An edge computing evaluation system based on artificial intelligence

Abstract

The present invention provides an edge computing evaluation system based on artificial intelligence, including an edge monitoring module, a central evaluation module, a transmission monitoring module, and a central monitoring module. The edge monitoring module is used to monitor the data processing situation of the edge server during the evaluation time period. The transmission monitoring module is used to monitor the data transmission situation between the edge server and the central server during the evaluation time period. The central monitoring module is used to monitor the data processing situation of the central server for the data uploaded by the edge server during the evaluation time period. The central evaluation module evaluates the edge computing situation of the edge server according to the monitoring data of the above three monitoring modules. When evaluating, this system evaluates edge computing based on data from three aspects: the edge side, the central side, and the transmission side, and adjusts the data allocation for edge computing according to the evaluation results to make the operation efficiency of edge computing higher.

Description

Technical Field

[0001] The present invention relates to the field of electrical digital data processing, and more particularly to an edge computing evaluation system based on artificial intelligence. Background Art

[0002] Edge computing refers to an open platform that integrates network, computing, storage, and application core capabilities on the side close to the object or the data source, providing the nearest-end services nearby. Its application programs are initiated on the edge side, generating faster network service responses, and meeting the basic needs of the industry in aspects such as real-time services, application intelligence, security, and privacy protection. Edge computing is located between physical entities and industrial connections, or at the top of physical entities. Edge computing and cloud computing distribute data, and a reasonable distribution method will improve the overall processing efficiency. There is a need for an evaluation system to evaluate the current data distribution method of edge computing and adjust the distribution method according to the evaluation results.

[0003] The foregoing discussion of the background art is only intended to facilitate an understanding of the present invention. This discussion does not recognize or admit that any of the materials mentioned is part of the common general knowledge.

[0004] Many evaluation systems have been developed. After a large amount of retrieval and reference by us, it is found that existing evaluation systems are like the system disclosed in the publication number CN110045679B. These systems generally include data acquisition, data splicing, data alignment, data quality judgment, and edge algorithm invocation. Among them, an acceleration sensor is used to collect the vibration signal of the spindle at a high-frequency sampling rate, and the machine tool controller signal is collected at a low-frequency sampling rate through the machine tool controller communication protocol; the high-frequency data and the low-frequency data are respectively spliced; according to the timestamp information of the high-frequency data, the corresponding low-frequency information is searched in the cache, and cross-judgment is made based on the aligned low-frequency data and high-frequency data to judge whether the signals of the machine tool and the sensor are abnormal at the data source; an edge algorithm is invoked to extract features from the data to obtain edge feature values. However, this system only evaluates the quality of the data and does not evaluate the data distribution method, and the processing efficiency of edge computing still needs to be improved. Summary of the Invention

[0005] The object of the present invention is to propose an edge computing evaluation system based on artificial intelligence for the existing deficiencies.

[0006] The present invention adopts the following technical solutions:

[0007] An edge computing evaluation system based on artificial intelligence, comprising an edge monitoring module, a central evaluation module, a transmission monitoring module and a central monitoring module. The edge monitoring module is used to monitor the data processing situation of the edge server within the evaluation time period. The transmission monitoring module is used to monitor the data transmission situation between the edge server and the central server within the evaluation time period. The central monitoring module is used to monitor the data processing situation of the central server for the data uploaded by the edge server within the evaluation time period. The central evaluation module evaluates the edge computing situation of the edge server according to the monitoring data of the above three monitoring modules;

[0008] The edge monitoring module processes the monitored data to obtain an edge processing index Q1 and a load index Q2. The transmission monitoring module processes the monitored data to obtain a transmission index Q3. The central monitoring module processes the monitored data to obtain a central processing index Q4. The central evaluation module processes the above four indexes of all edge servers to obtain the index ranges of the edge processing index [Q1 min ,Q1 max , the index range of the load index [Q2 min ,Q2 max , the index range of the transmission index [Q3 min ,Q3 max , and the index range of the central processing index [Q4 min ,Q4 max ;

[0009] The central evaluation module calculates the evaluation value E of each edge server within the evaluation time period according to the following formula:

[0010]

[0011] The larger the evaluation value of the edge server, the more the edge server needs to adjust the data allocation for edge computing;

[0012] Furthermore, the edge monitoring module calculates the edge processing index Q1 of the edge server according to the following formula:

[0013]

[0014] Where n is the total number of data batches generated by the terminal within the evaluation time period, Td(i) is the time interval between the edge server receiving the i-th batch of data and obtaining the i-th batch of processing results monitored by the edge monitoring module, Ta(i) is the time interval between obtaining the i-th batch of processing results and applying the i-th batch of processing results monitored by the edge monitoring module, and Se(i) is the amount of the i-th batch of data retained in the edge server;

[0015] Further, the edge monitoring module calculates the load index Q2 of the edge server according to the following formula:

[0016]

[0017] where P(i) is the ratio of the amount of the i-th batch of data retained in the edge server to the amount of the i-th batch of data generated by the terminal;

[0018] Further, the transmission monitoring module calculates the transmission index Q3 according to the following formula:

[0019]

[0020] where T is the duration of the evaluation period, Tin is the cumulative time for the edge server to transmit data to the central server within the evaluation period, and Tout is the cumulative time for the central server to transmit data to the edge server within the evaluation period;

[0021] Further, the central monitoring module calculates the central processing index Q4 of the edge server according to the following formula:

[0022]

[0023] where T 0 is the standard processing time, Tc(i) is the time interval from when the central server receives the i-th batch of data from the edge server to when the i-th batch of data is processed to obtain the processing result, and Sc(i) is the amount of the i-th batch of data sent by the edge server to the central server.

[0024] The beneficial effects achieved by the present invention are as follows:

[0025] By setting three monitoring modules to monitor the data processing or circulation conditions of the edge server, the transmission channel, and the central server respectively, this system integrates all the monitoring data corresponding to the edge servers monitored by these three monitoring modules to obtain a standard range, and then evaluates a single edge server based on the standard range. The evaluation value can accurately reflect whether the data distribution method of the edge server is reasonable. Based on the evaluation results, the data distribution is adjusted, ultimately improving the overall efficiency of edge computing.

[0026] To enable a further understanding of the features and technical content of the present invention, please refer to the following detailed description of the present invention and the attached drawings. However, the attached drawings are only provided for reference and illustration, and are not intended to limit the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 is a schematic diagram of the overall structural framework of the present invention;

[0028] Figure 2Schematic diagram of data distribution according to the present invention;

[0029] Figure 3 Schematic diagram of time data monitored according to the present invention;

[0030] Figure 4 Schematic diagram of the processing flow of the target index according to the present invention;

[0031] Figure 5 Schematic diagram of the evaluation process carried out by the central evaluation module according to the present invention. Detailed implementation manners

[0032] The following are specific embodiments to illustrate the implementation manners of the present invention. Those skilled in the art can understand the advantages and effects of the present invention from the content disclosed in this specification. The present invention can be implemented or applied through other different specific embodiments, and various details in this specification can also be modified and changed based on different viewpoints and applications without departing from the spirit of the present invention. Additionally, the drawings of the present invention are only simple schematic illustrations and are not drawn according to actual sizes, which is hereby stated in advance. The following implementation manners will further detail the related technical content of the present invention, but the disclosed content is not intended to limit the protection scope of the present invention.

[0033] Embodiment 1.

[0034] This embodiment provides an edge computing evaluation system based on artificial intelligence, combined with Figure 1 , including an edge monitoring module, a central evaluation module, a transmission monitoring module, and a central monitoring module. The edge monitoring module is used to monitor the data processing situation of the edge server during the evaluation time period. The transmission monitoring module is used to monitor the data transmission situation between the edge server and the central server during the evaluation time period. The central monitoring module is used to monitor the data processing situation of the central server for the data uploaded by the edge server during the evaluation time period. The central evaluation module evaluates the edge computing situation of the edge server according to the monitoring data of the above three monitoring modules;

[0035] The edge monitoring module processes the monitored data to obtain an edge processing index Q1 and a load index Q2. The transmission monitoring module processes the monitored data to obtain a transmission index Q3. The central monitoring module processes the monitored data to obtain a central processing index Q4. The central evaluation module processes the above four indexes of all edge servers to obtain the index range of the edge processing index [Q1 min , Q1 max , the index range of the load index [Q2 min , Q2 max , the index range of the transmission index [Q3 min , Q3 max , and the index range of the central processing index [Q4min , Q4 max ;

[0036] The central evaluation module calculates the evaluation value E of each edge server within the evaluation period according to the following formula:

[0037]

[0038] The larger the evaluation value of the edge server, the more the edge server needs to adjust the data allocation for edge computing;

[0039] The edge monitoring module calculates the edge processing index Q1 of the edge server according to the following formula:

[0040]

[0041] where n is the total number of data batches generated by the terminal within the evaluation period, Td(i) is the time interval between the edge server receiving the i-th batch of data and obtaining the i-th batch of processing results monitored by the edge monitoring module, Ta(i) is the time interval between obtaining the i-th batch of processing results and applying the i-th batch of processing results monitored by the edge monitoring module, and Se(i) is the amount of the i-th batch of data retained in the edge server;

[0042] The edge monitoring module calculates the load index Q2 of the edge server according to the following formula:

[0043]

[0044] where P(i) is the ratio of the amount of the i-th batch of data retained in the edge server to the amount of the i-th batch of data generated by the terminal;

[0045] The transmission monitoring module calculates the transmission index Q3 according to the following formula:

[0046]

[0047] where T is the duration of the evaluation period, Tin is the cumulative time for the edge server to transmit data to the central server within the evaluation period, and Tout is the cumulative time for the central server to transmit data to the edge server within the evaluation period;

[0048] The central monitoring module calculates the central processing index Q4 of the edge server according to the following formula:

[0049]

[0050] where T 0is the standard processing time, Tc(i) is the time interval from when the central server receives the i-th batch of data from the edge server to when the central server processes the i-th batch of data to obtain a processing result, and Sc(i) is the amount of data of the i-th batch sent by the edge server to the central server.

[0051] Embodiment 2.

[0052] This embodiment includes all the contents of Embodiment 1 and provides an edge computing evaluation system based on artificial intelligence, including an edge monitoring module, a central evaluation module, a transmission monitoring module, and a central monitoring module. The edge monitoring module is used to monitor the data processing situation of the edge server. The transmission monitoring module is used to monitor the amount of data transmitted by the edge server to the central server. The central monitoring module is used to monitor the data processing situation of the central server for the data uploaded by the edge server. The central evaluation module evaluates the edge computing of the edge server according to the monitoring data of the above three modules;

[0053] Combined with Figure 2 , the edge server sorts the data generated by the terminal. Part of the data is retained in the edge server for processing, and part of the data is sent to the central server for processing. The central server then feeds back the processing result to the edge server. The edge monitoring module counts the amount of data generated in each batch and the amount of data retained in the edge server, and obtains Sz(i) and Se(i) respectively, where i is the batch number of the data generated by the terminal;

[0054] The amount of data Sc(i) sent by the edge server to the central server is:

[0055] Sc(i) = Sz(i) - Se(i);

[0056] The proportion P(i) of the amount of data retained in the edge server is:

[0057]

[0058] Combined with Figure 3 , after the edge server performs edge computing on the data to obtain a processing result, the processing result is applied to the local terminal. The edge monitoring module counts the time interval from when the edge server receives the data to when it obtains the processing result, and obtains Td(i). The edge monitoring module counts the time interval from when it obtains the processing result to when it applies the processing result, and obtains Ta(i);

[0059] The edge monitoring module calculates the edge processing index Q1 of the edge server according to the following formula:

[0060]

[0061] Among them, n is the total number of data batches generated by the terminal within the evaluation time period;

[0062] The edge monitoring module calculates the load index Q2 of the edge server according to the following formula:

[0063]

[0064] The edge monitoring module sends the edge processing index and the load index to the central evaluation module;

[0065] The transmission monitoring module counts the cumulative time Tin for the edge server to transmit data to the central server and the cumulative time Tout for the central server to transmit data to the edge server within the evaluation time period, and calculates the transmission index Q3 according to the following formula:

[0066]

[0067] Among them, T is the duration of the evaluation time period;

[0068] The transmission monitoring module sends the transmission index to the central evaluation module;

[0069] The central monitoring module counts the time interval from when the central server receives data from a single edge server to when the data is processed to obtain the processing result, and obtains Tc(i);

[0070] The central monitoring module calculates the central processing index Q4 of the edge server according to the following formula:

[0071]

[0072] Among them, T 0 is the standard processing time, which is set by those skilled in the art according to experience;

[0073] The central monitoring module sends the central processing index to the central evaluation module;

[0074] The central evaluation module performs the same processing on the received edge processing index, load index, transmission index, and central processing index corresponding to all edge servers. The processed index is called the target index Q. The target index Q is one of the edge processing index, load index, transmission index, and central processing index. Combining Figure 4 , the processing process includes the following steps:

[0075] S1. Calculate the average value of the target index

[0076]

[0077] Among them, m is the number of edge servers, and Q(j) represents the target index of the j-th edge server;

[0078] S2. Calculate the difference ΔQ(j) between the target index of each edge server and the average value:

[0079]

[0080] S3. Calculate the reference span d of the target index Q:

[0081]

[0082] Among them, λ is the amplification factor, and its value range is (1, 2];

[0083] S4. Set as the target index range [Q min , Q max ;

[0084] After processing through the above process, the index range [Q1 min , Q1 max of the edge processing index, the index range [Q2 min , Q2 max of the load index, the index range [Q3 min , Q3 max of the transmission index, and the index range [Q4 min , Q4 max of the central processing index are obtained;

[0085] The central evaluation module calculates the evaluation value E of each edge server within the evaluation time period according to the following formula:

[0086]

[0087] The larger the evaluation value of the edge server, the more the edge server needs to adjust the data allocation for edge computing;

[0088] Combined with Figure 5 , the process of the central evaluation module evaluating the edge server includes the following steps:

[0089] S21. The central evaluation module sets the evaluation time start point and the evaluation time end point, and the time period between the evaluation time start point and the evaluation time end point is the evaluation time period;

[0090] S22. The central evaluation module sends a start instruction to the edge monitoring module, the transmission monitoring module, and the central monitoring module at the evaluation time start point;

[0091] S23. After receiving the start instruction, the edge monitoring module, the transmission monitoring module, and the central monitoring module clear the original statistical data and then start monitoring and statistics again;

[0092] S24. At the end of the evaluation time, the central evaluation module sends an end instruction to the edge monitoring module, the transmission monitoring module, and the central monitoring module;

[0093] S25. After receiving the end instruction, the edge monitoring module, the transmission monitoring module, and the central monitoring module respectively calculate the corresponding indexes and feedback the calculation results to the central evaluation module;

[0094] S26. The central evaluation module calculates the evaluation values of each edge server and sends adjustment instructions to the edge servers based on the evaluation values.

[0095] The content disclosed above is only the preferred feasible embodiment of the present invention, and does not limit the protection scope of the present invention. Therefore, all equivalent technical changes made by using the content of the specification and drawings of the present invention are included in the protection scope of the present invention. In addition, with the development of technology, the elements therein can be updated.

Claims

1. An edge computing evaluation system based on artificial intelligence, characterized in that, it includes an edge monitoring module, a central evaluation module, a transmission monitoring module and a central monitoring module. The edge monitoring module is used to monitor the data processing situation of the edge server during the evaluation period. The transmission monitoring module is used to monitor the data transmission situation between the edge server and the central server during the evaluation period. The central monitoring module is used to monitor the data processing situation of the central server for the data uploaded by the edge server during the evaluation period. The central evaluation module evaluates the edge computing situation of the edge server according to the monitoring data of the above three monitoring modules; The edge monitoring module processes the monitored data to obtain an edge processing index and a load index . The transmission monitoring module processes the monitored data to obtain a transmission index . The central monitoring module processes the monitored data to obtain a central processing index . The central evaluation module processes the above four indices of all edge servers to obtain the index range of the edge processing index , the index range of the load index , the index range of the transmission index and the index range of the central processing index ; The central evaluation module calculates the evaluation value of each edge server within the evaluation period according to the following formula :[[]]END]] ； the larger the evaluation value of the edge server, the more the edge server needs to adjust the data allocation for edge computing; The edge monitoring module calculates the edge processing index of the edge server according to the following formula :[[]]END]] ； where n is the total number of data batches generated by the terminal during the evaluation period, is the time interval between the reception of the i-th batch of data by the edge server monitored by the edge monitoring module and the obtaining of the processing result of the i-th batch, is the time interval between the obtaining of the processing result of the i-th batch and the application of the processing result of the i-th batch monitored by the edge monitoring module, is the amount of the i-th batch of data retained in the edge server; The edge monitoring module calculates the load index of the edge server according to the following formula :[[]]END]] ； Among them, is the ratio of the amount of data in the i-th batch retained in the edge server to the amount of data in the i-th batch generated by the terminal; The transmission monitoring module calculates a transmission index according to the following formula :[[]]END]] ； Among them, is the duration of the evaluation time period, is the cumulative time for the edge server to transmit data to the central server within the evaluation time period, is the cumulative time for the central server to transmit data to the edge server within the evaluation time period; The central monitoring module calculates the central processing index of the edge server according to the following formula :[[]]END]] ； wherein, is the standard processing time, is the time interval for the central server to receive the i-th batch of data from the edge server and process the i-th batch of data to obtain a processing result, is the data volume of the i-th batch sent by the edge server to the central server.

Images