CN108733726B - Network semantic model reconstruction system and method based on dynamic events - Google Patents
Network semantic model reconstruction system and method based on dynamic events Download PDFInfo
- Publication number
- CN108733726B CN108733726B CN201710272614.9A CN201710272614A CN108733726B CN 108733726 B CN108733726 B CN 108733726B CN 201710272614 A CN201710272614 A CN 201710272614A CN 108733726 B CN108733726 B CN 108733726B
- Authority
- CN
- China
- Prior art keywords
- event
- network
- network semantic
- data
- dynamic
- 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
Abstract
The invention relates to a network semantic model reconstruction system and method based on dynamic events. The network semantic model reconstruction system based on the dynamic events comprises: a system data receiving module for receiving a system data; an event generating module for generating a system event based on the system data; a relation correlation module for correlating a network semantic relation of a network semantic information model with the system event; and a network semantic relationship reconstruction module for reconstructing the network semantic relationship by analyzing the network semantic information model related to the system event and utilizing a domain data analysis algorithm to form a new dynamic network semantic model. The new dynamic semantic model is overlapped with the existing network information model and is changed when the system event is changed, so that the virtual network context information is more flexible to the upper application of data analysis, and the data analysis requirements under different application scenes can be met.
Description
Technical Field
The invention relates to data analysis based on a network semantic model, in particular to network semantic model reconstruction based on dynamic events.
Background
Domain data analysis for the physical network for collecting field data and sending to the service center via a computer network or wirelessly; then, the field data is marked with a data context by a domain data analysis method, including data generation time, data source description and the like. Semantic tags are then associated with the specialized data analysis methods, which are not available to other data analysis methods. For example, in the case of a Water Distribution Network (WDN), a separate Metering Area (DMA) is defined based on a prerequisite with a limitation. If the zone function is changed only from the commercial zone to the residential zone, the DMA cannot be easily repartitioned. Since all information used for data analysis is related to actual physical network characteristics, data service functions are limited and not particularly adaptable to various data innovations. Therefore, there is a need to make the semantic logic layer more flexible for the upper physical network data analysis application, so as to adapt to various data innovations.
However, there is currently no such specific dynamic semantic information model layer for physical network data analysis applications. All information needs to be modeled and reconfigured within a specific solution. The traditional information description methods, which require the collection of contextual information and analysis by experts, then curing and input into the solution system, then programming the data processing algorithms for specific analysis targets for a specific application scenario, do not support the flexibility of digital information model based applications and innovations.
Disclosure of Invention
In order to solve the problems, a network semantic model reconstruction system and a network semantic model reconstruction method based on dynamic events are provided, wherein the network semantic model reconstruction system has a semantic logic layer based on system events, and the system events enable the semantic logic layer to be more flexible for upper application.
According to a first aspect of the present invention, there is provided a dynamic event-based network semantic model reconstruction system, comprising: the system data receiving module is used for receiving system data; an event generation module for generating system events based on the system data; the relation correlation module is used for correlating the network semantic relation of the network semantic information model with the system event; and the network semantic relation reconstruction module is used for reconstructing the network semantic relation by utilizing a domain data analysis algorithm through analyzing the network semantic information model so as to form a new dynamic network semantic model.
The dynamic event-based network semantic model reconstruction system enables reconstruction of new network logical semantic relations based on existing network logical semantic relations based on dynamic system events and domain data analysis algorithms. The dynamic semantic model with the new network logic semantic relation is overlapped with the existing network information model with the existing network logic semantic relation, and changes when the system event changes, so that the virtual network context information is more flexible to the upper application of data analysis, and the data analysis requirements under different application scenes can be met.
In one embodiment of the dynamic event-based network semantic model reconstruction system according to the first aspect of the present invention, the network semantic model reconstruction system further includes: and the event rule base is used for storing event rules describing event prerequisites of the system events and configuring the event rules according to an upper application program, wherein the event generation module generates the system events based on the system data according to the event rules in the event rule base. The event rules in the event rule base are very flexible and can be configured according to the application scenario. The event rule may be a predefined rule, or the event rule may be composed of an event cluster generated by a self-learning method according to a change rule of system data and determined according to an upper application. Therefore, the virtual network context information can be more flexible to the upper application of data analysis by generating the system event based on the system data according to the event rule in the event rule base, and the data analysis requirements under different application scenes can be met.
In one embodiment of the system for reconstructing a network semantic model based on dynamic events according to the first aspect of the present invention, the system data is dynamic data, wherein the event generation module generates the system event based on the dynamic data and the event rule in the event rule base. The dynamic data may be real-time data or historical data. By analyzing the real-time data or analyzing according to historical data playback, analyzing and judging according to dynamic changes of the data, generating system events based on the dynamic data and event rules in an event rule base, the virtual network context information can be more flexible for upper-layer application of data analysis, and therefore the data analysis requirements under different application scenes can be met.
In one embodiment of the dynamic event-based network semantic model reconstruction system according to the first aspect of the present invention, the network semantic model reconstruction system further includes: a domain data analysis algorithm library storing said domain data analysis algorithms, said network semantic information model including event information about said system events, said domain data analysis algorithm library being configured based on said event information and according to upper layer applications. Therefore, the domain data analysis algorithm library can be configured according to the requirements of upper-layer application programs, so that the virtual network context information can be more flexible for upper-layer application of data analysis, and the data analysis requirements under different application scenes can be met.
In an embodiment of the system for reconstructing a network semantic model based on dynamic events according to the first aspect of the present invention, the network semantic information model is described by using a Resource Description Framework (RDF) file. By adopting the RDF to describe the network semantic information model, the upper application program can utilize the existing universal RDF resolver, so that the data analysis requirements under different application scenes can be met without developing a new resolver.
In one embodiment of the dynamic event based network semantic model reconstruction system according to the first aspect of the present invention, the data collection system is at least one of a supervisory control and data acquisition (SCADA) system, a Manufacturing Execution System (MES), a field automation system or an event simulation system. Therefore, the network semantic model reconstruction system according to the present invention can be used in various fields such as industrial processes such as manufacturing, production, power generation, metal working, refining, etc., water treatment and distribution, wastewater collection and treatment, oil and gas pipelines, power transmission and distribution, wind farms, defense warning systems, infrastructure processes such as large communication systems, etc., and facility processes such as heating, ventilation, air conditioning systems, access control (physical security and information security fields), energy consumption, etc., of buildings, airports, ships, space stations. Therefore, the virtual network context information can be more flexible for upper-layer application of data analysis, and the data analysis requirements under different application scenes can be met.
According to a second aspect of the present invention, there is provided a dynamic event-based network semantic model reconstruction method, including the following steps: receiving system data; generating a system event based on the system data; correlating the network semantic relationship of the network semantic information model with the system event; and reconstructing the network semantic relationship by analyzing the network semantic information model and utilizing a domain data analysis algorithm to form a new dynamic network semantic model. In one embodiment of the method for reconstructing a network semantic model based on dynamic events according to the second aspect of the present invention, the system event is generated based on the system data according to an event rule in an event rule library, the event rule describes an event prerequisite of the system event, and the event rule is configured according to an upper application program.
In one embodiment of the method for reconstructing a network semantic model based on dynamic events according to the second aspect of the present invention, the system data is dynamic data, wherein the system events are generated based on the dynamic data and the event rules in the event rule base.
In one embodiment of the method for reconstructing a dynamic event-based network semantic model according to the second aspect of the present invention, the domain data analysis algorithm is stored in a domain data analysis algorithm library, the network semantic information model includes event information about the system event, and the domain data analysis algorithm library is configured according to an upper application program based on the event information.
In one embodiment of the method for reconstructing a network semantic model based on dynamic events according to the second aspect of the present invention, the network semantic information model is described by using a resource description framework file.
In one embodiment of the method for dynamic event-based network semantic model reconstruction according to the second aspect of the present invention, the system data is collected by a data collection system, wherein the data collection system is at least one of a supervisory control and data acquisition (SCADA) system, a Manufacturing Execution System (MES), a field automation system or an event simulation system.
The advantages of the method for reconstructing a network semantic model based on dynamic events according to the present invention are similar to those of the system for reconstructing a network semantic model based on dynamic events according to the present invention, and for the sake of brevity, the description thereof is omitted here.
According to a third aspect of the present invention, there is provided a dynamic event-based network semantic model reconstruction system, comprising: a receiving device for receiving system data collected by the data collection system; and a processor configured to generate a system event based on the system data, correlate a network semantic relationship of a network semantic information model with the system event, and reconstruct the network semantic relationship using a domain data analysis algorithm in a domain data analysis algorithm library by analyzing the network semantic information model to form a new dynamic network semantic model. Therefore, the network semantic model reconstruction system based on the dynamic events can be easily realized on the basis of the existing equipment.
According to a third aspect of the present invention, there is provided a computer readable medium having stored thereon computer instructions which, when executed by a processor, cause the processor to perform a method according to the present invention. Thereby, the network semantic model reconstruction system based on the dynamic events can be easily realized on the basis of the existing equipment.
The system and method for dynamic event-based network semantic model reconstruction and computer readable medium according to the present invention enable reconstruction of new network logical semantic relationships based on existing network logical semantic relationships based on dynamic system event and domain data analysis algorithms. The dynamic semantic model with the new network logic semantic relation is overlapped with the existing network information model with the existing network logic semantic relation, and changes when the system event changes, so that the virtual network context information is more flexible to the upper application of data analysis, and the data analysis requirements under different application scenes can be met.
Drawings
To more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and it is obvious for those skilled in the art that other drawings can be obtained based on the drawings without inventive efforts.
FIG. 1 is a block diagram illustrating a dynamic event-based network semantic model reconstruction system according to one embodiment of the present invention.
FIG. 2 is a flowchart illustrating a method for reconstructing a network semantic model based on dynamic events according to an embodiment of the present invention.
FIG. 3 is a block diagram illustrating a specific implementation of a dynamic event-based network semantic model reconstruction system according to the present invention.
Fig. 4 is a view showing a general WDN structure.
Fig. 5 is a flow chart illustrating a method of reconstructing a WDN semantic model to locate leakage points of the WDN using a dynamic event based network semantic model reconstruction method according to the present invention.
Fig. 6 is a view of a simplified WDN network topology corresponding to fig. 4.
Fig. 7 is a view of a WDN network topology associated with generated system events.
Fig. 8 is a view of DMA scenario 1 of a WDN network topology generated in relation to system events.
Fig. 9 is a view of DMA scenario 2 of a WDN network topology generated in relation to system events.
Fig. 10 is a view showing an overlap region for leak monitoring.
List of reference numerals
100: network semantic model reconstruction system 101: system data receiving module
102: the event generation module 103: relationship correlation module
104: the network semantic relationship reconstruction module 105: data collection system
106: network semantic information model 107: domain data analysis algorithm library
108: event rule base S210-S260: step (ii) of
310: the receiving device 320: processor with a memory having a plurality of memory cells
S610 to S680: step (ii) of
Detailed Description
The technical solutions of the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present disclosure. It is to be understood that the described embodiments are merely a subset of the disclosed embodiments and not all embodiments.
FIG. 1 is a block diagram illustrating a dynamic event-based network semantic model reconstruction system according to one embodiment of the present invention. The dynamic event-based network semantic model reconstruction system 100 according to the present invention includes a system data receiving module 101, an event generating module 102, a relationship correlation module 103, and a network semantic relationship reconstruction module 104. The system data reception module 101 receives system data. The event generation module 102 generates a system event based on the system data received by the system data reception module 101. The relationship correlation module 103 correlates the network semantic relationships of the existing network semantic information model 106 with the system events generated by the event generation module 102. The network semantic relationship reconstructing module 104 reconstructs the network semantic relationship by analyzing the network semantic information model and using a domain data analysis algorithm to form a new dynamic network semantic model.
The network semantic model reconstruction system 100 may also include an event rule base 108, for example. Event rules repository 108 stores event rules that describe event prerequisites for system events. The event rules are very flexible and can be configured according to the requirements of upper-layer application programs. In one embodiment, the event rule is a predefined rule. In another embodiment, the event rule is composed of event clusters which are generated according to the change rule of system data by a self-learning method and determined according to an upper application. For example, the event prerequisite may be an upper limit of a minimum or maximum value. Therefore, the data analysis requirements under different application scenes can be met
The system data may be dynamic data. The event generation module 102 may generate system events based on the dynamic data and event rules in the event rules repository 108. The dynamic data may be real-time data or historical data. The analysis and determination may be made from dynamic changes in the data by analyzing real-time data or by analyzing playback from historical data.
The network semantic model reconstruction system 100 also includes a domain data analysis algorithm library 107 that stores domain data analysis algorithms. The network semantic information model 106 may include event information about system events. The domain data analysis algorithm library 107 can be configured according to upper-layer application programs based on event information, so that data analysis requirements under different application scenarios can be met.
In an exemplary embodiment, the system data is collected by the system collection system 105. For example, the System collection System 105 is at least one of a Supervisory Control And Data Acquisition (SCADA) System, a Manufacturing Execution System (MES), a field automation System, or an event simulation System. For example, SCADA may be used for industrial processing such as manufacturing, production, power generation, metal working, refining, etc., water treatment and distribution, wastewater collection and treatment, oil and gas pipelines, power transmission and distribution, wind farms, defense warning systems, large scale communication systems, etc., and equipment processing for heating, ventilation, air conditioning systems, access control (physical security and information security fields), energy consumption, etc., of buildings, airports, ships, space stations. Therefore, the network semantic model reconstruction system 100 of the present invention can also be applied to these fields.
In one embodiment, the relationship correlation module 103 may fix the system event to the network topology described by the network semantic information model 106 according to the geographic location, for example, and the network semantic relationship reconstruction module 104 generates a new dynamic network semantic model according to the geographic location based on the event information about the system event and pushes to the upper layer application on the application server.
In another embodiment, the relationship correlation module 103 may also reconstruct the relationship between system events according to the geographical location, for example, and the network semantic relationship reconstruction module 104 generates a new dynamic network semantic model according to the geographical location based on the reconstructed relationship between system events and pushes the new dynamic network semantic model to an upper application on the application server.
In both embodiments, the dynamic semantic model with new network logical semantic relationships overlaps with the existing network information model with existing network logical semantic relationships and changes when system events change. The context information of the virtual network established based on the geographic position is more flexible for upper-layer application of data analysis, and therefore the data analysis requirements under different application scenes can be met.
Of course, correlating the network semantic relationships of the network semantic information model with the system events is not limited to being based on geographic location. For example, when the network semantic model reconstruction system 100 according to the present invention is applied to the infrastructure processing of water treatment and distribution, wastewater collection and treatment, oil and gas pipelines, power transmission and distribution, wind farms, defense warning systems, large scale communication systems, etc., the network semantic relationship of the network semantic information model may be related to the system event according to the geographical location. When the network semantic model reconstruction system 100 according to the present invention is applied to equipment processing such as heating, ventilation, and air conditioning systems of buildings, airports, ships, and space stations, the network semantic relationship of the network semantic information model may be related to system events according to needs, for example, according to locations to be monitored, required heating load, ventilation amount, air conditioning set temperature, and the like. In addition, when the network semantic model reconstruction system 100 according to the present invention is applied to the network security field, the network semantic relationship of the network semantic information model may be related to the system event according to the specific node location of the network, such as the internet, and the dynamic semantic model may be changed when the system event is changed, so that the context information of the virtual network established based on the node location of the network is more flexible for the upper layer application of data analysis, thereby being capable of satisfying the data analysis needs in different application scenarios.
In an embodiment of the invention, the network semantic information model 106 may be described, for example, using a resource description framework file.
The dynamic event based network semantic model reconstruction system 100 according to the present invention enables reconstruction of new network logical semantic relationships based on existing network logical semantic relationships based on dynamic system event and domain data analysis algorithms. The dynamic semantic model with the new network logic semantic relation is overlapped with the existing network information model with the existing network logic semantic relation, and changes when the system event changes, so that the virtual network context information is more flexible to the upper application of data analysis, and the data analysis requirements under different application scenes can be met.
In the following, a method 200 for reconstructing a network semantic model based on dynamic events according to an embodiment of the present invention is described with reference to fig. 2. FIG. 2 is a flow diagram illustrating a method 200 for dynamic event-based network semantic model reconstruction according to one embodiment of the invention.
In step S210, the method 200 for reconstructing a network semantic model based on dynamic events starts.
In step S220, system data is received.
In step S230, a system event is generated based on the received system data.
In step S240, the network semantic relationships of the existing network semantic model 106 are correlated with the generated system events.
In step S250, the network semantic relationship is reconstructed by analyzing the network semantic information model 106 using a domain data analysis algorithm to form a new dynamic network semantic information model.
In step S260, the method 200 for reconstructing a network semantic model based on dynamic events ends.
Furthermore, although not shown in the flow diagram, the dynamic event-based network semantic model reconstruction method according to the present invention may be performed iteratively.
In one embodiment, the system data is dynamic data. As described above, the dynamic data may be real-time data or historical data, and the event rule may be a predefined rule or may be composed of an event cluster generated by a self-learning method according to a change rule of system data and determined according to an upper application. In one embodiment, the system events may be generated in step S230 based on the dynamic data and the event rules in the event rules repository 108 by analyzing the real-time data or by analyzing from historical data playback, analyzing and judging from dynamic changes in the data. The event rules in the event rule base 108 describe event prerequisites of system events and can be configured according to upper-layer application programs, so that context information of the virtual network is more flexible for upper-layer application of data analysis, and data analysis requirements under different application scenarios can be met.
The network semantic information model 106 is stored in the domain data analysis algorithm library 107. As described above, the network semantic information model 106 may include event information regarding system events. The domain data analysis algorithm library 107 can be configured based on the event information and according to the upper layer application. The context information of the virtual network is more flexible for upper-layer application of data analysis, and therefore the data analysis requirements under different application scenarios can be met.
In one embodiment, the system data is collected by the data collection system 105. As described above, the system collection system 105 is at least one of a supervisory control and data acquisition (SCADA) system, a Manufacturing Execution System (MES), a field automation system, or an event simulation system, for example.
For example, in one embodiment, in step S240, the system event may be fixed to the network topology described by the network semantic information model 106 according to the geographic location, and the network semantic relationship restructuring module 104 generates a new dynamic network semantic model according to the geographic location based on the event information about the system event, and pushes the new dynamic network semantic model to the upper layer application on the application server. Thereby meeting the data analysis requirements in different application scenarios.
For example, in another embodiment, in step S240, the relationship between the system events may also be reconstructed according to the geographic location, and the network semantic relationship reconstruction module 104 generates a new dynamic network semantic model according to the geographic location based on the reconstructed relationship between the system events and pushes the new dynamic network semantic model to the upper layer application on the application server.
The dynamic semantic model with new network logical semantic relationships overlaps with the existing network information model with existing network logical semantic relationships and changes when system events change. The context information of the virtual network established based on the geographic position is more flexible for upper-layer application of data analysis, and therefore the data analysis requirements under different application scenes can be met.
As described above with respect to the network semantic model reconstruction system 100 according to the present invention, the network semantic model reconstruction method 200 according to the present invention can also be applied to infrastructure processes such as manufacturing, production, power generation, metal working, refining, etc., water treatment and distribution, wastewater collection and treatment, oil and gas pipelines, power transmission and distribution, wind farms, defense warning systems, large communication systems, etc., and equipment processes for heating, ventilation, air conditioning systems, access control (physical security and information security fields), energy consumption, etc., of buildings, airports, ships, space stations. Thus, correlating the network semantic relationships of the network semantic information model with the system events is not limited to being based on geographic location.
In one embodiment, the network semantic information model 106 may be described using a resource description framework file.
The method 200 for reconstructing a network semantic model based on dynamic events according to the present invention also enables the reconstruction of new network logical semantic relationships based on existing network logical semantic relationships based on dynamic system event and domain data analysis algorithms. The dynamic semantic model with the new network logic semantic relation is overlapped with the existing network information model with the existing network logic semantic relation, and changes when the system event changes, so that the virtual network context information is more flexible to the upper application of data analysis, and the data analysis requirements under different application scenes can be met.
In the following, a specific implementation of the dynamic event-based network semantic model reconstruction system 100 according to the present invention is described with reference to fig. 3. FIG. 3 is a block diagram illustrating a specific implementation of a dynamic event-based network semantic model reconstruction system 100 according to the present invention.
For example, as shown in fig. 3, the system 100 for reconstructing a network semantic model based on dynamic events according to the present invention includes a receiving device 310 and a processor 320. The receiving device 310 receives system data collected by the data collection system 105. The processor 320 generates system events based on the system data received by the receiving device 320, correlates the network semantic relationships of the network semantic information model 106 with the system events, and reconstructs the network semantic relationships using a domain data analysis algorithm by analyzing the network semantic information model 106 to form a new dynamic network semantic model.
For example, the processor 320 may be implemented by a microcontroller, a microprocessor, a Central Processing Unit (CPU), an MPU (micro processor unit), a Digital Signal Processor (DSP), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or the like, or other controllers or processors.
The above-described system and method for reconstructing a network semantic model based on dynamic events according to the present invention can be implemented as a semantic logic layer (RDF + RDF Schema layer) of a semantic network architecture, which provides a semantic model for describing information and types on a network.
One typical application of a semantic logical layer based on dynamic events is leakage monitoring of Water Distribution Networks (WDNs). Large amounts of water in WDNs leak for various reasons, such as, for example, over time, due to tampering, intentional or unintentional damage. The water leakage not only causes a loss of water supply companies but also causes a waste of natural resources. Leak monitoring and location is a difficult task for water supply companies.
Currently, physical DMA (independent metering area) is the most commonly used method for WDN leakage monitoring. There are some rules how to identify DMAs in WDNs, for example, major roads or rivers may be used as the boundaries of the DMAs. The DMA can also be identified by the function of the zone, for example an industrial zone or a residential zone. A water flow meter or flow sensor is installed at the boundary of the DMAs for measuring the volume of water transferred into or out of each DMA. Minimum Night Flow (MNF) is an important indicator of DMA leakage. Leakage typically occurs if the MNF of an area is greater than the average of the entire WDN. If the DMA size is too large for leak monitoring, the large DMA may be divided into small child DMAs to locate the leak point of the network.
However, the conventional DMA method has a disadvantage in that the identification of the DMA is based on physical separation, and thus the DMA mode is limited. In addition, when analyzing for leaks, the valve must be closed for leak monitoring. This operation can only be performed when the water demand is low, or it may affect industrial production or human life.
Fig. 4 is a view showing a general WDN structure. Key semantic factors in WDN are nodes (e.g., N1, N2.., N36 in fig. 4) and pipeline segments (e.g., P1, P2.., P41 in fig. 4).
The semantic description of the WDN in fig. 4 using RDF files is as follows.
The general rules for identifying DMAs are as follows:
1) altitude, terrain, road, etc.
2) An internal pipe loop is formed in the DMA to ensure that there is no water return.
3) For a DMA it is preferred that there are only 1 inlet flow pipe, and at most 3 inlets.
The WDN semantic model is now reconstructed using the dynamic event based network semantic model reconstruction method according to the present invention to locate the leakage point of the WDN. Fig. 5 is a flow chart illustrating a method 600 of reconstructing a WDN semantic model to locate leakage points of a WDN using a dynamic event based network semantic model reconstruction method according to the present invention. Fig. 6 is a view of a simplified WDN structure corresponding to fig. 4. Fig. 7 is a view of a WDN network topology associated with generated system events. Fig. 8 is a view of a first DMA scenario of a WDN network topology generated in relation to system events. Fig. 9 is a diagram of a second DMA scenario of a WDN network topology generated in relation to system events. Fig. 10 is a view showing an overlap region for leak monitoring.
Referring now to fig. 5-10, a method 600 for reconstructing a WDN semantic model to locate a leakage point of a WDN using a dynamic event based network semantic model reconstruction method according to the present invention will be described.
In step S610, the method 600 begins.
In step S620, the water flow measured by the flow sensor or the water flow meter is received. Here, the measured water flow may be a water flow measured in real time, or may be a water flow measured in the past. The analysis and judgment can be made according to the dynamic change of the water flow by analyzing the water flow measured in real time or the water flow measured in the past.
In step S630, when it is calculated that the water flows at the points A, B, C, D, E, F and G shown in fig. 6 are equal to zero or less than a defined minimum value according to a predefined event rule stored in the event rule base, that is, the water flows are equal to zero or less than the defined minimum value, based on the received water flows measured by the flow sensor or the water flow meter, an event that the water flows at the points A, B, C, D, E, F and G are equal to zero or less than the defined minimum value is generated.
In step S640, the generated events with water flow equal to zero or less than a defined minimum at points A, B, C, D, E, F and G are fixed into the network topology described by the WDN semantic model shown above, as shown in fig. 7, according to the geographical locations of points A, B, C, D, E, F and G.
Then, in step S650, according to the leak analysis algorithm of the leak monitoring system, following the above general rules 1), 2) and 3) for identifying DMAs, DMA boundaries are generated, respectively, dividing the entire WDN into 3 sub-DMAs, namely DMA _1, DMA _2 and DMA _3 (as shown in fig. 7) and 2 sub-DMAs, namely DMA _ a and DMA _ B (as shown in fig. 8), respectively.
Then, in step S660, the new overlapping semantic relationship of the WDN network is reconstructed using the leakage analysis algorithm. As an example, only the dynamic WDN semantic model extended with DMA information describing DMA _1 of the WDN network is shown below.
The dynamic WDN semantic models of the remaining DMAs (DMA _2, DMA _3, DMA _ A and DMA _ B) extended with DMA information are similar to the dynamic WDN semantic model of DMA _1 extended with DMA information described and not shown here for simplicity and clarity.
Then, in step S670, the leak monitoring system analyzes the system characteristics of the WDN network and identifies that a leak may exist in virtual DMA _2 of DMA scenario 1 and in virtual DMA _ a of DMA scenario 2. If the MNF of the two DMAs is the same or the MNF of the two DMAs is different but both are larger than the average value of the entire WDN, since the two DMAs have a positional overlap, it can be prioritized that leakage is highly likely to occur in the overlap region WLA _ ALPHA of the two DMAs, as shown in fig. 10, and thus the leakage monitoring area becomes small. Then, by examining the overlap region WLA _ ALPHA, it is possible to determine whether a leak has occurred in the region and accurately locate the place where the leak has occurred.
In step S680, the method 600 ends.
Further, alternatively, virtual DMAs may be generated by iteratively calculating under different water supply scenarios until an accurate leak location is calculated. For example, under different water delivery scenarios, it may be calculated that the water flow at points other than points A, B, C, D, E, F and G is 0 or less than a defined minimum. Events at these points where the water flow is 0 or less than a defined minimum may be fixed into the network topology described by the WDN semantic model shown above, and different DMA boundaries are generated following the general rules identifying DMAs, dividing the entire WDN into another number of virtual DMAs. Then, a leakage analysis algorithm is further utilized to position the area where leakage is likely to occur, so that the leakage monitoring area is further reduced, and the positioning accuracy is improved. Under enough scenes, the leakage area can be fully reduced to meet the precision of engineering requirements.
As described above, by applying the system and method for reconstructing a network semantic model based on dynamic events according to the present invention in leakage monitoring of a Water Distribution Network (WDN), areas where leakage is likely to occur can be located step by step through virtual division of DMA, and leakage monitoring areas can be reduced, so that a leakage position can be located quickly, and location accuracy can be improved, thereby reducing workload of a water supply company in locating leakage and reducing resource waste.
The dynamic event-based network semantic model reconstruction system and method according to the present invention is not limited to be applied to leakage monitoring of Water Distribution Networks (WDNs). As described in the foregoing, the system and method for reconstructing a network semantic model based on dynamic events according to the present invention can also be applied to the processing of infrastructures such as manufacturing, production, power generation, metal processing, refining and the like, water processing and distribution, wastewater collection and processing, oil and gas pipelines, power transmission and distribution, wind farms, defense warning systems, large communication systems and the like, and the processing of equipment such as heating, ventilation, air conditioning systems, access control (physical security and information security fields), energy consumption and the like of buildings, airports, ships, space stations.
The dynamic event-based network semantic model reconstruction system and method enables a new network logic semantic relationship to be reconstructed on the basis of the existing network logic semantic relationship based on a dynamic system event and domain data analysis algorithm. The dynamic semantic model with the new network logic semantic relation is overlapped with the existing network information model with the existing network logic semantic relation, and changes when the system event changes, so that the virtual network context information is more flexible to the upper application of data analysis, and the data analysis requirements under different application scenes can be met.
The present invention also provides a computer storage medium storing instructions for causing a machine to perform an auditing method for program code as described herein. Specifically, a system or an apparatus equipped with a storage medium on which software program codes that realize the functions of any of the above-described embodiments are stored may be provided, and a computer (or a CPU or MPU) of the system or the apparatus is caused to read out and execute the program codes stored in the storage medium.
In this case, the program code itself read from the storage medium can realize the functions of any of the above-described embodiments, and thus the program code and the storage medium storing the program code constitute a part of the present invention.
Examples of the storage medium for supplying the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (e.g., CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD + RW), a magnetic tape, a nonvolatile memory card, and a ROM. Alternatively, the program code may be downloaded from a server computer via a communications network.
Further, it should be clear that the functions of any one of the above-described embodiments may be implemented not only by executing the program code read out by the computer, but also by causing an operating system or the like operating on the computer to perform a part or all of the actual operations based on instructions of the program code.
Further, it is to be understood that the program code read out from the storage medium is written to a memory provided in an expansion board inserted into the computer or to a memory provided in an expansion unit connected to the computer, and then causes a CPU or the like mounted on the expansion board or the expansion unit to perform part or all of the actual operations based on instructions of the program code, thereby realizing the functions of any of the above-described embodiments.
It should be noted that not all steps and modules in the above flows and system structure diagrams are necessary, and some steps or modules may be omitted according to actual needs. The execution order of the steps is not fixed and can be adjusted as required. The system structure described in the above embodiments may be a physical structure or a logical structure, that is, some modules may be implemented by the same physical entity, or some modules may be implemented by a plurality of physical entities, or some components in a plurality of independent devices may be implemented together.
In the above embodiments, the hardware unit may be implemented mechanically or electrically. For example, a hardware element may comprise permanent dedicated circuitry or logic such as a dedicated processor, Field Programmable Gate Array (FPGA) or Application Specific Integrated Circuit (ASIC) to perform the corresponding operations. The hardware elements may also comprise programmable logic or circuitry, such as a general purpose processor or other programmable processor, that may be temporarily configured by software to perform the corresponding operations. The specific implementation (mechanical, or dedicated permanent, or temporarily set) may be determined based on cost and time considerations.
While the invention has been shown and described in detail in the drawings and in the preferred embodiments, the invention is not limited to the embodiments disclosed, and those skilled in the art will appreciate that various combinations of code auditing means in the various embodiments described above may be employed to obtain further embodiments of the invention, which are also within the scope of the invention.
Claims (9)
1. The network semantic model reconstruction system based on the dynamic events comprises the following steps:
a system data receiving module (101) for receiving a system data;
an event generation module (102) for generating a system event based on the system data;
a relationship correlation module (103) for correlating a network semantic relationship of a network semantic information model (106) with the system event; and
a network semantic relationship reconstruction module (104) for reconstructing network semantic relationships using a domain data analysis algorithm by analyzing the network semantic information model (106) to form a new dynamic network semantic model,
wherein the network semantic model reconstruction system (100) further comprises:
an event rules repository (108) for storing event rules describing event prerequisites for the system events, the event rules configured according to an upper level application,
wherein the event generation module (102) generates the system events based on the system data according to event rules in the event rule base (108),
wherein the system data is a dynamic data,
wherein the event generation module (102) generates the system event based on the dynamic data and the event rule in the event rule base (108).
2. The dynamic event based network semantic model reconstruction system of claim 1, wherein the network semantic model reconstruction system (100) further comprises: a domain data analysis algorithm library (107) storing the domain data analysis algorithms, the network semantic information model (106) including event information about the system events, the domain data analysis algorithm library (107) being configured based on the event information and according to upper layer applications.
3. The dynamic event-based network semantic model reconstruction system of claim 1, wherein the network semantic information model (106) is described using a resource description framework file.
4. A dynamic event based network semantic model reconstruction system according to claim 1 wherein the system data is collected by a data collection system (105), wherein the data collection system (105) is at least one of a supervisory control and data acquisition (SCADA) system, a Manufacturing Execution System (MES), a field automation system or an event simulation system.
5. The network semantic model reconstruction method based on the dynamic event comprises the following steps:
receiving system data;
generating a system event based on the system data;
correlating a network semantic relationship of a network semantic information model with the system event; and
reconstructing the network semantic relationship by analyzing the network semantic information model and utilizing a domain data analysis algorithm to form a new dynamic network semantic model,
wherein the system event is generated based on the system data according to an event rule in an event rule base,
wherein the event rules describe event prerequisites for the system events, the event rules configured according to an upper layer application,
wherein the system data is dynamic data,
wherein the system event is generated based on the dynamic data and the event rules in the event rules repository.
6. The dynamic event-based network semantic model reconstruction method according to claim 5, characterized in that the domain data analysis algorithm is stored in a domain data analysis algorithm library, the network semantic information model comprises event information about the system event, and the domain data analysis algorithm library is configured according to an upper application program based on the event information.
7. The method according to claim 5, wherein the network semantic information model is described by using a resource description framework file.
8. The dynamic event-based network semantic model reconstruction method of claim 5, wherein the system data is collected by a data collection system, wherein the data collection system is at least one of a supervisory control and data acquisition (SCADA) system, a Manufacturing Execution System (MES), a field automation system, or an event simulation system.
9. The network semantic model reconstruction system based on the dynamic events comprises the following steps:
a receiving device (310) for receiving a system data;
a processor (320) configured to generate a system event based on the system data, correlate a network semantic relationship of a network semantic information model with the system event, and reconstruct the network semantic relationship using a domain data analysis algorithm from a library of domain data analysis algorithms by analyzing the network semantic information model to form a new dynamic network semantic model,
wherein the network semantic model reconstruction system (100) further comprises:
an event rules repository (108) for storing event rules describing event prerequisites for the system events, the event rules configured according to an upper level application,
wherein the processor is configured to generate the system events based on the system data according to event rules in the event rules repository (108),
wherein the system data is a dynamic data,
wherein the processor is configured to generate the system event based on the dynamic data and the event rule in the event rule base (108).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710272614.9A CN108733726B (en) | 2017-04-24 | 2017-04-24 | Network semantic model reconstruction system and method based on dynamic events |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710272614.9A CN108733726B (en) | 2017-04-24 | 2017-04-24 | Network semantic model reconstruction system and method based on dynamic events |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108733726A CN108733726A (en) | 2018-11-02 |
| CN108733726B true CN108733726B (en) | 2022-03-29 |
Family
ID=63934485
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710272614.9A Active CN108733726B (en) | 2017-04-24 | 2017-04-24 | Network semantic model reconstruction system and method based on dynamic events |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108733726B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3885854B1 (en) * | 2018-12-28 | 2024-03-27 | Siemens Aktiengesellschaft | Data analysis method, device and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101930369A (en) * | 2010-09-08 | 2010-12-29 | 浙江大学 | Task immigration-orientated component semantic matching method |
| CN106570081A (en) * | 2016-10-18 | 2017-04-19 | 同济大学 | Semantic net based large scale offline data analysis framework |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8041743B2 (en) * | 2007-04-17 | 2011-10-18 | Semandex Networks, Inc. | Systems and methods for providing semantically enhanced identity management |
| US7958155B2 (en) * | 2007-04-17 | 2011-06-07 | Semandex Networks, Inc. | Systems and methods for the management of information to enable the rapid dissemination of actionable information |
-
2017
- 2017-04-24 CN CN201710272614.9A patent/CN108733726B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101930369A (en) * | 2010-09-08 | 2010-12-29 | 浙江大学 | Task immigration-orientated component semantic matching method |
| CN106570081A (en) * | 2016-10-18 | 2017-04-19 | 同济大学 | Semantic net based large scale offline data analysis framework |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108733726A (en) | 2018-11-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11238055B2 (en) | Building management system with eventseries processing | |
| Zhang et al. | Leakage zone identification in large-scale water distribution systems using multiclass support vector machines | |
| TWI502299B (en) | System and method for monitoring resources in a water utility network | |
| US20130211797A1 (en) | System and method for analyzing gis data to improve operation and monitoring of water distribution networks | |
| CN102914761B (en) | System and method for monitoring quality of intelligent electric energy meter | |
| JP7161268B2 (en) | Quantifying the combined impact of interdependent and uncertain resources within the power grid | |
| US9178939B2 (en) | Auto incorporation of new components into a hierarchical network | |
| Marzola et al. | Leakage detection and localization in a water distribution network through comparison of observed and simulated pressure data | |
| Snider et al. | Combining machine learning and survival statistics to predict remaining service life of watermains | |
| US20170091304A1 (en) | Semantic mapping of topic map meta-models identifying assets and events to include directionality | |
| Candelieri et al. | Improving leakage management in urban water distribution networks through data analytics and hydraulic simulation | |
| Li et al. | Fast detection and localization of multiple leaks in water distribution network jointly driven by simulation and machine learning | |
| CN108733726B (en) | Network semantic model reconstruction system and method based on dynamic events | |
| KR20210113708A (en) | Leakage Detection Network Management System and Operation Method | |
| Bozkurt et al. | Development of a new comprehensive framework for the evaluation of leak management components and practices | |
| Momeni et al. | Application of neural network–based modeling for leak localization in water mains | |
| CN113065721A (en) | Method, device, equipment and medium for graded early warning of leakage events of community water supply network | |
| Sellitto et al. | A Cyber security digital twin for critical infrastructure protection: the intelligent transport system use case | |
| KR20210082581A (en) | IoT based power equipment remote monitoring and control system and method of the same | |
| US20150373555A1 (en) | Wireless Sensor Network Commissioning | |
| US20170201464A1 (en) | Apparatus for managing optimized asset of distributed resources and operation method of the same | |
| CN114458970A (en) | Remote monitoring processing method and device based on partition metering | |
| Fuentes Jr et al. | Leak detection in water distribution networks via pressure analysis using a machine learning ensemble | |
| CN111339227A (en) | Method for evaluating power supply scheme rationality based on GIS | |
| CN110659170A (en) | Vehicle-mounted T-BOX test system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |