Edge computing fine granularity scheduling method based on IBBO algorithm

Abstract

The invention relates to an edge computing fine granularity scheduling method based on an IBBO algorithm, and the method comprises the steps: obtaining a to-be-processed task of each terminal device in real time, carrying out the task decomposition of the to-be-processed task greater than a preset threshold value according to a specified mode, and obtaining to-be-processed sub-tasks; allocating corresponding priorities to the to-be-processed sub-tasks according to the importance and the emergency degree of the tasks; based on the to-be-processed sub-tasks and the corresponding priorities, a multi-objective optimization model of task scheduling is constructed, a fitness function is set for the multi-objective optimization model, and the optimal solution of the fitness function is a comprehensive optimal solution of optimal time delay and energy consumption based on task scheduling; solving the comprehensive optimal solution of the fitness function of the multi-objective optimization model based on an IBBO algorithm; and scheduling the to-be-processed sub-tasks based on the obtained comprehensive optimal solution. The migration probability between individuals is dynamically adjusted through a self-adaptive migration mechanism of the IBBO algorithm and an improved migration strategy, so that the optimization process is accelerated, the search efficiency is improved, and falling into a local optimal solution is avoided.

Description

Technical Field

[0001] The present invention belongs to the technical field of edge computing and task scheduling, and particularly relates to a fine-grained scheduling method for edge computing based on the IBBO algorithm. The IBBO algorithm is an improved biogeography-based optimization algorithm. Background Art

[0002] As a distributed computing model, edge computing pushes data processing capabilities to the network edge to reduce latency and bandwidth utilization and support rapid response to real-time data. In today's information society, edge computing plays an increasingly important role. However, task scheduling in the edge computing environment faces many challenges, and the most critical one is fine-grained task scheduling. This task scheduling must maximize resource utilization while meeting the performance requirements of application programs, so it is of extremely high importance.

[0003] The original intention of edge computing is to share the task processing pressure of the cloud computing center to improve service quality and response speed. However, the resources and computing capabilities of edge computing nodes are limited, which enables them to only process a small number of tasks. Therefore, how to reasonably schedule tasks to the corresponding edge nodes has become a difficult problem that needs to be solved urgently. This challenge mainly stems from two aspects: one is the difference in the distance between edge nodes and the cloud computing center, which leads to differences in the time and energy consumption required for task scheduling; the other is that different tasks require different computing resources. If small tasks are scheduled to edge nodes with strong computing capabilities, it will result in resource waste. Therefore, how to maximize the utilization of edge node resources on the premise of ensuring task scheduling efficiency has become an urgent problem to be solved.

[0004] There are the following several task scheduling strategies in the prior art: 1. Multi-user fine-grained task offloading scheduling for mobile edge computing: This solution abstracts computing tasks into a directed acyclic graph and uses the improved NSGA-II algorithm to solve the task offloading scheduling solution with the system latency as the optimization goal, considering constraints such as deadlines, priorities, and node completion deadlines.

[0005] 2. Adaptive genetic algorithm for MEC task offloading and resource allocation: This solution takes the total system cost as the optimization goal and decomposes it into three sub-problems, including task scheduling, resource allocation, etc. Through the adaptive genetic algorithm, these sub-problems are solved one by one to obtain a comprehensive task scheduling and resource offloading solution.

[0006] 3. Edge computing scheduling based on deep reinforcement learning: This solution aims to maximize task satisfaction. By scheduling multiple tasks into virtual machines on edge servers and using the deep reinforcement learning algorithm to solve the problems of time scheduling and resource allocation.

[0007] Although the above several task scheduling strategies have solved some technical problems to a certain extent, there are still some common limitations, including a huge search space: traditional optimization algorithms often need to face a large number of task and resource combination possibilities in the edge computing environment. This results in the algorithm consuming a large amount of computing resources and time to explore the search space, limiting its feasibility and practicality in practice. Slow convergence speed: When dealing with task scheduling problems in the edge computing environment, many existing algorithms have a slow convergence speed due to the complexity of the search space. The long computing process not only increases the delay of task scheduling but also may lead to the inability to meet real-time performance requirements. Prone to local optimal solutions: Some algorithms are prone to falling into local optimal solutions during the search process and cannot globally optimize the task scheduling scheme. This situation may be caused by limitations in algorithm design or deficiencies in search strategies, affecting the quality and performance of task scheduling.

[0008] Therefore, how to improve the task scheduling optimization algorithm in the prior art to solve the technical limitations of the above task scheduling strategies is a technical problem that urgently needs to be solved at present. Summary of the Invention

[0009] The purpose of the present invention is to provide a fine-grained scheduling method for edge computing based on the IBBO algorithm, which is used to improve the classical biogeography-based optimization algorithm. A decision-making mechanism and a dynamic migration mechanism are added to the migration rate of habitats to improve the convergence speed and solution quality of the algorithm, and to achieve high efficiency and high precision in fine-grained scheduling tasks for edge computing.

[0010] To solve the above technical problems, the technical solutions adopted by the present invention are as follows: A fine-grained scheduling method for edge computing based on the IBBO algorithm includes the following steps: S1: Real-time obtain the tasks to be processed of each terminal device, decompose the tasks to be processed that are greater than a preset threshold in a specified manner to obtain multiple subtasks, and uniformly label them and the tasks to be processed that are not decomposed as subtasks to be processed; S2: Assign corresponding priorities to the subtasks to be processed according to the importance and urgency of the tasks; S3: Based on the subtasks to be processed and their corresponding priorities, construct a multi-objective optimization model for task scheduling, set a fitness function for the multi-objective optimization model, and the optimal solution of the fitness function is the comprehensive optimal solution based on the optimal delay and energy consumption of task scheduling; S4: Solve the comprehensive optimal solution of the fitness function of the multi-objective optimization model based on the IBBO algorithm; S5: Schedule the subtasks to be processed based on the obtained comprehensive optimal solution.

[0011] Preferably, in step S1, the specific process of decomposing the to-be-processed tasks greater than the preset threshold into multiple subtasks according to a specified method is as follows: S11: Set a task data sharding key, and call a preset hash algorithm to calculate the hash value of the task data sharding key; S12: Determine the sharding area where the task data is placed based on the calculated hash value, and decompose the to-be-processed tasks.

[0012] Preferably, the specific process of assigning corresponding priorities to the to-be-processed subtasks according to the importance and urgency of the tasks in step S2 is as follows: S21: Add marks for the urgency and importance levels to each task, and both the urgency and importance levels are set to a specified number of levels; S22: First, create an initial task processing queue according to the urgency level. Among tasks with the same urgency level, adjust the initial task processing queue according to the importance level of the tasks to obtain an adjusted task processing queue; S23: Add marks for the urgency and importance levels to the newly generated to-be-processed tasks, and dynamically adjust the adjusted task processing queue based on step S22.

[0013] Preferably, the specific formula for setting the fitness function for the multi-objective optimization model in step S3 is as follows: ; ; ; Wherein, represents the minimum value of the comprehensive objective; y 1 represents the energy consumption of fine-grained task scheduling; y 2 represents the latency of fine-grained task scheduling; and respectively represent the adjustment factors of task scheduling energy consumption and task scheduling latency; and respectively represent the task i energy consumption and latency during local processing; p i represents the scheduling decision factor. When p i = 0, it means that the task i is processed locally. When p i = 1, the task i performs scheduling processing; q ij represents the edge server allocation factor. Whenq ij When = 0, the task i is not assigned to the edge server j for scheduling. When q ij = 1, the task i is assigned to the edge server j for scheduling. and respectively represent the energy consumption and latency of the task i processed on the edge node; m represents the number of edge servers.

[0014] Preferably, the specific process of solving the comprehensive optimal solution of the fitness function of the multi-objective optimization model based on the IBBO algorithm in step S4 is as follows: S41: Set the initial parameters of the IBBO algorithm based on the initial latency and energy consumption of the edge server nodes, create the initial population size NP and the random population individuals H. Each of the population individuals represents a potential task scheduling scheme, and an initial solution space is built by assigning different edge server nodes to each individual; S42: Evaluate the fitness of each individual through the fitness function based on the calculated latency and energy consumption metrics, obtain the performance of each individual in the current task scheduling environment, and determine the quality of each individual; S43: Search for new individuals by adjusting the perturbation degree of the differential vector based on the adaptive dynamic migration mechanism; S44: Obtain the individual mutation rate of each solution m i and the habitat probability P i , and select the individuals suitable for mutation according to the fitness and migration probability of the individuals; S45: Iteratively execute to continuously optimize the individual fitness until the preset number of iterations or the preset termination condition is met, realize population optimization, converge to the comprehensive optimal solution, and obtain the optimal habitat individual H, which is the optimal edge computing fine-grained task scheduling scheme.

[0015] Preferably, step S43 further includes adjusting the migration probability between individuals according to the calculation results. By normalizing the HSI values of the individuals and combining the maximum and minimum HSI values in the current population, the quality of the individuals in the population is monitored in real time, the migration rate is accurately adjusted, and the excellent individuals are retained.

[0016] Preferably, the specific process of step S43 for searching for new individuals by adjusting the perturbation degree of the differential vector based on the adaptive dynamic migration mechanism is as follows: S431: Calculate each habitat xi The immigration rate H in the population λ i and the emigration rate μ i , and adjust the migration probability between individuals according to the calculation results. The specific calculation formula is as follows: ; Wherein, F i is the HSI of the habitat x i , F max and F min are respectively the maximum and minimum values of HSI in the current population; S432: Calculate the migration probability of each individual based on the immigration rate λ i and the emigration rate μ i . The specific calculation formula is as follows: ; Wherein, x kj is the habitat to be migrated, a and b are random values between [1, NP ; x aj and x bj respectively represent the a th and b th dimensional variables of the j th habitat; r max and r min are respectively the maximum and minimum interference degrees.

[0017] The beneficial effects of the present invention include: The edge computing fine-grained scheduling method based on the IBBO algorithm provided by the present invention can obtain the to-be-processed tasks of each terminal device in real time, decompose the to-be-processed tasks greater than a preset threshold into to-be-processed subtasks in a specified manner; assign corresponding priorities to the to-be-processed subtasks according to the importance and urgency of the tasks; construct a multi-objective optimization model for task scheduling based on the to-be-processed subtasks and their corresponding priorities, set a fitness function for the multi-objective optimization model, and the optimal solution of the fitness function is the comprehensive optimal solution based on the optimal delay and energy consumption of task scheduling; solve the comprehensive optimal solution of the fitness function of the multi-objective optimization model based on the IBBO algorithm; and schedule the to-be-processed subtasks based on the obtained comprehensive optimal solution.

[0018] First, an adaptive migration mechanism and an improved migration strategy are added to the existing biogeography-based optimization algorithm, effectively solving the task scheduling optimization problem in the edge computing environment. The migration probability between individuals is dynamically adjusted according to the fitness and distribution of the population, accelerating the optimization process and improving the search efficiency.

[0019] Secondly, through the improved migration strategy, new individuals are searched by dynamically adjusting the perturbation degree of the differential vector to enhance the global search ability of the algorithm and avoid falling into local optimal solutions. A new optimization scheme is given for the fine-grained task scheduling problem in the edge computing environment, effectively improving the efficiency and performance of task scheduling, reducing latency and energy consumption, improving the optimization effect, and realizing the comprehensive optimization of task scheduling in the edge computing environment. Brief Description of the Drawings

[0020] Figure 1 It is a schematic diagram of the architecture of the edge computing task scheduling model of the present invention.

[0021] Figure 2 It is a schematic diagram of the process of the edge computing fine-grained scheduling method based on the IBBO algorithm of the present invention. Detailed Embodiments

[0022] The following further describes the present invention in detail with reference to the attached Figures 1 - 2 drawings: Embodiment 1 Referring to the attached Figure 1 and Figure 2 as shown, a fine-grained edge computing scheduling method based on the IBBO algorithm includes the following steps: S1: Real-time obtain the tasks to be processed of each terminal device, decompose the tasks to be processed greater than a preset threshold in a specified manner to obtain multiple subtasks, and uniformly label them and the tasks to be processed that are not decomposed as subtasks to be processed. Decomposing large-scale tasks into smaller subtasks, each subtask has a relatively short execution time. On the one hand, tasks can be assigned to different computing nodes for parallel execution, thereby improving the concurrency and overall execution efficiency of tasks. On the other hand, it reduces the performance requirements of the server for large-scale task data. Before task decomposition, this large-scale data can only be processed through the central cloud server. After decomposing the large-scale data, multiple subtasks are obtained, enabling edge server nodes to also process the subtasks. Therefore, while reducing the server processing performance, the processing efficiency is improved through the simultaneous processing of multiple servers.

[0023] S2: Assign corresponding priorities to the subtasks to be processed according to the importance and urgency of the tasks. Different tasks are given different priorities according to their importance and urgency. In the case of limited resources or high system load, prioritize the processing of important or urgent tasks to ensure the stability and performance of the system. Fine-grained scheduling requires real-time monitoring of the system status and resource utilization, and dynamically adjusting the task allocation and scheduling strategy according to the current load situation. Through dynamic scheduling, flexible task scheduling can be performed according to real-time requirements and resource changes, maximizing the resource utilization rate and performance of the system. Fine-grained scheduling also includes the dynamic allocation and management of computing resources. Dynamically allocate computing, storage, and network resources according to the task requirements and system load to maximize resource utilization and meet the requirements of task execution.

[0024] S3: Based on the subtasks to be processed and their corresponding priorities, construct a multi-objective optimization model for task scheduling, and set a fitness function for the multi-objective optimization model. The optimal solution of the fitness function is the comprehensive optimal solution based on the optimal delay and energy consumption of task scheduling. S4: Solve the comprehensive optimal solution of the fitness function of the multi-objective optimization model based on the IBBO algorithm. S5: Schedule the subtasks to be processed based on the obtained comprehensive optimal solution.

[0025] The edge computing task scheduling model of the present invention includes a local server and a central cloud server. A communication connection is established between the local server and the central cloud server through a network. The local server and the central cloud server are communicatively connected to a base station and an edge cloud through the network.

[0026] During the fine-grained task scheduling process, it is necessary to consider the dependencies between tasks to ensure that the tasks are executed in the correct order and to guarantee the integrity and consistency of the entire task flow. The scheduling algorithm needs to consider the dependencies between tasks and reasonably arrange the execution order of tasks to avoid deadlocks or incorrect task execution orders.

[0027] When the traditional Biogeography-Based Optimization algorithm BBO determines the immigration and emigration rates only based on the quality order of individuals, it ignores the overall evolutionary state of the current population. Such a processing method may lead to an unreasonable evaluation of individual quality. Especially when there is a large gap or uneven distribution between individuals, it is easy to make a wrong evaluation of the quality of individuals, resulting in the beneficial information of better individuals not being fully retained, or poorer individuals participating in the evolutionary process prematurely.

[0028] The present invention improves the existing Biogeography-Based Optimization Algorithm (BBO). Based on the importance of the migration rate and population migration mechanism in the BBO algorithm for the overall search speed and optimization ability, the present invention improves the iterative strategy and parameter settings of the algorithm, and makes corresponding improvements to the decision-making mechanism of the migration rate and the migration strategy of the population.

[0029] Embodiment 2 Based on Embodiment 1, in step S1, the specific process of decomposing the to-be-processed tasks greater than a preset threshold in a specified manner to obtain multiple subtasks is as follows: S11: Set the task data sharding key, and call a preset hash algorithm to calculate the hash value of the task data sharding key; S12: Based on the calculated hash value, determine the sharding area where the task data is placed to decompose the to-be-processed tasks.

[0030] During the process of decomposing the task data, all the task data in the database uses a unified hash algorithm, so that the hash function can evenly distribute the data and reduce the hotspot risk caused by data imbalance.

[0031] In another implementation manner of this embodiment, the large-scale data is divided according to the range of the task data value or key space. Adjacent sharding keys are more likely to fall on the same shard. In this process, a suitable sharding key needs to be selected, and the sharding key does not contain duplicate values, so that the candidate values are as discrete as possible.

[0032] The specific process of assigning corresponding priorities to the to-be-processed subtasks according to the importance and urgency of the tasks in step S2 is as follows: S21: Add marks for the urgency and importance to each task. Both the urgency and importance are set to a specified number of levels; S22: First, create an initial task processing queue according to the level of urgency. Among the tasks with the same level of urgency, adjust the initial task processing queue according to the importance level of the tasks to obtain an adjusted task processing queue; S23: Add marks for the urgency and importance to the newly generated to-be-processed tasks, and dynamically adjust the adjusted task processing queue based on step S22.

[0033] Embodiment 3 Based on Embodiment 1 or Embodiment 2, the specific formula for setting the fitness function for the multi-objective optimization model in step S3 is as follows: ; ; ; Wherein, Represents the minimum value of the comprehensive objective; y 1 Represents the energy consumption of fine-grained task scheduling; y 2 Represents the latency of fine-grained task scheduling; and respectively represent the adjustment factors of task scheduling energy consumption and task scheduling latency; and respectively represent the task i energy consumption and latency during local processing; p i Represents the scheduling decision factor. When p i = 0, it means the task i is processed locally. When p i = 1, the task i performs scheduling processing; q ij Represents the edge server allocation factor. When q ij = 0, the task i is not allocated to the edge server j for scheduling. When q ij = 1, the task i is allocated to the edge server j for scheduling, 、 respectively represent the energy consumption and latency of the task i processed on the edge node; m Represents the number of edge servers.

[0034] The fitness function plays a crucial role in fine-grained task scheduling. The fitness function comprehensively considers the energy consumption and latency of task scheduling in order to find the optimal task scheduling scheme. Task scheduling not only needs to consider the efficiency of resource utilization but also the latency of task execution, and these two are often mutually restrictive. Therefore, based on the above fitness function, the present invention models the task scheduling problem as a multi-objective optimization problem to better balance the trade-off relationship between energy consumption and latency.

[0035] The specific process of solving the comprehensive optimal solution of the fitness function of the multi-objective optimization model based on the IBBO algorithm (Improved Biogeography-Based Optimization Algorithm) in step S4 is as follows: S41: Set the initial parameters of the IBBO algorithm based on the initial latency and energy consumption of the edge server node, create the initial population size NP and the random population individuals H, H{ x i , i=1,2,…,NP}, each individual in the population represents a potential task scheduling solution. By assigning different edge server nodes to each individual, an initial solution space is built, which provides a starting point for subsequent optimization. The initial parameters of the IBBO algorithm are set, including the relevant characteristics of the edge server nodes, such as initial latency and energy consumption. By accurately setting the initial parameters, the foundation for the subsequent optimization process is laid and the algorithm can be effectively run.

[0036] S42: Based on the calculation delay and energy consumption indicators, the fitness of each individual is evaluated through the fitness function, the performance of each individual in the current task scheduling environment is obtained, and the quality of each individual is determined. The fitness of each individual is evaluated, that is, the performance in the current task scheduling environment. The quality of each individual is determined by calculating indicators such as delay and energy consumption, which provides a reference standard for the subsequent optimization process.

[0037] S43: Based on the adaptive dynamic migration mechanism, the disturbance degree of the differential vector is adjusted to search for new individuals.

[0038] The migration strategy of traditional BBO, as an important part of its evolution mechanism, directly affects the search ability of the algorithm. However, its migration mode of directly replacing the SIV of the original solution with the SIV to be migrated may lead to a certain blindness in the migration, poor ability to mine new solutions, and easy to cause premature convergence. To this end, the present invention sets an improved dynamic migration mechanism, which uses the designed adaptive migration rate to adjust the disturbance degree of the differential vector to search for new individuals, thereby realizing adaptive disturbance around the SIV to be migrated in different evolution cycles, and enhancing the search ability of the migration algorithm.

[0039] The migration strategy of BBO is a crucial part of its evolution mechanism, which directly affects the search ability of the algorithm. However, in the traditional migration strategy, directly using the SIV (Solution Improvement Vector) to be migrated to replace the SIV of the original solution may be blind, resulting in poor ability to mine new solutions, and even prone to premature convergence problems. Therefore, the present invention proposes to use an improved dynamic migration mechanism through the design, and use adaptive mobility to adjust the disturbance degree of the differential vector, so as to search for new individuals more flexibly. In different evolution cycles, the search process around the SIV to be migrated can be adaptively disturbed appropriately. This improvement process can enhance the search ability of the migration algorithm and improve the efficiency of the algorithm in exploring the solution space.

[0040] S44: Get the individual mutation rate of each solution m i and habitat probability P i, select individuals suitable for mutation according to the fitness and migration probability of individuals to explore new possibilities in the solution space; S45: Iteratively execute to continuously optimize the individual fitness until the preset number of iterations or the preset termination condition is met, realize population optimization, converge to the comprehensive optimal solution, and obtain the optimal habitat individual H, which is the optimal edge computing fine-grained task scheduling scheme.

[0041] In the traditional BBO algorithm, determining the immigration and emigration rates is only based on the quality order of individuals, thus ignoring the overall evolutionary state of the current population. Determining the immigration and emigration rates based on the quality order of individuals may lead to an unreasonable evaluation of individual quality. Especially when there is a large gap or uneven distribution between individuals, it is easy to make a wrong evaluation of the quality of individuals, resulting in the beneficial information of better individuals not being fully retained, or worse individuals participating in the evolutionary process prematurely. To solve this problem, the present invention improves the traditional BBO algorithm by adaptively adjusting the migration rate based on the HSI value of the normalized individual.

[0042] Step S43 further includes adjusting the migration probability between individuals according to the calculation result. By normalizing the HSI value of the individual and combining the maximum and minimum HSI values in the current population, the quality of individuals in the population is monitored in real time, and the migration rate is accurately adjusted to retain the excellent individuals among them.

[0043] The specific process of step S43 for searching for new individuals by adjusting the perturbation degree of the differential vector based on the adaptive dynamic migration mechanism is as follows: S431: Calculate each habitat x i In the population H the immigration rate λ i and the emigration rate μ i , and adjust the migration probability between individuals according to the calculation result. The specific calculation formula is as follows: ; Among them, F i is the HSI of habitat x i , F max and F min are respectively the maximum and minimum values of HSI in the current population; S432: Based on the immigration rate λ i and the emigration rate μ iCalculate the migration probability of each individual, and the specific calculation formula is as follows: ; where, x kj is the habitat to be migrated, a and b are random values between [1, NP ; x aj and x bj respectively represent the a -th and b -th dimensional variables of the j -th habitat; r max and r min are the maximum and minimum interference degrees respectively.

[0044] To sum up, the fine-grained scheduling method for edge computing based on the IBBO algorithm provided by the present invention can obtain the tasks to be processed of each terminal device in real time, decompose the tasks to be processed that are greater than the preset threshold according to the specified method to obtain the sub-tasks to be processed; assign corresponding priorities to the sub-tasks to be processed according to the importance and urgency of the tasks; construct a multi-objective optimization model for task scheduling based on the sub-tasks to be processed and their corresponding priorities, set a fitness function for the multi-objective optimization model, and the optimal solution of the fitness function is the comprehensive optimal solution based on the optimal delay and energy consumption of task scheduling; solve the comprehensive optimal solution of the fitness function of the multi-objective optimization model based on the IBBO algorithm; schedule the sub-tasks to be processed based on the obtained comprehensive optimal solution.

[0045] By adding an adaptive migration mechanism and an improved migration strategy on the basis of the existing biogeography-based optimization algorithm, the task scheduling optimization problem in the edge computing environment is effectively solved. The migration probability between individuals is dynamically adjusted according to the fitness and distribution of the population, accelerating the optimization process and improving the search efficiency. Through the improved migration strategy, new individuals are searched by dynamically adjusting the perturbation degree of the differential vector to enhance the global search ability of the algorithm and avoid falling into local optimal solutions. A new optimization scheme is given for the fine-grained task scheduling problem in the edge computing environment, effectively improving the efficiency and performance of task scheduling, reducing delay and energy consumption, improving the optimization effect, and realizing the comprehensive optimization of task scheduling in the edge computing environment.

Claims

1. A fine-grained scheduling method for edge computing based on the IBBO algorithm, characterized in that: The following steps are involved: S1: Obtain the pending tasks of each terminal device in real time, decompose the pending tasks that are greater than a preset threshold in a specified manner to obtain multiple subtasks, and mark them and the undecomposed pending tasks as pending subtasks; S2: Assign corresponding priorities to the subtasks to be processed according to their importance and urgency; S3: Based on the subtasks to be processed and their corresponding priorities, a multi-objective optimization model for task scheduling is constructed, and a fitness function is set for the multi-objective optimization model, wherein the optimal solution of the fitness function is a comprehensive optimal solution based on optimal delay and energy consumption of task scheduling; S4: Solve the comprehensive optimal solution of the fitness function of the multi-objective optimization model based on the IBBO algorithm; S5: Schedule the subtasks to be processed based on the obtained comprehensive optimal solution.

2. The edge computing fine-grained scheduling method based on the IBBO algorithm according to claim 1 is characterized in that: In step S1, the specific process of decomposing the pending tasks that are greater than the preset threshold in a specified manner to obtain multiple subtasks is as follows: S11: Setting a task data sharding key, and calling a preset hash algorithm to calculate a hash value of the task data sharding key; S12: Determine the sharding area where the task data is placed based on the calculated hash value and decompose the task to be processed.

3. According to claim 1, a fine-grained scheduling method for edge computing based on the IBBO algorithm is characterized in that: The specific process of assigning corresponding priorities to the subtasks to be processed according to the importance and urgency of the tasks in step S2 is as follows: S21: Add urgency and importance marks to each task, and set the urgency and importance to specified levels; S22: first, an initial task processing queue is created according to the level of urgency, and among tasks of the same level of urgency, the initial task processing queue is adjusted according to the importance of the tasks to obtain an adjusted task processing queue; S23: Add urgency and importance tags to the newly generated tasks to be processed, and dynamically adjust the adjusted task processing queue based on step S22.

4. According to claim 1, a fine-grained scheduling method for edge computing based on the IBBO algorithm is characterized in that: The specific formula for setting the fitness function for the multi-objective optimization model in step S3 is as follows: ； ； ； in, Represents the minimum value of the comprehensive target; y 1 represents the energy consumption of fine-grained task scheduling; y 2 represents the fine-grained task scheduling latency; and They represent the adjustment factors of task scheduling energy consumption and task scheduling delay respectively; and Represents tasks i Energy consumption and latency when processing locally; p i represents the scheduling decision factor, when p i =0, indicating the task i When processed locally, p i =1, the task i Execute scheduling processing; q ij represents the edge server allocation factor, when q ij =0, the task i Not assigned to an edge server j To schedule, q ij =1, the task i Assigned to edge servers j To schedule, , Represents tasks i Energy consumption and latency of processing at edge nodes; m Indicates the number of edge servers.

5. According to claim 4, a fine-grained scheduling method for edge computing based on the IBBO algorithm is characterized in that: The specific process of solving the comprehensive optimal solution of the fitness function of the multi-objective optimization model based on the IBBO algorithm in step S4 is as follows: S41: setting initial parameters of the IBBO algorithm based on the initial delay and energy consumption of the edge server node, creating an initial population size NP and a random population individual H, each of which represents a potential task scheduling solution, and building an initial solution space for each individual by allocating different edge server nodes; S42: Evaluate the fitness of each individual through the fitness function based on the calculation delay and energy consumption indicators, obtain the performance of each individual in the current task scheduling environment, and determine the quality of each individual; S43: Searching for new individuals by adjusting the disturbance degree of the differential vector based on an adaptive dynamic migration mechanism; S44: Get the individual mutation rate of each solution m i and habitat probability P i , according to the individual's fitness and migration probability, select individuals suitable for mutation; S45: Iterative execution continuously optimizes individual fitness until the preset number of iterations or the preset termination condition is met, achieving population optimization, converging to the comprehensive optimal solution, and obtaining the optimal habitat individual H, which is the optimal edge computing fine-grained task scheduling solution.

6. According to claim 5, a fine-grained scheduling method for edge computing based on the IBBO algorithm is characterized in that: Step S43 also adjusts the migration probability between individuals according to the calculation results, normalizes the HSI value of the individual, and combines the maximum and minimum HSI values ​​in the current population to monitor the quality of individuals in the population in real time, accurately adjust the migration rate, and retain the excellent individuals.

7. According to claim 5, a fine-grained scheduling method for edge computing based on the IBBO algorithm is characterized in that: The specific process of step S43 adjusting the disturbance degree of the differential vector based on the adaptive dynamic migration mechanism to search for new ones is as follows: S431: Calculate each habitat x i In the population H The immigration rate λ i and emigration rate μ i , and adjust the migration probability between individuals according to the calculation results. The specific calculation formula is as follows: ； in, F i It is a habitat x i HSI, F max and F min are the maximum and minimum values ​​of HSI in the current population, respectively; S432: Based on immigration rate λ i and emigration rate μ i Calculate the migration probability of each individual. The specific calculation formula is as follows: ； in, x kj It is a habitat to be migrated. a and b is between [1, NP ]’s random value; x aj and x bj Respectively represent a and b Habitat j Dimensional variables; r max and r min are the maximum and minimum interference respectively.

Images