Methods and systems for minimizing latency in mobile edge computing networks in underground and sheltered spaces

Abstract

This invention relates to a method and system for minimizing latency in underground and sheltered space mobile edge computing networks. The method includes: constructing a static resource allocation calculation model in a wireless cellular network consisting of a base station supported by mobile edge computing and K users; transforming the static resource allocation calculation model into a convex optimization problem, and solving the convex optimization problem to obtain the optimal solution for dynamic computing and bandwidth allocation schemes among users, thereby minimizing system latency. This invention addresses the problem that traditional static schemes cannot fully utilize computing and bandwidth resources under the diversity of users and different channel conditions in underground and sheltered spaces. This invention can be widely applied in the field of communication signal processing technology.

Description

Technical Field

[0001] This invention relates to the field of communication signal processing technology, and in particular to a method and system for minimizing latency in mobile edge computing networks in underground and sheltered spaces. Background Technology

[0002] In the research on latency of mobile edge computing networks in underground and sheltered spaces, how to fully utilize computing and bandwidth resources is two crucial research focus. Underground and sheltered IoT devices have limited battery capacity and computing resources, making it difficult to handle intensive computing tasks with ultra-low latency requirements. Achieving this ideal requirement and Quality of Experience (QoE) necessitates the effective allocation of computing resources and system bandwidth.

[0003] Due to the diversity of users, improving the basic performance of all users cannot guarantee the quality of experience for individual users. How to minimize system latency and fully utilize joint computing and bandwidth resources has become a pressing technical problem to be solved. Summary of the Invention

[0004] To address the aforementioned problems, the present invention aims to provide a method and system for minimizing latency in mobile edge computing networks in underground and sheltered spaces. This method can solve the problem that traditional static solutions cannot fully utilize computing and bandwidth resources under the diverse user environments and different channel conditions in underground and sheltered spaces.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: a method for minimizing latency in underground and sheltered space mobile edge computing networks, comprising: constructing a static resource allocation calculation model in a wireless cellular network consisting of a base station supported by mobile edge computing and K users; transforming the static resource allocation calculation model into a convex optimization problem, solving the convex optimization problem, obtaining the optimal solution of the dynamic calculation and bandwidth allocation scheme among users, and minimizing system latency.

[0006] Furthermore, the construction of the static resource allocation calculation model includes:

[0007]

[0008] st c1:

[0009] c2:∑ k∈K C k ≤C BS ,

[0010] c3:∑ k∈K β k ≤1

[0011] c4:β k>0, k∈K,

[0012] Where, β=(β k ) k∈K Assign a proportional vector to the bandwidth, β k The bandwidth allocation ratio for user k; K represents the index set of all users; C represents the computing resource allocation for all users. k The computing resources allocated to user k, t k The latency for user k to complete the computation task; For user k, the uninstallation delay; For user k's processing delay, C represents the maximum latency limit for user k to complete the computation task. BS c1 represents the computing power of the BS; c2 represents the total delay for user k not exceeding its deadline; c3 represents the computing power constraint of the BS; and c4 describes the requirements for user bandwidth allocation.

[0013] Furthermore, the convex optimization problem is:

[0014]

[0015] st c2,c3,c4,

[0016] c6:

[0017] c7:

[0018] c8:

[0019] In the formula, D is the set of auxiliary variables, D = {D k} k∈K D k This is an auxiliary variable introduced to define the lower bound of the uplink transmission rate for user k; T = max k∈K t k .

[0020] Furthermore, the convex optimization problem is solved using CVX to obtain the optimal solution;

[0021] The optimal solution is the bandwidth allocation ratio for all users in the network, and the computing resources allocated by the edge server to all users.

[0022] Furthermore, the method for minimizing system latency based on the optimal solution includes:

[0023] Based on the bandwidth allocation ratio and the computing resources, the latency for users to complete computing tasks is calculated, and the user k with the minimum time required to complete the computing task is found. * ;

[0024] Based on the computing resources, obtain the user k. * Unused computing resources for all users other than those mentioned above;

[0025] Update the maximum latency limit for other users to complete computing tasks, as well as the latency for completing all computing tasks, and stop updating according to the set stop conditions.

[0026] Furthermore, the step of calculating the latency for the user to complete the computing task based on the bandwidth allocation ratio and the computing resources includes:

[0027] The user's transmission rate is obtained based on the bandwidth allocation ratio, and the user's offload delay is obtained from the transmission rate.

[0028] The user's processing latency is calculated based on the computing resources.

[0029] The time delay for the user to complete the computing task is obtained by adding the unloading delay to the processing delay.

[0030] Furthermore, the stopping condition is: all users' computing tasks are completed or all users' computing task data transmission is completed.

[0031] A latency minimization system for mobile edge computing networks in underground and sheltered spaces includes: a processing module that constructs a static resource allocation calculation model in a wireless cellular network consisting of a base station supported by mobile edge computing and K users; and a solution module that transforms the static resource allocation calculation model into a convex optimization problem and solves the convex optimization problem to obtain the optimal solution for dynamic calculation and bandwidth allocation schemes among users, thereby minimizing system latency.

[0032] A computer-readable storage medium storing one or more programs, the one or more programs including instructions that, when executed by a computing device, cause the computing device to perform any of the methods described above.

[0033] A computing device includes: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for performing any of the methods described above.

[0034] The present invention has the following advantages due to the adoption of the above technical solutions:

[0035] This invention can make full use of bandwidth and computing resources under diverse user conditions and different channel conditions. By utilizing unused bandwidth and computing resources, it uses an iterative algorithm to obtain the optimal solution for dynamic computing and bandwidth allocation schemes among users, thereby minimizing system latency. Attached Figure Description

[0036] Figure 1 This is an overall flowchart of a method for minimizing latency in mobile edge computing networks in underground and sheltered spaces according to an embodiment of the present invention;

[0037] Figure 2 This invention relates to the latency performance and BSC of a conventional method under different user counts K values ​​in one embodiment of the present invention. BS Computational power;

[0038] Figure 3 This is an embodiment of the invention demonstrating the latency performance of the method used under different user counts K and the BSC. BS Computational power;

[0039] Figure 4 In one embodiment of the present invention, the system delay, system bandwidth W, and user transmit power p are obtained using existing methods. k Relationship curve;

[0040] Figure 5 In one embodiment of the present invention, the system delay, system bandwidth W, and user transmit power p using the method of the present invention are described. k The relationship curve. Detailed Implementation

[0041] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the described embodiments of the present invention are within the scope of protection of the present invention.

[0042] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments according to this application. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0043] The method and system for minimizing latency in underground and sheltered space mobile edge computing networks provided by this invention obtains the optimal solution for dynamic computing and bandwidth allocation schemes among users by jointly computing and bandwidth resources under diverse user and different channel conditions, thereby minimizing system latency.

[0044] In one embodiment of the present invention, such as Figure 1As shown, a method for minimizing latency in mobile edge computing networks in underground and sheltered spaces is provided. This embodiment illustrates the method by applying it to a terminal. It is understood that this method can also be applied to a server, and further to a system including both a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0045] 1) Construct a static resource allocation computation model in a wireless cellular network consisting of a base station supported by mobile edge computing and K users;

[0046] 2) Transform the static resource allocation calculation model into a convex optimization problem, solve the convex optimization problem, obtain the optimal solution of the dynamic calculation and bandwidth allocation scheme among users, and minimize system latency.

[0047] In step 1) above, let β = (β k ) k∈K To allocate a proportional vector to the system bandwidth, define C = (C k ) k∈K To allocate computing resources for all users, this invention minimizes system latency and user transmission latency requirements under the constraint of total system bandwidth, and considers the computing capabilities of the server and browser (BS), constructing a static resource allocation calculation model as follows:

[0048]

[0049] st c1:

[0050] c2:∑ k∈K C k ≤C BS ,

[0051] c3:∑ k∈K β k ≤1

[0052] c4:β k >0, k∈K,

[0053] Where, β=(β k ) k∈K Assign a proportional vector to the bandwidth, β k The bandwidth allocation ratio for user k; K represents the index set of all users; C represents the computing resource allocation for all users. k The computing resources allocated to user k, t k The latency for user k to complete the computation task; For user k, the uninstallation delay; For user k's processing delay, C represents the maximum latency limit for user k to complete the computation task. BSc1 represents the computing power of the BS; c2 represents the total delay for user k not exceeding its deadline; c3 represents the computing power constraint of the BS; and c4 describes the requirements for user bandwidth allocation.

[0054] In this embodiment, K = {1, 2, ..., K} represents the index set of all users. For k ∈ K, assuming user k has a task to be offloaded to the BS (base station) for processing, a three-dimensional array is used to describe user k, i.e., (L... k ,F k ,T k ), L k The task size for user k is represented in bits. Additionally, F k , and T k It describes the computing resources (in CPU cycles) and latency requirements (in seconds) required by the k-th user.

[0055] Among them, (1) the method for calculating the transmission delay during the unloading phase is as follows:

[0056] Let W be the bandwidth of the entire system, and define β. k W is the bandwidth allocated to user k for data offloading, where β k p represents the allocation ratio for users k∈K. k and g k Let R represent the transmit power and channel gain of user k, respectively. Then, the transmission rate R that user k can achieve during the offload phase is... k for:

[0057]

[0058] Where N0 represents the additive noise power spectral density, therefore, the offloading delay of user k for:

[0059]

[0060] (2) The delay calculation method in the data processing stage is as follows:

[0061] Define C k The computing resources allocated to user k (in CPU cycles) are assumed to be processed once user k's data is unloaded after the BS begins executing the data. Processing latency is also considered. The calculation formula is as follows:

[0062]

[0063] Assuming that the computational output of each user is very small and ignoring the result feedback delay, based on the above analysis, the time delay t for user k is... k for:

[0064]

[0065] Use C BS The calculation formula for representing the computing power of BS is as follows:

[0066] ∑ k∈K C k ≤C BS (5)

[0067] Furthermore, defining system latency as the maximum latency for all users to complete the uninstallation task and data processing, k∈K, we can obtain max. k∈K t k .

[0068] In step 2) above, the convex optimization problem is:

[0069]

[0070] st c2,c3,c4,

[0071] c6:

[0072] c7:

[0073] c8:

[0074] In the formula, D is an auxiliary variable, D = {D k} k∈K D k To introduce an auxiliary variable regarding the lower limit of the uplink transmission rate for user k; T = max k∈K t k .

[0075] In this embodiment, the method for transforming the static resource allocation calculation model into a convex optimization problem is as follows:

[0076] Introducing an auxiliary variable T to represent max k∈K t k The static resource allocation calculation model can be equivalently transformed into equation (7):

[0077]

[0078] st c1,c2,c3,c4

[0079] c5:t k ≤T,k∈K,

[0080] Equation (7) is still not a convex optimization programming problem because the constraints c1 and c5 are non-convex. To further simplify the analysis, another auxiliary variable D = {D k}k∈K Equation (7) can be transformed into equation (8):

[0081]

[0082] st c2,c3,c4,

[0083] c6:

[0084] c7:

[0085] c8:

[0086] Where, p k For the transmission power of user k, g k Let N be the channel gain for user k, and N0 be the additive noise power spectral density.

[0087] Equation (8) is a convex optimization problem that can be solved using the primal dual interior point method.

[0088] Specifically, for equation (8) to be a convex problem with respect to all variables T; β; C; D, the following argument is made:

[0089] After the above transformation, the objective function in equation (8) becomes a convex function. Simultaneously, c2, c3, and c4 are linear. Define β... k >0 And first focus on constraint c9:

[0090]

[0091] Because for β k >0, the right side of c9 is concave. Wherein It is the second derivative of the function f. The constraints c6, c7, and c8 are convex. Therefore, equation (8) is a convex optimization problem, which can be solved by CVX to obtain the optimal solution.

[0092] Equations (6) and (8) have the same optimal objective and optimal solution, specifically:

[0093] Using the newly introduced set of variables D = {D k} k∈K Constraints c1 and c5 can be transformed into the following three constraints:

[0094]

[0095]

[0096]

[0097] When equation (8) obtains its optimal value, the inequality constraint (11) holds; otherwise, for k∈K, the objective value of equation (8) will change with D. k The increase further reduces the value.

[0098] In step 2) above, CVX is used to solve the convex optimization problem to obtain the optimal solution. The optimal solution is the bandwidth allocation ratio for all users in the network, and the computing resources allocated by the edge server to all users.

[0099] Step 2) above, the method for minimizing system latency based on the optimal solution, includes the following steps:

[0100] 2.1) Calculate the latency for users to complete computing tasks based on the bandwidth allocation ratio and computing resources, and find the user k that requires the least time to complete the computing task. * ;

[0101] 2.2) Obtain the value excluding user k based on computing resources. * Unused computing resources for all users other than those mentioned above;

[0102] 2.3) Update the maximum latency limit for other users to complete computing tasks, as well as the latency for completing all computing tasks, and stop updating according to the set stop conditions.

[0103] The stopping condition is: all users' computing tasks are completed or all users' computing task data transmission is completed.

[0104] In step 2.1) above, the latency for the user to complete the computing task is calculated based on the bandwidth allocation ratio and computing resources, including the following steps:

[0105] 2.1.1) Calculate the user's transmission rate based on the bandwidth allocation ratio, and then obtain the user's offload delay from the transmission rate;

[0106] 2.1.2) Calculate the user's processing latency based on computing resources;

[0107] 2.1.3) The time it takes for the user to complete the computing task is obtained by adding the unloading delay and the processing delay.

[0108] In this embodiment, the optimal static resource allocation algorithm is used to obtain the latency required for each user to complete a task, denoted by k. * This represents the user with the lowest latency among all users. During rest time During this period, except for k * All users outside of this network can use unused bandwidth. Continue transmitting the task.

[0109] Under the fixed-allocation computing resource strategy of BS Continue processing the division by k* This affects tasks for all users other than those already using the system. Clearly, the BS is not fully utilizing wireless bandwidth and computing resources. Based on the method of this invention, system latency is further reduced under greater constraints on computing resources and bandwidth allocation.

[0110] In summary, when using this invention, considering that static calculation and bandwidth allocation schemes cannot fully exploit the potential of MEC networks under different users and channel conditions, and by combining calculation and bandwidth resources to minimize system latency, this invention can obtain the optimal solution through dynamic calculation and bandwidth allocation schemes among users, thereby minimizing system latency. Compared with traditional static schemes, this invention can fully utilize bandwidth and computing resources and reuse unused bandwidth and computing resources.

[0111] Example:

[0112] like Figure 2 and Figure 3 As shown, the latency performance of Algorithm 1 and Algorithm 2 under different user counts K and BSC are presented. BS Its computing power.

[0113] Figure 2 and Figure 3 The following describes how Algorithm 1 and Algorithm 2 are performed under different user numbers K and base station C values. BS Latency performance under computing power constraints. From Figure 2 It can be seen that the system latency under both Algorithm 1 and Algorithm 2 increases with the increase of K, because the larger K is, the greater the task offloading delay and execution delay, and the greater the interference power. For any given transmission power, the performance difference between Algorithm 1 and Algorithm 2 becomes more pronounced as the number of users increases, indicating that when K increases, Algorithm 2 can significantly reduce system latency. Because the diversity of different users increases with the increase of K, Algorithm 2 can make full use of the unused system bandwidth and computing resources left after task completion, which can significantly reduce system latency. Figure 3 It can be seen that, for any given user transmit power, Algorithm 2 is superior to Algorithm 1. Furthermore, with C... BS With the increase of , the system latency remains almost unchanged. This means that C BS There is a critical value, increasing C BS This will not reduce system latency.

[0114] like Figure 4 and Figure 5 The system delay versus system bandwidth W and user transmit power p of Algorithm 1 and Algorithm 2 are plotted respectively. k The relationship curve. From Figure 4 It can be seen that the system latency of Algorithm 1 and Algorithm 2 decreases as W increases, because the system bandwidth resources allocated to each user increase, and the user can achieve a transmission rate R.k This increases accordingly. Furthermore, for any given user transmit power, it can be seen that Algorithm 2 consumes less system latency to complete the task than Algorithm 1. As W increases, Algorithm 2 can significantly reduce system latency. This is because the bandwidth resources allocated to each user increase with W; for Algorithm 2, the unused system bandwidth increases while the task size remains constant, which can greatly reduce system latency. From Figure 5 As can be seen, for any given system bandwidth, Algorithm 2 requires less system latency to complete the task than Algorithm 1, and the system latency increases with the transmission power p of user k. k It decreases as the transmission power p of user k increases. This is because... k With the increase in [the number of], the transmission rate that users can achieve increases, and Algorithm 2 can make full use of unused computing resources.

[0115] Simulation results show that the iterative algorithm proposed in this invention, compared with the traditional static scheme, can make full use of bandwidth and computing resources, minimizing system latency by utilizing the remaining unused bandwidth and computing resources after task completion. This allows for the reallocation of bandwidth and computing resources in underground and sheltered space base stations (BS) to further reduce system latency in mobile edge computing (MEC) within the network.

[0116] In one embodiment of the present invention, a system for minimizing latency in underground and sheltered space mobile edge computing networks is provided, comprising:

[0117] The processing module constructs a static resource allocation calculation model in a wireless cellular network consisting of a base station supported by mobile edge computing and K users.

[0118] The solution module transforms the static resource allocation calculation model into a convex optimization problem, solves the convex optimization problem, and obtains the optimal solution for the dynamic calculation and bandwidth allocation scheme among users, thereby minimizing system latency.

[0119] The system provided in this embodiment is used to execute the above-described method embodiments. For specific processes and details, please refer to the above embodiments, which will not be repeated here.

[0120] The computing device structure provided in one embodiment of the present invention can be a terminal, which may include: a processor, a communication interface, memory, a display screen, and an input device. The processor, communication interface, and memory communicate with each other via a communication bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and a computer program. When executed by the processor, the computer program implements a method for minimizing latency in underground and sheltered space mobile edge computing networks. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The communication interface is used for wired or wireless communication with external terminals. Wireless communication can be achieved through Wi-Fi, a management network, NFC (Near Field Communication), or other technologies. The display screen can be a liquid crystal display or an e-ink display. The input device can be a touch layer covering the display screen, or buttons, a trackball, or a touchpad mounted on the casing of the computing device, or an external keyboard, touchpad, or mouse. The processor can call logical instructions in memory to execute the following method: in a wireless cellular network consisting of a base station supported by mobile edge computing and K users, construct a static resource allocation calculation model; transform the static resource allocation calculation model into a convex optimization problem, solve the convex optimization problem, obtain the optimal solution of the dynamic calculation and bandwidth allocation scheme among users, and minimize system latency.

[0121] Furthermore, the logical instructions in the aforementioned memory can be implemented as software functional units and sold or used as independent products, and can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0122] Those skilled in the art will understand that the structure shown in the above-described computing device is only a partial structure related to the solution of this application and does not constitute a limitation on the computing device on which the solution of this application is applied. A specific computing device may include more or fewer components, or combine certain components, or have different component arrangements.

[0123] In one embodiment of the present invention, a computer program product is provided, the computer program product including a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions, when the program instructions are executed by a computer, the computer is able to execute the methods provided in the above-described method embodiments, such as: constructing a static resource allocation calculation model in a wireless cellular network composed of a base station supported by mobile edge computing and K users; transforming the static resource allocation calculation model into a convex optimization problem, and solving the convex optimization problem to obtain the optimal solution of the dynamic calculation and bandwidth allocation scheme among users, thereby minimizing system latency.

[0124] In one embodiment of the present invention, a non-transitory computer-readable storage medium is provided, which stores server instructions that cause a computer to execute the methods provided in the above embodiments, such as: constructing a static resource allocation calculation model in a wireless cellular network consisting of a base station supported by mobile edge computing and K users; transforming the static resource allocation calculation model into a convex optimization problem, solving the convex optimization problem, obtaining the optimal solution of the dynamic calculation and bandwidth allocation scheme among users, and minimizing system latency.

[0125] The computer-readable storage medium provided in the above embodiments has a similar implementation principle and technical effect to the above method embodiments, and will not be described again here.

[0126] 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, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0127] 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, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0128] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0129] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for minimizing latency in mobile edge computing networks in underground and sheltered spaces, characterized in that, include: In a wireless cellular network consisting of a base station supported by mobile edge computing and K users, a static resource allocation computation model is constructed. The static resource allocation calculation model is transformed into a convex optimization problem, and the convex optimization problem is solved to obtain the optimal solution of the dynamic calculation and bandwidth allocation scheme among users, thereby minimizing system latency. The construction of the static resource allocation calculation model includes: c2:∑ k∈K C k ≤C BS , c3:∑ k∈K β k ≤1 c4:b k >0,k∈K, Where, β=(β k ) k∈K Assign a bandwidth scaling vector, β k The bandwidth allocation ratio for user k; K represents the index set of all users; C represents the computing resource allocation for all users. k The computing resources allocated to user k, t k The latency for user k to complete the computation task; For user k, the uninstallation delay; For user k's processing delay, C represents the maximum latency limit for user k to complete the computation task. BS c1 represents the computing power of the BS; c2 represents the total delay for user k not exceeding its deadline; c3 represents the computing power constraint of the BS; and c4 describes the requirements for user bandwidth allocation. The convex optimization problem is: stc2,c3,c4, In the formula, D is the set of auxiliary variables, D = {D k } k∈K D k This is an auxiliary variable introduced to define the lower bound of the uplink transmission rate for user k; T = max k∈K t k L k The size of user k's task is represented in bits; p k Represents the transmit power of user k; g k The channel gain of user k is represented by ; W is the bandwidth of the entire system; and N0 represents the additive noise power spectral density.

2. The method for minimizing latency in underground and sheltered space mobile edge computing networks as described in claim 1, characterized in that, The optimal solution to the convex optimization problem is obtained by using CVX. The optimal solution is the bandwidth allocation ratio for all users in the network, and the computing resources allocated by the edge server to all users.

3. The method for minimizing latency in underground and sheltered space mobile edge computing networks as described in claim 2, characterized in that, The method for minimizing system latency based on the optimal solution includes: Based on the bandwidth allocation ratio and the computing resources, the latency for users to complete computing tasks is calculated, and the user k with the minimum time required to complete the computing task is found. * ; Based on the computing resources, obtain the user k. * Unused computing resources for all users other than those mentioned above; Update the maximum latency limit for other users to complete computing tasks, as well as the latency for completing all computing tasks, and stop updating according to the set stop conditions.

4. The method for minimizing latency in underground and sheltered space mobile edge computing networks as described in claim 3, characterized in that, The step of calculating the latency for the user to complete the computing task based on the bandwidth allocation ratio and the computing resources includes: The user's transmission rate is obtained based on the bandwidth allocation ratio, and the user's offload delay is obtained from the transmission rate. The user's processing latency is calculated based on the computing resources. The time delay for the user to complete the computing task is obtained by adding the unloading delay to the processing delay.

5. The method for minimizing latency in underground and sheltered space mobile edge computing networks as described in claim 3, characterized in that, The stopping condition is: all users' computing tasks are completed or all users' computing task data transmission is completed.

6. A latency minimization system for mobile edge computing networks in underground and sheltered spaces, used to implement the latency minimization method for mobile edge computing networks in underground and sheltered spaces as described in any one of claims 1 to 5, characterized in that, include: The processing module constructs a static resource allocation calculation model in a wireless cellular network consisting of a base station supported by mobile edge computing and K users. The solution module transforms the static resource allocation calculation model into a convex optimization problem, solves the convex optimization problem, and obtains the optimal solution for the dynamic calculation and bandwidth allocation scheme among users, thereby minimizing system latency.

7. A computer-readable storage medium for storing one or more programs, characterized in that, The one or more programs include instructions that, when executed by a computing device, cause the computing device to perform any of the methods described in claims 1 to 5.

8. A computing device, characterized in that, include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for performing any of the methods described in claims 1 to 5.

Images