Cloud server data transmission and storage method and system based on fuzzy predictive control

Abstract

The present invention discloses a cloud server data transmission and storage method and system based on fuzzy predictive control, the system includes a device end and a cloud server, and the method includes: after the device end completes data acquisition, the data information is sent to the cloud server; the cloud server establishes a fuzzy predictive controller and optimizes the fuzzy predictive controller; the cloud server obtains data information from the device end, and inputs the data level and the current time as fuzzy variables of the fuzzy predictive controller respectively into the fuzzy predictive controller to obtain a sequence table multi-segment function; after the cloud server establishes the sequence table controller, the data information and the sequence table multi-segment function are input into the sequence table controller, the sequence table controller updates the sequence table according to the input data, and sends the updated sequence table to the device end; when the cloud server bandwidth is surplus, the device end sends the corresponding data to the cloud server in sequence according to the sequence in the sequence table. The present invention satisfies the timeliness requirements while making reasonable use of the network bandwidth.

Description

Technical Field

[0001] The present invention relates to fuzzy control technology, and in particular to a cloud server data transmission and storage method and system based on fuzzy predictive control. Background Art

[0002] In recent years, with the development of the Internet of Things and cloud computing, data storage and computing functions are increasingly deployed on servers provided by cloud providers. First, the device collects data, then transmits it to the cloud server through the network for storage and computing, and then transmits the required data to the user when the user needs it. For most companies, this ensures that data can be effectively and securely transmitted and stored while maintaining low costs, especially reducing server maintenance costs. However, there is a clear positive proportional relationship between the computing power and bandwidth of cloud servers and costs, and user needs are extremely sensitive to timeliness. How to reasonably utilize the network bandwidth of cloud servers while meeting the timeliness requirements of users is a problem worth studying. Summary of the invention

[0003] The technical problem to be solved by the present invention is as follows: In view of the above-mentioned problems in the prior art, a cloud server data transmission and storage method and system based on fuzzy predictive control are provided, which can reasonably utilize the cloud server network bandwidth while meeting the timeliness requirements of users.

[0004] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0005] A cloud server data transmission and storage method based on fuzzy predictive control is applied to a cloud service system, wherein the cloud service system includes a device end and a cloud server, and the method includes the following steps:

[0006] S101) After the device completes data collection, it sends the data information to the cloud server;

[0007] S102) The cloud server establishes a fuzzy prediction controller and optimizes the fuzzy prediction controller;

[0008] S103) The cloud server obtains data information from the device end, uses the data level L in the data information as the fuzzy variable E of the fuzzy prediction controller, uses the current time T as the fuzzy variable EC of the fuzzy prediction controller, inputs the fuzzy variables E and EC into the fuzzy prediction controller respectively, and obtains the sequence table multi-segment function f(T,L);

[0009] S104) The cloud server establishes a sequence table controller;

[0010] S105) The cloud server inputs the data information and the multi-segment function f(T, L) of the sequence table into the sequence table controller, and the sequence table controller updates the sequence table according to the input data and sends the updated sequence table to the device end;

[0011] S106) When there is surplus bandwidth on the cloud server, the device sends the corresponding data to the cloud server in sequence according to the order in the priority table.

[0012] Furthermore, the expression of the multi-segment function f(T, L) of the sequence table in step S103) is as follows:

[0013]

[0014] In the above formula, T is the current time, L is the data level, L1 to L n For preset fixed levels, T1 to T m A preset time interval in a day.

[0015] Furthermore, before step S105), it also includes: if the time interval between the current time T and the time T1 of the last update of the priority table is less than the preset time period Tt, return to step S103), until the time interval between the current time T and the time T1 of the last update of the priority table is equal to the preset time period Tt.

[0016] Further, in step S103), the time interval between the current time T and the previous time T-1 is equal to the preset time period Tt.

[0017] Furthermore, step S106) includes a step of determining the order of priority in the priority table, specifically including: sorting the data in the priority table in order from large to small according to the priority value, with the data with large priority value at the front; if there are data with the same priority value, the data with large data level at the front; if there are data with the same priority value and the same data level, the data with small device number at the front; if there are data with the same priority value, data level and device number, the data with small file number at the front.

[0018] Further, step S106) includes the following steps:

[0019] Subtract the allocated bandwidth from the bandwidth of the cloud server to get the remaining bandwidth of the cloud server;

[0020] Select the current data information in the priority table, and compare the device bandwidth in the current data information with the remaining bandwidth of the cloud server;

[0021] If the remaining bandwidth of the cloud server is greater than the device bandwidth, find the current data according to the file number in the current data information, allocate the bandwidth of the upload channel according to the device bandwidth in the current data information, send the current data to the cloud server through the upload channel, release the bandwidth of the corresponding upload channel after the current data is uploaded, and delete the current data information in the priority table;

[0022] If the remaining bandwidth of the cloud server is less than the bandwidth of the device, after waiting for a preset period of time, the step of subtracting the allocated bandwidth from the bandwidth of the cloud server is performed again.

[0023] Furthermore, the data information includes data level L, file number F, device number D, and device bandwidth B.

[0024] Furthermore, the cloud service system further includes a user terminal, and the method further includes:

[0025] S201) The cloud server obtains the data requirements of the user terminal;

[0026] S202) The cloud server matches the data demand with the stored data. If a match result exists, the cloud server sends the match result to the user end, and ends and exits. If no match result exists, the cloud server forwards the data demand to the device end.

[0027] S203) After receiving the data demand, the device matches the data demand with the priority table to obtain a matching result, sends the matching result to the cloud server first, and deletes the data information of the matching result in the priority table;

[0028] S204) The cloud server processes and stores the matching results of the device and sends them to the user.

[0029] The present invention also provides a cloud service system, including a cloud server and a device end, wherein:

[0030] The device is used to send data information to the cloud server after completing data collection; it is also used to send the corresponding data to the cloud server in sequence according to the order in the priority table when there is surplus bandwidth in the cloud server;

[0031] The cloud server is used to establish a fuzzy predictive controller and optimize the fuzzy predictive controller; then, data information is obtained from the device side, and the data level L in the data information is used as the fuzzy variable E of the fuzzy predictive controller, and the current time T is used as the fuzzy variable EC of the fuzzy predictive controller. The fuzzy variables E and EC are respectively input into the fuzzy predictive controller to obtain a priority table multi-segment function f(T,L); then, a priority table controller is established, and the data information and the priority table multi-segment function f(T,L) are input into the priority table controller. The priority table controller updates the priority table according to the input data and sends the updated priority table to the device side.

[0032] Furthermore, it also includes a user end, wherein the user end is used to send a data request to the cloud server, and then wait for and receive a return result from the cloud server;

[0033] The cloud server is also used to obtain the data requirements of the user end; then match the data requirements with the stored data, and if there is a matching result, send the matching result to the user end; if there is no matching result, forward the data requirement to the device end; and process and store the matching result of the device end and then send it to the user end;

[0034] The device end is used to match the data demand with the priority table to obtain a matching result after receiving the data demand, and after sending the matching result to the cloud server in priority, delete the data information of the matching result in the priority table.

[0035] Compared with the prior art, the present invention has the following advantages:

[0036] The present invention adopts the fuzzy prediction control method, takes the file level in the data collected by the device end and the time period of the user's data demand as the fuzzy variables of the fuzzy prediction controller, and according to the priority table output by the fuzzy prediction controller, when there is surplus bandwidth on the server, the corresponding file data is uploaded to the cloud server for storage according to the order in the priority table for calculation and user browsing and downloading. It can realize the reasonable use of the network bandwidth of the cloud server, so that the data can be saved to the cloud server to the greatest extent; and it can realize the prediction of customer request data, so as to reduce the customer waiting time. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 The figure is a schematic diagram of the application scenario structure of an embodiment of the present invention.

[0038] Figure 2 is a flow chart of an embodiment of the present invention.

[0039] Figure 3 This is a flow chart of a cloud server returning a request result according to a request from a user terminal in an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The present invention is further described below in conjunction with the accompanying drawings and specific preferred embodiments, but the protection scope of the present invention is not limited thereby.

[0041] Before introducing the specific embodiments of the present invention, the relevant concepts are first explained:

[0042] Fuzzy controller: Fuzzy controller is a kind of control that imitates humans. In the process of controlling the controlled object, decisions are generally made based on the deviation E between the set value and the controlled quantity, the deviation change EC and the rate of deviation change ER. People are most sensitive to deviations, followed by the change in deviations, and then the rate of deviation change. Therefore, the input variables of the fuzzy controller are usually E, E and EC, or EC and ER, which constitute the so-called one-dimensional, two-dimensional and three-dimensional fuzzy controllers respectively. The dynamic performance of the one-dimensional fuzzy controller is not good, and it is usually used for first-order controlled objects. The control performance and control complexity of the two-dimensional fuzzy controller are relatively good, and it is a widely used form at present. In addition, the incremental algorithm is generally selected as the output variable of the fuzzy controller.

[0043] Designing a stable and accurate cloud server data transmission and storage strategy with superior control performance and simple implementation is an important requirement for cloud service-related commercial projects. Figure 1 As shown in the figure, in the application scenarios including cloud servers, device ends and user ends, data generation is periodic, user needs are extremely sensitive to timeliness, and user needs have certain regularities from an overall perspective, which makes it difficult to establish an accurate physical model to describe the entire process. Therefore, a fuzzy predictive control algorithm is introduced to control the cloud server data transmission and storage process.

[0044] Embodiment 1

[0045] based on Figure 1 In the application scenario shown, this embodiment proposes a cloud server data transmission and storage method based on fuzzy predictive control, which is mainly divided into a fuzzy control decision stage and a priority table decision stage. In the fuzzy control decision stage, the device inputs data-related parameters to the fuzzy controller in the cloud server through the network. In the priority table decision stage, the priority table controller maintains the priority table through the file priority table value and other file information obtained in the previous stage. The device selects the priority table according to the file attributes and allocates the bandwidth of the cloud server through its priority and bandwidth to transmit data.

[0046] Specifically, for the fuzzy controller, we have:

[0047] (1) Selection of fuzzy variables

[0048] In different time periods, users' demands for data of different levels have certain regularity. In order to store and calculate the data required by users in advance, time and data level are selected as fuzzy variables.

[0049] (2) Fuzzy rule design

[0050] Before designing fuzzy rules, fuzzy variables need to be fuzzified. When fuzzifying, the accuracy of fuzzy decisions needs to be determined. Fuzzification principles are designed based on the accuracy of fuzzy decisions and the intensity of the influence of variables on node data scheduling. That is, the higher the accuracy of the output, the more states are generated after fuzzification; the greater the influence of variables on system performance, the more states are generated by fuzzification. After determining the number of states at a time, fuzzy variables need to be used to set fuzzy decisions based on the actual impact of each state combination on the system. Due to different strategies for processing different levels at different times, different fuzzy rule tables are designed to adapt to different goals.

[0051] (3) Generation of fuzzy decision

[0052] The input of the fuzzy controller is time T and data level L, and the output is a multi-segment function f(T,L) of the order table, which divides the data into n fixed values ​​of levels according to the characteristics, namely L 1, L 2, L3…L n ; Divide a day into m intervals, namely T 1, T 2, T3…T m ; Where E of the fuzzy controller is the data level value L, and EC is the current time and interval difference △T. A time period and level have corresponding fuzzy output U, namely function f(T,L). After obtaining this information, a fuzzy state is generated according to the fuzzification rules, and a fuzzy decision is obtained from the fuzzy state according to the fuzzy rules. The expression of function f(T,L) is as follows:

[0053]

[0054] In the above formula, T is the current time, L is the data level, L1 to L n For preset fixed levels, T1 to T m A preset time interval in a day.

[0055] For the sequence table controller, there are:

[0056] (1) Number of ranking tables

[0057] The input of the priority table controller is the priority table multi-segment function f(T,L) and the file number F as well as the device number D and the device bandwidth B. The output is the file number F to be transmitted. m , from formula (1), we can see that since the current time T is constantly changing, the number of priority tables is theoretically infinite. Every time new data needs to be transmitted, the priority table must be updated. Obviously, this requires a lot of server computing power and will affect the normal transmission of data when there are many files. Therefore, every time T t Only update it, so you only need to maintain 24 / T tThe sequence table function only needs to be updated when entering the sequence table controller 24 / T t Secondary value.

[0058] (2) Sequence table transmission strategy

[0059] The server will reserve a certain amount of bandwidth for communication with the device and client, as well as for data transmission when the client has sudden data demands. The remaining bandwidth will be allocated according to the device bandwidth from large to small based on the current time priority table. Only one data transmission can exist on a device at the same time.

[0060] (3) Other rules for the ranking table

[0061] From the above fuzzy controller rules, it can be seen that the priority table values ​​of data of the same level are the same at a certain moment, and data of different levels may also be equal at a certain moment. At this time, it is necessary to formulate an algorithm according to actual needs to select the data for priority transmission.

[0062] like Figure 2 As shown, the method of this embodiment includes the following steps:

[0063] S101) After the device completes data collection, it sends the data information to the cloud server. The data information includes data level L, file number F, device number D, and device bandwidth B;

[0064] S102) The cloud server establishes a fuzzy prediction controller and optimizes the fuzzy prediction controller;

[0065] S103) The cloud server obtains data information from the device end at a certain time interval, uses the data level L in the data information as the fuzzy variable E of the fuzzy prediction controller, uses the current time T as the fuzzy variable EC of the fuzzy prediction controller, and inputs the fuzzy variables E and EC into the fuzzy prediction controller respectively to obtain the sequence table multi-segment function f(T,L);

[0066] S104) The cloud server establishes a sequence table controller;

[0067] S105) The cloud server inputs the data information and the multi-segment function f(T, L) of the sequence table into the sequence table controller, and the sequence table controller updates the sequence table according to the input data and sends the updated sequence table to the device end;

[0068] S106) When there is surplus bandwidth on the cloud server, the device sends the corresponding data to the cloud server in sequence according to the order in the priority table.

[0069] In step S103 of this embodiment, the expression of the sequence table multi-segment function f(T, L) is as shown in the above formula (1). It should be noted that T1 to T mThe selection of the time interval is determined according to the user's demand for data, which can be achieved through empirical data or expert analysis.

[0070] Since the update interval of the priority table is time Tt, this embodiment can be implemented in the following two ways:

[0071] The first method adds a new step before step S105): if the time interval between the current time T and the time T1 of the last update of the ranking table is less than the preset time period Tt, return to step S103) until the time interval between the current time T and the time T1 of the last update of the ranking table is equal to the preset time period Tt.

[0072] The second way is to set step S103) so that the time interval between the current time T and the previous time T-1 is equal to the preset time period Tt.

[0073] These two methods can be selected according to the server computing power. It should be noted that the update interval of the priority table as time Tt is not limited to the above two methods. Technical personnel in this field can make adjustments based on these two methods according to actual conditions.

[0074] In step S105 of this embodiment, the objects of updating the priority table include the priority value in the priority table and the corresponding data file information. Taking into account the situation that there are data files with equal priority values ​​in the priority table, step S106) includes the step of determining the order in the priority table, specifically including: sorting the data in the priority table in order from large to small according to the priority value, with the data with large priority value at the front; if there are data with the same priority value, the data with large data level at the front; if there are data with the same priority value and the same data level, the data with small device number at the front; if there are data with the same priority value, data level and device number, the data with small file number at the front.

[0075] In this embodiment, step S106) includes the following steps of uploading data according to the data information in the sequence table:

[0076] Subtract the allocated bandwidth from the bandwidth of the cloud server to get the remaining bandwidth of the cloud server;

[0077] Select the current data information in the priority table, and compare the device bandwidth in the current data information with the remaining bandwidth of the cloud server;

[0078] If the remaining bandwidth of the cloud server is greater than the device bandwidth, find the current data according to the file number in the current data information, allocate the bandwidth of the upload channel according to the device bandwidth in the current data information, send the current data to the cloud server through the upload channel, release the bandwidth of the corresponding upload channel after the current data is uploaded, and delete the current data information in the priority table;

[0079] If the remaining bandwidth of the cloud server is less than the bandwidth of the device, after waiting for a preset period of time, the step of subtracting the allocated bandwidth from the bandwidth of the cloud server is performed again.

[0080] because Figure 1 The cloud service system in the example also includes the user end. The cloud server needs to return the request result according to the user end's request, such as Figure 3 As shown, the method of this embodiment also includes:

[0081] S201) The cloud server obtains the data requirements of the user terminal;

[0082] S202) The cloud server matches the data demand with the stored data. If a match result exists, the cloud server sends the match result to the user end, and ends and exits. If no match result exists, the cloud server forwards the data demand to the device end.

[0083] S203) After the device receives the data demand, it matches the data demand with the priority table to obtain the matching result, sends the matching result to the cloud server first, and then deletes the data information of the matching result in the priority table; specifically, when the matching result is sent to the cloud server first, the data information of the matching result in the priority table is moved to the front of the priority table, and the subsequent process of uploading data according to the data information is basically the same as step S106), which will not be repeated here.

[0084] S204) The cloud server processes and stores the matching results of the device and sends them to the user.

[0085] Through the above steps S101 to S106, and steps S201 to S204, it can be ensured that user needs are responded to in the shortest time, while the data on the device side is saved to the cloud server to the greatest extent for calculation and user browsing and downloading.

[0086] The method of this embodiment is described below by a specific example: for a cloud service system including a cloud server, n collection devices, and several clients, when the collection device collects data, there are three types of data, namely status data, key data, and media data, among which:

[0087] The amount of real-time status data is very small. When users query the real-time status, they often only need to forward it directly through the server. However, when users need to query the average data and overall data within a certain period of time, the total amount of data is large and requires a lot of calculations. In order to respond to customer needs in a timely manner, the data should be transferred to the cloud server for calculation in advance. The overall data volume is medium.

[0088] The amount of key data is relatively small, and it mainly consists of some key data collected by the equipment.

[0089] The amount of media data is very large, mainly video data collected by the device.

[0090] Critical data must be kept intact on the cloud server. However, due to limited server bandwidth, when local storage of media data on the device is insufficient, the oldest data can be deleted.

[0091] The fuzzy variables of the fuzzy prediction controller are E, L, B (media data), M (state data), and S (key data).

[0092] After the equipment completes the data collection, the data level L and file number F will be transmitted to the cloud server. According to the summary, the customer's demand for data is mainly divided into three parts: morning period, afternoon period and night period, among which:

[0093] In the morning, customers are more interested in status data, followed by key data; in the afternoon, customers are more interested in key data, followed by status data; in the evening, customers are more interested in media data, but the overall requests are relatively small.

[0094] The fuzzy variable EC of the fuzzy prediction controller is △T, which represents the time difference between the current time and the corresponding time period in the morning, afternoon and night time periods. In order to simplify the number of sequence tables, each time period is only divided into two parts from the center, that is, the morning period is divided into NS and NB; the afternoon period is divided into ZS and ZB; the night period is divided into PS and PB. At this time, the relationship between △T and EC fuzzy sets is one-to-one correspondence.

[0095] The fuzzy set of the output U of the fuzzy predictive controller is divided into five levels: NB, NS, ZO, PS, and PB. The simplified fuzzy predictive controller rule table, variables and output U, i.e., f(T, L), are shown in the following table.

[0096] Table 1 Fuzzy predictive controller variables and output relationships

[0097]

[0098]

[0099] In Table 1, when E belongs to B and EC belongs to NS, the output U belongs to NB. Similarly, when E belongs to B and EC belongs to NB, the output U belongs to NS, and so on.

[0100] After obtaining the fuzzy prediction controller output U, i.e., f(T, L), it is used together with the corresponding data level L, file number F, etc. as the input of the priority table controller. In order to further simplify the controller logic and reduce the number of priority tables to one, the output is used as the variable of the priority table. Every time the time period changes and the priority table needs to be updated, the priority table will calculate the priority value V according to the output of the fuzzy prediction controller, as shown below:

[0101] Table 2 Sequence value update calculation table

[0102]

[0103] Finally, we get an updated ranking table, the structure of which is as follows:

[0104] Table 3 Ranking table

[0105]

[0106] When the device transmits data according to the updated priority table, if V1>V2>V3 and D1≠D2≠D3, file F1 is transmitted first, and then the bandwidth of the cloud server is deducted from the bandwidth value B1, and the process is repeated until the remaining bandwidth of the cloud server cannot meet the transmission of the next priority value file. When the time period changes, all priority values ​​in the priority table are input into the fuzzy prediction controller for calculation to obtain the updated priority value and corresponding data information.

[0107] Since there will be a large number of data files with equal priority values, the following rules are established: when the priority values ​​are equal, the file level S is first and M is second; when the first two are equal, the file with the smaller device number is first; when the first three are equal, the file with the smaller file number is first; a device can only transfer one file at a time. Since the combination of device number and file number is unique, the order of the priority table is also unique.

[0108] When the data transmission is completed, the file number will be deleted from the priority list, and the data has been stored in the cloud server database for computing and user browsing and downloading. When the user makes a data request, if the data file has not been transmitted, the data should be transmitted immediately and the file number in the priority list should be deleted to ensure that the user's needs are responded to in the shortest time.

[0109] Embodiment 2

[0110] This embodiment provides a cloud service system, including a cloud server and a device end, wherein:

[0111] The device is used to send data information to the cloud server after completing data collection; it is also used to send the corresponding data to the cloud server in sequence according to the order in the priority table when there is surplus bandwidth in the cloud server;

[0112] The cloud server is used to establish a fuzzy predictive controller and optimize the fuzzy predictive controller; then, data information is obtained from the device side, and the data level L in the data information is used as the fuzzy variable E of the fuzzy predictive controller, and the current time T is used as the fuzzy variable EC of the fuzzy predictive controller. The fuzzy variables E and EC are respectively input into the fuzzy predictive controller to obtain a priority table multi-segment function f(T,L); then, a priority table controller is established, and the data information and the priority table multi-segment function f(T,L) are input into the priority table controller. The priority table controller updates the priority table according to the input data and sends the updated priority table to the device side.

[0113] The cloud service system of this embodiment further includes a user end, wherein the user end is used to send a data request to the cloud server, and then wait for and receive a return result from the cloud server;

[0114] The cloud server is also used to obtain the data requirements of the user end; then match the data requirements with the stored data, and if there is a matching result, send the matching result to the user end; if there is no matching result, forward the data requirement to the device end; and process and store the matching result of the device end and then send it to the user end;

[0115] The device end is used to match the data demand with the priority table to obtain a matching result after receiving the data demand, and after sending the matching result to the cloud server in priority, delete the data information of the matching result in the priority table.

[0116] In summary, the present invention adopts fuzzy prediction control for the data transmission and storage process, the algorithm is simple and easy to implement, the system is robust and stable, stable and accurate, the control performance is excellent, and the implementation is simple. It can realize the reasonable use of the cloud server network bandwidth, so that the data can be stored on the cloud server to the greatest extent; according to the fuzzy prediction algorithm, it can realize the prediction of customer request data, so that the customer waiting time is reduced. The method in the present invention can also be slightly modified and applied to other similar application scenarios.

[0117] The above is only a preferred embodiment of the present invention, and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment, it is not intended to limit the present invention. Therefore, any simple modification, equivalent change and modification made to the above embodiment according to the technical essence of the present invention without departing from the content of the technical solution of the present invention shall fall within the scope of protection of the technical solution of the present invention.

Claims

1. A cloud server data transmission and storage method based on fuzzy predictive control, characterized in that: Applied to a cloud service system, the cloud service system includes a device end and a cloud server, and the method includes the following steps: S101) After the device completes data collection, it sends the data information to the cloud server; S102) The cloud server establishes a fuzzy prediction controller and optimizes the fuzzy prediction controller; S103) The cloud server obtains data information from the device end, uses the data level L in the data information as the fuzzy variable E of the fuzzy prediction controller, uses the current time T as the fuzzy variable EC of the fuzzy prediction controller, inputs the fuzzy variables E and EC into the fuzzy prediction controller respectively, and obtains the sequence table multi-segment function f(T, L), which is expressed as follows: In the above formula, T is the current time, L is the data level, L1 to L n For preset fixed levels, T1 to T m Preset time intervals for the day; S104) The cloud server establishes a sequence table controller; S105) The cloud server inputs the data information and the multi-segment function f(T, L) of the sequence table into the sequence table controller, and the sequence table controller updates the sequence table according to the input data and sends the updated sequence table to the device end; S106) When there is surplus bandwidth on the cloud server, the device sends the corresponding data to the cloud server in sequence according to the order in the priority table.

2. The cloud server data transmission and storage method based on fuzzy predictive control according to claim 1 is characterized in that: Before step S105), the process also includes: if the time interval between the current time T and the time T1 of the last update of the priority table is less than the preset period Tt, returning to step S103), until the time interval between the current time T and the time T1 of the last update of the priority table is equal to the preset period Tt.

3. The cloud server data transmission and storage method based on fuzzy predictive control according to claim 1 is characterized in that: In step S103), the time interval between the current time T and the previous time T-1 is equal to the preset time period Tt.

4. The cloud server data transmission and storage method based on fuzzy predictive control according to claim 1 is characterized in that: Step S106) includes the step of determining the order of priority in the priority table, specifically including: sorting the data in the priority table in order from large to small according to the priority value, with the data with large priority value at the front; if there are data with the same priority value, the data with large data level at the front; if there are data with the same priority value and the same data level, the data with small device number at the front; if there are data with the same priority value, data level and device number, the data with small file number at the front.

5. The cloud server data transmission and storage method based on fuzzy predictive control according to claim 1 is characterized in that: Step S106) includes the following steps: Subtract the allocated bandwidth from the bandwidth of the cloud server to get the remaining bandwidth of the cloud server; Select the current data information in the priority table, and compare the device bandwidth in the current data information with the remaining bandwidth of the cloud server; If the remaining bandwidth of the cloud server is greater than the device bandwidth, find the current data according to the file number in the current data information, allocate the bandwidth of the upload channel according to the device bandwidth in the current data information, send the current data to the cloud server through the upload channel, release the bandwidth of the corresponding upload channel after the current data is uploaded, and delete the current data information in the priority table; If the remaining bandwidth of the cloud server is less than the bandwidth of the device, after waiting for a preset period of time, the step of subtracting the allocated bandwidth from the bandwidth of the cloud server is performed again.

6. The cloud server data transmission and storage method based on fuzzy predictive control according to claim 1 is characterized in that: The data information includes data level L, file number F, device number D, and device bandwidth B.

7. The cloud server data transmission and storage method based on fuzzy predictive control according to claim 1 is characterized in that: The cloud service system further includes a user end, and the method further includes: S201) The cloud server obtains the data requirements of the user terminal; S202) The cloud server matches the data demand with the stored data. If a match result exists, the cloud server sends the match result to the user end, and ends and exits. If no match result exists, the cloud server forwards the data demand to the device end. S203) After receiving the data demand, the device matches the data demand with the priority table to obtain a matching result, sends the matching result to the cloud server first, and deletes the data information of the matching result in the priority table; S204) The cloud server processes and stores the matching results of the device and sends them to the user.

8. A cloud service system, characterized in that: Including cloud server and device side, including: The device is used to send data information to the cloud server after completing data collection; it is also used to send the corresponding data to the cloud server in sequence according to the order in the priority table when there is surplus bandwidth in the cloud server; The cloud server is used to establish a fuzzy prediction controller and optimize the fuzzy prediction controller; then, data information is obtained from the device end, and the data level L in the data information is used as the fuzzy variable E of the fuzzy prediction controller, and the current time T is used as the fuzzy variable EC of the fuzzy prediction controller. The fuzzy variables E and EC are respectively input into the fuzzy prediction controller to obtain the sequence table multi-segment function f(T,L), which is expressed as follows: In the above formula, T is the current time, L is the data level, L1 to L n For preset fixed levels, T1 to T m It is a preset time interval in a day; then a priority table controller is established, and the data information and the priority table multi-segment function f(T, L) are input into the priority table controller. The priority table controller updates the priority table according to the input data and sends the updated priority table to the device end.

9. The cloud service system according to claim 8, characterized in that: It also includes a user end, which is used to send a data request to the cloud server and then wait for and receive a return result from the cloud server; The cloud server is also used to obtain the data requirements of the user end; then match the data requirements with the stored data, and if there is a matching result, send the matching result to the user end; if there is no matching result, forward the data requirement to the device end; and process and store the matching result of the device end and then send it to the user end; The device end is used to match the data demand with the priority table to obtain a matching result after receiving the data demand, and after sending the matching result to the cloud server in priority, delete the data information of the matching result in the priority table.

Images