A multi-user task offloading computing method, system, device and storage medium

Abstract

The application discloses a multi-user task offloading calculation method, system and device and a storage medium, belongs to the wireless communication technical field, and comprises the following steps: calculating the channel transmission rate of user task offloading to a small base station and the channel transmission rate of user task being forwarded to a macro base station through the small base station; calculating the transmission delay of user task offloading to the small base station and the transmission delay of user task being forwarded to the macro base station through the small base station according to the two channel transmission rates; calculating the processing delay of user task calculation at the small base station and the macro base station; inputting the two transmission delays and the two processing delays into a task offloading and calculation resource joint allocation model based on delay minimization which is constructed, and obtaining the optimal allocation scheme of MEC calculation resources in the small base station and the macro base station by solving; and based on the optimal allocation scheme, user task is offloaded to the small base station and the macro base station for calculation; the application reduces the total delay of user task processing through joint optimization of task offloading and calculation resource allocation.

Description

A multi-user task offloading calculation method, system, device and storage medium Technical Field

[0001] This invention relates to a multi-user task offloading calculation method, system, device, and storage medium, belonging to the field of wireless communication technology. Background Technology

[0002] In recent years, mobile edge computing (MEC) technology has attracted much attention in emerging fifth-generation (5G) mobile communication systems. MEC is a technology that combines cloud computing with mobile networks to provide substantial computing resources at the network edge, enabling remote execution of latency-sensitive and computationally intensive tasks, thereby significantly reducing user task execution latency. However, with the rapid development of wireless communication systems and the explosive growth in the number of mobile users, traditional edge computing offloading systems are overwhelmed, and problems such as high latency and limited computing resources still exist. Summary of the Invention

[0003] The purpose of this invention is to provide a multi-user task offloading computing method, system, device and storage medium to solve the problem of high latency caused by limited computing resources in the prior art.

[0004] To achieve the above objectives, the present invention employs the following technical solution:

[0005] In a first aspect, the present invention provides a multi-user task offloading calculation method, comprising:

[0006] Calculate the channel transmission rate of user tasks offloaded to small base stations and user tasks forwarded to macro base stations via small base stations;

[0007] Based on the transmission rates of the two channels, calculate the transmission delay of the user task being offloaded to the small base station and the transmission delay of the user task being forwarded to the macro base station through the small base station.

[0008] Calculate the processing latency of user tasks performed at small base stations and macro base stations;

[0009] The two transmission delays and two processing delays are input into the constructed task offloading and computing resource joint allocation model based on delay minimization, and the optimal allocation scheme of MEC computing resources in small base stations and macro base stations is obtained by solving the problem.

[0010] Based on the optimal allocation scheme, user tasks are offloaded to small base stations and macro base stations for computation.

[0011] In conjunction with the first aspect, the channel transmission rate of the user task offloaded to the small base station is further calculated using the following formula:

[0012]

[0013] in, User Offload the task to the small base station's transmit power. For users Channel gain with small base stations, For noise power, Indicates user The transmission bandwidth allocated between the base station and the small base station;

[0014] The channel transmission rate of the user task forwarded from the small base station to the macro base station is calculated using the following formula:

[0015]

[0016] in, Forwarding users for small base stations The transmit power allocated to the macro base station for the task. For small base stations to serve users The channel gain between the task forwarding to the macro base station Indicates that the small base station forwards the user The transmission bandwidth allocated to the macro base station for the task.

[0017] In conjunction with the first aspect, the transmission delay of the user task offloading to the small base station is further calculated using the following formula:

[0018] in, Indicates user The transmission latency of offloading tasks to small base stations, Indicates user The amount of data for the task Indicates user The task offloading to the channel transmission rate of the small base station;

[0019] The transmission delay of the user task forwarded from the small base station to the macro base station is calculated using the following formula:

[0020]

[0021] in, Indicates user The transmission delay of the task forwarded from the small base station to the macro base station, Indicates user The amount of tasks offloaded to macro base stations. Indicates user The task is to forward the channel transmission rate from the small base station to the macro base station.

[0022] In conjunction with the first aspect, the processing latency of the user task at the small base station is further calculated using the following formula:

[0023]

[0024] in, Indicates user The processing latency of the task being computed at the small base station, This represents the CPU frequency required to execute a 1-bit task. Small base stations are for users Allocated computing resources;

[0025] The processing latency of the user task at the macro base station is calculated using the following formula:

[0026]

[0027] in, Indicates user The processing latency of the task being computed at the macro base station, Macro base stations are for users Allocated computing resources.

[0028] In conjunction with the first aspect, further, the task offloading and computing resource joint allocation model based on latency minimization, when solving the problem, takes MEC computing resources as a constraint and minimizes the processing latency of multi-user tasks as the objective, introduces an auxiliary variable, and transforms the original problem into two sub-problems that are solved iteratively using an alternating optimization method.

[0029] In conjunction with the first aspect, the specific formula for the task offloading and computing resource joint allocation model based on latency minimization is as follows:

[0030]

[0031] st C1:

[0032] C2:

[0033] C3:

[0034] C4:

[0035] in, Indicates user The amount of data for the task Indicates user The amount of tasks offloaded to macro base stations. This represents the CPU frequency required to execute a 1-bit task. Indicates user The task offloading to the small base station's channel transmission rate, Small base stations are for users Allocated computing resources Indicates user The task is to forward the data from the small base station to the macro base station via the channel transmission rate. Macro base stations are for users The allocated computing resources are constrained by C1, which represents the MEC computing resource limit for small base stations, C2, which represents the MEC computing resource limit for macro base stations, and C3, which represents the computing task allocation limit. By jointly optimizing task allocation and computing resource allocation, the total system latency is minimized.

[0036] Secondly, the present invention also provides a multi-user task offloading computing system, comprising:

[0037] Channel transmission rate calculation module: used to calculate the channel transmission rate when user tasks are offloaded to small base stations and when user tasks are forwarded to macro base stations via small base stations;

[0038] Transmission delay calculation module: used to calculate the transmission delay of user tasks offloading to small base stations and the transmission delay of user tasks forwarded to macro base stations through small base stations, based on the transmission rates of the two channels respectively;

[0039] Processing latency calculation module: used to calculate the processing latency of user tasks performed at small base stations and macro base stations;

[0040] Resource allocation module: used to input the two transmission delays and two processing delays into the constructed task offloading and computing resource joint allocation model based on delay minimization, and solve for the optimal allocation scheme of MEC computing resources in small base stations and macro base stations;

[0041] Offload Calculation Module: Used to offload user tasks to small base stations and macro base stations for calculation based on the optimal allocation scheme.

[0042] Thirdly, the present invention also provides a multi-user task offloading computing device, including a processor and a storage medium;

[0043] The storage medium is used to store instructions;

[0044] The processor is configured to operate according to the instructions to perform the steps of the method according to any one of the first aspects.

[0045] Fourthly, the present invention also provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the method described in any of the first aspects.

[0046] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0047] This invention provides a multi-user task offloading computation method, system, device, and storage medium. When a user has a task to complete, the task is offloaded to a small base station. Part of the task is computed on the MEC server at the small base station, and the remaining task is forwarded by the small base station to the MEC server at the macro base station for computation. This invention constructs a joint allocation model for task offloading and computing resources based on latency minimization. With MEC computing resources as constraints and minimizing the processing latency of multi-user tasks as the goal, this invention significantly reduces the total latency of user task processing by jointly optimizing task offloading and computing resource allocation compared to equal task allocation and equal computing resource allocation schemes. Attached Figure Description

[0048] Figure 1 is a flowchart of a multi-user task offload calculation method provided in an embodiment of the present invention;

[0049] Figure 2 is a schematic diagram of the heterogeneous network edge computing system provided in an embodiment of the present invention;

[0050] Figure 3 is a simulation comparison diagram of the relationship between the total system latency and the single-user task volume provided in the embodiment of the present invention. Detailed Implementation

[0051] The present invention will be further described below with reference to the accompanying drawings. The following embodiments are only used to illustrate the technical solution of the present invention more clearly, and should not be used to limit the scope of protection of the present invention.

[0052] Example 1

[0053] The present invention proposes a multi-user task offloading computation method for a heterogeneous network mobile edge computing (MEC) system as shown in Figure 2. The system includes macro base stations (MBS), small base stations (SBS), and users. Both MBS and SBS are equipped with MEC servers, and users have computationally intensive tasks.

[0054] Macro base stations are far from users and connected to the power grid, while small base stations are located closer to user terminals but have limited computing resources. Each user has computationally intensive tasks, which are completed by offloading computation.

[0055] As shown in Figure 1, an embodiment of the present invention provides a multi-user task offloading calculation method, which includes the following steps:

[0056] S1. Calculate the channel transmission rate of user tasks offloaded to small base stations and user tasks forwarded to macro base stations via small base stations.

[0057] Obtain the channel gain and calculate the transmission rates of the two channels based on the channel gain.

[0058] The channel transmission rate for user tasks offloaded to small base stations is calculated using the following formula:

[0059]

[0060] in, For users The transmit power of the offloaded task to the small base station. For users Channel gain with small base stations, For noise power, Indicates user The transmission bandwidth allocated between the base station and the small base station. Taking equal bandwidth allocation as an example, here... ,in This represents the total bandwidth of SBS. This refers to the number of user terminals.

[0061] The channel transmission rate of user tasks forwarded from small base stations to macro base stations is calculated using the following formula:

[0062]

[0063] in, Forwarding users for small base stations The transmit power allocated to the macro base station for the task. For small base stations to serve users The channel gain between the task forwarding to the macro base station Indicates that the small base station forwards the user The transmission bandwidth allocated to the macro base station for the task. Taking equal bandwidth allocation as an example, here... ,in This represents the total bandwidth of MBS.

[0064] S2. Based on the two channel transmission rates, calculate the transmission delay of the user task being offloaded to the small base station and the transmission delay of the user task being forwarded to the macro base station through the small base station.

[0065] Since users are allocated orthogonal spectrum, and the spectrum between MBS and SBS is also orthogonal, transmission interference between users is not considered.

[0066] The transmission delay of user tasks offloading to small base stations is calculated using the following formula:

[0067] in, Indicates user The transmission latency of offloading tasks to small base stations, Indicates user The amount of data for the task Indicates user The task offloading to the channel transmission rate of the small base station;

[0068] The transmission delay of user tasks forwarded from small base stations to macro base stations is calculated using the following formula:

[0069]

[0070] in, Indicates user The transmission delay of the task forwarded from the small base station to the macro base station, Indicates user The amount of tasks offloaded to macro base stations. Indicates user The task is to forward the channel transmission rate from the small base station to the macro base station.

[0071] S3. Calculate the processing latency of user tasks at small base stations and macro base stations.

[0072] The processing latency of user tasks being computed at the small base station (the MEC server at the small base station completes the user task computation). (Some tasks) are calculated using the following formula:

[0073]

[0074] in, Indicates user The processing latency of the task being computed at the small base station, This represents the CPU frequency required to execute a 1-bit task. Small base stations are for users Allocated computing resources;

[0075] The processing latency of user tasks being computed at the macro base station (the MEC server at the macro base station completes the user task's computation). The remaining tasks are calculated using the following formula:

[0076]

[0077] in, Indicates user The processing latency of the task being computed at the macro base station, Macro base stations are for users Allocated computing resources.

[0078] S4. Input the two transmission delays and two processing delays into the constructed task offloading and computing resource joint allocation model based on delay minimization, and solve for the optimal allocation scheme of MEC computing resources in small base stations and macro base stations.

[0079] In this invention, the problem can be modeled as:

[0080]

[0081] st C1:

[0082] C2:

[0083] C3:

[0084] C4:

[0085] Among them, constraint C1 represents the computational resource limit of small base station MEC, constraint C2 represents the computational resource limit of macro base station MEC, and constraint C3 represents the computational task allocation limit; by jointly optimizing task allocation and computational resource allocation, the total system latency is minimized.

[0086] In this invention, the method for solving the problem is as follows:

[0087] First, introduce an auxiliary variable. Defined as:

[0088]

[0089] Therefore, the original problem can be transformed into:

[0090]

[0091] st C1:

[0092] C2:

[0093] C3:

[0094] C4:

[0095] C5:

[0096] C6:

[0097] Due to the introduction of auxiliary variables The original problem now includes two new constraints, C4 and C5.

[0098] Secondly, the original problem can be transformed into the following two subproblems, with the following steps:

[0099] For a given and Optimize variables and The corresponding subproblem can be expressed as:

[0100]

[0101] st C1:

[0102] C2:

[0103] C3:

[0104] C4:

[0105] This problem is a linear programming (LP) problem, and the KKT conditions can be obtained as follows:

[0106]

[0107]

[0108]

[0109]

[0110]

[0111]

[0112] The variables are thus derived. Closed-form solution:

[0113]

[0114]

[0115] For a given Optimize variables , , The subproblem can be expressed as:

[0116]

[0117] st C1:

[0118] C2:

[0119] C3:

[0120] C4:

[0121] C5:

[0122] Since both the objective function and constraints of this problem are convex functions, a convex optimization algorithm can be used to solve it.

[0123] Finally, the optimal solution to the original problem is obtained by iterative optimization of the two sub-problems.

[0124] The following is an example of a computer simulation of the invention. Assume each user has a computational task of the same size to process, divided into two parts: one part is computed on the SBS-side MEC server, and the other part is computed on the MBS-side MEC server. In the simulation example, the system has 10 terminal users. The channels for user terminals offloading to the SBS and the channels for the SBS forwarding tasks to the MBS both follow Rayleigh fading with a variance of 1. The channel bandwidth... and The value is 5MHz, representing the number of CPU cycles required per bit for a user terminal task. The values ​​are randomly generated following a uniform distribution between 400 cycles / bit and 600 cycles / bit, and the transmit power... and Both are 1W, and the channel noise power is 10. -14 w, the total computing resources of the MEC server at SBS 2×10 9 CPUcycles / s, total computing resources of the MEC server at MBS The value is 3×10 9CPU cycles / s. Figure 3 is a comparison between the heterogeneous wireless network offloading scheme proposed in this invention and the equal-task, equal-computation-resource-allocation offloading scheme. It can be seen that the heterogeneous wireless network offloading scheme proposed in this invention is significantly better than the equal-task, equal-computation-resource-allocation offloading scheme in terms of total system latency.

[0125] S5. Based on the optimal allocation scheme, the user tasks are offloaded to small base stations and macro base stations for calculation.

[0126] After obtaining the optimal allocation scheme in step S4, MEC computing resources are allocated to small base stations and macro base stations according to the optimal allocation scheme, and then user tasks are offloaded to small base stations and macro base stations for computing.

[0127] Example 2

[0128] An embodiment of the present invention provides a multi-user task offloading computing system, comprising:

[0129] Channel transmission rate calculation module: used to calculate the channel transmission rate when user tasks are offloaded to small base stations and when user tasks are forwarded to macro base stations via small base stations;

[0130] Transmission delay calculation module: used to calculate the transmission delay of user tasks offloading to small base stations and the transmission delay of user tasks forwarded to macro base stations through small base stations, based on the transmission rates of the two channels respectively;

[0131] Processing latency calculation module: used to calculate the processing latency of user tasks performed at small base stations and macro base stations;

[0132] Resource allocation module: used to input the two transmission delays and two processing delays into the constructed task offloading and computing resource joint allocation model based on delay minimization, and solve for the optimal allocation scheme of MEC computing resources in small base stations and macro base stations;

[0133] Offload Calculation Module: Used to offload user tasks to small base stations and macro base stations for calculation based on the optimal allocation scheme.

[0134] Example 3

[0135] An embodiment of the present invention provides a multi-user task offloading computing device, including a processor and a storage medium;

[0136] The storage medium is used to store instructions;

[0137] The processor is configured to operate according to the instructions to perform the steps of the following method:

[0138] Calculate the channel transmission rate of user tasks offloaded to small base stations and user tasks forwarded to macro base stations via small base stations;

[0139] Based on the transmission rates of the two channels, calculate the transmission delay of the user task being offloaded to the small base station and the transmission delay of the user task being forwarded to the macro base station through the small base station.

[0140] Calculate the processing latency of user tasks performed at small base stations and macro base stations;

[0141] The two transmission delays and two processing delays are input into the constructed task offloading and computing resource joint allocation model based on delay minimization, and the optimal allocation scheme of MEC computing resources in small base stations and macro base stations is obtained by solving the problem.

[0142] Based on the optimal allocation scheme, user tasks are offloaded to small base stations and macro base stations for computation.

[0143] Example 4

[0144] The computer-readable storage medium provided in this embodiment of the invention stores a computer program thereon, which, when executed by a processor, implements the steps of the following method:

[0145] Calculate the channel transmission rate of user tasks offloaded to small base stations and user tasks forwarded to macro base stations via small base stations;

[0146] Based on the transmission rates of the two channels, calculate the transmission delay of the user task being offloaded to the small base station and the transmission delay of the user task being forwarded to the macro base station through the small base station.

[0147] Calculate the processing latency of user tasks performed at small base stations and macro base stations;

[0148] The two transmission delays and two processing delays are input into the constructed task offloading and computing resource joint allocation model based on delay minimization, and the optimal allocation scheme of MEC computing resources in small base stations and macro base stations is obtained by solving the problem.

[0149] Based on the optimal allocation scheme, user tasks are offloaded to small base stations and macro base stations for computation.

[0150] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0151] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more blocks of the flowchart illustrations and / or one or more blocks of the block diagrams.

[0152] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0153] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.

[0154] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A multi-user task unloading calculation method, characterized in that, include: Calculate the channel transmission rate of user tasks offloaded to small base stations and user tasks forwarded to macro base stations via small base stations; Based on the transmission rates of the two channels, the transmission delay of the user task offloading to the small base station and the transmission delay of the user task forwarding to the macro base station via the small base station are calculated respectively; the processing delay of the user task performing calculations at the small base station and the macro base station are calculated; the two transmission delays and the two processing delays are input into the constructed joint allocation model of task offloading and computing resources based on delay minimization, and the optimal allocation scheme of task offloading and MEC computing resources is obtained by solving; based on the optimal allocation scheme, the user task is offloaded to the small base station and the macro base station for calculation; the specific formula of the joint allocation model of task offloading and computing resources based on delay minimization is as follows: ； st C1: ；C2: ；C3: ；C4: ;in, Indicates user The amount of data for the task Indicates user The amount of tasks offloaded to macro base stations. This represents the CPU frequency required to execute a 1-bit task. Indicates user The task offloading to the small base station's channel transmission rate, Small base stations are for users Allocated computing resources Indicates user The task is to forward the data from the small base station to the macro base station via the channel transmission rate. Macro base stations are for users The allocated computing resources are constrained by C1, which represents the MEC computing resource limit for small base stations, C2, which represents the MEC computing resource limit for macro base stations, and C3, which represents the computing task allocation limit. By jointly optimizing task allocation and computing resource allocation, the total system latency is minimized.

2. The multi-user task offloading calculation method according to claim 1, characterized in that, The channel transmission rate for the user task offloaded to the small base station is calculated using the following formula: ;in, User Offload the task to the small base station's transmit power. For users Channel gain with small base stations, For noise power, Indicates user The transmission bandwidth allocated between the small base station and the macro base station; the channel transmission rate of the user task forwarded from the small base station to the macro base station is calculated using the following formula: ;in, Forwarding user data for small base stations The transmit power allocated to the macro base station for the mission. For small base stations to serve users The channel gain between the task forwarding to the macro base station Indicates that the small base station forwards the user The transmission bandwidth allocated to the macro base station for the task.

3. The multi-user task offloading calculation method according to claim 2, characterized in that, The transmission delay of the user task offloading to the small base station is calculated using the following formula: ;in, Indicates user The transmission latency of offloading tasks to small base stations, Indicates user The amount of data for the task Indicates user The channel transmission rate at which the task is offloaded to the small base station; the transmission delay of the user task forwarded from the small base station to the macro base station is calculated using the following formula: ;in, Indicates user The transmission delay of the task forwarded from the small base station to the macro base station, Indicates user The amount of tasks that are forwarded from small base stations to macro base stations. Indicates user The task is to forward the channel transmission rate from the small base station to the macro base station.

4. The multi-user task offloading calculation method according to claim 3, characterized in that, The processing latency of the user task at the small base station is calculated using the following formula: ;in, Indicates user The processing latency of the task being computed at the small base station, This represents the CPU frequency required to execute a 1-bit task. Small base stations are for users The allocated computing resources; the processing latency of the user task at the macro base station is calculated using the following formula: ;in, Indicates user The processing latency of the task being computed at the macro base station, Macro base stations are for users Allocated computing resources.

5. The multi-user task offloading calculation method according to claim 1, characterized in that, The task offloading and computing resource joint allocation model based on latency minimization takes MEC computing resources as a constraint and minimizes the processing latency of multi-user tasks as the objective. It introduces an auxiliary variable and transforms the original problem into two sub-problems, which are then solved iteratively using an alternating optimization method.

6. A multi-user task offloading computing system, characterized in that, include: The module includes: a channel transmission rate calculation module for calculating the channel transmission rates of user tasks offloaded to small base stations and user tasks forwarded from small base stations to macro base stations; a transmission delay calculation module for calculating the transmission delay of user tasks offloaded to small base stations and user tasks forwarded from small base stations to macro base stations based on the two channel transmission rates; a processing delay calculation module for calculating the processing delay of user tasks at small base stations and macro base stations; and a resource allocation module for inputting the two transmission delays and two processing delays into a pre-constructed joint allocation model for task offloading and computing resources based on delay minimization, and solving for the optimal allocation scheme for task offloading and MEC computing resources. Offloading computation module: used to offload user tasks to small base stations and macro base stations for computation based on the optimal allocation scheme; wherein, the specific formula of the task offloading and computation resource joint allocation model based on latency minimization is: ;s.t. C1: ；C2: ；C3: ；C4: ;in, Indicates user The amount of data for the task Indicates user The amount of tasks offloaded to macro base stations. This represents the CPU frequency required to execute a 1-bit task. Indicates user The task offloading to the small base station's channel transmission rate, Small base stations are for users Allocated computing resources Indicates user The task is to forward the data from the small base station to the macro base station via the channel transmission rate. Macro base stations are for users The allocated computing resources are constrained by C1, which represents the MEC computing resource limit for small base stations, C2, which represents the MEC computing resource limit for macro base stations, and C3, which represents the computing task allocation limit. By jointly optimizing task allocation and computing resource allocation, the total system latency is minimized.

7. A multi-user task offloading computing device, characterized in that, It includes a processor and a storage medium; the storage medium is used to store instructions; the processor is used to operate according to the instructions to perform the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the steps of the method according to any one of claims 1 to 5.

Images