CN110177383B - Efficiency optimization method based on task scheduling and power allocation in mobile edge calculation - Google Patents

Efficiency optimization method based on task scheduling and power allocation in mobile edge calculation Download PDF

Info

Publication number
CN110177383B
CN110177383B CN201910428013.1A CN201910428013A CN110177383B CN 110177383 B CN110177383 B CN 110177383B CN 201910428013 A CN201910428013 A CN 201910428013A CN 110177383 B CN110177383 B CN 110177383B
Authority
CN
China
Prior art keywords
mobile
mobile device
mec server
sub
mec
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
Application number
CN201910428013.1A
Other languages
Chinese (zh)
Other versions
CN110177383A (en
Inventor
刘楚波
肖素容
李肯立
李敏灿
阳王东
李克勤
廖湘科
张尧学
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.)
Hunan University
Original Assignee
Hunan 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 Hunan University filed Critical Hunan University
Priority to CN201910428013.1A priority Critical patent/CN110177383B/en
Publication of CN110177383A publication Critical patent/CN110177383A/en
Application granted granted Critical
Publication of CN110177383B publication Critical patent/CN110177383B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • H04L67/50—Network services
    • H04L67/535—Tracking the activity of the user
    • 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
    • H04L67/50—Network services
    • H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
    • 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
    • H04W28/06—Optimizing the usage of the radio link, e.g. header compression, information sizing, discarding information
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W52/00—Power management, e.g. TPC [Transmission Power Control], power saving or power classes
    • H04W52/04—TPC
    • H04W52/30—TPC using constraints in the total amount of available transmission power
    • H04W52/34—TPC management, i.e. sharing limited amount of power among users or channels or data types, e.g. cell loading

Abstract

The invention discloses an efficiency optimization method based on task scheduling and power distribution in mobile edge calculation, which comprises the following steps: receiving data information sent by all mobile devices, including data volume to be processed and unit data workload, evenly distributing all the mobile devices to all MEC servers in a random mode, aiming at each MEC server, calculating the preference degree of each mobile device distributed to the MEC server to each sub-channel used by the MEC server according to the data information from each mobile device, adding the mobile device into a request list of sub-channels corresponding to the maximum preference degree, calculating the preference degree of each mobile device in the request list of the sub-channel to each sub-channel of each MEC server, and matching the sub-channel with the mobile device corresponding to the maximum preference degree in the obtained plurality of preference degrees. The method is suitable for a mobile edge computing system with a plurality of MEC servers, multiple users and a single task, and has high optimization efficiency.

Description

Efficiency optimization method based on task scheduling and power allocation in mobile edge calculation
Technical Field
The invention belongs to the technical field of edge computing, and particularly relates to an efficiency optimization method based on task scheduling and power allocation in mobile edge computing.
Background
With the generalization of mobile devices such as mobile phones and tablet computers, various mobile applications are continuously emerging, such as real-time network game applications, augmented reality applications, ultra-high-definition video streaming applications, and the like. The use of these mobile applications relies on real-time smooth communication and efficient and intensive computing, but the current mobile devices have very limited battery capacity and computing power and cannot meet the requirements of mobile application use. To solve this problem, Mobile Edge Computing (MEC) is proposed as a new architecture for providing Computing services to Mobile devices nearby. In a mobile edge computing architecture, a mobile device may send compute-intensive tasks to a nearby MEC server via wireless transmission, with the server performing its computing tasks and feeding back the results to the mobile device after they are generated. The method not only shortens the delay of the mobile application, but also saves the energy consumption of the mobile device.
The efficiency of an MEC system depends largely on the task offloading policy and the transmit power allocation policy adopted by the system, and the two policies are formulated in consideration of the characteristics of the computing task (i.e., computing data), the characteristics of the wireless channel, and the state of the MEC server. To improve the work efficiency of MEC systems, it is often necessary to use an efficiency optimization method based on task offloading and transmit power allocation strategies to shorten the completion time for the MEC server to finish processing data from all mobile devices.
The existing efficiency optimization method mainly aims at an MEC system comprising an MEC server and a mobile device (the mobile device has a plurality of computing tasks), and an MEC system comprising an MEC server and a plurality of mobile devices (each mobile device has only one computing task), but has some non-negligible technical problems: firstly, the existing efficiency optimization method only considers the time delay problem of the mobile equipment, but does not provide optimization for the system efficiency from the perspective of the whole MEC system, thereby resulting in low optimization efficiency; in addition, the existing efficiency optimization method cannot be applied to an MEC system comprising a plurality of MEC servers and a plurality of mobile devices (each mobile device has only one computing task), which causes the efficiency optimization method to have great limitation.
Disclosure of Invention
Aiming at the defects or improvement requirements of the prior art, the invention provides a mobile edge computing system efficiency optimization method based on task unloading scheduling and transmission power allocation, aiming at completing efficiency optimization by globally and integrally scheduling the unloading decision and power adjustment of tasks on the level of the whole system, so that the technical problem that the optimization efficiency is low because the existing efficiency optimization method does not optimize the system efficiency from the perspective of the whole MEC system can be solved; in addition, the invention is applicable to multi-MEC server, multi-user, single-task mobile edge computing systems.
To achieve the above object, according to an aspect of the present invention, there is provided a method for optimizing efficiency based on task scheduling and power allocation in mobile edge computing, which is provided on an MEC server in a mobile edge computing system including a plurality of MEC servers and mobile devices, the method including the steps of:
(1) receiving data information sent by all mobile devices, including the amount of data to be processed and the unit data workload, wherein all the mobile devices form a mobile device set Users {1, 2, … U }, where U represents the total number of the mobile devices, and d represents the total number of the mobile devicesuRepresents the amount of pending data for the U th mobile device, U ∈ [1, U]，cuMeans for indicating a unit data workload of the u th mobile station;
(2) distributing all the mobile devices to all MEC Servers in a random mode, wherein all the MEC Servers form an MEC server set Server {1, 2, … S }, and S represents the total number of MEC Servers;
(3) aiming at each MEC server, calculating the preference degree of each mobile device distributed to the MEC server to each sub-channel used by the MEC server, and adding the mobile device into a request list of the sub-channel corresponding to the maximum preference degree;
(4) calculating the preference degree of each subchannel to each mobile equipment in the request list of the subchannel aiming at each subchannel of each MEC server, and matching the subchannel with the mobile equipment corresponding to the maximum preference degree in the obtained plurality of preference degrees;
(5) for each sub-channel, calculating the preference degree of the mobile equipment to each MEC server according to the matching result of the sub-channel and the corresponding mobile equipment obtained in the step (4), and adding the mobile equipment into a request list of the MEC server corresponding to the maximum preference degree;
(6) for each MEC server, calculating the preference degree of the MEC server to each mobile device in the request list of the MEC server according to the data information received from the mobile device in the step (1) and the matching result of the sub-channel and the corresponding mobile device obtained in the step (4), and matching the MEC server with the mobile device corresponding to the minimum preference degree in the obtained preference degrees;
(7) adjusting the transmitting power of each mobile device one by one according to the matching results of the step (4) and the step (6);
(8) adding 1 to the iteration times, judging whether the iteration times reach a threshold value, if so, turning to the step (10), and otherwise, turning to the step (9);
(9) acquiring the total time required by each MEC server to finish processing the data sent by the mobile equipment according to the matching result obtained in the step (4) and the step (6) and the adjustment result of the transmitting power in the step (7), judging whether the difference value between the total time and the total time obtained in the last iteration process is smaller than a preset threshold value, if so, entering the step (10), otherwise, returning to the step (3);
(10) and (4) feeding back the matching results obtained in the steps (4) and (6) and the adjustment result of the transmitting power in the step (7) to each mobile device.
Preferably, in step (3), the mth mobile device to the mth MEC server is calculated (where S ∈ [1, S)]) The nth sub-channel (where N ∈ [1, N)]Where N represents the total number of subchannels used by the MEC server) preference level βu(n) is according to the following formula:
Figure BDA0002068095030000031
where W is the sub-channel bandWidth, omega1Is the equilibrium coefficient (the value range is 10)6To 108)，puRepresents the transmit power of the u-th mobile device,
Figure BDA0002068095030000041
is the channel gain for the nth station mobile to transmit data to the ith station server through the nth subchannel,
Figure BDA0002068095030000042
is the signal to interference plus noise ratio of the nth sub-channel from the mobile station to the server.
Preferably, the signal to interference plus noise ratio of the s-th server is obtained by the following formula:
Figure BDA0002068095030000043
wherein sigma2Representing background noise in a moving edge computing system, and
Figure BDA0002068095030000044
Usrepresenting the set of mobile devices assigned to the s-th MEC server,
Figure BDA0002068095030000045
indicating that the u-th mobile device can finally transmit its pending data volume to the s-th MEC server via the n-th sub-channel,
Figure BDA0002068095030000046
it means that the u-th mobile station is not able to finally transmit its pending data volume to the s-th MEC server via the n-th sub-channel.
Preferably, in step (4), the preference degree of the nth sub-channel to the u-th mobile device is calculated according to the following formula:
Figure BDA0002068095030000047
preferably, in step (5), the preference degree of the u-th mobile device to the s-th MEC server is calculated by using the following formula:
Figure BDA0002068095030000048
wherein ω is2Is the coefficient of balance of the process,
Figure BDA0002068095030000049
the data transmission rate of the nth mobile station transmitting data to the s th server through the nth sub-channel is as follows:
Figure BDA00020680950300000410
preferably, in step (6), the following formula is used to calculate the preference degree of the s-th MEC server for the u-th mobile device:
Figure BDA0002068095030000051
wherein
Figure BDA0002068095030000052
Is all mobile devices U transmitting data on the nth sub-channelnAverage number of CPU revolutions required, and
Figure BDA0002068095030000053
Figure BDA0002068095030000054
is the average execution frequency of all MEC servers, fsIndicating the execution frequency of the s-th MEC server.
Preferably, step (7) comprises the sub-steps of:
(7-1) setting the optional power set PL ═ p1,p2,…,pL]Where L represents the total number of selectable powers. And the selectable powers have the following relationship:
pmax＝p1＞p2＞…＞pL＞0，
wherein p ismaxRepresenting an initial transmit power for each mobile device;
(7-2) calculating the transmission time of the u-th station mobile equipment according to the data information sent by the mobile equipment and received in the step (1)
Figure BDA0002068095030000055
And start execution time
Figure BDA0002068095030000056
(7-3) judging whether the transmission time of the u mobile station is equal to the starting execution time, if so, ending the process, otherwise, turning to the step (7-4);
(7-4) finding the power p from the candidate powers PLlSo that it satisfies the following conditions, andlset to the transmit power of the u mobile, where L ∈ [1, L]：
Figure BDA0002068095030000057
Preferably, step (7-2) is specifically: the method comprises the following specific steps:
first, the data transmission time of the u-th mobile station is calculated as follows:
Figure BDA0002068095030000058
then, the execution time of the u-th mobile station is calculated as:
Figure BDA0002068095030000059
subsequently, a set U is obtainedsThe sequence formed by all the mobile devices in the system is arranged according to the sequence of arriving at the s-th server
Figure BDA0002068095030000061
(it isMiddle | UsI represents the set UsThe number of mobile devices in the group);
and finally, acquiring the starting execution time of the u-th mobile equipment according to the three parameters and by adopting the following formula:
Figure BDA0002068095030000062
in general, compared with the prior art, the above technical solution contemplated by the present invention can achieve the following beneficial effects:
1. because the invention adopts the steps (3) to (7) to shorten the time interval of the MEC server for processing the data sent by different mobile devices, the technical problem that the optimization efficiency is low because the optimization is not provided for the system efficiency from the perspective of the whole MEC system in the existing optimization method can be solved;
2. the invention has wide application range, and can be suitable for a plurality of MEC servers, a multi-user and single-task mobile edge computing system, a single MEC server, a single-user and multi-task system, a single MEC server and a multi-user mobile edge computing system;
3. by adopting the matching scheme of the invention, the system efficiency is improved by more than 4 times on average compared with the matching scheme of selecting the MEC server according to the close distance, and is improved by more than 100 times on average compared with the random matching scheme.
Drawings
FIG. 1 is a flow chart of an efficiency optimization method based on task scheduling and power allocation in mobile edge computing according to 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 described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
The invention divides the realization process of the efficiency optimization of the mobile edge computing system into two parts of task unloading scheduling and transmitting power distribution. Wherein, if the exhaustive method is adopted to search the optimal scheme of task unloading scheduling, the complexity of a system comprising 20 mobile devices and 8 MEC servers reaches 10 orders of magnitude26It is high. The invention then further divides the task unloading scheduling into device-server scheduling and device-subchannel scheduling, and adopts preference matching methods to respectively solve the problems, wherein the idea of the preference matching method is to select an optimal matching scheme according to the preference of matching parties to each other; the transmission power distribution of the invention is realized by using a heuristic algorithm on the basis of completing the task unloading scheduling.
The invention is suitable for a mobile edge computing system with a plurality of mobile devices and a plurality of MEC servers. The MEC servers are small data centers deployed by telecommunication operators, and have certain storage capacity and computing capacity, so that the MEC servers can store task input data of the mobile devices and compute tasks for the mobile devices. The whole frequency spectrum of the base station where each MEC server is located is divided into a plurality of sub-channels with the same bandwidth, so that the MEC server can simultaneously receive data transmitted by a plurality of mobile devices.
As shown in fig. 1, the method for optimizing efficiency based on task scheduling and power allocation in mobile edge computing according to the present invention is provided on one MEC server in a mobile edge computing system including a plurality of MEC servers and mobile devices, and the method includes the following steps:
(1) receiving data information sent by all mobile devices, including pending data amount and unit data workload (which is equal to total workload/pending data amount), wherein all mobile devices form a mobile device set Users ═ 1, 2, … U, where U represents the total number of mobile devices, d represents the total number of mobile devices, andurepresenting the amount of pending data for the U-th mobile device (where U ∈ [1, U)]) The unit is bit, cuRepresenting the unit data workload of the u mobile equipment, the unit is revolution/bit;
(2) distributing all the mobile devices to all MEC Servers in a random mode, wherein all the MEC Servers form an MEC server set Server {1, 2, … S }, and S represents the total number of MEC Servers;
(3) aiming at each MEC server, calculating the preference degree of each mobile device distributed to the MEC server to each sub-channel used by the MEC server, and adding the mobile device into a request list of the sub-channel corresponding to the maximum preference degree;
in this step, the u mobile device is computed for the S MEC server (where S ∈ [1, S)]) The nth sub-channel (where N ∈ [1, N)]Where N represents the total number of subchannels used by the MEC server) preference level βu(n) is according to the following formula:
Figure BDA0002068095030000081
where W is the subchannel bandwidth, ω1Is the equilibrium coefficient (the value range is 10)6To 108)，puRepresents the transmit power of the u-th mobile device,
Figure BDA0002068095030000082
is the channel gain for the nth station mobile to transmit data to the ith station server through the nth subchannel,
Figure BDA0002068095030000083
the Signal to Interference plus Noise Ratio (SINR) for the nth sub-channel data transmitted from the mobile station to the s-th server is expressed as follows:
Figure BDA0002068095030000084
wherein sigma2Representing background noise in a moving edge computing system, and
Figure BDA0002068095030000085
wherein U issRepresenting the set of mobile devices assigned to the s-th MEC server,
Figure BDA0002068095030000086
is a value of 0 or 1,
Figure BDA0002068095030000087
indicating that the u-th mobile device can finally transmit its pending data volume to the s-th MEC server via the n-th sub-channel,
Figure BDA0002068095030000088
it means that the u-th mobile station is not able to finally transmit its pending data volume to the s-th MEC server via the n-th sub-channel.
(4) Calculating the preference degree of each subchannel to each mobile equipment in the request list of the subchannel aiming at each subchannel of each MEC server, and matching the subchannel with the mobile equipment corresponding to the maximum preference degree in the obtained plurality of preference degrees;
in this step, the preference degree of the nth sub-channel to the uth mobile device is calculated according to the following formula:
Figure BDA0002068095030000091
(5) for each sub-channel, calculating the preference degree of the mobile equipment to each MEC server according to the matching result of the sub-channel and the corresponding mobile equipment obtained in the step (4), and adding the mobile equipment into a request list of the MEC server corresponding to the maximum preference degree;
in this step, the preference degree of the u-th mobile device to the s-th MEC server is calculated by using the following formula:
Figure BDA0002068095030000092
wherein ω is2Is the equilibrium coefficient (the value range is 10)6To 108)，
Figure BDA0002068095030000093
The data transmission rate of the nth mobile station transmitting data to the s th server through the nth sub-channel is as follows:
Figure BDA0002068095030000094
(6) for each MEC server, calculating the preference degree of the MEC server to each mobile device in the request list of the MEC server according to the data information received from the mobile device in the step (1) and the matching result of the sub-channel and the corresponding mobile device obtained in the step (4), and matching the MEC server with the mobile device corresponding to the minimum preference degree in the obtained preference degrees;
in this step, the following formula is adopted to calculate the preference degree of the mth MEC server to the uth mobile device:
Figure BDA0002068095030000095
wherein
Figure BDA0002068095030000096
Is all mobile devices U transmitting data on the nth sub-channelnAverage number of CPU revolutions required, and
Figure BDA0002068095030000097
Figure BDA0002068095030000098
is the average execution frequency of all MEC servers, fsIndicating the execution frequency of the s-th MEC server.
(7) Adjusting the transmitting power of each mobile device one by one according to the matching results of the step (4) and the step (6);
the method comprises the following substeps:
(7-1) setting the optional power set PL ═ p1,p2,…,pL]Where L represents the total number of selectable powers. And the selectable powers have the following relationship:
pmax＝p1＞p2＞…＞pL＞0，
wherein p ismaxRepresents the initial transmit power of each mobile device, which is equal to 100 dBm;
(7-2) calculating the transmission time of the u-th station mobile equipment according to the data information sent by the mobile equipment and received in the step (1)
Figure BDA0002068095030000107
And start execution time
Figure BDA0002068095030000102
(the transmission time must be equal to or less than the start execution time);
the method comprises the following specific steps:
first, the data transmission time of the u-th mobile station is calculated as follows:
Figure BDA0002068095030000103
then, the execution time of the u-th mobile station is calculated as:
Figure BDA0002068095030000104
subsequently, a set U is obtainedsThe sequence formed by all the mobile devices in the system is arranged according to the sequence of arriving at the s-th server
Figure BDA0002068095030000105
(wherein | UsI represents the set UsThe number of mobile devices in the group);
and finally, acquiring the starting execution time of the u-th mobile equipment according to the three parameters and by adopting the following formula:
Figure BDA0002068095030000106
the data of the mobile equipment can be executed only when 1) the data is transmitted to the corresponding MEC server, and 2) the corresponding MEC server finishes processing the data which arrives earlier;
(7-3) judging whether the transmission time of the u mobile station is equal to the starting execution time, if so, ending the process, otherwise, turning to the step (7-4);
(7-4) finding the power p from the candidate powers PLlSo that it satisfies the following conditions, andlset to the transmit power of the u mobile, where L ∈ [1, L]：
Figure BDA0002068095030000111
(8) Add 1 to the number of iterations and determine if the number of iterations has reached a threshold (the value of which is taken from the interval [10, 10 ]5]) If yes, the step (10) is carried out, otherwise, the step (9) is carried out;
(9) obtaining the total time required by each MEC server to finish processing the data sent by the mobile equipment according to the matching result obtained in the step (4) and the step (6) and the adjustment result of the transmitting power in the step (7), and judging whether the difference value between the total time and the total time obtained in the last iteration process is less than a preset threshold (the threshold is equal to 10)-5) If the comparison result is less than the preset value, the step (10) is carried out, otherwise, the step (3) is returned;
(10) feeding back the matching results obtained in the step (4) and the step (6) and the adjustment result of the transmitting power in the step (7) to each mobile device;
specifically, the results include which MEC server in the system each mobile device needs to transmit data to, over which sub-channel to transmit data, and what transmit power to use to send the data.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.

Claims (8)

1. A method for optimizing efficiency based on task scheduling and power allocation in mobile edge computing, which is arranged on an MEC server in a mobile edge computing system comprising a plurality of MEC servers and mobile equipment, is characterized by comprising the following steps:
(1) receiving data information sent by all mobile devices, including the amount of data to be processed and the unit data workload, wherein all the mobile devices form a mobile device set Users {1, 2, … U }, where U represents the total number of the mobile devices, and d represents the total number of the mobile devicesuRepresents the amount of pending data for the U th mobile device, U ∈ [1, U]，cuMeans for indicating a unit data workload of the u th mobile station;
(2) distributing all the mobile devices to all MEC Servers in a random mode, wherein all the MEC Servers form an MEC server set Server {1, 2, … S }, and S represents the total number of MEC Servers;
(3) aiming at each MEC server, calculating the preference degree of each mobile device distributed to the MEC server to each sub-channel used by the MEC server, and adding the mobile device into a request list of the sub-channel corresponding to the maximum preference degree;
(4) calculating the preference degree of each subchannel to each mobile equipment in the request list of the subchannel aiming at each subchannel of each MEC server, and matching the subchannel with the mobile equipment corresponding to the maximum preference degree in the obtained plurality of preference degrees;
(5) for each sub-channel, calculating the preference degree of the mobile equipment to each MEC server according to the matching result of the sub-channel and the corresponding mobile equipment obtained in the step (4), and adding the mobile equipment into a request list of the MEC server corresponding to the maximum preference degree;
(6) for each MEC server, calculating the preference degree of the MEC server to each mobile device in the request list of the MEC server according to the data information received from the mobile device in the step (1) and the matching result of the sub-channel and the corresponding mobile device obtained in the step (4), and matching the MEC server with the mobile device corresponding to the minimum preference degree in the obtained preference degrees;
(7) adjusting the transmitting power of each mobile device one by one according to the matching results of the step (4) and the step (6);
(8) adding 1 to the iteration times, judging whether the iteration times reach a threshold value, if so, turning to the step (10), and otherwise, turning to the step (9);
(9) acquiring the total time required by each MEC server to finish processing the data sent by the mobile equipment according to the matching result obtained in the step (4) and the step (6) and the adjustment result of the transmitting power in the step (7), judging whether the difference value between the total time and the total time obtained in the last iteration process is smaller than a preset threshold value, if so, entering the step (10), otherwise, returning to the step (3);
(10) and (4) feeding back the matching results obtained in the steps (4) and (6) and the adjustment result of the transmitting power in the step (7) to each mobile device.
2. The efficiency optimization method of claim 1, wherein in step (3), the preference degree β of the u-th mobile device for the n-th sub-channel of the s-th MEC server is calculatedu(n) is according to the following formula:
Figure FDA0002584750420000021
wherein S ∈ [1, S]，n∈[1，N]Where N denotes the total number of subchannels used by the MEC server, W is the subchannel bandwidth, ω1Is an equilibrium coefficient having a value in the range of 106To 108，puRepresents the transmit power of the u-th mobile device,
Figure FDA0002584750420000025
is the channel gain for the nth station mobile to transmit data to the ith station server through the nth subchannel,
Figure FDA0002584750420000022
is the signal to interference plus noise ratio of the nth sub-channel from the mobile station to the server.
3. The efficiency optimization method of claim 2, wherein the signal to interference plus noise ratio of the s-th server is obtained by the following formula:
Figure FDA0002584750420000023
wherein sigma2Representing background noise in a moving edge computing system, and
Figure FDA0002584750420000024
Usrepresenting the set of mobile devices assigned to the s-th MEC server,
Figure FDA0002584750420000031
indicating that the u-th mobile device can finally transmit its pending data volume to the s-th MEC server via the n-th sub-channel,
Figure FDA0002584750420000032
it means that the u-th mobile station is not able to finally transmit its pending data volume to the s-th MEC server via the n-th sub-channel.
4. The efficiency optimization method of claim 3, wherein in step (4), the preference degree of the nth sub-channel for the uth mobile station is calculated according to the following formula:
Figure FDA0002584750420000033
wherein ω is2Is the equilibrium coefficient.
5. The efficiency optimization method of claim 4, wherein in the step (5), the preference degree of the u-th mobile device for the s-th MEC server is calculated by using the following formula:
Figure FDA0002584750420000034
wherein
Figure FDA0002584750420000035
The data transmission rate of the nth mobile station transmitting data to the s th server through the nth sub-channel is as follows:
Figure FDA0002584750420000036
6. the efficiency optimization method of claim 5, wherein in the step (6), the preference degree of the s-th MEC server for the u-th mobile device is calculated by using the following formula:
Figure FDA0002584750420000037
wherein
Figure FDA0002584750420000038
Is all mobile devices U transmitting data on the nth sub-channelnAverage number of CPU revolutions required, and
Figure FDA0002584750420000039
Figure FDA00025847504200000310
is the average execution frequency of all MEC servers, fsIndicating the execution frequency of the s-th MEC server.
7. The efficiency optimization method according to claim 6, wherein step (7) comprises the sub-steps of:
(7-1) setting the optional power set PL ═ p1,p2,…,pL]Wherein L represents mayThe total number of the selected powers is selected, and the selectable powers have the following relation:
pmax＝p1＞p2＞…＞pL＞0，
wherein p ismaxRepresenting an initial transmit power for each mobile device;
(7-2) calculating the transmission time of the u-th station mobile equipment according to the data information sent by the mobile equipment and received in the step (1)
Figure FDA0002584750420000041
And start execution time
Figure FDA0002584750420000042
(7-3) judging whether the transmission time of the u mobile station is equal to the starting execution time, if so, ending the process, otherwise, turning to the step (7-4);
(7-4) finding the power p from the candidate powers PLlSo that it satisfies the following conditions, andlset to the transmit power of the u mobile, where L ∈ [1, L]：
Figure FDA0002584750420000043
8. The efficiency optimization method according to claim 7, wherein the step (7-2) is specifically: the method comprises the following specific steps:
first, the data transmission time of the u-th mobile station is calculated as follows:
Figure FDA0002584750420000044
then, the execution time of the u-th mobile station is calculated as:
Figure FDA0002584750420000045
subsequently, a set is acquiredClosed UsThe sequence formed by all the mobile devices in the system is arranged according to the sequence of arriving at the s-th server
Figure FDA0002584750420000046
Wherein | UsI represents the set UsThe number of the mobile devices;
finally, according to the data transmission time of the u mobile station
Figure FDA0002584750420000047
Execution time of the u-th mobile device
Figure FDA0002584750420000048
And set UsThe sequence phi formed by all the mobile devices in the system after the mobile devices are arranged according to the sequence of arriving at the s-th serversAnd obtaining the starting execution time of the u mobile station by adopting the following formula:
Figure FDA0002584750420000051
CN201910428013.1A 2019-05-22 2019-05-22 Efficiency optimization method based on task scheduling and power allocation in mobile edge calculation Active CN110177383B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910428013.1A CN110177383B (en) 2019-05-22 2019-05-22 Efficiency optimization method based on task scheduling and power allocation in mobile edge calculation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910428013.1A CN110177383B (en) 2019-05-22 2019-05-22 Efficiency optimization method based on task scheduling and power allocation in mobile edge calculation

Publications (2)

Publication Number Publication Date
CN110177383A CN110177383A (en) 2019-08-27
CN110177383B true CN110177383B (en) 2020-09-11

Family

ID=67691789

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910428013.1A Active CN110177383B (en) 2019-05-22 2019-05-22 Efficiency optimization method based on task scheduling and power allocation in mobile edge calculation

Country Status (1)

Country Link
CN (1) CN110177383B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111459662B (en) * 2020-03-18 2023-07-04 湖南大学 Migration management method, migration management device and storage medium in mobile edge computing
CN113542330B (en) * 2020-04-21 2023-10-27 中移(上海)信息通信科技有限公司 Mobile edge calculation data acquisition method and system

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106100907A (en) * 2016-08-15 2016-11-09 北京邮电大学 A kind of MEC server selection algorithm based on fairness
CN109413724A (en) * 2018-10-11 2019-03-01 重庆邮电大学 A kind of task unloading and Resource Allocation Formula based on MEC

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10848974B2 (en) * 2018-12-28 2020-11-24 Intel Corporation Multi-domain trust establishment in edge cloud architectures

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106100907A (en) * 2016-08-15 2016-11-09 北京邮电大学 A kind of MEC server selection algorithm based on fairness
CN109413724A (en) * 2018-10-11 2019-03-01 重庆邮电大学 A kind of task unloading and Resource Allocation Formula based on MEC

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Energy Efficient and Devices Priority Aware Computation Offloading to a Mobile Edge Computing Server;Youssef Hmimz;《IEEE》;20190426;全文 *
多用户移动边缘计算迁移的能量管理研究;王璐瑤;《物联网学报》;20190330;全文 *

Also Published As

Publication number Publication date
CN110177383A (en) 2019-08-27

Similar Documents

Publication Publication Date Title
CN109413724B (en) MEC-based task unloading and resource allocation scheme
CN109947545B (en) Task unloading and migration decision method based on user mobility
Bozorgchenani et al. Centralized and distributed architectures for energy and delay efficient fog network-based edge computing services
CN110798849A (en) Computing resource allocation and task unloading method for ultra-dense network edge computing
CN112105062B (en) Mobile edge computing network energy consumption minimization strategy method under time-sensitive condition
CN110493757B (en) Mobile edge computing unloading method for reducing system energy consumption under single server
CN107708152B (en) Task unloading method of heterogeneous cellular network
CN109756912B (en) Multi-user multi-base station joint task unloading and resource allocation method
CN111132191A (en) Method for unloading, caching and resource allocation of joint tasks of mobile edge computing server
CN109194763A (en) Caching method based on small base station self-organizing cooperative in a kind of super-intensive network
Saleem et al. Performance guaranteed partial offloading for mobile edge computing
Zhao et al. Task proactive caching based computation offloading and resource allocation in mobile-edge computing systems
Zhang et al. DMRA: A decentralized resource allocation scheme for multi-SP mobile edge computing
CN110177383B (en) Efficiency optimization method based on task scheduling and power allocation in mobile edge calculation
CN113407249B (en) Task unloading method facing to position privacy protection
Kim et al. Task popularity-based energy minimized computation offloading for fog computing wireless networks
CN112988347A (en) Edge computing unloading method and system for reducing system energy consumption and cost sum
KR102562732B1 (en) Apparatus and Method for Task Offloading of MEC-Based Wireless Network
Li et al. Computing-assisted task offloading and resource allocation for wireless vr systems
Paymard et al. Task scheduling based on priority and resource allocation in multi-user multi-task mobile edge computing system
CN111526526A (en) Task unloading method in mobile edge calculation based on service mashup
CN105451350A (en) Combined unicast and multicast mechanism-based resource allocation method
Lin et al. Optimizing AI service placement and computation offloading in mobile edge intelligence systems
Ni et al. Revenue-maximized offloading decision and fine-grained resource allocation in edge network
CN113162658A (en) Task unloading method based on quota-increasing matching in power line communication

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