CN110740473B - Management method for mobile edge calculation and edge server - Google Patents
Management method for mobile edge calculation and edge server Download PDFInfo
- Publication number
- CN110740473B CN110740473B CN201911007166.5A CN201911007166A CN110740473B CN 110740473 B CN110740473 B CN 110740473B CN 201911007166 A CN201911007166 A CN 201911007166A CN 110740473 B CN110740473 B CN 110740473B
- Authority
- CN
- China
- Prior art keywords
- mobile terminal
- decision
- task
- delay
- edge server
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/02—Traffic management, e.g. flow control or congestion control
- H04W28/0231—Traffic management, e.g. flow control or congestion control based on communication conditions
- H04W28/0236—Traffic management, e.g. flow control or congestion control based on communication conditions radio quality, e.g. interference, losses or delay
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W36/00—Hand-off or reselection arrangements
- H04W36/16—Performing reselection for specific purposes
- H04W36/165—Performing reselection for specific purposes for reducing network power consumption
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W36/00—Hand-off or reselection arrangements
- H04W36/16—Performing reselection for specific purposes
- H04W36/22—Performing reselection for specific purposes for handling the traffic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W72/00—Local resource management
- H04W72/50—Allocation or scheduling criteria for wireless resources
- H04W72/53—Allocation or scheduling criteria for wireless resources based on regulatory allocation policies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W72/00—Local resource management
- H04W72/50—Allocation or scheduling criteria for wireless resources
- H04W72/54—Allocation or scheduling criteria for wireless resources based on quality criteria
- H04W72/542—Allocation or scheduling criteria for wireless resources based on quality criteria using measured or perceived quality
Abstract
Before the edge server provides auxiliary calculation, the invention comprehensively considers the influence of uplink transmission delay, calculation delay and downlink transmission delay on the total delay, and optimally distributes the current limited resources of the system for each mobile terminal so as to reduce the total delay for executing all user tasks. Particularly, under the condition that the size of downlink data in some scenes is large and cannot be ignored due to the technical development at present, the total time delay of all tasks corresponding to the task execution request can be minimized, and under the condition that the size of the downlink data is small, the total time delay of all tasks corresponding to the task execution request can be minimized, the requirements of users on low time delay in different scenes can be met efficiently, and therefore user experience is improved.
Description
Technical Field
The present invention relates to the field of wireless communication, and in particular, to joint optimization of computation offload and resource allocation in mobile edge computing, and more particularly, to a management method and an edge server for mobile edge computing.
Background
With the rapid development of mobile communication and the rapid popularization of intelligent mobile terminals, many new applications are as follows: virtual reality, augmented reality, and automatic driving, etc. ensue. Such applications with low latency and high reliability communication requirements place high demands on the computing power of the mobile terminal. Because a mobile terminal with limited computing power will generate a higher application processing delay and affect the service experience of the terminal user when processing such applications, how to reduce the application processing delay and improve the service experience of the terminal user is one of the key problems that needs to be solved urgently at present.
In view of the above problems, Mobile Cloud Computing (MCC) technology has been proposed. The MCC aims to extend rich computing resources at the cloud to mobile terminals with limited resources, thereby enhancing potential computing capabilities of the mobile terminals and reducing application processing delay. To achieve this goal, the mobile terminal needs to migrate the computationally intensive task to the cloud server by way of wireless access. Although the method can reduce the load of the mobile terminal, the method also has the obvious defect that the longer distance between the mobile terminal and the cloud server and the large number of terminal service requests cause the increase of network delay, thereby reducing the service experience of terminal users.
The European Telecommunications Standards Institute (ETSI) proposed a new technology: mobile Edge Computing (MEC), in a new proposed technical architecture, a server with fixed location and powerful computing capability is disposed at the edge of a network (such as a base station) to reduce the communication load and network delay of users within its coverage area. However, due to cost constraints, edge servers typically have relatively limited computing resources compared to cloud servers. Thus, for the edge server, too many tasks may put extra load on the service node and thus affect the network latency.
Currently, there are three main methods for reducing the task delay of a mobile terminal in an MEC network:
the first category of approaches is to design and optimize the offload profile for the mobile user. This kind of method assumes that the base station can obtain the basic information of the user, such as transmission distance, requested task type, current cell user number, and the position information of the user in the cellular network in the cell, the computing power of the edge server, etc. The mobile user performs unloading selection by comparing the execution delay of the task in the edge server with the execution delay in the local server, so that the optimization of an unloading strategy is completed and the terminal user obtains the lowest delay. In this type of method, the maximum computing power of the edge server is dynamically varied according to the total number of cell users and the resources are evenly allocated to each requesting user, and the allocation of downlink bandwidth resources is ignored. Therefore, the method has at least two defects, one is that adaptive computing resources cannot be allocated to users differently according to the size of the tasks of the users, so that the computing resources cannot be fully utilized or the requirements cannot be met; the other is that downlink transmission delay is ignored, when users related to application scenarios such as AR and VR exist in the users, the size of data of the calculation result cannot be ignored, and downlink transmission delay may be large, which greatly affects user experience.
The second method is to design an unloading strategy and resource allocation joint optimization scheme. Compared with the first method, the method further limits the computing capacity and system communication resources of the edge server, and when a user task request exists, the edge server performs optimal allocation of uplink resources and computing resources for the user through the acquired task request, so that the time delay is minimized. And then comparing the time delay obtained by the optimized distribution with the local calculation time delay to further obtain an optimized unloading strategy and the lowest time delay. In the method, the allocation of the computing resources is allocated according to the needs, that is, more computing resources are needed for the task requests of the users, and more points are needed, and less computing resources are needed for points, and finally, under the constraint condition of the total computing resources, the optimal allocation of the resources is performed according to the needs by taking the minimum total time delay of all the users as a target. Although the second method performs joint optimization on communication resources, computing resources and an unloading strategy through an optimization allocation algorithm to minimize the execution delay of the user task when multiple users initiate task requests, the second method still does not consider the influence of the limited downlink resources on the total delay of the task.
In the third method, a cloud server is added, the cloud server is assumed to be a server with infinite resources, and a user can perform tasks in a local server, an edge server and the cloud server to achieve computing unloading with the aim of minimizing application processing delay. However, the third method has the disadvantages of long distance, increased communication delay of users, and easy network congestion caused by service requests from multiple users, further increased application processing delay, and the third method does not consider the influence of downlink transmission delay on the total task delay.
Therefore, the existing calculation unloading and resource optimization scheme optimizes the task delay of the mobile terminal under the condition of neglecting the influence of downlink resources. Since the task is composed of three parts, i.e., input data, output data, and CPU cycles (affected by computing resources) required for inputting data, the task latency of the mobile terminal will be affected by the following aspects: the first is the transmission delay of an uplink, and after a user inputs data, how to allocate an optimal bandwidth resource to the user to meet the user requirement is very important; secondly, task delay, how to allocate optimal computing resources to a task to meet the delay requirement of a user is very important, thirdly, transmission delay of a downlink is very influenced, and when the input data is computed and then output data to the user, how to allocate optimal bandwidth resources to the user to meet the transmission requirement of the output data is very influenced.
In addition to the above three main methods, there are some other methods, which are not exhaustive. For example, a random offload algorithm (ROC) randomly allocates offload decisions for each user when the user has a task request, so that tasks of some users are randomly executed locally, and tasks of other users are offloaded to an edge server for execution.
In all the above methods, it is assumed that the output data is small, so that the transmission delay of the downlink is ignored. However, in an actual cache communication application scenario, downlink data in some cases is large, such as AR, VR, remote monitoring, and the like, and the downlink data will seriously affect user delay, so that the downlink data cannot be ignored, and particularly in some special application scenarios, there is a great demand for low user delay. For example: in the unmanned technology, a user needs to monitor a vehicle in real time through a mobile terminal, however, in the process, monitoring information of the vehicle is subjected to calculation processing by an edge server and a calculation result is returned to the mobile terminal of the user through a downlink, so that in the application scenario, optimization of downlink resources is very important for reducing task delay.
In summary, the existing scheme has limited applicable scenarios, and cannot efficiently meet the requirement of low delay of users in different scenarios under the situation that the size of downlink data in some scenarios is large and cannot be ignored due to the technical development at present. Therefore, there is a need for improvements in the prior art.
Disclosure of Invention
Therefore, an object of the present invention is to overcome the above-mentioned drawbacks of the prior art, and to provide a management method for mobile edge calculation and an edge server, which comprehensively consider the influence of the uplink transmission delay, the computation delay, and the downlink transmission delay of the user task on the total delay of the task.
According to an aspect of the present invention, the present invention provides a management method for mobile edge calculation, which is used for edge assisted calculation and system resource optimized allocation before assisted calculation of a system composed of a base station, a mobile terminal and an edge server within a coverage area of the base station, and for each coverage area of the base station, the following steps are performed:
s1, responding to task requests of all mobile terminals at the current moment, initializing unloading decisions of each mobile terminal, and randomly setting the initial unloading decisions of each mobile terminal as a first decision or a second decision;
s2, based on the information of the mobile terminal, the current resources of the system and the initial unloading decision set in the step S1, calculating the total time delay including the uplink transmission time delay, the calculation time delay and the downlink transmission time delay corresponding to the execution of the tasks of all the mobile terminals according to the initial decision;
s3, sequentially calculating a total time delay when the offload decision of each mobile terminal is adjusted to a decision opposite to the current offload decision, wherein if the total time delay is reduced after a certain mobile terminal adjusts the current offload decision, the offload decision of the mobile terminal is adjusted, otherwise, the offload decision of the mobile terminal is not adjusted;
s4, calculating one round for each mobile terminal, then determining that no mobile terminal adjusts the unloading decision in the round of adjustment process, and ending the adjustment process to obtain the final unloading decision and the final system resource allocation scheme of each mobile terminal;
s5, independently distributing the uplink and downlink communication resources of the time and the computing resources of the edge server needed by the task of the auxiliary computing of the time for the mobile terminal of which the final unloading decision is the first decision according to the system resource distribution scheme;
s6, executing the task request according to the final unloading decision of each mobile terminal; and/or
S7, entering the next task cycle after completing the task requests of all the mobile terminals at the current moment, and re-executing the steps S1-S7;
the first decision indicates that the mobile terminal unloads the task corresponding to the task request to the edge server for calculation, the second decision indicates that the mobile terminal places the task corresponding to the task request on a local calculation, the uplink or downlink communication resources are the mobile terminals which allocate bandwidth resources to the final unloading decision in a percentage form as the first decision, the computing resources of the edge server are the mobile terminals which allocate the computing resources of the edge server to the final unloading decision in a percentage form as the first decision, and the percentage of the resources occupied by each mobile terminal which makes the final unloading decision as the first decision is the percentage of the task request requirements in the total task request requirements corresponding to all the mobile terminals which make the final unloading decision as the first decision.
Wherein the step S3 includes:
s31, sequentially calculating the total time delay when the unloading decision of each mobile terminal is adjusted to a decision opposite to the current unloading decision, wherein the total time delay is calculated each time based on the system resource allocation scheme adapted to the unloading decisions of all the mobile terminals after the current mobile terminal is adjusted; and/or
S32, if the total delay is reduced after a certain mobile terminal adjusts the current offload decision, adjusting the offload decision and the resource allocation scheme of the mobile terminal, otherwise, not adjusting.
Preferably, the downlink transmission delay is a ratio of the size of the calculation result data to the downlink transmission rate. In calculating the downlink transmission delay, the size of the corresponding calculation result data may be provided according to one of the following manners: under the condition that the same task is calculated by the edge server at the earlier stage, providing the size of calculation result data obtained at the earlier stage according to the historical data of the edge server as the size of the calculation result data of the corresponding task; under the condition that the same tasks but with the same type are not calculated in the earlier stage of the edge server, a reference range is formed according to historical data of the edge server, and a first random value is randomly provided in the reference range to serve as the size of a calculation result of the corresponding task; and under the condition that the same tasks and the same types of tasks are not calculated at the earlier stage of the edge server, randomly providing a second random value which is smaller than or equal to the size of the task by the edge server as the size of the corresponding calculation result.
According to another aspect of the present invention, there is provided an edge server for providing a service including at least an assistance calculation for a mobile terminal in an area covered by a base station associated therewith, the edge server comprising: one or more processors; and a memory, wherein the memory is to store executable instructions; the one or more processors are configured to perform the aforementioned methods via execution of the executable instructions.
Compared with the prior art, the invention has the advantages that: the invention fully considers the influence of the uplink transmission delay, the calculation delay and the downlink transmission delay on the total delay of the tasks for executing all the user tasks, comprehensively considers the influence of the uplink transmission delay, the calculation delay and the downlink transmission delay on the total delay before the edge server provides auxiliary calculation, and optimally distributes the current limited resources of the system for each mobile terminal so as to reduce the total delay for executing all the user tasks. Particularly, under the condition that the size of downlink data in some scenes is large and cannot be ignored due to the technical development at present, the total time delay of all tasks corresponding to the task execution request can be minimized, and under the condition that the size of the downlink data is small, the total time delay of all tasks corresponding to the task execution request can be minimized, the requirements of users on low time delay in different scenes can be met efficiently, and therefore user experience is improved.
Drawings
Embodiments of the invention are further described below with reference to the accompanying drawings, in which:
fig. 1 is a diagram illustrating a conventional architecture of a base station system according to an embodiment of the present invention;
fig. 2 is a schematic diagram illustrating a comparison of total delays corresponding to a management method for mobile edge calculation and three existing methods in different numbers of mobile terminals according to an embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating a comparison of total delays corresponding to a management method for mobile edge calculation and three existing methods under different input data sizes according to an embodiment of the present invention;
fig. 4 is a schematic diagram illustrating comparison of total delays corresponding to a management method for mobile edge calculation and three existing methods under different calculation result data sizes according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail by embodiments with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
First, the background of the present invention will be described.
When the inventor researches on reducing the user delay, the inventor finds that the transmission delay of downlink data is very important and cannot be ignored in the delay factors affecting the mobile user by researching factors affecting the mobile user delay in the existing mobile edge computing network and relevant solutions. Therefore, it is necessary to optimize the task delay of the mobile terminal by integrating uplink data transmission and computing resources on the basis of considering downlink data transmission. In the optimization process, because the computing power of different users in the area covered by a single base station is different, in addition, different users have different characteristics for executing tasks, namely: the size of input data, the size of output data and the number of CPU cycles required by tasks are different, that is, uplink network bandwidth resources, downlink network bandwidth resources and edge server computing resources required by different user task requests are different. In addition, in a single-base-station multi-user scenario, the computing power of the edge server and the spectrum resources of the base station are limited. Therefore, how to enable the mobile terminals corresponding to all the users to obtain the lowest total delay under the multi-user request is an important issue. According to the scheme, the task delay of the mobile user can be obviously reduced in a scene of considering uplink and downlink communication resources, and the user service experience is further improved.
Next, some of the terms used in the present invention are defined as follows:
an edge server refers to a server deployed near the edge of a network, such as a base station, to serve corresponding users. In the present application, the service includes at least an auxiliary computing service, and the user may refer to a mobile terminal.
CPU cycles refer to the number of times an instruction is executed per second, and are referred to by the English name CPU cycles.
Fig. 1 is a diagram illustrating a conventional architecture of a base station system according to an embodiment of the present invention, the system includes a base station, an edge server, and a mobile terminal in the coverage of the base station. The edge server is deployed at a base station at the edge of the network to serve mobile terminals within the coverage area of the base station. In the present application, each mobile terminal corresponds to one user of the base station. The base station is responsible for providing communication service for the mobile terminal, and the edge server is responsible for providing computing service for the mobile terminal. The mobile terminal may issue a task request seeking an edge server to provide ancillary computing services. However, in a system consisting of a base station, an edge server and a mobile terminal, the current resources of the system are limited and it is impossible to satisfy the task request of each mobile terminal. Therefore, before the edge server provides the auxiliary computation, how to optimally allocate the system resources to each mobile terminal needs to comprehensively consider the uplink transmission delay, the computation delay and the downlink transmission delay. Under the condition that the size of downlink data in some scenes is large and cannot be ignored due to technical development at present, the total time delay of all tasks corresponding to the task execution request is minimized, the requirement of low time delay of users in different scenes can be met efficiently, and therefore user experience is improved.
According to an embodiment of the present invention, the present invention provides a management method for mobile edge calculation, which is used for edge auxiliary calculation and system resource optimal allocation before auxiliary calculation of a system composed of a base station, a mobile terminal and an edge server within a coverage area of the base station, and for each coverage area of the base station, the following main steps are performed:
s1, responding to task requests of all mobile terminals at the current moment, initializing unloading decisions of each mobile terminal, and randomly setting the initial unloading decisions of each mobile terminal as a first decision or a second decision;
s2, based on the information of the mobile terminal, the current resources of the system and the initial unloading decision set in the step S1, calculating the total time delay including the uplink transmission time delay, the calculation time delay and the downlink transmission time delay corresponding to the execution of the tasks of all the mobile terminals according to the initial decision;
s3, sequentially calculating a total time delay when the offload decision of each mobile terminal is adjusted to a decision opposite to the current offload decision, wherein if the total time delay is reduced after a certain mobile terminal adjusts the current offload decision, the offload decision of the mobile terminal is adjusted, otherwise, the offload decision of the mobile terminal is not adjusted;
s4, calculating one round for each mobile terminal, then determining that no mobile terminal adjusts the unloading decision in the round of adjustment process, and ending the adjustment process to obtain the final unloading decision and the final system resource allocation scheme of each mobile terminal;
s5, independently distributing the uplink and downlink communication resources of the time and the computing resources of the edge server needed by the task of the auxiliary computing of the time for the mobile terminal of which the final unloading decision is the first decision according to the system resource distribution scheme;
s6, executing the task request according to the final unloading decision of each mobile terminal; and/or
S7, entering the next task cycle after completing the task requests of all the mobile terminals at the current moment, and re-executing the steps S1-S7;
the first decision indicates that the mobile terminal unloads the task corresponding to the task request to the edge server for calculation, the second decision indicates that the mobile terminal places the task corresponding to the task request on a local calculation, the uplink or downlink communication resources are the mobile terminals which allocate bandwidth resources to the final unloading decision in a percentage form as the first decision, the computing resources of the edge server are the mobile terminals which allocate the computing resources of the edge server to the final unloading decision in a percentage form as the first decision, and the percentage of the resources occupied by each mobile terminal which makes the final unloading decision as the first decision is the percentage of the task request requirements in the total task request requirements corresponding to all the mobile terminals which make the final unloading decision as the first decision.
Preferably, the method may further comprise: before executing step S1, each time, the mobile terminal information of all mobile terminals in the coverage area of the base station is acquired and the user information table in which the mobile terminal information is recorded is refreshed, so that the total time delay of this time is calculated based on the mobile terminal information updated in the user information table each time. The mobile terminal information includes location information of the mobile terminal, computing power, and requested specific task information. The mobile terminal information may also include the transmit power of the mobile terminal.
Preferably, for step S1, the edge server may complete a round of task requests of the users in the coverage area, send a calculation result obtained by performing an auxiliary calculation on the tasks offloaded by the mobile terminals to the corresponding mobile terminals, and then start to respond to the task requests of all the mobile terminals at the current time of the new round.
For a better understanding of the present invention, each step is described in detail below with reference to specific examples.
S1, responding to the task requests of all the mobile terminals at the current moment, initializing the unloading decision of each mobile terminal, and randomly setting the initial unloading decision of each mobile terminal as a first decision or a second decision. For example, suppose that mobile terminals of three users in the coverage area of the current base station send task requests, at this time, the task requests of all the mobile terminals at the current time are the task requests sent by the three users, and the edge server responds to the task requests of all the mobile terminals at the current time, and randomly sets the initial offloading decisions corresponding to the three users to 0 or 1, for example, the initial offloading decisions corresponding to the three users are randomly set to 0,1, and 1, respectively, where 1 represents a first decision and 0 represents a second decision.
And S2, calculating the total time delay including the uplink transmission time delay, the calculation time delay and the downlink transmission time delay corresponding to the execution of the tasks of all the mobile terminals according to the initial decision based on the information of the mobile terminals, the current resources of the system and the initial unloading decision set in the step S1. After the initial unloading decision of each user is randomly set, the system resources are correspondingly distributed according to the initial unloading decision of the user to form an initial system resource distribution scheme corresponding to the initial unloading decision, so that the corresponding total time delay obtained according to the initial system resource distribution scheme of the initial unloading decision is calculated. According to an embodiment of the invention, it is assumed that each mobile terminal requests only one task w to be performedi＝{si,di,ciIn which s isiIndicating the size of the input data corresponding to the task, diIndicating the size of the calculation result data, ciRepresenting the total amount of CPU cycles required for a task. The set of offloading decisions for all mobile terminals is an offloading policy.
Thus, the uplink transmission delay can be expressed as
Wherein the content of the first and second substances,
the rate of uplink data transmission can be expressed as:
wherein k isiRepresents the percentage of the uplink bandwidth occupied by the task uploaded by the mobile terminal i, Pi,sDenotes the transmission power, h, of the mobile terminal ii,BDenotes the channel fading coefficient from the mobile terminal i to the base station, d denotes the distance between the mobile terminal i and the base station, r denotes the path loss, σ2To representThe noise power of the channel.
The downlink transmission delay can be expressed as
Wherein the content of the first and second substances,
the rate of downlink transmission data can be expressed as:
wherein ξiRepresents the bandwidth percentage h occupied by the mobile terminal i when receiving the downlink dataB,iRepresenting the channel fading coefficient, P, from the base station to the mobile terminal iBRepresenting the transmit power of the base station.
The computation delay is divided into two types, one is the computation delay when the task is executed on the edge server, and the other is the computation delay when the task is executed locally.
The computational latency of a task executing on an edge server can be expressed as:
fi,mindicating the computing resources allocated by the edge server for mobile terminal i.
The computational latency of a task executing locally can be expressed as:
fi,lrepresenting the computing power local to the mobile terminal i.
Therefore, the time delay caused by the task of the mobile terminal i being offloaded to the edge server for execution can be expressed as: u shapei,m＝ti,u+ti,d+ti,m. The time delay caused by the local execution of the task of the mobile terminal i can be expressed as: u shapei,l＝ti,l. It can be seen that the time delay for the mobile terminal to unload to the edge server to execute the task includes uplink transmission time delay, calculation time delay and downlink transmission time delayAnd (4) time delay. The time delay of the mobile terminal for executing the task locally comprises calculation time delay, and the time delay of the mobile terminal for executing the task locally does not have uplink transmission time delay and downlink transmission time delay because the processes of uploading the task and receiving the calculation result data do not exist.
Preferably, in step S2, the factors affecting the total delay may be formally expressed by establishing a basic model of the delay problem, so as to define a calculation manner of the total delay. In other words, the basic model of the delay problem can be used to formally express the factors affecting the total delay based on the current resources of the system and the information of the mobile terminal. The delay problem model provided by the embodiment of the invention is a model when a multi-user task requests in an area covered by a single base station. In the basic model of the delay problem, the computing power of each mobile terminal can be different, each task can be different, and the bandwidth resources can be designed according to the percentage; each mobile terminal in the basic model of the latency problem may request one or more tasks at a time. The edge server has concurrent processing capabilities, namely: multiple tasks may be processed simultaneously. Therefore, in the initial stage, the base station needs to collect the mobile terminal information of the users in the system. The mobile terminal information may include computing power of each mobile terminal, location information relative to the base station, and/or transmit power of the mobile terminal. The mobile terminal information may be recorded in a user information table and periodically refreshed.
Preferably, the basic model of the delay problem can be expressed as:
where a denotes an offload policy, a ═ ai}i∈L，aiRepresents an offload decision for mobile terminal i, aiE {0,1}, when aiWhen the task request is 1, the unloading decision of the mobile terminal i is a first decision, and the mobile terminal i unloads the task corresponding to the task request to the edge server for calculation; when a isiWhen the current task is equal to 0, the offloading decision of the mobile terminal i is represented as a second decision, the mobile terminal i places the task corresponding to the task request in local computation, L represents the set of all the mobile terminals, and L is { i: i ═ 1, 2.. N },
fi,mindicating the computing resources allocated by the edge server to the mobile terminal i, fmIndicating the total computing power that the edge server can provide,
kirepresenting the percentage of uplink bandwidth occupied by the mobile terminal i uploading its task,
ξirepresents the percentage of bandwidth occupied by the mobile terminal i when receiving downlink data, a represents a specific set of offloading decisions, and a ═ a1,a2,...an}，anN in (1) is the current actual total number of users, i.e. the actual total number of mobile terminals, Ui,mRepresents the total time delay, U, calculated by the mobile terminal i offloading its tasks to the edge serveri,lThe computation delay generated by the task placed by the mobile terminal i in the local computation is represented, the limitation condition C1 represents that the sum of the computation resources allocated to at least two mobile terminals is less than or equal to the computation capacity of the server, the limitation condition C2 represents that the sum of the uplink spectrum resources allocated to at least two mobile terminals is less than or equal to the total uplink bandwidth of the system, the limitation condition C3 represents that the sum of the downlink spectrum resources allocated to at least two mobile terminals is less than or equal to the total downlink bandwidth of the system, the limitation condition C4 represents that the local computation resources of the mobile terminal i are non-negative, and the limitation condition C5 represents that the offloading decision of the mobile terminal i is the first decision or the second decision.
S3, sequentially calculating a total time delay when the offload decision of each mobile terminal is adjusted to a decision opposite to the current offload decision, wherein if the total time delay is reduced after a certain mobile terminal adjusts the current offload decision, the offload decision of the mobile terminal is adjusted, otherwise, the offload decision of the mobile terminal is not adjusted;
and S4, calculating one round for each mobile terminal, determining that no mobile terminal adjusts the unloading decision in the round of adjustment process, and ending the adjustment process to obtain the final unloading decision and the final system resource allocation scheme of each mobile terminal. .
In step S3, in the adjusting process of sequentially calculating the total delay when the offload decision of each mobile terminal is adjusted to the decision opposite to the current offload decision, the number of offload decisions adjusted each time may be one or more. For example, the total delay when the offload decision of each mobile terminal is adjusted to a decision opposite to the current offload decision may be calculated by adjusting only the offload decision of a single mobile terminal each time, but not adjusting the offload decisions of other mobile terminals this time, so as to calculate the total delay when the offload decision of the mobile terminal is adjusted to a decision opposite to the current offload decision. Specifically, if a certain mobile terminal is currently adjusted, and the current offload decision of the mobile terminal is 1, then 0 is adjusted, and the offload decisions of the other mobile terminals are not adjusted this time, so as to calculate the adjusted total time delay. Or, the total time delay when the offloading decision of each mobile terminal is adjusted to a decision opposite to the current offloading decision is calculated in sequence, which may be that the offloading decisions of two of the mobile terminals are adjusted each time while the offloading decisions of other mobile terminals are not adjusted this time, so as to calculate the total time delay when the offloading decisions of the two mobile terminals are adjusted to a decision opposite to the current offloading decision. Specifically, if the current offload decisions of two mobile terminals are 1 and 0 respectively when the current offload decisions of the two mobile terminals are currently adjusted to two mobile terminals, the offload decisions of the other mobile terminals are not adjusted at this time, so as to calculate the adjusted total time delay.
According to an embodiment of the present invention, for steps S3 to S4, a final unloading decision and system resource allocation scheme may be analyzed and determined by constructing a delay problem solution model, where the delay problem solution model provided in this embodiment adopts a game model, but solution of the problem is not limited to a game model. The reason for constructing the delay problem solution model is that the calculation time for solving the delay problem basic model may be long or it is difficult to solve the solution, so that the model is re-modeled based on the game theory on the basis of the constructed delay problem basic model to construct the delay problem solution model, thereby shortening the solution time. The delay problem solution model can be used for analyzing and obtaining a final unloading strategy and a final resource allocation scheme which can minimize the total delay required by the tasks corresponding to all the task requests. It should be understood that the final offloading policy is the set of final offloading decisions for each mobile terminal.
Preferably, the delay problem solution model can be expressed as:
G＝{L，(Ai)i∈L，ui}；
wherein L represents the set of all mobile terminals, AiIndicates the offload policy, u, of the mobile terminal iiThe time delay utility function of the mobile terminal i is represented, and the time delay of the mobile terminal i is represented as
Indicating the offloading decision of the other mobile terminal j of the at least two mobile terminals than mobile terminal i.
According to an embodiment of the present invention, the method of the present application can enable each mobile terminal to obtain a final resource allocation scheme containing an optimal solution through a time delay problem solution model through a game, which is expressed as:
optimal solution of computing resources allocated by edge server for mobile terminal i
Mobile terminal i uploads the optimal solution of the percentage of the uplink bandwidth occupied by the task
Optimal solution of bandwidth percentage occupied by mobile terminal i when receiving downlink data
Wherein the content of the first and second substances,
b represents the total spectral bandwidth, hi,BRepresenting the channel fading coefficient, P, from the mobile terminal i to the base stationi,sExpressed as the transmission power of the mobile terminal i, d the distance between the mobile terminal i and the base station, r the path loss, σ2Representing the noise power of the channel, hB,iRepresenting the channel fading coefficient, P, from the base station to the mobile terminal iBDenotes a transmission power of the base station, and μ, λ, and θ are first, second, and third optimization factors, respectively. The first optimization factor mu, the second optimization factor lambda and the third optimization factor theta are correspondingly optimized and updated each time the unloading decision of the corresponding mobile terminal is adjusted in the iterative adjustment process, and formulas adopted by the optimization and update are respectively as follows:
wherein the content of the first and second substances,
for the iteration step length, the value range of the iteration step length can be 10-5～10-7And t is the iteration number and is not less than 0, mu (t +1), lambda (t +1) and theta (t +1) are the values of mu, lambda and theta after the current adjustment respectively, and mu (t), lambda (t) and lambda (t) are the values of mu, lambda and theta before the current adjustment respectively. In one case, although μ (t) - μ (t +1) ≦ 10-6、λ(t)-λ(t+1)≤10-6And theta (t) -theta (t +1) is less than or equal to 10-6The conditions of the above-mentioned methods are not completely met, but in the adjustment process, in the whole process that a certain mobile terminal starts to go through a round of adjustment process and returns to the mobile terminal again, none of the mobile terminals adjusts the unloading decision in the round of adjustment process, and the adjustment process is ended, so that the final unloading decision and the final system resource allocation scheme of each mobile terminal corresponding to the minimum total time delay are obtained. In another case, the offload decision of the corresponding mobile terminal is adjusted at a time and after this adjustment μ (t) - μ (t +1) is less than or equal to 10-6、λ(t)-λ(t+1)≤10-6And theta (t) -theta (t +1) is less than or equal to 10-6The optimum solution is confirmed. Preferably, the number of iterations may be preset. For example, the number of iterations may be set manually or set and adjusted empirically by the edge server. The number of iterations may be set to any value of 10000 to 20000, for example. The number of iterations refers to the maximum number of iterations. In practice, the maximum number of times that may have been reached has resulted in the final offload decision and the final system resource allocation scheme. For example, the number of iterations is set to 15000, which may be performed during the actual adjustment processThe adjustment process is ended if one of the two conditions has occurred already at 8000 times.
From the above, it can be seen that the system resource allocation scheme includes first, second and third optimal solutions. The first optimal solution is the computational resources allocated for the respective mobile terminal. The second optimal solution is the percentage of uplink bandwidth occupied by the task of uploading allocated to the corresponding mobile terminal. The third optimal solution is the bandwidth percentage allocated to the corresponding mobile terminal to receive the downlink data. The first, second and third optimal solutions correspond to first, second and third optimization factors, respectively. Preferably, in order to prevent the iteration time from being too long, according to an embodiment of the present invention, the method further includes: in the process of executing steps S3 to S4, the adjustment process is ended if one of the following occurs: t1, the reduction values of the first, second and third optimization factors for optimizing the system resource allocation scheme are all smaller than the set threshold value; and T2, the actual iteration adjustment number reaches the set maximum iteration number. In this case, after the adjustment process is finished, the offloading decision and the system resource allocation scheme of each mobile terminal at the time of finishing the adjustment process are used as the final offloading decision and the final system resource allocation scheme of each mobile terminal. The reduced values of the first, second and third optimization factors are calculated values obtained by μ (t) - μ (t +1), λ (t) - λ (t +1) and θ (t) - θ (t + 1). After the final offload policy is obtained, the final offload policy may be written into the user information table. In this case, although an optimal offloading decision and system resource allocation scheme are not obtained, the problem that the solution time is too long due to long-time solution, which affects user experience, is avoided.
And according to the analysis, obtaining a final system resource allocation scheme to allocate system resources, namely uplink communication resources, calculation resources and downlink communication resources, to each mobile terminal. And then, the base station and the edge server receive the task unloaded by the mobile terminal with the final unloading decision as the first decision under the condition of the uplink communication resources distributed at this time and transmit the calculation result corresponding to the task to the corresponding mobile terminal under the condition of the downlink communication resources distributed at this time after completing the auxiliary calculation of the received task. Therefore, the total time delay for executing all tasks is minimized, and the user experience is improved.
Preferably, in step S4, the requirement for ending the adjustment process is: in a round of adjustment from one mobile terminal, none of the mobile terminals adjusts its offload decision in the round of adjustment. For example, assuming that 5 mobile terminals send task requests, when the initial offload decisions of the five mobile terminals are randomly set as the first decision or the second decision, the initial offload decisions of the five mobile terminals are 1, 0, and 0, respectively, the offload decisions of the five mobile terminals after multiple adjustments become 0,1, and 0, respectively, after the adjustment in the previous period, the offload decisions of the five mobile terminals are not adjusted from the first mobile terminal to the end of the fifth mobile terminal in the next round, and after the adjustment in the round is finished, the offload decisions of the five mobile terminals are still 0,1, and 0, and the adjustment process is finished.
In actual situations, the size of the result data is difficult to predict before the task obtains the calculation result data through calculation. Therefore, preferably, according to an embodiment of the present invention, the method of the present invention may further include: for the calculated task, the information of the task and the size of the corresponding calculation result data are associatively reserved so as to provide reference for the size of the calculation result data of the corresponding task based on the historical data.
According to an embodiment of the present invention, in order to perform downlink communication resource allocation in advance by using the size of the calculation result data, the size of the corresponding calculation result data may be provided according to one of the following manners:
the first mode is as follows: under the condition that the same task is calculated by the edge server at the earlier stage, providing the size of calculation result data obtained at the earlier stage according to the historical data of the edge server as the size of the calculation result data of the corresponding task; for example, a certain task edge server is calculated in an earlier stage, the edge server retains historical data, and the information of the task and the size of the corresponding calculation result data are recorded in the historical data, so that the size of the calculation result data obtained in the earlier stage can be used as the size of the calculation result data of the corresponding task. The same task may mean that the specific calculation tasks are the same, and accordingly, the corresponding calculation result data are also the same.
The second mode is as follows: under the condition that the same tasks but with the same type are not calculated in the earlier stage of the edge server, a reference range is formed according to historical data of the edge server, and a first random value is randomly provided in the reference range to serve as the size of a calculation result of the corresponding task; for example, for a task which is a certain data format in the AR domain, the edge server has not calculated the same task at the previous stage, but has calculated a task in the same data format at the previous stage, and the historical data indicates that the ratio of the size of the calculation result data of the data format to the size of the task is 20%, then a reference range is formed by multiplying the size of the task by 10% -30%, if the previous stage has calculated two times, the historical data indicates that the ratio of the size of the calculation result data of the data format to the size of the task in the previous two calculations is 20% and 40%, respectively, then a reference range is formed by multiplying the size of the task by 20% -40%, if the previous stage has calculated three times, the historical data indicates that the ratio of the size of the calculation result data of the data format to the size of the task in the previous three calculations is 10%, 20%, and 40%, respectively, then, the size of the task is multiplied by 10% -40% to form a reference range, and then the value is randomly taken in the reference range as the size of the calculation result of the corresponding task. Tasks of the same type may refer to tasks having the same data format.
The third mode is as follows: and under the condition that the same tasks and the same types of tasks are not calculated at the earlier stage of the edge server, randomly providing a second random value which is smaller than or equal to the size of the task by the edge server as the size of the corresponding calculation result.
Preferably, the mobile terminal may include at least one of a mobile phone, a tablet computer, a notebook computer, a vehicle-mounted computer, VR glasses, AR glasses, and a smart watch. Preferably, the onboard computer may be, for example, a drive computer of a motor vehicle.
According to an example of the present invention, the proposed method of the present invention is simulation verified by the following simulation parameters. The simulation parameters used in the simulation verification process are given in table 1.
TABLE 1 simulation parameters
In fig. 2, 3 and 4, the CORAG curve corresponds to the method adopted in the present application, which is an abbreviation of a computing offloading and resource allocation algorithm (CORAG) based on the game theory. The LOC curve corresponds to a Local offload algorithm (LOC) in which all tasks are not offloaded to the edge server for execution, but are executed locally at each mobile terminal. The ROC curve corresponds to a random offload algorithm (ROC). The COURG curve corresponds to a computation offloading and uplink resource allocation (COURG), and the second method of the background art uses the algorithm.
Fig. 2 is a schematic diagram illustrating a comparison of total delays corresponding to a method for assisting edge calculation and three existing methods for different numbers of mobile terminals according to an embodiment of the present invention. As can be seen from fig. 2, the performance of the method proposed by the present invention is superior to that of LOC, ROC and COURG algorithms. The advantage of the CORAG algorithm is more obvious as the number of mobile terminals increases. This is because under the condition of limited calculation and communication resources, the CORAG algorithm can better allocate the optimal calculation and communication resources to different mobile terminals, so that the total delay of all mobile terminals is the lowest. The input parameters of fig. 2 use the parameters listed in table 1, where some of the input parameters are varied. For example, the last four parameters in table 1 are random values randomly given by the computer within the normal distribution range described above.
Fig. 3 is a schematic diagram illustrating a total delay comparison corresponding to a management method for mobile edge calculation and three existing methods under different input data sizes according to an embodiment of the present invention. As can be seen from fig. 3, as the upstream input data increases, the total delay of the CORAG algorithm is lower than that of the LOC, ROC, and COURG algorithms. This is because, as the input data increases, the CORAG algorithm may allocate optimal uplink and downlink bandwidth resources and calculation resources according to the size of the input data, thereby minimizing the total delay of all terminal devices.
Fig. 4 is a schematic diagram illustrating a total delay comparison corresponding to a management method for mobile edge calculation and three existing methods under different calculation result data sizes according to an embodiment of the present invention. As can be seen from fig. 4, with the increasing of the calculation result data, the total delay of the CORAG algorithm is lower than that of the three algorithms of LOC, ROC, and COURG. The performance of the CORAG algorithm is obviously superior to that of the other three algorithms, and the performance advantage of the CORAG algorithm is more obvious along with the gradual increase of calculation result data.
In yet another embodiment of the present invention, there is also provided an edge server that may be used to provide services including at least assisted computing for mobile terminals in an area covered by a base station associated therewith. The edge server includes: one or more processors; and a memory, wherein the memory is to store executable instructions; the one or more processors are configured to execute the executable instructions to perform the aspects introduced in any of the foregoing embodiments and/or the methods of the present application.
In yet another embodiment of the present invention, there is also provided an electronic device, which may be more particularly referred to as a communication device, including an edge server and a base station communicatively connected to each other. The edge server can provide services including at least assistance calculations for mobile terminals in the area covered by the base station. The edge server includes: one or more processors; and a memory, wherein the memory is to store executable instructions; the one or more processors are configured to execute the executable instructions to perform the solutions presented in any of the foregoing embodiments and/or the methods of the present application.
It should be noted that, although the steps are described in a specific order, the steps are not necessarily performed in the specific order, and in fact, some of the steps may be performed concurrently or even in a changed order as long as the required functions are achieved.
The present invention may be a system, method and/or computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied therewith for causing a processor to implement various aspects of the present invention.
The computer readable storage medium may be a tangible device that retains and stores instructions for use by an instruction execution device. The computer readable storage medium may include, for example, but is not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing.
Having described embodiments of the present invention, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (9)
1. A management method for mobile edge calculation is used for edge auxiliary calculation of a system consisting of a base station, a mobile terminal and an edge server within the coverage area of the base station and optimal allocation of system resources before the auxiliary calculation, and is characterized in that the following steps are executed for each base station coverage area:
s1, responding to task requests of all mobile terminals at the current moment, initializing unloading decisions of each mobile terminal, and randomly setting the initial unloading decisions of each mobile terminal as a first decision or a second decision, wherein the first decision indicates that the mobile terminal unloads a task corresponding to the task request to an edge server for calculation, and the second decision indicates that the mobile terminal places the task corresponding to the task request in local calculation;
s2, based on the information of the mobile terminal, the current resources of the system and the initial unloading decision set in the step S1, calculating the total time delay including the uplink transmission time delay, the calculation time delay and the downlink transmission time delay corresponding to the execution of the tasks of all the mobile terminals according to the initial decision;
s3, sequentially calculating a total time delay when the offload decision of each mobile terminal is adjusted to a decision opposite to the current offload decision, wherein if the total time delay is reduced after a certain mobile terminal adjusts the current offload decision, the offload decision of the mobile terminal is adjusted, otherwise, the offload decision of the mobile terminal is not adjusted;
s4, calculating one round for each mobile terminal, then determining that no mobile terminal adjusts the unloading decision in the round of adjustment process, and ending the adjustment process to obtain the final unloading decision and the final system resource allocation scheme of each mobile terminal;
and S5, independently allocating the uplink and downlink communication resources of the time and the computing resources of the edge server required by the task of the auxiliary computing of the time for the mobile terminal of which the final unloading decision is the first decision according to the system resource allocation scheme.
2. A management method for mobile edge computing according to claim 1, further comprising:
s6, executing the task request according to the final unloading decision of each mobile terminal.
3. The management method according to claim 2, wherein the uplink or downlink communication resources are allocated to the mobile terminal whose final offload decision is the first decision in a percentage manner, the computing resources of the edge server are allocated to the mobile terminal whose final offload decision is the first decision in a percentage manner, and a percentage of the resource occupied by each mobile terminal whose final offload decision is the first decision is a percentage of a total task request requirement of all the mobile terminals whose final offload decision is the first decision.
4. The management method for mobile edge computing according to claim 2, wherein the system completes the task requests of all the mobile terminals at the current time as a task period, and the method further comprises:
s7, after the task requests of all the mobile terminals at the current time are completed, the next task cycle is entered, and the steps S1-S6 are executed again.
5. A management method for mobile edge computing according to claim 4, characterized in that said method further comprises: before executing step S1, each time, obtaining mobile terminal information of all mobile terminals in the coverage area of the base station and refreshing the user information table recording the mobile terminal information, so as to calculate the current total time delay by using the updated mobile terminal information each time;
the mobile terminal information comprises position information, computing capacity and requested specific task information of the mobile terminal.
6. The management method for mobile edge computing according to claim 4, wherein said step S3 includes:
s31, sequentially calculating the total time delay when the unloading decision of each mobile terminal is adjusted to a decision opposite to the current unloading decision, wherein the total time delay is calculated each time based on the system resource allocation scheme adapted to the unloading decisions of all the mobile terminals after the current mobile terminal is adjusted;
s32, if the total delay is reduced after a certain mobile terminal adjusts the current offload decision, adjusting the offload decision and the resource allocation scheme of the mobile terminal, otherwise, not adjusting.
7. The management method as claimed in claim 1, wherein the downlink transmission delay is a ratio of a size of the calculation result data to a downlink transmission rate, wherein, in calculating the downlink transmission delay, the corresponding size of the calculation result data is provided according to one of the following manners:
under the condition that the same task is calculated by the edge server at the earlier stage, providing the size of calculation result data obtained at the earlier stage according to the historical data of the edge server as the size of the calculation result data of the corresponding task;
under the condition that the same tasks but with the same type are not calculated in the earlier stage of the edge server, a reference range is formed according to historical data of the edge server, and a first random value is randomly provided in the reference range to serve as the size of a calculation result of the corresponding task; and
and under the condition that the same tasks and the same types of tasks are not calculated at the earlier stage of the edge server, randomly providing a second random value which is smaller than or equal to the size of the task by the edge server as the size of the corresponding calculation result.
8. A computer-readable storage medium having embodied thereon a computer program, the computer program being executable by a processor to perform the method of any one of claims 1 to 7.
9. An edge server for providing services including at least assisted computing for mobile terminals in an area covered by a base station associated therewith, the edge server comprising:
one or more processors; and
a memory, wherein the memory is to store executable instructions;
the one or more processors are configured to perform the method of any of claims 1-7 via execution of the executable instructions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911007166.5A CN110740473B (en) | 2019-10-22 | 2019-10-22 | Management method for mobile edge calculation and edge server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911007166.5A CN110740473B (en) | 2019-10-22 | 2019-10-22 | Management method for mobile edge calculation and edge server |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110740473A CN110740473A (en) | 2020-01-31 |
| CN110740473B true CN110740473B (en) | 2021-07-20 |
Family
ID=69270865
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911007166.5A Active CN110740473B (en) | 2019-10-22 | 2019-10-22 | Management method for mobile edge calculation and edge server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110740473B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112783567B (en) * | 2021-01-05 | 2022-06-14 | 中国科学院计算技术研究所 | DNN task unloading decision method based on global information |
| CN112685163B (en) * | 2021-01-06 | 2023-05-02 | 北京信息科技大学 | Calculation unloading method based on mobile edge calculation and mobile edge calculation server |
| CN112995280B (en) * | 2021-02-03 | 2022-04-22 | 北京邮电大学 | Data distribution method and device for multi-content demand service |
| CN112867061B (en) * | 2021-04-26 | 2021-09-17 | 香港中文大学（深圳） | Resource allocation method and device |
| CN113344152A (en) * | 2021-04-30 | 2021-09-03 | 华中农业大学 | System and method for intelligently detecting and uploading full-chain production information of dairy products |
| CN116432082B (en) * | 2023-03-29 | 2024-01-09 | 武汉理工大学 | Ship fault feature analysis method, system and storage medium |
| CN116483585B (en) * | 2023-06-16 | 2023-09-15 | 江西师范大学 | Multi-service pre-deployment method based on edge computing |
| CN117119444B (en) * | 2023-10-25 | 2024-01-16 | 成都信息工程大学 | Position privacy protection method based on mobile edge calculation |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017152723A1 (en) * | 2016-03-07 | 2017-09-14 | 大唐移动通信设备有限公司 | Data transmission method, apparatus and system |
| CN107249218A (en) * | 2017-06-05 | 2017-10-13 | 东南大学 | Radio Resource and the combined distributing method of cloud resource in a kind of MEC |
| CN107682443A (en) * | 2017-10-19 | 2018-02-09 | 北京工业大学 | Joint considers the efficient discharging method of the mobile edge calculations system-computed task of delay and energy expenditure |
| CN108901075A (en) * | 2018-06-28 | 2018-11-27 | 电子科技大学 | A kind of resource allocation methods based on GS algorithm |
-
2019
- 2019-10-22 CN CN201911007166.5A patent/CN110740473B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017152723A1 (en) * | 2016-03-07 | 2017-09-14 | 大唐移动通信设备有限公司 | Data transmission method, apparatus and system |
| CN107249218A (en) * | 2017-06-05 | 2017-10-13 | 东南大学 | Radio Resource and the combined distributing method of cloud resource in a kind of MEC |
| CN107682443A (en) * | 2017-10-19 | 2018-02-09 | 北京工业大学 | Joint considers the efficient discharging method of the mobile edge calculations system-computed task of delay and energy expenditure |
| CN108901075A (en) * | 2018-06-28 | 2018-11-27 | 电子科技大学 | A kind of resource allocation methods based on GS algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110740473A (en) | 2020-01-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110740473B (en) | Management method for mobile edge calculation and edge server | |
| CN113242568B (en) | Task unloading and resource allocation method in uncertain network environment | |
| CN107995660B (en) | Joint task scheduling and resource allocation method supporting D2D-edge server unloading | |
| CN110543336B (en) | Edge calculation task unloading method and device based on non-orthogonal multiple access technology | |
| CN111240701A (en) | Task unloading optimization method for end-edge-cloud collaborative computing | |
| CN110941667A (en) | Method and system for calculating and unloading in mobile edge calculation network | |
| CN112015545B (en) | Task unloading method and system in vehicle edge computing network | |
| CN111930436A (en) | Random task queuing and unloading optimization method based on edge calculation | |
| CN109951873B (en) | Task unloading mechanism under asymmetric and uncertain information in fog computing of Internet of things | |
| CN110519370B (en) | Edge computing resource allocation method based on facility site selection problem | |
| CN110489176B (en) | Multi-access edge computing task unloading method based on boxing problem | |
| CN111949409B (en) | Method and system for unloading computing task in power wireless heterogeneous network | |
| CN111163143B (en) | Low-delay task unloading method for mobile edge calculation | |
| CN111459662B (en) | Migration management method, migration management device and storage medium in mobile edge computing | |
| CN113867843B (en) | Mobile edge computing task unloading method based on deep reinforcement learning | |
| CN112188627B (en) | Dynamic resource allocation strategy based on state prediction | |
| CN114449529A (en) | Resource allocation optimization method and device based on mobile edge calculation and storage medium | |
| CN112866006A (en) | Cloud and mist fusion network multi-target task unloading method based on time delay energy consumption balance | |
| CN113573363A (en) | MEC calculation unloading and resource allocation method based on deep reinforcement learning | |
| CN113645637A (en) | Method and device for unloading tasks of ultra-dense network, computer equipment and storage medium | |
| CN116384504A (en) | Federal migration learning system | |
| CN111511028A (en) | Multi-user resource allocation method, device, system and storage medium | |
| CN112596910B (en) | Cloud computing resource scheduling method in multi-user MEC system | |
| CN112905315A (en) | Task processing method, device and equipment in Mobile Edge Computing (MEC) network | |
| CN116996938A (en) | Internet of vehicles task unloading method, terminal equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |