CN110650487B - Internet of things edge computing configuration method based on data privacy protection - Google Patents

Internet of things edge computing configuration method based on data privacy protection Download PDF

Info

Publication number
CN110650487B
CN110650487B CN201910921830.0A CN201910921830A CN110650487B CN 110650487 B CN110650487 B CN 110650487B CN 201910921830 A CN201910921830 A CN 201910921830A CN 110650487 B CN110650487 B CN 110650487B
Authority
CN
China
Prior art keywords
internet
things
terminal
server
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.)
Active
Application number
CN201910921830.0A
Other languages
Chinese (zh)
Other versions
CN110650487A (en
Inventor
孙高飞
邢晓双
钱振江
戴欢
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.)
Changshu Institute of Technology
CERNET Corp
Original Assignee
Changshu Institute of Technology
CERNET Corp
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 Changshu Institute of Technology, CERNET Corp filed Critical Changshu Institute of Technology
Priority to CN201910921830.0A priority Critical patent/CN110650487B/en
Publication of CN110650487A publication Critical patent/CN110650487A/en
Application granted granted Critical
Publication of CN110650487B publication Critical patent/CN110650487B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W24/00Supervisory, monitoring or testing arrangements
    • H04W24/02Arrangements for optimising operational condition
    • YGENERAL 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
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02DCLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00Reducing energy consumption in communication networks
    • Y02D30/70Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

The invention discloses a method for completing data calculation by using an edge calculation server for terminal equipment of the Internet of things, which comprises the following steps: firstly, each terminal of the internet of things knows the distribution information and the available channel information of an edge computing server in the geographic area through a common control channel; secondly, estimating the amount of energy consumed by local terminal calculation and judging whether the time delay meets the requirements or not for the amount of environment acquisition information which needs to be collected currently; thirdly, calculating server information according to the collected edge, and taking energy consumption and data transmission safety into consideration to obtain the optimal transmission power and transmission time delay when the data calculation is completed through the edge server; and finally, obtaining an optimal computing resource utilization strategy by the Internet of things terminal according to the data of the first two steps. The invention discloses a novel method for selecting the computing service of terminal equipment of the Internet of things, which can balance the energy consumption of the terminal of the Internet of things and the protection requirement of data privacy, improve the data security and prolong the service life of the terminal.

Description

Internet of things edge computing configuration method based on data privacy protection
Technical Field
The invention relates to an Internet of things edge computing configuration method based on data privacy protection, and belongs to the field of Internet of things communication.
Background
As the 5G network is accelerating to complete commercial deployment, the possibility is created for large-scale application of the Internet of things. Currently, internet of things equipment has entered all aspects of daily life and becomes an essential component of environment monitoring, video acquisition, smart cities and smart homes. The internet of things is limited by the cost of terminal equipment of the internet of things, the internet of things generally adopts a network architecture of a terminal and a cloud, the terminal equipment only finishes information acquisition and transmission, and all data processing is carried out by depending on a cloud server.
With the large increase of the devices of the internet of things and the increase of the delay requirement, the single network architecture is challenged unprecedentedly. A large amount of data are uploaded to the cloud, so that higher requirements are provided for the performance of a cloud server, and higher requirements for network bandwidth are also provided. Even so, a large number of sensors with high real-time requirements will still be difficult to meet the requirements, such as the time delay from the acquisition of information from the sensors to the implementation of vehicle control in unmanned driving must be within milliseconds. On the other hand, a large amount of data are uploaded to a cloud end, the link is too long and the complexity is too high, a safety problem is caused, and malicious users possibly intercept and capture data of the terminal equipment in a transmission link, so that the real-time state of a specific scene is analyzed, and illegal infringement is implemented.
In recent years, the transmission and delay problems caused by a single architecture of the internet of things can be relieved to a certain extent through the evolution of a data communication system, such as the improvement of transmission rate, but the fundamental solution lies in the further evolution of a network architecture, namely, a server gradually transits from a cloud end to a cloud end and coexists with a network edge. Under the network architecture, on one hand, the data volume transmitted to the cloud end through the network is reduced, and the data security is improved; on the other hand, data is processed nearby, the problem that the computing power of the terminal of the Internet of things is insufficient is solved, and meanwhile, data processing time delay is reduced. Finally, the number of the internet of things equipment terminals which can be accommodated by the network can be greatly increased.
The existing research work on the adoption of edge computing of an internet of things terminal mainly aims at reasonably selecting a plurality of edge computing servers and cloud servers in a certain geographic area by internet of things terminal equipment so as to minimize two performance indexes: total energy consumption and transmission delay. The problem of selecting an IOT terminal between a Computing unit and an Edge server is studied in the documents "Mao, Y., zhang, J., and Letaief, K.B.: dynamic Computing Offloading for Mobile-Edge Computing With Energy Harvesting Devices, IEEE Journal on Selected Areas in Communications,2016,34, (12), pp.3590-3605". The problem of stable selection in the scenario of multiple internet of things terminals and multiple Edge servers is studied in documents "Dinh, t.q., la, q.d., quek, t.q.s., and Shin, h.: learning for Computing off-flow in Mobile Edge Computing, IEEE Transactions on Communications,2018,66, (12), pp.6353-6367", and the internet of things terminals tend to be stable in the case of distributed selection of Edge servers by using the nash equilibrium theory. In the documents "Chen, m., and Hao, y.: task off-flow for Mobile Edge Computing in Software Defined Ultra-transmit Network, IEEE Journal on Selected Areas in Communications,2018,36, (3), pp.587-597", the optimal computation Task upload strategy of the end user is analyzed in the scene of a high density of terminals of the internet of things, by which the terminal energy consumption can be reduced by 30% and the data processing delay can be reduced by 20%. In general, current research neglects the dimension of data transmission security, and only focuses on two dimensions of energy consumption and processing delay.
Disclosure of Invention
In order to further optimize data processing of the terminal of the Internet of things from three dimensions, namely data security, energy consumption and processing time delay, the invention provides an Internet of things edge computing configuration method based on data privacy protection.
The invention adopts the following technical scheme for solving the technical problems:
the invention provides an Internet of things edge computing configuration method based on data privacy protection,
the method comprises the following steps:
step 1, periodically detecting state information sent by an edge computing server on an appointed control channel during the interval of collecting current environment information by each terminal of the Internet of things;
step 2, selecting a standby edge computing server j of joint computing * The method specifically comprises the following steps:
2.1, assuming that the terminal i of the Internet of things is to perform all calculation tasks S i Sending the data to the edge computing server j for data processing, i.e. the computing task processed by the edge computing server j
Figure BDA0002217826250000021
And computing task processed by terminal i of Internet of things
Figure BDA0002217826250000022
By minimizing
Figure BDA0002217826250000023
Obtaining the optimal transmitting power of the terminal i of the Internet of things
Figure BDA0002217826250000024
And a corresponding consumption energy of
Figure BDA0002217826250000025
The data processing duration of the edge computing server j is
Figure BDA0002217826250000026
If it is
Figure BDA0002217826250000027
The edge computing server j is an available server; wherein the content of the first and second substances,
Figure BDA0002217826250000028
h i,j calculating channel gain between terminal i and edge server j for Internet of things, B i For the channel bandwidth, sigma, between the terminal i of the internet of things and the edge computing server j 2 Is the power of white noise, p i Is the transmitting power of the terminal i of the internet of things,
Figure BDA0002217826250000029
is the maximum transmitting power, G, of the terminal i of the Internet of things i,j The method comprises the steps that an internet of things terminal set in a circle with an internet of things terminal i as a circle center and the distance between the internet of things terminal i and an edge calculation server j as a radius is formed, eta is the average probability that the internet of things terminal is a malicious user interception target, and c i Weight factors bringing risks for intercepting the data are reflected;
2.2, standby edge compute Server j * The server with the lowest corresponding energy consumption in the available server set obtained in the step 2.1 is obtained;
step 3, calculating a server j according to the standby edge * Corresponding to
Figure BDA0002217826250000031
And
Figure BDA0002217826250000032
the method for determining the configuration scheme of the computing task specifically comprises the following steps:
3.1, if satisfied
Figure BDA0002217826250000033
And is provided with
Figure BDA0002217826250000034
All calculation tasks S of Internet of things terminal i i Will be processed by its local computing unit; wherein the content of the first and second substances,
Figure BDA0002217826250000035
for all calculation tasks S i The total energy consumption for data processing by the internet of things terminal i,
Figure BDA0002217826250000036
for all calculation tasks S i The calculation time, tau, consumed by the internet of things terminal i for data processing i For processing the entire computational task S i The delay threshold of (a);
3.2 if satisfied
Figure BDA0002217826250000037
But do not
Figure BDA0002217826250000038
The terminal i of the Internet of things preferentially utilizes the local computing unit thereof to process part of tasks
Figure BDA0002217826250000039
If the rest of the computing task
Figure BDA00022178262500000310
By a standby edge computing server j * Upon completion satisfy
Figure BDA00022178262500000311
Then the terminal i of the internet of things calculates the part of the task
Figure BDA00022178262500000324
Send to a backup edge compute server j * Processing, otherwise S i Will be discarded; wherein the content of the first and second substances,
Figure BDA00022178262500000312
compute Server j for Standby edge * Treatment of
Figure BDA00022178262500000313
The length of time of;
3.3 if satisfied
Figure BDA00022178262500000314
And is provided with
Figure BDA00022178262500000315
All calculation tasks S of Internet of things terminal i i Will be sent to the standby edge computing server j * Finish the treatment, i.e.
Figure BDA00022178262500000316
3.4 if satisfied
Figure BDA00022178262500000317
But do not
Figure BDA00022178262500000318
The terminal i of the internet of things preferentially utilizes the server j * Handling partial tasks
Figure BDA00022178262500000319
If the rest of the computing task
Figure BDA00022178262500000320
Satisfied by local computing unit of terminal i of Internet of things
Figure BDA00022178262500000321
Then the terminal i of the internet of things calculates the part of the task
Figure BDA00022178262500000322
Processing at local computing unit, otherwise S i Will be discarded.
As a further technical solution of the present invention,
Figure BDA00022178262500000323
where κ denotes a coefficient determined by processor characteristics, W i =S i X and X represent the number of clock cycles of a Central Processing Unit (CPU) required by the terminal i of the Internet of things for processing 1 bit data, f i M The maximum clock period allowed for the central processing unit of the terminal i of the internet of things.
As a further technical scheme of the invention, the state information sent by the edge computing server comprises the geographical position of the edge server, the quality and available bandwidth of a data transmission channel and the computing and processing capacity.
Compared with the prior art, the invention adopting the technical scheme has the following technical effects:
1. the data processing flow of the terminal of the Internet of things is optimized, the computing power of the computing unit and the computing server near the edge of the computing unit is fully utilized, and the data processing efficiency is improved.
2. When the terminal of the Internet of things transmits data to the edge server, the possibility that the data is intercepted and utilized by other terminals is considered, and the risk is reduced through optimization;
drawings
FIG. 1 is a flow diagram of a computing arrangement of the present invention;
fig. 2 and fig. 3 are diagrams of computing configurations of end users of the internet of things with different delay requirements in a given scenario.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The technical scheme of the invention is further explained in detail by combining the drawings as follows:
the invention provides an Internet of things edge computing configuration method based on data privacy protection, which comprises the following steps of:
firstly, in a certain geographic area, a plurality of internet of things terminals for monitoring environmental state information are deployed, and a plurality of edge servers for data calculation processing exist. The terminals maintain the energy requirements in a mode of combining batteries and solar energy collection, are connected to the network through a wireless access technology, and have the capability of accessing an edge server and a cloud server. Each internet of things terminal periodically detects state information sent by the edge computing server on an appointed control channel at the interval of collecting current environment information, wherein the state information comprises the geographic position of the edge server, the quality and available bandwidth of a data transmission channel, computing processing capacity and the like.
Taking video information acquisition as an example, the internet of things terminal continuously acquires real-time pictures shot at the current position, finds whether interested persons, objects or behaviors appear or not, and uploads the result to the cloud server once a specific target is detected without directly uploading all video information. The terminal has limited memory capacity and the goal is to process 500 megabytes of video information to completion and obtain no more than 1 kilobyte of text information within a given period of time, e.g., 1 minute, to describe whether a particular event has been detected. Therefore, the terminal needs to complete the processing of these video data with as little energy consumption as possible and satisfying the requirement of processing time limit.
Secondly, after the terminal of the Internet of things collects the information of the edge calculation server and other terminals, a series of weights are obtained through calculation, and comparison is carried out according to the weights so as to determine which way to finish data calculation.
As a further technical solution of the present invention, taking the terminal i of the internet of things as an example, the data amount to be processed is S i (in bits) the delay requirement for processing the data is less than τ i . The weights needed to complete the calculation are as follows:
1) And the self computing unit of the terminal of the Internet of things processes and computes data. Assuming currently that X represents the number of CPU clock cycles required to process 1 bit of data, then the entire data S is processed i The required total CPU clock period is W i =S i And (4) X. In order to reduce the energy consumption to the maximum, the terminal will use the maximum clock period f allowed by the CPU i M The treatment is carried out, then the total consumed energy is
Figure BDA0002217826250000051
While the consumed calculation time is
Figure BDA0002217826250000052
Where κ denotes a coefficient determined by the processor characteristics.
2) The terminal of the Internet of things transmits all the calculation tasks S through a wireless data transmission means i And sending the data to a nearby edge computing server for data processing. The edge server has reliable energy supply and strong data calculation capacity, and the energy consumption calculated by the edge server mainly lies in the data transmission process and overcomes the safety problem caused by the data intercepted by other receiving equipment. It is assumed here that all computation tasks are to be transferred to edge server j for processing, with a channel gain of h i,j Channel bandwidth of B i White noise power of sigma 2 Then the terminal transmits at a transmission power p i The achievable transmission rate is
Figure BDA0002217826250000053
Thereby obtaining the total energy consumption of the transmission process as
Figure BDA0002217826250000054
Supposing that the data modulation and coding mode adopted in wireless transmission can realize infinite approach to r (h) i,j ,p i ) The actual transmission rate of the internet of things terminal i is used as the center of a circle, and the distance between the terminal i and the server j is used as the radius circle, so that the receiving terminal can intercept the data sent by the receiving terminal. Assume that the set of terminals within the circle is G i,j Receiving terminal n, n ∈ G i,j Probability of eta for malicious interception of a user n Then the probability of the data being intercepted is expressed as
Figure BDA0002217826250000055
Combining the above two parts, the terminal i needs to select a suitable server j and an optimal transmission power p i In a minimized manner
Figure BDA0002217826250000056
c i And a weight factor bringing risks for intercepting the data is reflected. Taking the average probability of malicious interception of the terminal as eta, and further simplifying the formula as
Figure BDA0002217826250000057
Given server j, the optimal transmit power can be calculated from this equation
Figure BDA0002217826250000058
And a corresponding consumption energy of
Figure BDA0002217826250000059
And obtains a data processing duration of
Figure BDA00022178262500000510
If the optimum transmission power
Figure BDA0002217826250000061
Must not be less than its maximum transmit power limit, i.e. satisfy
Figure BDA0002217826250000062
Then the server j is removed from the list of available servers and the lowest energy consuming server j is selected from the remaining servers * As an alternative.
Here, taking a certain internet of things terminal as an example, there are 3 edge servers around the terminal for computing services, which are a, B, and C, respectively. The terminal needs to calculate 4 groups of corresponding weights, namely energy and time delay (E) required by the terminal to complete processing through a self-calculating unit L ,D L ) And the capacity and delay required for processing if all data is sent to one of the servers, respectively (E) A ,D A ),(E B ,D B ),(E C ,D C ). In order to prolong the service life of the terminal or reduce the maintenance cost of personnel, the selection of the edge server takes the energy consumption of data transmission as a standard, and the server A with the minimum required energy is selected from the 3 servers. It should be noted that the transmission energy required by server a is minimal, but the transmission delay may not be minimal.
It should be noted that the energy consumption and the time delay of the server are not calculated only by solving the cost function, but can find the optimal value by numerical calculation. And is limited by the modulation scheme and coding scheme, where the power p i The values may be discrete rather than from 0 to maximum power
Figure BDA0002217826250000063
A continuous value of (c).
Thirdly, the terminal of the internet of things selects the following possible data processing schemes according to the comparison between the weight processed by the terminal of the internet of things and the value of the selected weight of the edge server, wherein the schemes are as follows: terminal i own computing unit, edge server j * Terminal self-calculating unitAnd (4) performing joint calculation with the edge server, and discarding the current data without processing.
As a further technical scheme of the invention, the selection of the scheme is carried out according to the following steps:
1) If it satisfies
Figure BDA0002217826250000064
And is provided with
Figure BDA0002217826250000065
All computation tasks S of terminal i i Will be processed by its local computing unit, i.e.
Figure BDA0002217826250000066
2) If it satisfies
Figure BDA0002217826250000067
But do not
Figure BDA0002217826250000068
The terminal i will preferentially handle part of the task with the local computing unit, i.e.
Figure BDA0002217826250000069
If the rest of the computing task
Figure BDA00022178262500000610
By server j * Complete and satisfy
Figure BDA00022178262500000611
Then terminal i sends the part of the computation task to server j * Processing, otherwise the computing task S i Will be discarded;
3) If it satisfies
Figure BDA00022178262500000612
And is provided with
Figure BDA00022178262500000613
All meters of terminal iCalculation task S i Will all be sent to server j * Finish the treatment, i.e.
Figure BDA00022178262500000614
4) If it is satisfied with
Figure BDA00022178262500000615
But do not
Figure BDA00022178262500000616
Terminal i will preferentially utilize server j * Handling part of the task, i.e.
Figure BDA00022178262500000617
If the rest of the computing task
Figure BDA00022178262500000618
Is done and satisfied by the local computing unit of terminal i
Figure BDA00022178262500000619
The terminal i processes the part of the calculation task in the local calculation unit, otherwise the calculation task S i Will be discarded.
Following the above example, the terminal has selected the weight (E) of server A A ,D A ) Weight value processed by self-computing unit (E) L ,D L ) The comparison is made and a selection is made among the 4 strategies described above to determine whether to send the video data, or a portion of the video data, to the edge server a for processing.
According to the scheme, if the calculation tasks are reasonably distributed, the terminal distributes the tasks between the local calculation unit and the edge server according to the obtained proportion and completes the data processing. If the final selection is discarded, then go back to selecting the edge server location in step, reselect the edge server that consumes the second place, and make the solution selection. And so on until there is no optional edge server, the portion of data will be discarded completely.
The technical solution of the present invention is further explained by the following specific examples:
example 1 a computing configuration method and a performance comparison diagram of an internet of things terminal in a specific environment are given.
In a deployment environment of a certain internet of things terminal, 3 edge servers with different distances exist, and the distance between the edge servers and the terminal is 5m,8m and 12m respectively. The data volume to be processed by the terminal of the Internet of things in a given time delay is 1500 bits, the maximum working frequency of a computing unit of the terminal of the Internet of things is 1.5GHz, and the value of a parameter kappa is 10 -28 Therefore, the calculation results in 1.99mJ of energy consumed by the local calculation and 5.9ms of processing delay. And assuming that the transmission of 3 edge servers adopts a 2.4GHz frequency band, the bandwidth is 20MHz, and the gain of a transmission channel is in inverse proportion to 4 power of the distance, the energy consumed by the 3 edge servers from near to far and the transmission delay are respectively (1.25mJ, 6.5 ms), (2.12mJ, 8.5 ms), (2.96mJ, 11.8 ms).
In fig. 2, when the processing delay required by the terminal of the internet of things is 5ms, the policy selection for performing joint data processing with each server is given. Under the condition, the independent calculation of the local calculation unit and all the servers does not meet the time delay requirement, so the calculation tasks are distributed between the local calculation unit and the servers according to the distribution method to carry out combined processing. Different energy consumption is brought by the distance between the servers, and the internet of things terminal finally utilizes the nearest edge server to carry out data combined processing.
In fig. 3, the policy selection for performing the joint data processing with each server when the processing delay required by the terminal of the internet of things is 10ms is shown. Under the condition, except for the farthest server, the local computing unit and other servers can independently compute and meet the time delay requirement, so that the computing task selects local or server to independently process data according to the distribution method. If the nearest server is available, all the data are sent to the server for processing, otherwise, all the data are calculated in the local calculation unit.
The above description is only an embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can understand that the modifications or substitutions within the technical scope of the present invention are included in the scope of the present invention, and therefore, the scope of the present invention should be subject to the protection scope of the claims.

Claims (3)

1. An Internet of things edge computing configuration method based on data privacy protection is characterized by comprising the following steps:
step 1, periodically detecting state information sent by an edge computing server on an appointed control channel during the interval of collecting current environment information by each terminal of the Internet of things;
step 2, selecting a standby edge computing server j of joint computing * The method specifically comprises the following steps:
2.1, assuming that the terminal i of the Internet of things is to perform all calculation tasks S i Sending the data to the edge computing server j for data processing, i.e. the computing task processed by the edge computing server j
Figure FDA0003794429990000011
And computing task processed by terminal i of Internet of things
Figure FDA0003794429990000012
By minimizing
Figure FDA0003794429990000013
Obtaining the optimal transmitting power of the terminal i of the Internet of things
Figure FDA0003794429990000014
And a corresponding consumption energy of
Figure FDA0003794429990000015
The data processing duration of the edge computing server j is
Figure FDA0003794429990000016
If it is
Figure FDA0003794429990000017
The edge computing server j is an available server; wherein the content of the first and second substances,
Figure FDA0003794429990000018
h i,j calculating channel gain between terminal i and edge server j for Internet of things, B i For the channel bandwidth, sigma, between the terminal i of the internet of things and the edge computing server j 2 Is the power of white noise, p i Is the transmitting power of the terminal i of the internet of things,
Figure FDA0003794429990000019
is the maximum transmitting power, G, of the terminal i of the Internet of things i,j The method comprises the steps that an internet of things terminal set in a circle with an internet of things terminal i as a circle center and the distance between the internet of things terminal i and an edge calculation server j as a radius is formed, eta is the average probability that the internet of things terminal is a malicious user interception target, and c i Weight factors bringing risks for intercepting the data are reflected;
2.2, standby edge compute Server j * The server with the lowest corresponding energy consumption in the available server set obtained in the step 2.1 is obtained;
step 3, calculating a server j according to the standby edge * Corresponding to
Figure FDA00037944299900000110
And
Figure FDA00037944299900000111
the method for determining the configuration scheme of the computing task specifically comprises the following steps:
3.1, if satisfied
Figure FDA00037944299900000112
And is
Figure FDA00037944299900000113
All calculation tasks S of Internet of things terminal i i Will be processed by its local computing unit; wherein the content of the first and second substances,
Figure FDA00037944299900000114
for all calculation tasks S i The total energy consumption for data processing by the internet of things terminal i,
Figure FDA00037944299900000115
for all calculation tasks S i The calculation time, tau, consumed by the internet of things terminal i for data processing i For processing the entire computational task S i The delay threshold of (c);
3.2 if satisfied
Figure FDA00037944299900000116
But do not
Figure FDA00037944299900000117
Terminal i of internet of things distributes part of calculation tasks to local calculation unit of terminal i of internet of things
Figure FDA0003794429990000021
If S i Of (2) the remainder of
Figure FDA0003794429990000022
By a standby edge computing server j * Upon completion satisfy
Figure FDA0003794429990000023
Then the terminal i of the internet of things will preferentially utilize the local computing unit to process
Figure FDA0003794429990000024
And will be
Figure FDA0003794429990000025
Send to a standby edge compute server j * Processing, otherwise S i Will be discarded; wherein the content of the first and second substances,
Figure FDA0003794429990000026
compute Server j for Standby edge * Treatment of
Figure FDA0003794429990000027
The length of time of;
3.3 if satisfied
Figure FDA0003794429990000028
And is
Figure FDA0003794429990000029
All calculation tasks S of terminal i of Internet of things i Will be sent to the standby edge computing server j * Finish the treatment, i.e.
Figure FDA00037944299900000210
3.4 if satisfied
Figure FDA00037944299900000211
But do not
Figure FDA00037944299900000212
Internet of things terminal i-to-server j * Distributing part of a computing task
Figure FDA00037944299900000213
If S i Of (2) the remainder of
Figure FDA00037944299900000214
Satisfied by local computing unit of terminal i of Internet of things
Figure FDA00037944299900000215
Then the terminal i of the internet of things will preferentially utilize the standby edge computing server j * Process S i E And processed by its local computing unit
Figure FDA00037944299900000216
Otherwise S i Will be discarded.
2. The Internet of things edge computing configuration method based on data privacy protection as claimed in claim 1,
Figure FDA00037944299900000217
where κ denotes a coefficient determined by processor characteristics, W i =S i X and X represent the number of clock cycles of a Central Processing Unit (CPU) required by the terminal i of the Internet of things for processing 1 bit data, f i M The maximum clock period allowed for the central processing unit of the terminal i of the internet of things.
3. The internet of things edge computing configuration method based on data privacy protection as claimed in claim 1, wherein the state information sent by the edge computing server includes edge server geographical location, data transmission channel quality and available bandwidth, and computing processing capacity.
CN201910921830.0A 2019-09-27 2019-09-27 Internet of things edge computing configuration method based on data privacy protection Active CN110650487B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910921830.0A CN110650487B (en) 2019-09-27 2019-09-27 Internet of things edge computing configuration method based on data privacy protection

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910921830.0A CN110650487B (en) 2019-09-27 2019-09-27 Internet of things edge computing configuration method based on data privacy protection

Publications (2)

Publication Number Publication Date
CN110650487A CN110650487A (en) 2020-01-03
CN110650487B true CN110650487B (en) 2022-10-28

Family

ID=69011562

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910921830.0A Active CN110650487B (en) 2019-09-27 2019-09-27 Internet of things edge computing configuration method based on data privacy protection

Country Status (1)

Country Link
CN (1) CN110650487B (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111585906A (en) * 2020-05-11 2020-08-25 浙江大学 Low-delay self-adaptive data distribution transmission method for industrial internet
CN111770477B (en) * 2020-06-08 2024-01-30 中天通信技术有限公司 Deployment method and related device for protection resources of MEC network
CN113452751A (en) * 2021-05-20 2021-09-28 国网江苏省电力有限公司信息通信分公司 Cloud edge cooperation-based power internet of things task secure migration system and method
CN113163019B (en) * 2021-05-28 2021-09-14 华中科技大学 Internet of things privacy protection service discovery system based on SDN and edge computing
CN115801693B (en) * 2023-01-05 2023-04-07 武汉朗宇智能科技有限公司 Low-blocking low-delay data communication method and system and readable storage medium

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
CN109829332A (en) * 2019-01-03 2019-05-31 武汉理工大学 A kind of combined calculation discharging method and device based on energy collection technology
CN109981753A (en) * 2019-03-07 2019-07-05 中南大学 A kind of system and resource allocation methods of the edge calculations of the software definition of internet of things oriented
CN110062026A (en) * 2019-03-15 2019-07-26 重庆邮电大学 Mobile edge calculations resources in network distribution and calculating unloading combined optimization scheme

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109829332A (en) * 2019-01-03 2019-05-31 武汉理工大学 A kind of combined calculation discharging method and device based on energy collection technology
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
CN109981753A (en) * 2019-03-07 2019-07-05 中南大学 A kind of system and resource allocation methods of the edge calculations of the software definition of internet of things oriented
CN110062026A (en) * 2019-03-15 2019-07-26 重庆邮电大学 Mobile edge calculations resources in network distribution and calculating unloading combined optimization scheme

Also Published As

Publication number Publication date
CN110650487A (en) 2020-01-03

Similar Documents

Publication Publication Date Title
CN110650487B (en) Internet of things edge computing configuration method based on data privacy protection
CN108880662B (en) Wireless information and energy transmission optimization method based on unmanned aerial vehicle
CN110839075A (en) Service migration method based on particle swarm in edge computing environment
CN113156992B (en) Three-layer architecture collaborative optimization method for unmanned aerial vehicle in edge environment
CN107708152B (en) Task unloading method of heterogeneous cellular network
CN110580199B (en) Service migration method based on particle swarm in edge computing environment
Jian et al. Joint computation offloading and resource allocation in C-RAN with MEC based on spectrum efficiency
Zou et al. Backscatter-aided hybrid data offloading for wireless powered edge sensor networks
Yao et al. Energy efficiency characterization in heterogeneous IoT system with UAV swarms based on wireless power transfer
CN111107153A (en) MEC pricing unloading method based on D2D communication in power Internet of things
CN111182569B (en) Edge calculation unloading period minimization method in 5G scene
Park et al. Kolkata paise restaurant game for resource allocation in the internet of things
Hammami et al. Drone-assisted cellular networks: A multi-agent reinforcement learning approach
CN109788540A (en) Power control and method for channel allocation in D2D system based on energy acquisition
Li et al. Online policies for throughput maximization of energy-constrained wireless-powered communication systems
He et al. A novel distributed resource allocation scheme for wireless-powered cognitive radio Internet of Things networks
CN107506847B (en) Stackelberg game-based pricing method in large-scale MIMO system for energy acquisition
Abuzainab et al. Robust Bayesian learning for wireless RF energy harvesting networks
Yan et al. Fairness-aware data offloading of IoT applications enabled by heterogeneous UAVs
Li et al. Operation state scheduling towards optimal network utility in RF-powered Internet of Things
Aldeen et al. Data communication for drone-enabled internet of things
CN110650526B (en) Energy-sharing EH distributed base station system power distribution method
Arabi et al. Tradeoffs for data collection and wireless energy transfer dilemma in IoT environments
Hamidouche et al. Popular matching games for correlation-aware resource allocation in the internet of things
CN109831826A (en) The joint resource allocation methods that row information is transmitted up and down in wireless energy supply communication 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