CN111263401A - Multi-user cooperative computing unloading method based on mobile edge computing - Google Patents

Multi-user cooperative computing unloading method based on mobile edge computing Download PDF

Info

Publication number
CN111263401A
CN111263401A CN202010043845.4A CN202010043845A CN111263401A CN 111263401 A CN111263401 A CN 111263401A CN 202010043845 A CN202010043845 A CN 202010043845A CN 111263401 A CN111263401 A CN 111263401A
Authority
CN
China
Prior art keywords
execution
expression
idle
task
decision
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.)
Pending
Application number
CN202010043845.4A
Other languages
Chinese (zh)
Inventor
曲雯毓
姜巍
周晓波
邱铁
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tianjin University
Original Assignee
Tianjin University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tianjin University filed Critical Tianjin University
Priority to CN202010043845.4A priority Critical patent/CN111263401A/en
Publication of CN111263401A publication Critical patent/CN111263401A/en
Pending legal-status Critical Current

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
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H04L43/0876—Network utilisation, e.g. volume of load or congestion level
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/16—Threshold monitoring
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
    • H04L67/1004—Server selection for load balancing
    • H04L67/1008—Server selection for load balancing based on parameters of servers, e.g. available memory or workload
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
    • H04L67/1029—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers using data related to the state of servers by a load balancer
    • 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
    • H04W28/08—Load balancing or load distribution
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W72/00—Local resource management
    • H04W72/50—Allocation or scheduling criteria for wireless resources
    • H04W72/52—Allocation or scheduling criteria for wireless resources based on load
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Environmental & Geological Engineering (AREA)
  • Computer Hardware Design (AREA)
  • General Engineering & Computer Science (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

The invention discloses a multi-user cooperative computing unloading method based on mobile edge computing.A mobile device in an MEC service coverage area is divided into a busy device and an idle device according to the change of a task arrival rate, the computing resource of the idle device is utilized for cooperative computing unloading, and if a device j determines to update a decision matrix, the device j requests an MEC server to update a decision; step 10, other busy devices obtain the information of the update decision of the device j with the help of the MEC server and update the decision according to the step 6 in the same way; when the MEC server does not receive the request message for updating the decision matrix any more, the convergence state of the system is reached, and the decision matrix D is the optimal cooperative computing unloading method. Compared with the prior art, the method and the device can expand the computing capability of the system under the condition that a single small-sized base station provides computing resources for users in the area, reduce the average task response time delay, enable the users to obtain better user experience, and can better improve the performance of the whole system.

Description

Multi-user cooperative computing unloading method based on mobile edge computing
Technical Field
The invention belongs to the technical field of wireless communication, and particularly relates to multi-user cooperative computing unloading under a communication system architecture of mobile edge computing.
Background
With the development of more and more applications such as Computer Vision (CV), Artificial Intelligence (AI), etc., mobile devices used daily cannot provide a satisfactory user experience due to limitations in computing power and battery capacity, etc. Moving Edge Computing (MEC), an emerging computing technology, has attracted widespread attention in recent years in both academic and industrial sectors. MECs can provide computing resources at the edge of a cellular network near a mobile device. But since the MEC server is "shared" by all mobile devices, the limited computing resources on the MEC server are not always sufficient to support all mobile devices within its coverage. And while offloading tasks to a more computationally powerful MEC server may reduce task response delays, data is transmitted to the MEC server over a wireless channel, which results in additional transmission delays and energy consumption. The existing multi-user offloading method is based on either cooperative offloading of the device locally with the MEC server or cooperative offloading of the introduced D2D. These offloading methods do not make good use of the computing resources in the entire system, and may result in long delay and poor user experience in the face of situations where the base station has weak computing power and the user has a large task computing requirement.
Therefore, how to design an efficient computation offloading method to improve the performance of the MEC system in terms of both task execution delay and energy consumption is a key and fundamental problem of the MEC system. The existing methods for solving the problems are divided into three categories: 1) the mobile device independently makes an unloading decision, and once the utilization rate of the computing resources exceeds a certain threshold value of the MEC server, the task is unloaded to the remote cloud by using the method. The execution delay of the task increases due to the backbone network transmission delay. 2) The mobile devices cooperate to make offloading decisions, which provides the computing resources of the MEC server based on priority, in which case only a portion of the handset devices may enjoy the benefits of computing offloading. 3) Device-to-device (D2D) computing offload is allowed, and the mobile device may offload tasks to MEC servers or to neighboring computing nodes over D2D links. But D2D communication is limited due to the short communication range of D2D.
Disclosure of Invention
Aiming at the technical problem of computation unloading of a multi-user MEC system, the invention provides a multi-user cooperative computation unloading method based on mobile edge computation.
The invention discloses a multi-user cooperative computing unloading method based on mobile edge computing, which comprises the following steps:
step 1, initializing the total number of devices N in an area, wherein a task reaches each device at the beginning of each time slot, and can be executed locally, or be unloaded to an MEC server and executed on the MEC server at the same time, or be unloaded to an idle device through the MEC server and executed on the idle device;
step 2, dividing the equipment into busy equipment J and idle equipment K according to the task arrival rate;
step 3, initializing equipment parameters, task parameters and communication link parameters; initializing a decision matrix D of the equipment to be all local execution;
step 4, determining that the slice of the task is allocated to K idle equipment;
step 5, judging whether the device j reaches the task I in the time slot tt,j.
Step 6, considering the execution situation of the tasks at 3 destinations respectively: the total CPU cycle required to process this task is St,jThe energy consumed per processing one CPU cycle is et,jThe complete computing power of device j is CjThe ratio available is βt，j；
Case one, local execution:
the expression of the time required by local execution is as follows:
Figure BDA0002368681360000031
the locally executed energy consumption expression is:
Figure BDA0002368681360000032
the execution load expression of the local execution is:
Figure BDA0002368681360000033
wherein, λ is a weight proportion parameter;
case two, MEC offload execution:
the wireless network link transmission rate expression is as follows:
Figure BDA0002368681360000034
the data transmission time expression is:
Figure BDA0002368681360000035
the local computation time expression is:
Figure BDA0002368681360000036
the expression for the time required for MEC offload execution is:
Figure BDA0002368681360000037
wherein Q ist,jA dynamic function queuing MEC server tasks;
the expression for MEC offload execution energy consumption is:
Figure BDA0002368681360000038
the expression for the MEC to offload the execution load of execution is:
Figure BDA0002368681360000041
case three, idle device offload execution:
the task is unloaded to a plurality of idle devices through the MEC server, and in order to ensure that the parallel computing time of the task on the idle devices is shortest, the mode theta of distributing the slice of the task to the K idle devices is determinedt,k；
The time when the task is sliced to be distributed to the idle device K at the MEC server comprises data transmission time and K calculation time:
the expression of the data transmission time is:
Figure BDA0002368681360000042
the task reaches a plurality of idle devices, and the calculation time of the slicing task executed on the device K is calculated as follows:
the expression for K calculation time is:
Figure BDA0002368681360000043
the expression of total time and allocation target is:
Figure BDA0002368681360000044
the expression of the time required for the idle device to unload execution is:
Figure BDA0002368681360000045
the expression for idle device offload execution energy consumption is:
Figure BDA0002368681360000046
the expression of the execution load that the idle device offloads execution is:
Figure BDA0002368681360000047
step 6, comparing and selecting the destination with the minimum system load according to the following conditions:
when in use
Figure BDA0002368681360000048
And is
Figure BDA0002368681360000049
When the execution is selected, local execution is selected;
when in use
Figure BDA0002368681360000051
And is
Figure BDA0002368681360000052
Selecting MEC to unload and execute;
when in use
Figure BDA0002368681360000053
And is
Figure BDA0002368681360000054
When the idle equipment is selected to unload and execute;
step 7, this is the optimal decision of the device j in the time slot t
Figure BDA0002368681360000055
If it is not
Figure BDA0002368681360000056
Updating the decision matrix;
step 8, if the equipment j determines to update the decision matrix, the equipment j sends an update decision request message to the MEC server;
step 9, the MEC server receives the request for updating the decision and sends back a confirmation message to update the optimal decision;
step 10, other busy devices obtain information of an update decision of the device j with the help of the MEC server, know the use condition of the computing resources of the current system and update the decision according to the step 6 in the same way;
when the MEC server does not receive the request message for updating the decision matrix any more, the convergence state of the system is reached; at this time, the decision matrix D is the optimal collaborative computing offloading method.
Compared with the prior art, the method and the device can expand the computing capability of the system under the condition that a single small-sized base station provides computing resources for users in the area, reduce the average task response time delay, enable the users to obtain better user experience, and better improve the performance of the whole system
Drawings
FIG. 1 is a flow chart of a method for offloading multi-user cooperative computing based on mobile edge computing according to the present invention;
fig. 2 is an example of mobile device distribution (number of busy devices 35, number of idle devices 15).
Detailed Description
The invention is further illustrated by the following figures and examples, which are not to be construed as limiting the invention.
As shown in fig. 1, a flow chart of a multi-user cooperative computing offloading method based on mobile edge computing according to the present invention is shown, and the specific operation steps are as follows:
step 1, initializing the total number of devices N in an area, wherein a task reaches each device at the beginning of each time slot, and can be executed locally, or be unloaded to an MEC server and executed on the MEC server at the same time, or be unloaded to an idle device through the MEC server and executed on the idle device;
step 2, dividing the equipment into busy equipment J and idle equipment K according to the task arrival rate (N is J + K);
step 3, initializing equipment parameters (including equipment position, equipment computing capability CN and MEC server computing capability C)mDevice power P), taskParameters (including calculating the size I of the input datat,jTotal CPU cycles S required to process the taskt，j＝αIt，jPartial unloaded proportionality coefficient is omega) and communication link parameters (including channel bandwidth B and channel gain G)NNoise power N0) Initializing a decision matrix D of the device to be all local execution;
step 4, the task can be unloaded to a plurality of idle devices through the MEC server, and in order to ensure that the time of parallel computing is the same, the slice of the task is determined to be distributed to K idle devices;
step 5, judging whether the device j reaches the task I in the time slot tt,j？
Step 6, considering the execution situation of the tasks at 3 destinations respectively: the total CPU cycle required to process this task is St,jThe energy consumed per processing one CPU cycle is et,j(effective switched-capacitance coefficient η depending on the chip architecture of the device.) the complete computing power of device j is CjThe ratio available is βt，j；
Case one, local execution:
the expression of the time required by local execution is as follows:
Figure BDA0002368681360000061
the locally executed energy consumption expression is:
Figure BDA0002368681360000062
the execution load expression of the local execution is:
Figure BDA0002368681360000063
wherein, λ is a weight proportion parameter;
case two, MEC offload execution:
the wireless network link transmission rate expression is as follows:
Figure BDA0002368681360000071
the data transmission time expression is:
Figure BDA0002368681360000072
the local computation time expression is:
Figure BDA0002368681360000073
the expression for the time required for MEC offload execution is:
Figure BDA0002368681360000074
wherein Q ist,jA dynamic function queuing MEC server tasks;
the expression for MEC offload execution energy consumption is:
Figure BDA0002368681360000075
the expression for the MEC to offload the execution load of execution is:
Figure BDA0002368681360000076
case three, idle device offload execution:
tasks can be unloaded to a plurality of idle devices through the MEC server, and in order to ensure that the time of parallel computation of the tasks on the idle devices is shortest, the mode theta of distributing the slices of the tasks to the K idle devices is determinedt,k。
The time when the task is sliced to be distributed to the idle device K at the MEC server comprises data transmission time and K calculation time:
the expression of the data transmission time is:
Figure BDA0002368681360000081
the task reaches a plurality of idle devices, and the calculation time of the slicing task executed on the device K is calculated as follows:
the expression for K calculation time is:
Figure BDA0002368681360000082
the expression of total time and allocation target is:
Figure BDA0002368681360000083
the expression of the time required for the idle device to unload execution is:
Figure BDA0002368681360000084
the expression for idle device offload execution energy consumption is:
Figure BDA0002368681360000085
the expression of the execution load that the idle device offloads execution is:
Figure BDA0002368681360000086
step 6, comparing and selecting the destination with the minimum system load according to the following conditions:
when in use
Figure BDA0002368681360000087
And is
Figure BDA0002368681360000088
When the execution is selected, local execution is selected;
when in use
Figure BDA0002368681360000089
And is
Figure BDA00023686813600000810
Selecting MEC to unload and execute;
when in use
Figure BDA00023686813600000811
And is
Figure BDA00023686813600000812
When the idle equipment is selected to unload and execute;
step 7, this is the optimal decision of the device j in the time slot t
Figure BDA00023686813600000813
If it is not
Figure BDA00023686813600000814
Updating the decision matrix;
step 8, if the equipment j determines to update the decision matrix, the equipment j sends an update decision request message to the MEC server;
step 9, the MEC server receives the request for updating the decision and sends back a confirmation message to update the optimal decision;
step 10, other busy devices obtain information of an update decision of the device j with the help of the MEC server, know the use condition of the computing resources of the current system and update the decision according to the step 6 in the same way;
when the MEC server does not receive the request message for updating the decision matrix any more, the convergence state of the system is reached; at this time, the decision matrix D is the optimal collaborative computing offloading method.

Claims (1)

1. A multi-user cooperative computing unloading method based on mobile edge computing is characterized by comprising the following steps:
step 1, initializing the total number of devices N in an area, wherein a task reaches each device at the beginning of each time slot, and can be executed locally, or be unloaded to an MEC server and executed on the MEC server at the same time, or be unloaded to an idle device through the MEC server and executed on the idle device;
step 2, dividing the equipment into busy equipment J and idle equipment K according to the task arrival rate;
step 3, initializing equipment parameters, task parameters and communication link parameters; initializing a decision matrix D of the equipment to be all local execution;
step 4, determining that the slice of the task is allocated to K idle equipment;
step 5, judging whether the device j reaches the task I in the time slot tt,j.
Step 6, considering the execution situation of the tasks at 3 destinations respectively: the total CPU cycle required to process this task is St,jThe energy consumed per processing one CPU cycle is et,jThe complete computing power of device j is CjThe ratio available is βt，j；
Case one, local execution:
the expression of the time required by local execution is as follows:
Figure FDA0002368681350000011
the locally executed energy consumption expression is:
Figure FDA0002368681350000012
the execution load expression of the local execution is:
Figure FDA0002368681350000013
wherein, λ is a weight proportion parameter;
case two, MEC offload execution:
the wireless network link transmission rate expression is as follows:
Figure FDA0002368681350000021
the data transmission time expression is:
Figure FDA0002368681350000022
the local computation time expression is:
Figure FDA0002368681350000023
the expression for the time required for MEC offload execution is:
Figure FDA0002368681350000024
wherein Q ist,jA dynamic function queuing MEC server tasks;
the expression for MEC offload execution energy consumption is:
Figure FDA0002368681350000025
the expression for the MEC to offload the execution load of execution is:
Figure FDA0002368681350000026
case three, idle device offload execution:
the task is unloaded to a plurality of idle devices through the MEC server, and in order to ensure that the parallel computing time of the task on the idle devices is shortest, the mode theta of distributing the slice of the task to the K idle devices is determinedt,k；
The time when the task is sliced to be distributed to the idle device K at the MEC server comprises data transmission time and K calculation time:
the expression of the data transmission time is:
Figure FDA0002368681350000031
the task reaches a plurality of idle devices, and the calculation time of the slicing task executed on the device K is calculated as follows:
the expression for K calculation time is:
Figure FDA0002368681350000032
the expression of total time and allocation target is:
Figure FDA0002368681350000033
the expression of the time required for the idle device to unload execution is:
Figure FDA0002368681350000034
the expression for idle device offload execution energy consumption is:
Figure FDA0002368681350000035
the expression of the execution load that the idle device offloads execution is:
Figure FDA0002368681350000036
step 6, comparing and selecting the destination with the minimum system load according to the following conditions:
when in use
Figure FDA0002368681350000037
And is
Figure FDA0002368681350000038
When the execution is selected, local execution is selected;
when in use
Figure FDA0002368681350000039
And is
Figure FDA00023686813500000310
Selecting MEC to unload and execute;
when in use
Figure FDA00023686813500000311
And is
Figure FDA00023686813500000312
When the idle equipment is selected to unload and execute;
step 7, this is the optimal decision of the device j in the time slot t
Figure FDA00023686813500000313
If it is not
Figure FDA00023686813500000314
Updating the decision matrix;
step 8, if the equipment j determines to update the decision matrix, the equipment j sends an update decision request message to the MEC server;
step 9, the MEC server receives the request for updating the decision and sends back a confirmation message to update the optimal decision;
step 10, other busy devices obtain information of an update decision of the device j with the help of the MEC server, know the use condition of the computing resources of the current system and update the decision according to the step 6 in the same way;
when the MEC server does not receive the request message for updating the decision matrix any more, the convergence state of the system is reached; at this time, the decision matrix D is the optimal collaborative computing offloading method.
CN202010043845.4A 2020-01-15 2020-01-15 Multi-user cooperative computing unloading method based on mobile edge computing Pending CN111263401A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010043845.4A CN111263401A (en) 2020-01-15 2020-01-15 Multi-user cooperative computing unloading method based on mobile edge computing

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010043845.4A CN111263401A (en) 2020-01-15 2020-01-15 Multi-user cooperative computing unloading method based on mobile edge computing

Publications (1)

Publication Number Publication Date
CN111263401A true CN111263401A (en) 2020-06-09

Family

ID=70952141

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010043845.4A Pending CN111263401A (en) 2020-01-15 2020-01-15 Multi-user cooperative computing unloading method based on mobile edge computing

Country Status (1)

Country Link
CN (1) CN111263401A (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112039965A (en) * 2020-08-24 2020-12-04 重庆邮电大学 Multitask unloading method and system in time-sensitive network
CN112600869A (en) * 2020-11-11 2021-04-02 南京邮电大学 Calculation unloading distribution method and device based on TD3 algorithm
CN113342409A (en) * 2021-04-25 2021-09-03 山东师范大学 Delay sensitive task unloading decision method and system for multi-access edge computing system
CN114189521A (en) * 2021-12-15 2022-03-15 福州大学 Method for cooperative computing offload in F-RAN architecture
CN114900860A (en) * 2022-05-05 2022-08-12 中国联合网络通信集团有限公司 Mobile terminal edge calculation method, device, edge calculation server and medium
CN115314942A (en) * 2022-07-11 2022-11-08 中国科学院深圳先进技术研究院 Load balancing method of unmanned aerial vehicle-assisted energy transmission mobile edge computing system

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090271502A1 (en) * 2007-10-09 2009-10-29 Xue Chuansong Data distribution method, data distribution system and relevant devices in edge network
CN106534333A (en) * 2016-11-30 2017-03-22 北京邮电大学 Bidirectional selection computing unloading method based on MEC and MCC
CN108809695A (en) * 2018-04-28 2018-11-13 国网浙江省电力有限公司电力科学研究院 A kind of distribution uplink unloading strategy towards mobile edge calculations
US20190141120A1 (en) * 2018-12-28 2019-05-09 Intel Corporation Technologies for providing selective offload of execution to the edge
CN110290507A (en) * 2019-05-28 2019-09-27 南京邮电大学 A kind of cache policy and frequency spectrum distributing method of D2D communication assistant edge caching system

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090271502A1 (en) * 2007-10-09 2009-10-29 Xue Chuansong Data distribution method, data distribution system and relevant devices in edge network
CN106534333A (en) * 2016-11-30 2017-03-22 北京邮电大学 Bidirectional selection computing unloading method based on MEC and MCC
CN108809695A (en) * 2018-04-28 2018-11-13 国网浙江省电力有限公司电力科学研究院 A kind of distribution uplink unloading strategy towards mobile edge calculations
US20190141120A1 (en) * 2018-12-28 2019-05-09 Intel Corporation Technologies for providing selective offload of execution to the edge
CN110290507A (en) * 2019-05-28 2019-09-27 南京邮电大学 A kind of cache policy and frequency spectrum distributing method of D2D communication assistant edge caching system

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
GUISHENG HU 等: "Multi-User Computation Offloading with D2D for Mobile Edge Computing", 《2018 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM)》 *
任静: "移动边缘网络三层处理架构中计算-通信资源调度策略研究", 《中国优秀硕士学位论文全文数据库（信息科技I辑）》 *

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112039965A (en) * 2020-08-24 2020-12-04 重庆邮电大学 Multitask unloading method and system in time-sensitive network
CN112039965B (en) * 2020-08-24 2022-07-12 重庆邮电大学 Multitask unloading method and system in time-sensitive network
CN112600869A (en) * 2020-11-11 2021-04-02 南京邮电大学 Calculation unloading distribution method and device based on TD3 algorithm
CN113342409A (en) * 2021-04-25 2021-09-03 山东师范大学 Delay sensitive task unloading decision method and system for multi-access edge computing system
CN114189521A (en) * 2021-12-15 2022-03-15 福州大学 Method for cooperative computing offload in F-RAN architecture
CN114189521B (en) * 2021-12-15 2024-01-26 福州大学 Method for collaborative computing offloading in F-RAN architecture
CN114900860A (en) * 2022-05-05 2022-08-12 中国联合网络通信集团有限公司 Mobile terminal edge calculation method, device, edge calculation server and medium
CN114900860B (en) * 2022-05-05 2024-04-02 中国联合网络通信集团有限公司 Edge computing method and device for mobile terminal, edge computing server and medium
CN115314942A (en) * 2022-07-11 2022-11-08 中国科学院深圳先进技术研究院 Load balancing method of unmanned aerial vehicle-assisted energy transmission mobile edge computing system

Similar Documents

Publication Publication Date Title
CN111263401A (en) Multi-user cooperative computing unloading method based on mobile edge computing
Zhang et al. Dynamic task offloading and resource allocation for mobile-edge computing in dense cloud RAN
CN108809695B (en) Distributed uplink unloading strategy facing mobile edge calculation
Jošilo et al. Decentralized algorithm for randomized task allocation in fog computing systems
CN109413724B (en) MEC-based task unloading and resource allocation scheme
CN111930436B (en) Random task queuing unloading optimization method based on edge calculation
Lee et al. An online secretary framework for fog network formation with minimal latency
CN109862592B (en) Resource management and scheduling method in mobile edge computing environment based on multi-base-station cooperation
Bozorgchenani et al. Centralized and distributed architectures for energy and delay efficient fog network-based edge computing services
US9955290B2 (en) Opportunistic offloading of tasks between nearby computing devices
Yu et al. Collaborative service placement for mobile edge computing applications
Labidi et al. Joint multi-user resource scheduling and computation offloading in small cell networks
WO2019200716A1 (en) Fog computing-oriented node computing task scheduling method and device thereof
CN110493757B (en) Mobile edge computing unloading method for reducing system energy consumption under single server
CN109756912B (en) Multi-user multi-base station joint task unloading and resource allocation method
Zhou et al. Markov approximation for task offloading and computation scaling in mobile edge computing
CN110149401B (en) Method and system for optimizing edge calculation task
CN114637608B (en) Calculation task allocation and updating method, terminal and network equipment
Xie et al. Dynamic service caching in mobile edge networks
CN112788698B (en) Data processing method and device and terminal equipment
Qu et al. Robust offloading scheduling for mobile edge computing
Shu et al. Joint offloading strategy based on quantum particle swarm optimization for MEC-enabled vehicular networks
Sato et al. Radio environment aware computation offloading with multiple mobile edge computing servers
Yang et al. Optimal task scheduling in communication-constrained mobile edge computing systems for wireless virtual reality
Guo et al. Dynamic computation offloading in multi-server MEC systems: An online learning approach

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
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20200609

WD01 Invention patent application deemed withdrawn after publication