CN117135663A - Abnormality identification method and device for base station energy saving index data, computer equipment and storage medium - Google Patents
Abnormality identification method and device for base station energy saving index data, computer equipment and storage medium Download PDFInfo
- Publication number
- CN117135663A CN117135663A CN202310961862.XA CN202310961862A CN117135663A CN 117135663 A CN117135663 A CN 117135663A CN 202310961862 A CN202310961862 A CN 202310961862A CN 117135663 A CN117135663 A CN 117135663A
- Authority
- CN
- China
- Prior art keywords
- base station
- station energy
- saving index
- saving
- index data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000005856 abnormality Effects 0.000 title claims abstract description 23
- 230000000737 periodic effect Effects 0.000 claims abstract description 88
- 230000003068 static effect Effects 0.000 claims abstract description 63
- 238000012512 characterization method Methods 0.000 claims abstract description 26
- 230000002159 abnormal effect Effects 0.000 claims description 86
- 238000004590 computer program Methods 0.000 claims description 20
- 238000012360 testing method Methods 0.000 claims description 19
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 11
- 238000012545 processing Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000012216 screening Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 3
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000011282 treatment Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/04—Arrangements for maintaining operational condition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W52/00—Power management, e.g. TPC [Transmission Power Control], power saving or power classes
- H04W52/02—Power saving arrangements
- H04W52/0203—Power saving arrangements in the radio access network or backbone network of wireless communication networks
- H04W52/0206—Power saving arrangements in the radio access network or backbone network of wireless communication networks in access points, e.g. base stations
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The application relates to an anomaly identification method, an anomaly identification device, computer equipment and a storage medium for base station energy saving index data. The method comprises the following steps: determining fluctuation characterization coefficients and autocorrelation coefficients respectively corresponding to energy-saving index items of all base stations according to the base station energy-saving index data sequences respectively corresponding to the energy-saving index items of all base stations; identifying a static base station energy-saving index item from the base station energy-saving index items according to the fluctuation characterization coefficient; identifying a periodic base station energy-saving index item from the base station energy-saving index items according to the autocorrelation coefficients; determining an unstable base station energy saving index item according to base station energy saving index items except the periodic base station energy saving index item and the static base station energy saving index item; and respectively carrying out anomaly identification on the base station energy-saving index data sequences corresponding to the static base station energy-saving index item, the periodic base station energy-saving index item and the unstable base station energy-saving index item according to corresponding anomaly identification modes. By adopting the method, the abnormality identification accuracy can be improved.
Description
Technical Field
The present application relates to the field of communications technologies, and in particular, to a method, an apparatus, a computer device, and a storage medium for identifying anomalies in base station energy saving index data.
Background
The base station energy-saving system has the advantages of more layers, large data volume and large later operation and maintenance cost. Because the system is sensitive to various anomalies and the system has high complexity, once anomalies occur, adverse consequences can be caused. Therefore, it is important to identify abnormality of the base station energy saving index.
At present, the base station energy-saving index is screened and judged by means of manual experience, so that the base station energy-saving index is quite objectively, and the abnormal recognition miss judgment or misjudgment rate is high. Therefore, it is highly desirable to provide a solution capable of improving the accuracy of anomaly identification.
Disclosure of Invention
In view of the foregoing, it is desirable to provide an anomaly identification method, apparatus, computer device, computer readable storage medium, and computer program product for base station energy saving index data that improves accuracy.
In a first aspect, the present application provides a method for identifying anomalies in base station energy saving index data. The method comprises the following steps:
acquiring base station energy-saving index data sequences corresponding to the base station energy-saving index items respectively; the base station energy-saving index data sequence comprises base station energy-saving index data of the base station energy-saving index item at different time points;
Determining fluctuation characterization coefficients and autocorrelation coefficients respectively corresponding to energy-saving index items of each base station according to the energy-saving index data sequences of each base station;
identifying a static base station energy-saving index item from the base station energy-saving index items according to the fluctuation characterization coefficient;
according to the autocorrelation coefficients, periodically detecting each base station energy-saving index data sequence to identify periodic base station energy-saving index items from the base station energy-saving index items;
determining an unstable base station energy saving index item according to base station energy saving index items except the periodic base station energy saving index item and the static base station energy saving index item;
and respectively carrying out anomaly identification on the base station energy-saving index data sequences corresponding to the static base station energy-saving index item, the periodic base station energy-saving index item and the unstable base station energy-saving index item according to corresponding anomaly identification modes.
In one embodiment, the ripple characterization coefficient is a coefficient of variation; determining the fluctuation characterization coefficient and the autocorrelation coefficient corresponding to each base station energy-saving index item according to each base station energy-saving index data sequence, including:
determining standard deviation of a base station energy-saving index data sequence corresponding to each base station energy-saving index item;
Determining the average value of base station energy-saving index data in a base station energy-saving index data sequence;
determining a variation coefficient corresponding to the base station energy-saving index item according to the standard deviation and the average value;
and identifying a static base station energy-saving index item from the base station energy-saving index items according to the fluctuation characterization coefficient, wherein the method comprises the following steps of:
and determining the base station energy saving index item with the variation coefficient smaller than or equal to the first preset threshold value as a static base station energy saving index item.
In one embodiment, the static base station energy saving index item corresponds to a first base station energy saving index data sequence;
the step of performing anomaly identification on the base station energy-saving index data sequences corresponding to the static base station energy-saving index item, the periodic base station energy-saving index item and the unstable base station energy-saving index item respectively according to a corresponding anomaly identification mode comprises the following steps:
sliding on the first base station energy saving index data sequence through a first moving average time window;
carrying out average value calculation on the static base station energy saving index data positioned in the first moving average time window to obtain a first average value;
and comparing the first average value with a first dynamic threshold value, and identifying abnormal data in the first base station energy-saving index data sequence according to the comparison result.
In one embodiment, the unstable base station energy saving index item corresponds to a second base station energy saving index data sequence;
the step of performing anomaly identification on the base station energy-saving index data sequences corresponding to the static base station energy-saving index item, the periodic base station energy-saving index item and the unstable base station energy-saving index item respectively according to a corresponding anomaly identification mode comprises the following steps:
under the condition that the number of the unstable base station energy-saving index items is multiple, determining an unstable base station energy-saving index item with an abnormal label from the multiple unstable base station energy-saving index items, and obtaining an abnormal label index item;
aiming at the abnormal tag index item, acquiring historical unstable base station energy-saving index data of the abnormal tag index item, and determining a second dynamic threshold;
sliding on the second base station energy-saving index data sequence through a second moving average time window, and calculating the average value of the unstable base station energy-saving index data in the second moving average time window to obtain a second average value;
and identifying abnormal data in the second base station energy-saving index data sequence according to a comparison result between the second average value and the second dynamic threshold value.
In one embodiment, the method further comprises:
aiming at an abnormal label-free index item in the plurality of unstable base station energy-saving index items, carrying out preliminary abnormal recognition on the unstable base station energy-saving index data under the abnormal label-free index item through an unsupervised abnormal recognition model to obtain unstable base station energy-saving index data with preliminary abnormal recognition;
and carrying out advanced anomaly identification on the energy-saving index data of the unstable base station which is initially identified as anomaly according to a second preset threshold value to obtain the energy-saving index data of the unstable base station which is finally identified as anomaly.
In one embodiment, the periodic base station energy saving index item corresponds to a third base station energy saving index data sequence;
the step of performing anomaly identification on the base station energy-saving index data sequences corresponding to the static base station energy-saving index item, the periodic base station energy-saving index item and the unstable base station energy-saving index item respectively according to a corresponding anomaly identification mode comprises the following steps:
dividing the third base station energy-saving index data sequence according to the period to obtain periodic base station energy-saving index data of each period;
predicting periodic base station energy-saving index data of a current period based on the periodic base station energy-saving index data of a previous period through a pre-trained periodic anomaly identification model, and determining the difference between the predicted periodic base station energy-saving index data of the current period and the periodic base station energy-saving index data of the current period in the third base station energy-saving index data sequence;
If the difference is larger than a preset difference threshold, judging that the energy-saving index data of the periodic base station in the current period is abnormal.
In one embodiment, each base station energy saving index item is a key base station energy saving index item; the obtaining the base station energy saving index data sequence corresponding to each base station energy saving index item respectively comprises the following steps:
acquiring base station energy saving index data sequences corresponding to candidate base station energy saving index items respectively;
dividing a base station energy-saving index data sequence corresponding to each candidate base station energy-saving index item into two groups of subsequences aiming at each candidate base station energy-saving index item;
carrying out hypothesis testing on the two groups of subsequences to obtain a hypothesis testing result;
and identifying key base station energy saving index items which are sensitive to abnormality from the candidate base station energy saving index items based on the hypothesis test result.
In a second aspect, the present application also provides an anomaly identification device for base station energy saving index data, where the device includes:
the index acquisition module is used for acquiring base station energy-saving index data sequences corresponding to the base station energy-saving index items respectively; the base station energy-saving index data sequence comprises base station energy-saving index data of the base station energy-saving index item at different time points;
The coefficient determining module is used for determining fluctuation characterization coefficients and autocorrelation coefficients corresponding to the energy-saving index items of the base stations respectively according to the energy-saving index data sequences of the base stations;
the index identification module is used for identifying a static base station energy-saving index item from all base station energy-saving index items according to the fluctuation characterization coefficient; according to the autocorrelation coefficients, periodically detecting each base station energy-saving index data sequence to identify periodic base station energy-saving index items from the base station energy-saving index items; determining an unstable base station energy saving index item according to base station energy saving index items except the periodic base station energy saving index item and the static base station energy saving index item;
the abnormal recognition module is used for recognizing the abnormal states of the base station energy-saving index data sequences corresponding to the static base station energy-saving index item, the periodic base station energy-saving index item and the unstable base station energy-saving index item respectively according to the corresponding abnormal recognition modes.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the steps described in the embodiments of the application when the processor executes the computer program.
In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps described in the embodiments of the present application.
In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps described in the various embodiments of the application.
According to the base station energy-saving index data sequence corresponding to each base station energy-saving index item, the fluctuation characterization coefficient and the autocorrelation coefficient corresponding to each base station energy-saving index item are determined, so that the static base station energy-saving index item and the periodic base station energy-saving index item can be accurately and conveniently identified from each base station energy-saving index item, the unstable base station energy-saving index item is further determined, then the base station energy-saving index data sequences corresponding to each static base station energy-saving index item, the periodic base station energy-saving index item and the unstable base station energy-saving index item are respectively subjected to anomaly identification according to the corresponding anomaly identification mode, adaptive anomaly identification processing is realized, and the accuracy of anomaly identification is greatly provided.
Drawings
Fig. 1 is an application scenario diagram of an anomaly identification method applicable to base station energy saving index data according to the present application in one embodiment;
FIG. 2 is a schematic diagram of a base station energy saving index item classification in one embodiment;
FIG. 3 is a schematic diagram of classification anomaly identification in one embodiment;
FIG. 4 is a schematic diagram illustrating a screening of key base station energy saving metrics in one embodiment;
FIG. 5 is a block diagram of an abnormality recognition device for base station energy saving index data in one embodiment;
fig. 6 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
In one embodiment, as shown in fig. 1, a method for identifying anomalies in energy saving index data of a base station is provided, and the method is applied to a computer device, which may be a terminal or a server, and the method may be performed by the terminal or the server alone or may be implemented through interaction between the terminal and the server. The method specifically comprises the following steps:
Step 102, acquiring base station energy saving index data sequences corresponding to the base station energy saving index items respectively.
The base station energy-saving index data sequence comprises base station energy-saving index data of base station energy-saving index items at different time points. The base station energy-saving index item is used for representing a base station energy-saving index. The base station energy-saving index items have different index data at different times, namely, the base station energy-saving index data, and the base station energy-saving index data at a plurality of time points are orderly arranged to form a base station energy-saving index data sequence.
It can be understood that each base station energy saving index item may be an initial base station energy saving index item, or may be a key base station energy saving index item to be subjected to anomaly analysis, which is screened from the initial base station energy saving index items.
In some embodiments, the base station energy saving index entry may include at least one of a number of energy saving deployment cells, an amount of energy saving, or a number of energy saving recommended cells, etc.
Step 104, according to the energy-saving index data sequence of each base station, determining the fluctuation characterization coefficient and the autocorrelation coefficient corresponding to each energy-saving index item of each base station.
The fluctuation characterization coefficient is used for characterizing the fluctuation degree of the base station energy-saving index data sequence. And the autocorrelation coefficient is used for representing the correlation degree between the base station energy-saving index data of the same base station energy-saving index item at different time points.
Specifically, for each base station energy-saving index item, the computer device may perform fluctuation degree analysis according to the base station energy-saving index data sequence corresponding to the base station energy-saving index item, so as to calculate a fluctuation characterization coefficient. The computer device may obtain the autocorrelation coefficients based on a degree of correlation between base station energy saving index data of the base station energy saving index data sequence at different points in time.
In some embodiments, the computer device may calculate the autocorrelation coefficient ACF (k) by the following formula:
wherein ACF (K) represents the autocorrelation coefficient at lag K, Z t For the base station energy saving index data sequence at any time t, n is the length of the base station energy saving index data sequence,is the mean value.
And 106, identifying a static base station energy-saving index item from the base station energy-saving index items according to the fluctuation characterization coefficient.
Specifically, the computer device may screen the static base station energy saving index items from the base station energy saving index items based on the fluctuation characterization coefficient. It can be understood that the fluctuation characterization coefficient of the selected static base station energy saving index item is smaller than the other remaining base station energy saving index items.
In some embodiments, the ripple characterization coefficient may be a coefficient of variation. The computer device may determine a base station energy saving indicator term having a coefficient of variation less than or equal to a first preset threshold as a static base station energy saving indicator term.
In some embodiments, the step of calculating the coefficient of variation comprises: determining standard deviation of a base station energy-saving index data sequence corresponding to each base station energy-saving index item; determining the average value of base station energy-saving index data in a base station energy-saving index data sequence; and determining a variation coefficient corresponding to the base station energy-saving index item according to the standard deviation and the average value.
In some embodiments, coefficient of variation C v This can be achieved by the following formula:
wherein σ is i For base station energy-saving index data x in base station energy-saving index data sequence i Standard deviation, mu i For base station energy-saving index data x in base station energy-saving index data sequence i Is a mean value of (c).
Step 108, according to the autocorrelation coefficient, the energy-saving index data sequence of each base station is periodically detected, so as to identify the energy-saving index item of the periodic base station from the energy-saving index items of each base station.
Specifically, the computer device may traverse the phase difference for the base station energy saving index data sequence, and when the autocorrelation coefficient of a certain phase difference is greater than a preset coefficient, consider that the base station energy saving index item has periodicity, that is, determine that the base station energy saving index item is a periodic base station energy saving index item.
Step 110, determining an unstable base station energy saving index item according to the base station energy saving index items except the periodical base station energy saving index item and the static base station energy saving index item.
In some embodiments, the computer device may determine remaining base station energy saving index entries of the base station energy saving index entries other than the periodic base station energy saving index entry and the static base station energy saving index entry, and determine the remaining base station energy saving index entries as unstable base station energy saving index entries. It will be appreciated that the computer device may also continue to screen and analyze the remaining base station energy saving metrics to determine unstable base station energy saving metrics therefrom.
In some embodiments, the computer device may also determine the base station energy saving index item with the variation coefficient greater than the first preset threshold, and then remove the periodic base station energy saving index item from the determined base station energy saving index item (i.e. the base station energy saving index item with the variation coefficient greater than the first preset threshold), where the remaining base station energy saving index items are unstable base station energy saving index items.
In some embodiments, a base station energy saving indicator term is determined to be an unstable base station energy saving indicator term when it satisfies the following condition:
c v more than c and not belonging to the energy saving index of the periodic base station;
wherein c is a first preset threshold value, c v And c is that the coefficient of variation is greater than a first predetermined threshold.
Step 112, respectively performing anomaly identification on the base station energy-saving index data sequences corresponding to the static base station energy-saving index item, the periodic base station energy-saving index item and the unstable base station energy-saving index item according to the corresponding anomaly identification modes.
It can be understood that the static base station energy-saving index item, the periodic base station energy-saving index item and the unstable base station energy-saving index item belong to three different base station energy-saving index items, and then, for the base station energy-saving index data sequences corresponding to the three different base station energy-saving index items, abnormality identification can be performed according to respective corresponding abnormality identification modes. That is, different types of base station energy saving index items can adaptively adopt different abnormality recognition modes to perform abnormality recognition.
To facilitate understanding of index item classification, a brief description will now be given with reference to fig. 2. Fig. 2 is a schematic diagram of base station energy saving index item classification in an embodiment. Referring to fig. 2, each base station energy saving index term may be divided into a static base station energy saving index term, a periodic base station energy saving index term, and an unstable base station energy saving index term according to a variation coefficient and an autocorrelation coefficient. The static base station energy-saving index item is screened by the variation coefficient being smaller than a first preset threshold value, the periodic base station energy-saving index item is obtained by traversing the phase difference, and if the autocorrelation coefficient of a certain phase difference is larger than a preset coefficient, the periodicity is judged. The unstable base station energy saving index item is a base station energy saving index item with a variation coefficient larger than a first preset threshold value and not belonging to the periodic base station energy saving index item.
According to the abnormal identification method of the base station energy-saving index data, according to the base station energy-saving index data sequences corresponding to the base station energy-saving index items respectively, the fluctuation characterization coefficient and the autocorrelation coefficient corresponding to the base station energy-saving index items respectively are determined, so that the static base station energy-saving index item and the periodic base station energy-saving index item can be accurately and conveniently identified from the base station energy-saving index items, the unstable base station energy-saving index item can be further determined, then the base station energy-saving index data sequences corresponding to the static base station energy-saving index item, the periodic base station energy-saving index item and the unstable base station energy-saving index item are respectively subjected to abnormal identification according to the corresponding abnormal identification mode, the self-adaptive abnormal identification processing is realized, and the accuracy of abnormal identification is greatly provided.
In some embodiments, the static base station energy saving index entry corresponds to the first base station energy saving index data sequence. In this embodiment, performing anomaly identification on base station energy saving index data sequences corresponding to the static base station energy saving index item, the periodic base station energy saving index item and the unstable base station energy saving index item respectively according to a corresponding anomaly identification mode, includes: sliding on the first base station energy saving index data sequence through a first moving average time window; carrying out average value calculation on the static base station energy saving index data positioned in the first moving average time window to obtain a first average value; and comparing the first average value with a first dynamic threshold value, and identifying abnormal data in the first base station energy-saving index data sequence according to the comparison result.
It is understood that the first base station energy saving index data sequence includes static base station energy saving index data at different time points. The first dynamic threshold is a threshold that dynamically and adaptively generates changes over time.
Specifically, the computer device may slide over the first base station energy saving index data sequence through a first moving average time window. This will continue to have static base station energy saving index data that falls within the first moving average time window. The computer device may perform a mean value calculation on the static base station energy saving index data located in the first moving average time window to obtain a first mean value. And the computer equipment compares the first average value with a first dynamic threshold value, and if the first average value is lower than the first dynamic threshold value, abnormal data exists in the static base station energy-saving index data in the first moving average time window.
In some embodiments, the first dynamic threshold may be determined from the first mean and the threshold coefficient α. That is, the first dynamic threshold may be determined from the product of the first mean and the threshold coefficient α.
According to the embodiment, the abnormal data can be conveniently and accurately identified according to the dynamic threshold value.
In some embodiments, the periodic base station energy saving index entry corresponds to a third base station energy saving index data sequence. In this embodiment, the performing anomaly identification on the base station energy saving index data sequences corresponding to the static base station energy saving index item, the periodic base station energy saving index item, and the unstable base station energy saving index item respectively according to the corresponding anomaly identification method includes: dividing the third base station energy-saving index data sequence according to the period to obtain periodic base station energy-saving index data of each period; predicting periodic base station energy-saving index data of a current period based on the periodic base station energy-saving index data of a previous period through a pre-trained periodic anomaly identification model, and determining the difference between the predicted periodic base station energy-saving index data of the current period and the periodic base station energy-saving index data of the current period in the third base station energy-saving index data sequence; if the difference is larger than a preset difference threshold, judging that the energy-saving index data of the periodic base station in the current period is abnormal.
Specifically, for the periodic base station energy-saving index item, the computer device may perform model training in advance using the historical periodic base station energy-saving index data sequence under the periodic base station energy-saving index item, to obtain the periodic anomaly identification model. The computer equipment can divide the current periodic base station energy-saving index data sequence corresponding to the periodic base station energy-saving index item into periods to obtain periodic base station energy-saving index data of each period. For each current period needing to be subjected to anomaly identification, predicting the periodic base station energy-saving index data of the current period based on the periodic base station energy-saving index data of the previous period through a periodic anomaly identification model, and determining the difference between the predicted periodic base station energy-saving index data of the current period and the real periodic base station energy-saving index data of the current period in a third base station energy-saving index data sequence. The computer equipment can compare the difference with a preset difference threshold, and if the difference is larger than the preset difference threshold, the computer equipment judges that the energy-saving index data of the periodical base stations in the two adjacent up-down periods are abnormal.
According to the embodiment, the abnormal identification can be performed aiming at the characteristics of the energy-saving index data of the periodic base station, and the abnormal data can be identified more accurately.
In some embodiments, the unstable base station power saving indicator term corresponds to a second base station power saving indicator data sequence. In this embodiment, performing anomaly identification on base station energy saving index data sequences corresponding to the static base station energy saving index item, the periodic base station energy saving index item and the unstable base station energy saving index item respectively according to a corresponding anomaly identification mode, includes: under the condition that a plurality of unstable base station energy-saving index items are provided, determining an unstable base station energy-saving index item with an abnormal label from the plurality of unstable base station energy-saving index items, and obtaining an abnormal label index item; aiming at the abnormal tag index item, acquiring historical unstable base station energy-saving index data of the abnormal tag index item, and determining a second dynamic threshold; sliding on a second base station energy-saving index data sequence through a second moving average time window, and calculating the mean value of unstable base station energy-saving index data positioned in the second moving average time window to obtain a second mean value; and identifying abnormal data in the second base station energy-saving index data sequence according to a comparison result between the second average value and the second dynamic threshold value.
It can be understood that, in the case that the unstable base station energy saving index items are plural, the computer device may further classify the plural unstable base station energy saving index items according to whether there is an abnormal tag, so as to divide the plural unstable base station energy saving index items into an abnormal tag index item and an abnormal tag free index item. Different treatments may be taken for the anomaly-tagged index item and the no-anomaly-tagged index item. The second base station energy-saving index data sequence comprises unstable base station energy-saving index data at different time points.
Specifically, the computer device may determine an unstable base station energy saving index item having an abnormal tag from a plurality of unstable base station energy saving index items, and obtain the abnormal tag index item. It is understood that the abnormal tag index item is an unstable base station energy saving index item to which abnormal data is recognized in the conventional process, and thus an abnormal tag is added thereto. For the abnormal tag indicator term, the computer device may obtain historical unstable base station energy saving indicator data for the abnormal tag indicator term, determining a second dynamic threshold. It will be appreciated that the second dynamic threshold is adaptively determined based on historical unstable base station energy saving indicator data for the anomaly tag indicator term, rather than a fixed threshold, which is more accurate.
The computer equipment can slide on the second base station energy-saving index data sequence through the second moving average time window, and average value calculation is carried out on unstable base station energy-saving index data positioned in the second moving average time window to obtain a second average value. The computer device may identify abnormal data in the second base station energy saving indicator data sequence based on a comparison between the second mean and the second dynamic threshold. Specifically, if the second average value is lower than the second dynamic threshold value, determining that abnormal data exists in the unstable base station energy saving index data in the second moving average time window.
In other embodiments, the computer device may also perform supervised training in advance according to the historical unstable base station energy-saving index data under the abnormal label index item, so as to train an abnormal recognition model, and may input the second base station energy-saving index data sequence to be recognized into the abnormal recognition model to perform abnormal recognition, so as to recognize the abnormal data in the second base station energy-saving index data sequence.
In some embodiments, the method further comprises: aiming at the non-abnormal tag index item in the plurality of unstable base station energy-saving index items, carrying out preliminary abnormal recognition on the unstable base station energy-saving index data under the non-abnormal tag index item through an unsupervised abnormal recognition model to obtain unstable base station energy-saving index data with preliminary abnormal recognition; and carrying out advanced anomaly identification on the energy-saving index data of the unstable base station which is initially identified as anomaly according to a second preset threshold value to obtain the energy-saving index data of the unstable base station which is finally identified as anomaly.
It can be appreciated that for a non-anomaly-tag indicator of the plurality of unstable base station energy saving indicator, the computer device can identify the anomaly data by combining the unsupervised training with a second preset threshold.
Specifically, the computer device can perform preliminary anomaly identification on the energy-saving index data of the unstable base station under the non-anomaly-tag index item through an unsupervised anomaly identification model to obtain the energy-saving index data of the unstable base station with the preliminary anomaly identification. And then, the computer equipment can conduct advanced anomaly identification on the energy-saving index data of the unstable base station which is initially identified as the anomaly according to a second preset threshold value, so as to obtain the energy-saving index data of the unstable base station which is finally identified as the anomaly.
In some embodiments, for a sequence of unstable base station energy-saving index data for primarily identifying an anomaly, that is, a primarily anomaly identification sequence, a third moving average time window may be used to slide on the primarily anomaly identification sequence, average calculation is performed on the unstable base station energy-saving index data located in the third moving average time window to obtain a third average, and if the third average is lower than a second preset threshold, it is determined that the anomaly data exists in the unstable base station energy-saving index data in the third moving average time window.
FIG. 3 is a schematic diagram of classification anomaly identification in one embodiment. Referring to fig. 3, for the static base station energy saving index item, a first dynamic threshold may be determined, and if the average value of the static base station energy saving index data in the time window is lower than the first dynamic threshold, the static base station energy saving index data is regarded as abnormal. Aiming at the energy-saving index item of the periodic base station, a periodic anomaly identification model can be trained in advance to identify anomalies. The abnormal recognition of the energy-saving index item of the unstable base station is divided into an abnormal label index item and an abnormal label-free index item, the threshold value can be updated based on historical data for the abnormal label index item, and the threshold value can be combined with an unsupervised abnormal recognition method for the abnormal label-free index item to perform abnormal recognition.
The embodiment can perform targeted abnormality recognition processing on the presence or absence of the tag, and can recognize the abnormal data more accurately.
In some embodiments, each base station energy saving indicator term is a critical base station energy saving indicator term. The obtaining the base station energy saving index data sequence corresponding to each base station energy saving index item respectively comprises the following steps: acquiring base station energy saving index data sequences corresponding to candidate base station energy saving index items respectively; dividing a base station energy-saving index data sequence corresponding to each candidate base station energy-saving index item into two groups of subsequences aiming at each candidate base station energy-saving index item; carrying out hypothesis testing on the two groups of subsequences to obtain a hypothesis testing result; and identifying key base station energy saving index items which are sensitive to abnormality from the candidate base station energy saving index items based on the hypothesis test result.
Specifically, the computer device may divide the base station energy saving index data sequence corresponding to the candidate base station energy saving index item into two sets of subsequences according to the target division basis. The target division basis can be energy saving in the base station energy saving system. That is, the base station energy saving index data sequence corresponding to each candidate base station energy saving index item may be divided into two sets of subsequences according to two cases that the change increment of the energy saving energy at a plurality of time points is greater than 0 and equal to 0. For example, according to the change increment of the energy saving amount of m time points being greater than 0 or equal to 0, the m base station energy saving index data in the base station energy saving index data sequence of each candidate base station energy saving index item are correspondingly divided into two groups, so as to obtain two groups of subsequences.
When the hypothesis test is carried out, the original hypothesis is that the two groups of sub-sequences are not different, the alternative hypothesis is that the two groups of sub-sequences are different, it can be understood that the aim is to find out the base station energy-saving index item with the difference between the two groups of sub-sequences, and the base station energy-saving index item can be considered to be sensitive to abnormality if the two groups of sub-sequences have larger difference. Therefore, the computer device can perform hypothesis testing on the two groups of subsequences to obtain a hypothesis testing result. And identifying key base station energy saving index items which are sensitive to abnormality from the candidate base station energy saving index items based on the hypothesis test result. Specifically, the computer device may compare the hypothesis test probability P value with the preset probability threshold K, and reject the original hypothesis if the P value is smaller than the preset probability threshold K, and accept the alternative hypothesis, where the base station energy-saving index item is considered to be sensitive to the system anomaly and has high significance, and is a key base station energy-saving index item that needs to be identified as anomaly subsequently. It can be understood that the health condition of the base station energy-saving system can be more accurately perceived by screening the base station energy-saving index items with strong abnormal sensitivity and high significance for abnormal identification analysis.
Fig. 4 is a schematic diagram illustrating screening of key base station energy saving indicators in an embodiment. As can be seen from fig. 4, the base station energy saving index data sequences under the candidate base station energy saving index items of each layer of the system are first input, the base station energy saving index data sequences are grouped by the gold standard (i.e. the target division basis) in the base station energy saving system, and then the hypothesis test is performed. Specifically, base station energy saving index data in m time points in the base station energy saving index data sequence of each candidate base station energy saving index item is marked as { k } 1 ,k 2 ,…,k m Dividing into two groups according to gold standards, e.g. into { k } 1 ,k 4 ,…,k m-1 { k } 2 ,k 3 ,…,k m Two sets. And screening out base station energy saving index items with hypothesis test probability P smaller than a probability threshold value as key base station energy saving index items.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides an abnormality recognition device for the base station energy saving index data, which is used for realizing the abnormality recognition method for the base station energy saving index data. The implementation scheme of the solution provided by the device is similar to the implementation scheme recorded in the method, so the specific limitation in the embodiment of the abnormality identification device for one or more base station energy saving index data provided below can be referred to the limitation of the abnormality identification method for the base station energy saving index data hereinabove, and is not repeated here.
In one embodiment, as shown in fig. 5, there is provided an abnormality identification device for base station energy saving index data, including: an index acquisition module 502, a coefficient determination module 504, an index identification module 506, and an anomaly identification module 508, wherein:
the index obtaining module 502 is configured to obtain base station energy saving index data sequences corresponding to the energy saving index items of each base station respectively; the base station energy-saving index data sequence comprises base station energy-saving index data of the base station energy-saving index item at different time points.
The coefficient determining module 504 is configured to determine, according to each base station energy saving index data sequence, a fluctuation characterization coefficient and an autocorrelation coefficient corresponding to each base station energy saving index item.
The index identification module 506 is configured to identify a static base station energy-saving index item from the base station energy-saving index items according to the fluctuation characterization coefficient; according to the autocorrelation coefficients, periodically detecting each base station energy-saving index data sequence to identify periodic base station energy-saving index items from the base station energy-saving index items; and determining an unstable base station energy saving index item according to the base station energy saving index items except the periodic base station energy saving index item and the static base station energy saving index item.
The anomaly identification module 508 is configured to identify anomalies according to the respective base station energy-saving index data sequences corresponding to the static base station energy-saving index item, the periodic base station energy-saving index item, and the unstable base station energy-saving index item.
In some embodiments, the coefficient determining module 504 is further configured to determine, for each base station energy saving indicator term, a standard deviation of a base station energy saving indicator data sequence corresponding to the base station energy saving indicator term; determining the average value of base station energy-saving index data in a base station energy-saving index data sequence; determining a variation coefficient corresponding to the base station energy-saving index item according to the standard deviation and the average value;
The index identification module 506 is further configured to determine a base station energy saving index item with a variation coefficient less than or equal to a first preset threshold value as a static base station energy saving index item.
In some embodiments, the static base station energy saving indicator term corresponds to a first base station energy saving indicator data sequence; the anomaly identification module 508 is further configured to slide on the first base station energy saving indicator data sequence through a first moving average time window; carrying out average value calculation on the static base station energy saving index data positioned in the first moving average time window to obtain a first average value; and comparing the first average value with a first dynamic threshold value, and identifying abnormal data in the first base station energy-saving index data sequence according to the comparison result.
In some embodiments, the unstable base station energy saving indicator term corresponds to a second base station energy saving indicator data sequence; the anomaly identification module 508 is further configured to determine an unstable base station energy saving index item with an anomaly tag from the plurality of unstable base station energy saving index items, to obtain an anomaly tag index item, if the unstable base station energy saving index items are plural; aiming at the abnormal tag index item, acquiring historical unstable base station energy-saving index data of the abnormal tag index item, and determining a second dynamic threshold; sliding on the second base station energy-saving index data sequence through a second moving average time window, and calculating the average value of the unstable base station energy-saving index data in the second moving average time window to obtain a second average value; and identifying abnormal data in the second base station energy-saving index data sequence according to a comparison result between the second average value and the second dynamic threshold value.
In some embodiments, the anomaly identification module 508 is further configured to perform preliminary anomaly identification on the unstable base station energy-saving index data under the non-anomaly-tag index item according to the non-anomaly-tag index item in the plurality of unstable base station energy-saving index items, to obtain unstable base station energy-saving index data with preliminary anomaly identification; and carrying out advanced anomaly identification on the energy-saving index data of the unstable base station which is initially identified as anomaly according to a second preset threshold value to obtain the energy-saving index data of the unstable base station which is finally identified as anomaly.
In some embodiments, the periodic base station energy saving index entry corresponds to a third base station energy saving index data sequence; the anomaly identification module 508 is further configured to divide the third base station energy saving index data sequence according to a period, so as to obtain periodic base station energy saving index data of each period; predicting periodic base station energy-saving index data of a current period based on the periodic base station energy-saving index data of a previous period through a pre-trained periodic anomaly identification model, and determining the difference between the predicted periodic base station energy-saving index data of the current period and the periodic base station energy-saving index data of the current period in the third base station energy-saving index data sequence; if the difference is larger than a preset difference threshold, judging that the energy-saving index data of the periodic base station in the current period is abnormal.
In some embodiments, the index obtaining module 502 is further configured to obtain base station energy saving index data sequences corresponding to candidate base station energy saving index items respectively; dividing a base station energy-saving index data sequence corresponding to each candidate base station energy-saving index item into two groups of subsequences aiming at each candidate base station energy-saving index item; carrying out hypothesis testing on the two groups of subsequences to obtain a hypothesis testing result; and identifying key base station energy saving index items which are sensitive to abnormality from the candidate base station energy saving index items based on the hypothesis test result.
All or part of each module in the abnormality recognition device of the base station energy saving index data can be realized by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be any of a primary base station or other network element device, and the internal structure diagram of which may be as shown in fig. 6. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program, when executed by a processor, implements a method for anomaly identification of base station energy saving index data.
It will be appreciated by those skilled in the art that the structure shown in FIG. 6 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, a computer device is provided that includes a memory having a computer program stored therein and a processor that when executing the computer program performs the steps of the above embodiments.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, implements the steps of the above embodiments.
In an embodiment, a computer program product is provided comprising a computer program which, when executed by a processor, implements the steps of the above embodiments.
It should be noted that, the user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related country and region.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.
Claims (10)
1. An anomaly identification method for base station energy saving index data, which is characterized by comprising the following steps:
acquiring base station energy-saving index data sequences corresponding to the base station energy-saving index items respectively; the base station energy-saving index data sequence comprises base station energy-saving index data of the base station energy-saving index item at different time points;
determining fluctuation characterization coefficients and autocorrelation coefficients respectively corresponding to energy-saving index items of each base station according to the energy-saving index data sequences of each base station;
Identifying a static base station energy-saving index item from the base station energy-saving index items according to the fluctuation characterization coefficient;
according to the autocorrelation coefficients, periodically detecting each base station energy-saving index data sequence to identify periodic base station energy-saving index items from the base station energy-saving index items;
determining an unstable base station energy saving index item according to base station energy saving index items except the periodic base station energy saving index item and the static base station energy saving index item;
and respectively carrying out anomaly identification on the base station energy-saving index data sequences corresponding to the static base station energy-saving index item, the periodic base station energy-saving index item and the unstable base station energy-saving index item according to corresponding anomaly identification modes.
2. The method of claim 1, wherein the fluctuation characterizing coefficient is a coefficient of variation; determining the fluctuation characterization coefficient and the autocorrelation coefficient corresponding to each base station energy-saving index item according to each base station energy-saving index data sequence, including:
determining standard deviation of a base station energy-saving index data sequence corresponding to each base station energy-saving index item;
determining the average value of base station energy-saving index data in a base station energy-saving index data sequence;
Determining a variation coefficient corresponding to the base station energy-saving index item according to the standard deviation and the average value;
and identifying a static base station energy-saving index item from the base station energy-saving index items according to the fluctuation characterization coefficient, wherein the method comprises the following steps of:
and determining the base station energy saving index item with the variation coefficient smaller than or equal to the first preset threshold value as a static base station energy saving index item.
3. The method of claim 1, wherein the static base station energy saving indicator term corresponds to a first base station energy saving indicator data sequence;
the step of performing anomaly identification on the base station energy-saving index data sequences corresponding to the static base station energy-saving index item, the periodic base station energy-saving index item and the unstable base station energy-saving index item respectively according to a corresponding anomaly identification mode comprises the following steps:
sliding on the first base station energy saving index data sequence through a first moving average time window;
carrying out average value calculation on the static base station energy saving index data positioned in the first moving average time window to obtain a first average value;
and comparing the first average value with a first dynamic threshold value, and identifying abnormal data in the first base station energy-saving index data sequence according to the comparison result.
4. The method of claim 1, wherein the unstable base station energy saving indicator term corresponds to a second base station energy saving indicator data sequence;
the step of performing anomaly identification on the base station energy-saving index data sequences corresponding to the static base station energy-saving index item, the periodic base station energy-saving index item and the unstable base station energy-saving index item respectively according to a corresponding anomaly identification mode comprises the following steps:
under the condition that the number of the unstable base station energy-saving index items is multiple, determining an unstable base station energy-saving index item with an abnormal label from the multiple unstable base station energy-saving index items, and obtaining an abnormal label index item;
aiming at the abnormal tag index item, acquiring historical unstable base station energy-saving index data of the abnormal tag index item, and determining a second dynamic threshold;
sliding on the second base station energy-saving index data sequence through a second moving average time window, and calculating the average value of the unstable base station energy-saving index data in the second moving average time window to obtain a second average value;
and identifying abnormal data in the second base station energy-saving index data sequence according to a comparison result between the second average value and the second dynamic threshold value.
5. The method according to claim 4, wherein the method further comprises:
aiming at an abnormal label-free index item in the plurality of unstable base station energy-saving index items, carrying out preliminary abnormal recognition on the unstable base station energy-saving index data under the abnormal label-free index item through an unsupervised abnormal recognition model to obtain unstable base station energy-saving index data with preliminary abnormal recognition;
and carrying out advanced anomaly identification on the energy-saving index data of the unstable base station which is initially identified as anomaly according to a second preset threshold value to obtain the energy-saving index data of the unstable base station which is finally identified as anomaly.
6. The method of claim 1, wherein the periodic base station energy saving indicator term corresponds to a third base station energy saving indicator data sequence;
the step of performing anomaly identification on the base station energy-saving index data sequences corresponding to the static base station energy-saving index item, the periodic base station energy-saving index item and the unstable base station energy-saving index item respectively according to a corresponding anomaly identification mode comprises the following steps:
dividing the third base station energy-saving index data sequence according to the period to obtain periodic base station energy-saving index data of each period;
predicting periodic base station energy-saving index data of a current period based on the periodic base station energy-saving index data of a previous period through a pre-trained periodic anomaly identification model, and determining the difference between the predicted periodic base station energy-saving index data of the current period and the periodic base station energy-saving index data of the current period in the third base station energy-saving index data sequence;
If the difference is larger than a preset difference threshold, judging that the energy-saving index data of the periodic base station in the current period is abnormal.
7. The method according to any one of claims 1 to 6, wherein each base station energy saving indicator term is a key base station energy saving indicator term; the obtaining the base station energy saving index data sequence corresponding to each base station energy saving index item respectively comprises the following steps:
acquiring base station energy saving index data sequences corresponding to candidate base station energy saving index items respectively;
dividing a base station energy-saving index data sequence corresponding to each candidate base station energy-saving index item into two groups of subsequences aiming at each candidate base station energy-saving index item;
carrying out hypothesis testing on the two groups of subsequences to obtain a hypothesis testing result;
and identifying key base station energy saving index items which are sensitive to abnormality from the candidate base station energy saving index items based on the hypothesis test result.
8. An abnormality identification device for base station energy saving index data, the device comprising:
the index acquisition module is used for acquiring base station energy-saving index data sequences corresponding to the base station energy-saving index items respectively; the base station energy-saving index data sequence comprises base station energy-saving index data of the base station energy-saving index item at different time points;
The coefficient determining module is used for determining fluctuation characterization coefficients and autocorrelation coefficients corresponding to the energy-saving index items of the base stations respectively according to the energy-saving index data sequences of the base stations;
the index identification module is used for identifying a static base station energy-saving index item from all base station energy-saving index items according to the fluctuation characterization coefficient; according to the autocorrelation coefficients, periodically detecting each base station energy-saving index data sequence to identify periodic base station energy-saving index items from the base station energy-saving index items; determining an unstable base station energy saving index item according to base station energy saving index items except the periodic base station energy saving index item and the static base station energy saving index item;
the abnormal recognition module is used for recognizing the abnormal states of the base station energy-saving index data sequences corresponding to the static base station energy-saving index item, the periodic base station energy-saving index item and the unstable base station energy-saving index item respectively according to the corresponding abnormal recognition modes.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310961862.XA CN117135663A (en) | 2023-08-01 | 2023-08-01 | Abnormality identification method and device for base station energy saving index data, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310961862.XA CN117135663A (en) | 2023-08-01 | 2023-08-01 | Abnormality identification method and device for base station energy saving index data, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117135663A true CN117135663A (en) | 2023-11-28 |
Family
ID=88857515
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310961862.XA Pending CN117135663A (en) | 2023-08-01 | 2023-08-01 | Abnormality identification method and device for base station energy saving index data, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117135663A (en) |
-
2023
- 2023-08-01 CN CN202310961862.XA patent/CN117135663A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CA3024960C (en) | Method,apparatus,and computer-readable medium for detecting anomalous user behavior | |
| CN112637132B (en) | Network anomaly detection method and device, electronic equipment and storage medium | |
| JP6815480B2 (en) | Methods and systems for discovering precursor substrings in time series | |
| US20060074828A1 (en) | Methods and apparatus for detecting temporal process variation and for managing and predicting performance of automatic classifiers | |
| US20170315855A1 (en) | Method of detecting anomalies on appliances and system thereof | |
| US7373332B2 (en) | Methods and apparatus for detecting temporal process variation and for managing and predicting performance of automatic classifiers | |
| CN110378386A (en) | Based on unmarked abnormality recognition method, device and the storage medium for having supervision | |
| CN111967535B (en) | Fault diagnosis method and device for temperature sensor of grain storage management scene | |
| CN116167010B (en) | Rapid identification method for abnormal events of power system with intelligent transfer learning capability | |
| CN110858072B (en) | Method and device for determining running state of equipment | |
| CN117170915A (en) | Data center equipment fault prediction method and device and computer equipment | |
| Li et al. | An adaptive prognostics method based on a new health index via data fusion and diffusion process | |
| Fargus | Optimisation of Correlation Matrix Memory Prognostic and Diagnostic Systems | |
| CN110874601B (en) | Method for identifying running state of equipment, state identification model training method and device | |
| CN116881029A (en) | Fault cause diagnosis method and device, computer equipment and storage medium | |
| CN116611003A (en) | Transformer fault diagnosis method, device and medium | |
| CN117135663A (en) | Abnormality identification method and device for base station energy saving index data, computer equipment and storage medium | |
| CN116186507A (en) | Feature subset selection method, device and storage medium | |
| US20060074826A1 (en) | Methods and apparatus for detecting temporal process variation and for managing and predicting performance of automatic classifiers | |
| CN113296990B (en) | Method and device for recognizing abnormity of time sequence data | |
| EP4360015A1 (en) | Method and system for optimizing training of a machine learning model | |
| US20060074827A1 (en) | Methods and apparatus for detecting temporal process variation and for managing and predicting performance of automatic classifiers | |
| CN118332481B (en) | Project data abnormity early warning method and system for power construction | |
| CN114137418B (en) | Storage battery performance recognition method, storage battery performance recognition device, computer equipment and storage medium | |
| CN117372161A (en) | Financial equipment evaluation model construction method, financial equipment evaluation method and device |
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 |