Task unloading method and device for computing power network, equipment and storage medium

Abstract

The invention discloses a task unloading method and device of a computing power network, equipment and a storage medium, relates to the technical field of wireless communication, and discloses the task unloading method of the computing power network, which comprises the following steps: after receiving a task unloading request, obtaining a to-be-unloaded task, a first target MEC node in an edge MBS and a second target MEC node in an edge SBS; determining a task allocation proportion and a bandwidth allocation proportion based on the task unloading request; and according to the task allocation proportion and the bandwidth allocation proportion, calling a preset unmanned aerial vehicle relay to unload the to-be-unloaded task to the first target MEC node or the second target MEC node in parallel. Namely, the to-be-unloaded task is unloaded to the first target MEC node or the second target MEC node, concentration of the MEC nodes is avoided, and the time delay required for transmitting the unloaded task is reduced to the minimum through the task distribution proportion, so that the time delay of task unloading is reduced.

Description

Technical Field

[0001] The present application relates to the field of wireless communication technology, and in particular to a method, device, equipment and storage medium for offloading tasks from a computing network. Background Art

[0002] Wireless networks are an important part of computing networks. By providing connectivity, flexibility, and mobility support, they enable computing networks to serve various application scenarios more widely and efficiently.

[0003] As smart applications have increasingly stringent requirements for computing power, a single edge node cannot meet the computing needs of smart applications. The collaboration between MEC (Mobile Edge Computing) nodes reduces task processing latency and processing costs, which can effectively improve resource utilization, especially in wireless networks, where the allocation of computing resources and bandwidth resources must be considered together. Currently, in distributed computing networks, MEC servers are deployed too centrally and are not deployed on distributed nodes that are backhauled wirelessly, resulting in longer delays in task offloading.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of this application is to provide a task offloading method for a computing network, aiming to solve the technical problem that the deployment of MEC servers is too centralized, resulting in a long delay in task offloading.

[0006] To achieve the above objectives, the present application proposes a method for offloading tasks from a computing network, the method comprising:

[0007] After receiving the task offloading request, obtain the task to be offloaded, the first target MEC node in the edge MBS, and the second target MEC node in the edge SBS;

[0008] Based on the task offloading request, determine a task allocation ratio and a bandwidth allocation ratio, wherein the task allocation ratio is a task ratio of offloading the task to be offloaded to the first target MEC node and the second target MEC node, and the bandwidth allocation ratio is a bandwidth occupancy ratio of the edge MBS and the edge SBS;

[0009] According to the task allocation ratio and the bandwidth allocation ratio, a preset drone relay is called to unload the tasks to be unloaded in parallel to the first target MEC node or the second target MEC node.

[0010] In one embodiment, the step of determining the task allocation ratio and the bandwidth allocation ratio based on the task offloading request includes:

[0011] extracting an initial allocation ratio from the task offloading request;

[0012] Determining, based on the task offloading request, a transmission duration of an offloading link for offloading the task to be offloaded;

[0013] Based on a preset genetic algorithm, the task offloading request and the transmission duration, the initial allocation ratio is optimized to determine the task allocation ratio, and the bandwidth allocation ratio corresponding to the task allocation ratio is determined.

[0014] In one embodiment, the offloading link includes a first link forwarded to the edge MBS through a drone relay, a second link directly offloaded to the edge SBS, and a third link that forwards the to-be-offloaded task offloaded to the SBS to the edge MBS. The step of optimizing the initial allocation ratio based on a preset genetic algorithm, the task offloading request, and the transmission duration to determine the task allocation ratio includes:

[0015] Based on the task offloading request, determine a first transmission duration of the first link, a second transmission duration of the second link, a third transmission duration of the third link, a first processing duration of the edge SBS processing the corresponding task to be processed, and a second processing duration of the edge MBS processing the corresponding task to be processed;

[0016] The initial allocation ratio is optimized based on a preset genetic algorithm in combination with the first transmission duration, the second transmission duration, the third transmission duration, the first processing duration and the second processing duration to determine the task allocation ratio.

[0017] In one embodiment, the step of calling a preset drone relay to unload the to-be-unloaded tasks to the first target MEC node or the second target MEC node in parallel according to the task allocation ratio and the bandwidth allocation ratio includes:

[0018] Based on the task allocation ratio, the to-be-offloaded task is divided into a first offloading task to be offloaded to the first target MEC node, and a second offloading task to be offloaded to the second target MEC node;

[0019] Based on the bandwidth allocation ratio, calling a preset drone relay to offload the first offload task to the first target MEC node according to a preset offload method, wherein the preset offload method is a parallel transmission method of off-chain and on-chain based on blockchain;

[0020] Or based on the bandwidth allocation ratio, the second offloading task is offloaded to the second target MEC node according to the preset offloading method.

[0021] In one embodiment, after the step of calling a preset drone relay to unload the to-be-unloaded tasks to the first target MEC node or the second target MEC node in parallel according to the task allocation ratio and the bandwidth allocation ratio, the step includes:

[0022] Obtaining a first result of blockchain verification of the first offloading task by the first target MEC node and a second result of blockchain verification of the second offloading task by the second target MEC node;

[0023] The first result and the second result are packaged into a verification block, and the verification block is recorded on the blockchain.

[0024] In one embodiment, the step of determining the task allocation ratio and the bandwidth allocation ratio based on the task offloading request includes:

[0025] Based on the task offloading request, determine the Los probability and NLos probability of the task to be offloaded to each drone link;

[0026] Based on the Los probability and the NLos probability, determine the initial channel gain from the transmitting node that transmits the task to be offloaded to each of the UAV links, and the forwarding channel gain from each of the UAV links to the edge MBS;

[0027] Identifying a minimum initial gain from each of the initial channel gains, and identifying a minimum forwarding gain from each of the forwarding channel gains;

[0028] The maximum gain is identified from the minimum initial gain and the minimum forwarding gain, and the drone link corresponding to the maximum gain is calibrated as a preset drone relay.

[0029] In addition, to achieve the above-mentioned purpose, the present application also proposes a task offloading device for a computing power network, wherein the task offloading device for the computing power network comprises:

[0030] An acquisition module, configured to acquire, after receiving a task offloading request, the task to be offloaded, the first target MEC node in the edge MBS, and the second target MEC node in the edge SBS;

[0031] a determination module, configured to determine a task allocation ratio and a bandwidth allocation ratio based on the task offloading request, wherein the task allocation ratio is a task ratio of offloading the task to be offloaded to the first target MEC node and the second target MEC node, and the bandwidth allocation ratio is a bandwidth occupancy ratio of the edge MBS and the edge SBS;

[0032] The unloading module is used to call a preset drone relay to unload the to-be-unloaded tasks in parallel to the first target MEC node or the second target MEC node according to the task allocation ratio and the bandwidth allocation ratio.

[0033] In addition, to achieve the above-mentioned purpose, the present application also proposes a task offloading device for a computing power network, the device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the task offloading method for the computing power network as described above.

[0034] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the task offloading method of the computing power network as described above are implemented.

[0035] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the task offloading method of the computing power network as described above.

[0036] One or more technical solutions proposed in this application have at least the following technical effects:

[0037] By setting MBS (Macro Base Station) and SBS (Small Base Station) at the edge of the computing power network, after receiving the task offloading request, the first target MEC node that needs to receive the task to be offloaded is determined from the edge MBS, and the second target MEC node that receives the task to be offloaded is determined from the edge SBS, thereby avoiding offloading the task to be offloaded to the dense MEC nodes. Since the delay of unloading the task to be offloaded to the first target MEC node or the second target MEC node is different, in order to minimize the unloading delay, it is necessary to determine the task allocation ratio of unloading the task to be offloaded to the first target MEC node or the second target MEC node, that is, unloading a part of the tasks to be offloaded to the first target MEC node, and unloading the other part of the tasks to be offloaded to the second target MEC node, so as to reduce the delay of unloading all the tasks to be offloaded to the shortest. Finally, according to the task allocation ratio, the preset drone relay is used to unload the task to the first target MEC node or the second target MEC node, so as to avoid calling the preset drone relay to unload the task in time when the ground relay communication quality is poor, so as to reduce the delay. That is, by offloading the task to be offloaded to the first target MEC node in the edge MBS or the second target MEC node in the edge SBS, the concentration of MEC nodes is avoided, and the MEC nodes are deployed on the distributed nodes of the wireless backhaul by using drone relays, and the delay required for the transmission offloading task is minimized through the task allocation ratio, thereby reducing the delay of task offloading. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0039] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0040] Figure 1 A flowchart of the first embodiment of the method for offloading tasks from a computing network of the present application;

[0041] Figure 2 A schematic diagram of the task intelligent offloading process in actual operation provided by the task offloading method of the computing power network of this application;

[0042] Figure 3 A flowchart diagram of the second embodiment of the method for offloading tasks from a computing network of the present application;

[0043] Figure 4 A schematic diagram of the genetic algorithm flow provided for the task offloading method of the computing power network of this application;

[0044] Figure 5 A flowchart diagram of the second embodiment of the method for offloading tasks from a computing network of the present application;

[0045] Figure 6 A schematic diagram of the structure of the end-to-edge collaborative blockchain provided for the task offloading method of the computing power network of this application;

[0046] Figure 7 This is a schematic diagram of the structure of the task offloading system of the computing power network in this application;

[0047] Figure 8 This is a schematic diagram of the module structure of a task offloading device of a computing power network according to an embodiment of the present application;

[0048] Fig. 9 A schematic diagram of the device structure of the hardware operating environment involved in the task offloading method of the computing power network in the embodiment of the present application.

[0049] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0050] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0051] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0052] The main solution of the embodiment of the present application is: after receiving the task offloading request, the network management platform obtains the task to be offloaded, the first target MEC node in the edge MBS and the second target MEC node in the edge SBS; based on the task offloading request, the task allocation ratio and the bandwidth allocation ratio are determined, the task allocation ratio is the task ratio of offloading the task to be offloaded to the first target MEC node and the second target MEC node, and the bandwidth allocation ratio is the bandwidth occupancy ratio of the edge MBS and the edge SBS; according to the task allocation ratio and the bandwidth allocation ratio, the preset drone relay is called to unload the task to be offloaded in parallel to the first target MEC node or the second target MEC node.

[0053] In this embodiment, for ease of description, the following description is made with the network management platform as the execution entity.

[0054] As the computing power requirements of intelligent applications become more and more stringent, a single edge node cannot meet the computing needs of intelligent applications. The collaboration between MEC nodes reduces the task processing delay and processing cost, which can effectively improve resource utilization, especially in wireless networks. The allocation of computing power resources and bandwidth resources needs to be considered together. Currently, in distributed computing power networks, the deployment of MEC servers is too centralized and is not deployed on distributed nodes through wireless backhaul, resulting in a long delay in task offloading.

[0055] The present application provides a solution, which sets MBS and SBS at the edge of the computing power network. After receiving the task offloading request, the first target MEC node that needs to receive the task to be offloaded is determined from the edge MBS, and the second target MEC node that receives the task to be offloaded is determined from the edge SBS, thereby avoiding offloading the task to be offloaded to dense MEC nodes. Since the delay of unloading the task to be offloaded to the first target MEC node or the second target MEC node is different, in order to minimize the unloading delay, it is necessary to determine the task allocation ratio for unloading the task to be offloaded to the first target MEC node or the second target MEC node, that is, unload a part of the tasks to be offloaded to the first target MEC node, and unload the other part of the tasks to be offloaded to the second target MEC node, so as to reduce the delay of unloading all the tasks to be offloaded to the shortest. Finally, according to the task allocation ratio, the preset drone relay is used to unload the task to the first target MEC node or the second target MEC node, so as to avoid calling the preset drone relay to unload the task in time when the ground relay communication quality is poor, so as to reduce the delay. That is, by offloading the task to be offloaded to the first target MEC node in the edge MBS or the second target MEC node in the edge SBS, the concentration of MEC nodes is avoided, and the MEC nodes are deployed on the distributed nodes of the wireless backhaul by using drone relays, and the delay required for the transmission offloading task is minimized through the task allocation ratio, thereby reducing the delay of task offloading.

[0056] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a network management platform, etc. The following takes the network management platform as an example to illustrate this embodiment and the following embodiments.

[0057] Based on this, the embodiment of the present application provides a method for offloading tasks of a computing network, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the task offloading method of the computing power network of the present application.

[0058] In this embodiment, the task offloading method of the computing power network includes steps S10 to S30:

[0059] Step S10, after receiving the task offloading request, obtaining the task to be offloaded, the first target MEC node in the edge MBS and the second target MEC node in the edge SBS;

[0060] It should be noted that the task offloading request may be a request to trigger the start of a network task, which may include the computing power network node to be offloaded and the basic information of the node, and the computing power network may be a central cloud. The task to be offloaded may be a processing task that needs to be offloaded by the computing power network involved in the task offloading request. The edge may be a network node closer to the data source. The edge MBS may be a macro base station in the edge network node. The edge SBS may be a micro base station in the edge network node. The first target MEC node is a MEC server selected from the macro base station to receive the task to be offloaded. The second target MEC node is a MEC server selected from the micro base station to receive the task to be offloaded.

[0061] In addition, it should be noted that macro base stations can provide omnidirectional coverage and are suitable for areas with dispersed traffic such as suburbs. They have a larger coverage area and higher power. Micro base stations are small wireless access devices with small size, small coverage area, and relatively low number of users.

[0062] It can be understood that by setting up edge MBS and edge SBS in the edge network, and each edge MBS and edge SBS is equipped with a MEC server and a distributed ledger of the blockchain, by setting up edge MBS and edge SBS, the tasks to be offloaded can be dispersed as much as possible, so as to offload intensive computing tasks to multiple MEC servers, effectively avoiding the concentration of tasks to be offloaded.

[0063] Step S20: determining a task allocation ratio and a bandwidth allocation ratio based on the task offloading request, wherein the task allocation ratio is a task ratio of offloading the task to be offloaded to the first target MEC node and the second target MEC node, and the bandwidth allocation ratio is a bandwidth occupancy ratio of the edge MBS and the edge SBS;

[0064] It is understandable that since the spare computing power of each MEC server is limited and the signal gain of each MEC server is also different, in order to evenly unload the tasks to be unloaded to the first target MEC nodes and the second target ME nodes, so that each target MEC node (first target MEC node and second target ME node) can complete the tasks to be unloaded in the shortest time, it is necessary to determine the task ratio (task allocation ratio) of the first target ME node and the second target MEC node.

[0065] It is understandable that since the total bandwidth required to process a certain amount of tasks to be offloaded is certain, in order to ensure that the time to complete the tasks to be offloaded is the shortest, it is also necessary to adjust the bandwidth occupancy ratio of each edge MBS and each edge SBS accordingly when determining the task allocation ratio to ensure that the tasks to be offloaded can be completely transmitted to the corresponding target MEC node, thereby reducing the total delay of task offloading.

[0066] Step S30: According to the task allocation ratio and the bandwidth allocation ratio, a preset drone relay is called to parallelly offload the tasks to be offloaded to the first target MEC node or the second target MEC node.

[0067] It should be noted that the preset drone relay can be a communication model composed of drones, that is, the communication model is used as a transfer station between the ground network equipment and the edge MBS.

[0068] It is understandable that the ground MEC network cannot provide computing services in remote areas or in emergency situations and is easily destroyed by natural disasters such as typhoons and earthquakes. In addition, the wireless link is fragile and cannot guarantee the service quality of users in harsh transmission environments. Therefore, by establishing a communication model of drone-assisted mobile edge computing network, when the ground transmission path is unavailable or the communication quality is poor, the best drone relay is selected to offload the tasks to be offloaded to the MEC server to avoid the long communication time caused by poor communication quality, thereby reducing the communication delay.

[0069] In the specific implementation, refer to Figure 2 In actual operation, the process of intelligent task unloading can be as follows: after receiving the task unloading request sent by the user, first verify the user's identity; determine whether there are idle resources on the transaction management platform, if so, trigger the smart contract for intelligent unloading, if not, enter the transaction pool queue; trigger the adaptive genetic algorithm for intelligent unloading of user tasks, calculate the MEC node for task unloading, task allocation ratio, and communication bandwidth allocation ratio; the user saves the original data of the task to be unloaded in the local database, and the corresponding task summary consensus is uploaded to the chain; through the on-chain and off-chain collaboration, the original data and summary are transmitted off-chain, and the task summary is verified on-chain to ensure the consistency and reliability of the task data, and the task is unloaded to the designated MEC node. In order to ensure the accuracy of the transmission of the unloaded task, after unloading the task to the designated MEC node, the task completion can also be calculated, and the MEC node generates a result summary, which is summarized to the MEC representative node with the highest reputation value; the MEC representative node packages the result summary into a block in the form of resource transaction information and verifies the broadcast; determine whether the execution of the PBFT consensus process based on reputation evaluation is successful, if so, the process ends, if not, the task enters the transaction pool.

[0070] Optionally, before step S10, the method may further include:

[0071] Based on the task offloading request, determine the Los probability and NLos probability of the task to be offloaded to each drone link;

[0072] Based on the Los probability and the NLos probability, determine the initial channel gain from the transmitting node that transmits the task to be offloaded to each of the UAV links, and the forwarding channel gain from each of the UAV links to the edge MBS;

[0073] Identifying a minimum initial gain from each of the initial channel gains, and identifying a minimum forwarding gain from each of the forwarding channel gains;

[0074] The maximum gain is identified from the minimum initial gain and the minimum forwarding gain, and the drone link corresponding to the maximum gain is calibrated as a preset drone relay.

[0075] It should be noted that Los (Line-of-Sight) is a straight-line transmission path between two communication devices, in which there are no obstacles or interference that affect the propagation of the signal.

[0076] Non-Line-of-Sight (NLOS) refers to the situation in which the signal propagation path in wireless communication is blocked by obstacles and cannot be directly transmitted in a straight line between two points. The Loss probability is the probability that the transmission process of the task to be offloaded is line-of-sight. The NLos probability is the probability that the transmission process of the task to be offloaded is non-line-of-sight. The channel gain is the ratio of the increase in the amplitude of the signal after passing through the channel during the transmission process.

[0077] It is understandable that in the actual communication environment, there are various obstructions, such as high-rise buildings, trees, etc., and the communication links have LoS and NLoS situations. The higher the channel gain, the greater the transmission quality of the channel. Therefore, the drone link with the largest channel gain can be selected as the preset drone relay to improve the reliability of data transmission.

[0078] The present embodiment provides a task offloading method for a computing power network. By setting an MBS and an SBS at the edge of the computing power network, after receiving a task offloading request, a first target MEC node that needs to receive the task to be offloaded is determined from the edge MBS, and a second target MEC node that receives the task to be offloaded is determined from the edge SBS, thereby avoiding offloading the task to be offloaded to dense MEC nodes. Since the delay of unloading the task to be offloaded to the first target MEC node or the second target MEC node is different, in order to minimize the offloading delay, it is necessary to determine the task allocation ratio for offloading the task to be offloaded to the first target MEC node or the second target MEC node, that is, a part of the tasks to be offloaded is offloaded to the first target MEC node, and another part of the tasks to be offloaded is offloaded to the second target MEC node, so as to reduce the delay of unloading all the tasks to be offloaded to the shortest. Finally, according to the task allocation ratio, the preset drone relay is used to offload the task to the first target MEC node or the second target MEC node, so as to avoid calling the preset drone relay to unload the task in time when the ground relay communication quality is poor, so as to reduce the delay. That is, by offloading the task to be offloaded to the first target MEC node in the edge MBS or the second target MEC node in the edge SBS, the concentration of MEC nodes is avoided, and the MEC nodes are deployed on the distributed nodes of the wireless backhaul by using drone relays, and the delay required for the transmission offloading task is minimized through the task allocation ratio, thereby reducing the delay of task offloading.

[0079] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can refer to the above introduction, and will not be repeated later. Figure 3 , step S20 also includes steps S21 to S23:

[0080] Step S21, extracting an initial allocation ratio from the task offloading request;

[0081] Step S22, based on the task offloading request, determining the transmission duration of the offloading link required to offload the task to be offloaded;

[0082] Step S23, based on a preset genetic algorithm, the task offloading request and the transmission duration, the initial allocation ratio is optimized to determine the task allocation ratio, and the bandwidth allocation ratio corresponding to the task allocation ratio is determined.

[0083] It should be noted that the initial allocation ratio can be a task allocation ratio generated according to historical records, and the task allocation ratio needs to be adjusted according to the current actual situation. The unloading link includes a first link forwarded to the edge MBS through a drone relay, a second link directly unloaded to the edge SBS, and a third link that forwards the task to be unloaded to the SBS to the edge MBS. The transmission duration includes the first transmission duration required for transmitting the corresponding task to be unloaded using the first link, the second transmission duration required for transmitting the corresponding task to be unloaded using the second link, and the third transmission duration required for transmitting the corresponding task to be unloaded using the third link. The preset genetic algorithm is an adaptive genetic algorithm, in which the genetic algorithm is a search algorithm that simulates natural selection and genetics principles, and is mainly used to solve optimization problems. Therefore, it can be used in this embodiment to optimize the task allocation ratio. When facing tasks with high latency requirements, it can speed up the convergence speed and reduce the calculation delay.

[0084] It can be understood that the preset genetic algorithm is used to solve the computing task allocation ratio offloaded to the edge MBS, the computing task allocation ratio offloaded from the edge SBS to the edge MBS, and the communication bandwidth allocation ratio to determine the offloading scheme with the minimum total delay. The preset genetic algorithm can be used to speed up the optimization speed and further reduce the overall delay of task offloading.

[0085] It is understandable that in the optimization search process, according to the convergence speed, the control parameters such as the crossover rate, mutation rate, and the number of individuals are dynamically adjusted, and a fast-rise and slow-fall method is adopted. When the convergence speed slows down, the number of individuals, the crossover rate, and the mutation rate are quickly increased, and when the convergence speed becomes faster, the number of individuals, the crossover rate, and the mutation rate are slowly reduced. This can better adapt to the current search state and problem characteristics, and in the crossover process, the single-point crossover and arithmetic crossover are used in combination to efficiently increase the population diversity, thereby making the task allocation ratio and bandwidth allocation ratio obtained by the final optimization more reasonable, and using the task allocation ratio and bandwidth allocation ratio determined by multiple optimization schemes to unload the tasks to be unloaded can minimize the unloading delay.

[0086] It can be understood that in order to speed up the task processing rate, a part of the tasks to be offloaded can be transmitted to the first target MEC node through the first link, and another part of the tasks to be offloaded can be transmitted to the second target MEC node through the second link, and then processed by the second target MEC node or partially forwarded to the first target MEC node for processing through the third link. Since different link channels are allocated different frequency bands, there will be no co-frequency interference when the offloading links are run in parallel, and the processing rate of the tasks to be offloaded can also be accelerated.

[0087] In the specific implementation, refer to Figure 4, initialize a population of K individuals, each individual consists of α, β, η, that is, the three variables of the optimization problem P1, satisfying constraints C1~C3, initializing the number of iterations t=0, the maximum number of iterations T, the initialization crossover rate is 0.5, and the mutation rate is 0.01; take the objective function of the optimization problem P1 as the fitness, and calculate the fitness of each individual Fit k ; Set the probability of an individual being selected to be proportional to the fitness; then select a corresponding number of individuals based on the crossover rate to form a parent population with excellent genes; remove the individual with the highest fitness in the parent generation, pair the individual with the highest fitness among the remaining individuals with a random individual for single-point crossover, and pair individuals with similar fitness for arithmetic crossover to form a new generation population; perform random mutations on the structure of the individuals in the new generation population according to the mutation rate, that is, perform random mutations on α, β, η that satisfy constraints C1~C3; take the parent population and the new generation population as the new population, calculate the individual fitness and average fitness, if the fitness increases rapidly with the number of iterations, it can be considered that the convergence speed is fast, then reduce the crossover rate and mutation rate through the adaptive mechanism, otherwise increase the crossover rate and mutation rate; judge whether the fitness of the optimal individual is stable within a few iterations, if so, it can be considered to be converged and the iteration ends; judge whether the number of iterations reaches the upper limit, if so, end the iteration.

[0088] Among them, problem P1 is:

[0089]

[0090] stC1:0#a 1

[0091] C2:0#b 1

[0092] C3:0#h 1

[0093] C1 is the constraint α on the proportion of computing tasks offloaded from users to MBS through the optimal UAV relay; C2 is the constraint β on the proportion of computing tasks offloaded from SBS to MBS; C3 is the constraint η on the proportion of communication bandwidth allocation, t u,s represents the time when the user end offloads part of the tasks to be offloaded to the edge SBS; t s represents the first processing time of the edge SBS processing the corresponding pending task; t s,M represents the time when the edge SBS offloads part of the tasks to the edge MBS; t R Indicates the time when the user end offloads part of the tasks to be offloaded to the MBS through the preset drone relay; t M Indicates the second processing duration of the edge MBS processing the corresponding task to be processed.

[0094] Further, step S23 includes:

[0095] Based on the task offloading request, determine a first transmission duration of the first link, a second transmission duration of the second link, a third transmission duration of the third link, a first processing duration of the edge SBS processing the corresponding task to be processed, and a second processing duration of the edge MBS processing the corresponding task to be processed;

[0096] The initial allocation ratio is optimized based on a preset genetic algorithm in combination with the first transmission duration, the second transmission duration, the third transmission duration, the first processing duration and the second processing duration to determine the task allocation ratio.

[0097] It can be understood that through the adaptive genetic algorithm, parameters such as the crossover rate, mutation rate, and number of individuals can be controlled and optimized during the iteration process, so that the optimization problem can converge quickly and reach an approximate optimal solution. Therefore, the task allocation ratio and bandwidth allocation ratio obtained by the final optimization can be made more reasonable.

[0098] Based on the first and second embodiments of the present application, in the third embodiment of the present application, the same or similar contents as those in the above embodiments can be referred to the above introduction, and will not be described in detail later. Figure 5 , step S30 also includes steps S31 to S33:

[0099] Step S31: dividing the to-be-offloaded task into a first offload task to be offloaded to the first target MEC node and a second offload task to be offloaded to the second target MEC node based on the task allocation ratio;

[0100] Step S32: Based on the bandwidth allocation ratio, calling a preset drone relay to offload the first offload task to the first target MEC node according to a preset offload method, wherein the preset offload method is a parallel transmission method of off-chain and on-chain based on blockchain;

[0101] Step S33, or based on the bandwidth allocation ratio, offloading the second offloading task to the second target MEC node according to the preset offloading method.

[0102] It should be noted that on-chain refers to the state where data is recorded in the blockchain network. Off-chain refers to the state where data is not directly stored or processed in the blockchain network. The parallel transmission method of on-chain and off-chain can be to transmit the task consensus through the blockchain through the on-chain transmission method, and simultaneously transmit the complete task data directly.

[0103] It should be noted that the chain only stores data summaries sufficient to ensure data consistency, such as task identifiers, user identifiers, and summaries indicating uninstallation results. The off-chain database stores complete task lists, user information, user behavior records, node information, node behavior records, transaction feedback, etc.

[0104] It is understandable that the use of blockchain technology provides a safe and reliable platform for the transaction of multi-dimensional resources such as computing power resources and communication bandwidth resources of distributed computing power networks. The use of decentralized identity authentication technology and consensus algorithms can improve the reliability of the source of transaction information and enhance the traceability and security of transaction information.

[0105] Optionally, after step S30, the task offloading method of the computing power network may further include:

[0106] Obtaining a first result of blockchain verification of the first offloading task by the first target MEC node and a second result of blockchain verification of the second offloading task by the second target MEC node;

[0107] The first result and the second result are packaged into a verification block, and the verification block is recorded on the blockchain.

[0108] It is understandable that in the process of task offloading, multiple MEC nodes need to participate. If each participating MEC node participates in the consensus of the result summary, it will lead to low efficiency of the system. Therefore, this paper proposes to select the node with the best reputation as the representative to reach consensus on the results.

[0109] In the specific implementation, the user initiates a computing offloading request, performs identity authentication, triggers a smart contract, and uses an adaptive genetic algorithm to intelligently offload the user's task, determine the best drone relay, MEC node for task offloading, task allocation ratio, and communication bandwidth allocation ratio; the user saves the original task data in the local database and uploads the corresponding task summary consensus to the chain; the user transmits the plaintext data and signature of the task to multiple MEC nodes in parallel off the chain. The MEC node verifies the signature through the blockchain; after the computing task is completed, the MEC node summarizes the calculation results to the MEC node with the highest reputation value, and uploads the offloading result summary to the chain through the PBFT consensus algorithm. The offloading results are recorded on the blockchain in the form of multi-dimensional resource transactions.

[0110] Among them, the structure of the end-edge collaborative blockchain is shown in Figure 6 The terminal layer is composed of various IoT devices, which are resource-constrained devices responsible for collecting raw data and do not deploy blockchain; the user layer is composed of servers and hosts held by users, which can be used as collection transfer stations to package filtered raw data into tasks and require the deployment of blockchain; the edge layer is composed of MEC servers on MBS and SBS, which can provide multi-dimensional resources and require the deployment of blockchain.

[0111] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the task offloading method of the computing network of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0112] This application also provides a task offloading system for computing network, please refer to Figure 7 The task offloading system of the computing network is a distributed computing network architecture based on blockchain, which consists of a blockchain network, a mobile edge computing network, and a drone relay network. The mobile edge computing network consists of macro base stations and micro base stations, and both are equipped with MEC servers and distributed ledgers of blockchain. The drone relay network consists of N drones.

[0113] This application also provides a task offloading device for a computing network, please refer to Figure 8 , the task offloading device of the computing power network includes:

[0114] The acquisition module 10 is used to acquire the task to be offloaded, the first target MEC node in the edge MBS and the second target MEC node in the edge SBS after receiving the task offloading request;

[0115] A determination module 20 is used to determine a task allocation ratio and a bandwidth allocation ratio based on the task offloading request, wherein the task allocation ratio is a task ratio of offloading the task to be offloaded to the first target MEC node and the second target MEC node, and the bandwidth allocation ratio is a bandwidth occupancy ratio of the edge MBS and the edge SBS;

[0116] The unloading module 30 is used to call a preset drone relay to unload the to-be-unloaded tasks in parallel to the first target MEC node or the second target MEC node according to the task allocation ratio and the bandwidth allocation ratio.

[0117] Optionally, the determination module 20 is also used to extract an initial allocation ratio from the task offloading request; determine the transmission duration of the offloading link for unloading the task to be offloaded based on the task offloading request; optimize the initial allocation ratio based on a preset genetic algorithm, the task offloading request and the transmission duration, determine the task allocation ratio, and determine the bandwidth allocation ratio corresponding to the task allocation ratio.

[0118] Optionally, the offloading link includes a first link forwarded to the edge MBS via a drone relay, a second link directly offloaded to the edge SBS, and a third link forwarding the to-be-offloaded task offloaded to the SBS to the edge MBS;

[0119] The determination module 20 is also used to determine, based on the task offloading request, a first transmission duration of the first link, a second transmission duration of the second link, a third transmission duration of the third link, a first processing duration of the edge SBS processing the corresponding task to be processed, and a second processing duration of the edge MBS processing the corresponding task to be processed; based on a preset genetic algorithm combined with the first transmission duration, the second transmission duration, the third transmission duration, the first processing duration and the second processing duration, the initial allocation ratio is optimized to determine the task allocation ratio.

[0120] Optionally, the unloading module 30 is further used to divide the task to be unloaded into a first unloading task to be unloaded to the first target MEC node and a second unloading task to be unloaded to the second target MEC node based on the task allocation ratio; based on the bandwidth allocation ratio, call a preset drone relay to unload the first unloading task to the first target MEC node according to a preset unloading method, and the preset unloading method is a parallel transmission method of off-chain and on-chain based on blockchain; or based on the bandwidth allocation ratio, unload the second unloading task to the second target MEC node according to the preset unloading method.

[0121] Optionally, the unloading module 30 is also used to obtain a first result of the blockchain verification of the first offloading task by the first target MEC node and a second result of the blockchain verification of the second offloading task by the second target MEC node; package the first result and the second result into a verification block, and record the verification block on the blockchain.

[0122] Optionally, the determination module 20 is also used to determine the Los probability and NLos probability of the task to be offloaded to each drone link based on the task offloading request; determine the initial channel gain from the transmitting node that transmits the task to be offloaded to each drone link, and the forwarding channel gain from each drone link to the edge MBS based on the Los probability and the NLos probability; identify the minimum initial gain from each initial channel gain, and identify the minimum forwarding gain from each forwarding channel gain; identify the maximum gain from the minimum initial gain and the minimum forwarding gain, and calibrate the drone link corresponding to the maximum gain as a preset drone relay.

[0123] The task offloading device of the computing power network provided in the present application adopts the task offloading method of the computing power network in the above embodiment, which can solve the technical problem that the deployment of MEC servers is too centralized, resulting in a long delay in task offloading. Compared with the prior art, the beneficial effects of the task offloading device of the computing power network provided in the present application are the same as the beneficial effects of the task offloading method of the computing power network provided in the above embodiment, and the other technical features of the task offloading device of the computing power network are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0124] The present application provides a task offloading device for a computing power network, the task offloading device for a computing power network comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the task offloading method for the computing power network in the above-mentioned embodiment one.

[0125] Reference below Fig. 9 , which shows a schematic diagram of the structure of a task offloading device of a computing power network suitable for implementing an embodiment of the present application. The task offloading device of the computing power network in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig. 9 The task offloading device of the computing power network shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0126] like Fig. 9As shown, the task offloading device of the computing power network may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 to the random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the task offloading device of the computing power network are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. The input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the task offloading device of the computing power network to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a task offloading device of a computing power network with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.

[0127] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0128] The task offloading device of the computing power network provided in the present application adopts the task offloading method of the computing power network in the above embodiment, which can solve the technical problem that the deployment of MEC servers is too centralized, resulting in a long delay in task offloading. Compared with the prior art, the beneficial effects of the task offloading device of the computing power network provided in the present application are the same as the beneficial effects of the task offloading method of the computing power network provided in the above embodiment, and the other technical features in the task offloading device of the computing power network are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0129] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0130] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0131] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the task offloading method of the computing power network in the above-mentioned embodiment.

[0132] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0133] The above-mentioned computer-readable storage medium may be included in the task offloading device of the computing power network; or it may exist independently without being assembled into the task offloading device of the computing power network.

[0134] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the task offloading device of the computing power network, the task offloading device of the computing power network: after receiving the task offloading request, obtains the task to be offloaded, the first target MEC node in the edge MBS and the second target MEC node in the edge SBS; based on the task offloading request, determines the task allocation ratio and the bandwidth allocation ratio, the task allocation ratio is the task ratio of offloading the task to be offloaded to the first target MEC node and the second target MEC node, and the bandwidth allocation ratio is the bandwidth occupancy ratio of the edge MBS and the edge SBS; according to the task allocation ratio and the bandwidth allocation ratio, calls the preset drone relay to parallelly offload the task to be offloaded to the first target MEC node or the second target MEC node.

[0135] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0136] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0137] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0138] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned task offloading method of the computing power network, which can solve the technical problem that the deployment of MEC servers is too centralized, resulting in a long delay in task offloading. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the task offloading method of the computing power network provided in the above-mentioned embodiment, and will not be repeated here.

[0139] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the task offloading method of the computing power network as described above.

[0140] The computer program product provided by this application can solve the technical problem that the deployment of MEC servers is too centralized, resulting in a long delay in task offloading. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the task offloading method of the computing power network provided in the above embodiment, which will not be repeated here.

[0141] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for offloading tasks from a computing network, characterized in that: The method includes: After receiving the task offloading request, obtain the task to be offloaded, the first target MEC node in the edge MBS, and the second target MEC node in the edge SBS; Based on the task offloading request, determine a task allocation ratio and a bandwidth allocation ratio, wherein the task allocation ratio is a task ratio of offloading the task to be offloaded to the first target MEC node and the second target MEC node, and the bandwidth allocation ratio is a bandwidth occupancy ratio of the edge MBS and the edge SBS; According to the task allocation ratio and the bandwidth allocation ratio, a preset drone relay is called to unload the tasks to be unloaded in parallel to the first target MEC node or the second target MEC node.

2. The method according to claim 1, characterized in that The step of determining the task allocation ratio and the bandwidth allocation ratio based on the task offloading request comprises: extracting an initial allocation ratio from the task offloading request; Determining, based on the task offloading request, a transmission duration of an offloading link required to offload the task to be offloaded; Based on a preset genetic algorithm, the task offloading request and the transmission duration, the initial allocation ratio is optimized to determine the task allocation ratio, and the bandwidth allocation ratio corresponding to the task allocation ratio is determined.

3. The method according to claim 2, characterized in that The offloading link includes a first link forwarded to the edge MBS through a drone relay, a second link directly offloaded to the edge SBS, and a third link that forwards the to-be-offloaded task offloaded to the SBS to the edge MBS. The step of optimizing the initial allocation ratio based on a preset genetic algorithm, the task offloading request and the transmission duration, and determining the task allocation ratio includes: Based on the task offloading request, determine a first transmission duration of the first link, a second transmission duration of the second link, a third transmission duration of the third link, a first processing duration of the edge SBS processing the corresponding task to be processed, and a second processing duration of the edge MBS processing the corresponding task to be processed; The initial allocation ratio is optimized based on a preset genetic algorithm in combination with the first transmission duration, the second transmission duration, the third transmission duration, the first processing duration and the second processing duration to determine the task allocation ratio.

4. The method according to claim 1, characterized in that The step of calling a preset drone relay to parallelly unload the to-be-unloaded tasks to the first target MEC node or the second target MEC node according to the task allocation ratio and the bandwidth allocation ratio comprises: Based on the task allocation ratio, the to-be-offloaded task is divided into a first offloading task to be offloaded to the first target MEC node, and a second offloading task to be offloaded to the second target MEC node; Based on the bandwidth allocation ratio, calling a preset drone relay to offload the first offload task to the first target MEC node according to a preset offload method, wherein the preset offload method is a parallel transmission method of off-chain and on-chain based on blockchain; Or based on the bandwidth allocation ratio, the second offloading task is offloaded to the second target MEC node according to the preset offloading method.

5. The method according to claim 4, characterized in that After the step of calling a preset drone relay to unload the to-be-unloaded tasks to the first target MEC node or the second target MEC node in parallel according to the task allocation ratio and the bandwidth allocation ratio, the following steps are included: Obtaining a first result of blockchain verification of the first offloading task by the first target MEC node and a second result of blockchain verification of the second offloading task by the second target MEC node; The first result and the second result are packaged into a verification block, and the verification block is recorded on the blockchain.

6. The method according to any one of claims 1 to 5, characterized in that: The step of determining the task allocation ratio and the bandwidth allocation ratio based on the task offloading request includes: Based on the task offloading request, determine the Los probability and NLos probability of the task to be offloaded to each drone link; Based on the Los probability and the NLos probability, determine the initial channel gain from the transmitting node that transmits the task to be offloaded to each of the UAV links, and the forwarding channel gain from each of the UAV links to the edge MBS; Identifying a minimum initial gain from each of the initial channel gains, and identifying a minimum forwarding gain from each of the forwarding channel gains; The maximum gain is identified from the minimum initial gain and the minimum forwarding gain, and the drone link corresponding to the maximum gain is calibrated as a preset drone relay.

7. A task offloading device for a computing network, characterized in that: The device comprises: An acquisition module, configured to acquire, after receiving a task offloading request, the task to be offloaded, the first target MEC node in the edge MBS, and the second target MEC node in the edge SBS; a determination module, configured to determine a task allocation ratio and a bandwidth allocation ratio based on the task offloading request, wherein the task allocation ratio is a task ratio of offloading the task to be offloaded to the first target MEC node and the second target MEC node, and the bandwidth allocation ratio is a bandwidth occupancy ratio of the edge MBS and the edge SBS; The unloading module is used to call a preset drone relay to unload the tasks to be unloaded in parallel to the first target MEC node or the second target MEC node according to the task allocation ratio and the bandwidth allocation ratio.

8. A task offloading device for a computing network, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the task offloading method of the computing power network as described in any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the task offloading method of the computing power network as described in any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the task offloading method of the computing power network as described in any one of claims 1 to 6 are implemented.

Images