CN114580861A - Energy data anomaly detection method and device and energy system - Google Patents
Energy data anomaly detection method and device and energy system Download PDFInfo
- Publication number
- CN114580861A CN114580861A CN202210147724.3A CN202210147724A CN114580861A CN 114580861 A CN114580861 A CN 114580861A CN 202210147724 A CN202210147724 A CN 202210147724A CN 114580861 A CN114580861 A CN 114580861A
- Authority
- CN
- China
- Prior art keywords
- energy data
- data
- abnormal
- preset
- energy
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- 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
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/82—Energy audits or management systems therefor
Abstract
The application relates to an energy data anomaly detection method, an energy data anomaly detection device and an energy system, wherein the energy data anomaly detection method comprises the steps of obtaining a preset number of energy data samples, judging whether each energy data sample belongs to a preset anomaly type, if so, calculating the deviation degree of the energy data sample corresponding to the preset anomaly type, comparing the deviation degree with a corresponding standard value, and determining whether the energy data corresponding to the preset anomaly type is abnormal energy data according to a comparison result, so that the timeliness and the accuracy of energy data anomaly detection can be ensured, the problem of alarm prejudgment errors is avoided, and the user experience is enhanced.
Description
Technical Field
The application belongs to the technical field of energy systems, and particularly relates to an energy data anomaly detection method and device and an energy system.
Background
The energy data can help enterprises and units to know the energy consumption condition of the enterprises and units in a certain period of time, so that references are provided for the enterprises and units in operation, maintenance and decision of energy conservation and emission reduction. Meanwhile, the abnormality of the energy data can directly and indirectly represent whether the operation states of the enterprise and unit energy systems are abnormal, and the abnormality detection and analysis of the energy data are needed in order to effectively locate, evaluate and solve the abnormal states. However, data anomalies may be caused by system anomalies and errors, while errors have the characteristics of contingency and instantaneity, the quantity of energy source data is huge, and anomalous data caused by system errors is inevitably included in the energy source data, but the anomaly does not mean that the energy source data generated by the system is anomalous, so that the data anomalies need to be discriminated whether the data anomalies are caused by the system anomalies or the errors. At present, data anomaly detection methods mainly include statistics, distance calculation or machine learning, but the methods all require a large amount of data for data fitting, the timeliness is low and the accuracy is low, energy data is applied to demand side response, and the timeliness and the response accuracy of the energy data require accurate analysis of data in a small range, so that the existing data anomaly detection methods cannot meet the requirements of power transaction and demand side response in the field of energy internet.
Disclosure of Invention
In order to overcome the problems that the existing data anomaly detection method needs a large amount of data for data fitting, and is low in timeliness and accuracy, the application provides an energy data anomaly detection method, an energy data anomaly detection device and an energy system.
In a first aspect, the present application provides a method for detecting an abnormality in energy data, including:
acquiring a preset number of energy data samples;
judging whether each energy data sample belongs to a preset abnormal type;
if yes, calculating the deviation degree of the energy data sample corresponding to the preset abnormal type;
comparing the deviation with a corresponding standard value;
and determining whether the energy data corresponding to the preset abnormal type is abnormal energy data or not according to the comparison result.
Further, the calculating the deviation degree of the energy data sample corresponding to the preset abnormal type includes:
substituting the energy data sample corresponding to the preset abnormal type into a chi-square formula to obtain a chi-square value of the sample, wherein the chi-square formula is as follows:
wherein, χ2Is a chi-square value, k is a preset number of energy data samples, i is a current energy data sample, fiFor the current energy data sample value, npiIs the average value from the first energy data sample to the current energy data sample;
and taking the chi-square value as the deviation degree of the energy data sample.
Further, the method for obtaining the corresponding standard value comprises the following steps:
establishing a comparison table of significance level, energy data sample quantity and standard value;
and matching the preset quantity and the set significance level of the energy data samples with the significance level and the energy data sample quantity and standard value comparison table to obtain corresponding standard values.
Further, the abnormal type includes negative data, and the calculating the deviation degree of the energy data sample corresponding to the preset abnormal type includes:
selecting energy data samples which belong to the energy data sample preset range corresponding to the negative data abnormal type;
substituting the energy data samples corresponding to the negative data abnormal types and the energy data samples within the preset range into a chi-square formula to obtain a first chi-square value;
and taking the first chi-square value as the deviation degree of the energy data sample.
Further, the determining, according to the comparison result, whether the energy data corresponding to the preset abnormal type is abnormal energy data includes:
if the deviation degree of the energy data sample is smaller than the corresponding standard value, judging that the energy data corresponding to the negative data abnormal type is not abnormal energy data;
and if the deviation degree of the energy data sample is not less than the corresponding standard value, judging that the energy data corresponding to the negative data abnormal type is negative abnormal energy data, and sending alarm information that the data is negative and the monitoring equipment is abnormally restarted.
Further, the method also comprises the following steps:
and if the number of times of occurrence of the negative abnormal energy data exceeds a preset first time threshold value within a preset time period, sending alarm information that the equipment and/or the monitoring equipment of the acquired data are abnormal.
Further, the abnormal type includes data of 0, and the calculating the deviation degree of the energy data sample corresponding to the preset abnormal type includes:
selecting energy data samples which belong to an energy data sample preset range corresponding to the abnormal type with the data of 0;
substituting the energy data sample corresponding to the abnormal type with the data of 0 and the energy data sample in the preset range into a chi-square formula to obtain a second chi-square value;
and taking the second chi-square value as the deviation degree of the energy data sample.
Further, the determining, according to the comparison result, whether the energy data corresponding to the preset abnormal type is abnormal energy data includes:
if the deviation degree of the energy data sample is smaller than the corresponding standard value, judging that the energy data corresponding to the abnormal type with the data of 0 is not abnormal energy data;
and if the deviation degree of the energy data sample is not less than the corresponding standard value, judging that the energy data corresponding to the type of 0 abnormal data is 0 abnormal energy data, and sending alarm information that the data is 0 and the data transmission of the monitoring equipment is abnormal.
Further, the method also comprises the following steps:
and if the occurrence frequency of the abnormal energy data is 0 in the preset time period and exceeds the preset second frequency threshold value, sending alarm information of abnormal power failure of the equipment with the acquired data.
Further, the exception type includes no data, and further includes:
and detecting the energy data samples transmitted behind the energy data samples corresponding to the data-free abnormal type, and if the energy data samples are data-free, sending alarm information of abnormal off-line of the monitoring equipment.
Further, if there is data transmission behind the energy data sample corresponding to the data-free abnormal type, the method further includes:
selecting energy data samples which belong to the energy data sample preset range corresponding to the data-free abnormal type;
substituting the energy data samples corresponding to the data-free abnormal type and the energy data samples within the preset range into a chi-square formula to obtain a third chi-square value;
and taking the third chi-square value as the deviation degree of the energy data sample.
Further, the determining, according to the comparison result, whether the energy data corresponding to the preset abnormal type is abnormal energy data includes:
if the deviation degree of the energy data sample is smaller than the corresponding standard value, judging that the energy data corresponding to the data-free abnormal type is not abnormal energy data;
if the deviation degree of the energy data sample is not smaller than the corresponding standard value, the energy data corresponding to the data-free abnormal type is judged to be data-free abnormal energy data, and alarm information of data-free and abnormal monitoring equipment is sent.
Further, the calculating the deviation degree of the energy data sample corresponding to the preset abnormal type includes:
selecting energy data samples in a preset range of energy data samples corresponding to the abnormal types of the data exceeding the preset range;
substituting the energy data sample corresponding to the abnormal type with the data exceeding the preset range and the energy data sample within the preset range into a chi-square formula to obtain a fourth chi-square value;
and taking the fourth chi-square value as the deviation degree of the energy data sample.
Further, the determining, according to the comparison result, whether the energy data corresponding to the preset abnormal type is abnormal energy data includes:
if the deviation degree of the energy data sample is smaller than the corresponding standard value, judging that the energy data corresponding to the abnormal type with the data exceeding the preset range is not abnormal energy data;
if the deviation degree of the energy data sample is not smaller than the corresponding standard value, the energy data corresponding to the abnormal type of the data exceeding the preset range is judged to be the abnormal energy data exceeding the preset range, and alarm information that the data exceed the preset range and the monitoring equipment is abnormally restarted is sent.
Further, the method also comprises the following steps:
and if the occurrence frequency of the abnormal energy data exceeding the preset range in the preset time period exceeds a preset third frequency threshold value, sending alarm information that the equipment is in overload operation or new equipment is merged into.
Further, the calculating the deviation degree of the energy data sample corresponding to the preset abnormal type includes:
and substituting the energy data samples corresponding to the preset abnormal types into a binomial test formula to obtain the deviation of the samples.
In a second aspect, the present application provides an energy data abnormality detection apparatus, including:
the acquisition module is used for acquiring a preset number of energy data samples;
the judging module is used for judging whether each energy data sample belongs to a preset abnormal type;
the calculation module is used for calculating the deviation degree of the energy data sample corresponding to the preset abnormal type when the energy data sample belongs to the preset abnormal type;
the comparison module is used for comparing the deviation degree with a corresponding standard value;
and the determining module is used for determining whether the energy data corresponding to the preset abnormal type is abnormal energy data according to the comparison result.
In a third aspect, the present application provides an energy system comprising:
the energy data abnormality detection apparatus according to the second aspect.
The technical scheme provided by the embodiment of the application can have the following beneficial effects:
the energy data anomaly detection method comprises the steps of obtaining a preset number of energy data samples, judging whether each energy data sample belongs to a preset anomaly type, if so, calculating the deviation degree of the energy data sample corresponding to the preset anomaly type, comparing the deviation degree with a corresponding standard value, and determining whether the energy data corresponding to the preset anomaly type is abnormal energy data according to a comparison result, so that the timeliness and the accuracy of energy data anomaly detection can be guaranteed, the problem of alarm prejudgment errors is avoided, and the user experience is enhanced.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and, together with the description, serve to explain the principles of the application.
Fig. 1 is a flowchart of an energy data anomaly detection method according to an embodiment of the present application.
Fig. 2 is a flowchart of an energy data anomaly detection method according to another embodiment of the present application.
Fig. 3 is a flowchart of another energy data anomaly detection method according to another embodiment of the present application.
Fig. 4 is a flowchart of another energy data anomaly detection method according to another embodiment of the present application.
Fig. 5 is a flowchart of another energy data anomaly detection method according to another embodiment of the present application.
Fig. 6 is a flowchart of another energy data anomaly detection method according to another embodiment of the present application.
Fig. 7 is a functional block diagram of an energy data abnormality detection apparatus according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail below. It should be apparent that the described embodiments are only a few embodiments of the present application, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the examples given herein without making any creative effort, shall fall within the protection scope of the present application.
Fig. 1 is a flowchart of an energy data anomaly detection method according to an embodiment of the present application, and as shown in fig. 1, the energy data anomaly detection method includes:
s11: acquiring a preset number of energy data samples;
s12: judging whether each energy data sample belongs to a preset abnormal type;
s13: if yes, calculating the deviation degree of the energy data sample corresponding to the preset abnormal type;
s14: comparing the deviation degree with a corresponding standard value;
s15: and determining whether the energy data corresponding to the preset abnormal type is abnormal energy data or not according to the comparison result.
The traditional abnormal energy data detection method needs a large amount of data for data fitting, is low in timeliness and accuracy, and the energy data is applied to demand side response, and the timeliness and the response accuracy of the energy data require accurate analysis on the data in a small range, so that the existing abnormal energy data detection method cannot meet the requirements of electric power transaction and demand side response in the field of energy internet.
In this embodiment, the energy data abnormality detection method includes acquiring a preset number of energy data samples, determining whether each energy data sample belongs to a preset abnormal type, if so, calculating a deviation degree of the energy data sample corresponding to the preset abnormal type, comparing the deviation degree with a corresponding standard value, and determining whether the energy data corresponding to the preset abnormal type is abnormal energy data according to a comparison result, so that timeliness and accuracy of energy data abnormality detection can be guaranteed, the problem of alarm pre-determination errors is avoided, the alarm frequency is reduced, and user experience is enhanced.
Fig. 2 is a flowchart of an energy data abnormality detection method according to another embodiment of the present application, and as shown in fig. 2, the energy data abnormality detection method includes:
s21: acquiring a preset number of energy data samples;
s22: judging whether each energy data sample belongs to a preset abnormal type;
s23: if yes, substituting the energy data sample corresponding to the preset abnormal type into a chi-square formula to obtain a chi-square value of the sample, wherein the chi-square formula is as follows:
wherein, χ2Is a chi-square value, k is a preset number of energy data samples, i is a current energy data sample, fiFor the current energy data sample value, npiIs the average value from the first energy data sample to the current energy data sample;
it should be noted that the k value is associated with the computing power, the detection response time and the user experience of the computer, and in order to avoid the detection response time being too long, the k value should not be too large; the significance level, i.e., the accuracy level, may be set as appropriate, and an example significance level ρ of 0.05 indicates that the data is 95% feasible.
S24: taking the chi-square value as the deviation degree of the energy data sample;
s25: establishing a comparison table of significance level, energy data sample quantity and standard value;
s26: matching the preset number of the energy data samples, the set significance level and the significance level, and the number of the energy data samples and the standard value comparison table to obtain corresponding standard values;
s27: comparing the deviation degree with a corresponding standard value;
s28: and determining whether the energy data corresponding to the preset abnormal type is abnormal energy data or not according to the comparison result.
χ2The number of samples tested can be small, which is not available with prediction methods such as data fitting, machine learning, etc. Chi shape2The method has the advantages of small sample quantity, requirement of local data sampling with accurate data and more suitability for the field of energy data anomaly detection.
As shown in fig. 3, the abnormality type includes negative data, and the energy data abnormality detection method includes:
s31: selecting energy data samples which belong to the energy data sample preset range corresponding to the negative data abnormal type;
if the preset number of the energy data samples is k, and the energy data sample corresponding to the negative data abnormal type is the ith energy data sample, the preset range is an interval of [ i-k/2, i + k/2 ].
S32: substituting the energy data samples corresponding to the negative data abnormal types and the energy data samples within the preset range into a chi-square formula to obtain a first chi-square value;
s33: taking the first chi-square value as the deviation degree of the energy data sample;
s34: if the deviation degree of the energy data sample is smaller than the corresponding standard value, judging that the energy data is not abnormal energy data;
s35: and if the deviation degree of the energy data sample is not less than the corresponding standard value, judging that the energy data is negative abnormal energy data, and sending alarm information that the data is negative and the monitoring equipment is abnormally restarted.
S36: and if the number of times of occurrence of the negative abnormal energy data exceeds a preset first time threshold value within a preset time period, sending alarm information that the equipment and/or the monitoring equipment of the acquired data are abnormal.
The first count threshold is, for example, 5. For example, if negative data is detected in the energy data section, namely the detected energy data is less than 0, expanding the detection range of the sample i to [ i-k/2, i + k/2], substituting the energy data sample in [ i-k/2, i + k/2] into a chi-square formula to calculate a chi 2 value, and if the energy data sample is in a standard value range corresponding to the set significance level, considering the abnormality as an error and not processing the error; if the data is not in the standard value range corresponding to the set significance level, the problems of abnormal restart of data monitoring equipment (such as an ammeter) and the like may exist, and an alarm short message with negative data is sent to remind operation and maintenance personnel to detect. If the abnormity appears repeatedly for a plurality of times (5 times or more) in one day, the alarm reminds the operation and maintenance personnel to detect the abnormal conditions of the equipment of the acquired data and the monitoring equipment.
As shown in fig. 4, the abnormality type includes data of 0, and the energy data abnormality detection method includes:
s41: selecting energy data samples which belong to an energy data sample preset range corresponding to the abnormal type with the data of 0;
s42: substituting the energy data sample corresponding to the abnormal type with the data of 0 and the energy data sample in the preset range into a chi-square formula to obtain a second chi-square value;
s43: taking the second chi-square value as the deviation degree of the energy data sample;
s44: if the deviation degree of the energy data sample is smaller than the corresponding standard value, judging that the energy data is not abnormal energy data;
s45: and if the deviation degree of the energy data sample is not less than the corresponding standard value, judging that the energy data is abnormal energy data with the data of 0, and sending alarm information that the data is abnormal and the data transmission of the monitoring equipment is abnormal, wherein the data of the alarm information is 0.
S46: and if the occurrence frequency of the abnormal energy data is 0 in the preset time period and exceeds the preset second frequency threshold value, sending alarm information of abnormal power failure of the equipment with the acquired data.
For example, if the energy data segment is detected to have data with a value of 0, expanding the detection range of the sample i to [ i-k/2, i + k/2], substituting the energy data sample in the [ i-k/2, i + k/2] range into the chi-square formula to calculate the chi 2 value, and if the energy data sample is in the standard value range corresponding to the set significance level, considering the abnormality as an error and not processing the error; if the monitoring device is not within the range, the data transmission problem of the monitoring device may exist, and the alarm short message with negative data is sent to remind operation and maintenance personnel to pay attention to the abnormal condition of the monitoring device (such as an ammeter). If the abnormity appears for a plurality of times continuously, the alarm reminds the operation and maintenance personnel to be abnormally powered off by the acquisition equipment.
As shown in fig. 5, the abnormality type includes no data, and the energy data abnormality detection method includes:
s51: and detecting the energy data samples transmitted behind the energy data samples corresponding to the data-free abnormal types, and if the energy data samples are data-free, sending alarm information for monitoring abnormal offline of equipment.
S52: if data transmission is carried out on the energy data samples corresponding to the data exception-free types, selecting the energy data samples within a preset range of the energy data samples corresponding to the data exception-free types;
s53: substituting the energy data samples corresponding to the data-free abnormal type and the energy data samples within the preset range into a chi-square formula to obtain a third chi-square value;
s54: taking the third chi-square value as the deviation degree of the energy data sample;
s55: if the deviation degree of the energy data sample is smaller than the corresponding standard value, judging that the energy data corresponding to the data-free abnormal type is not abnormal energy data;
s56: if the deviation degree of the energy data sample is not smaller than the corresponding standard value, the energy data corresponding to the data-free abnormal type is judged to be data-free abnormal energy data, and alarm information of data-free and abnormal monitoring equipment is sent.
For example, a breakpoint without data is detected in the energy data segment, several samples transmitted thereafter need to be detected first, if no data exists, the alarm monitoring device is off-line abnormally, if data is reported thereafter, the inspection range is extended to [ i-k/2, i + k/2] by taking the breakpoint as the center, chi-square formula is substituted to calculate chi-2 value, and if the breakpoint is within the standard value range corresponding to the set significance level, the data is considered as abnormal; if the current time is not within the range, judging that the monitoring equipment is abnormal.
As shown in fig. 6, the abnormality type includes that the data exceeds a preset range, and the energy data abnormality detection method includes:
s61: selecting energy data samples in a preset range of energy data samples corresponding to the abnormal types of the data exceeding the preset range;
for example, if the difference between the value of one energy data in the energy data segment and the value of the adjacent energy source data exceeds the preset range, for example, 10 times or 100 times, it is determined that the energy data belongs to the abnormal type in which the data exceeds the preset range.
S62: substituting the energy data sample corresponding to the abnormal type with the data exceeding the preset range and the energy data sample within the preset range into a chi-square formula to obtain a fourth chi-square value;
s63: taking the fourth chi-square value as the deviation degree of the energy data sample;
s64: if the deviation degree of the energy data sample is smaller than the corresponding standard value, judging that the energy data corresponding to the abnormal type with the data exceeding the preset range is not abnormal energy data;
s65: if the deviation degree of the energy data sample is not smaller than the corresponding standard value, the energy data corresponding to the abnormal type of the data exceeding the preset range is judged to be the abnormal energy data exceeding the preset range, and alarm information that the data exceed the preset range and the monitoring equipment is abnormally restarted is sent.
S66: and if the occurrence frequency of the abnormal energy data exceeding the preset range in the preset time period exceeds the preset third frequency threshold value, sending alarm information that the equipment is in overload operation or new equipment is merged in.
For example, if the data detected in the energy data segment exceeds a preset range, expanding the detection range to [ i-k/2, i + k/2] for the sample i, substituting the extended detection range into the chi-square formula to calculate the chi-2 value, and if the detected data is within the standard value range corresponding to the set significance level, considering the abnormality as an error and not processing the abnormality; if the data monitoring device is not in the range, the problems of abnormal restart of the data monitoring device (such as an ammeter) and the like may exist, and an alarm short message with negative data is sent to remind operation and maintenance personnel to detect. If the abnormality occurs for a plurality of times (5 times or more), the alarm reminds the operation and maintenance personnel to check the abnormal condition that the equipment runs in an overload mode or new equipment is merged.
In some embodiments, calculating the deviation of the energy data sample corresponding to the preset anomaly type includes:
and substituting the energy data samples corresponding to the preset abnormal types into a binomial test formula to obtain the deviation of the samples.
It is understood that the binomial test method belongs to the prior art in the field and is not described in detail herein.
The binomial test method is suitable for a scene with smaller data quantity or an application scene with less abnormal types.
The accuracy level of the response of the energy system on the demand side can be obviously influenced by the accuracy of the local data, abnormal data can be effectively discriminated under the condition of a small sample through X2 inspection, and then whether the abnormal data are caused by errors or whether the equipment or the system is abnormal is judged, so that the abnormal type of the local data can be well judged, an alarm can be given in time, and the false alarm is avoided.
In the embodiment, the problem of alarm pre-judgment error caused by mutation data can be avoided, the alarm accuracy is improved, the alarm frequency is reduced, and the user experience is enhanced; and the abnormal type of the data can be accurately predicted, such as the data is negative, the data is 0, no data exists, the data exceeds a preset range and the like, different alarm information is sent according to the abnormal type, so that maintenance personnel can repair the data conveniently, and the repair time is shortened.
An embodiment of the present invention provides an energy data anomaly detection apparatus, as shown in a functional structure diagram of fig. 7, including:
an obtaining module 71, configured to obtain a preset number of energy data samples;
the judging module 72 is used for judging whether each energy data sample belongs to a preset abnormal type;
the calculating module 73 is configured to calculate a deviation degree of the energy data sample corresponding to the preset abnormal type when the energy data sample belongs to the preset abnormal type;
a comparison module 74 for comparing the deviation with a corresponding standard value;
and a determining module 75, configured to determine whether the energy data corresponding to the preset abnormal type is abnormal energy data according to the comparison result.
In some embodiments, the calculation module 73 is configured to:
substituting the energy data sample corresponding to the preset abnormal type into a chi-square formula to obtain a chi-square value of the sample, wherein the chi-square formula is as follows:
wherein, χ2Is a chi-square value, k is a preset number of energy data samples, i is a current energy data sample, fiFor the current energy data sample value, npiIs the average value from the first energy data sample to the current energy data sample;
and taking the chi-square value as the deviation degree of the energy data sample.
The comparing module 74 further includes a corresponding standard value obtaining unit, configured to establish a comparison table of the significance level and the number of the energy data samples, and match the preset number of the energy data samples and the set significance level with the significance level and the number of the energy data samples and the standard value comparison table to obtain a corresponding standard value.
In some embodiments, the anomaly type comprises negative data, and the calculation module 73 is configured to:
selecting energy data samples which belong to the energy data sample preset range corresponding to the negative data abnormal type;
substituting the energy data samples corresponding to the negative data abnormal types and the energy data samples within the preset range into a chi-square formula to obtain a first chi-square value;
and taking the first chi-square value as the deviation degree of the energy data sample.
Further, the determination module 75 is configured to:
if the deviation degree of the energy data sample is smaller than the corresponding standard value, judging that the energy data corresponding to the negative data abnormal type is not abnormal energy data;
and if the deviation degree of the energy data sample is not less than the corresponding standard value, judging that the energy data corresponding to the negative data abnormal type is negative abnormal energy data, and sending alarm information that the data is negative and the monitoring equipment is abnormally restarted.
The determination module 75 is further configured to:
and if the number of times of occurrence of the negative abnormal energy data exceeds a preset first time threshold value within a preset time period, sending alarm information that the equipment and/or the monitoring equipment of the acquired data are abnormal.
In some embodiments, the exception type includes data of 0, and the calculation module 73 is configured to:
selecting energy data samples which belong to an energy data sample preset range corresponding to the abnormal type with the data of 0;
substituting the energy data sample corresponding to the abnormal type with the data of 0 and the energy data sample in the preset range into a chi-square formula to obtain a second chi-square value;
and taking the second chi-square value as the deviation degree of the energy data sample.
The determination module 75 is configured to:
if the deviation degree of the energy data sample is smaller than the corresponding standard value, judging that the energy data corresponding to the abnormal type with the data of 0 is not abnormal energy data;
and if the deviation degree of the energy data sample is not less than the corresponding standard value, judging that the energy data corresponding to the type of 0 abnormal data is 0 abnormal energy data, and sending alarm information that the data is 0 and the data transmission of the monitoring equipment is abnormal.
The determination module 75 is further configured to: and if the occurrence frequency of the abnormal energy data is 0 in the preset time period exceeds the preset second frequency threshold, sending alarm information of abnormal power failure of the equipment with the acquired data.
In some embodiments, the abnormal type includes no data, and the method further includes a continuous detection unit, which is configured to detect the energy data sample transmitted behind the energy data sample corresponding to the abnormal type without data, and send alarm information of abnormal offline of the monitoring device if the energy data sample is determined to be no data.
If the energy data sample corresponding to the data exception-free type is followed by data transmission, the calculation module 73 is configured to:
selecting energy data samples which belong to the energy data sample preset range corresponding to the data-free abnormal type;
substituting the energy data samples corresponding to the data-free abnormal type and the energy data samples within the preset range into a chi-square formula to obtain a third chi-square value;
and taking the third chi-square value as the deviation degree of the energy data sample.
The determination module 75 is configured to:
if the deviation degree of the energy data sample is smaller than the corresponding standard value, judging that the energy data corresponding to the data-free abnormal type is not abnormal energy data;
if the deviation degree of the energy data sample is not smaller than the corresponding standard value, the energy data corresponding to the data-free abnormal type is judged to be data-free abnormal energy data, and alarm information of data-free and abnormal monitoring equipment is sent.
In some embodiments, the anomaly type includes data out of a preset range, and the calculation module 73 is configured to:
selecting energy data samples in a preset range of energy data samples corresponding to the abnormal types of the data exceeding the preset range;
substituting the energy data sample corresponding to the abnormal type with the data exceeding the preset range and the energy data sample within the preset range into a chi-square formula to obtain a fourth chi-square value;
and taking the fourth chi-square value as the deviation degree of the energy data sample.
The determination module 75 is configured to:
if the deviation degree of the energy data sample is smaller than the corresponding standard value, judging that the energy data corresponding to the abnormal type with the data exceeding the preset range is not abnormal energy data;
if the deviation degree of the energy data sample is not smaller than the corresponding standard value, the energy data corresponding to the abnormal type of the data exceeding the preset range is judged to be the abnormal energy data exceeding the preset range, and alarm information that the data exceed the preset range and the monitoring equipment is abnormally restarted is sent.
The determination module 75 is further configured to: and if the occurrence frequency of the abnormal energy data exceeding the preset range in the preset time period exceeds the preset third frequency threshold value, sending alarm information that the equipment is in overload operation or new equipment is merged in.
In some embodiments, the calculation module is further configured to substitute the energy data samples corresponding to the preset anomaly types into a binomial test formula to obtain the deviation degrees of the samples.
In this embodiment, a preset number of energy data samples are obtained through the obtaining module, the judging module judges whether each energy data sample belongs to a preset abnormal type, the calculating module calculates the deviation of the energy data sample corresponding to the preset abnormal type when the energy data sample belongs to the preset abnormal type, the comparing module compares the deviation with a corresponding standard value, and the determining module determines whether the energy data corresponding to the preset abnormal type is abnormal energy data according to the comparison result, so as to ensure the timeliness and accuracy of energy data abnormality detection, avoid the problem of alarm prejudgment errors, reduce the alarm frequency, and enhance the user experience.
An embodiment of the present invention provides an energy system, including: the energy data abnormality detection apparatus according to the above embodiment.
It is understood that the same or similar parts in the above embodiments may be mutually referred to, and the same or similar parts in other embodiments may be referred to for the content which is not described in detail in some embodiments.
It should be noted that, in the description of the present application, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Further, in the description of the present application, the meaning of "a plurality" means at least two unless otherwise specified.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and the scope of the preferred embodiments of the present application includes other implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
It should be noted that the present invention is not limited to the above-mentioned preferred embodiments, and those skilled in the art can obtain other products in various forms without departing from the spirit of the present invention, but any changes in shape or structure can be made within the scope of the present invention with the same or similar technical solutions as those of the present invention.
Claims (18)
1. An energy data abnormality detection method, characterized by comprising:
acquiring a preset number of energy data samples;
judging whether each energy data sample belongs to a preset abnormal type;
if yes, calculating the deviation degree of the energy data sample corresponding to the preset abnormal type;
comparing the deviation with a corresponding standard value;
and determining whether the energy data corresponding to the preset abnormal type is abnormal energy data or not according to the comparison result.
2. The method according to claim 1, wherein the calculating the deviation degree of the energy data samples corresponding to the preset abnormality type includes:
substituting the energy data sample corresponding to the preset abnormal type into a chi-square formula to obtain a chi-square value of the sample, wherein the chi-square formula is as follows:
wherein, χ2Is a chi-square value, k is a preset number of energy data samples, i is a current energy data sample, fiFor the current energy data sample value, npiIs the average value from the first energy data sample to the current energy data sample;
and taking the chi-square value as the deviation degree of the energy data sample.
3. The method according to claim 1, wherein the method of acquiring the correspondence criterion value includes:
establishing a comparison table of significance level, energy data sample quantity and standard value;
and matching the preset quantity and the set significance level of the energy data samples with the significance level and the energy data sample quantity and standard value comparison table to obtain corresponding standard values.
4. The method according to claim 2, wherein the anomaly type includes negative data, and the calculating the degree of deviation of the energy data samples corresponding to the preset anomaly type includes:
selecting energy data samples which belong to the energy data sample preset range corresponding to the negative data abnormal type;
substituting the energy data samples corresponding to the negative data abnormal types and the energy data samples within the preset range into a chi-square formula to obtain a first chi-square value;
and taking the first chi-square value as the deviation degree of the energy data sample.
5. The method for detecting the abnormality of the energy data according to claim 4, wherein the determining whether the energy data corresponding to the preset abnormality type is abnormal energy data according to the comparison result includes:
if the deviation degree of the energy data sample is smaller than the corresponding standard value, judging that the energy data corresponding to the negative data abnormal type is not abnormal energy data;
and if the deviation degree of the energy data sample is not less than the corresponding standard value, judging that the energy data corresponding to the negative data abnormal type is negative abnormal energy data, and sending alarm information that the data is negative and the monitoring equipment is abnormally restarted.
6. The method of detecting an abnormality in energy data according to claim 5, further comprising:
and if the number of times of occurrence of the negative abnormal energy data exceeds a preset first time threshold value within a preset time period, sending alarm information that the equipment and/or the monitoring equipment of the acquired data are abnormal.
7. The method according to claim 2, wherein the abnormality type includes data of 0, and the calculating the degree of deviation of the energy data samples corresponding to the preset abnormality type includes:
selecting energy data samples which belong to an energy data sample preset range corresponding to the abnormal type with the data of 0;
substituting the energy data sample corresponding to the abnormal type with the data of 0 and the energy data sample in the preset range into a chi-square formula to obtain a second chi-square value;
and taking the second chi-square value as the deviation degree of the energy data sample.
8. The method for detecting abnormality of energy data according to claim 7, wherein said determining whether the energy data corresponding to the preset abnormality type is abnormal energy data according to the comparison result includes:
if the deviation degree of the energy data sample is smaller than the corresponding standard value, judging that the energy data corresponding to the abnormal type with the data of 0 is not abnormal energy data;
if the deviation degree of the energy data sample is not smaller than the corresponding standard value, the energy data corresponding to the abnormal type with the data of 0 is judged to be the abnormal energy data with the data of 0, and alarm information that the data of 0 and the data transmission of the monitoring equipment are abnormal is sent.
9. The method for detecting abnormality in energy source data according to claim 8, characterized by further comprising:
and if the occurrence frequency of the abnormal energy data is 0 in the preset time period exceeds the preset second frequency threshold, sending alarm information of abnormal power failure of the equipment with the acquired data.
10. The method according to claim 2, wherein the abnormality type includes no data, further comprising:
and detecting the energy data samples transmitted behind the energy data samples corresponding to the data-free abnormal types, and if the energy data samples are data-free, sending alarm information for monitoring abnormal offline of equipment.
11. The method according to claim 10, wherein if the energy data sample corresponding to the type without data anomaly is followed by data transmission, the method further comprises:
selecting energy data samples which belong to the energy data sample preset range corresponding to the data-free abnormal type;
substituting the energy data samples corresponding to the data-free abnormal type and the energy data samples within the preset range into a chi-square formula to obtain a third chi-square value;
and taking the third chi-square value as the deviation degree of the energy data sample.
12. The method according to claim 11, wherein the determining whether the energy data corresponding to the preset abnormality type is abnormal energy data according to the comparison result includes:
if the deviation degree of the energy data sample is smaller than the corresponding standard value, judging that the energy data corresponding to the data-free abnormal type is not abnormal energy data;
if the deviation degree of the energy data sample is not smaller than the corresponding standard value, the energy data corresponding to the data-free abnormal type is judged to be data-free abnormal energy data, and alarm information of data-free and abnormal monitoring equipment is sent.
13. The method according to claim 2, wherein the anomaly type includes data exceeding a preset range, and the calculating the deviation degree of the energy data samples corresponding to the preset anomaly type includes:
selecting energy data samples in a preset range of energy data samples corresponding to the abnormal types of the data exceeding the preset range;
substituting the energy data sample corresponding to the abnormal type with the data exceeding the preset range and the energy data sample within the preset range into a chi-square formula to obtain a fourth chi-square value;
and taking the fourth chi-square value as the deviation degree of the energy data sample.
14. The method according to claim 13, wherein the determining whether the energy data corresponding to the preset abnormality type is abnormal energy data according to the comparison result includes:
if the deviation degree of the energy data sample is smaller than the corresponding standard value, judging that the energy data corresponding to the abnormal type with the data exceeding the preset range is not abnormal energy data;
if the deviation degree of the energy data sample is not smaller than the corresponding standard value, the energy data corresponding to the abnormal type of the data exceeding the preset range is judged to be the abnormal energy data exceeding the preset range, and alarm information that the data exceed the preset range and the monitoring equipment is abnormally restarted is sent.
15. The method for detecting abnormality in energy source data according to claim 14, characterized by further comprising:
and if the occurrence frequency of the abnormal energy data exceeding the preset range in the preset time period exceeds a preset third frequency threshold value, sending alarm information that the equipment is in overload operation or new equipment is merged into.
16. The method according to claim 1, wherein the calculating the deviation degree of the energy data samples corresponding to the preset abnormality type includes:
and substituting the energy data samples corresponding to the preset abnormal types into a binomial test formula to obtain the deviation of the samples.
17. An energy data abnormality detection device characterized by comprising:
the acquisition module is used for acquiring a preset number of energy data samples;
the judging module is used for judging whether each energy data sample belongs to a preset abnormal type;
the calculation module is used for calculating the deviation degree of the energy data sample corresponding to the preset abnormal type when the energy data sample belongs to the preset abnormal type;
the comparison module is used for comparing the deviation degree with a corresponding standard value;
and the determining module is used for determining whether the energy data corresponding to the preset abnormal type is abnormal energy data according to the comparison result.
18. An energy system, comprising:
the energy data abnormality detection apparatus according to claim 17.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210147724.3A CN114580861A (en) | 2022-02-17 | 2022-02-17 | Energy data anomaly detection method and device and energy system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210147724.3A CN114580861A (en) | 2022-02-17 | 2022-02-17 | Energy data anomaly detection method and device and energy system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114580861A true CN114580861A (en) | 2022-06-03 |
Family
ID=81770692
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210147724.3A Pending CN114580861A (en) | 2022-02-17 | 2022-02-17 | Energy data anomaly detection method and device and energy system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114580861A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115223344A (en) * | 2022-07-18 | 2022-10-21 | 浙江正泰仪器仪表有限责任公司 | Monitoring alarm method and device for meter equipment, electronic equipment and storage medium |
| CN117648232A (en) * | 2023-12-11 | 2024-03-05 | 武汉天宝莱信息技术有限公司 | Application program data monitoring method, device and storage medium |
-
2022
- 2022-02-17 CN CN202210147724.3A patent/CN114580861A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115223344A (en) * | 2022-07-18 | 2022-10-21 | 浙江正泰仪器仪表有限责任公司 | Monitoring alarm method and device for meter equipment, electronic equipment and storage medium |
| CN117648232A (en) * | 2023-12-11 | 2024-03-05 | 武汉天宝莱信息技术有限公司 | Application program data monitoring method, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114580861A (en) | Energy data anomaly detection method and device and energy system | |
| WO2020052147A1 (en) | Monitoring device fault detection method and apparatus | |
| CN109186813B (en) | Temperature sensor self-checking device and method | |
| US10852357B2 (en) | System and method for UPS battery monitoring and data analysis | |
| US7902972B2 (en) | Supervising arrangement | |
| BRPI1100290A2 (en) | Method for detecting behavior in electrical substation equipment | |
| CN115982602B (en) | Photovoltaic transformer electrical fault detection method | |
| CN105041631A (en) | Method and system for detecting vibration signal of driving shaft of gas compressor | |
| CN112580961B (en) | Power grid information system based operation risk early warning method and device | |
| CN112286771A (en) | Alarm method for monitoring global resources | |
| CN112905371B (en) | Software change checking method and device based on heterogeneous multi-source data anomaly detection | |
| CN111930603A (en) | Server performance detection method, device, system and medium | |
| CN109725220B (en) | Detection method, system and device for transformer oil cooling loop | |
| CN106652393B (en) | False alarm determination method and device | |
| RU2687848C1 (en) | Method and system of vibration monitoring of industrial safety of dynamic equipment of hazardous production facilities | |
| CN103999316A (en) | Method for generating a signal indicating an oscillation in an electrical energy supply network | |
| CN116663747B (en) | Intelligent early warning method and system based on data center infrastructure | |
| US20170302506A1 (en) | Methods and apparatus for fault detection | |
| CN115877313A (en) | Power metering detection system | |
| CN115471968A (en) | Cable burglar alarm | |
| KR102608381B1 (en) | Instrumentation control system capable of self-diagnosis and the control method thereof | |
| KR100319934B1 (en) | Remote error detection system for elevator and control methof thereof | |
| CN116596336B (en) | State evaluation method and device of electronic equipment, electronic equipment and storage medium | |
| CN113469453B (en) | Elevator evaluation method and elevator evaluation device based on information physical system | |
| CN114710202B (en) | Online monitoring system based on optical time domain reflection and corresponding monitoring method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |