5G message real-time scheduling method and system in intelligent Internet of Things environment

Abstract

The invention belongs to the technical field of intelligent Internet of Things, and particularly relates to a 5G message real-time scheduling method and system in an intelligent Internet of Things environment. The message scheduling intelligent Internet of Things platform performs real-time scheduling on the acquired data message. The method comprises the following steps: step 1, the message scheduling intelligent Internet of Things platform firstly constructs a TTE multi-hop network topology message scheduling model; 2, generating a message transmission alternative short path set according to a message scheduling data message, selecting a message path according to a message length and a link load to obtain a path planning result with a load balancing characteristic, and outputting a static priority to generate a scheduling table; and step 3, calculating a response ratio according to the message length and the period, sorting the messages based on the response ratio, and finally, carrying out transmission scheduling distribution according to the sorting. According to the invention, some message scheduling with high emergency degree and late arrival can preferentially obtain the response of the system.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent Internet of Things, and specifically relates to a 5G message real-time scheduling method and system under an intelligent Internet of Things environment. Background Art

[0002] The main function of IoT message scheduling is to manage and allocate the processing order and time of device messages. The scheduler determines which thread or device message is allowed to execute at any point in time. This thread or message is called the current thread or message. In the IoT system, the working principle of the scheduler involves multiple aspects. First, the scheduler needs to create an idle task, configure SysTick and PendSV as the lowest priority, configure the SysTick register, and then call the SVC interrupt. The scheduler also determines which device messages should be processed first based on the priority and status of the device. In the traditional way, the system responds to the message scheduling in the order in which it arrives, but there is an inevitable problem. Some messages with lower urgency but priority will occupy storage resources for a long time and get the system's response first, while some messages with higher urgency but later arrival will not get the system's response for a long time. This will not only cause a waste of resources, but sometimes also have serious consequences. To this end, we propose a 5G message real-time scheduling method and system in an intelligent IoT environment. Summary of the invention

[0003] The purpose of the present invention is to provide a 5G message real-time scheduling method and system in an intelligent Internet of Things environment. By setting a TTE multi-hop network topology message scheduling model, the improved TTE multi-hop network topology message scheduling model can generate a message scheduling table based on messages of different lengths and periods in a complex topology environment. At the same time, the generated scheduling table can meet the message delay requirements. Finally, the data in the scheduling table is generated according to the static priority. If the waiting time of the message scheduling in the auxiliary memory buffer queue is the same, the shorter its execution time, the greater its corresponding response ratio, and it will be scheduled by the Internet of Things platform first, which ensures that the Internet of Things platform can schedule and respond to as many messages as possible within the unit; if the execution time of the message scheduling is the same, the longer its waiting time, the greater its corresponding response value; this ensures that a message scheduling event with a low priority but waiting for a long time in the buffer queue in the auxiliary memory can also get a scheduling response from the Internet of Things platform.

[0004] The technical solution adopted by the present invention is as follows:

[0005] The method for real-time scheduling of 5G messages in a smart IoT environment first builds a smart IoT platform, wherein the smart IoT platform includes a processing terminal and a plurality of smart terminals, and the plurality of smart terminals are all connected to the processing terminal in communication; then the plurality of smart terminals send the collected data to the processing terminal, and the processing terminal performs real-time scheduling on the acquired data messages, including the following steps:

[0006] Step 1: The intelligent IoT platform first constructs a TTE multi-hop network topology message scheduling model;

[0007] Step 2: The TTE multi-hop network topology message scheduling model generates a set of alternative shorter paths for message transmission according to the data message, selects a message path according to the message length and link load, obtains a path planning result with load balancing characteristics, and outputs a static priority generation scheduling table;

[0008] Step 3: Generate a scheduling table based on static priority, calculate the response ratio according to the message length and period, sort the messages based on the response ratio, and finally make transmission scheduling allocation based on the sorting.

[0009] Preferably, in step 1, the TTE multi-hop network includes a communication link and several switches; the switches and the intelligent terminals, and the switches and the switches are connected via communication links; the communication link in the TTE multi-hop network adopts a full-duplex mode, and data streams can be transmitted in both directions of the link at the same time.

[0010] Preferably, in step 1, the TTE multi-hop network topology message scheduling model G{V, E} is established, wherein V represents the collection of all intelligent terminals and switches in the network, and E represents the collection of communication links between intelligent terminals and switches and between switches; in the TTE multi-hop network topology message scheduling model, V=ES∪NS={ES1, ES2, ES3, ES4, ES5}∪{NS1, NS2, NS3, NS4, NS5}, E={VL1, VL2, VL3, VL4, ..., VL i}; Data stream link VL i =[vj,vk]∈L, where L is the link VL i Collection of; v j is the source node of the message, v k is the destination of the message, v j and v k Can be ES or NS, data stream link VL i The speed is R-VL i .

[0011] In the present invention, it should be noted that ES represents an intelligent terminal; NS represents a switch.

[0012] Preferably, in the TTE multi-hop network topology message scheduling model, a network topology matrix G is defined;

[0013] In the formula, there exists v j , v j ∈V, so that when the data flow link VL i When the network topology matrix element G exists ij The value is 1, when the data flow link VL i When the network topology matrix element G does not exist ij The value is 0;

[0014] The TT message is modeled as the following six-tuple form, which is used to describe the transmission behavior of the TT message: i ={m i.pe 、m i.l 、m i.s 、m i.d 、m i.pa 、m i.o}; where m i.pe Indicates the time length corresponding to the message cycle, m i.l Indicates the time length corresponding to the transmission time caused by the message length, m i.s Indicates the source node of message transmission, m i.d Indicates the destination node of the message transmission, m i.pa Indicates the message transmission path, m i.o In order to simplify the timing planning problem into an integer planning problem, the present invention uses time slots as the time unit of the scheduling table to integerize the message cycle and message transmission time, so that m i.pe is the number of time slots corresponding to the message cycle, m i.l The number of time slots corresponding to the transmission time caused by the message length.

[0015] Preferably, in step 2, the path planning process of the network message is based on the source node m of the message. i.s , destination node m i.d The transmission path m of each message is determined by the network topology G i.p , the path is an ordered sequence of data flow links {l1, l2, ..., l n}, the specific implementation process is as follows Figure 3 As shown; first, the K shortest path algorithm is used to generate a set of candidate paths for each message, then the messages are sorted according to the rules, and finally, the path with the smallest network link load is selected from the candidate path set for the message in the sorted order and added to the planned path set.

[0016] Preferably, in step 2, after adding the planned path set, define the data flow link l ij The calculation formula for the load B on the The minimum network link utilization Bmin is In the formula, j, k are network nodes, v j ,v k .

[0017] Preferably, in step 3, for the message timing planning of a known transmission path, the scheduling process first determines the offset of the first data frame of each message in each data flow link of its path. ij ,of ij Indicates the offset of the first message frame when the i-th message is transmitted on the j-th data flow link of the path, and also determines the end time of the message frame transmission end ij , output static priority generation schedule, the static priority generation schedule includes the start time and end time of each message frame transmission ij .

[0018] Preferably, in step 3, a scheduling table is generated based on the static priority, the response time and execution time of each message frame are calculated, and the response ratio R is introduced when calculating the message priority according to the priority evaluation calculation formula. The response ratio R is equal to the ratio of the response time to the execution time. The message priority is calculated and evaluated based on the response time and execution time of each message in the scheduling table generated according to the static priority. Then, the messages are prioritized in ascending order. The smaller the evaluation value, the higher the ranking and the higher the priority. Finally, the messages are scheduled and allocated according to the rules according to the priority ranking.

[0019] A 5G message real-time scheduling system in an intelligent Internet of Things environment includes an intelligent Internet of Things platform, wherein the intelligent Internet of Things platform includes a processing terminal and a plurality of intelligent terminals, and the plurality of intelligent terminals are all communicatively connected with the processing terminal; then the plurality of intelligent terminals send the collected data to the processing terminal, and a TTE multi-hop network topology message scheduling model is established inside the processing terminal, and the TTE multi-hop network topology message scheduling model is used to complete the message scheduling of the intelligent Internet of Things platform.

[0020] Preferably, the TTE multi-hop network topology message scheduling model generates a set of alternative shorter paths for message transmission according to the data message, selects the message path according to the message length and link load, obtains a path planning result with load balancing characteristics, and outputs a static priority generation scheduling table; generates a scheduling table based on the static priority, calculates the response ratio according to the message length and period, sorts the messages based on the response ratio, and finally performs transmission scheduling allocation according to the sorting.

[0021] The technical effects achieved by the present invention are:

[0022] In the present invention, by setting a TTE multi-hop network topology message scheduling model, the improved TTE multi-hop network topology message scheduling model can generate a message scheduling table based on messages of different lengths and periods in a complex topology environment, and the generated scheduling table can meet the message delay requirements. Finally, the data in the scheduling table is generated according to the static priority. If the waiting time of the message scheduling in the auxiliary memory buffer queue is the same, the shorter the execution time, the larger the corresponding response ratio, and the Internet of Things platform will be scheduled first, which ensures that the Internet of Things platform can schedule and respond to as many messages as possible within the unit; if the execution time of the message scheduling is the same, the longer the waiting time, the larger the corresponding response value; this ensures that a low priority message scheduling event that has been waiting for a long time in the buffer queue in the auxiliary memory can also get a scheduling response from the Internet of Things platform, so that some message schedulings with higher urgency but arriving later are given priority to get a response from the system, avoiding waste of resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a flow chart of the real-time scheduling method of 5G messages under the intelligent Internet of Things environment of the present invention;

[0024] Figure 2 It is a system block diagram of the 5G message real-time scheduling system under the intelligent Internet of Things environment of the present invention;

[0025] Figure 3 It is a multi-hop network topology diagram in the 5G message real-time scheduling method under the intelligent Internet of Things environment of the present invention;

[0026] Figure 4 This is the path planning flow chart in step 2 of the 5G message real-time scheduling method under the intelligent Internet of Things environment of the present invention. DETAILED DESCRIPTION

[0027] In order to make the purpose and advantages of the present invention more clearly understood, the present invention is specifically described below in conjunction with embodiments. It should be understood that the following text is only used to describe one or several specific embodiments of the present invention, and does not strictly limit the scope of protection of the specific claims of the present invention.

[0028] Embodiment 1:

[0029] like Figure 1-4As shown, the real-time scheduling method of 5G messages in the intelligent Internet of Things environment first builds an intelligent Internet of Things platform, which includes a processing terminal and several intelligent terminals, and the several intelligent terminals are all connected to the processing terminal in communication; then the several intelligent terminals send the collected data to the processing terminal, and the processing terminal performs real-time scheduling on the acquired data messages, including the following steps:

[0030] Step 1: The intelligent IoT platform first builds a TTE multi-hop network topology message scheduling model;

[0031] Step 2: The TTE multi-hop network topology message scheduling model generates a set of alternative shorter paths for message transmission according to the data message, selects the message path according to the message length and link load, obtains a path planning result with load balancing characteristics, and outputs a static priority generation scheduling table;

[0032] Step 3: Generate a scheduling table based on static priority, calculate the response ratio according to the message length and period, sort the messages based on the response ratio, and finally make transmission scheduling allocation based on the sorting.

[0033] In the present invention, by setting a TTE multi-hop network topology message scheduling model, the improved TTE multi-hop network topology message scheduling model can generate a message scheduling table based on messages of different lengths and periods in a complex topology environment, and the generated scheduling table can meet the message delay requirements. Finally, the data in the scheduling table is generated according to the static priority. If the waiting time of the message scheduling in the auxiliary memory buffer queue is the same, the shorter the execution time, the greater the corresponding response ratio, and it will be scheduled by the Internet of Things platform first, which ensures that the Internet of Things platform can schedule and respond to as many messages as possible within the unit; if the execution time of the message scheduling is the same, the longer the waiting time, the greater the corresponding response value; this ensures that a message scheduling event with a low priority but waiting for a long time in the buffer queue in the auxiliary memory can also get a scheduling response from the Internet of Things platform.

[0034] Preferably, in step 1, the TTE multi-hop network includes a communication link and several switches; several switches and intelligent terminals, and switches and switches are connected through communication links; the communication link in the TTE multi-hop network adopts a full-duplex mode, and the data stream can be transmitted in both directions of the link at the same time; a TTE multi-hop network topology message scheduling model G{V, E} is established, wherein V represents the collection of all intelligent terminals and switches in the network, and E represents the collection of communication links between intelligent terminals and switches, and between switches; in the TTE multi-hop network topology message scheduling model, V=ES∪NS={ES1, ES2, ES3, ES4, ES5}∪{NS1, NS2, NS3, NS4, NS5}, E={VL1, VL2, VL3, VL4, ..., VLi}; Data stream link VL i =[vj,vk]∈L, where L is the link VL i Collection of; v j is the source node of the message, v k is the destination of the message, v j and v k Can be ES or NS, data stream link VL i The speed is R-VL i .

[0035] In the present invention, it should be noted that ES represents an intelligent terminal; NS represents a switch. As shown in the figure, there are five intelligent terminals, three switches and eight data flow links. This embodiment improves the TT-RMS communication table generation algorithm. First, it supports the scheduling of non-harmonious periodic messages and adds a step of determining the length of the scheduling table cluster cycle. Then, time slots of different lengths are allocated to messages of different lengths. Finally, it supports the generation of scheduling tables for multi-hop networks, such as Figure 1 The network topology shown in the figure is shown in the figure; and after the scheduling table is generated, the delay of the message in the scheduling table can be judged to see whether it can reach the destination node within the maximum delay; in the calculation process of the TT-RMS communication table generation algorithm of this embodiment, in the network, all the messages to be scheduled are periodic messages, and the message set and the attributes of the messages are known; all communication link resources in the network can be used, and all link attributes are the same; the switch adopts the "store-and-forward" method, that is, the frame can wait and stay at the switch for a period of time and then be sent when the switch is idle; all messages in the network can be encapsulated in one frame, so that the message can be transmitted in one time slot.

[0036] In the TTE multi-hop network topology message scheduling model, the network topology matrix G is defined;

[0037] In the formula, there exists v j , v j ∈V, so that when the data flow link VL i When the network topology matrix element G exists ij The value is 1, when the data flow link VL i When the network topology matrix element G does not exist ij The value is 0;

[0038] The TT message is modeled as the following six-tuple form, which is used to describe the transmission behavior of the TT message: i ={m i.pe 、m i.l 、m i.s 、m i.d 、m i.pa 、mi.o}; where m i.pe Indicates the time length corresponding to the message cycle, m i.l Indicates the time length corresponding to the transmission time caused by the message length, m i.s Indicates the source node of message transmission, m i.d Indicates the destination node of the message transmission, m i.pa Indicates the message transmission path, m i.o In order to simplify the timing planning problem into an integer planning problem, the present invention uses time slots as the time unit of the scheduling table to integerize the message cycle and message transmission time, so that m i.pe is the number of time slots corresponding to the message cycle, m i.l is the number of time slots corresponding to the transmission time caused by the message length; in step 2, the path planning process of the network message is based on the source node m of the message i.s , destination node m i.d The transmission path m of each message is determined by the network topology G i.p , the path is an ordered sequence of data flow links {l1, l2, ..., l n}, the specific implementation process is as follows Figure 4 As shown; first, the K shortest path algorithm is used to generate a set of candidate paths for each message, then the messages are sorted according to the rules, and finally, the path with the smallest network link load is selected from the candidate path set for the message in the sorted order and added to the planned path set.

[0039] Preferably, in step 2, after adding the planned path set, define the data flow link l ij The calculation formula for the load B on the The minimum network link utilization Bmin is In the formula, j, k are network nodes, v j ,v k .

[0040] In the present invention, after generating the path to be selected, in order to select the load-balanced path result, the present invention first needs to sort the messages according to the rules; the present invention takes into account the impact of the message length and defines the rule that the longer the message length is, the higher the sorting is, and the path selection is given priority; the shorter the message length is, the later it is, and the path selection is performed based on the load of the selected path, and the messages of the same length are sorted according to the original order; in order to achieve the purpose of load balancing, the present invention selects the path with the smallest link minimum load in the message path as the result of path planning. Since the transmission task path of some messages is unique, the load of some trunk links is very high and difficult to alleviate. Therefore, designing the link minimum load as a condition for path selection can pay attention to the balance of smaller loads to achieve the purpose of load balancing.

[0041] Preferably, in step 3, for the message timing planning of a known transmission path, the scheduling process first determines the offset of the first data frame of each message in each data flow link of its path. ij ,of ij Indicates the offset of the first message frame when the i-th message is transmitted on the j-th data flow link of the path, and also determines the end time of the message frame transmission end ij , output static priority generation schedule, the static priority generation schedule includes the start time and end time of each message frame transmission ij ; In step 3, a scheduling table is generated based on the static priority, and the response time and execution time of each message frame are calculated. When calculating the message priority according to the priority evaluation calculation formula, the response ratio R is introduced. The corresponding ratio R is equal to the ratio of the response time to the execution time. The response time and execution time of each message in the scheduling table generated according to the static priority are used to calculate and evaluate the message priority. Then, the messages are prioritized in ascending order. The smaller the evaluation value, the higher the ranking and the higher the priority. Finally, the messages are scheduled and allocated according to the rules according to the priority ranking.

[0042] In the present invention, message scheduling with higher priority will be responded to by the system first; different from the existing SPFR algorithm, during the execution of the business process system, the event manager can modify the priority of message scheduling according to specific rules. In order to maximize the fairness of the priority scheduling algorithm, the core of the algorithm proposed by the present invention is the principle of priority modification. It should be ensured that each message scheduling can obtain reasonable computing resources from the business process system. To this end, the present invention proposes the concept of response ratio. On the premise of ignoring the transmission time, the response time is equal to the sum of the waiting time and the execution time; therefore, the response ratio can also be expressed as 1+waiting time / execution time; therefore, the event manager will periodically calculate and modify the values ​​of all message scheduling priorities, among which the message scheduling with the largest response ratio will be responded to by the system first.

[0043] In the present invention, the event manager will periodically calculate and modify the values ​​of all message scheduling priorities, among which the message scheduling with the largest corresponding ratio will be responded to by the system first; compared with the message scheduling algorithms based on FCFR and SPFR in the prior art, the algorithm of the present invention has the following differences: if the waiting time of the message scheduling in the auxiliary memory buffer queue is the same, the shorter its execution time, the larger its corresponding corresponding ratio, and it will get priority in getting the response of the business process system; this ensures that the business process system can respond to as many message scheduling as possible within a unit time; if the execution time of the message scheduling is the same, the longer its waiting time, the larger its corresponding corresponding ratio; this ensures that the message scheduling with low priority but waiting for a long time in the buffer queue in the auxiliary memory can also get the response of the business process system.

[0044] Embodiment 2:

[0045] like Figure 2 As shown, the 5G message real-time scheduling system in the intelligent Internet of Things environment includes an intelligent Internet of Things platform. The intelligent Internet of Things platform includes a processing terminal and several intelligent terminals. The several intelligent terminals are all communicated with the processing terminal; then the several intelligent terminals send the collected data to the processing terminal, and a TTE multi-hop network topology message scheduling model is established inside the processing terminal. The TTE multi-hop network topology message scheduling model is used to complete the message scheduling of the intelligent Internet of Things platform.

[0046] The TTE multi-hop network topology message scheduling model generates a set of alternative shorter paths for message transmission based on data messages, selects the message path based on the message length and link load, obtains a path planning result with load balancing characteristics, and outputs a static priority generation scheduling table; the scheduling table is generated based on the static priority, the response ratio is calculated according to the message length and period, and the messages are sorted based on the response ratio, and finally the transmission scheduling is allocated according to the sorting.

[0047] In the present invention, by setting a TTE multi-hop network topology message scheduling model, the improved TTE multi-hop network topology message scheduling model can generate a message scheduling table based on messages of different lengths and periods in a complex topology environment, and the generated scheduling table can meet the message delay requirements. Finally, the data in the scheduling table is generated according to the static priority. If the waiting time of the message scheduling in the auxiliary memory buffer queue is the same, the shorter the execution time, the greater the corresponding response ratio, and it will be scheduled by the Internet of Things platform first, which ensures that the Internet of Things platform can schedule and respond to as many messages as possible within the unit; if the execution time of the message scheduling is the same, the longer the waiting time, the greater the corresponding response value; this ensures that a message scheduling event with a low priority but waiting for a long time in the buffer queue in the auxiliary memory can also get a scheduling response from the Internet of Things platform.

[0048] The above is only a preferred embodiment of the present invention. It should be noted that, for those skilled in the art, several improvements and modifications can be made without departing from the principles of the present invention, and these improvements and modifications should also be considered as the protection scope of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention shall be implemented according to the conventional means in the art unless otherwise specified and limited.

Claims

1. A method for real-time scheduling of 5G messages in an intelligent Internet of Things environment, firstly building an intelligent Internet of Things platform, wherein the intelligent Internet of Things platform includes a processing terminal and a plurality of intelligent terminals, wherein the plurality of intelligent terminals are all connected to the processing terminal in communication; then the plurality of intelligent terminals send the collected data to the processing terminal, wherein: The processing terminal performs real-time scheduling on the acquired data message, including the following steps: Step 1: The intelligent IoT platform first constructs a TTE multi-hop network topology message scheduling model; Step 2: The TTE multi-hop network topology message scheduling model generates a set of alternative shorter paths for message transmission according to the data message, selects a message path according to the message length and link load, obtains a path planning result with load balancing characteristics, and outputs a static priority generation scheduling table; Step 3: Generate a scheduling table based on static priority, calculate the response ratio according to the message length and period, sort the messages based on the response ratio, and finally make transmission scheduling allocation based on the sorting.

2. The method for real-time scheduling of 5G messages under the intelligent Internet of Things environment according to claim 1 is characterized in that: In step 1, the TTE multi-hop network includes communication links and a plurality of switches; the plurality of switches and the intelligent terminals, and the switches and the switches are connected via communication links; and the communication links in the TTE multi-hop network adopt a full-duplex mode.

3. The method for real-time scheduling of 5G messages under the intelligent Internet of Things environment according to claim 2 is characterized in that: In the step 1, the TTE multi-hop network topology message scheduling model G{V, E} is established, wherein V represents the collection of all intelligent terminals and switches in the network, and E represents the collection of communication links between intelligent terminals and switches and between switches; in the TTE multi-hop network topology message scheduling model, V=ES∪NS={ES1, ES2, ES3, ES4, ES5}∪{NS1, NS2, NS3, NS4, NS5}, E={VL1, VL2, VL3, VL4, ..., VL i }; Data stream link VL i =[vj,vk]∈L, where L is the link VL i Collection of; v j is the source node of the message, v k is the destination of the message, v j and v k Can be ES or NS, data stream link VL i The speed is R-VL i ; ES stands for intelligent terminal; NS stands for switch.

4. The method for real-time scheduling of 5G messages under the intelligent Internet of Things environment according to claim 3 is characterized in that: In the TTE multi-hop network topology message scheduling model, a network topology matrix G is defined; In the formula, there exists v j , v j ∈V, so that when the data flow link VL i When the network topology matrix element G exists ij The value is 1, when the data flow link VL i When the network topology matrix element G does not exist ij The value is 0; The TT message is modeled as the following six-tuple form, which is used to describe the transmission behavior of the TT message: i ={m i.pe 、m i.l 、m i.s 、m i.d 、m i.pa 、m i.o }; where m i.pe Indicates the time length corresponding to the message cycle, m i.l Indicates the time length corresponding to the transmission time caused by the message length, m i.s Indicates the source node of message transmission, m i.d Indicates the destination node of the message transmission, m i.pa Indicates the message transmission path, m i.o Indicates the offset of the message relative to the start time of the cluster period.

5. The method for real-time scheduling of 5G messages in an intelligent Internet of Things environment according to claim 4 is characterized in that: In step 2, the path planning process of the network message is based on the source node m of the message. i.s , destination node m i.d The transmission path m of each message is determined by the network topology G i.p , the path is an ordered sequence of data flow links {l1, l2, ..., l n }, first, use the K shortest path algorithm to generate a set of candidate paths for each message, then sort the messages according to the rules, and finally select the path with the smallest network link load from the set of candidate paths for the message in the sorted order and add it to the set of planned paths.

6. The method for real-time scheduling of 5G messages in an intelligent Internet of Things environment according to claim 5 is characterized in that: In step 2, after adding the planned path set, define the data flow link l ij The calculation formula for the load B on the The minimum network link utilization Bmin is In the formula, j, k are network nodes, v j ,v k .

7. The method for real-time scheduling of 5G messages in an intelligent Internet of Things environment according to claim 6 is characterized in that: In step 3, for the message timing planning of a known transmission path, the scheduling process first determines the offset of the first data frame of each message in each data flow link of its path. ij ,of ij Indicates the offset of the first message frame when the i-th message is transmitted on the j-th data flow link of the path, and also determines the end time of the message frame transmission end ij , output static priority generation schedule, the static priority generation schedule includes the start time and end time of each message frame transmission ij .

8. The method for real-time scheduling of 5G messages in an intelligent Internet of Things environment according to claim 7 is characterized in that: In the step 3, a scheduling table is generated based on the static priority, the response time and execution time of each message frame are calculated, and the response ratio R is introduced when calculating the message priority according to the priority evaluation calculation formula. The response ratio R is equal to the ratio of the response time to the execution time. The message priority is calculated and evaluated based on the response time and execution time of each message in the scheduling table generated according to the static priority. Then, the messages are prioritized in ascending order. The smaller the evaluation value, the higher the ranking and the higher the priority. Finally, the messages are scheduled and allocated according to the rules according to the priority ranking.

9. 5G message real-time dispatching system under intelligent IoT environment, characterized by: It includes an intelligent Internet of Things platform, which includes a processing terminal and several intelligent terminals, and the several intelligent terminals are all communicatively connected to the processing terminal; then the several intelligent terminals send the collected data to the processing terminal, and a TTE multi-hop network topology message scheduling model is established inside the processing terminal, and the TTE multi-hop network topology message scheduling model is used to complete the message scheduling of the intelligent Internet of Things platform.

10. The 5G message real-time dispatching system under the intelligent Internet of Things environment according to claim 9 is characterized in that: The TTE multi-hop network topology message scheduling model generates a set of alternative shorter paths for message transmission according to the data message, selects a message path according to the message length and link load, obtains a path planning result with load balancing characteristics, and outputs a static priority generation scheduling table; A scheduling table is generated based on static priority, the response ratio is calculated according to the message length and period, and the messages are sorted based on the response ratio. Finally, transmission scheduling is allocated according to the sorting.

Images