CN114285880B - Intelligent method for lightweight equipment of Internet of things based on enhanced twinning - Google Patents
Intelligent method for lightweight equipment of Internet of things based on enhanced twinning Download PDFInfo
- Publication number
- CN114285880B CN114285880B CN202111615461.6A CN202111615461A CN114285880B CN 114285880 B CN114285880 B CN 114285880B CN 202111615461 A CN202111615461 A CN 202111615461A CN 114285880 B CN114285880 B CN 114285880B
- Authority
- CN
- China
- Prior art keywords
- node
- enhanced
- resource
- twin
- matching
- 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
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 16
- 230000002068 genetic effect Effects 0.000 claims abstract description 10
- 238000010276 construction Methods 0.000 claims description 49
- 230000005540 biological transmission Effects 0.000 claims description 31
- 238000003860 storage Methods 0.000 claims description 24
- 210000000349 chromosome Anatomy 0.000 claims description 22
- 238000004891 communication Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000002708 enhancing effect Effects 0.000 claims description 9
- 239000012634 fragment Substances 0.000 claims description 4
- 230000006978 adaptation Effects 0.000 abstract description 5
- 230000006870 function Effects 0.000 description 17
- 238000012545 processing Methods 0.000 description 13
- 230000009286 beneficial effect Effects 0.000 description 10
- 238000004458 analytical method Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 5
- 230000008447 perception Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000000556 factor analysis Methods 0.000 description 2
- 238000005469 granulation Methods 0.000 description 2
- 230000003179 granulation Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 210000002383 alveolar type I cell Anatomy 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
Images
Classifications
-
- 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
- Data Exchanges In Wide-Area Networks (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an intelligent method of an Internet of things light-weight device based on enhanced twinning, which comprises the steps of collecting original data through each light-weight device, uploading the original data to a Sink node, obtaining an initialized enhanced twinning matching state, performing enhanced twinning matching based on the Sink node, obtaining an enhanced twinning matching node based on the Sink node, and calculating total time delay of the enhanced twinning matching node; performing enhanced twin matching based on the resource-rich equipment node on the residual enhanced twin matching state after Sink node matching by using a matching solving algorithm based on a genetic algorithm to obtain an optimal matching solution of the resource-rich equipment node; combining the total time delay of the enhanced twin matching node based on Sink node to obtain a global optimal solution; the invention provides a low-cost intelligent enhancement method for lightweight equipment of the Internet of things, which is used for constructing an enhancement twin body for the lightweight equipment on nodes with surplus resources in the Internet of things and improving the intelligence, the coordination capability and the application adaptation capability of the lightweight equipment.
Description
Technical Field
The invention relates to the field of Internet of things, in particular to an intelligent method for lightweight equipment of the Internet of things based on enhanced twinning.
Background
In recent years, the internet of things is rapidly raised and widely applied, wherein the intelligent evolution of the internet of things is one of the key directions of the current development of the internet of things, and through the intelligent evolution, the internet of things can provide more accurate, intelligent and flexible services according to the environment and application requirements.
Currently, there are two main ways of intelligent upgrade to the internet of things equipment:
the first is to directly upgrade hardware, and upgrade all non-intelligent devices to intelligent devices with strong computing, storage and other capabilities. The method has high cost and long period, and along with the development speed of software and hardware, the method also needs to be replaced frequently and has huge reconstruction cost.
The second is to keep the current equipment and update the software intelligently based on the existing equipment. The method is that a software module (middleware) with intelligent analysis and processing capability is added on the current equipment, and the current equipment is intelligently controlled to carry out intelligent analysis and processing through preset logic of software. But this approach is heavily dependent on the resource richness of the existing devices. For the Internet of things equipment with rich resources, the intelligent upgrading of the Internet of things equipment is only a time problem. However, the device composition of the internet of things has a large difference, and a large number of lightweight devices exist, and the devices can only perform basic sensing and data transmission functions and cannot support the resource overhead of intelligent evolution.
Considering that the quantity of the light-weight equipment in the Internet of things is very large, the overall ratio is high, if the intelligent evolution or enhancement can be carried out on the equipment, so that better analysis, system and decision-making capability can be realized, the intelligence of the whole Internet of things can be leaved, and the performance and efficiency of the application of the Internet of things can be improved essentially. However, as shown by the previous analysis, the lightweight device in the internet of things has high hardware upgrading cost and excessive cost; the resources required for the software upgrade are insufficient and difficult to implement.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides an intelligent method for the lightweight equipment of the Internet of things based on enhanced twinning, which constructs an enhanced twinning body with intelligent analysis and processing capability for the lightweight equipment on nodes with redundant internal resources of the Internet of things, improves the intelligence, the cooperative capability and the application adaptation capability of the lightweight equipment, enhances the intelligence of the lightweight equipment, expands the intelligent evolution of the Internet of things and diversifies application types.
In order to achieve the aim of the invention, the invention adopts the following technical scheme:
the invention provides an intelligent method for an Internet of things light-weight device based on enhanced twinning, which comprises the following steps:
S1, acquiring original data through each light-weight device, and uploading the original data to a Sink node to obtain an initialized enhanced twin matching state;
s2, carrying out enhanced twin matching of light-weight equipment on the initialized enhanced twin matching state based on the resource limitation of the Sink node to obtain an enhanced twin matching node based on the Sink node;
s3, calculating the total time delay of the enhanced twin matching node based on the Sink node;
s4, utilizing a matching solving algorithm based on a genetic algorithm, and carrying out enhanced twin matching based on the resource surplus type equipment nodes according to the initialized enhanced twin matching state remained after the enhanced twin matching in the step S2 to obtain an optimal matching solution of the resource surplus type equipment nodes;
and S5, calculating a global optimal solution based on enhanced twinning according to the total time delay of the optimal solution matched with the resource surplus type equipment node and the enhanced twinning matched node based on the Sink node.
Preferably, step S2 is specifically:
under the condition of limiting the resources based on Sink nodes, the initialized enhanced twin matching state is matched with the lightweight equipment nodes according to the sequence of perceived data volume from high to low under the same service priority from highest priority to lowest priority according to the service priority of the lightweight equipment.
The beneficial effect of this preferred scheme is:
the data convergence and business totipotency of Sink nodes in the Internet of things are fully utilized. The Sink node is used as a data Sink node in the Internet of things, the perceived data acquired by the LD can be converged and forwarded to a data destination, and the Sink node is used as a first building part for enhancing twinning to avoid communication overhead caused by repeated transmission of the acquired data; because the Sink node has more data types and more comprehensive covered services, the Sink can effectively support the enhanced twin construction of multiple services.
Preferably, the resource limitation based on Sink node in step S2 specifically includes:
communication resource constraint on Sink node:
sink storage limit:
sink computational power limitation:
wherein C is S Computing resources are available for a single cycle of Sink nodes; r is R S The transmission capacity required for Sink nodes for enhancing twin construction is increased; sigma (sigma) S To store a load threshold; s is S S (t) is real-time available storage capacity of Sink nodes; m is the total number of LD nodes of the lightweight equipment;
for enhancing twinning in a single cycleGenerating the calculated amount required by construction; />
The amount of update data generated within a single cycle for a lightweight device LD node; alpha is the total number of periods, t is a time variable; / >
Is a lightweight device LD node->
A characteristic value R for judging whether the enhanced twin is established on the Sink node l For every lightweight device LD node in the cycle +.>
Available transmission capacity, < >>
Is a lightweight device LD node->
To enhance the fixed storage resources required to be occupied by the twinning itself.
The beneficial effect of this preferred scheme is:
the practical feasibility and the high efficiency of the invention are ensured, and the resource requirements of the enhanced twin construction are met to the greatest extent by considering the various resource requirements of the enhanced twin construction and the resource limitations of the Sink node.
Preferably, the total time delay calculation formula of the Sink node-based enhanced twin matching node in step S3 is expressed as follows:
wherein,,
for the total time delay of the enhanced twin matching node based on Sink node in a single period, +.>
For updating data in a single period from a lightweight device node +.>
Multi-hop transmission delay to Sink node, < >>
Lightweight device node in a single cycle>
Propagation delay required to Sink node, < >>
Is a lightweight device node for Sink nodes in a single period +.>
The computation delay required to build the enhanced twinning, m is the number of lightweight devices.
The beneficial effect of this preferred scheme is:
The construction time delay of the enhanced twin is analyzed by granulation, so that the efficiency of enhancing twin matching is improved pertinently. Component analysis is carried out on the constructed time delay, factor analysis can be carried out on the component components of the constructed time delay, the influence factors which can be optimized are found, and the enhancement twin-generation matching efficiency can be improved by optimizing the influence factors.
Preferably, step S4 comprises the following sub-steps:
s41, performing primary matching on the rest initialized enhanced twin matching states after the Sink node-based enhanced twin matching nodes are screened by utilizing service matching constraint conditions to obtain a target set of matching of the light-weight equipment nodes after primary matching to the resource-rich equipment nodes;
s42, performing chromosome coding on the target set to obtain a plurality of chromosome fragments;
s43, initializing the population of the chromosome segments based on the resource limitation of the resource-rich equipment nodes;
s44, constructing an fitness function, and selecting the parent with the highest fitness value to perform chromosome crossing to obtain a new population;
s45, judging whether the resource capacity of the current population exceeds the resource limit of the resource-rich equipment node, and if so, returning to the step S44; otherwise, outputting the optimized new population, and proceeding to step S46;
S46, judging whether the iteration times meet preset times, and if so, ending the iteration; obtaining an optimal matching solution of the resource surplus type equipment nodes; otherwise, the current population is taken as the latest parent and the step S44 is returned.
The beneficial effect of this preferred scheme is:
because the resource surplus type equipment nodes and the light-weight type equipment are in a many-to-many complex relationship, the matching schemes of the resource surplus type equipment nodes and the light-weight type equipment cannot be directly obtained, the optimal matching scheme is obtained through multiple evolutions of a genetic algorithm, and the NPL problem is solved efficiently.
Preferably, the expression of the service matching constraint in step S41 is:
wherein,,
is a lightweight device node->
For determining whether enhanced twinning is established at the resource-rich device node>
The characteristic value of the upper part; />
Is single in natureA service k feature vector supported by a lightweight equipment node of a service; />
And the characteristic vector of the service k supported by the lightweight equipment section of the non-omnipotent service is q, the total service quantity supported by the enhanced twinning is q, n is the quantity of the resource-rich equipment, and m is the quantity of the lightweight equipment.
The beneficial effect of this preferred scheme is:
considering the practical service limitation of the non-omnipotent resource surplus equipment, differentiating the resource surplus equipment, constructing an enhanced twin network in an enhanced twin construction distributed form according to service matching constraint conditions, realizing the balanced distribution of the service in the network, and guaranteeing the practical feasibility of the invention.
Preferably, the expression of the fitness function in step S44 is:
wherein x is y Is chromosome, f (x y ) In order to adapt the function of the degree of adaptation,
lightweight device node in a single cycle>
In the resource-rich device node->
The total delay of the enhanced twinning is constructed, n is the number of the resource-rich devices, and m is the number of the light-weight devices. The beneficial effect of this preferred scheme is:
the gradual trend of constructing an enhanced twin scheme on the resource surplus equipment is optimized. Taking the reciprocal of the construction time delay of completing construction of all the enhanced twins on the resource-rich equipment as an adaptability function, the chromosome with smaller construction time delay can be easily reserved and evolved, so that the construction time delay of constructing the enhanced twins scheme on the resource-rich equipment is ensured to be towards the minimum value, and the optimal solution of the invention is obtained.
Preferably, the total time delay of the lightweight device node in a single cycle in step S44 to construct enhanced twinning at the resource-rich device node is expressed as:
wherein,,
for updating data in a single period from a lightweight device node +.>
To resource-rich equipment node
Multi-hop transmission delay of->
Lightweight device node in a single cycle>
To the resource-rich device node- >
The required propagation delay +.>
For a resource-rich device node within a single period +.>
Is a lightweight device node->
Construction of the augmentationThe computational delay required for strong twinning.
The beneficial effect of this preferred scheme is:
the construction time delay of the enhanced twin is analyzed by granulation, so that the efficiency of enhancing twin matching is improved pertinently. Component analysis is carried out on the constructed time delay, factor analysis can be carried out on the component components of the constructed time delay, the influence factors which can be optimized are found, and the enhancement twin-generation matching efficiency can be improved by optimizing the influence factors.
Preferably, the resource limitation based on the resource-rich device node in step S43 and step S45 includes:
communication resource constraint on resource-rich device nodes:
resource-rich device node storage limits:
resource-rich device node computational capability limitations:
wherein,,
for each resource-rich device node +.>
Available computing resources within each cycle; />
The amount of computation required for constructing enhanced twinning; />
Is a node of each light-weight device; r is R l Available transmission capacity for the lightweight device node in the cycle; />
Is a resource-rich device node->
Storing a load threshold; />
New data amount generated in a single period; alpha is the total number of periods, and k is a time variable; / >
For judging lightweight device node->
Whether or not enhanced twin can be established at the resource-rich device node>
Is a characteristic value of (2); />
Is a resource-rich device node->
The transmission capacity of the twin architecture can be enhanced; />
Is a lightweight device node->
The fixed storage resources occupied by the twin are enhanced; />
Is light in weightReal-time available storage capacity of the mass-storage device node; n is the total number of the nodes of the resource-rich equipment; m is the total number of lightweight device nodes.
The beneficial effect of this preferred scheme is:
the practical feasibility and the high efficiency of the invention are ensured. Considering various resource requirements of the enhanced twin construction and the resource limitation of the resource-rich device RD node, the resource requirements of the enhanced twin construction are met to the greatest extent within the range of not exceeding the self resource limitation of the resource-rich device RD node.
Preferably, the calculation expression of the global optimal solution in step S5 is:
wherein T is ATN For the total construction time delay of the enhanced twin network in a single period, T coop After the construction of each enhanced twin is completed, each enhanced twin bearing node cooperatively generates the cooperative time of the enhanced twin network in a single period,
constructing enhanced twin total time delay for light-weight equipment nodes in a single period in resource-rich equipment nodes, wherein the enhanced twin total time delay is- >
The method is characterized in that the method is the total time delay of an enhanced twin matching node based on Sink nodes in a single period, max is an extremum function, n is the number of resource-rich devices, and m is the number of lightweight devices.
The beneficial effect of this preferred scheme is:
the global optimum is ensured by the local optimum, and the intelligent evolution of the twin network is enhanced by the individual intelligent promotion and guarantee. The construction time delay obtained on the Sink node is the minimum construction time delay obtained based on the service priority of the light-weight equipment and the size of the enhanced twin construction data; the resource-rich device node obtains the minimum construction time delay of the residual lightweight device in the construction and enhancement of twinning through a genetic algorithm. The comparison of the two types of local minimum construction delays ensures the global minimum construction delay. And after all the enhanced twins are established, the enhanced twins cooperate with each other, so that the enhanced twins complete intelligent evolution.
The invention has the following beneficial effects:
collecting original data through each light-weight device, and uploading the original data to a Sink node to obtain an initialized enhanced twin matching state; performing enhanced twin matching of light-weight equipment on the initialized enhanced twin matching state based on the resource limitation of the Sink node to obtain an enhanced twin matching node based on the Sink node, and calculating the total time delay of the enhanced twin matching node based on the Sink node; meanwhile, utilizing a matching solving algorithm based on a genetic algorithm to perform enhanced twin matching based on the resource-rich equipment nodes on the initialized enhanced twin matching state remained after the enhanced twin matching in the step S2 so as to obtain an optimal matching solution of the resource-rich equipment nodes; finally, calculating a global optimal solution based on enhanced twinning according to the total time delay of the optimal solution matched with the resource surplus equipment node and the enhanced twinning matched node based on Sink node; the intelligent enhancement method for the lightweight equipment of the Internet of things is provided, an enhancement twin body with intelligent analysis and processing capacity is constructed for the lightweight equipment on nodes with redundant resources in the Internet of things, the intelligence, the coordination capacity and the application adaptation capacity of the lightweight equipment are improved, and the intelligent enhancement of the lightweight equipment, the intelligent evolution of the Internet of things and the diversified expansion of application types are facilitated.
Drawings
FIG. 1 is a flow chart of steps of an intelligent method for an Internet of things light-weight device based on enhanced twinning, which is provided by the invention;
FIG. 2 is a substep flow chart of step S4;
fig. 3 is an intelligent enhanced twin model for lightweight equipment of the internet of things, which is provided by the embodiment of the invention.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and all the inventions which make use of the inventive concept are protected by the spirit and scope of the present invention as defined and defined in the appended claims to those skilled in the art.
As shown in fig. 1, the embodiment of the invention provides an intelligent method for an internet of things light-weight device based on enhanced twinning, which comprises the following steps:
s1, acquiring original data through each light-weight device, and uploading the original data to a Sink node to obtain an initialized enhanced twin matching state;
optionally, the data required for twinning is enhanced by each lightweight device LD following the requirements of the sub-network of the internet of things, including: and uniformly uploading the acquired data information, equipment information and surrounding node communication state information to the Sink node.
Optionally, the intellectualization of the lightweight device of the internet of things based on enhanced twinning provided by the embodiment of the invention includes three types of nodes, specifically: lightweight Device nodes (Lightweight Device, LD), resource-rich Device nodes (RD), and Sink nodes; the light-weight device LD node is generally severely limited in resources, has low computing, storage and communication capabilities, and is often used for performing simple functions such as environment sensing and data acquisition. The related data of environment perception or state monitoring collected by the LD node of the light-weight equipment is called perception data; the resource-rich device RD node usually has rich resources, and can also have rich resources to provide calculation or communication services for other nodes besides completing own tasks; the Sink node is a data aggregation node in the Internet of things, and perceived data acquired by the light-weight device LD node are aggregated to the Sink node and forwarded to a data destination through the Sink node;
if a certain lightweight device LD node wants to construct enhanced twinning (AT) by means of other nodes, it is necessary to transmit not only sensing data to the counterpart but also device information (device information) of itself and connection state data (connection state) of other nodes that cooperate with each other around.
Nodes that can be used to provide enhanced twin AT build services to lightweight device LD nodes must possess spare resources, including Sink nodes and resource-spare device RD nodes. When the Sink node is used as the enhanced twin AT to construct the service providing node, as the Sink node has converged the perceived data of the light-weight device LD node, the light-weight device LD node only needs to transmit binary information < device information, connection state > -to the Sink. When the resource-rich device RD node is used as an enhanced twin AT to construct a service node, the lightweight device LD node needs to additionally transmit ternary information < perception data, device information and connection state > to the resource-rich device RD node.
S2, carrying out enhanced twin matching of light-weight equipment on the initialized enhanced twin matching state based on the resource limitation of the Sink node to obtain an enhanced twin matching node based on the Sink node;
preferably, step S2 is specifically:
under the condition of limiting the resources based on Sink nodes, the initialized enhanced twin matching state is matched with the lightweight equipment nodes according to the sequence of perceived data volume from high to low under the same service priority from highest priority to lowest priority according to the service priority of the lightweight equipment.
Optionally, the Sink node receives the traffic-priority type device LD node with the highest traffic priority according to the traffic priority, and receives the traffic-priority type device LD node with the next highest traffic priority after the traffic-priority type device LD node receives the traffic, if the traffic-priority type device LD node has the remaining resources, and so on; in addition, if the residual resources of the Sink node can only provide service for part of the volume type devices LD in a certain service priority, the perceived data volume periodically reported to the Sink node by the volume type devices LD node is sequentially selected from large to small.
Optionally, only binary information < device data, network data > needs to be transmitted to construct the enhanced twin AT based on Sink nodes, so that Sink nodes are preferentially selected as an enhanced twin AT construction service provider by all the quantity-based device LD nodes; however, due to the limited Sink node resources, enhanced twin ATs can only be built for a portion of LD nodes; the remaining quantity type device LD nodes need to construct corresponding enhanced twin ATs on other resource-rich type device RD nodes.
Preferably, the resource limitation based on Sink node in step S2 specifically includes:
communication resource constraint on Sink node:
sink storage limit:
Sink computational power limitation:
wherein C is S Computing resources are available for a single cycle of Sink nodes; r is R S The transmission capacity required for Sink nodes for enhancing twin construction is increased; sigma (sigma) S To store a load threshold; s is S S (t) is real-time available storage capacity of Sink nodes; m is the total number of LD nodes of the lightweight equipment;
the amount of computation required for enhancing twin construction in a single cycle; />
Generating an update data amount for only storing alpha periods in a single period for the light-weight device LD node; alpha is the total number of periods, t is a time variable; />
Is a lightweight device LD node->
The characteristic value for judging whether the enhanced twinning can be established on the Sink node is 1, and the value is 1, which indicates the lightweight device LD node +.>
Is built on Sink, and a value of 0 represents the lightweight device LD node +.>
Is not established on Sink; r is R l For every lightweight device LD node in the cycle +.>
Available transmission capacity, < >>
Is a lightweight device LD node
To enhance the fixed storage resources required to be occupied by the twinning itself.
Alternatively, when LD constructs AT on Sink or RD, it will follow period T data Transmitting data required for construction to a constructor, while the transmission capacity available for AT construction is limited; thus, constructing an AT for an LD by the same Sink or RD is limited, i.e., the amount of transmission data required to construct the AT cannot exceed the transmission capacity available to the AT for the corresponding Sink or RD itself;
Similarly, since LD is for each period T data Transmitting data to Sink, RD, except for the basic resources required by AT
Is not permanent but generates real-time data per cycle>
Will retain alpha periods T data . Because the available storage capacity and load threshold on Sink and RD are real-timeUpdated, arbitrary αT data The storage resources occupied by AT on each Sink and RD in the network cannot exceed the load threshold of the real-time available storage capacity;
in addition, when the Sink node and the RD node are in the traditional working state, the Sink node and the RD node can run processes occupying computing resources, and the two types of nodes are used as AT construction task unloading targets of the LDs, namely, when the two types of nodes are used as AT bearing parties of the LDs, the number of the ATs borne by the Sink node or the RD node has certain requirements on the computing resources, and each period T data The total amount of computation required for the inner bearer AT construction cannot exceed the computational resources available on the bearer side.
S3, calculating the total time delay of the enhanced twin matching node based on the Sink node;
preferably, the total time delay calculation formula of the Sink node-based enhanced twin matching node in step S3 is expressed as follows:
wherein,,
for the total time delay of the enhanced twin matching node based on Sink node in a single period, +.>
For updating data in a single period from a lightweight device node +. >
Multi-hop transmission delay to Sink node, < >>
Lightweight device node in a single cycle>
Propagation delay required to Sink node, < >>
Is a lightweight device node for Sink nodes in a single period +.>
The computation delay required to build the enhanced twinning, m is the number of lightweight devices.
Optionally, the AT construction delay mainly includes two parts, namely communication delay and calculation delay; wherein the communication delay consists of multi-hop transmission delay and propagation delay; calculating time delay, namely calculating time required by AT construction after Sink/RD receives corresponding data;
the time delay of the enhanced twin AT matching node based on the Sink node comprises the following steps:
1. multi-hop transmission delay
Each LD is in period T data The update data required for AT construction is sent to its AT bearer (Sink or RD node), which will create a certain delay from sending to reaching the AT bearer, i.e. the transmission delay in the communication. Assuming that the data does not need to be queued in the source node and the forwarding node and its processing time is ignored, then:
LD node for building AT AT Sink node
In other words, the update data thereof contains only the device information and the connection status. Wherein, the equipment information is transmitted once, and the connection status is periodically transmitted. Thus, its update data is from LD node +. >
The multi-hop transmission delay to Sink nodes is:
wherein,,
is Sink node and LD node->
Is a distance of (2); w is the node communication distance; />
For LD node->
Whether or not enhanced twinning is established on Sink is 0-1 characteristic value, the value of 1 represents +.>
The enhanced twinning of (2) is established on Sink, and a value of 0 indicates +.>
Is not established on Sink; r is R l For every LD node in period->
The available transmission capacity of the unified representation; />
Is->
The amount of update data that needs to be sent per cycle in the AT to remove the awareness data is built.
2. Propagation delay
There are two types of transmission objects of data collected by each LD: sink, RD, LD propagates the AT build data in the form of signals over the wireless channel. Considering that LD nodes are uniformly distributed, each LD node can form a communication path which is approximately straight line from Sink or RD node, therefore, the paths of both communication sides are abstracted into straight line paths, and the propagation delay of the paths depends on the physical distance between LD and Sink or RD, namely:
in each period, LD nodes
To SThe propagation delay required by the ink node is:
where v is the signal propagation rate.
3. Calculating time delay
The data processing time delay is that AT data is transmitted to a receiver and is processed and calculated by the receiver, and the processing time delay of the data is different because the computing capacities of Sink and RD are different. The data processing delay of each LD is determined by the available computational resources of the AT builder and the amount of computation to build the AT.
In each period, sink node is LD node
The computation delay required to construct an AT is:
wherein C is S Computing resources are available for a single cycle of Sink nodes.
S4, utilizing a matching solving algorithm based on a genetic algorithm, and carrying out enhanced twin matching nodes based on the resource-rich equipment nodes according to the initialized original data remained after enhanced twin matching in the step S2 to obtain an optimal matching solution of the resource-rich equipment nodes;
as shown in fig. 2, step S4 includes the following sub-steps:
s41, performing primary matching on the rest initialized enhanced twin matching states after the Sink node-based enhanced twin matching nodes are screened by utilizing service matching constraint conditions to obtain a target set of matching of the light-weight equipment nodes after primary matching to the resource-rich equipment nodes;
optionally, because the service attributes of each LD and RD are different, the LD node can be obtained preliminarily according to the service matching constraint condition
To RD node->
Matched 0-1 target set +.>
Thus, the initial population needs to be set within the framework of the target set; on this basis, the initial number is chosen according to the situation, and if the initial number is too small, the coverage area in the vector space is too small, so that the algorithm is terminated when the non-optimal solution is converged. In the embodiment of the invention, for the convenience of calculation, the initial population is set to contain 4 biological individuals x y Y.epsilon {1,2,3,4}, each chromosome is treated as if new LD nodes were obtained +.>
0-1 target set of allocatable RD
An m-segment of length n 0-1 chromosome fragment is obtained, the total product of which should be the zero vector of length n.
Preferably, the expression of the service matching constraint in step S41 is:
wherein,,
is a lightweight device node->
For determining whether enhanced twinning can be established at the resource-rich device node>
The value of the characteristic value is 1, which represents the lightweight equipment node->
Is twinned at the resource-rich device node
The upper establishment, the value of 0 represents the lightweight equipment node +.>
Is not in the resource-rich device node +.>
Building up; />
The 0-1 eigenvector of the service k supported by the lightweight equipment node for single service satisfies the following conditions
Representation->
Support traffic k->
Representation->
Service k is not supported; q is the total traffic supported by the network; />
The 0-1 eigenvector of the service k supported by the lightweight equipment section of the non-omnipotent service meets the requirement of->
Representing node->
Support traffic k->
Then represent node +.>
Service k is not supported.
Optionally, because Sink is a full-function node, service attribute matching is not considered. The RD is used as a non-omnipotent node, so that the computing advantages of all the RD can be fully invoked and an optimal scheme can be quickly found when task allocation is met, the LD and the RD are correspondingly established with the directed service mapping relation, data of specific services are transmitted to the RD with specific functions, and unnecessary path selection schemes are avoided being computed.
Each LD usually corresponds to a certain type of specific service, but multiple types of services supported on a certain RD are not necessarily applicable to all LD services, so when AT matching is performed, service attributes on the corresponding RD are considered to match the AT, so that an invalid AT matching path is avoided from being selected, that is, when the product of each LD and the corresponding service vector of the RD which can be used as an AT carrier is not 0, the current matching allocation path is valid.
S42, performing chromosome coding on the target set to obtain a plurality of chromosome fragments;
alternatively, each chromosome x is set x The length is m multiplied by n, which indicates that whether each LD allocates the corresponding AT on the RD is 0-1 code with the length of n, if allocated on the RD, the sequence number value of the RD of the corresponding LD section is 1, otherwise, the sequence number value is 0;
optionally, the enhanced twin matching is an NP-Hard problem with a matching priority and with the shortest construction time as a guide, in the embodiment of the present invention, the chromosome represents an AT matching relationship, population evolution is performed based on a genetic algorithm until the iteration number is reached, and the generated optimal AT matching relationship is output, that is, under the premise that all LDs on the RD are constructed, the construction time used in the link reaches the minimum value in the search space of the genetic algorithm.
S43, initializing the population of the chromosome segments based on the resource limitation of the resource-rich equipment nodes;
s44, constructing an fitness function, and selecting the parent with the highest fitness value to perform chromosome crossing to obtain a new population;
preferably, the expression of the fitness function in step S44 is:
wherein x is y Is chromosome, f (x y ) In order to adapt the function of the degree of adaptation,
is->
Lightweight device node in a single cycle>
In the resource-rich device node->
Constructing the total time delay of the enhanced twinning, wherein y is the number of organisms in the initial population.
Alternatively, since chromosomes with greater fitness are more easily preserved in the genetic algorithm, in the embodiment of the present invention, the minimum value of the RD total construction delay in the current chromosome needs to be solved, so the fitness function is set to be the inverse of the total construction delay.
Alternatively, the number of organisms in the initial population in the embodiment of the invention is 4.
Preferably, the total time delay of the lightweight device node in a single cycle in step S44 to construct enhanced twinning at the resource-rich device node is expressed as:
wherein,,
for updating data in a single period from a lightweight device node +.>
To resource-rich equipment node
Multi-hop transmission delay of- >
Lightweight device node in a single cycle>
To the resource-rich device node->
The required propagation delay +.>
For a resource-rich device node within a single period +.>
Is a lightweight device node->
Constructing a meter required to enhance twinningAnd (5) calculating time delay.
Optionally, for at RD node
LD node constructing AT->
In other words, the update data thereof contains device information, perception data, and connection status. Wherein, the device information is transmitted once, the perceived data and the connection status are transmitted periodically, so that the update data in a single period is distributed from the lightweight device node +.>
To the resource-rich device node->
The calculation formula of the multi-hop transmission delay is expressed as follows:
wherein; w is the node communication distance; r is R l For each lightweight equipment node in period
The available transmission capacity of the unified representation; />
Is a lightweight device node->
For determining whether enhanced twinning can be established at the resource-rich device node>
The characteristic value of the upper part; />
Is a lightweight device node->
The amount of update data that is needed to be sent to contain the perceived data is built up to enhance a single cycle in the twin AT.
Within each cycle, lightweight device nodes
To the resource-rich device node->
The required propagation delay is expressed as:
Wherein,,
is a resource-rich device node->
And lightweight device node->
Is a distance of (2); v is the signal propagation rate;
within each period, the resource-rich device node
Is a lightweight device node->
The computational delay required to construct the enhanced twin AT match is expressed as:
wherein,,
for each resource-rich device node +.>
Available computing resources within each cycle; />
The amount of computation required for constructing enhanced twinning; />
For judging lightweight device node->
Whether or not enhanced twin can be established at the resource-rich device node>
0-1 eigenvalues of (2);
s45, judging whether the resource capacity of the current population exceeds the resource limit of the resource-rich equipment node, and if so, returning to the step S44; otherwise, outputting the optimized new population, and proceeding to step S46;
preferably, the resource limitation based on the resource-rich device node in step S43 and step S45 includes:
communication resource constraint on resource-rich device nodes:
resource-rich device node storage limits:
resource-rich device node computational capability limitations:
wherein,,
for each resource-rich device node +.>
Available computing resources within each cycle; />
The amount of computation required for constructing enhanced twinning; r is R l Available transmission capacity for the lightweight device node in the cycle; />
Is a resource-rich device node->
Storing a load threshold; />
New data amount generated in a single period; alpha is the total number of periods, t is a time variable; />
For judging lightweight device node->
Whether enhanced twinning is established at the resource-rich device node +.>
The value of 0-1 characteristic value of (2) is 1, and is light-weight equipment node +.>
Is enhanced twinned in the resource-rich device node->
The upper establishment, the value of 0 represents the lightweight equipment node +.>
Is not in the resource-rich device node +.>
Building up; />
For a resource-rich device node within a single period +.>
The transmission capacity of the twin architecture can be enhanced; />
Is a lightweight device node->
The fixed storage resources occupied by the twin are enhanced; />
Real-time available storage capacity for lightweight device nodes; n is the total number of the nodes of the resource-rich equipment; m is the total number of lightweight device nodes.
S46, judging whether the iteration times meet preset times, and if so, ending the iteration; obtaining an optimal matching solution of the resource surplus type equipment nodes; otherwise, the current population is taken as the latest parental model, and the step S44 is returned.
And S5, calculating a global optimal solution based on enhanced twinning according to the total time delay of the optimal solution matched with the resource surplus type equipment node and the enhanced twinning matched node based on the Sink node.
Preferably, the calculation expression of the global optimal solution in step S5 is:
wherein T is ATN For the total construction time delay of the enhanced twin network in a single period, T coop After the construction of each enhanced twin is completed, each enhanced twin bearing node cooperatively generates the cooperative time of the enhanced twin network in a single period,
constructing enhanced twin total time delay for light-weight equipment nodes in a single period in resource-rich equipment nodes, wherein the enhanced twin total time delay is->
The method is characterized in that the method is the total time delay of an enhanced twin matching node based on Sink nodes in a single period, max is an extremum function, n is the number of resource-rich devices, and m is the number of lightweight devices.
Alternatively, since the collaboration time T is given in a collaboration mode coop To determine a value; therefore, in the embodiment of the present invention, the time required for optimizing all ATs to complete the construction is mainly considered, namely, T shown in the following formula AT Part (c):
on the basis that the requirements that each AT can be successfully constructed and the used resources do not exceed the resource capacity limit of the AT bearing party, the shortest AT construction time is obtained, and the target and constraint conditions are as follows:
as shown in fig. 3, according to the distribution situation of AT data and in combination with the method for intelligent device of the internet of things based on enhanced twinning provided by the invention, an embodiment of the invention constructs a method for intelligent device of the internet of things based on enhanced twinning Intelligent enhanced twin model for lightweight equipment of Internet of things, wherein the Internet of things sub-network is a wireless network and comprises 1 Sink node D S N randomly distributed RD devices
And m homogeneously distributed LD devices +.>
The node communication distance is denoted as W, and the signal propagation rate is +.>
LD requiring remote construction of AT for period T data The relevant data is transmitted to its AT construction node.
The network can support q kinds of service types (q < m), the service characteristic vector of each node can be expressed as a 0-1 vector with the length of q, and if a certain item of the service characteristic vector is 1, the node has the capability of processing the corresponding service, otherwise, the value is 0.Sink is a full-function node and can cover all services, and the service characteristic vector is a full 1 vector
RD node->
Can be expressed as a traffic feature vector of (a)
Representing node->
Support traffic k->
Then represent node +.>
Service k is not supported. LD is a single service node, a certain LD node +.>
The traffic vector may be expressed as
Satisfy->
Representation->
The service k is supported and,
representation->
Service k is not supported.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The principles and embodiments of the present invention have been described in detail with reference to specific examples, which are provided to facilitate understanding of the method and core ideas of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Those of ordinary skill in the art will recognize that the embodiments described herein are for the purpose of aiding the reader in understanding the principles of the present invention and should be understood that the scope of the invention is not limited to such specific statements and embodiments. Those of ordinary skill in the art can make various other specific modifications and combinations from the teachings of the present disclosure without departing from the spirit thereof, and such modifications and combinations remain within the scope of the present disclosure.
Claims (8)
1. The intelligent method for the lightweight equipment of the Internet of things based on the enhanced twinning is characterized by comprising the following steps of:
s1, acquiring original data through each light-weight device, and uploading the original data to a Sink node to obtain an initialized enhanced twin matching state;
s2, carrying out enhanced twin matching of light-weight equipment on the initialized enhanced twin matching state based on the resource limitation of the Sink node to obtain an enhanced twin matching node based on the Sink node;
s3, calculating the total time delay of the enhanced twin matching node based on the Sink node;
s4, utilizing a matching solving algorithm based on a genetic algorithm, and carrying out enhanced twin matching based on the resource surplus type equipment nodes according to the initialized enhanced twin matching state remained after the enhanced twin matching in the step S2 to obtain an optimal matching solution of the resource surplus type equipment nodes;
Step S4 comprises the following sub-steps:
s41, performing primary matching on the rest initialized enhanced twin matching states after the Sink node-based enhanced twin matching nodes are screened by utilizing service matching constraint conditions to obtain a target set of matching of the light-weight equipment nodes after primary matching to the resource-rich equipment nodes;
s42, performing chromosome coding on the target set to obtain a plurality of chromosome fragments;
s43, initializing the population of the chromosome segments based on the resource limitation of the resource-rich equipment nodes;
s44, constructing an fitness function, and selecting the parent with the highest fitness value to perform chromosome crossing to obtain a new population;
s45, judging whether the resource capacity of the current population exceeds the resource limit of the resource-rich equipment node, and if so, returning to the step S44; otherwise, outputting the optimized new population, and proceeding to step S46;
s46, judging whether the iteration times meet the preset times, if so, ending the iteration, and obtaining a resource surplus type equipment node matching optimal solution; otherwise, taking the current population as the latest parental model and returning to the step S44;
s5, calculating a global optimal solution based on enhanced twinning according to the total time delay of the optimal solution matched with the resource surplus equipment node and the enhanced twinning matched node based on the Sink node;
The calculation expression of the global optimal solution in step S5 is:
wherein,,
for the total construction delay of the construction of the enhanced twin network in a single cycle +.>
After the construction of each enhanced twin is completed, the enhanced twin bearing nodes cooperatively generate the cooperative time of the enhanced twin network in a single period, and the cooperative time is +.>
Constructing enhanced twin total time delay for light-weight equipment nodes in a single period in resource-rich equipment nodes, wherein the enhanced twin total time delay is->
For the total time delay of the enhanced twin matching node based on Sink node in a single period, max is an extremum function,nfor the number of resource-rich devices,mis the number of lightweight devices.
2. The method for intelligent device of the enhanced twinning-based internet of things of claim 1, wherein step S2 is specifically:
under the condition of limiting the resources based on Sink nodes, the initialized enhanced twin matching state is matched with the lightweight equipment nodes according to the sequence from high to low of the uploading data amount under the same service priority from the highest priority to the lowest priority according to the service priority of the lightweight equipment.
3. The enhanced twinning-based internet of things light-weight device intelligent method according to claim 2, wherein the Sink node-based resource limitation in step S2 specifically comprises:
Communication resource constraint on Sink node:
；
sink storage limit:
sink computational power limitation:
；
wherein,,
computing resources are available for a single cycle of Sink nodes; />
The transmission capacity required for Sink nodes for enhancing twin construction is increased; />
To store a load threshold; />
Real-time available storage capacity for Sink nodes;mthe total number of LD nodes is light-weight equipment; />
The amount of computation required for enhancing twin construction in a single cycle; />
The amount of update data generated within a single cycle for a lightweight device LD node; />
As a total number of cycles,tis a time variable; />
Is a lightweight device LD node->
Characteristic values for determining whether enhanced twinning is established on Sink nodes, ++>
For every lightweight device LD node in the cycle +.>
Available transmission capacity, < >>
Is a lightweight device LD node->
To enhance the fixed storage resources required to be occupied by the twinning itself.
4. The enhanced twinning-based internet of things lightweight device intelligent method according to claim 1, wherein the total time delay calculation formula of the enhanced twinning-matched node based on Sink node in step S3 is expressed as:
wherein,,
for the total time delay of the enhanced twin matching node based on Sink node in a single period, +. >
For updating data in a single period from a lightweight device node +.>
Multi-hop transmission delay to Sink node, < >>
Lightweight device node in a single cycle>
Propagation delay required to Sink node, < >>
The Sink node in a single period is a lightweight equipment node
The computational delay required to enhance twinning is built,mis the number of lightweight devices.
5. The enhanced twinning-based intelligent device method for the internet of things according to claim 1, wherein the expression of the service matching constraint condition in step S41 is:
wherein,,
is a lightweight device node->
For determining whether enhanced twinning is established at the resource-rich device node
The characteristic value of the upper part; />
Services supported by a lightweight device node for a single service>
A feature vector; />
Services supported by lightweight equipment nodes for non-all-round services>
Is used for the feature vector of (a),qfor the total number of services supported by the enhanced twinning,nfor the number of resource-rich devices,mis the number of lightweight devices.
6. The enhanced twinning-based internet of things light-weight device intelligent method of claim 1, wherein the fitness function in step S44 has the expression:
wherein,, 
Is chromosome, is->
For fitness function>
Lightweight device node in a single cycle>
In the resource-rich device node->
The total time delay of the enhanced twinning is constructed,nfor the number of resource-rich devices,mis the number of lightweight devices.
7. The enhanced twinning-based internet of things lightweight device intelligent method of claim 1, wherein the total delay of the lightweight device node constructing the enhanced twinning at the resource-rich device node in a single cycle in step S44 is expressed as:
wherein,,
for updating data in a single period from a lightweight device node +.>
To the resource-rich device node->
Multi-hop transmission delay of->
Lightweight device node in a single cycle>
To the resource-rich device node->
The required propagation delay +.>
For a resource-rich device node within a single period +.>
Is a lightweight device node->
The computational delay required to enhance twinning is built.
8. The enhanced twinning-based internet of things lightweight device intelligent method of claim 1, wherein the resource limitation based on the resource-rich device node in step S43 and step S45 comprises:
communication resource constraint on resource-rich device nodes:
Resource-rich device node storage limits:
resource-rich device node computational capability limitations:
wherein,,
for each resource-rich device node +.>
Available computing resources within a single cycle; />
The amount of computation required for constructing enhanced twinning; />
Available transmission capacity for lightweight device nodes within a single period; />
Is a resource-rich device node->
Storing a load threshold; />
New data amount generated in a single period; />
As a total number of cycles,tis a time variable; />
For judging lightweight device node->
Whether enhanced twinning is established at the resource-rich device node +.>
Is a characteristic value of (2); />
Is a resource-rich device node->
The transmission capacity of the twin architecture can be enhanced; />
Is a lightweight device node->
The fixed storage resources occupied by the twin are enhanced; />
Real-time available storage capacity for lightweight device nodes;nthe total number of the equipment nodes is the resource surplus;mis a lightweight device node total number.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111615461.6A CN114285880B (en) | 2021-12-27 | 2021-12-27 | Intelligent method for lightweight equipment of Internet of things based on enhanced twinning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111615461.6A CN114285880B (en) | 2021-12-27 | 2021-12-27 | Intelligent method for lightweight equipment of Internet of things based on enhanced twinning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114285880A CN114285880A (en) | 2022-04-05 |
| CN114285880B true CN114285880B (en) | 2023-06-23 |
Family
ID=80876414
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111615461.6A Active CN114285880B (en) | 2021-12-27 | 2021-12-27 | Intelligent method for lightweight equipment of Internet of things based on enhanced twinning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114285880B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016165392A1 (en) * | 2015-04-17 | 2016-10-20 | 华南理工大学 | Genetic algorithm-based cloud computing resource scheduling method |
| CN108809860A (en) * | 2018-05-03 | 2018-11-13 | 北京航空航天大学 | Network node resource distribution method based on service reliability |
| CN108880663A (en) * | 2018-07-20 | 2018-11-23 | 大连大学 | Incorporate network resource allocation method based on improved adaptive GA-IAGA |
| CN111510323A (en) * | 2020-03-24 | 2020-08-07 | 中国科学院上海微系统与信息技术研究所 | Firmware upgrading method, device and system for Internet of things equipment and storage medium |
| US10798175B1 (en) * | 2019-06-28 | 2020-10-06 | CohesionIB | IoT contextually-aware digital twin with enhanced discovery |
| CN111835565A (en) * | 2020-07-06 | 2020-10-27 | 重庆金美通信有限责任公司 | Communication network optimization method, device and system based on digital twin |
| CN112101899A (en) * | 2020-09-09 | 2020-12-18 | 北京航空航天大学 | Physical fusion method for digital twin enhanced manufacturing service information |
| CN112600912A (en) * | 2020-12-10 | 2021-04-02 | 西安君能清洁能源有限公司 | Unmanned aerial vehicle-assisted edge computing unloading algorithm distributed excitation method |
| CN112702401A (en) * | 2020-12-15 | 2021-04-23 | 北京邮电大学 | Multi-task cooperative allocation method and device for power Internet of things |
| CN113537514A (en) * | 2021-07-27 | 2021-10-22 | 北京邮电大学 | High-energy-efficiency federal learning framework based on digital twins |
| US11200045B1 (en) * | 2020-10-15 | 2021-12-14 | International Business Machines Corporation | Digital twin enabled asset performance and upgrade management |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10305734B2 (en) * | 2016-04-07 | 2019-05-28 | General Electric Company | Method, system, and program storage device for customization of services in an industrial internet of things |
| US10671435B1 (en) * | 2017-10-19 | 2020-06-02 | Pure Storage, Inc. | Data transformation caching in an artificial intelligence infrastructure |
| US10754704B2 (en) * | 2018-07-11 | 2020-08-25 | International Business Machines Corporation | Cluster load balancing based on assessment of future loading |
| US10951713B2 (en) * | 2019-06-28 | 2021-03-16 | CohesionIB | IoT analytics edge application on IoT gateway |
| US20210096975A1 (en) * | 2019-09-30 | 2021-04-01 | International Business Machines Corporation | Digital twin maturation tracking |
-
2021
- 2021-12-27 CN CN202111615461.6A patent/CN114285880B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016165392A1 (en) * | 2015-04-17 | 2016-10-20 | 华南理工大学 | Genetic algorithm-based cloud computing resource scheduling method |
| CN108809860A (en) * | 2018-05-03 | 2018-11-13 | 北京航空航天大学 | Network node resource distribution method based on service reliability |
| CN108880663A (en) * | 2018-07-20 | 2018-11-23 | 大连大学 | Incorporate network resource allocation method based on improved adaptive GA-IAGA |
| US10798175B1 (en) * | 2019-06-28 | 2020-10-06 | CohesionIB | IoT contextually-aware digital twin with enhanced discovery |
| CN111510323A (en) * | 2020-03-24 | 2020-08-07 | 中国科学院上海微系统与信息技术研究所 | Firmware upgrading method, device and system for Internet of things equipment and storage medium |
| CN111835565A (en) * | 2020-07-06 | 2020-10-27 | 重庆金美通信有限责任公司 | Communication network optimization method, device and system based on digital twin |
| CN112101899A (en) * | 2020-09-09 | 2020-12-18 | 北京航空航天大学 | Physical fusion method for digital twin enhanced manufacturing service information |
| US11200045B1 (en) * | 2020-10-15 | 2021-12-14 | International Business Machines Corporation | Digital twin enabled asset performance and upgrade management |
| CN112600912A (en) * | 2020-12-10 | 2021-04-02 | 西安君能清洁能源有限公司 | Unmanned aerial vehicle-assisted edge computing unloading algorithm distributed excitation method |
| CN112702401A (en) * | 2020-12-15 | 2021-04-23 | 北京邮电大学 | Multi-task cooperative allocation method and device for power Internet of things |
| CN113537514A (en) * | 2021-07-27 | 2021-10-22 | 北京邮电大学 | High-energy-efficiency federal learning framework based on digital twins |
Non-Patent Citations (4)
| Title |
|---|
| 《Digital Twin in the IoT Context: A Survey on Technical Features, Scenarios, and Architectural Models》;ROBERTO MINERVA,GYU MYOUNG LEE等;《PROCEEDINGS OF THE IEEE》(第10期);第1785-1824页 * |
| 《Digital Twin: Enabling Technologies,Challenges and Open Research》;AIDAN FULLER,ZHONG FAN等;《IEEE Access》(第5期);第108952-108971页 * |
| AIoT未来的发展趋势;徐建明;;中国安防(05);第85-90页 * |
| 基于数字孪生的泛在电力物联网模型研究;纪志伟;;电力学报(03);第93-98页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114285880A (en) | 2022-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111245651B (en) | Task unloading method based on power control and resource allocation | |
| CN107172166B (en) | Cloud and mist computing system for industrial intelligent service | |
| Khalili et al. | Inter‐layer per‐mobile optimization of cloud mobile computing: a message‐passing approach | |
| Li et al. | An integrated optimization-learning framework for online combinatorial computation offloading in MEC networks | |
| CN113641504B (en) | Information interaction method for improving edge computing effect of multi-agent reinforcement learning | |
| CN113781002B (en) | Low-cost workflow application migration method based on agent model and multiple group optimization in cloud edge cooperative network | |
| Yang et al. | Deep reinforcement learning based wireless network optimization: A comparative study | |
| CN116541106B (en) | Computing task unloading method, computing device and storage medium | |
| Chen et al. | A hybrid task scheduling scheme for heterogeneous vehicular edge systems | |
| CN114710439B (en) | Network energy consumption and throughput joint optimization routing method based on deep reinforcement learning | |
| Bi et al. | Stable online computation offloading via Lyapunov-guided deep reinforcement learning | |
| CN114710571A (en) | Data packet processing system | |
| Perin et al. | EASE: Energy-aware job scheduling for vehicular edge networks with renewable energy resources | |
| Mafuta et al. | Decentralized resource allocation-based multiagent deep learning in vehicular network | |
| CN114285880B (en) | Intelligent method for lightweight equipment of Internet of things based on enhanced twinning | |
| CN112231117B (en) | Cloud robot service selection method and system based on dynamic vector hybrid genetic algorithm | |
| Shaodong et al. | Multi-step reinforcement learning-based offloading for vehicle edge computing | |
| CN115720226A (en) | Time delay perception resource reservation method based on space-time task demand prediction | |
| CN115460710A (en) | Intelligent calculation unloading method in vehicle edge calculation scene based on deep reinforcement learning | |
| CN115473838A (en) | Network request processing method and device, computer readable medium and electronic equipment | |
| CN113316188B (en) | AI engine supporting access network intelligent slice control method and device | |
| Sun et al. | Towards Heterogeneous Environment: Lyapunov-orientated ImpHetero Reinforcement Learning for Task Offloading | |
| Vu et al. | Optimal task offloading and resource allocation for fog computing | |
| Liu et al. | GA-DRL: Graph Neural Network-Augmented Deep Reinforcement Learning for DAG Task Scheduling over Dynamic Vehicular Clouds | |
| Wu et al. | QoS provisioning in space information networks: Applications, challenges, architectures, and solutions |
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 |