CN111787618A - Energy consumption optimization resource allocation method for combining energy acquisition in edge calculation - Google Patents

Energy consumption optimization resource allocation method for combining energy acquisition in edge calculation Download PDF

Info

Publication number
CN111787618A
CN111787618A CN202010451272.9A CN202010451272A CN111787618A CN 111787618 A CN111787618 A CN 111787618A CN 202010451272 A CN202010451272 A CN 202010451272A CN 111787618 A CN111787618 A CN 111787618A
Authority
CN
China
Prior art keywords
energy consumption
energy
edge server
resource allocation
edge
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.)
Granted
Application number
CN202010451272.9A
Other languages
Chinese (zh)
Other versions
CN111787618B (en
Inventor
邝祝芳
朱伊
马志豪
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.)
Central South University of Forestry and Technology
Original Assignee
Central South University of Forestry and Technology
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 Central South University of Forestry and Technology filed Critical Central South University of Forestry and Technology
Priority to CN202010451272.9A priority Critical patent/CN111787618B/en
Publication of CN111787618A publication Critical patent/CN111787618A/en
Application granted granted Critical
Publication of CN111787618B publication Critical patent/CN111787618B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W72/00—Local resource management
    • H04W72/04—Wireless resource allocation
    • H04W72/044—Wireless resource allocation based on the type of the allocated resource
    • H04W72/0473—Wireless resource allocation based on the type of the allocated resource the resource being transmission power
    • 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
    • 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
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W72/00—Local resource management
    • H04W72/04—Wireless resource allocation
    • H04W72/044—Wireless resource allocation based on the type of the allocated resource
    • 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
    • H04W72/543—Allocation or scheduling criteria for wireless resources based on quality criteria based on requested quality, e.g. QoS
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Abstract

The invention discloses an energy consumption optimization resource allocation method for combining energy acquisition in edge calculation. The method mainly comprises the following steps: 1. and constructing a mathematical model of energy consumption optimization resource allocation combined with energy acquisition in edge calculation. 2. And constructing a Lagrangian function for the constructed mathematical model. 3. And solving the time and the charging power of the edge server for charging the mobile terminal equipment. 4. And solving the CPU frequency distributed by the end user and the CPU frequency distributed by the edge server. 5. And solving the transmission power from the terminal equipment to the edge server. 6. And solving an unloading decision variable unloaded from the task of the end user to the edge server. 7. And solving the energy consumption optimization resource allocation problem obtained by combining energy based on a gradient descent method. By applying the method and the device, the optimization problems of unloading decision combining energy acquisition, energy acquisition time, charging power distribution, transmission power distribution and CPU frequency distribution in edge calculation are solved, and the energy consumption of all tasks can be minimized.

Description

Energy consumption optimization resource allocation method for combining energy acquisition in edge calculation
Technical Field
The invention belongs to the technical field of mobile edge calculation, and relates to an energy consumption optimization resource allocation method for joint energy acquisition in edge calculation.
Background
A Mobile Edge Computing Network (MECN) that combines Energy Harvesting (EH) technology is a Mobile edge computing network that incorporates Energy harvesting technology. The MECN is used as a 5G next-generation broadband access system, and the EH is applied to the MECN to solve the problems of limited battery capacity and insufficient resources at the mobile equipment end. Compared with a typical mobile cloud computing network, a mobile terminal user can migrate an application to the edge cloud end for processing to reduce larger energy consumption generated by unloading a task to a cloud server, and the defects of weak computer capability and small storage space of the mobile terminal are overcome, and the service experience quality of the user is greatly improved. The EH is applied to the MECN, so that the problem of limited capacity of the end battery of the mobile equipment can be effectively solved, and the pressure of the mobile terminal equipment is reduced.
The invention researches the problem of energy consumption minimization resource allocation of combined EH in MECN, considers energy acquisition constraint and executes time delay constraint by local and edge servers, and performs combined optimization on unloading decision, transmission power and CPU frequency of a mobile terminal device end, charging power and CPU frequency of a mobile edge server and energy acquisition time. After reviewing the relevant literature, no research on the problem in MECN was found.
In view of the above considerations, the present invention provides an energy consumption optimization resource allocation method for joint energy acquisition in edge computing.
Disclosure of Invention
The technical problem to be solved by the invention is to provide an EH-combined energy consumption minimization method in an MECN, which combines an unloading decision, optimizes the transmission power and the CPU frequency of a mobile terminal device end, the charging power and the CPU frequency of an edge server and the energy acquisition time through the cooperation between the edge server and a local terminal device, reasonably distributes calculation and communication resources and reduces the execution energy consumption of a system.
The technical solution of the invention is as follows:
in MECN, N (i ═ 1.. N) end users are included, 1 task per user, and 1 Mobile Edge Computing (MEC) server. Task T of end user iiIs (D)i,Ci) Wherein D isiThe size of the data volume input for the task is in bits, CiThe number of CPU cycles required to execute a task is in cycles. Each task may be executed locally, on a mobile edge serverAnd (6) executing tasks. Wherein xiAs decision variables, xi∈{0,1}，xi1 denotes the offloading of end user i's tasks to the mobile edge server for execution, xi0 denotes local execution.
The invention provides an energy consumption optimization resource allocation method for combining energy acquisition in edge calculation, which comprises the following steps:
1. the method comprises the following steps of constructing a mathematical model of energy consumption optimization resource allocation by combining energy acquisition in edge calculation, firstly defining the mathematical model of charging an end user device by an edge server, and then defining energy consumption and delay of local task execution and unloading calculation, wherein the steps are as follows:
1) energy acquisition model
The edge server charges the mobile terminal equipment, and the energy acquired by the terminal user i is
Figure BDA0002507647470000021
As follows:
Figure BDA0002507647470000022
η thereiniRepresenting the conversion rate at which each end user device i converts the received signal into energy. PsIs the power at which the edge server charges the end user, hiIs the MEC to device i channel gain. Tau is0Is the time the MEC charges the end user.
2) Local execution
The task for end user i is executed locally with a delay of
Figure BDA0002507647470000023
The formula is as follows:
Figure BDA0002507647470000024
wherein f isi,locThe CPU frequency is the CPU frequency of the end user and has the unit of cycles/s.
Energy consumption for local execution of tasks by end user i is expressed as
Figure BDA0002507647470000025
The formula is as follows:
Figure BDA0002507647470000026
wherein gamma islAnd the effective capacitance coefficient depends on the chip architecture of the CPU of the end user equipment.
3) Offload execution
When a local user i offloads a task to an edge server computation, the task needs to be offloaded from the local to the edge server. The data rate from the local to the edge server is Ri，
The formula is as follows:
Figure BDA0002507647470000027
wherein g is0，d0，θ，N0Is a constant number diDistance from end user i to edge server, B is channel bandwidth, piOffloading the power of the task for end user i.
The time delay of the task unloading of the end user i to the edge server is expressed as
Figure BDA0002507647470000031
And
Figure BDA0002507647470000032
the formula is as follows:
Figure BDA0002507647470000033
Figure BDA0002507647470000034
wherein f isi,serThe CPU frequency allocated to the end user is in cycles/s.
Offloading of end user i's tasks to edge server upload energy consumption and executionThe line energy consumption is expressed as
Figure BDA0002507647470000035
And
Figure BDA0002507647470000036
the formula is as follows:
Figure BDA0002507647470000037
Figure BDA0002507647470000038
wherein gamma iscThe effective capacitance coefficient depends on the chip architecture of the edge server CPU.
Defining a mathematical model, optimizing calculation and communication resources jointly, optimizing local CPU frequency and transmission power, optimizing charging power, charging time and CPU frequency of an edge server and unloading decision under the condition of considering local execution delay constraint, edge server execution delay and energy acquisition constraint, wherein the goal is to minimize energy consumption for executing all tasks, and an objective function is defined as follows:
Figure BDA0002507647470000039
the constraint conditions are as follows:
Figure BDA00025076474700000310
Figure BDA00025076474700000311
Figure BDA00025076474700000312
Figure BDA00025076474700000313
Figure BDA00025076474700000314
Figure BDA00025076474700000315
Figure BDA0002507647470000041
xi∈{0,1}，pi≥0，ps≥0，fi,ser≥0，fi,loc≥0，τ0∈[0,T](17)
wherein χ ═ xi,pi,ps,fi,ser,fi,loc,τ0The optimization variable is used as the optimization variable; equations (10), (11) represent the latency constraint executed locally and the latency constraint executed by the edge server, equation (12) represents the energy consumption constraint executed locally,
Figure BDA0002507647470000045
energy harvested for end user i, see equation (1), EoInitial energy for the end user; equations (13) and (14) represent CPU frequency constraints of the local and edge servers, equations (15) and (16) represent power constraints of the local and edge servers, and equation (17) represents a value range of each optimization variable.
2. Carrying out variable relaxation on the constructed mathematical model and constructing a Lagrangian function, wherein the steps are as follows:
the mathematical model contains continuous optimization variables: the local CPU frequency and transmission power, the CPU frequency, charging power and charging time of the edge server, and binary optimization variables: and (6) unloading the decision. First, a binary variable xiThe relaxation is carried out to be a continuous variable, and according to the convex-concave rule of the composite function, the characteristics of the convex-concave function and the perspective function can prove that the objective function is a concave function, so that the problem after the relaxation of the variable is carried out is a convex problem. Introducing Lagrange multiplier variable matrix lambda ═ lambda1,λ2,λ3,λ4,λ5,λ6,λ7]The lagrange function is constructed as follows:
Figure BDA0002507647470000042
let χ ═ xi,pi,ps,fi,ser,fi,loc,τ0The dual function of the mathematical model is defined as
Figure BDA0002507647470000043
The dual problem is that
Figure BDA0002507647470000044
s.t.λ≥0。
3. Solving the time tau of charging the mobile terminal equipment by the edge server0And charging power psThe method comprises the following steps:
lagrange function (18) for τ respectively0And psThe partial derivatives are calculated as follows:
Figure BDA0002507647470000051
Figure BDA0002507647470000052
by solving formulas (19) and (20), p can be obtainedsAnd τ0The expression of (c) is as follows:
Figure BDA0002507647470000053
Figure BDA0002507647470000054
4. solving the CPU frequency f allocated by the end useri,locAnd edge server assigned CPU frequency fi,serThe method comprises the following steps:
lagrange function (18) for fi,locAnd fi,serThe partial derivatives are calculated as follows:
Figure BDA0002507647470000055
Figure BDA0002507647470000056
by solving formulas (23) and (24), the compounds can be obtained with respect to fi,locAnd fi,serA cubic equation of (f)i,locAnd fi,serAs follows:
Figure BDA0002507647470000057
Figure BDA0002507647470000058
solving f by Shengjing formula method based on solving unitary cubic equationi,locAnd fi,serFirstly, discriminant discrimination is carried out, and then direct solution is carried out, wherein the method comprises the following steps:
1) and calculating a heavy root discriminant and a total discriminant. Let a unitary cubic equation aX3+bX2+ cX + d is 0, where (a, b, c, d ∈ R, and a ≠ 0), and for formula (25), a is 2 γlCi，b＝λ6,i，c＝0，d＝-λ1,iCi(ii) a For formula (26), a ═ 2 γcCi，b＝λ5，c＝0，d＝-λ2,iCi. Calculating the heavy root discriminant A ═ b2-3ac，B＝bc-9ad，C＝c2-3bd, calculating the total discriminant Δ ═ B2-4AC。
2) When a ═ B ═ 0, 3 equal solutions of the one-dimensional cubic equation from shengjing equation 1 can be found as follows:
Figure BDA0002507647470000059
3) when delta is B2When-4 AC is more than 0, 3 solutions of the unitary cubic equation obtained from equation 2 of Shengjing are as followsThe following steps:
Figure BDA0002507647470000061
Figure BDA0002507647470000062
wherein
Figure BDA0002507647470000063
4) When delta is B2When-4 AC ═ 0, 3 solutions of the one-dimensional cubic equation from shengjing equation 3 can be obtained as follows:
Figure BDA0002507647470000064
Figure BDA0002507647470000065
wherein
Figure BDA0002507647470000066
5) When delta is B2-4AC<At 0, 3 solutions of the one-dimensional cubic equation from shengjing equation 4 are as follows:
Figure BDA0002507647470000067
Figure BDA0002507647470000068
wherein theta is arccos t,
Figure BDA0002507647470000069
5. solving the transmission power p from the terminal equipment unloading task to the edge serveriThe method comprises the following steps:
1) lagrangian function (18) for piThe partial derivatives are calculated as followsShown in the figure:
Figure BDA00025076474700000610
wherein
Figure BDA00025076474700000611
By solving formula (34), p can be obtainediThe logarithmic equation of (a) is as follows:
Figure BDA00025076474700000612
Figure BDA0002507647470000071
2) after the partial derivative is obtained again for equation (35), the following equation is obtained:
Figure BDA0002507647470000072
by observation, equation (36) is non-positive, that is, equation (35) is a monotonically decreasing function.
3) Solving for p based on dichotomyi. In the interval
Figure BDA0002507647470000073
Obtaining p by gradually approximating the binary approximation to the optimal valueiThe optimal solution of (2) comprises the following steps:
determining an interval [ a, b ], verifying that f (a) and f (b) are less than 0, and giving accuracy omega;
② find the interval [ a, b]Is at the midpoint of
Figure BDA0002507647470000074
Calculating f (c), if f (c) is 0, c is zero point of function;
if f (a) and f (c) are less than 0, b is equal to c;
if f (c) f (b) is less than 0, making a equal to c;
judging whether the difference value of two sections of interval points reaches accuracy omega, if | a-b | is less than omega, obtaining zero point approximate value a (or b) of formula (35) to finish the optimal value solution, otherwise, skipping to the step II.
6. Offloading decision variable x for solving offloading of task of end user i to edge serveriThe method comprises the following steps:
dependent load decision variable xiIs a binary variable, and is subjected to unloading decision variable xiAfter the variable relaxation, the variable x is extracted from the Lagrangian function (18)iAnd 1-xiThe modifications are as follows:
Figure BDA0002507647470000075
Figure BDA0002507647470000081
considering the idea of a greedy algorithm, when the offloading decision can reduce the total energy consumption, it is considered to offload it, as shown in the following equation:
Figure BDA0002507647470000082
wherein:
Figure BDA0002507647470000083
Figure BDA0002507647470000084
7. solving the energy consumption optimization resource allocation problem obtained by combining energy based on a gradient descent method, comprising the following steps:
1) initializing the dual variable matrix λ and the step size α ═ α1,α2,α3,α4,α5,α6,α7]The number of iterations m is 1,
Figure BDA0002507647470000085
2) calculating charging power of the edge server side according to equation (21) and equation (22)
Figure BDA0002507647470000086
And charging time
Figure BDA0002507647470000087
Calculating the energy of the edge server for charging the terminal device i according to the formula (1)
Figure BDA0002507647470000088
3) Based on the Shengjing formula method, the CPU frequency distributed by the end user is calculated according to the formulas (25) and (26)
Figure BDA0002507647470000089
And CPU frequency of edge server side
Figure BDA00025076474700000810
4) Calculating the end-user transmission power according to equation (35) based on dichotomy
Figure BDA00025076474700000811
5) Solving the offload decision variable of the end user i for offloading the task to the edge server according to equation (38)
Figure BDA00025076474700000812
6) Respectively solving the time delay of the task executed locally, transmitted to the edge server and executed at the edge server according to the formulas (2), (5) and (6)
Figure BDA00025076474700000813
And energy consumption for executing the calculation tasks locally, transmitting the calculation tasks to the edge server and executing the calculation tasks at the edge server according to the formulas (3), (7) and (8)
Figure BDA00025076474700000814
7) Gradient descent method for updating Lagrange multiplier lambda ═ lambda1,λ2,λ3,λ4,λ5,λ6,λ7]As follows:
Figure BDA00025076474700000815
Figure BDA00025076474700000816
Figure BDA0002507647470000091
Figure BDA0002507647470000092
Figure BDA0002507647470000093
Figure BDA0002507647470000094
Figure BDA0002507647470000095
8) calculating the total consumed energy of the task according to the formula (9)
Figure BDA0002507647470000096
9) Judgment of
Figure BDA0002507647470000097
If yes, ending iteration to show that the optimal solution is obtained; if not, continue the next iteration, m ═ m +1, go to step 2).
Has the advantages that:
the invention solves the problem of energy consumption optimization resource allocation of joint energy acquisition in edge calculation, and the task of the terminal user is selected to be executed locally or unloaded by the edge server, thereby effectively reducing the energy consumption of the system.
The present invention is described in further detail below with reference to the attached drawing figures.
FIG. 1 is a schematic view of a scene model of the present invention;
FIG. 2 is a flowchart of a minimum latency algorithm under the cooperative offloading mechanism of the present invention;
FIG. 3 is a flowchart of a gradient descent method for solving an energy consumption optimization resource allocation problem of joint energy acquisition.
Detailed Description
The invention will be described in further detail below with reference to the following figures and specific examples:
example 1:
in this embodiment, fig. 1 is a schematic diagram of a mobile edge computing network model of a joint energy acquisition technology, where the network includes 30(N ═ 30) end users, each user has 1 task, and 1 MEC server. Task T of end user iiIs (D)i,Ci)，DiSize of input data volume for task in range of [ bits]，CiThe number of CPU cycles required to execute a task ranges from cycles]. Wherein g is0＝-40dB，d0＝1m，diDistance of user i to edge server, N0＝-174dB/HZ，B＝20KHZ，θ＝3，
Figure BDA0002507647470000098
ηi＝0.5。
S1 creating a scenario
S1-1 has 30 end users in the scene, each user has 1 task and 1 edge server.
Task T of end user iiC of (A)iAnd DiAs follows:
Figure BDA0002507647470000101
end user i to mobile edge serverDistance diComprises the following steps:
Figure BDA0002507647470000102
channel gain h from mobile edge server to end user iiComprises the following steps:
Figure BDA0002507647470000111
s2 energy consumption optimization resource allocation problem based on gradient descent method for solving joint energy acquisition
Initial value for the first iteration of S2-1:
λ3 900
λ5 4e-6
Figure BDA0002507647470000112
Figure BDA0002507647470000121
Figure BDA0002507647470000131
p is calculated by the equations (21) and (22)s,
Figure BDA0002507647470000132
Figure BDA0002507647470000133
F is calculated by the equations (25), (26), (35)i,loc，fi,ser，pi。
Figure BDA0002507647470000134
Figure BDA0002507647470000141
Obtained by the equations (3), (7) and (8), respectively
Figure BDA0002507647470000142
Figure BDA0002507647470000143
Figure BDA0002507647470000151
S2-2 making an unload decision x by equation (38) based on the temporary optimum variable found at S2-1i。
Offload decision x for end user i's taski:
Figure BDA0002507647470000152
Figure BDA0002507647470000161
The energy consumption to perform all tasks is: 6.429288179930334e +03
S2-3 judges whether the target converges, and if not, updates λ ═ λ1,λ2,λ3,λ4,λ5,λ6,λ7]And continuing the next iteration until the target converges.
The difference between the two iterations when the target converges is 9.323995527665830 e-06.
Value of λ at convergence:
λ3 946.0862137880565
λ5 8.827558293088503e-05
Figure BDA0002507647470000162
Figure BDA0002507647470000171
Figure BDA0002507647470000181
charging power and charging time of the edge server during convergence:
Figure BDA0002507647470000182
CPU frequency of local device at convergence:
Figure BDA0002507647470000183
CPU frequency of edge server at convergence:
Figure BDA0002507647470000184
Figure BDA0002507647470000191
transmission power from the terminal device to the edge server at convergence:
Figure BDA0002507647470000192
Figure BDA0002507647470000201
task offload decision x for end user i at convergencei:
Figure BDA0002507647470000202
The energy consumption to perform all tasks at convergence is: 6.829703870241112e +02

Claims (8)

1. An energy consumption optimization resource allocation method for combining energy acquisition in edge computing is characterized by comprising the following steps:
step 1: and constructing a mathematical model of energy consumption optimization resource allocation combined with energy acquisition in edge calculation.
Step 2: and performing variable relaxation on the constructed mathematical model and constructing a Lagrangian function.
And step 3: solving the time tau of charging the mobile terminal equipment by the edge server0And charging power ps。
And 4, step 4: solving the CPU frequency f allocated by the end useri,locAnd edge server assigned CPU frequency fi,ser。
And 5: solving the transmission power p from the terminal equipment unloading task to the edge serveri。
Step 6: offloading decision variable x for solving offloading of task of end user i to edge serveri。
And 7: and solving the energy consumption optimization resource allocation problem obtained by combining energy based on a gradient descent method.
2. The method for energy consumption optimized resource allocation based on energy acquisition in edge computing according to claim 1, wherein a mathematical model of energy consumption optimized resource allocation based on energy acquisition in edge computing is constructed in step 1.
Defining optimized variables of a mathematical model, including decision variables xi∈{0,1}，xi1 means that the task of the end user i is unloaded to the edge server for execution; CPU frequency f assigned by end user ii,locEdge server assigned CPU frequency fi,ser(ii) a Offloading of end user i's tasks to edge server transmission power piCharging time tau of edge server to mobile terminal equipment0Charging power p of edge server to mobile terminal devices. Defining the energy acquired by the end user i as
Figure FDA0002507647460000011
The time delay of the local execution of the task is Ti lWith task local execution energy consumption
Figure FDA0002507647460000012
End user to edge server data rate Ri(ii) a The time delay for unloading the task to the edge server and uploading is represented as Ti transAnd Ti cOffloading of tasks to edge servers for energy consumption
Figure FDA0002507647460000013
And execution energy consumption
Figure FDA0002507647460000014
An objective function that minimizes the energy consumption for executing all tasks is defined as
Figure FDA0002507647460000015
3. The method for energy consumption optimization resource allocation in combination with energy acquisition in edge computing as claimed in claim 1, wherein in step 2, the constructed mathematical model is subjected to variable relaxation and a lagrangian function is constructed.
4. The method as claimed in claim 1, wherein the step 3 of solving the time τ for the edge server to charge the mobile terminal device is further performed by using the energy-consumption-optimized resource allocation method based on energy-harvesting0And charging power ps。
5. The method for energy consumption optimization resource allocation by combining energy acquisition in edge computing according to claim 1, wherein the step 4 is performed to solve the CPU frequency f allocated by the end useri,locAnd edge server assigned CPU frequency fi,ser。
6. The method for energy consumption optimization resource allocation based on energy acquisition in edge computing according to claim 1, wherein the solution of the transmission power p unloaded from the terminal device to the edge server in step 5 is performedi。
7. The method for energy consumption optimization resource allocation based on energy acquisition in edge computing as claimed in claim 1, wherein the step 6 is to solve the off-load decision variable x for off-loading the task of the end user i to the edge serveri。
8. The method for energy consumption optimized resource allocation based on joint energy acquisition in edge computing according to claim 1, wherein the step 7 is based on a gradient descent method to solve the problem of energy consumption optimized resource allocation based on joint energy acquisition.
CN202010451272.9A 2020-05-25 2020-05-25 Energy consumption optimization resource allocation method for combining energy acquisition in edge calculation Active CN111787618B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010451272.9A CN111787618B (en) 2020-05-25 2020-05-25 Energy consumption optimization resource allocation method for combining energy acquisition in edge calculation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010451272.9A CN111787618B (en) 2020-05-25 2020-05-25 Energy consumption optimization resource allocation method for combining energy acquisition in edge calculation

Publications (2)

Publication Number Publication Date
CN111787618A true CN111787618A (en) 2020-10-16
CN111787618B CN111787618B (en) 2022-03-18

Family

ID=72754379

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010451272.9A Active CN111787618B (en) 2020-05-25 2020-05-25 Energy consumption optimization resource allocation method for combining energy acquisition in edge calculation

Country Status (1)

Country Link
CN (1) CN111787618B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113542357A (en) * 2021-06-15 2021-10-22 长沙理工大学 Electric vehicle auxiliary mobile edge calculation unloading method with minimized energy consumption cost
CN116541153A (en) * 2023-07-06 2023-08-04 南昌工程学院 Task scheduling method and system for edge calculation, readable storage medium and computer

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140118108A1 (en) * 2012-10-26 2014-05-01 Mark Kramer Wireless Personal Tracking Device
CN109240818A (en) * 2018-09-04 2019-01-18 中南大学 Task discharging method based on user experience in a kind of edge calculations network
CN109710336A (en) * 2019-01-11 2019-05-03 中南林业科技大学 The mobile edge calculations method for scheduling task of joint energy and delay optimization
CN109814951A (en) * 2019-01-22 2019-05-28 南京邮电大学 The combined optimization method of task unloading and resource allocation in mobile edge calculations network
CN110545584A (en) * 2019-08-20 2019-12-06 浙江科技学院 Communication processing method of full-duplex mobile edge computing communication system
CN110809291A (en) * 2019-10-31 2020-02-18 东华大学 Double-layer load balancing method of mobile edge computing system based on energy acquisition equipment
CN111124639A (en) * 2019-12-11 2020-05-08 安徽大学 Operation method and system of edge computing system and electronic equipment

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140118108A1 (en) * 2012-10-26 2014-05-01 Mark Kramer Wireless Personal Tracking Device
CN109240818A (en) * 2018-09-04 2019-01-18 中南大学 Task discharging method based on user experience in a kind of edge calculations network
CN109710336A (en) * 2019-01-11 2019-05-03 中南林业科技大学 The mobile edge calculations method for scheduling task of joint energy and delay optimization
CN109814951A (en) * 2019-01-22 2019-05-28 南京邮电大学 The combined optimization method of task unloading and resource allocation in mobile edge calculations network
CN110545584A (en) * 2019-08-20 2019-12-06 浙江科技学院 Communication processing method of full-duplex mobile edge computing communication system
CN110809291A (en) * 2019-10-31 2020-02-18 东华大学 Double-layer load balancing method of mobile edge computing system based on energy acquisition equipment
CN111124639A (en) * 2019-12-11 2020-05-08 安徽大学 Operation method and system of edge computing system and electronic equipment

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
于博文等: "移动边缘计算任务卸载和基站关联协同决策问题研究", 《计算机研究与发展》 *
陈超等: "移动云计算基于随机数据模型的最优控制策略", 《计算机工程与设计》 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113542357A (en) * 2021-06-15 2021-10-22 长沙理工大学 Electric vehicle auxiliary mobile edge calculation unloading method with minimized energy consumption cost
CN113542357B (en) * 2021-06-15 2022-05-31 长沙理工大学 Electric vehicle auxiliary mobile edge calculation unloading method with minimized energy consumption cost
CN116541153A (en) * 2023-07-06 2023-08-04 南昌工程学院 Task scheduling method and system for edge calculation, readable storage medium and computer
CN116541153B (en) * 2023-07-06 2023-10-03 南昌工程学院 Task scheduling method and system for edge calculation, readable storage medium and computer

Also Published As

Publication number Publication date
CN111787618B (en) 2022-03-18

Similar Documents

Publication Publication Date Title
CN110928654B (en) Distributed online task unloading scheduling method in edge computing system
CN108920280B (en) Mobile edge computing task unloading method under single-user scene
CN113242568B (en) Task unloading and resource allocation method in uncertain network environment
CN113950103B (en) Multi-server complete computing unloading method and system under mobile edge environment
CN112817653A (en) Cloud-side-based federated learning calculation unloading computing system and method
CN107708152B (en) Task unloading method of heterogeneous cellular network
CN111913723B (en) Cloud-edge-end cooperative unloading method and system based on assembly line
Shi et al. Toward energy-efficient federated learning over 5g+ mobile devices
CN109388492B (en) Mobile block chain optimization calculation force distribution method based on simulated annealing in multi-edge calculation server scene
CN111787618A (en) Energy consumption optimization resource allocation method for combining energy acquisition in edge calculation
CN111988792B (en) System and decision calculation method of unmanned aerial vehicle alliance network unloading model
CN113286329B (en) Communication and computing resource joint optimization method based on mobile edge computing
CN111836284B (en) Energy consumption optimization calculation and unloading method and system based on mobile edge calculation
CN111107153B (en) MEC pricing unloading method based on D2D communication in power Internet of things
CN112866006B (en) Cloud and mist fusion network multi-target task unloading method based on time delay energy consumption balance
CN110809291B (en) Double-layer load balancing method of mobile edge computing system based on energy acquisition equipment
CN111556143A (en) Method for minimizing time delay under cooperative unloading mechanism in mobile edge computing
CN112667406A (en) Task unloading and data caching method in cloud edge fusion heterogeneous network
CN113821346B (en) Edge computing unloading and resource management method based on deep reinforcement learning
Yuan et al. An energy-efficient computing offloading framework for blockchain-enabled video streaming systems
CN110768827A (en) Task unloading method based on group intelligent algorithm
CN116528299A (en) Combined unloading and micro-service deployment decision optimization method in mobile perception edge computing system
CN116663644A (en) Multi-compression version Yun Bianduan DNN collaborative reasoning acceleration method
CN114567564B (en) Task unloading and computing resource allocation method based on server collaboration
CN115119234A (en) Method for optimizing task processing of wireless equipment in wireless energy supply edge computing network

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