CN108632860A - A kind of mobile edge calculations rate maximization approach based on deeply study - Google Patents
A kind of mobile edge calculations rate maximization approach based on deeply study Download PDFInfo
- Publication number
- CN108632860A CN108632860A CN201810342359.5A CN201810342359A CN108632860A CN 108632860 A CN108632860 A CN 108632860A CN 201810342359 A CN201810342359 A CN 201810342359A CN 108632860 A CN108632860 A CN 108632860A
- Authority
- CN
- China
- Prior art keywords
- wireless device
- energy
- base station
- wireless devices
- wireless
- 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
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/02—Arrangements for optimising operational condition
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
A kind of mobile edge calculations rate maximization approach based on deeply study, includes the following steps：1) the rate summation by the edge calculations system of wireless power, calculating all wireless devices in system in the case where providing model selection is made of a base station and multiple wireless devices at one；2) an optimal model selection, i.e., the model selection M of all wireless devices are found by nitrification enhancement0And M1；3) the model selection M of all wireless devices0And M1System mode x as intensified learningt, action a is then to system mode xtChange, if system after changing it is total calculate speed ratio before to make currently to reward r (x greatlyt, it a) is set as positive value, on the contrary it is set as negative value, and simultaneity factor enters NextState xt+1, constantly repeat this iterative process and select M until obtaining optimal mode0And M1.The present invention maximizes the summation computation rate of all wireless devices under the premise of ensureing user experience.
Description
Technical field
The invention belongs to the communications fields, more particularly, to the communication system for moving edge calculations and are based on deeply
The mobile edge calculations rate maximization approach practised.
Background technology
The latest development of technology of Internet of things is the key that march toward really intelligence and one step of autonomous control, in many important works
It is especially prominent in industry and business system.In an Internet of Things network, the nothing that largely can be communicated and be calculated is deployed
Line equipment (WDs), limitation and production cost due to equipment size consider that internet of things equipment (such as sensor) often carries capacity
Limited battery and energy-efficient low performance processor, therefore, limited equipment life and low computing capability can not be supported increasingly
The sustainable new applications for needing high-performance calculation, such as automatic Pilot and augmented reality more.Wireless energy transfer system
(WPT) deployment can solve above-mentioned two performance issues, but frequent device battery failure has not only been upset normally
Personal wireless device operation can also significantly reduce overall network performance, for example, the sensing accuracy in wireless sensor network.It passes
The wireless system of system needs frequently to replace battery manually, this is costly and very inconvenient, since stringent battery capacity limits,
Energy consumption minimized in battery powered wireless system, it is a crucial design to extend wireless device operation life cycle.
The wireless device of each collection of energy follows binary computations distributing strategy, that is, the data set of a task can be at this
Ground is performed or is shunted by long-range server to execute.In order to maximize the summation computation rate of all wireless devices, look for
It is necessary to optimal independent calculating model selection.
Invention content
In order to overcome the lower deficiency of summation computation rate of existing wireless energy transfer system, in order to maximize whether there is or not
The summation calculation rate of line equipment finds optimal independent calculating model selection and the distribution of system transmission time, the present invention provides
A kind of mobile edge calculations rate maximization approach based on deeply study, maximizes under the premise of ensureing user experience
The summation computation rate of all wireless devices.
The technical scheme adopted by the invention to solve the technical problem is that：
A kind of mobile edge calculations rate maximization approach based on deeply study, the method includes following steps
Suddenly：
1) be made of by the edge calculations system of wireless power a base station and multiple wireless devices at one, base station and
There are one individual antennas for each wireless device；RF energy transmitter and edge calculations server all integrate in a base station,
Assuming that there are one the energy supplies stablized for base station, and energy broadcast radio frequency energy gives all wireless devices；Each wireless device
All there are one energy collection circuit and a rechargeable batteries, some tasks are completed by storing the energy collected；At this
In wireless communication system, each wireless device is required for establishing with base station and contact, the channel gain between wireless device i and base station
hiIt is calculated as：
Wherein, each parameter definition is as follows：
Ad：Antenna gain；
π：Pi；
fc：Carrier frequency；
di：The distance between wireless device i and base station；
de：Path loss index；
2) assume that the calculating task of each wireless device can execute or divide on the microprocessor of local low performance
It flows to the edge calculations server with more powerful processing capacity, then result is sent back processing calculating task wirelessly by it
Equipment；Assuming that wireless device is regular using binary computations shunting, it is, a wireless device must select to be local computing
Pattern or shunt mode；Use the set of two non-overlapping copiesWithIt is illustrated respectively in local computing pattern and shunting
All wireless devices of pattern, all wireless device setIt is expressed as：
3) it is in setIn wireless device can collect energy and handle local task simultaneously, and be in setIn wireless device can only after collecting energy by task branch to base station processing, it is assumed that the computing capability of base station and transmission
Ability is eager to excel much bigger than energy acquisition wireless device, and in this case, in task branching process, wireless device exhausts
Its energy collected；The computation rate summation maximization problems of all wireless devices is described as：
Constraints is：
In formula：
Wherein, each parameter definition is as follows：
ωi：The conversion weight of i-th of wireless device；
μ：Efficiency of energy collection；
P：RF energy transimission power；
Φ：Handle the calculating cycle-index needed for each data；
hi：The channel gain of i-th of wireless device；
ki：The energy efficiency coefficient of i-th of wireless device；
a：Time coefficient；
vμ：Transfer efficiency；
B：Bandwidth；
τj：The time coefficient of j-th of wireless device；
N0：The number of wireless device under processing locality pattern；
4) an optimal model selection, i.e., the model selection of all wireless devices are found by nitrification enhancementWithThe reinforcement learning system is made of intelligent body and environment.The model selection of all usersWithAll by
It compiles into system current state xt, intelligent body is taken under current state acts a into next state xt+1, while obtaining ring
Reward r (the x that border returnst, a), under intelligent body and the continuous interactive refreshing of environment, model selectionWithTo be constantly excellent
Change is optimal until finding, and the update mode of intelligent body is：
Qθ(xt, a)=r (xt,a)+γmaxQθ′(xt+1,a′) (4)
Wherein, each parameter definition is as follows：
θ：Assess the parameter in network；
θ′：Parameter in target network；
xt：In moment t, system status；
Qθ(xt,a)：In state xtUnder take action the obtained Q values of a；
r(xt,a)：In state xtUnder take action the obtained rewards of a；
γ：Reward decaying proportion；
5) model selection of all wireless devicesWithSystem mode x as deeply studyt, action a is then
It is to system mode xtChange, if system after changing it is total calculate speed ratio before to make currently to reward r (x greatlyt,
A) it is set as positive value, otherwise is set as negative value, simultaneity factor enters NextState xt+1。
Further, in the step 5), the iterative process of intensified learning is：
Step 5.1：Initialize the assessment network in intensified learning, target network and data base.Current system conditions are xt,
T is initialized as 1, and iterations k is initialized as 1；
Step 5.2：When k is less than or equal to given iterations K, a Probability p is randomly choosed；
Step 5.3：If p is less than or equal to ε；The action a (t) for then selecting assessment network to be exported, otherwise randomly chooses
One action；
Step 5.4：After taking action a (t), receive awards r (t) and next step state x (t+1), and these information are pressed
(x (t), a (t), r (t), x (t+1)) is stored in data base in accordance with the form provided；
Step 5.5：The output of combining target network calculates the target y=r (x of assessment networkt,a)+γmaxQθ′(xt+1,
a′)；
Step 5.6：Minimize error (y-Q (x (t), a (t)；θ))2, while updating the parameter θ of assessment network so that its
Next time can measure more accurate in advance；
Step 5.7：It is walked every S, the parameter assignment for assessing network is returned into step to target network with season k=k+1
4.2；
Step 5.8：When k is more than given iterations K, learning process terminates, and obtains optimal mode selectionWith
The present invention technical concept be：First, in an Internet of Things network, deploy can largely carry out communication and
The wireless device (WDs) of calculating, limitation and production cost due to equipment size consider that internet of things equipment (such as sensor) is frequent
The limited battery of capacity and energy-efficient low performance processor are carried, therefore, limited equipment life and low computing capability can not prop up
More and more sustainable new applications for needing high-performance calculation are held, since stringent battery capacity limits, with battery
Energy consumption minimized in the wireless system of power supply, it is a crucial design to extend wireless device operation life cycle.Each energy
The wireless device that amount is collected all follows binary computations distributing strategy, that is, the data set of a task can be locally executed
Or it is shunted by long-range server to execute.In order to maximize the summation computation rate of all wireless devices, it is proposed that a kind of
Optimal independent calculating mode selecting method.
Beneficial effects of the present invention are mainly manifested in：Optimal model selection side is searched out by deeply study study
Method maximizes the summation computation rate of all wireless devices, energy consumption minimized, extends wireless device operation life cycle.
Description of the drawings
Fig. 1 is system model schematic diagram.
Fig. 2 is the method flow diagram for finding optimal model selection.
Specific implementation mode
Present invention is further described in detail below in conjunction with the accompanying drawings.
Referring to Figures 1 and 2, a kind of mobile edge calculations rate maximization approach based on deeply study study, most
Change the summation computation rate of all wireless devices greatly, it is energy consumption minimized, extend wireless device operation life cycle, the present invention is based on
The system model (as shown in Figure 1) of multiradio device, it is proposed which optimal independent calculating mode selecting method determines
The task of a little wireless devices can be split to base station, and the optimal independent calculating mode selecting method includes following steps
(as shown in Figure 2)：
1) be made of by the edge calculations system of wireless power a base station and multiple wireless devices at one, base station and
There are one individual antennas for each wireless device；RF energy transmitter and edge calculations server all integrate in a base station,
Assuming that there are one the energy supplies stablized for base station, and energy broadcast radio frequency energy gives all wireless devices；Each wireless device
All there are one energy collection circuit and a rechargeable batteries, some tasks are completed by storing the energy collected；At this
In wireless communication system, each wireless device is required for establishing with base station and contact, the channel gain between wireless device i and base station
hiIt is calculated as：
Wherein, each parameter definition is as follows：
Ad：Antenna gain；
π：Pi；
fc：Carrier frequency；
di：The distance between wireless device i and base station；
de：Path loss index；
2) assume that the calculating task of each wireless device can execute or divide on the microprocessor of local low performance
It flows to the edge calculations server with more powerful processing capacity, then result is sent back processing calculating task wirelessly by it
Equipment；Assuming that wireless device is regular using binary computations shunting, it is, a wireless device must select to be local computing
Pattern or shunt mode；Use the set of two non-overlapping copiesWithIt is illustrated respectively in local computing pattern and shunting
All wireless devices of pattern, all wireless device setIt is expressed as：
3) it is in setIn wireless device can collect energy and handle local task simultaneously, and be in setIn wireless device can only after collecting energy by task branch to base station processing, it is assumed that the computing capability of base station and transmission
Ability is eager to excel much bigger than energy acquisition wireless device, and in this case, in task branching process, wireless device exhausts
Its energy collected, the computation rate summation maximization problems of all wireless devices are described as：
Constraints is：
In formula：
Wherein, each parameter definition is as follows：
ωi：The conversion weight of i-th of wireless device；
μ：Efficiency of energy collection；
P：RF energy transimission power；
Φ：Handle the calculating cycle-index needed for each data；
hi：The channel gain of i-th of wireless device；
ki：The energy efficiency coefficient of i-th of wireless device；
a：Time coefficient；
vμ：Transfer efficiency；
B：Bandwidth；
τj：The time coefficient of j-th of wireless device；
N0：The number of wireless device under processing locality pattern；
4) an optimal model selection, i.e., the model selection of all wireless devices are found by nitrification enhancementWithThe reinforcement learning system is made of intelligent body and environment.The model selection of all usersWithAll by
It compiles into system current state xt, intelligent body is taken under current state acts a into next state xt+1, while obtaining ring
Reward r (the x that border returnst, a), under intelligent body and the continuous interactive refreshing of environment, model selectionWithTo be constantly excellent
Change is optimal until finding, and the update mode of intelligent body is：
Qθ(xt, a)=r (xt,a)+γmaxQθ′(xt+1,a′) (4)
Wherein, each parameter definition is as follows：
θ：Assess the parameter in network；
θ′：Parameter in target network；
xt：In moment t, system status；
Qθ(xt,a)：In state xtUnder take action the obtained Q values of a；
r(xt,a)：In state xtUnder take action the obtained rewards of a；
γ：Reward decaying proportion；
5) model selection of all wireless devicesWithSystem mode x as deeply studyt, action a is then
It is to system mode xtChange, if system after changing it is total calculate speed ratio before to make currently to reward r (x greatlyt,
A) it is set as positive value, otherwise is set as negative value, simultaneity factor enters NextState xt+1。
In the step 5), the iterative process of intensified learning is：
Step 5.1：Initialize the assessment network in intensified learning, target network and data base.Current system conditions are xt,
T is initialized as 1, and iterations k is initialized as 1；
Step 5.2：When k is less than or equal to given iterations K, a Probability p is randomly choosed；
Step 5.3：If p is less than or equal to ε；The action a (t) for then selecting assessment network to be exported, otherwise randomly chooses
One action；
Step 5.4：After taking action a (t), receive awards r (t) and next step state x (t+1), and these information are pressed
(x (t), a (t), r (t), x (t+1)) is stored in data base in accordance with the form provided；
Step 5.5：The output of combining target network calculates the target y=r (x of assessment networkt,a)+γmaxQθ′(xt+1,
a′)；
Step 5.6：Minimize error (y-Q (x (t), a (t)；θ))2, while updating the parameter θ of assessment network so that its
Next time can measure more accurate in advance；
Step 5.7：It is walked every S, the parameter assignment for assessing network is returned into step to target network with season k=k+1
4.2；
Step 5.8：When k is more than given iterations K, learning process terminates, and obtains optimal mode selectionWith
Claims (2)
1. a kind of mobile edge calculations rate maximization approach based on deeply study, which is characterized in that the method packet
Include following steps：
1) it is made of by the edge calculations system of wireless power a base station and multiple wireless devices at one, base station and each
All there are one individual antennas for wireless device；RF energy transmitter and edge calculations server all integrate in a base station, it is assumed that
There are one the energy supplies stablized for base station, and energy broadcast radio frequency energy gives all wireless devices；Each wireless device has
One energy collection circuit and a rechargeable battery complete some tasks by storing the energy collected；It is wireless at this
In communication system, each wireless device is required for establishing with base station and contact, the channel gain h between wireless device i and base stationiMeter
It is：
Wherein, each parameter definition is as follows：
Ad：Antenna gain；
π：Pi；
fc：Carrier frequency；
di：The distance between wireless device i and base station；
de：Path loss index；
2) assume that the calculating task of each wireless device can be executed or be diverted on the microprocessor of local low performance
Edge calculations server with more powerful processing capacity, then result is sent back and is wirelessly set by it by processing calculating task
It is standby；Assuming that wireless device is regular using binary computations shunting, it is, a wireless device must select to be local computing mould
Formula or shunt mode；Use the set of two non-overlapping copiesWithIt is illustrated respectively in local computing pattern and divergent die
All wireless devices of formula, all wireless device setIt is expressed as：
3) it is in setIn wireless device can collect energy and handle local task simultaneously, and be in setIn
Wireless device can only after collecting energy by task branch to base station processing, it is assumed that the computing capability and transmittability of base station are wanted
It is eager to excel than energy acquisition wireless device much bigger, in this case, in task uninstall process, wireless device runs out of its receipts
The computation rate summation maximization problems of the energy of collection, all wireless devices is described as：
Constraints is：
In formula：
Wherein, each parameter definition is as follows：
ωi：The conversion weight of i-th of wireless device；
μ：Efficiency of energy collection；
P：RF energy transimission power；
Φ：Handle the calculating cycle-index needed for each data；
hi：The channel gain of i-th of wireless device；
ki：The energy efficiency coefficient of i-th of wireless device；
a：Time coefficient；
vμ：Transfer efficiency；
B：Bandwidth；
τj：The time coefficient of j-th of wireless device；
N0：The number of wireless device under processing locality pattern；
4) an optimal model selection, i.e., the model selection of all wireless devices are found by nitrification enhancementWithThe reinforcement learning system is made of intelligent body and environment；The model selection of all usersWithAll compiled into
System current state xt, intelligent body is taken under current state acts a into next state xt+1, while obtaining environment return
Reward r (xt,a)；Under intelligent body and the continuous interactive refreshing of environment, model selectionWithWill constantly it is optimised until
Find optimal, the update mode of intelligent body is：
Qθ(xt, a)=r (xt,a)+γmaxQθ′(xt+1,a′) (4)
Wherein, each parameter definition is as follows：
θ：Assess the parameter in network；
θ′：Parameter in target network；
xt：In moment t, system status；
Qθ(xt,a)：In state xtUnder take action the obtained Q values of a；
r(xt,a)：In state xtUnder take action the obtained rewards of a；
γ：Reward decaying proportion；
5) model selection of all wireless devicesWithSystem mode x as deeply studyt, action a is then pair
System mode xtChange, if system after changing it is total calculate speed ratio before to make currently to reward r (x greatlyt, a) set
For positive value, on the contrary to be set as negative value, simultaneity factor enters NextState xt+1。
2. a kind of mobile edge calculations rate maximization approach based on deeply study as described in claim 1, special
Sign is：In the step 5), the iterative process of intensified learning is：
Step 5.1：Initialize the assessment network in intensified learning, target network and data base, current system conditions xt, t is initial
1 is turned to, iterations k is initialized as 1；
Step 5.2：When k is less than or equal to given iterations K, a Probability p is randomly choosed；
Step 5.3：If p is less than or equal to ε；The action a (t) for then selecting assessment network to be exported, otherwise randomly chooses one
Action；
Step 5.4：After taking action a (t), receive awards r (t) and next step state x (t+1), and by these information according to lattice
Formula (x (t), a (t), r (t), x (t+1)) is stored in data base；
Step 5.5：The output of combining target network calculates the target y=r (x of assessment networkt,a)+γmaxQθ′(xt+1,a′)；
Step 5.6：Minimize error (y-Q (x (t), a (t)；θ))2, while updating the parameter θ of assessment network so that its next energy
It measures in advance more accurate；
Step 5.7：It is walked every S, the parameter assignment for assessing network is returned into step 4.2 to target network with season k=k+1；
Step 5.8：When k is more than given iterations K, learning process terminates, and obtains optimal mode selectionWith
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810342359.5A CN108632860B (en) | 2018-04-17 | 2018-04-17 | Mobile edge calculation rate maximization method based on deep reinforcement learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810342359.5A CN108632860B (en) | 2018-04-17 | 2018-04-17 | Mobile edge calculation rate maximization method based on deep reinforcement learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108632860A true CN108632860A (en) | 2018-10-09 |
| CN108632860B CN108632860B (en) | 2021-06-18 |
Family
ID=63705383
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810342359.5A Active CN108632860B (en) | 2018-04-17 | 2018-04-17 | Mobile edge calculation rate maximization method based on deep reinforcement learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108632860B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109618399A (en) * | 2018-12-26 | 2019-04-12 | 东华大学 | Distributed energy management solutions optimization method in the mobile edge calculations system of multi-user |
| CN109756371A (en) * | 2018-12-27 | 2019-05-14 | 上海无线通信研究中心 | A kind of network node resource perception motivational techniques and system based on game |
| CN109803292A (en) * | 2018-12-26 | 2019-05-24 | 佛山市顺德区中山大学研究院 | A method of the mobile edge calculations of more secondary user's based on intensified learning |
| CN110809306A (en) * | 2019-11-04 | 2020-02-18 | 电子科技大学 | Terminal access selection method based on deep reinforcement learning |
| CN111556461A (en) * | 2020-04-29 | 2020-08-18 | 南京邮电大学 | Vehicle-mounted edge network task distribution and unloading method based on deep Q network |
| WO2021147192A1 (en) * | 2020-01-21 | 2021-07-29 | 厦门邑通软件科技有限公司 | Machine heuristic learning method, system and device for operation behavior record management |
| CN113727362A (en) * | 2021-05-31 | 2021-11-30 | 南京邮电大学 | Unloading strategy method of wireless power supply system based on deep reinforcement learning |
| CN118138640A (en) * | 2024-05-07 | 2024-06-04 | 安徽省交通规划设计研究总院股份有限公司 | Cloud platform user data transmission optimization system and method |
| CN118138640B (en) * | 2024-05-07 | 2024-07-02 | 安徽省交通规划设计研究总院股份有限公司 | Cloud platform user data transmission optimization system and method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107708135A (en) * | 2017-07-21 | 2018-02-16 | 上海交通大学 | A kind of resource allocation methods for being applied to mobile edge calculations scene |
| CN107734558A (en) * | 2017-10-26 | 2018-02-23 | 北京邮电大学 | A kind of control of mobile edge calculations and resource regulating method based on multiserver |
| CN107846704A (en) * | 2017-10-26 | 2018-03-27 | 北京邮电大学 | A kind of resource allocation and base station service arrangement method based on mobile edge calculations |
| CN107872823A (en) * | 2016-09-28 | 2018-04-03 | 维布络有限公司 | The method and system of communication operational mode in the mobile edge calculations environment of identification |
| US9942825B1 (en) * | 2017-03-27 | 2018-04-10 | Verizon Patent And Licensing Inc. | System and method for lawful interception (LI) of Network traffic in a mobile edge computing environment |
| CN107911242A (en) * | 2017-11-15 | 2018-04-13 | 北京工业大学 | A kind of cognitive radio based on industry wireless network and edge calculations method |
-
2018
- 2018-04-17 CN CN201810342359.5A patent/CN108632860B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107872823A (en) * | 2016-09-28 | 2018-04-03 | 维布络有限公司 | The method and system of communication operational mode in the mobile edge calculations environment of identification |
| US9942825B1 (en) * | 2017-03-27 | 2018-04-10 | Verizon Patent And Licensing Inc. | System and method for lawful interception (LI) of Network traffic in a mobile edge computing environment |
| CN107708135A (en) * | 2017-07-21 | 2018-02-16 | 上海交通大学 | A kind of resource allocation methods for being applied to mobile edge calculations scene |
| CN107734558A (en) * | 2017-10-26 | 2018-02-23 | 北京邮电大学 | A kind of control of mobile edge calculations and resource regulating method based on multiserver |
| CN107846704A (en) * | 2017-10-26 | 2018-03-27 | 北京邮电大学 | A kind of resource allocation and base station service arrangement method based on mobile edge calculations |
| CN107911242A (en) * | 2017-11-15 | 2018-04-13 | 北京工业大学 | A kind of cognitive radio based on industry wireless network and edge calculations method |
Non-Patent Citations (1)
| Title |
|---|
| SUZHI BI等: "Computation Rate Maximization for Wireless Powered Mobile-Edge Computing With Binary Computation Offloading", 《IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109618399A (en) * | 2018-12-26 | 2019-04-12 | 东华大学 | Distributed energy management solutions optimization method in the mobile edge calculations system of multi-user |
| CN109803292A (en) * | 2018-12-26 | 2019-05-24 | 佛山市顺德区中山大学研究院 | A method of the mobile edge calculations of more secondary user's based on intensified learning |
| CN109803292B (en) * | 2018-12-26 | 2022-03-04 | 佛山市顺德区中山大学研究院 | Multi-level user moving edge calculation method based on reinforcement learning |
| CN109756371A (en) * | 2018-12-27 | 2019-05-14 | 上海无线通信研究中心 | A kind of network node resource perception motivational techniques and system based on game |
| CN109756371B (en) * | 2018-12-27 | 2022-04-29 | 上海无线通信研究中心 | Game-based network node resource perception excitation method and system |
| CN110809306A (en) * | 2019-11-04 | 2020-02-18 | 电子科技大学 | Terminal access selection method based on deep reinforcement learning |
| WO2021147192A1 (en) * | 2020-01-21 | 2021-07-29 | 厦门邑通软件科技有限公司 | Machine heuristic learning method, system and device for operation behavior record management |
| CN111556461A (en) * | 2020-04-29 | 2020-08-18 | 南京邮电大学 | Vehicle-mounted edge network task distribution and unloading method based on deep Q network |
| CN113727362A (en) * | 2021-05-31 | 2021-11-30 | 南京邮电大学 | Unloading strategy method of wireless power supply system based on deep reinforcement learning |
| CN113727362B (en) * | 2021-05-31 | 2022-10-28 | 南京邮电大学 | Unloading strategy method of wireless power supply system based on deep reinforcement learning |
| CN118138640A (en) * | 2024-05-07 | 2024-06-04 | 安徽省交通规划设计研究总院股份有限公司 | Cloud platform user data transmission optimization system and method |
| CN118138640B (en) * | 2024-05-07 | 2024-07-02 | 安徽省交通规划设计研究总院股份有限公司 | Cloud platform user data transmission optimization system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108632860B (en) | 2021-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108632860A (en) | A kind of mobile edge calculations rate maximization approach based on deeply study | |
| CN101835237B (en) | Data aggregation method in wireless sensor network | |
| Hou et al. | Greenhouse wireless sensor network monitoring system design based on solar energy | |
| CN105242239A (en) | Indoor subarea positioning method based on crowdsourcing fingerprint clustering and matching | |
| CN107613567A (en) | A kind of radio sensing network resource allocation methods based on wireless power transfer | |
| CN106887887A (en) | Movable charging vehicle dispatching method in a kind of wireless chargeable Sensor Network | |
| CN101610567A (en) | A kind of dynamic group scheduling method based on wireless sensor network | |
| CN205193059U (en) | Wireless sensor's network node for water quality monitoring | |
| CN108632861A (en) | A kind of mobile edge calculations shunting decision-making technique based on deeply study | |
| CN104767833B (en) | A kind of high in the clouds transfer method of the calculating task of mobile terminal | |
| CN103323866A (en) | Low-power-consumption beidou receiver based on cloud calculation and positioning method thereof | |
| CN108738045A (en) | A kind of mobile edge calculations rate maximization approach based on depth deterministic policy gradient method | |
| CN103995859A (en) | Geographical-tag-oriented hot spot area event detection system applied to LBSN | |
| CN109831236A (en) | A kind of beam selection method based on Monte Carlo tree search auxiliary | |
| CN108738046A (en) | A kind of mobile edge calculations rate maximization approach based on semi-supervised learning | |
| CN105550480A (en) | Greedy energy source minimization arrangement method of RF (Radio Frequency)-energy harvesting wireless sensor network | |
| Dehni et al. | Power control and clustering in wireless sensor networks | |
| CN110060176A (en) | Electric power Internet of Things intelligent power distribution method, readable storage medium storing program for executing and terminal | |
| CN103327450A (en) | Intensive-calculating GPS receiver based on mobile communication network and positioning method of same | |
| Rinne et al. | Viability bounds of M2M communication using energy-harvesting and passive wake-up radio | |
| CN111757266A (en) | UAV data acquisition trajectory algorithm based on solar power supply type agricultural Internet of things | |
| CN105338620B (en) | Positioning module, wireless location card and system applied to Internet of Things | |
| CN108650710B (en) | Resource allocation method of wireless energy supply communication network based on hybrid multiple access | |
| Wei et al. | Accurate visible light positioning technique using extreme learning machine and meta-heuristic algorithm | |
| CN116980834A (en) | Low-power consumption control method and system for Bluetooth beacon |
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 |