CN107527123B - Disturbance event prediction method and device based on distributed association rule - Google Patents
Disturbance event prediction method and device based on distributed association rule Download PDFInfo
- Publication number
- CN107527123B CN107527123B CN201710923345.8A CN201710923345A CN107527123B CN 107527123 B CN107527123 B CN 107527123B CN 201710923345 A CN201710923345 A CN 201710923345A CN 107527123 B CN107527123 B CN 107527123B
- Authority
- CN
- China
- Prior art keywords
- disturbance event
- electrical information
- disturbance
- association rule
- data center
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06F16/23—Updating
-
- 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
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The invention provides a disturbance event prediction method and a device based on a distributed association rule, which distribute the calculation amount mined by the association rule to each local data center through a distributed method, improve the overall calculation efficiency, effectively utilize the communication networks of the local data center and the global data center, realize the search of the global association rule, and solve the technical problems that the existing method has low calculation efficiency and cannot solve the complex network communication in a centralized data processing structure.
Description
Technical Field
The invention relates to the field of power quality monitoring, in particular to a disturbance event prediction method and device based on a distributed association rule.
Background
In recent years, the problem of power quality has been a common concern of grid companies and power consumers. With the gradual construction and popularization of a Power Quality Measurement System (PQMS) in various provinces, how to effectively utilize a data analysis technology to extract information from data and establish a causal relationship of events so as to achieve the purpose of decision support is one of the development trends of value attention and value in power quality research. On one hand, due to the large-area construction of the distributed power supply, the operation decision of the converter with the power quality control capability needs to accurately predict the power quality level. On the other hand, reliable prediction of the variation trend of the power quality is one of the key measures for ensuring the safe and economic operation of the power grid.
At present, the deepening application of the power quality monitoring data is mostly focused on the aspects of disturbance type identification, fault source positioning, load on-line monitoring, power quality comprehensive evaluation and the like, and related researches on power quality prediction are few. The existing method combines power disturbance historical data and standard power grid operation indexes, effectively evaluates the power quality state of the power transmission and distribution network through a mathematical statistics analysis method, but does not consider the power quality change trend. The existing related prediction method only considers the influence of uncertain output of a wind power system on power quality fluctuation, and the power quality level of the system is difficult to be comprehensively measured.
The disturbance events are caused by a plurality of reasons, including thunderstorm weather factors and load factors such as nonlinearity, impact and volatility, and the disturbance event prediction is difficult to realize from the viewpoint of mechanical analysis. With the large-range coverage of the power quality monitoring device, a large number of power disturbance event records are collected to a monitoring system platform. On one hand, the traditional centralized big data analysis processing mode enables the application program and the resources to be operated on the same centralized computer, so that the system efficiency is not high. On the other hand, centralized connectivity can become a big problem for centralized networks. It is an urgent need for those skilled in the art to provide a solution that has high operation efficiency and can solve the technical problem of complex network communication in a centralized data processing structure.
Disclosure of Invention
The invention provides a disturbance event prediction method and device based on a distributed association rule, and solves the technical problems that the existing method is low in operation efficiency and cannot solve the problem of complex network communication in a centralized data processing structure.
The invention provides a disturbance event prediction method based on a distributed association rule, which comprises the following steps:
s2, acquiring a non-repetitive disturbance event, discretizing the non-repetitive disturbance event to obtain disturbance event electrical information and disturbance event non-electrical information, and sending the disturbance event electrical information and the disturbance event non-electrical information to a local data center, wherein the local data center respectively counts the occurrence frequency of the disturbance event electrical information and the disturbance event non-electrical information;
s3, acquiring all disturbance event electrical information and disturbance event non-electrical information counted by a local data center, acquiring association rules of the disturbance event electrical information and the disturbance event non-electrical information according to an association rule mining algorithm, and storing the association rules to a local association rule base;
s4, sending association rules of the disturbance event electrical information and the disturbance event non-electrical information in each local association rule base to the global data center through communication connection between the local data center and the global data center, obtaining global association rules of the disturbance event electrical information and the disturbance event non-electrical information, storing the global association rules to the global association rule base, and meanwhile updating the local association rule base and the global association rule base by adopting a frequent pattern tree algorithm;
s5, acquiring an association rule of disturbance event electrical information and disturbance event non-electrical information which are most matched with a target area or a target time period in the global association rule base through a similarity matching method, acquiring corresponding support degree and confidence degree, calculating a probability value of occurrence of the most matched disturbance event according to the support degree and the confidence degree, and if the probability value is higher than a preset threshold value, giving an early warning.
Preferably, step S2 is preceded by:
and S1, fusing the repeatedly recorded disturbance events by using a neighbor sorting method according to the time characteristic information, the space characteristic information and the disturbance energy propagation characteristics of the occurrence of the disturbance events to obtain non-repeated disturbance events, and determining a disturbance event source.
Preferably, step S2 specifically includes:
obtaining a non-repetitive disturbance event, and discretizing the non-repetitive disturbance event by using a symbol aggregation approximation method to obtain disturbance event electrical information and disturbance event non-electrical information;
and sending the disturbance event electrical information and the disturbance event non-electrical information to a local data center, and respectively counting the occurrence times of the disturbance event electrical data information and the disturbance event non-electrical data information by the local data center.
Preferably, the disturbance event electrical information specifically includes: monitoring node voltage level, disturbance event type, disturbance event duration and disturbance amplitude characteristics, wherein the disturbance event type comprises: the harmonic voltage content rate is out of limit, the total harmonic voltage distortion rate is out of limit, the frequency deviation is out of limit, the voltage deviation is out of limit, the short-time flicker is out of limit, the long-time flicker is out of limit, and the voltage unbalance degree is out of limit.
Preferably, the disturbance event non-electrical information specifically includes: monitoring node position, disturbance event occurrence date, disturbance event occurrence time and weather type.
The invention provides a disturbance event prediction device based on a distributed association rule, which comprises:
the device comprises a discretization unit, a local data center and a data processing unit, wherein the discretization unit is used for acquiring a non-repeated disturbance event, discretizing the non-repeated disturbance event to obtain disturbance event electrical information and disturbance event non-electrical information, and sending the disturbance event electrical information and the disturbance event non-electrical information to the local data center, and the local data center respectively counts the occurrence frequency of the disturbance event electrical information and the disturbance event non-electrical information;
the association rule mining unit is used for acquiring all disturbance event electrical information and disturbance event non-electrical information counted by the local data center, acquiring an association rule of the disturbance event electrical information and the disturbance event non-electrical information according to an association rule mining algorithm, and storing the association rule to a local association rule base;
the rule base updating unit is used for sending association rules of the disturbance event electrical information and the disturbance event non-electrical information in each local association rule base to the global data center through communication connection between the local data center and the global data center to obtain global association rules of the disturbance event electrical information and the disturbance event non-electrical information, storing the global association rules to the global association rule base, and meanwhile updating the local association rule base and the global association rule base by adopting a frequent pattern tree algorithm;
and the early warning unit is used for acquiring an association rule of disturbance event electrical information and disturbance event non-electrical information which are most matched with the target area or the target time period in the global association rule base through a similarity matching method, acquiring corresponding support degree and confidence degree, calculating a probability value of occurrence of the most matched disturbance event according to the support degree and the confidence degree, and giving early warning if the probability value is higher than a preset threshold value.
Preferably, the method further comprises the following steps:
and the data cleaning unit is used for fusing the repeatedly recorded disturbance events by utilizing a neighbor sorting method according to the time characteristic information, the space characteristic information and the disturbance energy propagation characteristics of the occurrence of the disturbance events to obtain non-repeated disturbance events and determine a disturbance event source.
Preferably, the discrete units specifically include:
the discrete subunit is used for acquiring the non-repetitive disturbance events, and discretizing the non-repetitive disturbance events by utilizing a symbol aggregation approximation method to obtain disturbance event electrical information and disturbance event non-electrical information;
and the data sending subunit is used for sending the disturbance event electrical information and the disturbance event non-electrical information to the local data center, and the local data center respectively counts the occurrence frequency of the disturbance event electrical information and the disturbance event non-electrical information.
Preferably, the disturbance event electrical information specifically includes: monitoring node voltage level, disturbance event type, disturbance event duration and disturbance amplitude characteristics, wherein the disturbance event type comprises: the harmonic voltage content rate is out of limit, the total harmonic voltage distortion rate is out of limit, the frequency deviation is out of limit, the voltage deviation is out of limit, the short-time flicker is out of limit, the long-time flicker is out of limit, and the voltage unbalance degree is out of limit.
Preferably, the disturbance event non-electrical information specifically includes: monitoring node position, disturbance event occurrence date, disturbance event occurrence time and weather type.
According to the technical scheme, the invention has the following advantages:
the invention provides a disturbance event prediction method based on a distributed association rule, which comprises the following steps: s2, acquiring a non-repetitive disturbance event, discretizing the non-repetitive disturbance event to obtain disturbance event electrical information and disturbance event non-electrical information, and sending the disturbance event electrical information and the disturbance event non-electrical information to a local data center, wherein the local data center respectively counts the occurrence frequency of the disturbance event electrical information and the disturbance event non-electrical information; s3, acquiring all disturbance event electrical information and disturbance event non-electrical information counted by a local data center, acquiring association rules of the disturbance event electrical information and the disturbance event non-electrical information according to an association rule mining algorithm, and storing the association rules to a local association rule base; s4, sending association rules of the disturbance event electrical information and the disturbance event non-electrical information in each local association rule base to the global data center through communication connection between the local data center and the global data center, obtaining global association rules of the disturbance event electrical information and the disturbance event non-electrical information, storing the global association rules to the global association rule base, and meanwhile updating the local association rule base and the global association rule base by adopting a frequent pattern tree algorithm; s5, acquiring an association rule of disturbance event electrical information and disturbance event non-electrical information which are most matched with a target area or a target time period in the global association rule base through a similarity matching method, acquiring corresponding support degree and confidence degree, calculating a probability value of occurrence of the most matched disturbance event according to the support degree and the confidence degree, and if the probability value is higher than a preset threshold value, giving an early warning.
In the invention, the non-repeated disturbance event is dispersed to obtain the electric information and the non-electric information of the disturbance event, the electric information and the non-electric information of the disturbance event are subjected to association rule mining in a local data center according to an association rule mining algorithm, the mined association rule is stored in a local association rule base and is sent to a global data center, the global data center stores and analyzes the association rule sent by each local data center to obtain the global association rule, finally, in a prediction stage, the association rule which is most matched with a target area or a target time period is searched in the global association rule base, the corresponding support degree and confidence coefficient are obtained, the probability of disturbance occurrence is calculated so as to carry out early warning, the calculation amount mined by the association rule is distributed to each local data center by a distributed method, the whole calculation efficiency is improved, and meanwhile, the communication network of the local data center and the global data center is effectively utilized, the method realizes the search of the global association rule and solves the technical problems that the existing method has low operation efficiency and cannot solve the complex network communication in a centralized data processing structure.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a schematic flowchart of an embodiment of a disturbance event prediction method based on a distributed association rule according to the present invention;
FIG. 2 is a schematic flowchart of a disturbance event prediction method based on a distributed association rule according to another embodiment of the present invention;
FIG. 3 is a schematic structural diagram of an embodiment of a disturbance event prediction apparatus based on a distributed association rule according to the present invention;
fig. 4 is a schematic structural diagram of another embodiment of a disturbance event prediction apparatus based on a distributed association rule according to the present invention.
Detailed Description
The embodiment of the invention provides a disturbance event prediction method and device based on a distributed association rule, and solves the technical problems that the existing method is low in operation efficiency and cannot solve the problem of complex network communication in a centralized data processing structure.
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, an embodiment of the present invention provides an embodiment of a disturbance event prediction method based on a distributed association rule, including:
101. acquiring a non-repetitive disturbance event, discretizing the non-repetitive disturbance event to obtain disturbance event electrical information and disturbance event non-electrical information, and sending the disturbance event electrical information and the disturbance event non-electrical information to a local data center, wherein the local data center respectively counts the occurrence frequency of the disturbance event electrical information and the disturbance event non-electrical information;
the method includes the steps of acquiring a non-repetitive disturbance event, discretizing the non-repetitive disturbance event into disturbance event electrical information and disturbance event non-electrical information, respectively sending the disturbance event electrical information and the disturbance event non-electrical information to a local data center, and counting the occurrence frequency of the disturbance event electrical information and the disturbance event non-electrical information by the local data center.
102. Acquiring all disturbance event electrical information and disturbance event non-electrical information counted by a local data center, acquiring association rules of the disturbance event electrical information and the disturbance event non-electrical information according to an association rule mining algorithm, and storing the association rules to a local association rule base;
it should be noted that all the disturbance event electrical information and non-electrical information counted by the local data center are obtained, the disturbance event electrical information and the disturbance event non-electrical information are subjected to association rule mining through an association rule mining algorithm, an association rule of the disturbance event counted by the local data center is obtained, and the association rule is stored in the local association rule base.
103. Sending association rules of the disturbance event electrical information and the disturbance event non-electrical information in each local association rule base to the global data center through communication connection between the local data center and the global data center to obtain global association rules of the disturbance event electrical information and the disturbance event non-electrical information, storing the global association rules to the global association rule base, and updating the local association rule base and the global association rule base by adopting a frequent pattern tree algorithm;
it should be noted that, by using the communication connection between the local data center and the global data center, the association rule of the disturbance event electrical information and the disturbance event non-electrical information in each local association rule base is sent to the global data center, and the global data center performs statistics and analysis to obtain the global association rule, and stores the global association rule in the global association rule base. Meanwhile, the local association rule base and the global association rule base are updated through a frequent pattern tree algorithm by utilizing the communication connection between the local data center and the global data center.
104. And acquiring an association rule of disturbance event electrical information and disturbance event non-electrical information which are most matched with a target area or a target time period in a global association rule base through a similarity matching method, acquiring corresponding support degree and confidence degree, calculating a probability value of occurrence of the most matched disturbance event according to the support degree and the confidence degree, and performing early warning if the probability value is higher than a preset threshold value.
It should be noted that, when a disturbance event prediction needs to be performed on a target area or a target time period, an association rule of disturbance event electrical information and disturbance event non-electrical information which are most matched with the target area or the target time period is searched in the global association rule base by a similarity matching method, a support degree and a confidence degree corresponding to the association rule are obtained, a probability value of the disturbance event occurring in the target area or the target time period is calculated according to the support degree and the confidence degree, and if the probability value is higher than a preset threshold value, an early warning is performed.
In the embodiment of the invention, the electrical information and the non-electrical information of the disturbance event are obtained through dispersing the non-repeated disturbance event, the association rule mining is carried out on the electrical information and the non-electrical information of the disturbance event in the local data center according to an association rule mining algorithm, the mined association rule is stored in a local association rule base and is sent to a global data center, the global data center stores and analyzes the association rule sent by each local data center to obtain the global association rule, at the final prediction stage, the association rule which is most matched with a target area or a target time period is searched in the global association rule base, the corresponding support degree and confidence degree are obtained, the probability of disturbance occurrence is calculated to carry out early warning, the calculation amount mined by the association rule is distributed to each local data center through a distributed method, the whole calculation efficiency is improved, and meanwhile, the communication network of the local data center and the global data center is effectively utilized, the method realizes the search of the global association rule and solves the technical problems that the existing method has low operation efficiency and cannot solve the complex network communication in a centralized data processing structure.
The foregoing is a description of an embodiment of a disturbance event prediction method based on a distributed association rule provided by the present invention, and another embodiment of a disturbance event prediction method based on a distributed association rule provided by the present invention is described below.
Referring to fig. 2, another embodiment of the disturbance event prediction method based on the distributed association rule according to the present invention includes:
201. according to the time characteristic information, the space characteristic information and the disturbance energy propagation characteristics of the occurrence of the disturbance events, fusing the repeatedly recorded disturbance events by using a neighbor sorting method to obtain non-repeated disturbance events, and determining a disturbance event source;
it should be noted that, according to the time characteristic information, the space characteristic information and the disturbance energy propagation characteristics of the occurrence amount of the disturbance event, the disturbance events recorded repeatedly are fused into one disturbance event by using a neighbor sorting method to obtain a non-repeated disturbance event, and a disturbance event source is determined according to the information.
2021. Obtaining a non-repetitive disturbance event, and discretizing the non-repetitive disturbance event by using a symbol aggregation approximation method to obtain disturbance event electrical information and disturbance event non-electrical information;
the disturbance event electrical information specifically includes: monitoring node voltage level, disturbance event type, disturbance event duration and disturbance amplitude characteristics, wherein the disturbance event type comprises: the harmonic voltage content rate exceeds the limit, the total harmonic voltage distortion rate exceeds the limit, the frequency deviation exceeds the limit, the voltage deviation exceeds the limit, the short-time flicker exceeds the limit, the long-time flicker exceeds the limit and the voltage unbalance degree exceeds the limit;
the disturbance event non-electrical information specifically includes: monitoring node position, disturbance event occurrence date, disturbance event occurrence time and weather type.
It should be noted that the non-repetitive disturbance event is acquired, discretization processing is performed on the non-repetitive disturbance event through a symbol aggregation approximation method, and the non-repetitive disturbance event is discretized into disturbance event electrical information and disturbance event non-electrical information.
2022. Sending the disturbance event electrical information and the disturbance event non-electrical information to a local data center, and respectively counting the occurrence frequency of the disturbance event electrical data information and the disturbance event non-electrical data information by the local data center;
it should be noted that the disturbance event electrical information and the disturbance event non-electrical information are respectively sent to the local data center, and the local data center counts the occurrence frequency of the disturbance event electrical information and the disturbance event non-electrical information.
203. Acquiring all disturbance event electrical information and disturbance event non-electrical information counted by a local data center, acquiring association rules of the disturbance event electrical information and the disturbance event non-electrical information according to an association rule mining algorithm, and storing the association rules to a local association rule base;
it should be noted that all the disturbance event electrical information and non-electrical information counted by the local data center are obtained, the disturbance event electrical information and the disturbance event non-electrical information are subjected to association rule mining through an association rule mining algorithm, an association rule of the disturbance event counted by the local data center is obtained, and the association rule is stored in the local association rule base.
204. Sending association rules of the disturbance event electrical information and the disturbance event non-electrical information in each local association rule base to the global data center through communication connection between the local data center and the global data center to obtain global association rules of the disturbance event electrical information and the disturbance event non-electrical information, storing the global association rules to the global association rule base, and updating the local association rule base and the global association rule base by adopting a frequent pattern tree algorithm;
it should be noted that, by using the communication connection between the local data center and the global data center, the association rule of the disturbance event electrical information and the disturbance event non-electrical information in each local association rule base is sent to the global data center, and the global data center performs statistics and analysis to obtain the global association rule, and stores the global association rule in the global association rule base. Meanwhile, the local association rule base and the global association rule base are updated through a frequent pattern tree algorithm by utilizing the communication connection between the local data center and the global data center.
205. Acquiring an association rule of disturbance event electrical information and disturbance event non-electrical information which are most matched with a target area or a target time period in a global association rule base through a similarity matching method, acquiring corresponding support degree and confidence degree, calculating a probability value of occurrence of the most matched disturbance event according to the support degree and the confidence degree, and if the probability value is higher than a preset threshold value, performing early warning;
it should be noted that, when a disturbance event prediction needs to be performed on a target area or a target time period, an association rule of disturbance event electrical information and disturbance event non-electrical information which are most matched with the target area or the target time period is searched in the global association rule base by a similarity matching method, a support degree and a confidence degree corresponding to the association rule are obtained, a probability value of the disturbance event occurring in the target area or the target time period is calculated according to the support degree and the confidence degree, and if the probability value is higher than a preset threshold value, an early warning is performed.
In the above, another embodiment of the disturbance event prediction method based on the distributed association rule provided by the present invention is described, and an embodiment of the disturbance event prediction apparatus based on the distributed association rule provided by the present invention is described below.
Referring to fig. 3, an embodiment of a disturbance event prediction apparatus based on a distributed association rule according to the present invention includes:
the discrete unit 301 is configured to acquire a non-repetitive disturbance event, perform discretization on the non-repetitive disturbance event to obtain disturbance event electrical information and disturbance event non-electrical information, and send the disturbance event electrical information and the disturbance event non-electrical information to a local data center, where the local data center respectively counts the occurrence frequency of the disturbance event electrical information and the disturbance event non-electrical information;
the association rule mining unit 302 is configured to obtain all disturbance event electrical information and disturbance event non-electrical information counted by the local data center, obtain an association rule between the disturbance event electrical information and the disturbance event non-electrical information according to an association rule mining algorithm, and store the association rule in a local association rule base;
the rule base updating unit 303 is configured to send association rules of the disturbance event electrical information and the disturbance event non-electrical information in each local association rule base to the global data center through communication connection between the local data center and the global data center, obtain global association rules of the disturbance event electrical information and the disturbance event non-electrical information, store the global association rules to the global association rule base, and update the local association rule base and the global association rule base by using a frequent pattern tree algorithm;
the early warning unit 304 is configured to obtain, in the global association rule base, an association rule of disturbance event electrical information and disturbance event non-electrical information that are most matched with the target area or the target time period by a similarity matching method, obtain corresponding support degree and confidence level, calculate a probability value of occurrence of the most matched disturbance event according to the support degree and the confidence level, and perform early warning if the probability value is higher than a preset threshold value.
In the above, an embodiment of the disturbance event prediction device based on the distributed association rule according to the present invention is described, and another embodiment of the disturbance event prediction device based on the distributed association rule according to the present invention is described below.
Referring to fig. 4, another embodiment of a disturbance event prediction apparatus based on a distributed association rule according to the present invention includes:
the data cleaning unit 401 is configured to fuse repeatedly recorded disturbance events by using a neighbor sorting method according to time characteristic information, spatial characteristic information and disturbance energy propagation characteristics of occurrence of the disturbance events to obtain non-repeated disturbance events, and determine a disturbance event source;
the discrete subunit 4021 is configured to acquire a non-repetitive disturbance event, and discretize the non-repetitive disturbance event by using a symbol aggregation approximation method to obtain disturbance event electrical information and disturbance event non-electrical information;
the data sending subunit 4022 is configured to send the disturbance event electrical information and the disturbance event non-electrical information to the local data center, where the local data center counts the occurrence frequency of the disturbance event electrical information and the disturbance event non-electrical information, respectively.
The association rule mining unit 403 is configured to obtain all disturbance event electrical information and disturbance event non-electrical information counted by the local data center, obtain an association rule between the disturbance event electrical information and the disturbance event non-electrical information according to an association rule mining algorithm, and store the association rule in a local association rule base;
a rule base updating unit 404, configured to send association rules of the disturbance event electrical information and the disturbance event non-electrical information in each local association rule base to the global data center through communication connection between the local data center and the global data center, obtain global association rules of the disturbance event electrical information and the disturbance event non-electrical information, store the global association rules to the global association rule base, and update the local association rule base and the global association rule base by using a frequent pattern tree algorithm;
the early warning unit 405 is configured to obtain, in the global association rule base, an association rule of disturbance event electrical information and disturbance event non-electrical information that are most matched with the target area or the target time period by a similarity matching method, obtain corresponding support degree and confidence level, calculate a probability value of occurrence of the most matched disturbance event according to the support degree and the confidence level, and perform early warning if the probability value is higher than a preset threshold value.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (8)
1. A disturbance event prediction method based on a distributed association rule is characterized by comprising the following steps:
s1, fusing repeatedly recorded disturbance events by using a neighbor sorting method according to time characteristic information, space characteristic information and disturbance energy propagation characteristics of the occurrence of the disturbance events to obtain non-repeated disturbance events, and determining a disturbance event source;
s2, acquiring a non-repetitive disturbance event, discretizing the non-repetitive disturbance event to obtain disturbance event electrical information and disturbance event non-electrical information, and sending the disturbance event electrical information and the disturbance event non-electrical information to a local data center, wherein the local data center respectively counts the occurrence frequency of the disturbance event electrical information and the disturbance event non-electrical information;
s3, acquiring all disturbance event electrical information and disturbance event non-electrical information counted by a local data center, acquiring association rules of the disturbance event electrical information and the disturbance event non-electrical information according to an association rule mining algorithm, and storing the association rules to a local association rule base;
s4, sending association rules of the disturbance event electrical information and the disturbance event non-electrical information in each local association rule base to the global data center through communication connection between the local data center and the global data center, obtaining global association rules of the disturbance event electrical information and the disturbance event non-electrical information, storing the global association rules to the global association rule base, and meanwhile updating the local association rule base and the global association rule base by adopting a frequent pattern tree algorithm;
s5, acquiring an association rule of disturbance event electrical information and disturbance event non-electrical information which are most matched with a target area or a target time period in the global association rule base through a similarity matching method, acquiring corresponding support degree and confidence degree, calculating a probability value of occurrence of the most matched disturbance event according to the support degree and the confidence degree, and if the probability value is higher than a preset threshold value, giving an early warning.
2. The method for predicting the disturbance event based on the distributed association rule according to claim 1, wherein the step S2 specifically includes:
obtaining a non-repetitive disturbance event, and discretizing the non-repetitive disturbance event by using a symbol aggregation approximation method to obtain disturbance event electrical information and disturbance event non-electrical information;
and sending the disturbance event electrical information and the disturbance event non-electrical information to a local data center, and respectively counting the occurrence times of the disturbance event electrical information and the disturbance event non-electrical information by the local data center.
3. The disturbance event prediction method based on the distributed association rule according to claim 2, wherein the disturbance event electrical information specifically includes: monitoring node voltage level, disturbance event type, disturbance event duration and disturbance amplitude characteristics, wherein the disturbance event type comprises: the harmonic voltage content rate is out of limit, the total harmonic voltage distortion rate is out of limit, the frequency deviation is out of limit, the voltage deviation is out of limit, the short-time flicker is out of limit, the long-time flicker is out of limit, and the voltage unbalance degree is out of limit.
4. The disturbance event prediction method based on the distributed association rule according to claim 3, wherein the disturbance event non-electrical information specifically comprises: monitoring node position, disturbance event occurrence date, disturbance event occurrence time and weather type.
5. A disturbance event prediction device based on a distributed association rule is characterized by comprising:
the data cleaning unit is used for fusing repeatedly recorded disturbance events by utilizing a neighbor sorting method according to time characteristic information, space characteristic information and disturbance energy propagation characteristics of the occurrence of the disturbance events to obtain non-repeated disturbance events and determine a disturbance event source;
the device comprises a discretization unit, a local data center and a data processing unit, wherein the discretization unit is used for acquiring a non-repeated disturbance event, discretizing the non-repeated disturbance event to obtain disturbance event electrical information and disturbance event non-electrical information, and sending the disturbance event electrical information and the disturbance event non-electrical information to the local data center, and the local data center respectively counts the occurrence frequency of the disturbance event electrical information and the disturbance event non-electrical information;
the association rule mining unit is used for acquiring all disturbance event electrical information and disturbance event non-electrical information counted by the local data center, acquiring an association rule of the disturbance event electrical information and the disturbance event non-electrical information according to an association rule mining algorithm, and storing the association rule to a local association rule base;
the rule base updating unit is used for sending association rules of the disturbance event electrical information and the disturbance event non-electrical information in each local association rule base to the global data center through communication connection between the local data center and the global data center to obtain global association rules of the disturbance event electrical information and the disturbance event non-electrical information, storing the global association rules to the global association rule base, and meanwhile updating the local association rule base and the global association rule base by adopting a frequent pattern tree algorithm;
and the early warning unit is used for acquiring an association rule of disturbance event electrical information and disturbance event non-electrical information which are most matched with the target area or the target time period in the global association rule base through a similarity matching method, acquiring corresponding support degree and confidence degree, calculating a probability value of occurrence of the most matched disturbance event according to the support degree and the confidence degree, and giving early warning if the probability value is higher than a preset threshold value.
6. The disturbance event prediction device based on the distributed association rule as claimed in claim 5, wherein the discrete unit specifically comprises:
the discrete subunit is used for acquiring the non-repetitive disturbance events, and discretizing the non-repetitive disturbance events by utilizing a symbol aggregation approximation method to obtain disturbance event electrical information and disturbance event non-electrical information;
and the data sending subunit is used for sending the disturbance event electrical information and the disturbance event non-electrical information to the local data center, and the local data center respectively counts the disturbance event electrical information and the disturbance event non-electrical information.
7. The distributed association rule based disturbance event prediction device according to claim 6, wherein the disturbance event electrical information specifically comprises: monitoring node voltage level, disturbance event type, disturbance event duration and disturbance amplitude characteristics, wherein the disturbance event type comprises: the harmonic voltage content rate is out of limit, the total harmonic voltage distortion rate is out of limit, the frequency deviation is out of limit, the voltage deviation is out of limit, the short-time flicker is out of limit, the long-time flicker is out of limit, and the voltage unbalance degree is out of limit.
8. The distributed association rule based disturbance event prediction device according to claim 7, wherein the disturbance event non-electrical information specifically comprises: monitoring node position, disturbance event occurrence date, disturbance event occurrence time and weather type.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710923345.8A CN107527123B (en) | 2017-09-30 | 2017-09-30 | Disturbance event prediction method and device based on distributed association rule |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710923345.8A CN107527123B (en) | 2017-09-30 | 2017-09-30 | Disturbance event prediction method and device based on distributed association rule |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107527123A CN107527123A (en) | 2017-12-29 |
| CN107527123B true CN107527123B (en) | 2020-09-01 |
Family
ID=60683978
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710923345.8A Active CN107527123B (en) | 2017-09-30 | 2017-09-30 | Disturbance event prediction method and device based on distributed association rule |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107527123B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107918670A (en) * | 2017-11-29 | 2018-04-17 | 国网电力信息通信有限公司 | A kind of alert processing method applied to power communication system |
| CN108647626B (en) * | 2018-05-04 | 2021-11-02 | 广东电网有限责任公司广州供电局 | Method and device for determining incidence relation between power quality event and event cause |
| CN109410109B (en) * | 2018-10-19 | 2020-10-16 | 智器云南京信息科技有限公司 | Big data based accompanying event analysis method and system |
| CN109521305A (en) * | 2018-12-29 | 2019-03-26 | 广东电网有限责任公司 | A kind of electrical energy power quality disturbance incident visualization method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103647276A (en) * | 2013-12-10 | 2014-03-19 | 国家电网公司 | Electric energy quality early warning system and method thereof |
| CN103872782A (en) * | 2014-03-31 | 2014-06-18 | 国家电网公司 | Electric energy quality data comprehensive service system |
| EP2988140A2 (en) * | 2014-08-19 | 2016-02-24 | Eltel Networks Oy | A method and apparatus for locating a disturbance in an electrical grid |
| CN105608519A (en) * | 2015-11-09 | 2016-05-25 | 国家电网公司 | Prediction method for operation state of electrical-network communication equipment |
-
2017
- 2017-09-30 CN CN201710923345.8A patent/CN107527123B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103647276A (en) * | 2013-12-10 | 2014-03-19 | 国家电网公司 | Electric energy quality early warning system and method thereof |
| CN103872782A (en) * | 2014-03-31 | 2014-06-18 | 国家电网公司 | Electric energy quality data comprehensive service system |
| EP2988140A2 (en) * | 2014-08-19 | 2016-02-24 | Eltel Networks Oy | A method and apparatus for locating a disturbance in an electrical grid |
| CN105608519A (en) * | 2015-11-09 | 2016-05-25 | 国家电网公司 | Prediction method for operation state of electrical-network communication equipment |
Non-Patent Citations (1)
| Title |
|---|
| 分布式关联规则挖掘研究;王治和 等;《南京师大学报（自然科学版）》;20101231;第33卷(第4期);第114-118页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107527123A (en) | 2017-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107527123B (en) | Disturbance event prediction method and device based on distributed association rule | |
| US10041968B2 (en) | Power line management system | |
| CN102947801B (en) | malicious attack detection and analysis | |
| Bialek et al. | Benchmarking and validation of cascading failure analysis tools | |
| He et al. | Online dynamic security assessment with missing pmu measurements: A data mining approach | |
| US10164431B2 (en) | Outage management and prediction for a power grid system | |
| CN106446016A (en) | Parallel association rule mining-based method for predicting running reliability of power distribution network | |
| CN104951990B (en) | Power grid data processing method and equipment | |
| US10923915B2 (en) | System and method for congestion forecasting in electrical networks | |
| CA2846288A1 (en) | Methods and apparatus for determining conditions of power lines | |
| CN110826228B (en) | Regional power grid operation quality limit evaluation method | |
| Bhuiyan et al. | Review of static risk‐based security assessment in power system | |
| Taheri et al. | Distribution systems resilience enhancement via pre‐and post‐event actions | |
| Bao et al. | Resilience-oriented transmission line fragility modeling and real-time risk assessment of thunderstorms | |
| US20230118175A1 (en) | Event analysis in an electric power system | |
| CN112348699A (en) | Power supply system power equipment life cycle management method and system | |
| CN103198139A (en) | Energy consumption analyzing method of user electricity data | |
| Dehghani et al. | An overview of the assessment metrics of the concept of resilience in electrical grids | |
| Hong et al. | Data integrity attacks against outage management systems | |
| Dehbozorgi et al. | Decision tree‐based classifiers for root‐cause detection of equipment‐related distribution power system outages | |
| Gonzalez et al. | Characterisation of router and link failure processes in UNINETT’s IP backbone network | |
| CN117424224A (en) | Power failure plan balance optimization method, device, equipment and storage medium | |
| CN108876138A (en) | A kind of supervisory control of substation information leakage prison detection method based on big data analysis | |
| CN207586323U (en) | A kind of unit negative damping online recognition system | |
| WO2024003367A1 (en) | Method and device for forecasting upcoming faults in power systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |