CN113810953B - Wireless sensor network resource scheduling method and system based on digital twinning - Google Patents
Wireless sensor network resource scheduling method and system based on digital twinning Download PDFInfo
- Publication number
- CN113810953B CN113810953B CN202111048000.5A CN202111048000A CN113810953B CN 113810953 B CN113810953 B CN 113810953B CN 202111048000 A CN202111048000 A CN 202111048000A CN 113810953 B CN113810953 B CN 113810953B
- Authority
- CN
- China
- Prior art keywords
- network
- data
- scheduling
- space
- scheduling scheme
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/16—Central resource management; Negotiation of resources or communication parameters, e.g. negotiating bandwidth or QoS [Quality of Service]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/06—Testing, supervising or monitoring using simulated traffic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W84/00—Network topologies
- H04W84/18—Self-organising networks, e.g. ad-hoc networks or sensor networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Quality & Reliability (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention belongs to the field of wireless sensor networks, and relates to a wireless sensor network resource scheduling method and system based on digital twinning; firstly, building a wireless sensor network system architecture of an end-side cloud, and building a wireless sensor network digital twin system by using physical space data acquisition, data processing, physical space network system modeling and scheduling algorithm modeling methods; secondly, acquiring wireless sensor network transmission requirements and real-time operation data through edge equipment, executing a wireless sensor network resource scheduling flow based on digital twin, simulating and verifying a scheduling scheme in a digital twin space and analyzing feasibility; then, a control instruction is output according to the simulation result and is applied to a physical space wireless sensor network system, and the performance of the network resource scheduling method based on digital twinning is verified; and finally, the physical space and the digital twin space interact data and control instructions in real time, so that reasonable and reliable scheduling of the whole network resources is ensured.
Description
Technical Field
The invention belongs to the field of wireless sensor networks, and relates to a wireless sensor network resource scheduling method and system based on digital twinning.
Background
In recent years, the internet of things has appeared in a variety of applications, one of which is the industrial internet of things. The industrial internet of things connects a large number of industrial devices to the internet to realize factory automation, distributed process control, real-time monitoring and other applications. However, the difficulty and cost of deploying an industrial wired network are high, and research and development of a high-certainty wireless network are important directions. The typical IEEE 802.15.4e protocol proposes three MAC mechanisms, low Latency Deterministic Network (LLDN), deterministic synchronization multi-channel extension (DSME) and Time Slot Channel Hopping (TSCH). The TSCH mode communication adopts a scheduling mode of combining TDMA (Time Division Multiple Access, TDMA) and frequency hopping, and network capacity and reliability are improved and network delay and energy consumption are reduced by reducing the influence of interference and multipath fading. However, the communication mechanism of the MAC layer is only suitable for network communication in specific occasions, and a better resource scheduling method needs to be defined for resource scheduling of complex wireless networks such as large-traffic and multi-hop.
The wireless sensor network resource scheduling mainly comprises two main types, namely centralized type and distributed type. Centralized resource scheduling requires a relatively computationally powerful gateway that can provide a collision-free resource scheduling scheme, but this is only applicable to static networks, which will generate huge traffic for dynamic networks. In comparison, distributed scheduling can reduce bandwidth consumption generated by whole network management, but distributed resource scheduling is easy to generate a local optimal solution, and is an important point of research of each research team on how to find the optimal solution of resource scheduling.
Digital twinning is a complementary technology of intelligent manufacturing and industry 4.0, and is currently applied to the fields of product design, production planning, assembly, workshop man-machine interaction, prediction, health management and the like. Under the push of each field, the current and future manufacturing patterns can be changed, so that the digital twin is a mirror of the physical world, and a simulation, prediction and optimization method is provided for manufacturing and manufacturing, so that researchers can make more accurate decisions. In summary, digital twinning techniques may make the production process more reliable, flexible, and predictable. If the intelligent algorithm is combined, the data-driven system operation monitoring and optimization can be realized.
The current wireless network resource scheduling algorithm is mainly in the relation of weighing certainty and power consumption. Along with the rapid development of digital twin, the application of the digital twin in the field of resource energy optimal configuration is borrowed from reference. However, how to introduce digital twin in resource scheduling, and to improve the network resource utilization rate, reduce the communication delay and reduce the power consumption by dynamically adjusting the scheduling policy through real-time interaction of the digital space and the physical space is a technical problem to be solved urgently.
Disclosure of Invention
In view of the above, the invention aims to provide a wireless sensor network resource scheduling method and system based on digital twinning, which are characterized in that a digital twinning space model is established by acquiring physical space data, a scheduling scheme is adjusted and simulated according to communication requirements, and finally, a control instruction is generated according to simulation results to adjust the physical space scheduling scheme, so that the wireless sensor network resource scheduling scheme based on digital twinning is realized.
In order to achieve the above purpose, the present invention provides the following technical solutions:
in a first aspect of the present invention, the present invention provides a wireless sensor network resource scheduling method based on digital twinning, the method comprising:
the edge equipment collects field equipment data of the sensor and network information data in the transmission process through a wireless network, and builds a physical space and a digital twin space of the wireless sensor network;
deploying a plurality of machine learning prediction algorithm models which are trained in a digital twin space, and establishing a scheduling algorithm model according to a wireless sensing network;
in the initial stage, executing a scheduling algorithm model in a digital twin space according to the transmission requirement of a physical space to obtain an initialization scheduling scheme;
in a real-time stage, according to real-time data of a physical space, a prediction algorithm model is executed in a digital twin space to predict and obtain a network running state; verifying whether the prediction error meets the first communication requirement in the digital twin space through simulation, if so, maintaining the scheduling scheme of the previous stage, otherwise, executing a scheduling algorithm model to generate a real-time scheduling scheme;
simulation verification is carried out to verify whether the initialized scheduling scheme or the real-time scheduling scheme meets the second communication requirement, if the initialized scheduling scheme or the real-time scheduling scheme does not meet the second communication requirement, the scheduling algorithm model is executed to regenerate the scheduling scheme until the regenerated scheduling scheme meets the second communication requirement;
mapping the control instruction generated by the initialization scheduling scheme, the real-time scheduling scheme or the regenerated scheduling scheme meeting the second communication requirement to a physical space by using the scheduling scheme meeting the first communication requirement at the previous stage;
the physical space issues control instructions to the edge equipment to complete resource scheduling.
In a second aspect of the present invention, the present invention further provides a wireless sensor network resource scheduling system based on digital twinning, which is characterized in that the system includes a physical space and a digital twinning space;
the physical space comprises edge equipment, a wireless network and a sensor; the edge device collects field device data of the sensor and network information data in the transmission process through the wireless network; the edge device issues a control instruction to the wireless network to complete resource scheduling;
the digital twin space comprises a data center memory, a modeling module, a prediction algorithm module, a scheduling algorithm module and a simulation verification module; the data center memory stores field device data of a sensor from a physical space and network information data in a transmission process, and the modeling module establishes a plurality of physical models according to the field device data of the sensor and the network information data in the transmission process; the prediction algorithm module is deployed with a plurality of machine learning prediction algorithm models with complete training, and data prediction is called from the data center to obtain a network running state; the scheduling algorithm module is provided with a scheduling algorithm model, and a scheduling scheme is obtained by calling data from the data center; and the simulation verification module performs simulation verification on the prediction error output by the prediction algorithm module and performs simulation verification on the scheduling scheme output by the scheduling algorithm module.
The invention has the beneficial effects that:
the invention can well establish a digital twin space according to the physical space wireless sensor network, execute a scheduling flow in the digital twin space according to network system data and real-time data, predict the network state and give a scheduling scheme to carry out simulation verification, and finally ensure the synchronization of the physical space and the digital space through the data and instruction transmission of the edge equipment, thereby completing the scheduling of wireless sensor network resources.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objects and other advantages of the invention may be realized and obtained by means of the instrumentalities and combinations particularly pointed out in the specification.
Drawings
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in the following preferred detail with reference to the accompanying drawings, in which:
fig. 1 is a schematic diagram of a wireless sensor network resource scheduling system based on digital twinning in an embodiment of the invention;
fig. 2 is a schematic diagram of a wireless sensor network resource scheduling flow based on digital twinning in an embodiment of the present invention;
fig. 3 is a schematic diagram of a flow model of a wireless sensor network according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Other advantages and effects of the present invention will become apparent to those skilled in the art from the following disclosure, which describes the embodiments of the present invention with reference to specific examples. The invention may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present invention. It should be noted that the illustrations provided in the following embodiments merely illustrate the basic idea of the present invention by way of illustration, and the following embodiments and features in the embodiments may be combined with each other without conflict.
Fig. 1 is a schematic diagram of a wireless sensor network resource scheduling system based on digital twinning in an embodiment of the invention; as shown in fig. 1, the system includes a physical space and a digital twin space;
the physical space comprises edge equipment, a wireless network and a sensor;
in the physical space, the data transmission mainly comprises an uplink process and a downlink process, in the uplink process, the wireless network acquires field device data acquired by the sensor and uploads the field device data to the edge device for subsequent processing, and besides, the wireless network uploads information such as a wireless sensor network system schedule, network topology information, network node state information, network information data such as link communication parameters and the like to the edge device; in the downlink process, the edge device executes network management, and issues network management information to the wireless network, so that the wireless network completes resource scheduling.
In some possible embodiments, the edge device is a smart edge device having a built-in processor therein, with on-board analysis or artificial intelligence capabilities. These devices may include sensors, drivers, and internet of things gateways. By directly processing a certain amount of data on the intelligent edge device, rather than uploading, processing and storing the data on the cloud, the enterprise can increase efficiency and reduce cost.
The digital twin space comprises a data center memory, a modeling module, a prediction algorithm module, a scheduling algorithm module and a simulation verification module;
the data center memory stores field device data of a sensor from a physical space and network information data in a transmission process, and the modeling module establishes a plurality of physical models according to the field device data of the sensor and the network information data in the transmission process; the prediction algorithm module is deployed with a plurality of machine learning prediction algorithm models with complete training, and data prediction is called from the data center to obtain a network running state; the scheduling algorithm module is provided with a scheduling algorithm model, and a scheduling scheme is obtained by calling data from the data center; and the simulation verification module performs simulation verification on the prediction error output by the prediction algorithm module and performs simulation verification on the scheduling scheme output by the scheduling algorithm module.
Specifically, in the initial stage, according to the transmission requirement of the physical space, the scheduling algorithm module can generate an initialization scheduling scheme in the digital twin space; in a real-time stage, the prediction algorithm module predicts a network running state in a digital twin space according to real-time data of a physical space; after obtaining the network operation state, verifying the prediction error, namely whether the predicted network operation state parameter and the actual network operation state parameter meet the first communication requirement or not through a simulation verification module, if so, maintaining the scheduling scheme of the previous stage, and otherwise, executing a scheduling algorithm model to generate a real-time scheduling scheme; the simulation verification module can also be used for verifying whether the initialized scheduling scheme or the real-time scheduling scheme meets the second communication requirement, if the initialized scheduling scheme or the real-time scheduling scheme does not meet the second communication requirement, the scheduling algorithm model is executed to regenerate the scheduling scheme until the regenerated scheduling scheme meets the second communication requirement; the simulation verification module outputs an initialization scheduling scheme, a real-time scheduling scheme or a regenerated scheduling scheme meeting the first communication requirement as a simulation result, and generates a control instruction to be mapped into a physical space based on the simulation result.
In some preferred embodiments, the system further comprises an edge cloud, i.e. the system comprises a cloud server, a physical space and a digital twin space;
the edge cloud is a cloud computing platform based on the core and edge computing capability of a cloud computing technology, is built on an edge infrastructure, forms an elastic cloud platform with comprehensive computing, network, storage, safety and other capabilities of edge positions, and forms an end-to-end technical framework of 'cloud edge end three-body cooperation' with a central cloud and an Internet of things terminal.
It will be appreciated that in the embodiments of the present invention, descriptions of the edge device intelligent gateway, the wireless network gateway device, these gateway devices and other communication necessary devices not pointed out are omitted, and those skilled in the art may make corresponding designs or settings according to practical situations.
In a preferred embodiment of the present invention, the edge cloud is used for data storage and auxiliary computation, and the edge cloud can be used as an auxiliary device for physical space and digital twin space. Specifically, the edge cloud long-term storage wireless sensor network data includes: the wireless sensor network system scheduling table, network topology information, network node state information and link communication parameter network real-time data; and analyzing the wireless sensor network data stored for a long time, and being used for assisting the digital space to calculate the network real-time state data.
Fig. 2 is a schematic flow chart of a wireless sensor network resource scheduling method based on digital twinning in an embodiment of the invention, and the method includes:
the edge equipment collects field equipment data of the sensor and network information data in the transmission process through a wireless network, and builds a physical space and a digital twin space of the wireless sensor network;
in this embodiment, on the one hand, the edge device needs to collect data, and on the other hand, the edge device intelligent gateway needs to preprocess the collected data.
The acquisition process comprises the following steps:
1) The wireless sensor network node adapts to a sensor transmission protocol, reads sensor data and uploads the sensor data to the edge equipment through the wireless network;
2) And running the upper computer software of the wireless sensor network on the edge equipment, and reading network information data such as a wireless sensor network system schedule, network topology information, network node state information, link communication parameters and the like, and system field environment data such as system equipment position information and the like.
The preprocessing process comprises the processes of data cleaning, feature extraction, data analysis and the like on the collected data in the edge equipment.
In this embodiment, the physical space of the wireless sensor network is built, that is, the corresponding physical model is built according to the transmission relations of the sensor, the wireless network and the edge device.
In this embodiment, the digital twin space of the wireless sensor network is that the digital twin space which is the same as the physical space is built according to the data transmitted by the physical space, where the process of building the digital twin space of the wireless sensor network includes:
extracting the attribute of each sensor device in the field device data, and obtaining the relation between the type of the sensor device and the sensor device; constructing a digital model by using a modeling language such as unified modeling language (Unified Modeling Language, UML), system modeling language (Systems Modeling Language, sysML), automated markup language (Automation Markup Language, automationML) and the like, standardizing the constructed digital model by using tools such as opcua-model and the like, defining input and output ends of each physical model forming module in the digital model, and completing interaction between each physical model and mapping with a physical space; the digital model is updated and a digital twin space is formed by sensing physical space real-time data, namely field device data of the sensor and network information data in the transmission process, and real-time synchronization of the physical space and the digital twin space is maintained.
Wherein the physical model mainly comprises: in-situ physical device model, network model, flow model, channel model and the like, for network data collected by edge devices, establishing a network model according to an undirected graph of G= (V, E), wherein V= { n 0 ，n 1 ，n 2 ，...，n i -representing a set of network nodes, e (n) j ，n k ) E represents the communication link of any two nodes in the network; for network traffic, the network traffic model is built according to a queuing model of queuing theory, as shown in fig. 3, and is a network with n nodes, each corresponding to a queue, capable of implementing (n-1) hops. Data packet source in queueIs divided into two parts: the nodes themselves collect data and forward the underlying node data. The arrival time interval of the data packet obeys the negative exponential distribution with the parameter lambda, the service time of the communication resource is mutually independent, and the negative exponential distribution with the parameter mu is satisfied; for wireless network communication frequencies, the IEEE802.15.4 standards 868MHz, 915MHz, and 2.4GHz bands are employed for a total of 27 channels.
Deploying a plurality of machine learning prediction algorithm models which are trained in a digital twin space, and establishing a scheduling algorithm model according to a wireless sensing network;
for the predictive algorithm model, in the present embodiment, a plurality of machine learning predictive algorithm models, such as LS-SVM, catboost, lightGBM, etc., are deployed in digital twin space with sufficient running space. The trained prediction algorithm model is embedded into a digital twin space, the running state of the network is predicted according to the prediction algorithm models, and the optimal solution can be obtained through simulation prediction.
For the scheduling algorithm model, in this embodiment, the scheduling algorithm model is built in the digital twin space according to the characteristics of network structure, flow and bandwidth, and the flow model of the undirected graph of g= (V, E) can output a scheduling scheme according to the queue model. In addition, based on the wireless sensor network flow model, the scheduling scheme is optimized by using a heuristic algorithm, which comprises the following steps: graph coloring, nearby allocation, and game theory.
For example, in a digital twin space, parameters such as the number of data packets arriving in unit time, the number of data packets processed in unit time of a node, the number of communication resources and the size of a buffer area are input according to the M/M/s/K queue model principle, the node queue length probability, the data packet loss probability, the average buffer queue length, the average occupied resource number and the like are output, and resource scheduling is realized in the digital space. The M/M/s/K queue model based on queuing theory deploys a scheduling algorithm according to the following principle:
(1) For any state n there is:
therefore, the probability distribution p of the captain after the network node reaches the equilibrium state is obtained n The method comprises the following steps:
wherein the buffer queue idle probability p 0 The method comprises the following steps:
wherein, the liquid crystal display device comprises a liquid crystal display device,
as the service strength, the packet loss probability pK can be calculated therefrom;
(2) According to probability distribution p of team leader after equilibrium n N=0, 1..k, the average buffer queue length can be found:
according to
The average buffer queue length is calculated as:
(3) Because the M/M/s/K queue model is a service desk system, the effective arrival rate lambda of customers e The method meets the following conditions: lambda (lambda) e ＝λ(1-p K ) The method comprises the steps of carrying out a first treatment on the surface of the According to a queuing theory basic formula Little formula, the method comprises the following steps:
wherein W is s Mean residence time for data packets, W q The latency is averaged for the data packet. The average number of occupied scheduling blocks is:
in this embodiment, the edge device obtains the transmission requirement and real-time operation data of the wireless sensor network, executes the wireless sensor network resource scheduling flow based on digital twin, and verifies the scheduling scheme and analyzes the feasibility in the digital twin space simulation, and specifically includes the following steps:
s41: according to the real-time and deterministic requirements of the physical space wireless sensor network, determining the input parameters of the adopted resource scheduling algorithm model, and initializing a scheduling scheme in a digital twin space;
in one embodiment, specifically, according to the requirements of real-time performance and certainty of the physical space wireless sensor network, node data packet arrival rate and data packet processing rate are input to a scheduling algorithm of a digital space based on an M/M/s/K queue model through real-time data perception, a scheduling scheme is initialized to output scheduling basis such as data packet loss probability, buffer queue idle probability, average buffer queue length and average occupied resource number, and whether scheduling is executed is determined by comparing a set threshold.
S42: verifying whether the initial scheduling scheme meets the second communication requirement, if not, regenerating the scheduling scheme, otherwise, generating a control instruction to be mapped to a physical space;
s43: predicting the network operation state according to real-time data (including flow change, scheduling table, topology information, node electric quantity, signal strength, data queue cache and the like) of the wireless sensor network in the digital twin space of the wireless sensor network in the physical space;
s44: whether the duty ratio, the transmission success rate, the end-to-end delay and the like meet the first communication requirement is predicted in the digital twin space through simulation verification, if so, a scheduling scheme is maintained, otherwise, the scheduling scheme is regenerated;
s45: cycling the scheduling scheme and the simulation verification step of the digital space regeneration until the first communication requirement and the second communication requirement of the simulation are met;
s46: generating a control instruction to map to a physical space, and monitoring whether the operation of a physical space network meets the requirement in real time;
s47: if the physical space wireless network operation does not meet the third communication requirement, comparing the updated system data and the real-time data with the digital twin space data to determine whether the digital space model needs to be updated, and then regenerating the scheduling scheme operation step S45.
In other embodiments, the scheduling process is divided into an initial stage and a real-time stage, wherein the initial stage is an initial scheduling stage, and the node data packet arrival rate and the data packet processing rate of the current stage are known in the stage, so that the initial scheduling scheme of the initial stage can be obtained only by directly calling a scheduling algorithm model; in the real-time stage, the arrival rate of the node data packet and the processing rate of the data packet in the subsequent stage can be predicted by using the prediction algorithm model, so that the scheduling scheme in the real-time stage is obtained by combining the prediction algorithm model and the scheduling algorithm model.
In the initial stage, executing a scheduling algorithm model in a digital twin space according to the transmission requirement of a physical space to obtain an initialization scheduling scheme;
in a real-time stage, according to real-time data of a physical space, a prediction algorithm model is executed in a digital twin space to predict and obtain a network running state; verifying whether the prediction error meets the first communication requirement in the digital twin space through simulation, if so, maintaining the scheduling scheme of the previous stage, otherwise, executing a scheduling algorithm model to generate a real-time scheduling scheme;
simulation verification is carried out to verify whether the initialized scheduling scheme or the real-time scheduling scheme meets the second communication requirement, if the initialized scheduling scheme or the real-time scheduling scheme does not meet the second communication requirement, the scheduling algorithm model is executed to regenerate the scheduling scheme until the regenerated scheduling scheme meets the second communication requirement;
mapping the control instruction generated by the initialization scheduling scheme, the real-time scheduling scheme or the regenerated scheduling scheme meeting the second communication requirement to a physical space by using the scheduling scheme meeting the first communication requirement at the previous stage;
the physical space issues control instructions to the edge equipment to complete resource scheduling.
Specifically, after the edge device in the physical space receives the control instruction, the network management instruction is encapsulated according to the wireless sensor network protocol, and the resource scheduling is realized by adopting a centralized resource scheduling method and adopting information such as a modified scheduling table.
It can be understood that in the embodiment of the invention, the edge device needs to feed back the running state of the physical space in real time, so as to realize the interactive mapping of the physical space and the digital space, and the scheduling process shown in fig. 3 is circularly operated to ensure reasonable resource allocation of the wireless sensor network.
Wherein the drawings are for illustrative purposes only and are shown in schematic, non-physical, and not intended to limit the invention; for the purpose of better illustrating embodiments of the invention, certain elements of the drawings may be omitted, enlarged or reduced and do not represent the size of the actual product; it will be appreciated by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The same or similar reference numbers in the drawings of embodiments of the invention correspond to the same or similar components; in the description of the present invention, it should be understood that, if there are terms such as "upper", "lower", "left", "right", "front", "rear", etc., that indicate an azimuth or a positional relationship based on the azimuth or the positional relationship shown in the drawings, it is only for convenience of describing the present invention and simplifying the description, but not for indicating or suggesting that the referred device or element must have a specific azimuth, be constructed and operated in a specific azimuth, so that the terms describing the positional relationship in the drawings are merely for exemplary illustration and should not be construed as limiting the present invention, and that the specific meaning of the above terms may be understood by those of ordinary skill in the art according to the specific circumstances.
Edge device
In the description of the present invention, it should be understood that the terms "coaxial," "bottom," "one end," "top," "middle," "another end," "upper," "one side," "top," "inner," "outer," "front," "center," "two ends," etc. indicate or are based on the orientation or positional relationship shown in the drawings, merely to facilitate description of the invention and simplify the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the invention.
In the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "configured," "connected," "secured," "rotated," and the like are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; either directly or indirectly through intermediaries, or in communication with each other or in interaction with each other, unless explicitly defined otherwise, the meaning of the terms described above in this application will be understood by those of ordinary skill in the art in view of the specific circumstances.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (6)
1. The method for scheduling the wireless sensor network resources based on the digital twinning is characterized by comprising the following steps:
the edge equipment collects field equipment data of the sensor and network information data in the transmission process through a wireless network and preprocesses the field equipment data and the network information data, and a physical space and a digital twin space of the wireless sensor network are built;
the edge equipment acquires field equipment data of a sensor and network information data in a transmission process through a wireless network, preprocesses the field equipment data and the network information data, wherein the field equipment data comprise sensor transmission protocols adapted to all nodes in the wireless sensor network, reads the field equipment data of the sensor, uploads the field equipment data to the edge equipment through the wireless network, runs a wireless sensor network upper computer on the edge equipment, and reads network information data comprising a wireless sensor network system schedule, network topology information, network node state information and link communication parameters; cleaning, analyzing and extracting features of the data in the edge equipment;
the process of constructing the digital twin space of the wireless sensor network comprises the steps of extracting the attribute of each sensor device in the data of the field devices, and obtaining the relation between the type of the sensor device and the sensor device; constructing a digital model by using a modeling language, standardizing the constructed digital model, defining input and output ends of each physical model forming module in the digital model, and finishing interaction between each physical model and mapping with a physical space; the digital model is updated and a digital twin space is formed by sensing physical space real-time data, namely field device data of the sensor and network information data in the transmission process, and real-time synchronization of the physical space and the digital twin space is maintained;
deploying a plurality of machine learning prediction algorithm models which are trained in a digital twin space, and establishing a scheduling algorithm model according to a wireless sensing network;
in the initial stage, executing a scheduling algorithm model in a digital twin space according to the transmission requirement of a physical space to obtain an initialization scheduling scheme;
in a real-time stage, according to real-time data of a physical space, a prediction algorithm model is executed in a digital twin space to predict and obtain a network running state; verifying whether the prediction error meets the first communication requirement in the digital twin space through simulation, if so, maintaining the scheduling scheme of the previous stage, otherwise, executing a scheduling algorithm model to generate a real-time scheduling scheme;
simulation verification is carried out to verify whether the initialized scheduling scheme or the real-time scheduling scheme meets the second communication requirement, if the initialized scheduling scheme or the real-time scheduling scheme does not meet the second communication requirement, the scheduling algorithm model is executed to regenerate the scheduling scheme until the regenerated scheduling scheme meets the second communication requirement;
and mapping the control instruction generated by the initialization scheduling scheme, the real-time scheduling scheme or the regenerated scheduling scheme meeting the first communication requirement to the edge equipment in the physical space, and completing resource scheduling by the edge equipment.
2. The wireless sensor network resource scheduling method based on digital twinning according to claim 1, wherein the physical model comprises a sensor device model, a network model, a flow model and a channel model.
3. The wireless sensor network resource scheduling method based on digital twinning according to claim 1, wherein the method further comprises monitoring whether the physical space network operation meets a third communication requirement in real time, if not, updating system data and real-time data, and comparing the digital twinning space data to determine whether to update the digital twinning space; and executing a scheduling algorithm to regenerate a scheduling scheme in the updated digital twin space.
4. The method for scheduling the wireless sensor network resources based on the digital twin system according to claim 1, wherein the generated control instruction is mapped to the edge equipment in the physical space, and the completion of the resource scheduling of the edge equipment comprises the steps that after the edge equipment in the physical space receives the control instruction, the network management instruction is packaged according to the wireless sensor network protocol, and the resource scheduling is completed by adopting the centralized resource scheduling method.
5. The wireless sensor network resource scheduling system based on digital twinning is characterized by comprising a physical space and a digital twinning space;
the physical space comprises edge equipment, a wireless network and a sensor; the edge device collects field device data of the sensor and network information data in the transmission process through the wireless network; the edge device issues a control instruction to the wireless network to complete resource scheduling;
the digital twin space comprises a data center memory, a modeling module, a prediction algorithm module, a scheduling algorithm module and a simulation verification module; the data center memory stores field device data of a sensor from a physical space and network information data in a transmission process, and the modeling module establishes a plurality of physical models according to the field device data of the sensor and the network information data in the transmission process; the prediction algorithm module is deployed with a plurality of machine learning prediction algorithm models with complete training, and data prediction is called from the data center to obtain a network running state; the scheduling algorithm module is provided with a scheduling algorithm model, and a scheduling scheme is obtained by calling data from the data center; the simulation verification module performs simulation verification on the prediction error output by the prediction algorithm module and performs simulation verification on the scheduling scheme output by the scheduling algorithm module;
in the initial stage, according to the transmission requirement of a physical space, executing a scheduling algorithm model in a digital twin space to obtain an initialization scheduling scheme;
in a real-time stage, according to real-time data of a physical space, a prediction algorithm model is executed in a digital twin space to predict and obtain a network running state; verifying whether the prediction error meets the first communication requirement in the digital twin space through simulation, if so, maintaining the scheduling scheme of the previous stage, otherwise, executing a scheduling algorithm model to generate a real-time scheduling scheme;
simulation verification is carried out to verify whether the initialized scheduling scheme or the real-time scheduling scheme meets the second communication requirement, if the initialized scheduling scheme or the real-time scheduling scheme does not meet the second communication requirement, the scheduling algorithm model is executed to regenerate the scheduling scheme until the regenerated scheduling scheme meets the second communication requirement;
and mapping the control instruction generated by the initialization scheduling scheme, the real-time scheduling scheme or the regenerated scheduling scheme meeting the first communication requirement to the edge equipment in the physical space, and completing resource scheduling by the edge equipment.
6. The digital twinning-based wireless sensor network resource scheduling system of claim 5, further comprising an edge cloud that stores wireless sensor network data over a long period of time, comprising: the wireless sensor network system scheduling table, network topology information, network node state information and link communication parameter network real-time data; and analyzing the wireless sensor network data stored for a long time, and being used for assisting the digital space to calculate the network real-time state data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111048000.5A CN113810953B (en) | 2021-09-08 | 2021-09-08 | Wireless sensor network resource scheduling method and system based on digital twinning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111048000.5A CN113810953B (en) | 2021-09-08 | 2021-09-08 | Wireless sensor network resource scheduling method and system based on digital twinning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113810953A CN113810953A (en) | 2021-12-17 |
| CN113810953B true CN113810953B (en) | 2023-06-27 |
Family
ID=78940541
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111048000.5A Active CN113810953B (en) | 2021-09-08 | 2021-09-08 | Wireless sensor network resource scheduling method and system based on digital twinning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113810953B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115086198B (en) * | 2022-04-14 | 2023-11-03 | 安世亚太科技股份有限公司 | Reliability analysis method and system based on network digital twin |
| CN115086202B (en) * | 2022-04-14 | 2023-06-20 | 安世亚太科技股份有限公司 | Time delay analysis method and system based on network digital twin |
| CN114520781B (en) * | 2022-04-21 | 2022-09-30 | 中国科学技术大学 | Network technology and protocol testing platform based on digital twinning and testing method thereof |
| CN115983536A (en) * | 2022-04-24 | 2023-04-18 | 重庆邮电大学工业互联网研究院 | Emergency police force scheduling method and system based on digital twin |
| CN115190074B (en) * | 2022-06-08 | 2024-03-22 | 安世亚太科技股份有限公司 | Resource management method based on network digital twin |
| CN117440417A (en) * | 2022-07-15 | 2024-01-23 | 中兴通讯股份有限公司 | Network prediction system, method, electronic device and storage medium |
| CN115361663A (en) * | 2022-08-09 | 2022-11-18 | 广州天环信息技术有限公司 | Wireless sensor network deployment method |
| TR2022014285A2 (en) * | 2022-09-15 | 2022-10-21 | Bts Kurumsal Bilisim Teknolojileri Anonim Sirketi | Digital twin-based interference reduction system and method in local autonomous networks with dense access points |
| CN115604725B (en) * | 2022-11-03 | 2024-04-19 | 中国联合网络通信集团有限公司 | Method and device for determining propagation loss and storage medium |
| CN115883464A (en) * | 2022-11-30 | 2023-03-31 | 广州地铁设计研究院股份有限公司 | Digital twin optical network flow regulation and control system and flow regulation and control method |
| CN116506352B (en) * | 2023-06-26 | 2023-08-29 | 安世亚太科技股份有限公司 | Network data continuing forwarding selection method based on centralized reinforcement learning |
| CN117453398A (en) * | 2023-10-27 | 2024-01-26 | 国网江苏省电力有限公司南通供电分公司 | Intelligent optimization method and system for power calculation scheduling for improving power supply reliability |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108040081A (en) * | 2017-11-02 | 2018-05-15 | 同济大学 | A kind of twin monitoring operational system of subway station numeral |
| CN111523277A (en) * | 2020-05-19 | 2020-08-11 | 珠海格力电器股份有限公司 | Fire prediction method, storage device and processor |
| CN111857065A (en) * | 2020-06-08 | 2020-10-30 | 北京邮电大学 | Intelligent production system and method based on edge calculation and digital twinning |
| CN112534452A (en) * | 2018-05-06 | 2021-03-19 | 强力交易投资组合2018有限公司 | Method and system for improving machines and systems for automatically performing distributed ledger and other transactions in spot and forward markets for energy, computing, storage, and other resources |
| CN112637276A (en) * | 2020-12-08 | 2021-04-09 | 电子科技大学 | Multi-user computing migration method based on digital twin technology |
| CN112818490A (en) * | 2021-03-18 | 2021-05-18 | 中国人民解放军陆军工程大学 | Cloud-edge-architecture equipment digital twin parallel simulation system and method |
| WO2021108680A1 (en) * | 2019-11-25 | 2021-06-03 | Strong Force Iot Portfolio 2016, Llc | Intelligent vibration digital twin systems and methods for industrial environments |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10977153B1 (en) * | 2019-11-01 | 2021-04-13 | EMC IP Holding Company LLC | Method and system for generating digital twins of resource pools and resource pool devices |
-
2021
- 2021-09-08 CN CN202111048000.5A patent/CN113810953B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108040081A (en) * | 2017-11-02 | 2018-05-15 | 同济大学 | A kind of twin monitoring operational system of subway station numeral |
| CN112534452A (en) * | 2018-05-06 | 2021-03-19 | 强力交易投资组合2018有限公司 | Method and system for improving machines and systems for automatically performing distributed ledger and other transactions in spot and forward markets for energy, computing, storage, and other resources |
| WO2021108680A1 (en) * | 2019-11-25 | 2021-06-03 | Strong Force Iot Portfolio 2016, Llc | Intelligent vibration digital twin systems and methods for industrial environments |
| CN111523277A (en) * | 2020-05-19 | 2020-08-11 | 珠海格力电器股份有限公司 | Fire prediction method, storage device and processor |
| CN111857065A (en) * | 2020-06-08 | 2020-10-30 | 北京邮电大学 | Intelligent production system and method based on edge calculation and digital twinning |
| CN112637276A (en) * | 2020-12-08 | 2021-04-09 | 电子科技大学 | Multi-user computing migration method based on digital twin technology |
| CN112818490A (en) * | 2021-03-18 | 2021-05-18 | 中国人民解放军陆军工程大学 | Cloud-edge-architecture equipment digital twin parallel simulation system and method |
Non-Patent Citations (2)
| Title |
|---|
| Yunlong Lu ; et al.Communication-efficient federated learning for digital twin edge networks in industrial IOT.《IEEE transactions on industrial informatics》.2020,全文. * |
| 数字孪生模型构建理论及应用;陶飞；et al;《计算机集成制造系统》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113810953A (en) | 2021-12-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113810953B (en) | Wireless sensor network resource scheduling method and system based on digital twinning | |
| Lei et al. | Toward intelligent cooperation of UAV swarms: When machine learning meets digital twin | |
| Dai et al. | Adaptive digital twin for vehicular edge computing and networks | |
| CN103118439B (en) | based on the data fusion method of sensor network node universal middleware | |
| Fadlullah et al. | Value iteration architecture based deep learning for intelligent routing exploiting heterogeneous computing platforms | |
| Wang et al. | Mobility-aware partial computation offloading in vehicular networks: A deep reinforcement learning based scheme | |
| Billet et al. | From task graphs to concrete actions: a new task mapping algorithm for the future internet of things | |
| Jamil et al. | IRATS: A DRL-based intelligent priority and deadline-aware online resource allocation and task scheduling algorithm in a vehicular fog network | |
| Xu et al. | RJCC: Reinforcement-learning-based joint communicational-and-computational resource allocation mechanism for smart city IoT | |
| Munir et al. | Intelligent service fulfillment for software defined networks in smart city | |
| CN113341712B (en) | Intelligent hierarchical control selection method for unmanned aerial vehicle autonomous control system | |
| Huang et al. | Toward decentralized and collaborative deep learning inference for intelligent IoT devices | |
| Qi et al. | Vehicular edge computing via deep reinforcement learning | |
| Hazarika et al. | RADiT: Resource allocation in digital twin-driven UAV-aided internet of vehicle networks | |
| Xia et al. | A delay-tolerant data transmission scheme for internet of vehicles based on software defined cloud-fog networks | |
| Ashtari et al. | Knowledge-defined networking: Applications, challenges and future work | |
| Huang | Quality of service optimization in wireless transmission of industrial Internet of Things for intelligent manufacturing | |
| Wang et al. | Cooperative channel assignment for VANETs based on multiagent reinforcement learning | |
| Xu et al. | Digital twin-driven collaborative scheduling for heterogeneous task and edge-end resource via multi-agent deep reinforcement learning | |
| Ergun et al. | A survey on how network simulators serve reinforcement learning in wireless networks | |
| CN113821346A (en) | Computation uninstalling and resource management method in edge computation based on deep reinforcement learning | |
| Costa et al. | Planning and resource allocation of a hybrid IoT network using artificial intelligence | |
| Meng et al. | Intelligent routing orchestration for ultra-low latency transport networks | |
| Moghaddasi et al. | An enhanced asynchronous advantage actor-critic-based algorithm for performance optimization in mobile edge computing-enabled internet of vehicles networks | |
| Wang et al. | Joint offloading decision and resource allocation in vehicular edge computing networks |
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 |