A smart construction site edge unloading method assisted by an aerial intelligent reflective surface

Abstract

The present invention discloses a method for smart construction site edge unloading assisted by an aerial intelligent reflective surface. The method comprises the following steps: first, obtaining basic information of an aerial intelligent reflective surface-assisted mobile edge computing system in a smart construction site scenario, establishing an uplink transmission communication network model, a security model, and a computing model based on the basic information of the aerial intelligent reflective surface-assisted mobile edge computing system, and constructing a minimum energy consumption optimization problem; then, obtaining an initial solution based on the minimum energy consumption optimization problem, defining a whale population and initial whale individuals, and using an improved whale particle genetic algorithm to search the entire whale population, outputting the position of the global optimal whale individual as the optimization result; finally, performing a minimum energy consumption optimization configuration based on the position of the global optimal whale individual. The method of the present invention can achieve multi-base station optimized unloading of pending task data of construction site equipment, minimizing the uplink transmission energy consumption, delay, and transmission power of the construction site equipment to the base station.

Description

Technical Field

[0001] The present invention relates to the fields of wireless communications and edge computing technology, and specifically to a smart construction site edge unloading method assisted by an aerial intelligent reflective surface. Background Art

[0002] Smart construction sites are the application of the Internet of Things (IoT) in the industrial sector. By connecting equipment, systems, and personnel, they enable data collection, transmission, and analysis to improve production efficiency, reduce costs, and enhance product quality. As flexible mobile platforms, drones offer rapid deployment, wide coverage, and high flexibility, and are widely used in industrial monitoring, logistics, transportation, and environmental monitoring.

[0003] Intelligent Reflective Surfaces (IRS) are an emerging technology that intelligently controls the propagation path of radio waves by adjusting the phase and amplitude of reflected signals, thereby improving the signal quality and coverage of communication systems. IRSs have great potential in assisting drone communications, significantly reducing energy consumption and improving communication efficiency by optimizing signal transmission paths.

[0004] Mobile edge computing (MEC) moves computing power from the cloud to the edge of the network, enabling data processing close to users and reducing data transmission latency and bandwidth consumption. Mobile edge computing is particularly important in smart construction sites because it can process large amounts of sensor data and control commands in real time, meeting the low latency and high reliability requirements of industrial applications.

[0005] Against this backdrop, the UAV-IRS-assisted Mobile Edge Computing (MEC) system combines these technologies. By leveraging the flexible deployment of drones, the intelligent reflection of intelligent reflective surfaces, and the edge computing capabilities of mobile edge computing, it aims to optimize energy consumption in smart construction sites. This not only helps reduce overall system energy consumption but also improves communication efficiency and computing performance in industrial applications, thereby promoting the intelligent and sustainable development of industrial production.

[0006] In smart construction sites, existing technologies often achieve real-time data processing and analysis by deploying computing resources at edge nodes close to data sources. This involves configuring edge devices, offloading tasks, and caching data. However, these technologies suffer from limited device capabilities, insufficient network coverage, and a relatively fixed task flow from construction site equipment to the base station, making it susceptible to interference from external factors. For example, patent application CN118042494A provides a secure computational efficiency optimization method for ultra-dense multi-access mobile edge computing networks. This method, an immune algorithm-based edge computing offloading and resource management solution, is primarily applied to non-orthogonal multiple access (NOMA)-mobile edge computing (MEC) systems in ultra-dense heterogeneous networks. Its core objective is to minimize system energy consumption while meeting user latency constraints by jointly optimizing computational task offloading, user association, and wireless resource management. This method leverages NOMA technology to improve spectrum utilization. However, the main drawback of this method is its high computational complexity. Although genetic algorithms can effectively search the solution space, the optimization process relies on significant computational resources and time, which can lead to a decrease in system response speed, especially as user density increases. Summary of the Invention

[0007] In response to the shortcomings of the existing technology, the present invention provides a smart construction site edge unloading method assisted by an aerial intelligent reflective surface. The purpose is to solve the problem of energy consumption optimization during the smart construction site edge unloading process. Specifically, the aerial intelligent reflective surface is used to assist the mobile edge computing system, and the improved whale particle genetic algorithm is used to optimize the uplink transmission rate, delay and security cost of data transmission, thereby minimizing the total energy consumption of the system.

[0008] To achieve the above objectives, the present invention provides the following technical solutions.

[0009] A smart construction site edge unloading method assisted by an aerial intelligent reflective surface comprises the following steps:

[0010] Step S1: Establish an aerial intelligent reflective surface-assisted mobile edge computing system in a smart construction site scenario, wherein the aerial intelligent reflective surface-assisted mobile edge computing system includes several drone-assisted intelligent reflective surfaces, several construction site equipment, several micro base stations, and one macro base station; obtain basic information of the aerial intelligent reflective surface-assisted mobile edge computing system in the smart construction site scenario, establish an uplink transmission communication network model, a security model, and a computing model based on the basic information of the aerial intelligent reflective surface-assisted mobile edge computing system, and construct an energy consumption minimization optimization problem based on the uplink transmission communication network model, the security model, and the computing model under the constraints of the aerial intelligent reflective surface-assisted mobile edge computing system;

[0011] The energy consumption minimization optimization problem includes the joint optimization of the following five sub-problems: the selection decision of the construction site equipment for the drone-assisted smart reflective surface, the selection decision of the base station associated with the construction site equipment, the optimization of the reflection coefficient matrix angle of the drone-assisted smart reflective surface, the selection decision of the secure cryptographic algorithm, and the selection decision of the sub-channel for the construction site equipment to transmit to the base station and the drone-assisted smart reflective surface;

[0012] Step S2: Obtain an initial solution based on the energy consumption minimization optimization problem, define the solution space containing all feasible solutions to the energy consumption minimization optimization problem as a whale population, and use the initial solution as the initial whale individual in the whale population. Use the improved whale particle genetic algorithm to search the entire whale population, obtain the best whale individual in the whale population through the search process, and finally output the position of the global best whale individual as the optimization result. The specific process is as follows:

[0013] Step S21, initialize the population of whale individuals and determine the best whale individual in history;

[0014] Step S22, based on the whale's predation behavior and the adaptive single-point crossover mutation operation, the position of the individual whale is dynamically optimized, so that the individual whale moves according to the predefined direction and distance. Specifically, the whale moves closer to the optimal solution when encircling the prey and moves away from the current optimal solution when searching for prey globally. The moving distance gradually shortens as the whale approaches the optimal solution, so as to better explore the solution space. The dynamic optimization of the position of the individual whale based on the whale's predation behavior and the adaptive single-point crossover mutation operation mainly includes the following process: first, a random number is generated. , according to the random number The range interval in which the whale is located performs one of the following operations: whale encirclement operation, spiral bubble net attack and prey search operation, adaptive single point crossover mutation operation, and whale individual movement parameter adjustment operation;

[0015] Among them, the whale encirclement operation simulates the behavior of whales surrounding their prey during the hunting process, and updates the position of each individual whale in the population in real time;

[0016] The Spiral Bubble Net Attack and Prey Search operations include the Spiral Bubble Net Attack operation and the Prey Search operation. The Spiral Bubble Net Attack operation simulates the mechanism of whales creating bubble nets to capture prey, further optimizing the position of individual whales. The Prey Search operation searches for prey in the solution space and continuously updates the position of individual whales to find the global optimal solution. This stage aims to improve the global search ability of individual whales and avoid falling into local optimality.

[0017] In addition, the improved whale particle genetic algorithm also introduces an adaptive single-point crossover and mutation operation, which includes a crossover operation and a mutation operation to enhance the algorithm's local search capability. The crossover operation specifically involves randomly selecting the chromosomes of two whale individuals and then exchanging part of the genetic information of the two selected whale individuals according to a single-point crossover, thereby combining the excellent characteristics of different whale individuals to generate a new whale individual, thereby generating a better solution in the local area and avoiding falling into the local optimum. The mutation operation specifically involves randomly changing one or more gene sites in the chromosomes of the whale individuals to introduce new individual diversity, making the whale individuals more comprehensive in local search.

[0018] The whale individual movement parameter adjustment operation controls the movement and adjustment speed of the whale individual by adjusting the inertia weight, self-learning factor, and social learning factor, balancing the needs of global exploration and local optimization, thereby jumping out of the local optimal solution, exploring a wider search space, and finding a better global optimal solution, thereby finding the current global best whale individual position;

[0019] Step S23: The position of the global best whale individual is updated. The fitness value of all whale individuals in the target whale population is calculated using the fitness function. If the fitness value of any whale individual in the target whale population is higher than the fitness value of the historical global best whale individual, the whale individual with the higher fitness value is replaced with the global best whale individual to obtain the position of the current global best whale individual.

[0020] Step S24, repeating steps S22 and S23 in sequence until the maximum number of iterations is reached; finally, outputting the global best whale individual in the target whale population, and obtaining the position of the global best whale individual in the target whale population;

[0021] Step S3: Execute the energy-minimizing optimization configuration based on the position of the global best whale individual.

[0022] Furthermore, in step S1, obtaining basic information of the aerial intelligent reflective surface assisted mobile edge computing system in the smart construction site scenario specifically includes the following steps: First, obtaining The index set of construction site equipment is ,in, represents any construction site equipment in the aerial intelligent reflective surface assisted mobile edge computing system, represents the number of construction site equipment in the aerial intelligent reflective surface-assisted mobile edge computing system; The index set of micro base stations is , the index set of the macro base station is , the index set of all base stations is expressed as ,in, represents any micro base station in the aerial intelligent reflective surface assisted mobile edge computing system, It represents the number of micro base stations in the aerial intelligent reflective surface assisted mobile edge computing system, s represents any base station in the aerial intelligent reflective surface assisted mobile edge computing system, and S represents the total number of base stations in the aerial intelligent reflective surface assisted mobile edge computing system; The index set of drone-assisted smart reflective surfaces is ,in, represents any drone-assisted smart reflective surface, Indicates the number of drone-assisted smart reflective surfaces; a drone-assisted smart reflective surface contains A reflective element, The index set of reflective elements is ,in, represents any reflective element in the drone-assisted smart reflective surface, Indicates the number of reflective elements in a drone-assisted smart reflective surface; drone-assisted smart reflective surface The reflection coefficient matrix of the reflective element is recorded as ,in, Reflective element The reflection coefficient on the drone-assisted smart reflective surface m; then, the physical locations of all micro base stations are obtained, and the physical locations of all micro base stations are used The clustering algorithm divides all micro base stations into clusters; one cluster contains micro base stations and Any site equipment and drone-assisted smart reflective surfaces, with The subchannels are used by the micro base stations, construction site equipment, and drone-assisted smart reflective surfaces in the cluster. The construction site equipment uses the same subchannel when transmitting to the base station and the drone-assisted smart reflective surface. The index set of sub-channels is recorded as , where n represents any subchannel within the cluster; obtain the total bandwidth of the aerial intelligent reflective surface assisted mobile edge computing system and subchannel bandwidth , the task is to pass the construction site equipment Channel Transmitted to drone-assisted smart reflective surfaces The channel gain is recorded as , the mission is achieved through drone-assisted smart reflective surfaces Channel Transmission to micro base station The channel gain is recorded as , the task is to pass the micro base station Send back to construction site equipment The channel gain is recorded as , the Gaussian white noise power is recorded as .

[0023] Furthermore, in step S1, the specific process of establishing the uplink transmission communication network model based on the basic information of the aerial intelligent reflective surface assisted mobile edge computing system is as follows:

[0024] Construct uplink transmission communication network model: First, divide the total bandwidth of the aerial intelligent reflective surface assisted mobile edge computing system into For micro base stations, divided into For use by macro base stations, where is the frequency band division factor, and , the number of sub-channels used by each cluster is , Represents the rounding function;

[0025] When the construction site equipment is associated with the micro base station, the construction site equipment is connected to the micro base station by using the non-orthogonal multiple access technology NOMA. The part of the task to be offloaded is sent to the micro base station; then, the uplink transmission rate is calculated according to the Shannon formula, that is: according to the formula , calculated in the subchannel Construction site equipment Send the task to the micro base station Uplink NOMA transmission rate ;in, Indicates the bandwidth used by micro base stations, Indicates construction site equipment Smart reflective surfaces assisted by connected drones The decision index coefficient of at the same time , representing any construction site equipment Must select any drone-assisted smart reflective surface Make an association, Indicates construction site equipment Its own transmission power; It means that in the process of uplink NOMA transmission, except for the construction site equipment, and drone-assisted smart reflective surfaces Any other construction site equipment ( ) and any other drone-assisted smart reflective surfaces For construction site equipment and drone-assisted smart reflective surfaces The sum of the interferences generated; Indicates any other construction site equipment Connect to any other drone-assisted smart reflective surface Decision-making index; Indicates any other construction site equipment The transmission power; Indicates other construction site equipment during uplink NOMA transmission Send missions to other drone-assisted smart reflective surfaces The resulting channel gain interference, Represents any other drone-assisted smart reflective surface An indexed set of reflection coefficients of the reflective elements in ; Indicates that the mission is assisted by any other drone's smart reflective surface Channel Channel gain for transmission to micro base stations.

[0026] When the construction site equipment is associated with the macro base station, according to the formula , calculated in the subchannel Construction site equipment Uplink NOMA transmission rate for sending tasks to the macro base station ;in, Indicates the bandwidth used by the macro base station; The mission is to use drone-assisted smart reflective surfaces Through the sub-channel Channel gain for transmission to the macro base station; Indicates the distance from the macro base station to the construction site equipment channel gain.

[0027] Furthermore, in step S1, the specific process of establishing the security model is as follows: First, define the index set of the cryptographic algorithm as , where v represents any cryptographic algorithm and V represents the number of cryptographic algorithms. The task of selecting a cryptographic algorithm to protect transmission When the expected security level is not achieved, the probability of encryption failure of the cryptographic algorithm is expressed as Otherwise, it is expressed as ;in, Indicates construction site equipment The task of protecting transmission The safety risk factor, Indicates the desired protection level of the task, Indicates the cryptographic algorithm The protection level of Calculating construction site equipment Security costs ,in, Indicates a transfer task loss of funds in case of failure; For construction site equipment With base station The correlation decision index between construction site equipment Associate to base station hour, , construction site equipment Not associated with a base station hour, ; Construction site equipment Choose any drone-assisted smart reflective surface When making an association, ,otherwise .

[0028] Furthermore, a calculation model is constructed based on the uplink transmission communication network model and security model:

[0029] When the construction site equipment is not associated with the base station for calculation, and the task is to calculate on the construction site equipment itself, according to the formula Calculate the time required for the task to be processed by the construction site equipment itself, where the first term on the right side of the equation represents the local processing time of the unloaded task data, and the second term on the right side of the equation represents the encryption time of the task data to be unloaded; Indicates the bit size of the task data calculated locally, Indicates construction site equipment The total task data bit size that needs to be processed, Indicates construction site equipment The bit size of the task data offloaded to the base station; Indicates construction site equipment Computing tasks The number of CPU cycles used by one bit represents the computational complexity or computational resource requirements of the task. Indicates construction site equipment The computing power allocated for local processing of calculations; Indicates construction site equipment The cryptographic algorithm selected when the transmitted task passes through the drone-assisted smart reflective surface and the base station in sequence; Represents a cryptographic algorithm Ability to encrypt transfer tasks.

[0030] When construction site equipment is associated with the micro base station for calculation, the equipment's unloaded tasks are first transmitted to the drone-assisted smart reflective surface, which then transmits the tasks to the micro base station. Finally, the micro base station transmits the tasks to the macro base station for processing. The time required to partially offload the tasks to the micro base station for processing is calculated as follows:

[0031] ;

[0032] Among them, the first term on the right side of the equation Indicates that the construction site equipment The time required for the task data to be offloaded to be uploaded to the micro base station through the selected sub-channel, Indicates construction site equipment Associated micro base stations Select subchannel when performing calculations As the state variable of the task uplink transmission connection node, Indicates construction site equipment Transferring tasks to drone-assisted smart reflective surfaces Select subchannel As the state variable of the connection node, Representing drone-assisted smart reflective surfaces Transfer tasks to micro base stations Select subchannel As the state variable of the connection node, Indicates construction site equipment The bit size of the task data offloaded to the micro base station; the second term on the right side of the equation Indicates construction site equipment The time required for the task data to be offloaded to be processed in the micro base station, Indicates the bit size of the task data processed by the micro base station, Indicates the bit size of the data that is offloaded from the micro base station to the macro base station, Represents the computing power allocated to the micro base station; the third term on the right side of the equation is the time required to offload tasks from the micro base station to the macro base station, Indicates the wired backhaul rate; the fourth term on the right side of the equation Indicates the time required for the macro base station to process the task data offloaded from the micro base station. Represents the computing power allocated to the macro base station; the fifth term on the right side of the equation Indicates encrypted construction site equipment The time for offloading tasks to the micro base station; the sixth term on the right side of the equation The time required to process the task of decrypting the micro base station, Represents a cryptographic algorithm The computing power of the decryption transmission task; the seventh term on the right side of the equation represents the time for the encrypted micro base station to offload the task to the macro base station; the eighth term on the right side of the equation Indicates the time required to process the decryption task of the macro base station.

[0033] When the construction site equipment is directly connected to the macro base station for calculation, the equipment's unloading task is first transmitted to the drone-assisted intelligent reflective surface, and then the drone-assisted intelligent reflective surface transmits the task to the macro base station. According to the formula The time it takes to calculate the task processing time at the macro base station, where the first term on the right side of the equation Indicates that the construction site equipment The time required for the task data to be offloaded to be uploaded to the macro base station through the selected sub-channel, Indicates construction site equipment Select subchannel when directly associated with macro base station for calculation As the state variable of the task uplink transmission connection node, Representing drone-assisted smart reflective surfaces Select subchannel when transferring tasks to the macro base station As the state variable of the connection node, Indicates construction site equipment The bit size of the task data transmitted uplink to the macro base station; the second term on the right side of the equation Indicates construction site equipment The time required for the macro base station to process the task data transmitted uplink to the macro base station. Indicates construction site equipment The bit size of the task data processed by the macro base station in the task data uplinked to the macro base station; the third term on the right side of the equation Indicates encrypted construction site equipment The time for uplink transmission to the macro base station; the fourth term on the right side of the equation Decryption of construction site equipment The time required for the macro base station to process the task data in the uplink transmission to the macro base station.

[0034] construction site equipment There are multiple tasks to be processed on the task, and the index set of the task is recorded as , assuming that tasks are executed in the order of priority of the construction site equipment, local processing and computation offloading can be performed in parallel for any task, which can be expressed by the formula to complete the construction site equipment The total processing time of all computing tasks .in, Indicates construction site equipment Select the time required for the associated base station calculation process. Based on the calculation offloading method of the construction site equipment k, the time required for the corresponding construction site equipment to first associate with the micro base station and then associate with the macro base station through the micro base station for processing, or the time required for the corresponding construction site equipment to directly associate with the macro base station for calculation processing; Indicates construction site equipment Select the time required for local computing processing;

[0035] The calculated total energy consumption for all tasks of all construction site equipment can be expressed by the formula:

[0036] ,

[0037] Among them, the first term on the right side of the equal sign Indicates the energy consumption generated when the task is performed by the equipment itself at the construction site; the second item on the right side of the equal sign Indicates the energy consumption generated by encryption during task encryption transmission; the third item on the right side of the equal sign Indicates the energy consumption generated by uplink transmission of task data to the base station and calculation and processing by the base station. Indicates construction site equipment Associated base station Select subchannel when performing calculations As the state variable of the task uplink transmission connection node, Representing drone-assisted smart reflective surfaces Transfer tasks to the base station Select subchannel As a state variable of the connection node; represents the uplink NOMA transmission rate of the construction site equipment k sending the task to the base station s. When the construction site equipment is associated with the micro base station, ,When the construction site equipment is associated with the macro base station, .

[0038] Furthermore, the energy consumption minimization optimization problem constructed based on the uplink transmission communication network model, computing model, and security model is specifically as follows:

[0039] ;

[0040] Where, The goal of the energy consumption minimization optimization problem is to minimize the total computational energy consumption of all tasks of all construction site equipment in the aerial intelligent reflective surface assisted mobile edge computing system. ; Indicates construction site equipment Whether to decide with base station The index status set of the status indicators of the established connection, ; Indicates construction site equipment The cryptographic algorithm selected when first transmitting the task to the drone-assisted smart reflective surface and then transmitting the task to the base station through the drone-assisted smart reflective surface The index state set, ; Indicates construction site equipment Transferring tasks to drone-assisted smart reflective surfaces and drone-assisted smart reflective surfaces Transfer tasks to the base station Select subchannel As an indexed state set of state variables of connected nodes, If the construction site equipment Transferring tasks to drone-assisted smart reflective surfaces Select subchannel As a connecting node, ,otherwise ; If drone-assisted smart reflective surfaces Transfer tasks to the base station Select subchannel As a connecting node, ,otherwise ; Represents the allocation index set of the transmission power of all construction site equipment, , Indicates the maximum transmit power; Indicates construction site equipment Whether to associate and select drone-assisted smart reflective surfaces The index collection of ; Indicates construction site equipment The task processing delay, Indicates construction site equipment The maximum execution time of An indexed set representing the reflection coefficients of the reflective elements in the drone-assisted smart reflective surface. ; Indicates construction site equipment An index set of bit sizes of task data offloaded to the base station, ; A set of indices representing the bit size of data for offloading tasks from a micro base station to a macro base station, ;

[0041] in, and Indicates construction site equipment Only one base station can be selected for association; 、 and Indicates construction site equipment and the UAV-assisted smart reflective surface m can only select one sub-channel within the cluster as the connection node; Indicates construction site equipment The execution time will not exceed its maximum constraint time; and Indicates construction site equipment When transmitting a task, you must select a cryptographic algorithm and only one cryptographic algorithm can be associated; and Indicates construction site equipment Only one drone-assisted smart reflective surface can be selected for association; Indicates construction site equipment The total task data bit size that needs to be processed Greater than or equal to construction site equipment The bit size of the task data transmitted to the base station , construction site equipment The bit size of the task data transmitted to the base station Greater than or equal to construction site equipment The bit size of the task data offloaded to the micro base station , construction site equipment The bit size of the task data offloaded to the micro base station Greater than or equal to the data transmitted from the micro base station to the macro base station , and the bit size of all offloaded transmission task data must be greater than or equal to an infinitesimal constant ; It represents that the reflection coefficient of each reflective element in the UAV-assisted smart reflective surface m is within its constrained range; Indicates encrypted transmission of construction site equipment The safe execution cost of the resulting task will not exceed its maximum constraint cost, Indicates construction site equipment The maximum cost of the constraint.

[0042] Furthermore, the specific process of step S21 is:

[0043] Step S211, initialize the maximum number of iterations of the improved whale particle genetic algorithm , and the current number of iterations Set to 1;

[0044] Step S212: Assume the number of whales in the population is , any individual whale in the population uses The whale population is defined as ; The whale population of the improved whale particle genetic algorithm The index state set of each whale individual in Encoded into optimization parameters , Represents individual whales Construction site equipment Index status of the status indicator of establishing a connection with the base station; index status set Encoded into optimization parameters , Represents individual whales Construction site equipment Index status of the selected cryptographic algorithm; index status set Encoded into optimization parameters , Represents individual whales Construction site equipment Index status of the selected subchannel; index set Encoded into optimization parameters , Represents individual whales Construction site equipment Transmit power index of Encoded into optimization parameters , Represents individual whales Construction site equipment Index state of the selected drone-assisted smart reflective surface; index collection Encoded into optimization parameters , Indicates construction site equipment Reflection coefficient index of the reflective element in the associated drone-assisted smart reflective surface; index collection Encoded into optimization parameters , Represents individual whales Medium mission from construction site equipment Index of bit size of data offloaded to micro base station; index set Encoded into optimization parameters , An index representing the bit size of data for offloading tasks from the micro base station to the macro base station;

[0045] Step S213: Initialize the whale population and establish individual whales in the whale population. The fitness function of :

[0046] ;

[0047] Where, For construction site equipment The penalty factor for the maximum execution time of the task; For construction site equipment The penalty factor of the maximum security cost; represents the fitness function; Represents the total energy consumption of all construction site equipment;

[0048] Step S214: use the fitness function to calculate the fitness values ​​of all whale individuals in the whale population, and take the whale individual with the largest fitness value as the historical global best whale individual.

[0049] Furthermore, in step S22, the specific process of dynamically optimizing the position of individual whales based on the whales' predation behavior and the adaptive single-point crossover mutation operation is as follows: first, a random number between 0 and 1 is generated. ,like , then execute the whale hunting operation; if , then execute the spiral bubble net attack and search prey operation; if , then perform adaptive single-point crossover mutation operation, if , then the whale individual movement parameter adjustment operation is performed.

[0050] Furthermore, the specific steps of step S3 are: based on the solution of the position of the global best whale individual in the target whale population, executing the selection decision of the construction site equipment for the drone-assisted intelligent reflective surface, the selection decision of the construction site equipment associated base station, the optimization of the reflection coefficient matrix angle of the drone-assisted intelligent reflective surface, the selection decision of the security cryptographic algorithm, the sub-channel selection decision of the construction site equipment to the base station, and the sub-channel selection decision of the construction site equipment to the drone-assisted intelligent reflective surface.

[0051] Compared with the existing technology, the present invention has the following beneficial effects:

[0052] (1) This paper searches for whale populations using an improved Whale Particle Genetic Algorithm (AWG-PSO). This algorithm combines the random search operation of a particle swarm with the adaptive single-point crossover and mutation operation. Furthermore, by controlling the movement speed of individual whales, the whale population's local search capability in the solution space is enhanced, effectively improving the algorithm's search efficiency and optimization capabilities. This method can quickly find the optimal solution, significantly improving the overall weighted computational efficiency, and enabling the system to maintain high performance even in complex environments.

[0053] (2) This invention significantly improves the uplink transmission rate from the device to the base station by combining unmanned aerial vehicles (UAVs) and intelligent reflective surface (IRS) technology. The higher transmission rate effectively shortens the data transmission time, thereby reducing the system's energy consumption. Combined with an improved whale particle swarm genetic algorithm (AWG-PSO), this technology not only improves transmission efficiency but also optimizes overall energy management, allowing the system to operate efficiently while maintaining low energy consumption.

[0054] (3) The present invention can effectively minimize energy consumption under multiple constraints, including latency, security costs, sub-channel selection decisions for transmission from construction site equipment to base stations (micro base stations (SBS) or macro base stations (MBS)) and unmanned aerial vehicle-assisted intelligent reflective surfaces (UAV-IRS), selection decisions for construction site equipment to unmanned aerial vehicle-assisted intelligent reflective surfaces (UAV-IRS), and selection decisions for construction site equipment to associate with base stations. By comprehensively applying intelligent reflective surface (IRS) technology and an improved whale particle genetic algorithm (AWG-PSO), not only is the performance and reliability of the overall system improved, but energy consumption is also minimized, giving it significant advantages in practical applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 This is a flow chart of a smart construction site edge unloading method assisted by an aerial intelligent reflective surface provided by an embodiment of the present invention;

[0056] Figure 2 This is a diagram illustrating an application scenario of a smart construction site edge unloading method assisted by an aerial intelligent reflective surface provided by an embodiment of the present invention;

[0057] Figure 3 This is a simulation diagram of the energy consumption optimization effect provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0058] like Figure 1 The method for intelligent construction site edge unloading assisted by an aerial intelligent reflective surface includes the following steps:

[0059] Step S1: Establish an aerial intelligent reflective surface-assisted mobile edge computing system in a smart construction site scenario. The aerial intelligent reflective surface-assisted mobile edge computing system includes several unmanned aerial vehicle-assisted intelligent reflective surfaces (UAV-IRS), several construction site equipment, several micro base stations (SBSs), and one macro base station (MBS). Establish an uplink transmission communication network model, a computing model, and a security model, and construct an optimization problem under the constraints of the aerial intelligent reflective surface-assisted mobile edge computing system.

[0060] In step S2, an initial solution is obtained based on the energy consumption minimization optimization problem. The solution space containing all feasible solutions to the energy consumption minimization optimization problem is defined as the whale population. The initial solution is used as the initial whale individual in the whale population. The improved whale particle genetic algorithm (AWG-PSO) is used to search the entire whale population. The best whale individual in the whale population is obtained through the search process, and the position of the global best whale individual is finally output as the optimization result.

[0061] Step S3: performing energy consumption minimization optimization configuration according to the position of the global best whale individual.

[0062] Application scenarios of the smart construction site edge unloading method assisted by aerial intelligent reflective surfaces include Figure 2 shown.

[0063] The specific process of step S1 is as follows:

[0064] Step S11, obtain basic information of the aerial intelligent reflective surface assisted mobile edge computing system in the smart construction site scenario, specifically, first obtain The index set of construction site equipment is ,in, represents any construction site equipment in the aerial intelligent reflective surface assisted mobile edge computing system, represents the number of construction site equipment in the aerial intelligent reflective surface-assisted mobile edge computing system; The index set of micro base stations is , the index set of the macro base station is , the index set of all base stations is expressed as ,in, represents any micro base station in the aerial intelligent reflective surface assisted mobile edge computing system, It represents the number of micro base stations in the aerial intelligent reflective surface assisted mobile edge computing system, s represents any base station in the aerial intelligent reflective surface assisted mobile edge computing system, and S represents the total number of base stations in the aerial intelligent reflective surface assisted mobile edge computing system; The index set of drone-assisted smart reflective surfaces is ,in, represents any drone-assisted smart reflective surface, Indicates the number of drone-assisted smart reflective surfaces; a drone-assisted smart reflective surface contains A reflective element, The index set of reflective elements is ,in, represents any reflective element in the drone-assisted smart reflective surface, Indicates the number of reflective elements in a drone-assisted smart reflective surface; drone-assisted smart reflective surface The reflection coefficient matrix of the reflective element is recorded as , where diag represents a diagonal matrix, Reflective element The reflection coefficient on the drone-assisted smart reflective surface m; then, the physical locations of all micro base stations are obtained, and the physical locations of all micro base stations are used The clustering algorithm divides all micro base stations into clusters; one cluster contains micro base stations and Any site equipment and drone-assisted smart reflective surfaces, with The subchannels are used by the micro base stations, construction site equipment, and drone-assisted smart reflective surfaces in the cluster. The construction site equipment uses the same subchannel when transmitting to the base station and the drone-assisted smart reflective surface. The index set of sub-channels is recorded as , where n represents any subchannel within the cluster; obtain the total bandwidth of the aerial intelligent reflective surface assisted mobile edge computing system and subchannel bandwidth , the task is to pass the construction site equipment Channel Transmitted to drone-assisted smart reflective surfaces The channel gain is recorded as , the mission is achieved through drone-assisted smart reflective surfaces Channel Transmission to micro base station The channel gain is recorded as , the task is to pass the micro base station Send back to construction site equipment The channel gain is recorded as , the Gaussian white noise power is recorded as .

[0065] Step S12, further establishing an uplink transmission communication network model, a security model, and a computing model based on the basic information of the aerial intelligent reflective surface-assisted mobile edge computing system; including:

[0066] Step S121, constructing an uplink transmission communication network model: First, the total bandwidth of the aerial intelligent reflective surface assisted mobile edge computing system is divided into For micro base stations, divided into For use by macro base stations, where is the frequency band division factor, and , the number of sub-channels used by each cluster is , Represents the rounding function;

[0067] When the construction site equipment is associated with the micro base station, the construction site equipment is connected to the micro base station by using the non-orthogonal multiple access technology NOMA. The part of the task to be offloaded is sent to the micro base station; then, the uplink transmission rate is calculated according to the Shannon formula, that is: according to the formula , calculated in the subchannel Construction site equipment Send the task to the micro base station Uplink NOMA transmission rate ;in, Indicates the bandwidth used by micro base stations, Indicates construction site equipment Smart reflective surfaces assisted by connected drones The decision index coefficient of at the same time , representing any construction site equipment Must select any drone-assisted smart reflective surface Make an association, Indicates construction site equipment Its own transmission power; It means that in the process of uplink NOMA transmission, except for the construction site equipment, and drone-assisted smart reflective surfaces Any other construction site equipment ( ) and any other drone-assisted smart reflective surfaces For construction site equipment and drone-assisted smart reflective surfaces The sum of the interferences generated; Indicates any other construction site equipment Connect to any other drone-assisted smart reflective surface Decision-making index; Indicates any other construction site equipment The transmission power; Indicates other construction site equipment during uplink NOMA transmission Send missions to other drone-assisted smart reflective surfaces The resulting channel gain interference, Represents any other drone-assisted smart reflective surface An indexed set of reflection coefficients of the reflective elements in ; Indicates that the mission is assisted by any other drone's smart reflective surface Channel Channel gain for transmission to micro base stations.

[0068] in, , where and They represent the path loss factor and the task from the construction site equipment Transmitted to drone-assisted smart reflective surfaces The Rice fading factor, Represents the construction site equipment within the cluster to drone-assisted smart reflective surfaces distance, ,in, , ,in, represents transpose, Indicates construction site equipment The three-dimensional Cartesian coordinates of Indicates construction site equipment The three-dimensional Cartesian coordinates of The coordinate values ​​on the axis define the construction site equipment In space Direction of location, Indicates construction site equipment The three-dimensional Cartesian coordinates of The coordinate values ​​on the axis define the construction site equipment In space Direction location; Representing drone-assisted smart reflective surfaces The three-dimensional Cartesian coordinates of Representing drone-assisted smart reflective surfaces The three-dimensional Cartesian coordinates of Coordinate values ​​on the axis that define the drone-assisted smart reflective surface exist Direction of location, Representing drone-assisted smart reflective surfaces The three-dimensional Cartesian coordinates of Coordinate values ​​on the axis that define the drone-assisted smart reflective surface exist Direction of location, Representing drone-assisted smart reflective surfaces The three-dimensional Cartesian coordinates of Coordinate values ​​on the axis that define the drone-assisted smart reflective surface exist Direction location;

[0069] Indicates construction site equipment to drone-assisted smart reflective surfaces The non-line-of-sight link component is a constant; Indicates construction site equipment to drone-assisted smart reflective surfaces The line-of-sight link component, ; where o represents the imaginary unit, is the frequency; Indicates that when drones assist smart reflective surfaces With construction site equipment Drone-assisted smart reflective surfaces The reflection coefficient vector of each reflective element in, It means the signal propagation distance is The phase change produced when Indicates that the signal is from the construction site equipment Spread to drone-assisted smart reflective surfaces A reflective element The phase change experienced when Indicates that the signal is from the construction site equipment Spread to drone-assisted smart reflective surfaces When, after The phase change of each reflective element, Indicates that the signal is from the construction site equipment Spread to drone-assisted smart reflective surfaces When, after Phase change of each reflective element. and I both represent the number of the reflective element. The drone-assisted smart reflective surface has reflective elements, numbered from 1 to I. Among them, Indicates the construction site equipment within the cluster to drone-assisted smart reflective surfaces The direction angle, .

[0070] , where and They represent the path loss factor and the task from the UAV-assisted smart reflective surface. To micro base station The Rice fading factor, Representing drone-assisted smart reflective surfaces and micro base stations The distance between Where, , Indicates micro base station The three-dimensional Cartesian coordinates of Indicates micro base station The three-dimensional Cartesian coordinates of The coordinate values ​​on the axis define the micro base station exist Direction of location, Indicates micro base station The three-dimensional Cartesian coordinates of The coordinate values ​​on the axis define the micro base station exist Direction of location, Indicates micro base station The three-dimensional Cartesian coordinates of The coordinate values ​​on the axis define the micro base station exist Direction location; Representing drone-assisted smart reflective surfaces To micro base station The non-line-of-sight link component is a constant; Representing drone-assisted smart reflective surfaces To micro base station The line-of-sight link component, ; The signal propagation distance is The phase change produced when Indicates that the signal comes from the drone-assisted smart reflective surface A reflective element Propagation to micro base stations The phase change experienced when Indicates that the signal comes from the drone-assisted smart reflective surface Middle reflective elements propagate to the micro base station The phase change experienced when Indicates that the signal comes from the drone-assisted smart reflective surface The first reflection element propagates to the micro base station The phase change experienced when Representing the intelligent reflective surface assisted by drones in a cluster To micro base station The direction angle, .

[0071] When the construction site equipment is associated with the macro base station, according to the formula , calculated in the subchannel Construction site equipment Uplink NOMA transmission rate for sending tasks to the macro base station ;in, Indicates the bandwidth used by the macro base station; The mission is to use drone-assisted smart reflective surfaces Through the sub-channel Channel gain for transmission to the macro base station; Indicates the distance from the macro base station to the construction site equipment channel gain.

[0072] Step S122, constructing a security model: First, define the index set of the cryptographic algorithm as , where v represents any cryptographic algorithm and V represents the number of cryptographic algorithms. Select a cryptographic algorithm The task of protecting transmission When the expected security level is not achieved, the probability of encryption failure of the cryptographic algorithm is expressed as Otherwise, it is expressed as ;in, Indicates construction site equipment The task of protecting transmission The safety risk factor, Indicates the desired protection level of the task, Indicates the cryptographic algorithm The protection level of Calculating construction site equipment Security costs ,in, Indicates a transfer task loss of funds in case of failure; For construction site equipment With base station The correlation decision index between construction site equipment Associate to base station hour, , construction site equipment Not associated with a base station hour, ; Indicates construction site equipment Smart reflective surfaces assisted by connected drones The decision index coefficient of the construction site equipment Choose any drone-assisted smart reflective surface When making an association, ,otherwise .

[0073] Step S123: construct a calculation model based on the communication model and the security model:

[0074] When the construction site equipment is not associated with the base station for calculation, and the task is to calculate on the construction site equipment itself, according to the formula Calculate the time required for the task to be processed by the construction site equipment itself, where the first term on the right side of the equation represents the local processing time of the unloaded task data, and the second term on the right side of the equation represents the encryption time of the task data to be unloaded; Indicates the bit size of the task data calculated locally, Indicates construction site equipment The total task data bit size that needs to be processed, Indicates construction site equipment The bit size of the task data offloaded to the base station; Indicates construction site equipment Computing tasks The number of CPU cycles used by one bit represents the computational complexity or computational resource requirements of the task. Indicates construction site equipment The computing power allocated for local processing of calculations; Indicates construction site equipment The cryptographic algorithm selected when the transmitted task passes through the drone-assisted smart reflective surface and the base station in sequence; Represents a cryptographic algorithm The ability to encrypt transmission tasks; among them, construction site equipment The bit size of the task data offloaded to the base station For construction site equipment The bit size of the task data offloaded to the micro base station or macro base station.

[0075] When construction site equipment is associated with the micro base station for calculation, the equipment's unloaded tasks are first transmitted to the drone-assisted smart reflective surface, which then transmits the tasks to the micro base station. Finally, the micro base station transmits the tasks to the macro base station for processing. The time required to partially offload the tasks to the micro base station for processing is calculated as follows:

[0076] ;

[0077] Among them, the first term on the right side of the equation Indicates that the construction site equipment The time required for the task data to be offloaded to be uploaded to the micro base station through the selected sub-channel, Indicates construction site equipment Associated micro base stations Select subchannel when performing calculations As the state variable of the task uplink transmission connection node, Indicates construction site equipment Transferring tasks to drone-assisted smart reflective surfaces Select subchannel As the state variable of the connection node, Representing drone-assisted smart reflective surfaces Transfer tasks to micro base stations Select subchannel As the state variable of the connection node, Indicates construction site equipment The bit size of the task data offloaded to the micro base station; the second term on the right side of the equation Indicates construction site equipment The time required for the task data to be offloaded to be processed in the micro base station, Indicates the bit size of the task data processed by the micro base station, Indicates the bit size of the data that is offloaded from the micro base station to the macro base station, Represents the computing power allocated to the micro base station; the third term on the right side of the equation is the time required to offload tasks from the micro base station to the macro base station, Indicates the wired backhaul rate; the fourth term on the right side of the equation Indicates the time required for the macro base station to process the task data offloaded from the micro base station. Represents the computing power allocated to the macro base station; the fifth term on the right side of the equation Indicates encrypted construction site equipment The time for offloading tasks to the micro base station; the sixth term on the right side of the equation The time required to process the task of decrypting the micro base station, Represents a cryptographic algorithm The computing power of the decryption transmission task; the seventh term on the right side of the equation represents the time for the encrypted micro base station to offload the task to the macro base station; the eighth term on the right side of the equation Indicates the time required to process the decryption task of the macro base station.

[0078] When the construction site equipment is directly connected to the macro base station for calculation, the equipment's unloading task is first transmitted to the drone-assisted intelligent reflective surface, and then the drone-assisted intelligent reflective surface transmits the task to the macro base station. According to the formula The time it takes to calculate the task processing time at the macro base station, where the first term on the right side of the equation Indicates that the construction site equipment The time required for the task data to be offloaded to be uploaded to the macro base station through the selected sub-channel, Indicates construction site equipment Select subchannel when directly associated with macro base station for calculation As the state variable of the task uplink transmission connection node, Representing drone-assisted smart reflective surfaces Select subchannel when transferring tasks to the macro base station As the state variable of the connection node, Indicates construction site equipment The bit size of the task data transmitted uplink to the macro base station; the second term on the right side of the equation Indicates construction site equipment The time required for the macro base station to process the task data transmitted uplink to the macro base station. Indicates construction site equipment The bit size of the task data processed by the macro base station in the task data uplinked to the macro base station; the third term on the right side of the equation Indicates encrypted construction site equipment The time for uplink transmission to the macro base station; the fourth term on the right side of the equation Decryption of construction site equipment The time required for the macro base station to process the task data in the uplink transmission to the macro base station.

[0079] construction site equipment There are multiple tasks to be processed on the task, and the index set of the task is recorded as Assuming that tasks are executed sequentially (i.e., they are executed in the order of priority of the equipment on the construction site), any task can be executed locally and offloaded in parallel. The completion of the equipment on the construction site can be expressed by the formula The total processing time of all computing tasks .in, Indicates construction site equipment Select the time required for the associated base station calculation process. Based on the calculation offloading method of the construction site equipment k, the time required for the corresponding construction site equipment to first associate with the micro base station and then associate with the macro base station through the micro base station for processing, or the time required for the corresponding construction site equipment to directly associate with the macro base station for calculation processing; Indicates construction site equipment Select the time required for local computing processing;

[0080] The calculated total energy consumption for all tasks of all construction site equipment can be expressed by the formula:

[0081] ,

[0082] Among them, the first term on the right side of the equal sign Indicates the energy consumption generated when the task is performed by the equipment itself at the construction site; the second item on the right side of the equal sign Indicates the energy consumption generated by encryption during task encryption transmission; the third item on the right side of the equal sign Indicates the energy consumption generated by uplink transmission of task data to the base station and calculation and processing by the base station. Indicates construction site equipment Associated base station Select subchannel when performing calculations As the state variable of the task uplink transmission connection node, Representing drone-assisted smart reflective surfaces Transfer tasks to the base station Select subchannel As a state variable of the connection node; represents the uplink NOMA transmission rate of the construction site equipment k sending the task to the base station s. When the construction site equipment is associated with the micro base station, ,When the construction site equipment is associated with the macro base station, .

[0083] Step S13: Based on the uplink transmission communication network model, the computational model, and the security model, a minimization energy consumption optimization problem is constructed. The minimization energy consumption optimization problem includes the joint optimization of the following five sub-problems: the selection decision of the construction site equipment for the drone-assisted intelligent reflective surface, the selection decision of the construction site equipment associated with the base station, the optimization of the reflection coefficient matrix angle of the drone-assisted intelligent reflective surface, the selection decision of the security cryptographic algorithm, and the selection decision of the sub-channel for the construction site equipment to transmit to the base station and the drone-assisted intelligent reflective surface. The minimization energy consumption optimization problem is specifically as follows:

[0084] ;

[0085] Where, The goal of the energy consumption minimization optimization problem is to minimize the total computational energy consumption of all tasks of all construction site equipment in the aerial intelligent reflective surface assisted mobile edge computing system. ; Indicates construction site equipment Whether to decide with base station The index status set of the status indicators of the established connection, , For construction site equipment With base station The association decision index between the construction site equipment With base station When the connection is established, ,otherwise, ; Indicates construction site equipment The cryptographic algorithm selected when first transmitting the task to the drone-assisted smart reflective surface and then transmitting the task to the base station through the drone-assisted smart reflective surface The index state set, , Indicates construction site equipment The cryptographic algorithm selected when the transmitted task passes through the drone-assisted smart reflective surface and the base station in sequence; Indicates construction site equipment Transferring tasks to drone-assisted smart reflective surfaces and drone-assisted smart reflective surfaces Transfer tasks to the base station Select subchannel As an indexed state set of state variables of connected nodes, , Indicates construction site equipment Transferring tasks to drone-assisted smart reflective surfaces Select subchannel As the state variable of the connection node, It represents the drone-assisted smart reflective surface Transfer tasks to the base station Select subchannel As the state variable of the connection node; if the construction site equipment Transferring tasks to drone-assisted smart reflective surfaces Select subchannel As a connecting node, ,otherwise ; If drone-assisted smart reflective surfaces Transfer tasks to the base station Select subchannel As a connecting node, ,otherwise ; Represents the allocation index set of the transmission power of all construction site equipment, , Indicates construction site equipment Its own transmission power, Indicates the maximum transmit power; Indicates construction site equipment Whether to associate and select drone-assisted smart reflective surfaces The index collection of , Indicates construction site equipment Smart reflective surfaces assisted by connected drones The decision index coefficient of the construction site equipment Choose any drone-assisted smart reflective surface When making an association, ,otherwise ; Indicates construction site equipment The task processing delay, Indicates construction site equipment The maximum execution time of An indexed set representing the reflection coefficients of the reflective elements in the drone-assisted smart reflective surface. , Reflective element Reflection coefficient on the drone-assisted smart reflective surface m; Indicates construction site equipment An index set of bit sizes of task data offloaded to the base station, , Indicates construction site equipment The bit size of the task data offloaded to the micro base station; A set of indices representing the bit size of data for offloading tasks from a micro base station to a macro base station, , Indicates the bit size of the data for offloading tasks from the micro base station to the macro base station;

[0086] in, and Indicates construction site equipment Only one base station can be selected for association; 、 and Indicates construction site equipment and the UAV-assisted smart reflective surface m can only select one sub-channel within the cluster as the connection node; Indicates construction site equipment The execution time will not exceed its maximum constraint time; and Indicates construction site equipment When transmitting a task, you must select a cryptographic algorithm and only one cryptographic algorithm can be associated; and Indicates construction site equipment Only one drone-assisted smart reflective surface can be selected for association; Indicates construction site equipment The total task data bit size that needs to be processed Greater than or equal to construction site equipment The bit size of the task data transmitted to the base station , construction site equipment The bit size of the task data transmitted to the base station Greater than or equal to construction site equipment The bit size of the task data offloaded to the micro base station , construction site equipment The bit size of the task data offloaded to the micro base station Greater than or equal to the data transmitted from the micro base station to the macro base station , and the bit size of all offloaded transmission task data must be greater than or equal to an infinitesimal constant ; It represents that the reflection coefficient of each reflective element in the UAV-assisted smart reflective surface m is within its constrained range; Indicates encrypted transmission of construction site equipment The safe execution cost of the resulting task will not exceed its maximum constraint cost, Indicates construction site equipment The security cost, Indicates construction site equipment The maximum cost of the constraint.

[0087] The specific process of step S2 is:

[0088] Step S21: Initialize the population of whale individuals and determine the best whale individual in history. The specific process is as follows:

[0089] Step S211, initialize the maximum number of iterations of the improved whale particle genetic algorithm , and the current number of iterations Set to 1;

[0090] Step S212: Assume the number of whales in the population is , any individual whale in the population uses The whale population is defined as ; The whale population of the improved whale particle genetic algorithm The index state set of each whale individual in Encoded into optimization parameters , Represents individual whales Construction site equipment Index status of the status indicator of establishing a connection with the base station; index status set Encoded into optimization parameters , Represents individual whales Construction site equipment Index status of the selected cryptographic algorithm; index status set Encoded into optimization parameters , Represents individual whales Construction site equipment Index status of the selected subchannel; index set Encoded into optimization parameters , Represents individual whales Construction site equipment Transmit power index of Encoded into optimization parameters , Represents individual whales Construction site equipment Index state of the selected drone-assisted smart reflective surface; index collection Encoded into optimization parameters , Indicates construction site equipment Reflection coefficient index of the reflective element in the associated drone-assisted smart reflective surface; index collection Encoded into optimization parameters , Represents individual whales Medium mission from construction site equipment Index of bit size of data offloaded to micro base station; index set Encoded into optimization parameters , An index representing the bit size of data for offloading tasks from the micro base station to the macro base station;

[0091] Step S213: Initialize the whale population and establish individual whales in the whale population. The fitness function of :

[0092] ;

[0093] Where, For construction site equipment The penalty factor for the maximum execution time of the task; For construction site equipment The penalty factor of the maximum security cost; represents the fitness function; Represents the total energy consumption of all construction site equipment;

[0094] Step S214: use the fitness function to calculate the fitness values ​​of all whale individuals in the whale population, and take the whale individual with the largest fitness value as the historical global best whale individual.

[0095] Step S22, based on the whale's predation behavior and the adaptive single-point crossover mutation operation, the position of the individual whale is dynamically optimized, so that the individual whale moves according to the predefined direction and distance. Specifically, the whale moves closer to the optimal solution when encircling the prey and shrinks the encirclement, and moves away from the current optimal solution when searching for prey globally. The moving distance gradually shortens as the whale gets closer to the optimal solution, so as to better explore the solution space. The specific process of dynamically optimizing the position of the individual whale based on the whale's predation behavior and the adaptive single-point crossover mutation operation is as follows: first, a random number between 0 and 1 is generated. ,like , then execute the whale hunting operation; if , then execute the spiral bubble net attack and search prey operation; if , then perform adaptive single-point crossover mutation operation, if , then the whale individual movement parameter adjustment operation is performed;

[0096] Step S221, the whale encirclement operation is specifically described as follows:

[0097] ,

[0098] in, Represents the rounding function; t represents the current number of iterations; , , , , , , , Indicates the position of the individual whale corresponding to each optimization parameter at the t+1th iteration; , , , , , , , Indicates the position of the best individual whale corresponding to the current optimization parameters; , , , , , , , Indicates the current position of the individual whale corresponding to each optimization parameter; specifically, The corresponding optimization parameter is the status indicator of the connection between the construction site equipment k and the base station; The corresponding optimization parameter is the cryptographic algorithm selected by the construction site equipment k; The corresponding optimization parameter is the subchannel selected by the construction site equipment k; The corresponding optimization parameter is the transmission power of the construction site equipment k; The corresponding optimization parameter is the drone-assisted intelligent reflective surface selected by the construction site equipment k; The corresponding optimization parameter is the bit size of the data that the task offloads from the construction site equipment k to the micro base station; The corresponding optimization parameter is the bit size of the data that the task is offloaded from the micro base station to the macro base station; The corresponding optimization parameter is the reflection coefficient of the reflective element in the drone-assisted smart reflective surface associated with the construction site equipment k; is a random number, ,in, is a random number that decays from 2 to 0, and r and C are both random numbers between 0 and 1;

[0099] Step S222, the spiral bubble net attack and prey search operations are specifically described as follows:

[0100] ,

[0101] in, , , , , , , , Indicates the position of the individual whale corresponding to each optimization parameter at the t+1th iteration; , , , , , , , Indicates the position of the best individual whale corresponding to the current optimization parameters; , , , , , , , Indicates the current position of the individual whale corresponding to each optimization parameter; represents the exponential function; where is a constant used to define the route of the whale when performing a spiral bubble net attack; is a random number between [-1,1];

[0102] Step S223, the adaptive single-point crossover mutation operation is specifically as follows:

[0103] First, randomly select the chromosome gene fragments of two whale individuals, perform single-point crossover transformation based on the crossover probability, and exchange the chromosome gene fragments of the two selected whale individuals to form two new whale individuals; the crossover probability The calculation formula is:

[0104] ,

[0105] in, and is a random parameter greater than 0 and less than 1, Represents individual whales The fitness value of represents the best fitness value in the whale population, that is, the maximum fitness value, represents the minimum fitness value in the whale population;

[0106] Then randomly select two whale individuals, and randomly select one or more gene fragments from the chromosomes of the two whale individuals. Change the chromosome gene fragments of the two selected whale individuals according to the mutation probability, thereby forming two new whale individuals, further ensuring the comprehensiveness and accuracy of the algorithm search and jumping out of the local optimum; mutation probability The calculation formula is:

[0107] ,

[0108] in, and is a random parameter greater than 0 and less than 1, represents the average fitness value in the whale population;

[0109] The whale individuals are mutated as follows:

[0110] ,

[0111] in, and is a random parameter greater than 0 and less than 1, Controlling the mutation rate of individual whales, What is controlled is the search direction of individual whales; , , , , , , , Represents the position of the individual whale after the current optimization parameters are mutated; , , , , , , , Represents the position of the individual whales before the mutation corresponding to the current optimization parameters; specifically, , The corresponding optimization parameter is the status indicator of the connection between the construction site equipment k and the base station; , The corresponding optimization parameter is the cryptographic algorithm selected by the construction site equipment k; , The corresponding optimization parameter is the subchannel selected by the construction site equipment k; , The corresponding optimization parameter is the transmission power of the construction site equipment k; , The corresponding optimization parameter is the drone-assisted intelligent reflective surface selected by the construction site equipment k; , The corresponding optimization parameter is the bit size of the data that the task offloads from the construction site equipment k to the micro base station; , The corresponding optimization parameter is the bit size of the data that the task is offloaded from the micro base station to the macro base station; , The corresponding optimization parameter is the reflection coefficient of the reflective element in the drone-assisted smart reflective surface associated with the construction site equipment k; S represents the total number of base stations, V represents the total number of cryptographic algorithms, and N represents the total number of sub-channels. represents the maximum transmission power, and D represents the maximum amount of data processed by the construction site equipment;

[0112] In step S224, the whale individual movement parameter adjustment operation is to control the movement and adjustment speed of the whale individual by adjusting the inertia weight, self-learning factor and social learning factor. The specific formula is expressed as:

[0113] ,

[0114] in, represents the inertia weight of the individual whale, , and They represent the maximum and minimum values ​​of the whale's individual inertia weight, t represents the current number of iterations, and T represents the total number of iterations; and represent learning factors and social factors respectively, where and ; It represents a random number; Represents the speed of the whale individual at the t+1th iteration corresponding to each optimized parameter after the movement parameters are adjusted; Represents the speed of the whale individual corresponding to each optimization parameter at the tth iteration before the movement parameter is adjusted; represents the local optimal position of the individual whale movement parameters corresponding to each optimization parameter in the tth iteration before adjustment; represents the global optimal position of the whale individual movement parameters before adjustment in the tth iteration. Represents the position of the individual whale before the adjustment of the movement parameters corresponding to each optimization parameter in the tth iteration; represents the position of the whale's individual movement parameters after adjustment in the t+1th iteration. Specifically, The corresponding optimization parameter is the status indicator of the connection between the construction site equipment k and the base station; The corresponding optimization parameter is the cryptographic algorithm selected by the construction site equipment k; The corresponding optimization parameter is the subchannel selected by the construction site equipment k; The corresponding optimization parameter is the transmission power of the construction site equipment k; The corresponding optimization parameter is the drone-assisted intelligent reflective surface selected by the construction site equipment k; The corresponding optimization parameter is the bit size of the data that the task offloads from the construction site equipment k to the micro base station; The corresponding optimization parameter is the bit size of the data that the task is offloaded from the micro base station to the macro base station; The corresponding optimization parameter is the reflection coefficient of the reflective element in the drone-assisted smart reflective surface associated with the construction site equipment k;

[0115] Step S23: The position of the global best whale individual is updated. The fitness value of all whale individuals in the target whale population is calculated using the fitness function. If the fitness value of any whale individual in the target whale population is higher than the fitness value of the historical global best whale individual, the whale individual with the higher fitness value is replaced with the global best whale individual to obtain the position of the current global best whale individual.

[0116] Step S24, then repeat the aforementioned step S22 of dynamically optimizing the position of the whale individual based on the whale predation behavior and the adaptive single-point crossover mutation operation and the position update of the global best whale individual in step S23 until the maximum number of iterations is reached; finally, the global best whale individual in the target whale population is output, and the position of the global best whale individual in the target whale population is obtained.

[0117] Among them, the specific steps of step S3 are: according to the solution of the position of the global best whale individual in the target whale population, the selection decision of the construction site equipment for the drone-assisted intelligent reflective surface, the selection decision of the construction site equipment associated base station, the optimization of the reflection coefficient matrix angle of the drone-assisted intelligent reflective surface, the selection decision of the security cryptographic algorithm, the sub-channel selection decision of the construction site equipment to the base station, and the sub-channel selection decision of the construction site equipment to the drone-assisted intelligent reflective surface.

[0118] Figure 3This diagram shows a simulation of the energy consumption optimization effect provided by an embodiment of the present invention. Comparison tests were conducted using existing Comparison Algorithms 1 and 2, compared to the edge offloading method of the present invention. Comparison Algorithm 1 is the original Whale Optimization Algorithm (WOA), which optimizes by simulating the hunting behavior of humpback whales; Comparison Algorithm 2 is a Genetic Algorithm (GA), which simulates natural selection and genetics mechanisms and optimizes through selection, crossover, and mutation operations. Simulation results show that the edge offloading method of the present invention exhibits lower energy consumption at various device densities. In high-density environments, the energy savings are particularly significant compared to WOA and GA, validating its effectiveness in energy optimization.

Claims

1. A smart construction site edge unloading method assisted by an aerial intelligent reflective surface, characterized in that: The steps include: Step S1: Establish an aerial intelligent reflective surface-assisted mobile edge computing system in a smart construction site scenario, wherein the aerial intelligent reflective surface-assisted mobile edge computing system includes several drone-assisted intelligent reflective surfaces, several construction site equipment, several micro base stations, and one macro base station; obtain basic information of the aerial intelligent reflective surface-assisted mobile edge computing system in the smart construction site scenario, establish an uplink transmission communication network model, a security model, and a computing model based on the basic information of the aerial intelligent reflective surface-assisted mobile edge computing system, and construct an energy consumption minimization optimization problem based on the uplink transmission communication network model, the security model, and the computing model under the constraints of the aerial intelligent reflective surface-assisted mobile edge computing system; The energy consumption minimization optimization problem includes the joint optimization of the following five sub-problems: the selection decision of the construction site equipment for the drone-assisted smart reflective surface, the selection decision of the base station associated with the construction site equipment, the optimization of the reflection coefficient matrix angle of the drone-assisted smart reflective surface, the selection decision of the secure cryptographic algorithm, and the selection decision of the sub-channel for the construction site equipment to transmit to the base station and the drone-assisted smart reflective surface; Step S2: Obtain an initial solution based on the energy consumption minimization optimization problem, define the solution space containing all feasible solutions to the energy consumption minimization optimization problem as a whale population, and use the initial solution as the initial whale individual in the whale population. Use the improved whale particle genetic algorithm to search the entire whale population, obtain the best whale individual in the whale population through the search process, and finally output the position of the global best whale individual as the optimization result; The specific process is: Step S21, initialize the population of whale individuals and determine the best whale individual in history; Step S22, based on the whale's predation behavior and the adaptive single-point crossover mutation operation, dynamically optimize the position of the individual whale. Specifically, first generate a random number , according to the random number The range interval in which the whale is located performs one of the following operations: whale encirclement operation, spiral bubble net attack and prey search operation, adaptive single point crossover mutation operation, and whale individual movement parameter adjustment operation; Step S23: The position of the global best whale individual is updated. The fitness value of all whale individuals in the whale population is calculated using the fitness function. If the fitness value of any whale individual in the whale population is higher than the fitness value of the historical global best whale individual, the whale individual with the higher fitness value is replaced with the global best whale individual to obtain the position of the current global best whale individual. Step S24, repeating steps S22 and S23 in sequence until the maximum number of iterations is reached; finally, outputting the global best whale individual in the target whale population, and obtaining the position of the global best whale individual in the target whale population; Step S3: Execute the energy-minimizing optimization configuration based on the position of the global best whale individual.

2. The method for intelligent construction site edge unloading assisted by an aerial intelligent reflective surface according to claim 1, characterized in that: In step S1, obtaining basic information of the aerial intelligent reflective surface assisted mobile edge computing system in the smart construction site scenario specifically includes the following steps: First, obtain The index set of construction site equipment is ,in, represents any construction site equipment in the aerial intelligent reflective surface assisted mobile edge computing system, represents the number of construction site equipment in the aerial intelligent reflective surface-assisted mobile edge computing system; The index set of micro base stations is , the index set of the macro base station is , the index set of all base stations is expressed as ,in, represents any micro base station in the aerial intelligent reflective surface assisted mobile edge computing system, It represents the number of micro base stations in the aerial intelligent reflective surface assisted mobile edge computing system, s represents any base station in the aerial intelligent reflective surface assisted mobile edge computing system, and S represents the total number of base stations in the aerial intelligent reflective surface assisted mobile edge computing system; The index set of drone-assisted smart reflective surfaces is ,in, represents any drone-assisted smart reflective surface, Indicates the number of drone-assisted smart reflective surfaces; a drone-assisted smart reflective surface contains A reflective element, The index set of reflective elements is ,in, represents any reflective element in the drone-assisted smart reflective surface, Indicates the number of reflective elements in a drone-assisted smart reflective surface; drone-assisted smart reflective surface The reflection coefficient matrix of the reflective element is recorded as ,in, Reflective element The reflection coefficient on the drone-assisted smart reflective surface m; then, the physical locations of all micro base stations are obtained, and the physical locations of all micro base stations are used The clustering algorithm divides all micro base stations into clusters; one cluster contains micro base stations and Any site equipment and drone-assisted smart reflective surfaces, with The subchannels are used by the micro base stations, construction site equipment, and drone-assisted smart reflective surfaces in the cluster. The construction site equipment uses the same subchannel when transmitting to the base station and the drone-assisted smart reflective surface. The index set of sub-channels is recorded as , where n represents any subchannel within the cluster; obtain the total bandwidth of the aerial intelligent reflective surface assisted mobile edge computing system and subchannel bandwidth , the task is to pass the construction site equipment Channel Transmitted to drone-assisted smart reflective surfaces The channel gain is recorded as , the mission is achieved through drone-assisted smart reflective surfaces Channel Transmission to micro base station The channel gain is recorded as , the task is to pass the micro base station Send back to construction site equipment The channel gain is recorded as , the Gaussian white noise power is recorded as .

3. The method for intelligent construction site edge unloading assisted by an aerial intelligent reflective surface according to claim 2, characterized in that: In step S1, the specific process of establishing the uplink transmission communication network model is as follows: First, the total bandwidth of the aerial intelligent reflective surface assisted mobile edge computing system is divided into For micro base stations, divided into For use by macro base stations, where is the frequency band division factor, and , the number of sub-channels used by each cluster is , Represents the rounding function; When the construction site equipment is associated with the micro base station, the construction site equipment is connected to the micro base station by using the non-orthogonal multiple access technology NOMA. The part of the task to be offloaded is sent to the micro base station; then, the uplink transmission rate is calculated according to the Shannon formula, that is: according to the formula , calculated in the subchannel Construction site equipment Send the task to the micro base station Uplink NOMA transmission rate ;in, Indicates the bandwidth used by micro base stations, Indicates construction site equipment Smart reflective surfaces assisted by connected drones The decision index coefficient of at the same time , representing any construction site equipment Must select any drone-assisted smart reflective surface Make an association, Indicates construction site equipment Its own transmission power; It means that in the process of uplink NOMA transmission, except for the construction site equipment, and drone-assisted smart reflective surfaces Any other construction site equipment and any other drone-assisted smart reflective surfaces For construction site equipment and drone-assisted smart reflective surfaces The sum of the interferences generated; Indicates any other construction site equipment Connect to any other drone-assisted smart reflective surface Decision-making index; Indicates any other construction site equipment The transmission power; Indicates other construction site equipment during uplink NOMA transmission Send missions to other drone-assisted smart reflective surfaces The resulting channel gain interference, Represents any other drone-assisted smart reflective surface An indexed set of reflection coefficients of the reflective elements in ; Indicates that the mission is assisted by any other drone's smart reflective surface Channel Channel gain for transmission to the micro base station; When the construction site equipment is associated with the macro base station, according to the formula , calculated in the subchannel Construction site equipment Uplink NOMA transmission rate for sending tasks to the macro base station ;in, Indicates the bandwidth used by the macro base station; The mission is to use drone-assisted smart reflective surfaces Through the sub-channel Channel gain for transmission to the macro base station; Indicates the distance from the macro base station to the construction site equipment channel gain.

4. The method for intelligent construction site edge unloading assisted by an aerial intelligent reflective surface according to claim 3 is characterized in that: In step S1, the specific process of establishing the security model is as follows: First, define the index set of the cryptographic algorithm as , where v represents any cryptographic algorithm and V represents the number of cryptographic algorithms. Select a cryptographic algorithm The task of protecting transmission When the expected security level is not achieved, the probability of encryption failure of the cryptographic algorithm is expressed as Otherwise, it is expressed as ;in, Indicates construction site equipment The task of protecting transmission The safety risk factor, Indicates the desired protection level of the task, Indicates the cryptographic algorithm The protection level of Calculating construction site equipment Security costs ,in, Indicates a transfer task loss of funds in case of failure; For construction site equipment With base station The correlation decision index between construction site equipment Associate to base station hour, , construction site equipment Not associated with a base station hour, ; Construction site equipment Choose any drone-assisted smart reflective surface When making an association, ,otherwise .

5. The method for intelligent construction site edge unloading assisted by an aerial intelligent reflective surface according to claim 4, characterized in that: In step S1, the specific process of establishing the calculation model is: When the construction site equipment is not associated with the base station for calculation, and the task is to calculate on the construction site equipment itself, according to the formula Calculate the time required for the task to be processed by the construction site equipment itself, where the first term on the right side of the equation represents the local processing time of the unloaded task data, and the second term on the right side of the equation represents the encryption time of the task data to be unloaded; Indicates the bit size of the task data calculated locally, Indicates construction site equipment The total task data bit size that needs to be processed, Indicates construction site equipment The bit size of the task data offloaded to the base station; Indicates construction site equipment Computing tasks The number of CPU cycles used by one bit represents the computational complexity or computational resource requirements of the task. Indicates construction site equipment The computing power allocated for local processing of calculations; Indicates construction site equipment The cryptographic algorithm selected when the transmitted task passes through the drone-assisted smart reflective surface and the base station in sequence; Represents a cryptographic algorithm The ability to encrypt transmission tasks; When construction site equipment is associated with the micro base station for calculation, the equipment's unloaded tasks are first transmitted to the drone-assisted smart reflective surface, which then transmits the tasks to the micro base station. Finally, the micro base station transmits the tasks to the macro base station for processing. The time required to partially offload the tasks to the micro base station for processing is calculated as follows: ； Among them, the first term on the right side of the equation Indicates that the construction site equipment The time required for the task data to be offloaded to be uploaded to the micro base station through the selected sub-channel, Indicates construction site equipment Associated micro base stations Select subchannel when performing calculations As the state variable of the task uplink transmission connection node, Indicates construction site equipment Transferring tasks to drone-assisted smart reflective surfaces Select subchannel As the state variable of the connection node, Representing drone-assisted smart reflective surfaces Transfer tasks to micro base stations Select subchannel As the state variable of the connection node, Indicates construction site equipment The bit size of the task data offloaded to the micro base station; the second term on the right side of the equation Indicates construction site equipment The time required for the task data to be offloaded to be processed in the micro base station, Indicates the bit size of the task data processed by the micro base station, Indicates the bit size of the data that is offloaded from the micro base station to the macro base station, Represents the computing power allocated to the micro base station; the third term on the right side of the equation is the time required to offload tasks from the micro base station to the macro base station, Indicates the wired backhaul rate; the fourth term on the right side of the equation Indicates the time required for the macro base station to process the task data offloaded from the micro base station. Represents the computing power allocated to the macro base station; the fifth term on the right side of the equation Indicates encrypted construction site equipment The time for offloading tasks to the micro base station; the sixth term on the right side of the equation The time required to process the task of decrypting the micro base station, Represents a cryptographic algorithm The computing power of the decryption transmission task; the seventh term on the right side of the equation represents the time for the encrypted micro base station to offload the task to the macro base station; the eighth term on the right side of the equation Indicates the time required to process the decryption macro base station task; When the construction site equipment is directly connected to the macro base station for calculation, the equipment's unloading task is first transmitted to the drone-assisted intelligent reflective surface, and then the drone-assisted intelligent reflective surface transmits the task to the macro base station. According to the formula The time it takes to calculate the task processing time at the macro base station, where the first term on the right side of the equation Indicates that the construction site equipment The time required for the task data to be offloaded to be uploaded to the macro base station through the selected sub-channel, Indicates construction site equipment Select subchannel when directly associated with macro base station for calculation As the state variable of the task uplink transmission connection node, Representing drone-assisted smart reflective surfaces Select subchannel when transferring tasks to the macro base station As the state variable of the connection node, Indicates construction site equipment The bit size of the task data transmitted uplink to the macro base station; the second term on the right side of the equation Indicates construction site equipment The time required for the macro base station to process the task data transmitted uplink to the macro base station. Indicates construction site equipment The bit size of the task data processed by the macro base station in the task data uplinked to the macro base station; the third term on the right side of the equation Indicates encrypted construction site equipment The time for uplink transmission to the macro base station; the fourth term on the right side of the equation Decryption of construction site equipment The time required for the macro base station to process the task data in the uplink transmission to the macro base station; construction site equipment There are multiple tasks to be processed on the task, and the index set of the task is recorded as , assuming that tasks are executed in the order of priority of task processing by construction site equipment, local processing and computation offloading can be performed in parallel for any task to complete the construction site equipment The total processing time of all computing tasks is expressed as ,in, Indicates the time required for construction site device k to select and associate with the base station for computation and processing. Depending on the computation offloading mode of construction site device k, this may involve the time required for the construction site device to first associate with the micro base station and then with the macro base station through the micro base station, or the time required for the construction site device to directly associate with the macro base station for computation and processing. Indicates construction site equipment Select the time required for local computing processing; The formula for calculating the total energy consumption of all tasks of all construction site equipment is expressed as: ， Among them, the first term on the right side of the equal sign Indicates the energy consumption generated when the task is performed by the equipment itself at the construction site; the second item on the right side of the equal sign Indicates the energy consumption generated by encryption during task encryption transmission; the third item on the right side of the equal sign Indicates the energy consumption generated by uplink transmission of task data to the base station and calculation and processing by the base station. Indicates construction site equipment Associated base station Select subchannel when performing calculations As the state variable of the task uplink transmission connection node, Representing drone-assisted smart reflective surfaces Transfer tasks to the base station Select subchannel As a state variable of the connection node; represents the uplink NOMA transmission rate of the construction site equipment k sending the task to the base station s. When the construction site equipment is associated with the micro base station, ,When the construction site equipment is associated with the macro base station, .

6. The method for intelligent construction site edge unloading assisted by an aerial intelligent reflective surface according to claim 5, characterized in that: The energy consumption minimization optimization problem constructed based on the uplink transmission communication network model, computing model, and security model is specifically: ； Where, The goal of the energy consumption minimization optimization problem is to minimize the total computational energy consumption of all tasks of all construction site equipment in the aerial intelligent reflective surface assisted mobile edge computing system. ; Indicates construction site equipment Whether to decide with base station The index status set of the status indicators of the established connection, ; Indicates construction site equipment The cryptographic algorithm selected when first transmitting the task to the drone-assisted smart reflective surface and then transmitting the task to the base station through the drone-assisted smart reflective surface The index state set, ; Indicates construction site equipment Transferring tasks to drone-assisted smart reflective surfaces and drone-assisted smart reflective surfaces Transfer tasks to the base station Select subchannel As an indexed state set of state variables of connected nodes, If the construction site equipment Transferring tasks to drone-assisted smart reflective surfaces Select subchannel As a connecting node, ,otherwise ; If drone-assisted smart reflective surfaces Transfer tasks to the base station Select subchannel As a connecting node, ,otherwise ; Represents the allocation index set of the transmission power of all construction site equipment, , Indicates the maximum transmit power; Indicates construction site equipment Whether to associate and select drone-assisted smart reflective surfaces The index collection of ; Indicates construction site equipment The task processing delay, Indicates construction site equipment The maximum execution time of An indexed set representing the reflection coefficients of the reflective elements in the drone-assisted smart reflective surface. ; Indicates construction site equipment An index set of bit sizes of task data offloaded to the base station, ; A set of indices representing the bit size of data for offloading tasks from a micro base station to a macro base station, ; in, and Indicates construction site equipment Only one base station can be selected for association; 、 and Indicates construction site equipment and the UAV-assisted smart reflective surface m can only select one sub-channel within the cluster as the connection node; Indicates construction site equipment The execution time will not exceed its maximum constraint time; and Indicates construction site equipment When transmitting a task, you must select a cryptographic algorithm and only one cryptographic algorithm can be associated; and Indicates construction site equipment Only one drone-assisted smart reflective surface can be selected for association; Indicates construction site equipment The total task data bit size that needs to be processed Greater than or equal to construction site equipment The bit size of the task data transmitted to the base station , construction site equipment The bit size of the task data transmitted to the base station Greater than or equal to construction site equipment The bit size of the task data offloaded to the micro base station , construction site equipment The bit size of the task data offloaded to the micro base station Greater than or equal to the data transmitted from the micro base station to the macro base station , and the bit size of all offloaded transmission task data must be greater than or equal to an infinitesimal constant ; It represents that the reflection coefficient of each reflective element in the UAV-assisted smart reflective surface m is within its constrained range; Indicates encrypted transmission of construction site equipment The safe execution cost of the resulting task will not exceed its maximum constraint cost, Indicates construction site equipment The maximum cost of the constraint.

7. The method for intelligent construction site edge unloading assisted by an aerial intelligent reflective surface according to claim 6, characterized in that: The specific process of step S21 is: Step S211, initialize the maximum number of iterations of the improved whale particle genetic algorithm , and the current number of iterations Set to 1; Step S212: Assume the number of whales in the population is , any individual whale in the population uses The whale population is defined as ; The whale population of the improved whale particle genetic algorithm is The index state set of each whale individual in Encoded into optimization parameters , Represents individual whales Construction site equipment Index status of the status indicator of establishing a connection with the base station; index status set Encoded into optimization parameters , Represents individual whales Construction site equipment Index status of the selected cryptographic algorithm; index status set Encoded into optimization parameters , Represents individual whales Construction site equipment Index status of the selected subchannel; index set Encoded into optimization parameters , Represents individual whales Construction site equipment Transmit power index of Encoded into optimization parameters , Represents individual whales Construction site equipment Index state of the selected drone-assisted smart reflective surface; index collection Encoded into optimization parameters , Indicates construction site equipment Reflection coefficient index of the reflective element in the associated drone-assisted smart reflective surface; index collection Encoded into optimization parameters , Represents individual whales Medium mission from construction site equipment Index of bit size of data offloaded to micro base station; index set Encoded into optimization parameters , An index representing the bit size of data for offloading tasks from the micro base station to the macro base station; Step S213: Initialize the whale population and establish individual whales in the whale population. The fitness function of : ； Where, For construction site equipment The penalty factor for the maximum execution time of the task; For construction site equipment The penalty factor of the maximum security cost; represents the fitness function; Represents the total energy consumption of all construction site equipment; Step S214: use the fitness function to calculate the fitness values ​​of all whale individuals in the whale population, and take the whale individual with the largest fitness value as the historical global best whale individual.

8. The method for intelligent construction site edge unloading assisted by an aerial intelligent reflective surface according to claim 7, characterized in that: In step S22, the specific process of dynamically optimizing the position of individual whales based on the whale predation behavior and the adaptive single-point crossover mutation operation is as follows: first, a random number between 0 and 1 is generated. ,like , then execute the whale hunting operation; if , then execute the spiral bubble net attack and search prey operation; if , then perform adaptive single-point crossover mutation operation, if , then the whale individual movement parameter adjustment operation is performed.

9. The method for intelligent construction site edge unloading assisted by an aerial intelligent reflective surface according to claim 8, characterized in that: The specific steps of step S3 are: based on the solution of the position of the global best whale individual in the target whale population, executing the selection decision of the construction site equipment for the drone-assisted intelligent reflective surface, the selection decision of the construction site equipment associated base station, the optimization of the reflection coefficient matrix angle of the drone-assisted intelligent reflective surface, the selection decision of the security cryptographic algorithm, the sub-channel selection decision of the construction site equipment to the base station, and the sub-channel selection decision of the construction site equipment to the drone-assisted intelligent reflective surface.

Images