CN117955843A - Internet of things data transmission method and system for building HVAC system - Google Patents
Internet of things data transmission method and system for building HVAC system Download PDFInfo
- Publication number
- CN117955843A CN117955843A CN202410323638.2A CN202410323638A CN117955843A CN 117955843 A CN117955843 A CN 117955843A CN 202410323638 A CN202410323638 A CN 202410323638A CN 117955843 A CN117955843 A CN 117955843A
- Authority
- CN
- China
- Prior art keywords
- data
- value
- communication data
- missing communication
- wireless network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000005540 biological transmission Effects 0.000 title claims abstract description 85
- 238000000034 method Methods 0.000 title claims abstract description 55
- 230000006854 communication Effects 0.000 claims abstract description 131
- 238000004891 communication Methods 0.000 claims abstract description 130
- 238000012937 correction Methods 0.000 claims description 51
- 238000010606 normalization Methods 0.000 claims description 26
- 238000012545 processing Methods 0.000 claims description 25
- 230000003595 spectral effect Effects 0.000 claims description 4
- 230000006870 function Effects 0.000 description 9
- 238000012549 training Methods 0.000 description 5
- 238000002955 isolation Methods 0.000 description 3
- 238000011084 recovery Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000004378 air conditioning Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000009423 ventilation Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0896—Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0893—Assignment of logical groups to network elements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0894—Policy-based network configuration management
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/142—Network analysis or design using statistical or mathematical methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/33—Services specially adapted for particular environments, situations or purposes for indoor environments, e.g. buildings
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W72/00—Local resource management
- H04W72/04—Wireless resource allocation
- H04W72/044—Wireless resource allocation based on the type of the allocated resource
- H04W72/0453—Resources in frequency domain, e.g. a carrier in FDMA
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W72/00—Local resource management
- H04W72/50—Allocation or scheduling criteria for wireless resources
- H04W72/51—Allocation or scheduling criteria for wireless resources based on terminal or device properties
- H04W72/512—Allocation or scheduling criteria for wireless resources based on terminal or device properties for low-latency requirements, e.g. URLLC
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W72/00—Local resource management
- H04W72/50—Allocation or scheduling criteria for wireless resources
- H04W72/535—Allocation or scheduling criteria for wireless resources based on resource usage policies
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- Algebra (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Pure & Applied Mathematics (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention provides an internet of things data transmission method and system for a building HVAC system, wherein the method comprises the steps of establishing a bandwidth combination strategy of a wireless network and a core network of the internet of things on the premise of based on first data transmission requirements and with the aim of shortest second data transmission time; solving the bandwidth combination strategy based on fmincon function to obtain bandwidths of the wireless network and the core network required by the first data and the second data respectively, creating network slices oriented to the first data and the second data based on the required bandwidths of the wireless network and the core network respectively, and transmitting the first data and the second data correspondingly; judging whether the first data and the second data have missing communication data or not, if the first data and the second data have missing communication data, creating a prediction model, and inputting the missing communication data into the prediction model to obtain a predicted value; and the transmission efficiency of the network is improved.
Description
Technical Field
The invention belongs to the technical field of Internet of things, and particularly relates to an Internet of things data transmission method and system for a building HVAC system.
Background
HVAC systems are widely used in medium and large industrial or office buildings, and include not only the basic functions of heating, ventilation and air conditioning, but also related equipment and components;
In order to better meet the requirements of people on the comfort level of learning work environment for medium and large industrial buildings or office buildings, a large amount of data generated by related equipment and components of the HVAC system can be transmitted in the use process of the HVAC system so as to facilitate the subsequent analysis of the related equipment and components of the HVAC system, but the existing data transmission method of the Internet of things only simply distributes a plurality of business data of the related equipment and components to the broadband of the Internet of things uniformly, so that the transmission delay is poor.
Disclosure of Invention
In order to solve the technical problems, the invention provides an Internet of things data transmission method and system for a building HVAC system, which are used for solving the technical problems that the existing Internet of things transmission method only simply equally divides a plurality of service data into a broadband of the Internet of things, so that the transmission delay is poor.
In one aspect, the invention provides the following technical scheme, namely an internet of things data transmission method for a building HVAC system, the method comprising: on the premise of the first data transmission requirement, establishing a bandwidth combination strategy of a wireless network and a core network of the Internet of things by taking the shortest second data transmission time as an aim;
Solving the bandwidth combination strategy based on fmincon function to obtain bandwidths of the wireless network and the core network required by the first data and the second data respectively, creating network slices oriented to the first data and the second data based on the required bandwidths of the wireless network and the core network respectively, and transmitting the first data and the second data correspondingly;
Judging whether the first data and the second data have missing communication data or not, if the first data and the second data have missing communication data, creating a prediction model, and inputting the missing communication data into the prediction model to obtain a predicted value;
and creating a correction model, inputting the predicted value into the correction model to obtain a replacement value, and replacing the missing communication data by using the replacement value to finish data transmission.
Compared with the prior art, the application has the beneficial effects that: the method comprises the steps of solving a wireless network bandwidth and a core network bandwidth of a bandwidth combination strategy when the total transmission time delay of second data is minimum by using a fmincon function as a basis, constructing a network slice of the second data, constructing the network slice of the first data by using the wireless network bandwidth when the service quality requirement of the first data is met and the core network bandwidth distributed to the first data as a basis, realizing logic isolation between services, enabling the data transmission of the second data not to be influenced by the first data, ensuring the minimum data transmission time of the second data, ensuring that the transmission bandwidth of the services is reasonably arranged when the multi-service data is transmitted, and improving the transmission efficiency of the network; errors generated by the prediction model are corrected through the correction model, so that accuracy of prediction data is improved through cooperation of the prediction model and the correction model in the prediction process, accurate prediction and recovery of communication data missing from the Internet of things are achieved, and integrity of communication transmission of the first data and the second data is guaranteed.
Further, the step of inputting the missing communication data into the predictive model to obtain a predicted value includes:
iteratively segmenting the missing communication data based on a moving sliding window operation, constructing a first time sequence, and inputting the first time sequence into the prediction model to obtain a first predicted value;
Judging whether the first predicted value meets the cycle length of the missing communication data or not, and if the first predicted value does not meet the cycle length of the missing communication data, re-iterating and dividing the missing communication data;
And replacing tail data of the data segment of the missing communication data after re-segmentation with the first predicted value, forming a second time sequence, and inputting the second time sequence into the prediction model to obtain a second predicted value.
Further, the step of inputting the predicted value to the correction model to obtain an alternative value includes:
The second predicted value and the first data or the second data corresponding to the second predicted value are subjected to difference so as to obtain a difference value;
inputting the difference value into the correction model to obtain a difference value predicted value;
Correcting the first predicted value output in each loop iteration process of the prediction model based on the difference predicted value to obtain a corrected value;
judging whether the time sequence length of the correction value reaches the period length of the missing communication data, and if the time sequence length of the correction value reaches the period length of the missing communication data, the correction value is a replacement value.
Further, after the step of determining whether the time-series length of the correction value reaches the period length of the missing communication data, the method further includes:
If the time sequence length of the correction value does not reach the period length of the missing communication data, dynamically reconstructing the missing communication data;
Replacing tail data of the data segment of the missing communication data after reconstruction with the first predicted value to obtain a third time sequence;
inputting the third time series to the predictive model and repeating the step of inputting the predictive value to the correction model to obtain a replacement value.
Further, the bandwidth federation policy includes:
./>./>
in the method, in the process of the invention, Bandwidth of the internet of things required for representing the second data,/>Expressed as the size of the second data,/>Expressed as core network transmission rate,/>Represented as sender-side wireless network broadband allocated to said second data,/>Expressed as the transmission power of the transmitting end transmitting the second data,/>Represented as sender-to-sender/>, sending the second dataChannel gain of/>Denoted as base station,/>Is the noise power spectral density,/>Expressed as a receiver-side wireless network broadband allocated to said second data,/>Expressed as transmit power of the base station,/>Expressed as channel gain from base station to receiving end,/>Denoted as receiving end of the second data,/>Represented as a sender-side wireless network broadband allocated to the first data,Represented as the total bandwidth of the wireless network,/>Expressed as a receiver-side wireless network broadband allocated to said first data,/>Is the total broadband of the wireless network,/>Expressed as core network broadband allocated to said second data,/>Represented as core network broadband allocated to said first data,/>Expressed as the total bandwidth of the core network,/>Denoted as receiving end of first data,/>Average transmission rate requirement of wireless network denoted as first data,/>Expressed as mathematical expectation,/>./>Expressed as satisfying/>To/>Condition of/>To/>Respectively denoted as condition one through condition five.
Further, before the step of providing the first data transmission requirement, the method further includes:
and creating an Internet of things communication model, wherein the communication model comprises a first wireless network, a second wireless network and a core network.
Further, before the step of inputting the missing communication data into the predictive model to obtain a predicted value, the method further includes:
normalizing the missing communication data;
Wherein the formula of normalization processing includes:
in the method, in the process of the invention, Expressed as missing communication data after normalization processing,/>Expressed as missing communication data before normalization processing,/>Expressed as maximum value in missing communication data before normalization processing,/>Expressed as the minimum value in missing communication data before normalization processing,/>Is interval, and interval is/>。
In a second aspect, the present invention provides the following technical solutions, where the data transmission system of the internet of things for HVAC systems of buildings includes:
the combination module is used for establishing a bandwidth combination strategy of a wireless network and a core network of the Internet of things on the premise of the first data transmission requirement and with the aim of minimizing second data transmission time;
The transmission module is used for solving the bandwidth combination strategy based on a fmincon function, respectively obtaining bandwidths of the wireless network and the core network required by the first data and the second data, respectively creating network slices oriented to the first data and the second data based on the required bandwidths of the wireless network and the core network, and correspondingly transmitting the first data and the second data;
The prediction module is used for judging whether the first data and the second data have missing communication data or not, if the first data and the second data have missing communication data, a prediction model is created, and the missing communication data are input into the prediction model to obtain a prediction value;
And the replacing module is used for creating a correction model, inputting the predicted value into the correction model to obtain a replacing value, and replacing the missing communication data by using the replacing value to finish data transmission.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments or the description of the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of an internet of things data transmission method for a building HVAC system according to a first embodiment of the present invention;
FIG. 2 is a flow chart of obtaining predicted values according to a first embodiment of the present invention;
FIG. 3 is a flow chart of obtaining alternative values according to a first embodiment of the present invention;
fig. 4 is a block diagram of a communication model according to a first embodiment of the present invention;
fig. 5 is a block diagram of an internet of things data transmission system for a building HVAC system according to a second embodiment of the present invention.
Description of main reference numerals: 11. a first wireless network; 12. a second wireless network; 21. a first receiving end; 22. a second receiving end; 31. a first transmitting end; 32. a second transmitting end; 40. a core network.
Embodiments of the present invention will be further described below with reference to the accompanying drawings.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and intended to illustrate embodiments of the invention and should not be construed as limiting the invention.
In the description of the embodiments of the present invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like indicate orientations or positional relationships based on the orientation or positional relationships shown in the drawings, merely to facilitate description of the embodiments of the present invention and simplify 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 thus should not be construed as limiting the present invention.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the embodiments of the present invention, the meaning of "plurality" is two or more, unless explicitly defined otherwise.
Example 1
In a first embodiment of the present invention, as shown in fig. 1 to 4, an internet of things data transmission method for a building HVAC system includes the steps of S01 to S05:
S01, creating an Internet of things communication model, wherein the communication model comprises a first wireless network, a second wireless network and a core network;
In this embodiment, the communication model includes a first receiving end 21, a second receiving end 22, a first transmitting end 31, a second transmitting end 32, base stations (i.e. the first wireless network 11 and the second wireless network 12) corresponding to the first receiving end, the second receiving end, the first transmitting end, and the second transmitting end, respectively, and a core network 40.
S02, on the premise of the first data transmission requirement, establishing a bandwidth combination strategy of a wireless network and a core network of the Internet of things by taking the shortest second data transmission time as a purpose;
specifically, the bandwidth combination strategy includes:
./>./>
in the method, in the process of the invention, Bandwidth of the internet of things required for representing the second data,/>Expressed as the size of the second data,/>Expressed as core network transmission rate,/>Represented as sender-side wireless network broadband allocated to said second data,/>Expressed as the transmission power of the transmitting end transmitting the second data,/>Represented as sender-to-sender/>, sending the second dataChannel gain of/>Denoted as base station,/>Is the noise power spectral density,/>Expressed as a receiver-side wireless network broadband allocated to said second data,/>Expressed as transmit power of the base station,/>Expressed as channel gain from base station to receiving end,/>Denoted as receiving end of the second data,/>Represented as a sender-side wireless network broadband allocated to the first data,Represented as the total bandwidth of the wireless network,/>Expressed as a receiver-side wireless network broadband allocated to said first data,/>Is the total broadband of the wireless network,/>Expressed as core network broadband allocated to said second data,/>Represented as core network broadband allocated to said first data,/>Expressed as the total bandwidth of the core network,/>Denoted as receiving end of first data,/>Average transmission rate requirement of wireless network denoted as first data,/>Expressed as mathematical expectation,/>./>Expressed as satisfying/>To/>Condition of/>To/>Respectively denoted as condition one through condition five.
It is worth to say that, on the premise of meeting the service quality requirement of the first data, the access network bandwidth and the core network bandwidth of the second data are jointly optimized, and the transmission bandwidth resources of the wireless network and the core network are allocated, so that the transmission delay of the second data is minimum.
S03, solving the bandwidth combination strategy based on a fmincon function to respectively obtain bandwidths of the wireless network and the core network required by the first data and the second data, respectively creating network slices oriented to the first data and the second data based on the required bandwidths of the wireless network and the core network, and correspondingly transmitting the first data and the second data;
In this embodiment, the wireless network bandwidth and the core network bandwidth when the total transmission time of the second data is minimum in the multi-service-oriented scenario are obtained. The wireless network bandwidth and the core network width of the first data are obtained from the quality of service requirements of the first data. And taking the residual bandwidth of the core network after being distributed to the second data as the wireless network bandwidth of the first data according to the total broadband of the wireless network and the total bandwidth of the core network.
For example, in this embodiment, the first data is eMBB service type data, and the service data has a higher requirement on the transmission rate, so that the first data is the service quality requirement taking the transmission rate as the data on the premise of taking the first data transmission requirement, and the second data is URLLC service type, and the service type has a higher requirement on the transmission delay of the data;
It is worth to say that, by fmincon function solving the wireless network bandwidth and core network bandwidth when the total transmission delay of the second data of the bandwidth combination strategy is minimum, constructing the network slice of the second data. And constructing the network slice of the first data based on the wireless network bandwidth when the service quality requirement of the first data is met and the core network bandwidth allocated to the first data. The logic isolation between the services is realized, so that the data transmission of the second data is not influenced by the first data, the minimum data transmission time of the second data is ensured, the broadband transmitted between the services is reasonably arranged when the multi-service data is transmitted, and the transmission efficiency of the network is improved.
S04, judging whether the first data and the second data have missing communication data, if the first data and the second data have missing communication data, creating a prediction model, and inputting the missing communication data into the prediction model to obtain a prediction value;
Specifically, the prediction model is based on an LSTM model and mainly comprises an input layer, a 3-layer LSTM model layer, a 2-layer full-connection layer and an output layer;
In the specific implementation, carrying out preprocessing operations such as abnormal data screening, data noise reduction, single-period missing value complementation and the like on missing communication data based on methods such as maximum standard deviation, moving window, linear interpolation, threshold setting and the like; after screening abnormal data of the missing communication data, carrying out normalization processing on the missing communication data, then mapping and dividing the missing communication data based on a moving window operation, establishing a prediction model training data set and a test data set based on the divided missing communication data, wherein an input layer of a prediction model is responsible for receiving time sequence perception data parameters of the missing communication data, an LSTM model layer is responsible for learning missing communication data characteristics, a full connection layer is used for converting the dimension of the missing communication data, and an output layer is responsible for mapping predicted values into a real space; and finally, performing inverse normalization processing on the obtained model training result to obtain a real numerical value, and completing initial prediction of the industrial Internet of things communication missing data.
Wherein the formula of the normalization process includes:
The formula of the inverse normalization process includes:
in the method, in the process of the invention, Expressed as missing communication data after normalization processing,/>Expressed as inverse normalized communication data,/>Expressed as missing communication data before normalization processing,/>Expressed as maximum value in missing communication data before normalization processing,/>Expressed as the minimum value in missing communication data before normalization processing,/>Is interval, and interval is/>。
The step of inputting the missing communication data into the predictive model to obtain a predictive value includes:
S41, performing iterative segmentation on the missing communication data based on a moving sliding window operation, constructing a first time sequence, and inputting the first time sequence into the prediction model to obtain a first predicted value;
In this embodiment, the length of the window of the sliding window is referred to, then the operation is performed on the missing communication data after normalization processing, after each iteration, the window is moved backwards by a preset data point to form a new time segment, and the window sliding process is continuously repeated until all the missing communication data obtained after normalization processing is completely segmented, so that a training input data set with an equal step length time segment as a model is formed.
S42, judging whether the first predicted value meets the cycle length of the missing communication data, and if the first predicted value does not meet the cycle length of the missing communication data, re-iterating and dividing the missing communication data;
Specifically, in the existing internet of things communication process, various external factors exist, so that the integrity of time sequence data (first data or second data) cannot be effectively ensured, and therefore, it is required to execute period prediction on multi-period continuous data.
S43, replacing tail data of the data segment of the missing communication data after re-segmentation with the first predicted value, forming a second time sequence, and inputting the second time sequence into the prediction model to obtain a second predicted value.
It will be appreciated that when the second predicted value is obtained, it is also necessary to determine whether the cycle length of the missing communication data is satisfied, and if not, it is necessary to replace the tail data of the data segment of the missing communication data after repartitioning with the second predicted value, and continue to form a new time sequence.
S05, creating a correction model, inputting the predicted value into the correction model to obtain a replacement value, and replacing the missing communication data by using the replacement value to finish data transmission;
Specifically, the correction model is based on a multi-layer perceptron MLP model, and comprises an input layer, a 6-layer hidden layer and an output layer.
It is worth to say that the error generated by the prediction model is corrected through the correction model, so that the accuracy of the prediction data is improved through the cooperation of the prediction model and the correction model in the prediction process, the accurate prediction and recovery of the communication data of the Internet of things missing are realized, and the integrity of the communication transmission of the first data and the second data is ensured.
The step of inputting the predicted value to the correction model to obtain a replacement value includes:
s51, the second predicted value and the first data or the second data corresponding to the second predicted value are subjected to difference to obtain a difference value;
It should be noted that, since an error value is introduced when the first predicted value is added at the tail of the data segment, the error value is continuously amplified in the process of performing iteration, so that the final second predicted value is seriously deviated from the true value, and the accuracy of prediction is affected; it is understood that the first data or the second data corresponding to the second predicted value is differenced, that is, if the second predicted value is predicted for the first data, the second predicted value is differenced from the true value of the first data, and if the second predicted value is predicted for the second data, the second predicted value is differenced from the true value of the second data.
S52, inputting the difference value into the correction model to obtain a difference value predicted value;
specifically, a training set and a testing set of a correction model are established based on the difference value, and an MLP-based correction model is input for training and prediction to obtain a difference value predicted value;
S53, correcting the first predicted numerical value output in each loop iteration process of the prediction model based on the difference predicted value to obtain a corrected numerical value;
S54, judging whether the time sequence length of the correction value reaches the period length of the missing communication data;
S55, if the time sequence length of the correction value reaches the period length of the missing communication data, the correction value is a replacement value;
S56, if the time sequence length of the correction value does not reach the period length of the missing communication data, dynamically reconstructing the missing communication data; replacing tail data of the data segment of the missing communication data after reconstruction with the first predicted value to obtain a third time sequence; inputting the third time series to the predictive model and repeating the step of inputting the predictive value to the correction model to obtain a replacement value.
Specifically, the step of inputting the predicted value to the correction model to obtain the alternative value is repeated, which may be understood as continuing to execute step S51 after the step of inputting the third time series to the prediction model.
In summary, the fmincon function is used for solving the wireless network bandwidth and the core network bandwidth of the bandwidth combination strategy when the total transmission time delay of the second data is minimum as the basis, constructing a network slice of the second data, and the wireless network bandwidth and the core network bandwidth allocated to the first data are used for constructing the network slice of the first data as the basis when the service quality requirement of the first data is met, so that the logic isolation between services is realized, the data transmission of the second data is not influenced by the first data, the data transmission time of the second data is ensured to be minimum, the broadband transmitted between the services is reasonably arranged when the multi-service data is transmitted, and the transmission efficiency of the network is improved; errors generated by the prediction model are corrected through the correction model, so that accuracy of prediction data is improved through cooperation of the prediction model and the correction model in the prediction process, accurate prediction and recovery of communication data missing from the Internet of things are achieved, and integrity of communication transmission of the first data and the second data is guaranteed.
Example two
As shown in fig. 5, in a third embodiment of the present invention, there is provided an internet of things data transmission system for a building HVAC system, comprising:
The combination module 10 is configured to create a bandwidth combination policy of a wireless network and a core network of the internet of things with the purpose of minimizing a second data transmission time on the premise of the first data transmission requirement;
A transmission module 20, configured to solve the bandwidth combination policy based on an fmincon function, obtain bandwidths of the wireless network and the core network required by the first data and the second data, respectively, create network slices oriented to the first data and the second data based on the required bandwidths of the wireless network and the core network, and correspondingly transmit the first data and the second data;
The prediction module 30 is configured to determine whether missing communication data exists in the first data and the second data, and if missing communication data exists in the first data and the second data, create a prediction model, and input the missing communication data to the prediction model to obtain a predicted value;
and the replacing module 40 is configured to create a correction model, input the predicted value to the correction model to obtain a replacement value, and replace the missing communication data with the replacement value to complete data transmission.
Further, the prediction module 30 includes:
The prediction unit is used for iteratively dividing the missing communication data based on a moving sliding window operation, constructing a first time sequence, and inputting the first time sequence into the prediction model to obtain a first predicted value; judging whether the first predicted value meets the cycle length of the missing communication data or not, and if the first predicted value does not meet the cycle length of the missing communication data, re-iterating and dividing the missing communication data; and replacing tail data of the data segment of the missing communication data after re-segmentation with the first predicted value, forming a second time sequence, and inputting the second time sequence into the prediction model to obtain a second predicted value.
Further, the substitution module 40 includes:
The replacing unit is used for making a difference between the second predicted value and the first data or the second data corresponding to the second predicted value so as to obtain a difference value; inputting the difference value into the correction model to obtain a difference value predicted value; correcting the first predicted value output in each loop iteration process of the prediction model based on the difference predicted value to obtain a corrected value; judging whether the time sequence length of the correction value reaches the period length of the missing communication data, and if the time sequence length of the correction value reaches the period length of the missing communication data, the correction value is a replacement value.
Further, the substitution module 40 further includes:
A reconstruction unit, configured to dynamically reconstruct the missing communication data if the time-series length of the correction value does not reach the period length of the missing communication data; replacing tail data of the data segment of the missing communication data after reconstruction with the first predicted value to obtain a third time sequence; inputting the third time series to the predictive model and repeating the step of inputting the predictive value to the correction model to obtain a replacement value.
Further, the joint module 10 includes
The policy unit, configured to perform the bandwidth association policy, includes:
./>./>
in the method, in the process of the invention, Bandwidth of the internet of things required for representing the second data,/>Expressed as the size of the second data,/>Expressed as core network transmission rate,/>Represented as sender-side wireless network broadband allocated to said second data,/>Expressed as the transmission power of the transmitting end transmitting the second data,/>Represented as sender-to-sender/>, sending the second dataChannel gain of/>Denoted as base station,/>Is the noise power spectral density,/>Expressed as a receiver-side wireless network broadband allocated to said second data,/>Expressed as transmit power of the base station,/>Expressed as channel gain from base station to receiving end,/>Denoted as receiving end of the second data,/>Represented as a sender-side wireless network broadband allocated to the first data,Represented as the total bandwidth of the wireless network,/>Expressed as a receiver-side wireless network broadband allocated to said first data,/>Is the total broadband of the wireless network,/>Expressed as core network broadband allocated to said second data,/>Represented as core network broadband allocated to said first data,/>Expressed as the total bandwidth of the core network,/>Denoted as receiving end of first data,/>Average transmission rate requirement of wireless network denoted as first data,/>Expressed as mathematical expectation,/>./>Expressed as satisfying/>To/>Condition of/>To/>Respectively denoted as condition one through condition five.
Further, the internet of things data transmission system for a building HVAC system further includes:
the system comprises a creation module, a communication module and a communication module, wherein the creation module is used for creating an Internet of things communication model, and the communication model comprises a first wireless network, a second wireless network and a core network.
Further, the prediction module 30 further includes:
The processing unit is used for carrying out normalization processing on the missing communication data;
Wherein the formula of normalization processing includes:
in the method, in the process of the invention, Expressed as missing communication data after normalization processing,/>Expressed as missing communication data before normalization processing,/>Expressed as maximum value in missing communication data before normalization processing,/>Expressed as the minimum value in missing communication data before normalization processing,/>Is interval, and interval is/>。
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (7)
1. An internet of things data transmission method for a building HVAC system, the method comprising:
On the premise of the first data transmission requirement, establishing a bandwidth combination strategy of a wireless network and a core network of the Internet of things by taking the shortest second data transmission time as an aim;
Solving the bandwidth combination strategy based on fmincon function to obtain bandwidths of the wireless network and the core network required by the first data and the second data respectively, creating network slices oriented to the first data and the second data based on the required bandwidths of the wireless network and the core network respectively, and transmitting the first data and the second data correspondingly;
Judging whether the first data and the second data have missing communication data or not, if the first data and the second data have missing communication data, creating a prediction model, and inputting the missing communication data into the prediction model to obtain a predicted value;
creating a correction model, inputting the predicted value into the correction model to obtain a replacement value, and replacing the missing communication data by using the replacement value to finish data transmission;
the step of inputting the missing communication data into the predictive model to obtain a predictive value includes:
iteratively segmenting the missing communication data based on a moving sliding window operation, constructing a first time sequence, and inputting the first time sequence into the prediction model to obtain a first predicted value;
Judging whether the first predicted value meets the cycle length of the missing communication data or not, and if the first predicted value does not meet the cycle length of the missing communication data, re-iterating and dividing the missing communication data;
And replacing tail data of the data segment of the missing communication data after re-segmentation with the first predicted value, forming a second time sequence, and inputting the second time sequence into the prediction model to obtain a second predicted value.
2. The internet of things data transmission method for a building HVAC system of claim 1, wherein the step of inputting the predictive value to the correction model to obtain an alternative value comprises:
The second predicted value and the first data or the second data corresponding to the second predicted value are subjected to difference so as to obtain a difference value;
inputting the difference value into the correction model to obtain a difference value predicted value;
Correcting the first predicted value output in each loop iteration process of the prediction model based on the difference predicted value to obtain a corrected value;
judging whether the time sequence length of the correction value reaches the period length of the missing communication data, and if the time sequence length of the correction value reaches the period length of the missing communication data, the correction value is a replacement value.
3. The internet of things data transmission method for a building HVAC system of claim 2, wherein after the step of determining whether the time series length of the correction value reaches the cycle length of the missing communication data, the method further comprises:
If the time sequence length of the correction value does not reach the period length of the missing communication data, dynamically reconstructing the missing communication data;
Replacing tail data of the data segment of the missing communication data after reconstruction with the first predicted value to obtain a third time sequence;
inputting the third time series to the predictive model and repeating the step of inputting the predictive value to the correction model to obtain a replacement value.
4. The internet of things data transmission method for a building HVAC system of claim 1, wherein the bandwidth federation policy includes:
./>./>
in the method, in the process of the invention, Bandwidth of the internet of things required for representing the second data,/>Expressed as the size of the second data,/>Expressed as core network transmission rate,/>Represented as a sender-side wireless network broadband allocated to the second data,Expressed as the transmission power of the transmitting end transmitting the second data,/>Represented as sender-to-sender/>, sending the second dataChannel gain of/>Denoted as base station,/>Is the noise power spectral density,/>Expressed as a receiver-side wireless network broadband allocated to said second data,/>Expressed as transmit power of the base station,/>Expressed as channel gain from base station to receiving end,/>Denoted as receiving end of the second data,/>Represented as a sender-side wireless network broadband allocated to the first data,Represented as the total bandwidth of the wireless network,/>Expressed as a receiver-side wireless network broadband allocated to said first data,/>Is the total broadband of the wireless network,/>Expressed as core network broadband allocated to said second data,/>Represented as core network broadband allocated to said first data,/>Expressed as the total bandwidth of the core network,/>Denoted as receiving end of first data,/>Average transmission rate requirement of wireless network denoted as first data,/>Expressed as mathematical expectation,/>./>Expressed as satisfying/>To/>Condition of/>To/>Respectively denoted as condition one through condition five.
5. The internet of things data transmission method for a building HVAC system of claim 1, wherein prior to the step of based on the premise of the first data transmission requirement, the method further comprises:
and creating an Internet of things communication model, wherein the communication model comprises a first wireless network, a second wireless network and a core network.
6. The internet of things data transmission method for a building HVAC system of claim 1, wherein prior to the step of inputting the missing communication data into the predictive model to obtain a predictive value, the method further comprises:
normalizing the missing communication data;
Wherein the formula of normalization processing includes:
in the method, in the process of the invention, Expressed as missing communication data after normalization processing,/>Expressed as missing communication data before normalization processing,/>Expressed as maximum value in missing communication data before normalization processing,/>Expressed as the minimum value in missing communication data before normalization processing,/>Is interval, and interval is/>。
7. An internet of things data transmission system for a building HVAC system, the internet of things data transmission system for a building HVAC system comprising:
the combination module is used for establishing a bandwidth combination strategy of a wireless network and a core network of the Internet of things on the premise of the first data transmission requirement and with the aim of minimizing second data transmission time;
The transmission module is used for solving the bandwidth combination strategy based on a fmincon function, respectively obtaining bandwidths of the wireless network and the core network required by the first data and the second data, respectively creating network slices oriented to the first data and the second data based on the required bandwidths of the wireless network and the core network, and correspondingly transmitting the first data and the second data;
The prediction module is used for judging whether the first data and the second data have missing communication data or not, if the first data and the second data have missing communication data, a prediction model is created, and the missing communication data are input into the prediction model to obtain a prediction value;
The replacing module is used for creating a correction model, inputting the predicted value into the correction model to obtain a replacing value, and replacing the missing communication data by the replacing value to finish data transmission;
The prediction module comprises a prediction unit, wherein the prediction unit is used for iteratively dividing the missing communication data based on a moving sliding window operation and constructing a first time sequence, and the first time sequence is input into the prediction model to obtain a first prediction value; judging whether the first predicted value meets the cycle length of the missing communication data or not, and if the first predicted value does not meet the cycle length of the missing communication data, re-iterating and dividing the missing communication data; and replacing tail data of the data segment of the missing communication data after re-segmentation with the first predicted value, forming a second time sequence, and inputting the second time sequence into the prediction model to obtain a second predicted value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410323638.2A CN117955843A (en) | 2024-03-21 | 2024-03-21 | Internet of things data transmission method and system for building HVAC system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410323638.2A CN117955843A (en) | 2024-03-21 | 2024-03-21 | Internet of things data transmission method and system for building HVAC system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117955843A true CN117955843A (en) | 2024-04-30 |
Family
ID=90805352
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410323638.2A Pending CN117955843A (en) | 2024-03-21 | 2024-03-21 | Internet of things data transmission method and system for building HVAC system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117955843A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113094357A (en) * | 2021-04-23 | 2021-07-09 | 大连理工大学 | Traffic missing data completion method based on space-time attention mechanism |
| CN113709885A (en) * | 2021-10-12 | 2021-11-26 | 南京邮电大学 | Multi-service network resource allocation method |
| US20220292699A1 (en) * | 2021-03-08 | 2022-09-15 | Nvidia Corporation | Machine learning techniques for predicting depth information in image data |
| CN116304569A (en) * | 2023-03-21 | 2023-06-23 | 北京科技大学 | Filling method for missing data of distributed optical fiber sensor |
| CN116881643A (en) * | 2023-07-17 | 2023-10-13 | 中车工业研究院有限公司 | Sensory data depth signal complement method and device |
-
2024
- 2024-03-21 CN CN202410323638.2A patent/CN117955843A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220292699A1 (en) * | 2021-03-08 | 2022-09-15 | Nvidia Corporation | Machine learning techniques for predicting depth information in image data |
| CN113094357A (en) * | 2021-04-23 | 2021-07-09 | 大连理工大学 | Traffic missing data completion method based on space-time attention mechanism |
| CN113709885A (en) * | 2021-10-12 | 2021-11-26 | 南京邮电大学 | Multi-service network resource allocation method |
| CN116304569A (en) * | 2023-03-21 | 2023-06-23 | 北京科技大学 | Filling method for missing data of distributed optical fiber sensor |
| CN116881643A (en) * | 2023-07-17 | 2023-10-13 | 中车工业研究院有限公司 | Sensory data depth signal complement method and device |
Non-Patent Citations (2)
| Title |
|---|
| 李明时: "工业物联网安全通信关键技术研究", 中国优秀博士学位论文全文数据库信息科技辑, 15 February 2023 (2023-02-15), pages 4 * |
| 秦文虎;陈溪莹;: "基于长短时记忆网络的水质预测模型研究", 安全与环境学报, no. 01, 25 February 2020 (2020-02-25) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104640220B (en) | A kind of frequency and power distribution method based on NOMA systems | |
| CN110417496B (en) | Cognitive NOMA network stubborn resource allocation method based on energy efficiency | |
| JP4852616B2 (en) | Selection of radio resources in a wireless communication network | |
| CN111182582B (en) | Multitask distributed unloading method facing mobile edge calculation | |
| CN112533251B (en) | Cell interference assessment method and device | |
| US11277786B2 (en) | Facilitating compact signaling design for reserved resource configuration in wireless communication systems | |
| CN111553463B (en) | Method for estimating throughput of wireless access point based on deep learning and network parameters | |
| CN114462509A (en) | Distributed Internet of things equipment anomaly detection method | |
| CN106027184B (en) | A kind of interface method based on the link level of LTE-A to system integration project | |
| CN113038612A (en) | Cognitive radio power control method based on deep learning | |
| US9768911B2 (en) | System and method for designing constellations and use thereof | |
| CN114189852B (en) | Downlink multiuser beam alignment and data transmission method for millimeter wave hidden communication | |
| CN117033278B (en) | Data transmission method and system for multiple types of interfaces | |
| CN108199805A (en) | A kind of method for reducing Sparse Code multi-address system decoding complexity | |
| DE60202115T2 (en) | Method for blind detection of transport format | |
| Jaiswal et al. | Transfer learning based joint resource allocation for underlay D2D communications | |
| CN117955843A (en) | Internet of things data transmission method and system for building HVAC system | |
| Liu et al. | Semantic communications system with model division multiple access and controllable coding rate for point cloud | |
| CN110072197B (en) | Emergency communication transmission channel optimal selection intelligent switching selection method | |
| Zhao et al. | Least squares approximations to lognormal sum distributions | |
| US12074694B2 (en) | ACQI decoding confidence detection | |
| CN107370564A (en) | Polarization code processing method and processing device, node | |
| Mahmoudi et al. | A-LAQ: Adaptive lazily aggregated quantized gradient | |
| US11387870B2 (en) | MIMO detector selection | |
| WO2017194012A1 (en) | Polar code processing method and apparatus, and node |
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 |