithm With Decision Tree, K-Nearest Neighbor Algorithm and Multilayer Perceptron | |
| CN115769238A (en) | Load identification method, computer-readable storage medium and device | |
| CN114169226A (en) | Short-term power load prediction method, computer device, and storage medium | |
| CN117368751B (en) | Remote controller low-power detection method and system | |
| CN117691756B (en) | Safety early warning management method and system for power distribution cabinet | |
| Liu et al. | Multi-timescale event detection in nonintrusive load monitoring based on MDL principle | |
| CN117407666B (en) | Intelligent garbage can parameter analysis and control method and device based on artificial intelligence | |
| Bosco et al. | A comparative study of machine learning classifiers for electric load disaggregation based on an extended nilm dataset | |
| CN117498522B (en) | Power supply control method and system for photovoltaic energy storage charging pile | |
| US20220381832A1 (en) | Production of a Quality Test System |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |