AI-driven 6g edge computing resource scheduling method and system

Abstract

The application relates to the technical field of computing power scheduling, and relates to an AI-driven 6G edge computing resource scheduling method and system, which comprises the following steps: confirming an edge robot, a center computing terminal and a plurality of edge computing terminals based on a resource scheduling instruction; confirming a task difficulty index based on the edge robot; confirming a data transmission rate based on the edge robot, the center computing terminal, a center distance, total bandwidth, the number of robots and robot transmission power; confirming an edge pressure index based on the edge computing terminal; confirming a delay constraint index based on a maximum tolerable delay and total delay; inputting the task difficulty index, the edge pressure index, the total delay, the delay constraint index and total energy consumption into a pre-constructed AI scheduling model to obtain a scheduling score; and completing resource scheduling based on a target edge computing terminal and the edge robot. The application can improve the intelligent degree of resource scheduling and improve the task processing efficiency of the edge robot.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of computing power scheduling, in particular to an AI-driven 6G edge computing resource scheduling method and system. BACKGROUND

[0002] With the rapid development of edge computing and robot technology, edge robots have been widely applied in industrial, logistics, security and other scenarios. Computing resource scheduling for edge robots and then completing task distribution and processing have become a key link in the application of edge robots.

[0003] In the prior art, most resource scheduling schemes use static or heuristic algorithm-based methods to allocate tasks.

[0004] Although this way can realize the scheduling of system resources, the existing scheme fails to effectively consider the energy consumption and delay of tasks in the task scheduling process, resulting in low overall computing energy efficiency and inability to meet the actual demand for efficient computing. Therefore, how to improve the intelligent degree of scheduling computing resources for edge robots and improve the task processing efficiency of edge robots has become a technical problem to be solved at present. SUMMARY

[0005] The application provides an AI-driven 6G edge computing resource scheduling method and system, which mainly aims to improve the intelligent degree of resource scheduling and improve the task processing efficiency of edge robots.

[0006] To achieve the above purpose, the AI-driven 6G edge computing resource scheduling method provided by the application comprises the following steps:

[0007] Receiving a resource scheduling instruction, confirming an edge robot, a central computing end and a plurality of edge computing ends based on the resource scheduling instruction, wherein the edge robot and the central computing end have a data transmission function, and each of the plurality of edge computing ends has a data transmission function with the central computing end;

[0008] Obtaining processing task information, total bandwidth, robot quantity and robot transmission power of the edge robot, wherein the processing task information comprises a center distance, a data size and a maximum tolerable delay;

[0009] Confirming a task difficulty index based on the edge robot;

[0010] Confirming a data transmission rate based on the edge robot, the central computing end, the center distance, the total bandwidth, the robot quantity and the robot transmission power;

[0011] Each of the plurality of edge computing ends performs the following operation:

[0012] Confirming the edge pressure index based on the edge computing end;

[0013] Obtaining edge resource data and edge bandwidth, wherein the edge resource data includes task load, CPU frequency, load capacitance, working voltage and clock frequency;

[0014] Confirming the total delay based on data size, data transmission rate, center distance, data transmission rate and edge bandwidth;

[0015] Confirming the total energy consumption based on data size, data transmission rate, robot transmission power and edge resource data;

[0016] Confirming the delay constraint index based on the maximum tolerable delay and the total delay;

[0017] Inputting the task difficulty index, the edge pressure index, the total delay, the delay constraint index and the total energy consumption into a pre-built AI scheduling model to obtain a scheduling score;

[0018] Summarizing the scheduling scores to obtain a plurality of scheduling scores, wherein the scheduling scores correspond one-to-one to the edge computing ends;

[0019] Confirming a target edge computing end based on the plurality of scheduling scores, and completing resource scheduling based on the target edge computing end and the edge robot.

[0020] Optionally, the confirming the task difficulty index based on the edge robot comprises:

[0021] Obtaining a plurality of sets of historical task information of the edge robot, wherein the historical task information includes completion time, energy consumption and failure rate;

[0022] Extracting a plurality of completion times, a plurality of energy consumptions and a plurality of failure rates from the plurality of sets of historical task information;

[0023] Respectively performing normalization operations on the plurality of completion times, the plurality of energy consumptions and the plurality of failure rates to obtain a plurality of standard times, a plurality of standard energy consumptions and a plurality of standard failure rates;

[0024] Respectively performing weight calculations on the plurality of standard times, the plurality of standard energy consumptions and the plurality of standard failure rates to obtain time weight, energy consumption weight and failure rate weight;

[0025] Confirming an average time based on the plurality of standard times, wherein the average time is an average value of the plurality of standard times;

[0026] Confirming an average energy consumption based on the plurality of standard energy consumptions, wherein the average energy consumption is an average value of the plurality of standard energy consumptions;

[0027] Confirming an average failure rate based on the plurality of standard failure rates, wherein the average failure rate is an average value of the plurality of standard failure rates;

[0028] The task difficulty index is calculated based on the average time, average energy consumption, average failure rate, time weight, energy consumption weight, and failure rate weight. The calculation formula is as follows:

[0029]

[0030] in, represents the task difficulty index, represents the average time, represents the average energy consumption, represents the average failure rate, represents the time weight, represents the energy consumption weight, Represents the failure rate weight.

[0031] Optionally, determining the data transmission rate based on the edge robot, the central computing terminal, the center distance, the total bandwidth, the number of robots, and the robot transmission power includes:

[0032] Noise is collected from the edge robot and the central computing end to obtain edge noise signals, wherein the collection frequency and collection time of the noise are preset;

[0033] Performing a fast Fourier transform on the edge noise signal to obtain an amplitude spectrum, wherein the amplitude spectrum includes a plurality of frequency points and a plurality of amplitude values, wherein the frequency points correspond to the amplitude values ​​one to one;

[0034] The average amplitude value is determined based on the amplitude spectrum. The calculation formula is as follows:

[0035]

[0036] in, represents the average amplitude value, Indicates the number of frequency points in multiple frequency points, Indicates the first of multiple frequency points The amplitude value of the frequency point, Indicates taking the absolute value;

[0037] The noise power spectral density is calculated based on the acquisition frequency and average amplitude value. The calculation formula is as follows:

[0038]

[0039] in, represents the noise power spectral density, Indicates the acquisition frequency;

[0040] The data transmission rate is calculated based on the center distance, total bandwidth, number of robots, robot transmission power, and noise power spectrum density. The calculation formula is as follows:

[0041]

[0042] wherein, denotes a data transmission rate, denotes a total bandwidth, denotes a number of robots, denotes a robot transmission power, denotes a center distance, is a preset noise index, is a natural logarithm.

[0043] Optionally, the edge computing end confirms the edge pressure index, comprising:

[0044] obtaining a plurality of historical queuing information of the edge computing end, wherein the historical queuing information comprises: a queuing quantity and a queuing duration;

[0045] inputting a plurality of queuing quantities in the plurality of historical queuing information into a pre-constructed ARIMA model to obtain a future queuing quantity;

[0046] confirming an average queuing duration based on a plurality of queuing durations, wherein the average queuing duration is an average value of the plurality of queuing durations;

[0047] confirming the edge pressure index based on the future queuing quantity and the average queuing duration, wherein the edge pressure index is a product of the future queuing quantity and the average queuing duration.

[0048] Optionally, the total delay is confirmed based on the data size, the data transmission rate, the center distance, the data transmission rate and the edge bandwidth, comprising:

[0049] calculating a first delay according to the data size, the data transmission rate and the center distance, and the calculation formula is as follows:

[0050]

[0051] wherein, denotes the first delay, denotes the data size, is a preset speed of light;

[0052] calculating a second delay according to the data size and the edge bandwidth, and the calculation formula is as follows:

[0053]

[0054] wherein, denotes the second delay, denotes the edge bandwidth;

[0055] The total delay is confirmed based on the first delay and the second delay, wherein the total delay is a sum of the first delay and the second delay.

[0056] Optionally, the total energy consumption is confirmed based on the data size, the data transmission rate, the robot transmission power and the edge resource data, comprising:

[0057] The first energy consumption is calculated according to the data size, the data transmission rate and the robot transmission power, and the calculation formula is as follows:

[0058]

[0059] wherein, represents the first energy consumption;

[0060] The second energy consumption is calculated according to the task load, the CPU frequency, the load capacitance, the working voltage and the clock frequency in the edge resource data, and the calculation formula is as follows:

[0061]

[0062] wherein, represents the second energy consumption, represents the load capacitance, represents the working voltage, represents the clock frequency, represents the CPU frequency, represents the task load;

[0063] The total energy consumption is confirmed based on the first energy consumption and the second energy consumption, wherein the total energy consumption is a sum of the first energy consumption and the second energy consumption.

[0064] Optionally, the delay constraint index is confirmed based on the maximum tolerable delay and the total delay, comprising:

[0065] The delay constraint index is calculated according to the maximum tolerable delay and the total delay, and the calculation formula is as follows:

[0066]

[0067] wherein, represents the delay constraint index, represents the total delay, represents the maximum tolerable delay.

[0068] Optionally, the AI scheduling model is as follows:

[0069]

[0070] wherein, represents the AI scheduling model, represents the task difficulty index, is an edge pressure index, is a delay constraint index, is a total energy consumption, is a total delay, is an exponential function, is a preset energy consumption delay proportion, is a natural constant.

[0071] Optionally, the target edge computing end is confirmed based on the plurality of scheduling scores, including:

[0072] The plurality of scheduling scores are zero-eliminated and screened to obtain a zero-eliminated scheduling score set;

[0073] The best scheduling score is confirmed based on the zero-eliminated scheduling score set, wherein the best scheduling score is the smallest zero-eliminated scheduling score in the zero-eliminated scheduling score set;

[0074] The edge computing end corresponding to the best scheduling score is taken as the target edge computing end.

[0075] To achieve the above object, the application further provides an AI-driven 6G edge computing resource scheduling system, including:

[0076] A basic device confirmation module is configured to receive a resource scheduling instruction and confirm an edge robot, a center computing end and a plurality of edge computing ends based on the resource scheduling instruction, wherein the edge robot and the center computing end have a data transmission function, and the center computing end and each edge computing end of the plurality of edge computing ends have a data transmission function;

[0077] A task information processing module is configured to obtain processing task information of the edge robot, total bandwidth, robot quantity and robot transmission power, and process the task information, including a center distance, data size and maximum tolerable delay, confirm a task difficulty index based on the edge robot, and confirm a data transmission rate based on the edge robot, the center computing end, the center distance, the total bandwidth, the robot quantity and the robot transmission power;

[0078] An edge information processing module is configured to perform the following operations on each edge computing end of the plurality of edge computing ends: confirm an edge pressure index based on the edge computing end, obtain edge resource data and edge bandwidth, wherein the edge resource data includes task load, CPU frequency, load capacitance, working voltage and clock frequency, confirm a total delay based on the data size, the data transmission rate, the center distance, the data transmission rate and the edge bandwidth, confirm a total energy consumption based on the data size, the data transmission rate, the robot transmission power and the edge resource data, and confirm a delay constraint index based on the maximum tolerable delay and the total delay;

[0079] The intelligent scoring scheduling module is configured to input the task difficulty index, the edge pressure index, the total delay, the delay constraint index and the total energy consumption into a pre-constructed AI scheduling model to obtain a scheduling score, aggregate the scheduling scores to obtain a plurality of scheduling scores, wherein the scheduling scores correspond to the edge computing ends one by one, confirm a target edge computing end based on the plurality of scheduling scores, and complete resource scheduling based on the target edge computing end and the edge robot.

[0080] To solve the above problems, the present application further provides an electronic device, which comprises:

[0081] a memory configured to store at least one instruction; and

[0082] a processor configured to execute the instruction stored in the memory to implement the AI-driven 6G edge computing resource scheduling method described above.

[0083] To solve the above problems, the present application further provides a computer readable storage medium, which stores at least one instruction, and the at least one instruction is executed by a processor in an electronic device to implement the AI-driven 6G edge computing resource scheduling method described above.

[0084] The application is to solve the problems described in the background art. The application confirms the edge robot, the center computing terminal and the plurality of edge computing terminals based on the resource scheduling instruction. The edge robot and the center computing terminal have data transmission function. The center computing terminal and each edge computing terminal of the plurality of edge computing terminals have data transmission function. It can be seen that the edge robot, the center computing terminal and the plurality of edge computing terminals are confirmed in advance in the embodiment of the application. The subsequent calculation task generated by the edge robot is distributed to the edge computing terminal for calculation and processing by using the center computing terminal. The intelligent degree of resource scheduling is improved. The processing task information, the total bandwidth, the number of robots and the robot transmission power of the edge robot are obtained. The processing task information includes the center distance, the data size and the maximum tolerable delay. It can be seen that the processing task information, the total bandwidth, the number of robots and the robot transmission power of the edge robot are obtained in the embodiment of the application. The calculation task generated by the edge robot is analyzed. The task difficulty index is calculated. The subsequent automatic edge computing resource scheduling is performed according to the task difficulty index. The intelligent degree of resource scheduling is improved. The data transmission rate is calculated based on the edge robot, the center computing terminal, the center distance, the total bandwidth, the number of robots and the robot transmission power. It can be seen that the delay of data transmission is considered in the embodiment of the application. The subsequent edge computing resource scheduling is performed according to the data transmission rate. The intelligent degree of resource scheduling is improved. The following operation is performed on each edge computing terminal of the plurality of edge computing terminals: the edge pressure index is confirmed based on the edge computing terminal. It can be seen that the historical operation data of each edge computing terminal is obtained in the embodiment of the application. The current edge pressure index of each edge computing terminal is calculated. The edge resource data and the edge bandwidth are obtained. The edge resource data includes the task load, the CPU frequency, the load capacitance, the working voltage and the clock frequency. It can be seen that the real-time operation data of the edge computing terminal is obtained in the embodiment of the application. The total delay and the total energy consumption are calculated subsequently. The total delay is confirmed based on the data size, the data transmission rate, the center distance, the data transmission rate and the edge bandwidth. The total energy consumption is confirmed based on the data size, the data transmission rate, the robot transmission power and the edge resource data. It can be seen that the total delay and the total energy consumption required for completing the calculation task are calculated comprehensively in the embodiment of the application. The intelligent scheduling of edge computing resources is performed subsequently according to the total delay and the total energy consumption. The delay and the energy consumption are reduced. The task processing efficiency of the edge robot is improved. The delay constraint index is confirmed based on the maximum tolerable delay and the total delay. It can be seen that the delay constraint index is confirmed by comparing the maximum tolerable delay and the total delay in the embodiment of the application. The scheduling score is calculated subsequently.The task processing efficiency of the edge robot is improved, the task difficulty index, the edge pressure index, the total delay, the delay constraint index and the total energy consumption are input to the pre-constructed AI scheduling model to obtain a scheduling score, it can be seen that the embodiment of the present application uses the pre-constructed AI scheduling model to analyze the obtained data, thereby intelligently obtaining the scheduling score, improving the intelligent degree of resource scheduling, and the scheduling score is one-to-one corresponding to the edge computing end, it can be seen that the embodiment of the present application calculates the scheduling score of each edge computing end, and the scheduling scores are summarized, so as to facilitate subsequent confirmation of the best scheduling score, the target edge computing end is confirmed based on the multiple scheduling scores, and the resource scheduling is completed based on the target edge computing end and the edge robot, it can be seen that the embodiment of the present application confirms the best edge computing end through the best scheduling score, so as to distribute the computing task to the best edge computing end, and then intelligently realize the edge computing resource scheduling. Therefore, the present application can improve the intelligent degree of resource scheduling and improve the task processing efficiency of the edge robot. BRIEF DESCRIPTION OF DRAWINGS

[0085] Figure 1 The flowchart of the AI-driven 6G edge computing resource scheduling method provided by an embodiment of the present application is shown.

[0086] Figure 2 The functional module diagram of the AI-driven 6G edge computing resource scheduling system provided by an embodiment of the present application is shown.

[0087] Figure 3 The structural schematic diagram of the electronic device for implementing the AI-driven 6G edge computing resource scheduling method provided by an embodiment of the present application is shown.

[0088] Explanation of reference signs:

[0089] 1, electronic device; 10, processor; 11, storage; 12, bus.

[0090] The implementation of the present application, the functional characteristics and the advantages will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0091] It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0092] The embodiment of the present application provides an AI-driven 6G edge computing resource scheduling method. The execution subject of the AI-driven 6G edge computing resource scheduling method includes but is not limited to at least one of electronic devices such as a server, a terminal and the like which can be configured to execute the method provided by the embodiment of the present application. In other words, the AI-driven 6G edge computing resource scheduling method can be executed by software or hardware installed in a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to a single server, a server cluster, a cloud server or a cloud server cluster and the like.

[0093] Referring to Figure 1 Fig. 1 shows a flowchart of the AI-driven 6G edge computing resource scheduling method provided by an embodiment of the present application. In the embodiment, the AI-driven 6G edge computing resource scheduling method includes the following steps.

[0094] S1, receiving a resource scheduling instruction, confirming an edge robot, a central computing end and a plurality of edge computing ends based on the resource scheduling instruction, wherein the edge robot and the central computing end have a data transmission function, and the central computing end and each of the plurality of edge computing ends have a data transmission function.

[0095] It should be explained that the resource scheduling instruction is an instruction issued by a logistics dispatcher. For example, Zhang is a logistics dispatcher who needs to schedule the computing resources of the edge robots in a logistics factory. Therefore, Zhang issues a resource scheduling instruction, and the resource scheduling instruction contains a specific number or code, so that the corresponding edge robot, central computing end and a plurality of edge computing ends can be confirmed through the specific number or code. The edge robot refers to a sorting robot in a logistics factory which performs sorting and carrying tasks. The central computing end is a computer responsible for distributing computing tasks generated by the edge robot to the target edge computing end, wherein the computing task refers to a computing work generated by the edge robot in the logistics factory in the process of sorting and carrying goods and needs to be processed in the edge computing end. For example, when the edge robot in the logistics factory sorts and carries goods, it will generate task requirements including but not limited to image recognition, path planning, dynamic obstacle avoidance, real-time positioning and state monitoring, i.e. computing tasks. The edge computing end is a computer responsible for processing the computing tasks generated by the edge robot.

[0096] It can be understood that the center computing end is taken as the task scheduling center of the logistics factory, responsible for unified management and distribution of the computing tasks generated by multiple edge robots, to ensure that the computing tasks are reasonably allocated to the target edge computing end. Distributing the computing tasks to the target edge computing end can make full use of the computing resources of the edge computing end, and realize the optimization of computing efficiency and computing energy consumption. Through this distributed cooperation mode of center and edge, both the local rapid response of the edge robot and the efficient scheduling of the global task are realized, thereby greatly improving the overall operation efficiency of the logistics factory.

[0097] S2, obtain processing task information, total bandwidth, robot quantity and robot transmission power of the edge robot, the processing task information including: center distance, data size and maximum tolerable delay.

[0098] It should be explained that the processing task information refers to the data of the computing task generated by the edge robot, the total bandwidth refers to the bandwidth of the communication link between the edge robot and the center computing end, usually expressed in bits per second (bps). The robot quantity refers to the number of edge robots in the logistics factory, and the robot transmission power refers to the power of the edge robot in wireless communication transmission of data with the center computing end. The center distance refers to the distance between the edge robot and the center computing end, the data size refers to the size of the data of the computing task generated by the edge robot, and the data size is exemplarily 2mb. The maximum tolerable delay refers to the longest response time allowed by the edge robot from the task initiation to the completion, and the maximum tolerable delay is artificially set by the logistics scheduler according to the task performed by the robot.

[0099] S3, confirming the task difficulty index based on the edge robot, confirming the data transmission rate based on the edge robot, the center computing end, the center distance, the total bandwidth, the robot quantity and the robot transmission power.

[0100] In detail, the task difficulty index is confirmed based on the edge robot, including:

[0101] Obtaining multiple sets of historical task information of the edge robot, wherein the historical task information includes: completion time, energy consumption and failure rate;

[0102] Extracting multiple completion times, multiple energy consumptions and multiple failure rates from the multiple sets of historical task information;

[0103] Respectively performing normalization operation on the multiple completion times, the multiple energy consumptions and the multiple failure rates to obtain multiple standard times, multiple standard energy consumptions and multiple standard failure rates;

[0104] Respectively performing weight calculation on the multiple standard times, the multiple standard energy consumptions and the multiple standard failure rates to obtain time weight, energy consumption weight and failure rate weight;

[0105] confirm an average time based on the plurality of standard times, wherein the average time is an average of the plurality of standard times;

[0106] confirm an average energy consumption based on the plurality of standard energy consumptions, wherein the average energy consumption is an average of the plurality of standard energy consumptions;

[0107] confirm an average failure rate based on the plurality of standard failure rates, wherein the average failure rate is an average of the plurality of standard failure rates;

[0108] According to the average time, the average energy consumption, the average failure rate, the time weight, the energy consumption weight and the failure rate weight, calculate the task difficulty index, the calculation formula is as follows:

[0109]

[0110] wherein, represents the task difficulty index, represents the average time, represents the average energy consumption, represents the average failure rate, represents the time weight, represents the energy consumption weight, represents the failure rate weight.

[0111] It should be explained that the historical task information refers to the data recorded when the edge robot performs the task in history, and the historical task information includes: completion time, energy consumption and failure rate. The completion time refers to the time required by the edge robot to complete each historical task, the energy consumption refers to the energy consumed by the edge robot to complete each historical task, and the failure rate refers to the probability of failure of the edge robot to complete the historical task. The completion time, energy consumption and failure rate are obtained from the log of the edge robot performing the task.

[0112] For example, if the plurality of sets of historical task information are: the first set (1s, 5j, 0.5), the second set (1s, 10j, 0.4), the third set (2s, 5j, 0.3), and the fourth set (1s, 6j, 0.2), then after extracting the plurality of completion times, the plurality of energy consumptions and the plurality of failure rates from the plurality of sets of historical task information, the plurality of completion times are (1s, 1s, 2s, 1s), the plurality of energy consumptions are (5j, 10j, 5j, 6j), and the plurality of failure rates are (0.5, 0.4, 0.3, 0.2).

[0113] It should be explained that the standard time refers to the completion time after normalization operation. The standard energy consumption is the energy consumption after normalization operation. The standard failure rate refers to the failure rate after normalization operation. The time weight reflects the contribution degree of the average completion time to the change of task difficulty. The energy consumption weight reflects the contribution degree of the average energy consumption to the change of task difficulty. The failure rate weight reflects the contribution degree of the failure rate to the change of task difficulty. The task difficulty reflects the difficulty degree of the edge robot when executing the task.

[0114] In detail, the normalization operation is performed on the plurality of completion times, the plurality of energy consumptions and the plurality of failure rates respectively to obtain a plurality of standard times, a plurality of standard energy consumptions and a plurality of standard failure rates, comprising:

[0115] The following operation is performed on each of the plurality of completion times:

[0116] The minimum completion time is determined based on the plurality of completion times, wherein the minimum completion time is the minimum value in the plurality of completion times. The maximum completion time is determined based on the plurality of completion times, wherein the maximum completion time is the maximum value in the plurality of completion times;

[0117] The standard time is calculated according to the completion time, the minimum completion time and the maximum completion time, and the calculation formula is as follows:

[0118]

[0119] wherein, denotes the standard time, denotes the completion time, denotes the minimum completion time, denotes the maximum completion time;

[0120] The standard times are summarized to obtain a plurality of standard times;

[0121] The plurality of standard energy consumptions are determined based on the plurality of energy consumptions;

[0122] The plurality of standard failure rates are determined based on the plurality of failure rates.

[0123] It should be understood that the method of determining the plurality of standard energy consumptions based on the plurality of energy consumptions and the method of determining the plurality of standard failure rates based on the plurality of failure rates are the same as the method of performing normalization operation on the plurality of completion times to obtain a plurality of standard times, which will not be described here.

[0124] In detail, the weight calculation is performed on the plurality of standard times, the plurality of standard energy consumptions and the plurality of standard failure rates respectively to obtain a time weight, an energy consumption weight and a failure rate weight, comprising:

[0125] The time weight is calculated according to the plurality of standard times, and the calculation formula is as follows:

[0126]

[0127] wherein, denotes a time weight, denotes a number of standard times, denotes a frequency point in the plurality of frequency points, denotes a frequency point in the plurality of frequency points;

[0128] The energy consumption weight is determined based on the plurality of standard energy consumptions, and the failure rate weight is determined based on the plurality of standard failure rates.

[0129] It should be understood that the method of determining the energy consumption weight based on the plurality of standard energy consumptions and the method of determining the failure rate weight based on the plurality of standard failure rates are the same as the method of calculating the time weight based on the plurality of standard times, which will not be described here.

[0130] In detail, the data transmission rate is determined based on the edge robot, the center computing end, the center distance, the total bandwidth, the number of robots, and the robot transmission power, comprising:

[0131] Noise signals of the edge robot and the center computing end are collected, wherein the collection frequency and the collection time during noise collection are preset;

[0132] The edge noise signal is subjected to fast Fourier transform to obtain an amplitude spectrum, wherein the amplitude spectrum comprises a plurality of frequency points and a plurality of amplitude values, and the frequency points and the amplitude values correspond to each other one by one;

[0133] The average amplitude value is determined based on the amplitude spectrum, and the calculation formula is as follows:

[0134]

[0135] wherein, denotes an average amplitude value, denotes a number of frequency points in the plurality of frequency points, denotes an amplitude value of a frequency point in the plurality of frequency points, denotes an amplitude value of a frequency point in the plurality of frequency points; denotes taking an absolute value;

[0136] The noise power spectral density is calculated based on the collection frequency and the average amplitude value, and the calculation formula is as follows:

[0137]

[0138] wherein, denotes a noise power spectral density, denotes a collection frequency;

[0139] The data transmission rate is calculated according to the center distance, the total bandwidth, the number of robots, the robot transmission power and the noise power spectral density, and the calculation formula is as follows:

[0140]

[0141] wherein, represents the data transmission rate, represents the total bandwidth, represents the number of robots, represents the robot transmission power, represents the center distance, is a preset noise index, is a natural logarithm.

[0142] It should be explained that the noise collection of the edge robot and the center computing end refers to collecting the transmission signal in the wireless channel between the edge robot and the center computing end, processing the collected transmission signal through a filter, filtering out the components of the useful signal in the transmission signal, and then obtaining the remaining signal, which is the edge noise signal. The specific waveform characteristics of the useful signal are artificially set by the logistics dispatcher of the logistics factory according to the characteristics of the signal waveform recorded during the data transmission between the edge robot and the center computing end in history. And the technology of processing the collected transmission signal through a filter to filter out the components of the useful signal in the transmission signal is prior art, which will not be described here.

[0143] For example, since any periodic signal (or approximately periodic signal) can be regarded as the superposition of multiple sine waves or cosine waves of different frequencies, a periodic signal can be decomposed into multiple frequency components. By performing a fast Fourier transform on the edge noise signal, a complex sequence is obtained, wherein the complex sequence includes multiple complex numbers, and each complex number in the complex sequence corresponds to a frequency component decomposed from the edge noise signal. Then the modulus of each complex number in the multiple complex numbers is calculated in turn to obtain multiple moduli. Since the complex number and the frequency component are one-to-one corresponding, the modulus reflects the vibration amplitude of the edge noise signal at the frequency component corresponding to the modulus. Therefore, by constructing a coordinate system with the moduli as the vertical axis and the frequencies as the horizontal axis, and mapping the multiple moduli and the multiple frequency components corresponding thereto onto the coordinate system, the amplitude spectrum can be obtained. The multiple frequency components in the amplitude spectrum are the multiple frequency points, and the multiple moduli in the amplitude spectrum are the multiple amplitude values. The fast Fourier transform and the steps of generating the amplitude spectrum are prior art, which will not be described here.

[0144] It can be understood that the average amplitude value refers to the arithmetic mean of the amplitude values of all frequency points in the amplitude spectrum, reflecting the intensity of the overall edge noise signal. The sampling frequency refers to the time interval of collecting the edge noise signal in the wireless channel between the edge robot and the central computing end. The noise power spectral density refers to the power distribution of noise within a bandwidth of 1 Hz, reflecting the intensity of noise at different frequencies. The larger the noise power spectral density, the stronger the interference of noise within a bandwidth of 1 Hz, and the more serious the impact on signal transmission. The data transmission rate reflects the speed of data generated by the edge robot from the edge robot to the central computing end. The larger the data transmission rate, the faster the data generated by the edge robot from the edge robot to the central computing end.

[0145] Optionally, the collection frequency is 20 hz, and the collection time is 10 s.

[0146] It should be noted that the noise index is a value set by the logistics dispatcher of the logistics factory. Optionally, the noise index is 3.

[0147] S4, for each edge computing end in the plurality of edge computing ends, the following operations are performed: based on the edge computing end confirming the edge stress index, obtaining edge resource data and edge bandwidth, wherein the edge resource data includes: task load, CPU frequency, load capacitance, working voltage and clock frequency.

[0148] It should be noted that the edge resource data refers to data related to the running state of the edge computing end, including: task load, CPU frequency, load capacitance, working voltage and clock frequency. The edge bandwidth refers to the bandwidth of the communication link between the edge computing end and the central computing end. The task load refers to the amount of computation of the computing task that the edge computing end needs to process. The CPU frequency refers to the number of oscillation periods of the processor of the edge computing end per unit time. The load capacitance is used to measure the amount of charge required by the chip to switch per unit clock period. The working voltage refers to the power supply voltage of the CPU of the edge computing end when it is working normally. The clock frequency refers to the frequency of the system clock signal of the CPU of the edge computing end.

[0149] In detail, the edge computing end confirming the edge stress index based on the edge computing end includes:

[0150] Obtaining a plurality of historical queuing information of the edge computing end, wherein the historical queuing information includes: queuing quantity and queuing duration;

[0151] Inputting a plurality of queuing quantities in the plurality of historical queuing information into a pre-constructed ARIMA model to obtain a future queuing quantity;

[0152] Confirming an average queuing duration based on a plurality of queuing durations, wherein the average queuing duration is the average of the plurality of queuing durations;

[0153] The edge pressure index is determined based on the future queuing quantity and the average queuing time length, wherein the edge pressure index is the product of the future queuing quantity and the average queuing time length.

[0154] It should be explained that the historical queuing information refers to the data of the task queuing condition recorded by the edge computing end in the running process, which can be obtained from the task processing log of the edge computing end. The queuing quantity refers to the number of tasks waiting for processing in the task queue of the edge computing end in the historical sampling period, and the queuing time length refers to the time waiting for each task from entering the queue to starting processing.

[0155] For example, there are multiple edge robots in a logistics factory, each of which generates a computing task. The computing task generated by the edge robot is distributed to the edge computing end for calculation via the center computing end. Since the number of edge computing ends is limited and a certain time is needed to complete the computing task, when the number of computing tasks is greater than the number of edge computing ends, the task queuing condition occurs. When the queued task is queued at the edge computing end, the edge computing end needs to complete the processing of the current computing task before processing the queued task, and the completion time of the queued task will also be affected by the queuing time length.

[0156] It can be understood that the main operation principle of the ARIMA model is as follows: the autoregression (AR), difference (I) and moving average (MA) modules in the ARIMA model are used to model, stabilize and correct the residual error of multiple queuing quantities to obtain the prediction result of the future queuing quantity, the difference module is used to eliminate the non-stationarity of the prediction result and obtain a stationary result sequence, and finally the moving average module is used to white noise correct the model residual error of the stationary result sequence to obtain the future queuing quantity. The above process is a publicly disclosed technical solution, and the embodiments of the present application will not be described here. The future queuing quantity refers to the number of queued tasks of the edge computing end in a future time period. The edge pressure index reflects the current pressure condition of the edge computing end, and the greater the edge pressure index, the greater the current computing pressure of the edge computing end.

[0157] S5, based on the data size, data transmission rate, center distance, data transmission rate and edge bandwidth, the total delay is determined, and based on the data size, data transmission rate, robot transmission power and edge resource data, the total energy consumption is determined.

[0158] In detail, the total delay is determined based on the data size, data transmission rate, center distance, data transmission rate and edge bandwidth, comprising:

[0159] The first delay is calculated according to the data size, data transmission rate and center distance, and the calculation formula is as follows:

[0160]

[0161] wherein, represents the first delay, represents the data size, is a preset light speed;

[0162] The second delay is calculated according to the data size and the edge bandwidth, and the calculation formula is as follows:

[0163]

[0164] wherein, represents the second delay, represents the edge bandwidth;

[0165] The total delay is confirmed based on the first delay and the second delay, wherein the total delay is the sum of the first delay and the second delay.

[0166] It should be explained that the first delay reflects the time length of the data of the computing task generated by the edge robot being transmitted from the edge robot to the center computing end, the greater the first delay, the longer the time of the data of the computing task generated by the edge robot being transmitted from the edge robot to the center computing end. The second delay reflects the time length of the data of the computing task generated by the edge robot being transmitted from the center computing end to the edge computing end, the greater the second delay, the longer the time of the data of the computing task generated by the edge robot being transmitted from the center computing end to the edge computing end. The total delay reflects the total time length required for the computing task generated by the robot to be completed, the greater the total delay, the longer the total time length required for the computing task to be completed, and the light speed is .

[0167] In detail, the total energy consumption is confirmed based on the data size, the data transmission rate, the robot transmission power and the edge resource data, comprising:

[0168] The first energy consumption is calculated according to the data size, the data transmission rate and the robot transmission power, and the calculation formula is as follows:

[0169]

[0170] wherein, represents the first energy consumption;

[0171] The second energy consumption is calculated according to the task load, the CPU frequency, the load capacitance, the working voltage and the clock frequency in the edge resource data, and the calculation formula is as follows:

[0172]

[0173] wherein, represents the second energy consumption, represents the load capacitance, represents the working voltage, Indicates the clock frequency, Indicates the CPU frequency, Indicates task load;

[0174] A total energy consumption is determined based on the first energy consumption and the second energy consumption, wherein the total energy consumption is the sum of the first energy consumption and the second energy consumption.

[0175] It should be explained that the first energy consumption reflects the amount of energy consumed when the data of the computing tasks generated by the edge robot is transmitted from the edge robot to the central computing end. The greater the first energy consumption, the more energy is consumed when the data of the computing tasks generated by the edge robot is transmitted from the edge robot to the central computing end. The second energy consumption reflects the amount of energy consumed when the data of the computing tasks generated by the edge robot is transmitted from the central computing end to the edge computing end. The greater the second energy consumption, the more energy is consumed when the data of the computing tasks generated by the edge robot is transmitted from the central computing end to the edge computing end. The total energy consumption reflects the total energy required to complete the computing tasks generated by the edge robot. The greater the total energy consumption, the greater the total energy required to complete the computing tasks.

[0176] S6. Determine the delay constraint index based on the maximum tolerable delay and total delay, and input the task difficulty index, edge pressure index, total delay, delay constraint index and total energy consumption into the pre-built AI scheduling model to obtain the scheduling score.

[0177] Specifically, determining the delay constraint index based on the maximum tolerable delay and the total delay includes:

[0178] The delay constraint index is calculated based on the maximum tolerable delay and the total delay. The calculation formula is as follows:

[0179]

[0180] in, represents the delay constraint index, represents the total delay, Indicates the maximum tolerable delay.

[0181] It should be explained that the delay constraint index is used to measure whether the current delay of the computing task meets the task requirements. If the total delay is less than or equal to the maximum tolerable delay, it means that the computing task is completed within the maximum tolerable delay range, and the value is assigned to 1, indicating that the task meets the delay requirements. If the total delay is greater than the maximum tolerable delay, the task times out and the value is assigned to 0, indicating that the task does not meet the delay requirements.

[0182] In detail, the AI ​​scheduling model is as follows:

[0183]

[0184] in, represents an AI scheduling model, represents a task difficulty index, is an edge pressure index, represents a delay constraint index, represents total energy consumption, represents total delay, is an exponential function, is a preset energy consumption and delay proportion, is a natural constant.

[0185] It should be explained that the scheduling score is a value calculated by inputting the task difficulty index, the edge pressure index, the total delay, the delay constraint index and the total energy consumption into the AI scheduling model. The scheduling score is used to quantify the appropriateness of the allocation of the computing task of the edge robot to the edge computing end. The smaller the scheduling score, the higher the appropriateness of the allocation of the computing task of the edge robot to the edge computing end. The energy consumption and delay proportion is a value artificially set by the logistics scheduler of the logistics factory according to historical data. Alternatively, the average energy consumption and the average delay of the edge computing end in processing the computing task in the past are obtained, and the proportion of the average energy consumption in the sum of the average energy consumption and the average delay is taken as the energy consumption and delay proportion.

[0186] S7, aggregating the scheduling scores to obtain a plurality of scheduling scores, wherein the scheduling scores correspond to the edge computing ends one by one, confirming a target edge computing end based on the plurality of scheduling scores, and completing resource scheduling based on the target edge computing end and the edge robot.

[0187] In detail, the confirming of the target edge computing end based on the plurality of scheduling scores comprises:

[0188] performing zero-removal screening on the plurality of scheduling scores to obtain a zero-removed scheduling score set;

[0189] confirming a best scheduling score based on the zero-removed scheduling score set, wherein the best scheduling score is the smallest zero-removed scheduling score in the zero-removed scheduling score set;

[0190] taking the edge computing end corresponding to the best scheduling score as the target edge computing end.

[0191] It should be explained that the zero-removal screening on the plurality of scheduling scores means that the scheduling scores with a value of 0 in the plurality of scheduling scores are screened out. For example, if the values of the plurality of scheduling scores are 1, 2, 3, 0, 2 and 1, the zero-removed scheduling score set obtained after the zero-removal screening is 1, 2, 3, 2 and 1. The zero-removed scheduling score set refers to a set composed of the scheduling scores after the zero-removal screening. The target edge computing end refers to the edge computing end corresponding to the best scheduling score.

[0192] The application is to solve the problems described in the background art. The application confirms the edge robot, the center computing terminal and the plurality of edge computing terminals based on the resource scheduling instruction. The edge robot and the center computing terminal have data transmission function. The center computing terminal and each edge computing terminal of the plurality of edge computing terminals have data transmission function. It can be seen that the edge robot, the center computing terminal and the plurality of edge computing terminals are confirmed in advance in the embodiment of the application. The subsequent calculation task generated by the edge robot is distributed to the edge computing terminal for calculation and processing by using the center computing terminal. The intelligent degree of resource scheduling is improved. The processing task information, the total bandwidth, the number of robots and the robot transmission power of the edge robot are obtained. The processing task information includes the center distance, the data size and the maximum tolerable delay. It can be seen that the processing task information, the total bandwidth, the number of robots and the robot transmission power of the edge robot are obtained in the embodiment of the application. The calculation task generated by the edge robot is analyzed. The task difficulty index is calculated. The subsequent automatic edge computing resource scheduling is performed according to the task difficulty index. The intelligent degree of resource scheduling is improved. The data transmission rate is calculated based on the edge robot, the center computing terminal, the center distance, the total bandwidth, the number of robots and the robot transmission power. It can be seen that the delay of data transmission is considered in the embodiment of the application. The subsequent edge computing resource scheduling is performed according to the data transmission rate. The intelligent degree of resource scheduling is improved. The following operation is performed on each edge computing terminal of the plurality of edge computing terminals: the edge pressure index is confirmed based on the edge computing terminal. It can be seen that the historical operation data of each edge computing terminal is obtained in the embodiment of the application. The current edge pressure index of each edge computing terminal is calculated. The edge resource data and the edge bandwidth are obtained. The edge resource data includes the task load, the CPU frequency, the load capacitance, the working voltage and the clock frequency. It can be seen that the real-time operation data of the edge computing terminal is obtained in the embodiment of the application. The total delay and the total energy consumption are calculated subsequently. The total delay is confirmed based on the data size, the data transmission rate, the center distance, the data transmission rate and the edge bandwidth. The total energy consumption is confirmed based on the data size, the data transmission rate, the robot transmission power and the edge resource data. It can be seen that the total delay and the total energy consumption required for completing the calculation task are calculated comprehensively in the embodiment of the application. The intelligent scheduling of edge computing resources is performed subsequently according to the total delay and the total energy consumption. The delay and the energy consumption are reduced. The task processing efficiency of the edge robot is improved. The delay constraint index is confirmed based on the maximum tolerable delay and the total delay. It can be seen that the delay constraint index is confirmed by comparing the maximum tolerable delay and the total delay in the embodiment of the application. The scheduling score is calculated subsequently.The task processing efficiency of the edge robot is improved, the task difficulty index, the edge pressure index, the total delay, the delay constraint index and the total energy consumption are input to the pre-constructed AI scheduling model to obtain a scheduling score, it can be seen that the pre-constructed AI scheduling model is used to analyze the obtained data, so that the scheduling score is intelligently obtained, the intelligent degree of resource scheduling is improved, the scheduling scores are summarized, and a plurality of scheduling scores are obtained, wherein the scheduling score corresponds to the edge computing terminal one by one, it can be seen that the scheduling score of each edge computing terminal is calculated, and the scheduling scores are summarized, so that the best scheduling score is confirmed subsequently, the target edge computing terminal is confirmed based on the plurality of scheduling scores, and the resource scheduling is completed based on the target edge computing terminal and the edge robot, it can be seen that the best edge computing terminal is confirmed through the best scheduling score, so that the computing task is distributed to the best edge computing terminal, and the edge computing resource scheduling is intelligently realized. Therefore, the intelligent degree of resource scheduling can be improved, and the task processing efficiency of the edge robot is improved.

[0193] As Figure 2 shown is a functional module diagram of an AI-driven 6G edge computing resource scheduling system provided by an embodiment of the present application.

[0194] The AI-driven 6G edge computing resource scheduling system 100 can be installed in an electronic device. According to the functions implemented, the AI-driven 6G edge computing resource scheduling system 100 can include a basic device confirmation module 101, a task information processing module 102, an edge information processing module 103 and an intelligent score scheduling module 104. The modules of the present application can also be referred to as units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0195] The basic device confirmation module 101 is configured to receive a resource scheduling instruction, and confirm an edge robot, a center computing terminal and a plurality of edge computing terminals based on the resource scheduling instruction, wherein the edge robot and the center computing terminal have a data transmission function, and the center computing terminal and each edge computing terminal of the plurality of edge computing terminals have a data transmission function.

[0196] The task information processing module 102 is configured to obtain processing task information of the edge robot, total bandwidth, robot quantity and robot transmission power, the processing task information including center distance, data size and maximum tolerable delay, confirm a task difficulty index based on the edge robot, and confirm a data transmission rate based on the edge robot, the center computing terminal, the center distance, the total bandwidth, the robot quantity and the robot transmission power.

[0197] The edge information processing module 103 is configured to perform the following operations on each edge computing terminal in the plurality of edge computing terminals: based on the edge computing terminal confirming an edge stress index, acquiring edge resource data and edge bandwidth, wherein the edge resource data comprises task load, CPU frequency, load capacitance, working voltage and clock frequency, confirming total delay based on data size, data transmission rate, center distance, data transmission rate and edge bandwidth, confirming total energy consumption based on data size, data transmission rate, robot transmission power and edge resource data, confirming delay constraint index based on maximum tolerable delay and total delay;

[0198] The intelligent scoring scheduling module 104 is configured to input the task difficulty index, the edge stress index, the total delay, the delay constraint index and the total energy consumption into a pre-constructed AI scheduling model to obtain a scheduling score, aggregate the scheduling scores to obtain a plurality of scheduling scores, wherein the scheduling score corresponds to one edge computing terminal, confirm a target edge computing terminal based on the plurality of scheduling scores, and complete resource scheduling based on the target edge computing terminal and the edge robot.

[0199] In detail, the modules in the AI-driven 6G edge computing resource scheduling system 100 in the embodiments of the present application adopt the same technical means as the AI-driven 6G edge computing resource scheduling method in the above Figure 1 , and can produce the same technical effects, which will not be described here.

[0200] As shown in Figure 3 , it is a structural schematic diagram of an electronic device for implementing the AI-driven 6G edge computing resource scheduling method according to an embodiment of the present application.

[0201] The electronic device 1 can include a processor 10, a memory 11 and a bus 12, and can further include a computer program stored in the memory 11 and executable on the processor 10, such as an AI-driven 6G edge computing resource scheduling method program.

[0202] The memory 11 includes at least one type of readable storage medium, such as flash memory, mobile hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 can also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 1. Further, the memory 11 includes both an internal storage unit and an external storage device of the electronic device 1. The memory 11 can be used not only to store application software and various data installed on the electronic device 1, such as the code of the AI-driven 6G edge computing resource scheduling method program, but also to temporarily store data that has been output or will be output.

[0203] The processor 10 can be composed of an integrated circuit in some embodiments, such as a single packaged integrated circuit or a plurality of packaged integrated circuits with the same or different functions, including one or more combinations of central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips, etc. The processor 10 is the control core of the electronic device, which connects various components of the entire electronic device through various interfaces and lines, executes programs or modules stored in the memory 11 (such as the AI-driven 6G edge computing resource scheduling method program, etc.), and calls data stored in the memory 11 to perform various functions and process data of the electronic device 1.

[0204] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0205] Figure 3 Only an electronic device with components is shown, and those skilled in the art can understand that, Figure 3The structure shown does not constitute a limitation on the electronic device 1 , and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0206] For example, although not shown, the electronic device 1 may further include a power supply (e.g., a battery) to power various components. Preferably, the power supply may be logically connected to the at least one processor 10 via a power management device, thereby enabling functions such as charge management, discharge management, and power consumption management via the power management device. The power supply may further include any components such as one or more DC or AC power supplies, a recharging device, a power failure detection circuit, a power converter or inverter, and a power status indicator. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which are not further described here.

[0207] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0208] Optionally, the electronic device 1 may further include a user interface, which may be a display or an input unit (such as a keyboard). Optionally, the user interface may also be a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. The display may also be appropriately referred to as a display screen or a display unit, and is used to display information processed by the electronic device 1 and to display a visual user interface.

[0209] The AI-driven 6G edge computing resource scheduling method program stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve:

[0210] Receive a resource scheduling instruction, and identify an edge robot, a central computing end, and multiple edge computing ends based on the resource scheduling instruction, wherein the edge robot and the central computing end have a data transmission function, and the central computing end and each of the multiple edge computing ends have a data transmission function;

[0211] Obtain edge robot processing task information, total bandwidth, number of robots, and robot transmission power. Processing task information includes: center distance, data size, and maximum tolerable delay;

[0212] Confirm a task difficulty index based on the edge robot;

[0213] Confirm a data transmission rate based on the edge robot, the center computing end, the center distance, the total bandwidth, the number of robots, and the robot transmission power;

[0214] For each edge computing end in the plurality of edge computing ends, the following operations are performed:

[0215] Confirm an edge pressure index based on the edge computing end;

[0216] Obtain edge resource data and edge bandwidth, wherein the edge resource data includes task load, CPU frequency, load capacitance, working voltage, and clock frequency;

[0217] Confirm a total delay based on the data size, the data transmission rate, the center distance, the data transmission rate, and the edge bandwidth;

[0218] Confirm a total energy consumption based on the data size, the data transmission rate, the robot transmission power, and the edge resource data;

[0219] Confirm a delay constraint index based on the maximum tolerable delay and the total delay;

[0220] Input the task difficulty index, the edge pressure index, the total delay, the delay constraint index, and the total energy consumption into a pre-constructed AI scheduling model to obtain a scheduling score;

[0221] Summarize the scheduling scores to obtain a plurality of scheduling scores, wherein the scheduling scores correspond one-to-one to the edge computing ends;

[0222] Confirm a target edge computing end based on the plurality of scheduling scores, and complete resource scheduling based on the target edge computing end and the edge robot.

[0223] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to the description of the related steps in the corresponding embodiments, which will not be repeated here. Figures 1 to 3 The description of the related steps in the corresponding embodiments, which will not be repeated here.

[0224] Further, the modules / units integrated in the electronic device 1, if implemented in the form of software function units and sold or used as independent products, can be stored in a computer readable storage medium. The computer readable storage medium can be volatile or non-volatile. For example, the computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory).

[0225] The application further provides a computer readable storage medium, which stores a computer program, and the computer program can realize the following when executed by a processor of an electronic device:

[0226] receiving a resource scheduling instruction, and confirming an edge robot, a center computing terminal and a plurality of edge computing terminals based on the resource scheduling instruction, wherein the edge robot and the center computing terminal have a data transmission function, and the center computing terminal and each of the plurality of edge computing terminals have a data transmission function;

[0227] obtaining processing task information, total bandwidth, robot quantity and robot transmission power of the edge robot, wherein the processing task information includes center distance, data size and maximum tolerable delay;

[0228] confirming a task difficulty index based on the edge robot;

[0229] confirming a data transmission rate based on the edge robot, the center computing terminal, the center distance, the total bandwidth, the robot quantity and the robot transmission power;

[0230] performing the following operations on each of the plurality of edge computing terminals:

[0231] confirming an edge pressure index based on the edge computing terminal;

[0232] obtaining edge resource data and edge bandwidth, wherein the edge resource data includes task load, CPU frequency, load capacitance, working voltage and clock frequency;

[0233] confirming total delay based on the data size, the data transmission rate, the center distance, the data transmission rate and the edge bandwidth;

[0234] confirming total energy consumption based on the data size, the data transmission rate, the robot transmission power and the edge resource data;

[0235] confirming a delay constraint index based on the maximum tolerable delay and the total delay;

[0236] inputting the task difficulty index, the edge pressure index, the total delay, the delay constraint index and the total energy consumption into a pre-constructed AI scheduling model to obtain a scheduling score;

[0237] summarizing the scheduling scores to obtain a plurality of scheduling scores, wherein the scheduling scores correspond to the edge computing terminals one by one;

[0238] confirming a target edge computing terminal based on the plurality of scheduling scores, and completing resource scheduling based on the target edge computing terminal and the edge robot.

[0239] In several embodiments provided by the present application, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the above-described system embodiments are only illustrative, and actual implementation can have other divisions.

[0240] The modules described as separate components can or can not be physically separate, and the components shown as modules can or can not be physical units, i.e., can be located in one place or distributed to multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the present embodiment.

[0241] In addition, the functional modules in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of hardware plus software functional modules.

[0242] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application.

[0243] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. An AI-driven 6G edge computing resource scheduling method, characterized in that: The method comprises: Receive a resource scheduling instruction, and identify an edge robot, a central computing end, and multiple edge computing ends based on the resource scheduling instruction, wherein the edge robot and the central computing end have a data transmission function, and the central computing end and each of the multiple edge computing ends have a data transmission function; Obtain edge robot processing task information, total bandwidth, number of robots, and robot transmission power. Processing task information includes: center distance, data size, and maximum tolerable delay; Determine the task difficulty index based on the edge robot; Determine the data transmission rate based on the edge robot, central computing terminal, center distance, total bandwidth, number of robots, and robot transmission power; Perform the following operations on each of the multiple edge computing terminals: Determine the edge pressure index based on the edge computing end; Obtain edge resource data and edge bandwidth, where edge resource data includes: task load, CPU frequency, load capacitance, operating voltage, and clock frequency; Determine the total latency based on data size, data rate, center distance, data rate, and edge bandwidth; Determine the total energy consumption based on data size, data transmission rate, robot transmission power and edge resource data; Determine the delay constraint index based on the maximum tolerable delay and the total delay; Input the task difficulty index, edge pressure index, total delay, delay constraint index and total energy consumption into the pre-built AI scheduling model to obtain the scheduling score; Summarize the scheduling scores to obtain multiple scheduling scores, where the scheduling scores correspond one-to-one to the edge computing terminals; The target edge computing end is identified based on multiple scheduling scores, and resource scheduling is completed based on the target edge computing end and edge robot.

2. The AI-driven 6G edge computing resource scheduling method according to claim 1, characterized in that: The determination of the task difficulty index based on the edge robot includes: Obtain multiple sets of historical task information of the edge robot, where the historical task information includes: completion time, energy consumption, and failure rate; Extract multiple completion times, multiple energy consumptions, and multiple failure rates from multiple sets of historical task information; Normalizing the multiple completion times, the multiple energy consumptions, and the multiple failure rates respectively to obtain multiple standard times, multiple standard energy consumptions, and multiple standard failure rates; The weights of multiple standard times, multiple standard energy consumptions and multiple standard failure rates are calculated respectively to obtain time weights, energy consumption weights and failure rate weights; Determine an average time based on the multiple standard times, wherein the average time is an average value of the multiple standard times; Determine an average energy consumption based on multiple standard energy consumptions, wherein the average energy consumption is an average value of the multiple standard energy consumptions; Determining an average failure rate based on multiple standard failure rates, wherein the average failure rate is an average of the multiple standard failure rates; The task difficulty index is calculated based on the average time, average energy consumption, average failure rate, time weight, energy consumption weight and failure rate weight.

3. The AI-driven 6G edge computing resource scheduling method according to claim 2, characterized in that: The data transmission rate is determined based on the edge robot, the central computing terminal, the center distance, the total bandwidth, the number of robots, and the robot transmission power, including: Noise is collected from the edge robot and the central computing end to obtain edge noise signals, wherein the collection frequency and collection time of the noise are preset; Performing a fast Fourier transform on the edge noise signal to obtain an amplitude spectrum, wherein the amplitude spectrum includes a plurality of frequency points and a plurality of amplitude values, wherein the frequency points correspond to the amplitude values ​​one to one; Determine the average amplitude value based on the amplitude spectrum; Calculate the noise power spectral density based on the acquisition frequency and average amplitude value; The data transmission rate is calculated based on the center distance, total bandwidth, number of robots, robot transmission power, and noise power spectrum density.

4. The AI-driven 6G edge computing resource scheduling method according to claim 3, characterized in that: The determining of the edge pressure index based on the edge computing end includes: Obtain multiple historical queue information from the edge computing end, where the historical queue information includes: queue number and queue duration; Input multiple queue quantities from multiple historical queue information into the pre-built ARIMA model to obtain the future queue quantity; Determine an average queue time based on multiple queue times, where the average queue time is the average of the multiple queue times; The marginal pressure index is determined based on the number of future queues and the average queue time, wherein the marginal pressure index is the product of the number of future queues and the average queue time.

5. The AI-driven 6G edge computing resource scheduling method according to claim 4, characterized in that: The total latency is determined based on data size, data transmission rate, center distance, data transmission rate, and edge bandwidth, including: Calculating a first delay based on data size, data transmission rate, and center distance; Calculate the second delay according to the data size and edge bandwidth; A total delay is determined based on the first delay and the second delay, wherein the total delay is the sum of the first delay and the second delay.

6. The AI-driven 6G edge computing resource scheduling method according to claim 5, characterized in that: The total energy consumption is determined based on data size, data transmission rate, robot transmission power and edge resource data, including: Calculate the first energy consumption based on the data size, data transmission rate and robot transmission power; Calculating a second energy consumption based on the task load, CPU frequency, load capacitance, operating voltage, and clock frequency in the edge resource data; A total energy consumption is determined based on the first energy consumption and the second energy consumption, wherein the total energy consumption is the sum of the first energy consumption and the second energy consumption.

7. The AI-driven 6G edge computing resource scheduling method according to claim 6, characterized in that: Determining the delay constraint index based on the maximum tolerable delay and the total delay includes: The delay constraint index is calculated based on the maximum tolerable delay and the total delay. The calculation formula is as follows: in, represents the delay constraint index, represents the total delay, Indicates the maximum tolerable delay.

8. The AI-driven 6G edge computing resource scheduling method according to claim 7, characterized in that: The AI ​​scheduling model is as follows: in, represents the AI ​​scheduling model, represents the task difficulty index, is the edge pressure index, represents the delay constraint index, represents the total energy consumption, represents the total delay, is an exponential function, is the preset energy consumption delay ratio, is a natural constant.

9. The AI-driven 6G edge computing resource scheduling method according to claim 8, characterized in that: The determining of the target edge computing end based on multiple scheduling scores includes: Perform zero-removal screening on multiple scheduling scores to obtain a zero-removed scheduling score set; Determine the optimal scheduling score based on the zero-removing scheduling score set, wherein the optimal scheduling score is the minimum zero-removing scheduling score in the zero-removing scheduling score set; The edge computing end corresponding to the best scheduling score is used as the target edge computing end.

10. An AI-driven 6G edge computing resource scheduling system, characterized in that: The system comprises: A basic equipment confirmation module is used to receive resource scheduling instructions and confirm the edge robot, the central computing end, and multiple edge computing ends based on the resource scheduling instructions. The edge robot and the central computing end have a data transmission function, and the central computing end and each of the multiple edge computing ends have a data transmission function; The task information processing module is used to obtain the processing task information, total bandwidth, number of robots, and robot transmission power of the edge robot. The processing task information includes: center distance, data size, and maximum tolerable delay. The task difficulty index is determined based on the edge robot, and the data transmission rate is determined based on the edge robot, center computing end, center distance, total bandwidth, number of robots, and robot transmission power. an edge information processing module, configured to perform the following operations on each of the plurality of edge computing terminals: determining an edge pressure index based on the edge computing terminal, obtaining edge resource data and edge bandwidth, wherein the edge resource data includes task load, CPU frequency, load capacitance, operating voltage, and clock frequency; determining a total delay based on data size, data transmission rate, center distance, data transmission rate, and edge bandwidth; determining a total energy consumption based on data size, data transmission rate, robot transmission power, and edge resource data; and determining a delay constraint index based on a maximum tolerable delay and total delay; The intelligent scoring scheduling module is used to input the task difficulty index, edge pressure index, total delay, delay constraint index and total energy consumption into the pre-built AI scheduling model to obtain a scheduling score, summarize the scheduling scores, and obtain multiple scheduling scores. Among them, the scheduling score corresponds one-to-one to the edge computing end. Based on multiple scheduling scores, the target edge computing end is confirmed, and resource scheduling is completed based on the target edge computing end and the edge robot.

Images