Data acquisition and calculation system based on edge calculation

Abstract

The invention relates to the technical field of data acquisition and calculation, in particular to a data acquisition and calculation system based on edge calculation, which comprises a dynamic sensing adjustment module, an edge redundancy packing module, a priority transmission scheduling module, a distributed calculation resource management module and a calculation task integration module. According to the method, the network load and the signal strength are dynamically sensed, working parameters are dynamically adjusted in combination with the transmission coverage range, node cooperative work configuration optimization is achieved, and data transmission stability and safety are achieved through packet processing of data packets in combination with redundancy coding statistics and integrity verification. Through path and time sequence priority ranking and dynamic adjustment, the transmission delay is reduced, the data transmission efficiency and the path utilization rate are improved, allocation is optimized based on the cooperative relation, balanced utilization of computing resources is achieved, the system bottleneck problem is reduced, the task execution condition is recorded and analyzed in real time, the task processing strategy is optimized, and the task processing efficiency of edge devices is improved.

Description

Technical Field

[0001] The present invention relates to the field of data acquisition and computing technology, and in particular to a data acquisition and computing system based on edge computing. Background Art

[0002] The field of data acquisition computing technology focuses on capturing data through various sensors and devices, and analyzing the data in real time or near real time to support decision-making and improve operational efficiency. It involves data collection, transmission, storage and analysis, and is often used in the Internet of Things (IoT), industrial automation, environmental monitoring and smart cities. It usually needs to be combined with an efficient computing architecture to process large amounts of data and extract useful information from it. The key to these systems is the ability to quickly and accurately process and analyze data, as well as to ensure the security and integrity of data during collection and transmission.

[0003] Among them, the data collection and computing system based on edge computing refers to a system that implements preliminary data processing and analysis on edge devices near the source of data generation. It can reduce dependence on central servers, reduce latency, improve response speed, and reduce bandwidth requirements during data transmission. It has a wide range of uses, especially in application scenarios that require rapid decision support, such as self-driving cars, smart manufacturing, and urban security monitoring. By processing data locally, edge computing systems can provide more real-time data analysis and processing, optimizing the overall performance and efficiency of the system.

[0004] The existing technology lacks a perception and adjustment mechanism for the dynamic state of nodes, resulting in insufficient coordination between nodes and low resource utilization efficiency. During the data transmission process, the flexible allocation of redundant information cannot be effectively realized, which easily leads to the loss of data packet integrity and affects the stability of transmission. The lack of real-time dynamic adjustment of path selection and transmission timing leads to reduced transmission efficiency and significantly increased latency under high load conditions. Task allocation mainly relies on the central server, and fails to fully consider the coordination capabilities and resource allocation optimization between edge nodes, which easily leads to idle or overloaded node computing power and weakens the overall performance of the system. The lack of real-time feedback and analysis of task execution makes it difficult to achieve rapid response and dynamic optimization. It is not suitable for the refined requirements in complex real-time scenarios, which limits the system's adaptability in diversified scenarios. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and propose a data acquisition and computing system based on edge computing.

[0006] In order to achieve the above objectives, the present invention adopts the following technical solutions: The data collection and calculation system based on edge computing includes:

[0007] The dynamic perception and adjustment module collects the signal strength and network load level of the edge node, calculates the transmission frequency of the edge node, calculates the dynamic working range value of the edge node according to the transmission coverage, calculates the edge node collaborative working parameters according to the determination result combined with the signal coverage distribution, and generates dynamic node collaborative configuration data;

[0008] The edge redundant packet grouping module performs grouping processing based on the dynamic node collaborative configuration data, calculates the redundant bit allocation ratio of the data packet, counts the redundant coding amount, adds redundant information to each group of data packets according to the statistical results and performs integrity verification, and groups the validity of the data packets in combination with the integrity verification to form a valid data grouping table;

[0009] The priority transmission scheduling module calculates the priority ranking value of the data packet according to the effective data grouping table, adjusts the transmission path and transmission timing distribution, records the transmission delay distribution according to the path selection and distribution situation, and obtains the path transmission efficiency distribution record;

[0010] The distributed computing resource management module calculates the resource allocation demand value of the edge node based on the path transmission efficiency distribution record, counts the task load distribution, adjusts the task processing content of the edge node, records the collaborative processing relationship between the edge nodes in combination with the task distribution, and forms the edge node collaborative processing analysis result;

[0011] The computing task integration module counts the task execution time according to the edge node collaborative processing analysis results, records the completion status of the tasks of each edge node, and obtains the computing task completion statistical record.

[0012] As a further solution of the present invention, the calculation step of the dynamic working range value is:

[0013] Collect the signal strength parameters and network load level parameters of the edge nodes, calculate the average value of the signal strength and the occupancy rate of the network load respectively, and generate the preliminary transmission frequency value of the edge node by comparing the fluctuation range of the signal strength and the proportional relationship between the network load occupancy;

[0014] According to the preliminary transmission frequency value of the edge node and the node transmission coverage, the formula is adopted:

[0015]

[0016] Calculate the signal coverage radius R of the node c , get the edge node transmission coverage, where F t is the initial transmission frequency value, S n is the normalized value of signal intensity, D l is the normalized parameter of load level;

[0017] According to the transmission coverage of the edge node, combined with the dynamic change rate of the coverage and the actual working area limit of the edge node, the distribution density of the signal strength within the coverage is adjusted, the working area boundary value is determined, and the dynamic working range value of the edge node is generated.

[0018] As a further solution of the present invention, the step of acquiring the dynamic node collaborative configuration data is:

[0019] According to the edge node dynamic working range value, analyze the distribution characteristics of the signal strength within the coverage range, record the maximum and minimum values ​​of the signal strength, the average value of the signal strength and the intersection area of ​​the coverage area, analyze the uniformity of the signal distribution within the coverage area, and generate a preliminary node coordination range;

[0020] According to the preliminary node coordination range, combined with the transmission frequency of the node and the signal distribution characteristics in the coverage area, the formula is adopted:

[0021]

[0022] Calculate the edge node collaborative efficiency value E c , generate node collaborative efficiency distribution records, where C i is the cooperative coverage area of ​​the i-th node, S i is the mean signal strength within the corresponding range, and n is the total number of nodes participating in the collaboration;

[0023] According to the node collaborative efficiency distribution record, the collaborative matching between edge nodes is analyzed, the numerical distribution analysis of signal strength and collaborative efficiency is simultaneously performed, the matching characteristics of the overlapping areas of signal coverage are determined, and dynamic node collaborative configuration data is generated.

[0024] As a further solution of the present invention, the statistical step of the redundant coding amount is:

[0025] Extract basic information of node groups and data packets according to the dynamic node collaborative configuration data, calculate the mean signal strength and number of grouped data packets of each group according to the signal coverage and signal strength distribution characteristics within the group, and generate a basic characteristic table of grouped data packets;

[0026] Based on the basic characteristics table of the group data packets, combined with the signal strength mean value and the number of data packets in the group, the formula is adopted:

[0027]

[0028] Calculate the redundant bit allocation ratio Ri of the i-th group of data packets and generate a group redundant bit allocation table, where Q i is the mean signal strength, N i is the number of packets in the current group, N maxis the maximum number of packets in all groups;

[0029] According to the group redundant bit allocation table, combined with the group number and redundant bit allocation ratio of the data packet, the redundant coding amount of the data packet is determined group by group, the total redundant coding amount of each group of data is cumulatively calculated, and the group redundant coding amount distribution table is generated.

[0030] As a further solution of the present invention, the steps of obtaining the valid data grouping table are:

[0031] Based on the group redundant coding amount distribution table, redundant information is added to corresponding data packets one by one according to the redundant coding amount of each group of data packets, and a redundantly enhanced data packet is generated by combining the original content of the data packet with the redundant information;

[0032] According to the redundancy-enhanced data packets, the content integrity of the data packets is checked group by group, the matching between the redundant information in each group of data packets and the actual data received is analyzed, the integrity characteristic parameters of each group of data packets are recorded, and a data packet integrity characteristic table is generated;

[0033] According to the data packet integrity characteristic table, the data packet groups are screened for validity, the data packets that meet the integrity standards are classified as valid groups, and the data packets that do not meet the integrity standards are marked as invalid, and a valid data group table is generated.

[0034] As a further solution of the present invention, the steps of obtaining the path transmission efficiency distribution record are:

[0035] Based on the effective data grouping table, the target node number, data volume and transmission time limit of each group of data packets are extracted using the formula:

[0036]

[0037] Calculate the preliminary priority value P of the i-th group of data packets i , by normalizing the priority values ​​of each group of data, a preliminary data packet priority ranking value is generated, where H i is the amount of data, T i is the transmission time limit, T max is the maximum transmission time limit, N i is the target node number;

[0038] Based on the preliminary data packet priority ranking value, combined with the path capacity, path load status and data packet transmission requirements, priority ranking is adjusted group by group, and the transmission timing distribution of the path is optimized by adjustment, and the distribution order is dynamically adjusted according to the path load, so as to generate an adjusted transmission path and transmission timing distribution record;

[0039] Based on the adjusted transmission path and transmission timing distribution record, the transmission delay of the path is calculated one by one, the comparative relationship between the delay and the path capacity and load is analyzed, and the path transmission efficiency distribution record is generated.

[0040] As a further solution of the present invention, the step of acquiring the edge node collaborative processing analysis result is:

[0041] Calling the transmission efficiency distribution record of the path, extracting the transmission efficiency value of each path and the task distribution of the corresponding edge node, calculating the resource allocation demand value of each node, and normalizing the task demand and transmission efficiency to generate a preliminary resource allocation result of the edge node;

[0042] According to the preliminary resource allocation results, combined with the task load distribution of the edge nodes, the task processing content of each node is adjusted, the matching degree between the load and resource requirements of each node is analyzed, the task processing content is dynamically allocated, and the resource and task transfer between edge nodes during the task adjustment process is recorded, and the collaborative processing record between nodes is generated;

[0043] Based on the collaborative processing records between the nodes, the collaborative processing relationship between the edge nodes is analyzed, and the collaborative processing analysis results of the edge nodes are formed by counting the interaction amount of task allocation and processing resources between the nodes.

[0044] As a further solution of the present invention, the steps for obtaining the statistical record of the completion of the computing task are:

[0045] Based on the edge node collaborative processing analysis results, analyze the task distribution and collaborative processing relationship of each edge node, combine the start time and end time of the task, calculate the actual execution time of each task, summarize the execution time of each task, and form an edge node task execution time record;

[0046] Based on the edge node task execution time record, by comparing the task execution time with the resource allocation efficiency, the total task completion time of each edge node is calculated to obtain the node task completion status record;

[0047] Based on the node task completion status record, combined with the task completion ratio and execution status of each edge node, the overall task completion distribution is counted, the task completion status of each node is summarized, and a computing task completion statistical record is formed.

[0048] Compared with the prior art, the advantages and positive effects of the present invention are:

[0049] In the present invention, by dynamically sensing the network load and signal strength and dynamically adjusting the working parameters in combination with the transmission coverage range, the node collaborative working configuration optimization is realized, and the stability and security of data transmission are realized by grouping and processing data packets in combination with redundant coding statistics and integrity verification. By sorting and dynamically adjusting the path and timing priorities, the transmission delay is reduced, the data transmission efficiency and path utilization are improved, and the allocation is optimized based on the collaborative relationship to achieve balanced utilization of computing resources and reduce system bottleneck problems. The task execution status is recorded and analyzed in real time, the task processing strategy is optimized, and the task processing efficiency of edge devices is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 is a system flow chart of the present invention;

[0051] Figure 2 A flow chart for determining the dynamic working range value of the present invention;

[0052] Figure 3 A flowchart for obtaining dynamic node collaborative configuration data of the present invention;

[0053] Figure 4 It is a statistical flow chart of the redundant coding amount of the present invention;

[0054] Figure 5 The flowchart of obtaining the effective data grouping table of the present invention;

[0055] Figure 6 A flowchart for obtaining the path transmission efficiency distribution record of the present invention;

[0056] Figure 7 The following is a flow chart of obtaining the analysis results of the edge node collaborative processing of the present invention;

[0057] Figure 8 A flow chart for obtaining statistical records of the computing task completion of the present invention. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0059] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0060] See also Figure 1 , the data collection and computing system based on edge computing includes:

[0061] The dynamic perception and adjustment module collects the signal strength and network load level of the edge node, calculates the transmission frequency of the edge node, determines the dynamic working range value of the edge node according to the transmission coverage range, calculates the edge node collaborative working parameters according to the determination result and the signal coverage distribution, and generates dynamic node collaborative configuration data;

[0062] The edge redundant packet grouping module performs grouping processing based on dynamic node collaborative configuration data, calculates the redundant bit allocation ratio of the data packet, counts the redundant coding amount, adds redundant information to each group of data packets according to the statistical results and performs integrity verification, and groups the validity of the data packets based on the integrity verification to form a valid data grouping table;

[0063] The priority transmission scheduling module calculates the priority ranking value of the data packet according to the valid data grouping table, adjusts the transmission path and transmission timing distribution, records the transmission delay distribution according to the path selection and distribution, and obtains the path transmission efficiency distribution record;

[0064] The distributed computing resource management module calculates the resource allocation demand value of the edge node based on the path transmission efficiency distribution record, counts the task load distribution, adjusts the task processing content of the edge node, records the collaborative processing relationship between the edge nodes in combination with the task distribution, and forms the edge node collaborative processing analysis results;

[0065] The computing task integration module calculates the task execution time based on the edge node collaborative processing analysis results, records the completion status of each edge node task, and obtains the computing task completion statistical record.

[0066] The dynamic node collaborative configuration data includes the transmission frequency, dynamic working range value and collaborative working parameters. The effective data grouping table includes the redundant bit allocation ratio, redundant coding amount and data packet integrity verification status. The path transmission efficiency distribution record is specifically the transmission path, transmission timing distribution record and transmission delay distribution record. The edge node collaborative processing analysis results include the resource allocation demand value, task load distribution amount and collaborative processing relationship between edge nodes. The computing task completion statistical records include task execution time and edge node task completion status.

[0067] See also Figure 2 , the steps to determine the dynamic working range value are:

[0068] Collect the signal strength parameters and network load level parameters of the edge nodes, calculate the average value of the signal strength and the occupancy rate of the network load respectively, and generate the preliminary transmission frequency value of the edge node by comparing the fluctuation range of the signal strength and the proportional relationship between the network load occupancy;

[0069] The signal strength parameters and network load level parameters of the edge nodes are collected, and the signal strength of the edge nodes at different time points is recorded through the signal receiving equipment to form a time series data set. The changing trend of the signal strength is extracted and its average value is calculated. The load occupancy data of the node is obtained by using the network load monitoring equipment. The load level is subdivided according to the time series to generate a time distribution table of the load level. By comparing the fluctuation range of the signal strength and the network load occupancy ratio, the correlation between the two is analyzed. The ratio of signal strength to load level is used for comparison. Based on the signal strength, the calculation step size is gradually increased to fit the correlation curve between the two parameters. Finally, the preliminary transmission frequency value of the edge node under the current conditions is determined according to the extreme point of the curve.

[0070] According to the preliminary transmission frequency value of the edge node and the node transmission coverage, the formula is adopted:

[0071]

[0072] Calculate the signal coverage radius R of the node c , get the edge node transmission coverage, where F t is the initial transmission frequency value, S n is the normalized value of signal intensity, D1 is the normalized parameter of load level;

[0073] Assume F t =50 (unit: Hz). Signal strength normalization value (S n ): The collected signal intensity is obtained by normalization, and the calculation formula is:

[0074]

[0075] Assume signal strength range I min =20 and I max =120, the monitoring value is I i =70, then:

[0076]

[0077] Load level normalization parameter (D1): The network load level monitoring value is obtained through normalization processing. Assume that the monitoring value is L = 25 and the maximum load is L max =100, we get:

[0078]

[0079] Substitute the above parameters:

[0080] F t =50, S n =50, D1=25

[0081] Calculate the numerator:

[0082] 50×50=2500

[0083] Calculate the denominator:

[0084] π·25=78.54

[0085] Calculate the score:

[0086]

[0087] Calculate the square root:

[0088]

[0089] The results show that the signal transmission coverage radius of the edge node is 5.64 units, which directly reflects the effective transmission range of the node under the current signal strength and load level conditions. It is not only used to define the coverage area of ​​the node, but also provides initial parameters for subsequent dynamic adjustments to ensure the adaptability and accuracy of the working range.

[0090] According to the transmission coverage of the edge node, combined with the dynamic change rate of the coverage and the actual working area limit of the edge node, the distribution density of the signal strength within the coverage is adjusted, the boundary value of the working area is determined, and the dynamic working range value of the edge node is generated;

[0091] Based on the transmission coverage parameters of the edge nodes and combined with the real-time environmental parameters, the signal strength distribution data within the transmission coverage is collected to form a distribution density table of the signal strength within the coverage range. For the regional data in the distribution density table, the signal strength value of each area is refined in a grid-based manner to generate a spatial model of the signal strength distribution. The mean signal strength within each grid area is extracted and normalized. The signal strength change rate in different areas is calculated through a statistical distribution model. Combined with the actual working area restrictions of the node, the coverage threshold of each area is gradually adjusted according to the signal strength distribution density in different areas and the dynamic change rate within the coverage range, the signal coverage range of the edge node is optimized, and finally the dynamic working range value of the node is generated.

[0092] See also Figure 3 ,The steps to obtain dynamic node collaborative configuration data are:

[0093] According to the dynamic working range value of the edge node, analyze the distribution characteristics of the signal strength within the coverage area, record the maximum and minimum values ​​of the signal strength, the average value of the signal strength and the intersection area of ​​the coverage area, analyze the uniformity of the signal distribution within the coverage area, and generate a preliminary node coordination range;

[0094] According to the determined dynamic working range of edge nodes, the distribution data of signal coverage is collected. The signal receiving area of ​​edge nodes is divided into equally spaced grid areas. Each grid unit records the numerical range of signal strength. The data of each area is classified and counted. The maximum signal strength value, minimum signal strength value and average signal strength value are extracted. The distribution density of signal strength in the grid is calculated. Combined with the collected coverage area data, the area value of each grid is calculated according to the geometric characteristics of the grid division, and the total area and total signal strength density of the coverage are summarized. The uniformity of signal strength distribution is analyzed by step-by-step iteration, and the characteristic values ​​of the intersection part of the coverage range are extracted, such as the maximum intersection range of signal strength and the area value of the signal overlapping part. At the same time, combined with the uniformity index of the signal in the coverage area, the signal coverage area data for collaborative analysis is extracted, and finally a preliminary node collaboration range is generated.

[0095] According to the preliminary node coordination range, combined with the node transmission frequency and the signal distribution characteristics in the coverage area, the formula is adopted:

[0096]

[0097] Calculate the edge node collaborative efficiency value E c , generate node collaborative efficiency distribution records, where C i is the cooperative coverage area of ​​the i-th node, S i is the mean signal strength within the corresponding range, and n is the total number of nodes participating in the collaboration;

[0098] Collaborative coverage area (C i ): By monitoring the coverage of node signals, the coverage area of ​​each node is calculated one by one by using the geometric segmentation method of the coverage area. For example, the coverage area of ​​node 1 is C1=30, that of node 2 is C2=40, and that of node 3 is C3=50 (in square meters).

[0099] The mean signal strength (S i ): Based on the signal collection value within the coverage area, calculate the average signal strength within the coverage area of ​​each node. For example, the average signal strength of node 1 is S1=80, node 2 is S2=70, and node 3 is S3=60 (in dBm).

[0100] Total number of nodes (n): The number of nodes involved in the calculation of the collaborative coverage, in this example n = 3.

[0101] Substitute the above parameters:

[0102]

[0103] Right now:

[0104]

[0105] Calculate the numerator step by step:

[0106] (30×80)=2400, (40×70)=2800, (50×60)=3000

[0107] Numerator sum:

[0108] 2400+2800+3000=8200

[0109] Calculate the denominator:

[0110] 30+40+50=120

[0111] The final calculation of collaborative efficiency:

[0112]

[0113] The results show that the node coordination efficiency value is 68.33 (unit: dBm·m 2 ), represents the collaborative working ability of each node under the current coverage range and signal strength conditions. The higher the collaborative efficiency, the better the match between the coverage range and signal distribution between nodes. This result is used to guide the parameter optimization of dynamic node collaborative configuration, ensuring that the collaborative relationship between signal strength and coverage can reach a better state, and at the same time providing an important basis for subsequent dynamic adjustments.

[0114] According to the node coordination efficiency distribution records, the coordination matching between edge nodes is analyzed, and the numerical distribution analysis of signal strength and coordination efficiency is simultaneously performed to determine the matching characteristics of the overlapping areas of signal coverage and generate dynamic node coordination configuration data;

[0115] According to the collaborative efficiency distribution data and the detailed records of the signal strength coverage distribution, the coverage is further divided into sub-areas, and the actual signal distribution value and area of ​​each sub-area are calculated. By extracting the regional distribution data of signal strength, the signal distribution relationship and strength change between regions are analyzed respectively. The regional distribution data is compared with the initial calculated value of the collaborative efficiency. The signal coverage of each region is optimized by setting the proportional relationship of the regional distribution. According to the proportional relationship between the coverage range and the signal strength, the overlapping parts of the signal within the signal coverage range are gradually adjusted to non-overlapping areas to further reduce the possibility of signal interference. Finally, the optimized signal coverage data of each region is summarized, and the signal matching value and the final collaborative coverage range are calculated in combination with the actual area to generate dynamic node collaborative configuration data.

[0116] See also Figure 4 , the statistical steps of redundant coding amount are:

[0117] Extract basic information of node groups and data packets based on dynamic node collaborative configuration data, calculate the mean signal strength and number of grouped data packets in each group based on signal coverage and signal strength distribution characteristics within the group, and generate a basic characteristic table of grouped data packets;

[0118] Call the dynamic node collaborative configuration data, parse the node grouping information and data packet attributes contained in the data, divide the data into several groups according to the coverage range and signal strength characteristics of the nodes, and gradually count the numerical range of its signal strength for each group, including the maximum value, minimum value and mean value. The statistical signal strength data comes from the real-time collected coverage area signal value, and the average value of each group signal strength is calculated by segmenting the area by area to ensure the accuracy of each group signal characteristic. Subsequently, the number of each group of data packets is counted, and the number of data packets is combined with the signal strength characteristics. The basic characteristic table of the group data packet is generated with the group signal strength mean and the number of data packets as the core, and the integrity of the group data is verified by repeated sampling and calculation, and finally the basic characteristic table of the group data packet is ensured to be accurate and reliable, providing accurate input for subsequent calculations.

[0119] Based on the basic characteristics table of packet data, combined with the mean signal strength and the number of packets in the group, the formula is used:

[0120]

[0121] Calculate the redundant bit allocation ratio Ri of the i-th group of data packets and generate a group redundant bit allocation table, where Q i is the mean signal strength, N i is the number of packets in the current group, N max is the maximum number of packets in all groups;

[0122] The mean signal strength (Q i ): The average value of each group is calculated from the group signal strength data, for example, Q1 = 70 (unit: dBm) for the first group, Q2 = 80 for the second group, and Q3 = 60 for the third group.

[0123] Maximum number of packets (N max ): Take the maximum number of packets in all groups, for example N max =200.

[0124] The current group of data packets (N i ): Extract the total number of data packets of the i-th group from the group basic characteristic table, for example, N1=150 for the first group, N2=120 for the second group, and N3=180 for the third group.

[0125] Group 1 calculations

[0126] Bring in parameters:

[0127]

[0128] Calculate the numerator:

[0129] 70×200=14000

[0130] Calculate the denominator:

[0131]

[0132] Calculate the square root:

[0133]

[0134] Group 2 calculations

[0135] Bring in parameters:

[0136]

[0137] Calculate the numerator:

[0138] 80×200=16000

[0139] Calculate the denominator:

[0140]

[0141] Calculate the square root:

[0142]

[0143] Group 3 calculations

[0144] Bring in parameters:

[0145]

[0146] Calculate the numerator:

[0147] 60×200=12000

[0148] Calculate the denominator:

[0149]

[0150] Calculate the square root:

[0151]

[0152] The calculation results show that the redundancy bit allocation ratio of group 1 is 9.66, group 2 is 11.55, and group 3 is 8.16. These values ​​​​describe the proportion of redundant resources allocated to each group of data packets based on the actual needs of the mean signal strength and the number of data packets. The higher the redundancy bit allocation ratio, the more redundant support is needed for this group of data to ensure the integrity and reliability of data transmission.

[0153] According to the group redundant bit allocation table, combined with the number of groups and the redundant bit allocation ratio of the data packet, the redundant coding amount of the data packet is determined group by group, the total redundant coding amount of each group of data is cumulatively calculated, and the group redundant coding amount distribution table is generated;

[0154] Call the group redundant bit allocation table, parse the redundant bit allocation ratio of each group of data in the table, combine the group information of the data packet with the allocation ratio, calculate the redundant coding amount of each group of data in turn by calculating the product of the number of data packets in each group and the redundant bit allocation ratio, record the redundant coding amount of all groups and generate a group statistical table, and then accumulate the statistical results of each group of redundant coding amount to generate the overall redundant coding amount of each group of data. For the calculation process of the redundant coding amount, it is necessary to check the accuracy of the group data one by one to avoid allocation deviations caused by signal fluctuations or data errors, verify the rationality of the grouping results through repeated calculations, and form a group redundant coding amount distribution table after completing the statistics to ensure that the data input for subsequent processing is accurate and reliable.

[0155] See also Figure 5 , the steps to obtain the valid data grouping table are:

[0156] Based on the group redundant coding amount distribution table, redundant information is added to the corresponding data packets one by one according to the redundant coding amount of each group of data packets, and a redundantly enhanced data packet is generated by merging the original content of the data packet with the redundant information;

[0157] Based on the group redundant coding amount distribution table, according to the redundant coding amount value of each group of data packets, determine the redundant information content and number of bits to be added, extract the original content of each group of data packets in turn, and analyze the data structure and the position where the redundant information can be inserted packet by packet. For each data packet, the redundant information is added to the specified position with a predetermined number of bits. By checking the length and structural consistency of the added data packet, it is ensured that the addition of redundant information will not destroy the integrity of the original data. All group data packets are processed with redundant information superposition in turn. During the processing, the validity of the redundant information is monitored in real time and the content of the complete data packet after addition is recorded. Finally, a group data table containing redundant enhanced data is formed to provide input data for subsequent integrity verification.

[0158] According to the data packets with enhanced redundancy, the content integrity of the data packets is checked group by group, the matching between the redundant information in each group of data packets and the actual data received is analyzed, the integrity characteristic parameters of each group of data packets are recorded, and a data packet integrity characteristic table is generated;

[0159] Based on the redundantly enhanced packet data table, the content integrity of each group of data packets is checked one by one. For each data packet, the redundantly enhanced content and the actual received data content are extracted to analyze the matching degree between the two. For the matching check process, the difference value between the redundantly enhanced data and the received data is calculated by bit-by-bit comparison, and the number of difference bits in each group of data packets is counted. At the same time, the number and location information of the lost redundant information are recorded to generate a content integrity parameter record table for the data packet. During the inspection process, according to the set content integrity standard, key parameters such as the difference index and loss rate of each group of data packets are recorded to ensure that the integrity check results can reflect the actual transmission and reception status of each group of data packets. Finally, a data packet integrity characteristic table is generated to provide a direct reference for subsequent packet screening.

[0160] According to the data packet integrity characteristic table, the data packet groups are screened for validity, the data packets that meet the integrity standards are classified as valid groups, and the data packets that do not meet the integrity standards are marked as invalid, and a valid data group table is generated;

[0161] Based on the data packet integrity characteristic table, the integrity characteristic parameters are analyzed group by group, and valid data groups are screened according to the minimum integrity standard set by the integrity check result. The integrity parameters of each group of data packets, including content difference values, loss rates and other indicators, are compared with the integrity standards one by one. For groups that meet the standards, their valid status is recorded and classified as valid data groups. For groups that do not meet the integrity standards, their invalid status is recorded and marked as invalid data. During the screening process, the final valid data statistical record is generated by successively accumulating the number of valid groups, and the data groups marked as invalid are separated to ensure the accuracy and independence of the valid data groups. Finally, a valid data group table is formed to provide reliable data support for subsequent data analysis and transmission.

[0162] See also Figure 6 , the steps to obtain the path transmission efficiency distribution record are:

[0163] Based on the valid data grouping table, the number of target nodes, data volume and transmission time limit of each group of data packets are extracted using the formula:

[0164]

[0165] Calculate the preliminary priority value P of the i-th group of data packets i , by normalizing the priority values ​​of each group of data, a preliminary data packet priority ranking value is generated, where H i is the amount of data, T i is the transmission time limit, T max is the maximum transmission time limit, N i is the target node number;

[0166] Data volume (H i ):obtained by extracting the total transmission data volume of the data packets in the group, for example H1=800 (unit: KB).

[0167] Maximum transmission time (T max ): Extract the maximum transmission time allowed from all packets, such as T max =1500 (unit: milliseconds).

[0168] Transmission time limit (T i ) is the actual transmission time limit of the current packet data, for example T1=600 (unit: milliseconds).

[0169] The number of target nodes (N i ):Reflects the number of target distribution nodes of the data packet, for example N1=12.

[0170] Calculate the numerator:

[0171] 800×1500=1200000

[0172] Calculate the denominator:

[0173] 600×12=7200

[0174] Calculate the priority ranking value:

[0175]

[0176] The results show that the preliminary priority ranking value of the first group of data packets is 166.67. This value indicates that this group of data packets has a higher importance under the constraints of the transmission time limit and the number of target nodes. The larger the priority ranking value, the higher the transmission priority it needs in the scheduling process. This result provides an important reference for subsequent path optimization and timing adjustment.

[0177] Based on the preliminary data packet priority ranking value, combined with the path capacity, path load status and data packet transmission requirements, priority ranking is adjusted group by group, and the path transmission timing distribution is optimized by adjustment. The distribution order is dynamically adjusted according to the path load, and the adjusted transmission path and transmission timing distribution record are generated;

[0178] Based on the preliminary data packet priority ranking value, the preliminary priority value is adjusted one by one in combination with the transmission path capacity, path load status and transmission requirements of each group of data packets. During the adjustment process, the current transmission path capacity of each group of data packets is first extracted, and the available capacity of the path is corrected according to the real-time load value of the path, so as to match the path capacity with the data packet transmission requirements. For each group of data packets, the priority value is reallocated according to the dynamic load of the transmission path, and the priority of the group with higher path load is lowered, while the priority of the group with lower path load is increased to balance the efficiency of path resource utilization. By recording the priority value after each adjustment and comparing it with the original value, the rationality and effectiveness of the adjustment result are ensured. Finally, the adjusted transmission path and transmission timing distribution record are generated, and the adjustment results are verified group by group to ensure that the priority ranking and timing distribution can meet the transmission requirements of each group of data packets.

[0179] Based on the adjusted transmission path and transmission timing distribution record, the transmission delay of each path is calculated, the comparative relationship between the delay and the path capacity and load is analyzed, and the path transmission efficiency distribution record is generated;

[0180] Based on the adjusted transmission path and transmission timing distribution records, the distribution records and receiving time information of the data packets are extracted path by path, and the actual transmission delay on each path is analyzed. For each path, the path capacity and load status are extracted, and the path transmission efficiency is analyzed. First, the transmission delay value of each group of data packets on the path is recorded, and the ratio of the path transmission delay and the corresponding data volume is calculated to determine the unit data transmission efficiency of the path. Subsequently, the load status of the path is compared and analyzed with the transmission efficiency, and the comparison results are recorded as the transmission efficiency distribution value of the path. Through path-by-path statistical analysis, the transmission efficiency distribution is classified by path, and the overall transmission efficiency of the path is summarized and recorded to ensure that the transmission efficiency results of each path can accurately reflect its performance in actual transmission, and finally generate a path transmission efficiency distribution record table.

[0181] See also Figure 7 ,The steps for obtaining the analysis results of edge node collaborative processing are:

[0182] Call the path transmission efficiency distribution record, extract the transmission efficiency value of each path and the task distribution of the corresponding edge node, calculate the resource allocation demand value of each node, and normalize the task demand and transmission efficiency to generate the preliminary resource allocation result of the edge node;

[0183] Call the path transmission efficiency distribution record, extract the transmission efficiency value and task distribution of each path, obtain the corresponding relationship between resource utilization and transmission efficiency on each path, match the task requirements of the edge node with the transmission efficiency of the path one by one, and calculate the current task load of each node and its demand for resource allocation. In the calculation, the transmission efficiency of the path is used as a measure to analyze the optimal allocation of resources required by the node, and the preliminary resource allocation of the node is recorded. In the recording process, it is also important to analyze the corresponding relationship between node resource allocation and task load to ensure the feasibility of the allocation results. After the preliminary resource allocation results of all nodes are summarized, they are organized into a preliminary resource allocation result table for subsequent adjustment and verification.

[0184] According to the preliminary resource allocation results, combined with the task load distribution of edge nodes, the task processing content of each node is adjusted, the matching degree between the load and resource requirements of each node is analyzed, and the task processing content is dynamically allocated. At the same time, the resource and task transfer between edge nodes during the task adjustment process is recorded, and the collaborative processing records between nodes are generated;

[0185] Call the preliminary resource allocation result table, compare and analyze the task load of each node with the allocated resource requirements, extract the matching degree between resource allocation and task processing in turn, and adjust the nodes with unbalanced task ratios. During the adjustment process, record the changes in task transfer node by node, analyze the dynamic relationship between resource allocation and task processing content, and reallocate task processing content based on the task distribution of each node. During the adjustment process, consider the flow of resources and the load changes of tasks at the same time, record the interaction between tasks and resource transfers between nodes, and ensure that the allocation optimization of resources and tasks can further support collaborative processing relationships. Finally, a task processing adjustment record table is formed, which fully reflects the resource and task adjustments of each node, providing support for subsequent collaborative relationship analysis.

[0186] Based on the collaborative processing records between nodes, the collaborative processing relationship between edge nodes is analyzed, and the interactive amount of task allocation and processing resources between nodes is counted to form the edge node collaborative processing analysis results;

[0187] Call the task processing adjustment record table to count the changes in resource allocation and task processing content node by node, and record the node collaborative processing relationship by analyzing the task interaction volume and resource sharing between nodes one by one. In the record, analyze the parameters such as the task interaction frequency and resource sharing ratio between nodes one by one, extract the collaborative characteristic parameters through the dynamic change trend of the task and resource interaction between nodes, and form a dynamic description of the node collaborative relationship. Based on the record of the collaborative processing relationship, further count the stability of task allocation and resource flow between nodes, generate a distribution map of node collaborative processing, and finally sort out the edge node collaborative processing analysis results to provide a basis for further strategy formulation for resource optimization and task allocation.

[0188] See also Figure 8 , the steps to obtain the statistical records of the computing task completion are:

[0189] Based on the edge node collaborative processing analysis results, analyze the task distribution and collaborative processing relationship of each edge node, combine the start time and end time of the task, calculate the actual execution time of each task, summarize the execution time of each task, and form an edge node task execution time record;

[0190] The task distribution of each edge node is extracted from the edge node collaborative processing analysis results, and the task timestamp data is called node by node. The actual execution time of the task is calculated by recording the start time and end time of the task. The start and end time points of each task are compared with the current system time to correct the timestamp deviation. The calculated task duration is stored in the form of an array and grouped by nodes. The task execution time distribution of each group is stored in the corresponding node statistical table. Finally, by summarizing all node statistical tables, a distribution table containing all task execution times is generated.

[0191] Based on the edge node task execution time record, by comparing the task execution time and resource allocation efficiency, the total task completion time of each edge node is calculated to obtain the node task completion status record;

[0192] Call the task execution time distribution table, extract the actual execution time of each task, compare it with the preset task plan time one by one, and judge whether the actual duration of each task meets the planned duration. Use Boolean variables to mark the completion status of the task, sort the results of each judgment according to the task number and the node to which it belongs, and generate a task completion mark table. Then, count the Boolean variables of all task completions in the mark table, calculate the total number of tasks completed and the completion ratio of each node, and finally merge the statistical results of each node to generate a global task completion status record table.

[0193] Based on the node task completion records, combined with the task completion ratio and execution status of each edge node, the overall task completion distribution is counted, the task completion status of each node is summarized, and the computing task completion statistics are formed;

[0194] Call the task completion status record table, extract the task completion distribution information by node and task number, count the interval values ​​of task completion time one by one, analyze the statistical characteristics of task completion distribution by calculating the mean and variance of the time interval, match these characteristic values ​​with the relationship between collaborative tasks between nodes, summarize the characteristic pattern of task distribution, then summarize the distribution pattern and time interval records of all tasks to generate a task distribution record table, and finally organize the statistical characteristic data of task completion based on the record table and save it as a task completion statistical record.

[0195] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A data collection and computing system based on edge computing, characterized in that: The system comprises: The dynamic perception and adjustment module collects the signal strength and network load level of the edge node, calculates the transmission frequency of the edge node, calculates the dynamic working range value of the edge node according to the transmission coverage, calculates the edge node collaborative working parameters according to the determination result combined with the signal coverage distribution, and generates dynamic node collaborative configuration data; The edge redundant packet grouping module performs grouping processing based on the dynamic node collaborative configuration data, calculates the redundant bit allocation ratio of the data packet, counts the redundant coding amount, adds redundant information to each group of data packets according to the statistical results and performs integrity verification, and groups the validity of the data packets in combination with the integrity verification to form a valid data grouping table; The priority transmission scheduling module calculates the priority ranking value of the data packet according to the effective data grouping table, adjusts the transmission path and transmission timing distribution, records the transmission delay distribution according to the path selection and distribution situation, and obtains the path transmission efficiency distribution record; The distributed computing resource management module calculates the resource allocation demand value of the edge node based on the path transmission efficiency distribution record, counts the task load distribution, adjusts the task processing content of the edge node, records the collaborative processing relationship between the edge nodes in combination with the task distribution, and forms the edge node collaborative processing analysis result; The computing task integration module counts the task execution time according to the edge node collaborative processing analysis results, records the completion status of the tasks of each edge node, and obtains the computing task completion statistical record.

2. The data collection and computing system based on edge computing according to claim 1, characterized in that: The calculation steps of the dynamic working range value are: Collect the signal strength parameters and network load level parameters of the edge nodes, calculate the average value of the signal strength and the occupancy rate of the network load respectively, and generate the preliminary transmission frequency value of the edge node by comparing the fluctuation range of the signal strength and the proportional relationship between the network load occupancy; According to the preliminary transmission frequency value of the edge node and the node transmission coverage, the formula is adopted: Calculate the signal coverage radius R of the node c , get the edge node transmission coverage, where F t is the initial transmission frequency value, S n is the normalized value of signal intensity, D1 is the normalized parameter of load level; According to the transmission coverage of the edge node, combined with the dynamic change rate of the coverage and the actual working area limit of the edge node, the distribution density of the signal strength within the coverage is adjusted, the working area boundary value is determined, and the dynamic working range value of the edge node is generated.

3. The data collection and computing system based on edge computing according to claim 2, characterized in that: The steps for acquiring the dynamic node collaborative configuration data are as follows: According to the edge node dynamic working range value, analyze the distribution characteristics of the signal strength within the coverage range, record the maximum and minimum values ​​of the signal strength, the average value of the signal strength and the intersection area of ​​the coverage area, analyze the uniformity of the signal distribution within the coverage area, and generate a preliminary node coordination range; According to the preliminary node coordination range, combined with the transmission frequency of the node and the signal distribution characteristics in the coverage area, the formula is adopted: Calculate the edge node collaborative efficiency value E c , generate node collaborative efficiency distribution records, where C i is the cooperative coverage area of ​​the i-th node, S i is the mean signal strength within the corresponding range, and n is the total number of nodes participating in the collaboration; According to the node collaborative efficiency distribution record, the collaborative matching between edge nodes is analyzed, the numerical distribution analysis of signal strength and collaborative efficiency is simultaneously performed, the matching characteristics of the overlapping areas of signal coverage are determined, and dynamic node collaborative configuration data is generated.

4. The data collection and computing system based on edge computing according to claim 3 is characterized in that: The statistical steps of the redundant coding amount are as follows: Extract basic information of node groups and data packets according to the dynamic node collaborative configuration data, calculate the mean signal strength and number of grouped data packets of each group according to the signal coverage and signal strength distribution characteristics within the group, and generate a basic characteristic table of grouped data packets; Based on the basic characteristics table of the group data packets, combined with the signal strength mean value and the number of data packets in the group, the formula is adopted: Calculate the redundant bit allocation ratio Ri of the i-th group of data packets and generate a group redundant bit allocation table, where Qi is the mean signal strength, N i is the number of packets in the current group, N max is the maximum number of packets in all groups; According to the group redundant bit allocation table, combined with the group number and redundant bit allocation ratio of the data packet, the redundant coding amount of the data packet is determined group by group, the total redundant coding amount of each group of data is cumulatively calculated, and the group redundant coding amount distribution table is generated.

5. The data collection and computing system based on edge computing according to claim 4 is characterized in that: The steps for obtaining the valid data grouping table are: Based on the group redundant coding amount distribution table, redundant information is added to corresponding data packets one by one according to the redundant coding amount of each group of data packets, and a redundantly enhanced data packet is generated by combining the original content of the data packet with the redundant information; According to the redundancy-enhanced data packets, the content integrity of the data packets is checked group by group, the matching between the redundant information in each group of data packets and the actual data received is analyzed, the integrity characteristic parameters of each group of data packets are recorded, and a data packet integrity characteristic table is generated; According to the data packet integrity characteristic table, the data packet groups are screened for validity, the data packets that meet the integrity standards are classified as valid groups, and the data packets that do not meet the integrity standards are marked as invalid, and a valid data group table is generated.

6. The data collection and computing system based on edge computing according to claim 5, characterized in that: The steps for obtaining the path transmission efficiency distribution record are as follows: Based on the effective data grouping table, the target node number, data volume and transmission time limit of each group of data packets are extracted using the formula: Calculate the preliminary priority value P of the i-th group of data packets i , by normalizing the priority values ​​of each group of data, a preliminary data packet priority ranking value is generated, where H i is the amount of data, T i is the transmission time limit, T max is the maximum transmission time limit, N i is the target node number; Based on the preliminary data packet priority ranking value, combined with the path capacity, path load status and data packet transmission requirements, priority ranking is adjusted group by group, and the transmission timing distribution of the path is optimized by adjustment, and the distribution order is dynamically adjusted according to the path load, so as to generate an adjusted transmission path and transmission timing distribution record; Based on the adjusted transmission path and transmission timing distribution record, the transmission delay of the path is calculated one by one, the comparative relationship between the delay and the path capacity and load is analyzed, and the path transmission efficiency distribution record is generated.

7. The data collection and computing system based on edge computing according to claim 6, characterized in that: The steps of acquiring the edge node collaborative processing analysis results are as follows: Calling the transmission efficiency distribution record of the path, extracting the transmission efficiency value of each path and the task distribution of the corresponding edge node, calculating the resource allocation demand value of each node, and normalizing the task demand and transmission efficiency to generate a preliminary resource allocation result of the edge node; According to the preliminary resource allocation results, combined with the task load distribution of the edge nodes, the task processing content of each node is adjusted, the matching degree between the load and resource requirements of each node is analyzed, the task processing content is dynamically allocated, and the resource and task transfer between edge nodes during the task adjustment process is recorded, and the collaborative processing record between nodes is generated; Based on the collaborative processing records between the nodes, the collaborative processing relationship between the edge nodes is analyzed, and the collaborative processing analysis results of the edge nodes are formed by counting the interaction amount of task allocation and processing resources between the nodes.

8. The data collection and computing system based on edge computing according to claim 7, characterized in that: The steps for obtaining the statistical records of the computing task completion are as follows: Based on the edge node collaborative processing analysis results, analyze the task distribution and collaborative processing relationship of each edge node, combine the start time and end time of the task, calculate the actual execution time of each task, summarize the execution time of each task, and form an edge node task execution time record; Based on the edge node task execution time record, by comparing the task execution time with the resource allocation efficiency, the total task completion time of each edge node is calculated to obtain the node task completion status record; Based on the node task completion status record, combined with the task completion ratio and execution status of each edge node, the overall task completion distribution is counted, the task completion status of each node is summarized, and a computing task completion statistical record is formed.

Images