CN107734579A - A kind of mobile platform energy consumption optimization method based on Markovian decision process - Google Patents
A kind of mobile platform energy consumption optimization method based on Markovian decision process Download PDFInfo
- Publication number
- CN107734579A CN107734579A CN201710962155.7A CN201710962155A CN107734579A CN 107734579 A CN107734579 A CN 107734579A CN 201710962155 A CN201710962155 A CN 201710962155A CN 107734579 A CN107734579 A CN 107734579A
- Authority
- CN
- China
- Prior art keywords
- network
- value
- optimal
- microblogging
- energy consumption
- 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
- H04W36/00—Hand-off or reselection arrangements
- H04W36/0005—Control or signalling for completing the hand-off
- H04W36/0083—Determination of parameters used for hand-off, e.g. generation or modification of neighbour cell lists
- H04W36/0085—Hand-off measurements
- H04W36/0094—Definition of hand-off measurement parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/52—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail for supporting social networking services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W36/00—Hand-off or reselection arrangements
- H04W36/14—Reselecting a network or an air interface
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W52/00—Power management, e.g. TPC [Transmission Power Control], power saving or power classes
- H04W52/02—Power saving arrangements
- H04W52/0209—Power saving arrangements in terminal devices
- H04W52/0212—Power saving arrangements in terminal devices managed by the network, e.g. network or access point is master and terminal is slave
-
- 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)
- Computing Systems (AREA)
- Telephone Function (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
A kind of mobile platform energy consumption optimization method based on Markovian decision process, this method considers the network state of varying environment, according to mobile phone current electric quantity and user's refreshing frequency, optimal policy is selected in the decision table of Markovian decision process generation, optimal picture format is downloaded in the optimal network insertion of dynamic select and refreshing.This method not only reduces refresh time, and can reduce the energy consumption of mobile platform.Test result indicates that compared to the picture refresh mode using single network, on the premise of ensureing not reducing user's refreshing frequency, energy consumption optimization method proposed by the present invention reduces energy consumption about 12.1%.
Description
Technical field
The invention belongs to computer network communication technology field, and in particular to a kind of shifting based on Markovian decision process
Moving platform energy consumption optimization method.
Background technology
As science and technology is constantly weeded out the old and bring forth the new, the market share volume of Intelligent mobile equipment is constantly lifted.At the same time, with nothing
The development and lifting of line access network technology, mobile Internet become after large scale computer, minicomputer, PC, desktop interconnection
The 5th lead-time after net.By in June, 2016, domestic mobile phone netizen number has reached 6.56 hundred million, Wang Minzhong
Lifted to 92.5% from the 90.1% of the end of the year 2015 with the number of surfing Internet with cell phone, only also accounted for by surfing Internet with cell phone netizen
24.5%, people's equipment for surfing the net is more concentrated to mobile terminal.
Social networks is as in the form of the network service by mankind's social activity for core, with the continuous development of internet, also by
Gradually turn into the main flow in network.In daily life, the whole nation takes about 200 minutes in mobile phone using upper for each person every day, and makes
With being mostly frequently more social software, include wechat, QQ, Sina weibo etc..Interior survey is carried out from Sina weibo in 2009 to open
Begin, Sina weibo just becomes one of domestic social platform with strongest influence power.According to the domestic social media of issue in 2011
Share seniority among brothers and sisters, Sina weibo user percentage is 31.29%, is ranked first.Sina weibo is put down as now the most hot social activity
One of platform, in, registered user has surpassed 500,000,000 in by the end of December, 2012, until actively measuring user by the microblogging moon in 2015 breaches 2.12 hundred million,
Mobile end subscriber occupies 86%.Microblogging produces 100,000 articles, up to ten thousand of video, 21,000,000, picture daily.In micro-blog information
In, picture becomes main transloading mode, is a part essential in microblogging.
In Sina weibo open platform, can view the picture format included in microblogging be divided into artwork, high definition figure with
And thumbnail different type, experimental result are shown, energy consumption of the different-format picture required in refresh process is different, and
There is notable difference.And in real life, user under varying environment state, mobile phone-downloaded power and downloading duration be it is each not
Identical, the energy consumption required for refresh picture microblogging are higher.The present invention proposes mobile phone in different network rings regarding to the issue above
Under the state of border, different refresh activities is performed, refreshes optimal picture form under prevailing circumstances state, it is excellent to reach maximization energy consumption
Change.
During mobile client use, the network environment where user is continually changing, and network signal is strong
Degree is continuous dynamic change, and the change of 4G and Wi-Fi network signal is all separate, next signal intensity and upper one
Individual signal intensity does not have interrelated relation, and in order to tackle the process of this dynamic change, proposition uses Markov decisior process
Journey.Markovian decision process is the state observed according to each moment, from available set of actions from an action simultaneously
Make a policy, and the state of system next step changes at random.In daily life, many processes and Markovian decision
Process is all quite similar, such as queuing system, population change process, and 4G network signals and Wi-Fi nets are found in the present invention
Network signal change procedure is also quite similar with above mentioned problem, and their condition conversions all change at random, and pass through difference
Action obtain different award value, optimal policy decision table is finally calculated.
The content of the invention
In order to overcome the above-mentioned deficiencies of the prior art, it is an object of the invention to provide one kind to be based on Markovian decision process
Mobile platform energy consumption optimization method, download content for mobile social networking application itself, in mobile social networking application running,
Network signal intensity grade point (predominantly 4G, Wi-Fi), the environment at place according to where active user be it is continually changing,
Time interval value, residual electric quantity, select the different-format of picture in microblogging, including artwork, high definition, thumbnail and without figure,
Environmental condition change process is described using the MDP models of continuous time, state transition probability performance state shifts randomness, then
Mathematical modeling is carried out for user's decision-making process, simulation optimization obtains optimal policy decision table, reduces mobile platform energy consumption,
Reduce user's refresh time simultaneously.
To achieve these goals, the technical solution adopted by the present invention is:
A kind of mobile platform energy consumption optimization method based on Markovian decision process, comprises the following steps:
1)Using the Android application of the api interface independent development provided based on Sina weibo open platform, Mix test APP, should answer
With possess the login of Sina weibo mobile client end subscriber, refreshing information, the work(such as release news, browse information and log off
Energy;
2)Ambient condition value where Mix test APP automatic data collections users, ambient condition value include network signal, described network
Signal is 4G or Wi-Fi network, and 4G or Wi-Fi network strength grade value, time interval value, mobile phone residual electric quantity, user brush
New microblogging frequency values, meanwhile, Wi-Fi network disconnection threshold value is set according to network signal intensity grade point, mobile terminal is cut automatically
Change 4G and Wi-Fi communication networks;Markovian decision process is the set of a four-tuple state, including (S,A,P(),R()), step 2)The ambient condition value collected, the state that as finite state set S is included, when user is whole using movement
During end, then mobile terminal preferential attachment Wi-Fi network sets network switching threshold value, the method turns into Mix network switching moulds
Formula, the LTE signal strength scale value dividing modes that network signal level value is increased income defined in API according to Android, each network
Level of signal is divided into 5 grades, and respectively 5,4,3,2,1, when Wi-Fi network signal strength scale value is not more than 2, user can not
Complete to refresh microblogging action, now reach network switching threshold value, using automatically switching to 4G communication networks;
3)Countinuous time MDP mathematical modeling is established, according to step 2)The ambient condition value collected is empty as the state of MDP models
Between, the dynamic transfer probability of MDP models is then established, the motion space of MDP models is finally established, mesh is used as using optimal award value
Scalar functions, MDP model change procedures are emulated, obtain optimal policy decision table;
4)MDP models are emulated using MATLAB, optimal policy decision-making is obtained using all state sets as input value, solving model
Table;
5)In actual use, Mix tests APP according to ambient condition value and step 4)Optimal policy decision table, selection
Optimal communication network and optimal picture form, complete to refresh microblogging action.
Described step 1)Middle Mix tests APP, comprising user's login, refreshing information, release news, browse information and
Log off, asked during actual refreshing information, it is necessary to be sent by network connection to server end, according to return URL
Address is downloaded related content, and wherein content includes text information, pictorial information, in optimization method, passes through dynamic select
Picture format, according to corresponding picture format URL addresses, optimal picture form is selected, downloads and refreshes microblogging.
Described step 3)By step 2)The ambient condition value collected arranges generating probability setP, and relevant action
SetA, set of rewardsRAs MDP mode input values, refresh picture corresponding to network signal level value is included in set of actions A
Form, set of actions A is sub-divided into 4G and two kinds of network action set of Wi-Fi, under 4G network connections, works as signal strength scale
Be worth for 1 when, now network will be regarded as that network can not be connected, such because now needing a large amount of energy consumptions to download refreshes microbloggings
Can not refresh microblogging under level value, under other grade points, correspond to from high to low download pictures form be original image, high definition picture,
Thumbnail and without bitmap-format, and under Wi-Fi network connection, it is considered as network disconnection when signal strength scale value is not more than 2,
Can not download refreshing microblogging, other grade points from high to low correspond to download pictures form be respectively original image, high definition picture with
And thumbnail pictures.
The beneficial effects of the invention are as follows:
This method core is according to user's local environment state value, constantly dynamic adjustment user's decision table.In actual use process
In, APP and Mix network switching patterns are tested using Mix, using optimum network and selection optimal picture form, reduce net
Itself energy consumption is applied in network disconnection time and reduction.
Brief description of the drawings
Fig. 1 is the social APP models of the present invention.
Fig. 2 is usage scenario figure of the present invention
Fig. 3 is the workflow diagram of the inventive method.
Embodiment
Technical scheme is described in detail with reference to embodiment and Figure of description, but not limited to this.
As shown in figure 1, user logs in Mix test APP, using Sina weibo user authentication interface is automatic jumped to, input
Account number cipher obtains user's Token secret orders, and Token secret orders are effective within a certain period of time, and logins next time without verifying again.
User is logined after Mix tests APP, using by ambient condition value where automatic data collection user, ambient condition value bag
Refresh containing network signal (predominantly 4G and Wi-Fi network) strength grade value, time interval value, mobile phone residual electric quantity, user
Microblogging frequency values, the form that the ambient condition value collected is set with database is subjected to arranging order, mobile phone sheet is arrived in storage
Ground database, and data are finally sent to specified mailbox with mail he.
Countinuous time MDP mathematical modeling is established, state of the ambient condition value collected according to step 2 as MDP models
Space, probable value between the conversion of each ambient condition is calculated according to data, then establishes the dynamic transfer probability matrix of MDP models, most
The set of actions of MDP models is established afterwards, using optimal award value as object function, is emulated MDP model change procedures, is obtained optimal
Strategic decision-making table, is output to local.In general, Markovian decision process is the set of a four-tuple state, including (S,
A, P. (), R. ()).The ambient condition value that step 2 collects, the state that as finite state set S is included.When user makes
During with mobile terminal, then mobile terminal preferential attachment Wi-Fi network sets network switching threshold value, the method turns into Mix networks
Switch mode.The LTE signal strength scale value dividing modes that network signal level value is increased income defined in API according to Android, often
Individual network signal level is divided into 5 grades, and respectively 5,4,3,2,1.When Wi-Fi network signal strength scale value is not more than 2, use
Family can not complete to refresh microblogging action, now reach network switching threshold value, using 4G communication networks are automatically switched to, complete microblogging
Refresh.
MDP models are emulated using MATLAB, solving model obtains optimal policy decision table, and optimal policy decision table is embedding
Enter to Mix and test in APP mobile phones, optimal policy is searched when being actually used so as to user.Network signal etc. is included in set of actions A
Refresh picture form corresponding to level value, 4G and two kinds of network action set of Wi-Fi are sub-divided into by set of actions A.Connect in 4G networks
Connect down, when signal strength scale value is 1, now network will be regarded as that network can not be connected, because now needing under a large amount of energy consumptions
Carry and refresh microblogging, so microblogging can not be refreshed under the grade point.Under other grade points, corresponding to download pictures form from high to low is
Original image, high definition picture, thumbnail and without bitmap-format.And under Wi-Fi network connection, when signal strength scale value is little
It is considered as network disconnection when 2, refreshing microblogging can not be downloaded, it is respectively original that other grade points from high to low, which correspond to download pictures form,
Beginning picture, high definition picture and thumbnail pictures.
In actual use, Mix tests APP by the ambient condition value that gets, in the optimal plan being locally stored
Optimal policy slightly is searched in decision table, switches optimal communication network (predominantly 4G and Wi-Fi), downloads optimal picture form, it is complete
Acted into microblogging is refreshed.
As shown in Fig. 2 this method usage scenario is as illustrated, user holds mobile terminal device in LTE as user
Moved freely in base station and Wi-Fi coverages, terminal device is opened 4G and is connected with Wi-Fi network, and terminal will connect first
Wi-Fi network, user will check refreshing microblogging in region according to itself behavioural habits.
When user uses process for the first time, mobile terminal device will adopt ambient condition value where automatic data collection user
The state value collected is arrived locally, as shown in Figure 2 with setting form to store in database.Then, when data volume reaches specified quantity
During level, terminal device will be sent to specified mailbox automatically by lettergram mode.When the number that received server-side to user collects
After according to this, server specified location is arrived in storage, and data are fitted by service data processing routine.Data processing detailed process is as follows:
All state values being likely to occur are derived and recorded, and the matrix for setting each state value mutually to change.
According to the data being an actually-received, analysis calculates the number that adjacent two states value occurs, and recorded state and turn
Change in matrix.
The total degree that state value occurs in real data is counted, then respectively by state transition matrix, each state turns
The number divided by total degree changed, finally gives state transition probability matrix.
By emulation tool, by reward function of the probability matrix after processing to set as input value, MDP is established
Mathematical modeling, detailed process are as follows:
Resultant awards function R is set, resultant awards value matrix is set according to reward function.
Set in set of actions A and include refresh picture form corresponding to network signal level value, set of actions A is sub-divided into
4G and two kinds of network action set of Wi-Fi.Under 4G network connections, when signal strength scale value is 1, now network will be regarded as
Network can not be connected, because now needing a large amount of energy consumptions to download refreshes microblogging, microblogging can not be refreshed under the grade point.It is other
Under grade point, download pictures form is corresponded to from high to low as original image, high definition picture, thumbnail and without bitmap-format.And
Under Wi-Fi network connection, it is considered as network disconnection when signal strength scale value is not more than 2, picture format is that can not download refreshing
Microblogging.Network signal intensity grade point arranges from high to low, be 5,4,3 three kind of effective grade point, now correspond to respectively it is optimal its
Grade point corresponds to download pictures form from high to low is respectively original image, high definition picture and thumbnail pictures for it.
State transition probability matrix and reward value matrix are brought into emulation tool, obtain related optimal policy decision table
The optimal policy decision table that emulation tool is obtained, run by data preparation program and export the lattice that Mix tests APP and can identified
Formula, decision table after arrangement is then sent to application with mail he, user now freely moves in 4G and Wi-Fi coverages
It is dynamic, refresh microblogging according to itself use habit, overall flow figure is as shown in figure 3, as follows using now specifically used process:
When user refreshes microblogging, mobile terminal preferential attachment Wi-Fi network, user collects ambient condition value automatically.
, i.e., will when signal strength scale value is not more than 2 if Wi-Fi network signal strength scale value is less than given threshold
Using Mix network switching patterns, 4G networks are automatically switched to.
If Wi-Fi network is not up to switching threshold, according to optimal policy decision table, optimal picture form is selected, is downloaded
Refresh microblogging.
It is optimal according to optimal policy decision table, selection if network does not reach disconnection threshold value if being switched to 4G networks
Picture format, download and refresh microblogging.If reaching network connection threshold value, inform that user can not refresh.
Claims (3)
1. a kind of mobile platform energy consumption optimization method based on Markovian decision process, it is characterised in that comprise the following steps:
1)Using the Android application of the api interface independent development provided based on Sina weibo open platform, Mix test APP, should answer
With possess the login of Sina weibo mobile client end subscriber, refreshing information, the work(such as release news, browse information and log off
Energy;
2)Ambient condition value where Mix test APP automatic data collections users, ambient condition value include network signal, described network
Signal is 4G or Wi-Fi network, and 4G or Wi-Fi network strength grade value, time interval value, mobile phone residual electric quantity, user brush
New microblogging frequency values, meanwhile, Wi-Fi network disconnection threshold value is set according to network signal intensity grade point, mobile terminal is cut automatically
Change 4G and Wi-Fi communication networks;Markovian decision process is the set of a four-tuple state, including (S,A,P(),R()), step 2)The ambient condition value collected, the state that as finite state set S is included, when user is whole using movement
During end, then mobile terminal preferential attachment Wi-Fi network sets network switching threshold value, the method turns into Mix network switching moulds
Formula, the LTE signal strength scale value dividing modes that network signal level value is increased income defined in API according to Android, each network
Level of signal is divided into 5 grades, and respectively 5,4,3,2,1, when Wi-Fi network signal strength scale value is not more than 2, user can not
Complete to refresh microblogging action, now reach network switching threshold value, using automatically switching to 4G communication networks;
3)Countinuous time MDP mathematical modeling is established, according to step 2)The ambient condition value collected is empty as the state of MDP models
Between, the dynamic transfer probability of MDP models is then established, the motion space of MDP models is finally established, mesh is used as using optimal award value
Scalar functions, MDP model change procedures are emulated, obtain optimal policy decision table;
4)MDP models are emulated using MATLAB, optimal policy decision-making is obtained using all state sets as input value, solving model
Table;
5)In actual use, Mix tests APP according to ambient condition value and step 4)Optimal policy decision table, selection
Optimal communication network and optimal picture form, complete to refresh microblogging action.
2. a kind of mobile platform energy consumption optimization method based on Markovian decision process according to claim 1, it is special
Sign is, described step 1)Middle Mix tests APP, comprising user's login, refreshing information, releases news, browses information and moves back
Go out to log in, asked during actual refreshing information, it is necessary to be sent by network connection to server end, according to returning to URL
Location is downloaded related content, and wherein content includes text information, pictorial information, in optimization method, passes through dynamic select figure
Piece form, according to corresponding picture format URL addresses, optimal picture form is selected, downloads and refreshes microblogging.
3. a kind of mobile platform energy consumption optimization method based on Markovian decision process according to claim 1, it is special
Sign is, described step 3)By step 2)The ambient condition value collected arranges generating probability setP, and set of related actions
CloseA, set of rewardsRAs MDP mode input values, refresh picture lattice corresponding to network signal level value are included in set of actions A
Formula, set of actions A is sub-divided into 4G and two kinds of network action set of Wi-Fi, under 4G network connections, when signal strength scale value
For 1 when, now network will be regarded as that network can not be connected, because now needing a large amount of energy consumptions to download refreshes microbloggings, the grade
It can not refresh microblogging under value, under other grade points, correspond to download pictures form from high to low as original image, high definition picture, contracting
Sketch map and without bitmap-format, and under Wi-Fi network connection, it is considered as network disconnection when signal strength scale value is not more than 2, nothing
Method download refresh microblogging, other grade points from high to low correspond to download pictures form be respectively original image, high definition picture and
Thumbnail pictures.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710962155.7A CN107734579B (en) | 2017-10-16 | 2017-10-16 | Mobile platform energy consumption optimization method based on Markov decision process |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710962155.7A CN107734579B (en) | 2017-10-16 | 2017-10-16 | Mobile platform energy consumption optimization method based on Markov decision process |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107734579A true CN107734579A (en) | 2018-02-23 |
CN107734579B CN107734579B (en) | 2021-02-05 |
Family
ID=61211696
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710962155.7A Active CN107734579B (en) | 2017-10-16 | 2017-10-16 | Mobile platform energy consumption optimization method based on Markov decision process |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107734579B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108509551A (en) * | 2018-03-19 | 2018-09-07 | 西北大学 | A kind of micro blog network key user digging system under the environment based on Spark and method |
CN108966330A (en) * | 2018-09-21 | 2018-12-07 | 西北大学 | A kind of mobile terminal music player dynamic regulation energy consumption optimization method based on Q-learning |
CN109041187A (en) * | 2018-09-21 | 2018-12-18 | 西北大学 | A kind of mobile platform energy consumption optimization method based on network aware PCA-SVM blending algorithm |
CN109511277A (en) * | 2018-08-01 | 2019-03-22 | 东莞理工学院 | The cooperative method and system of multimode Continuous action space |
CN110598906A (en) * | 2019-08-15 | 2019-12-20 | 珠海米枣智能科技有限公司 | Method and system for controlling energy consumption of superstores in real time based on deep reinforcement learning |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105956968A (en) * | 2016-05-26 | 2016-09-21 | 程欧亚 | Artificial intelligent college entrance examination voluntary reporting system and method |
CN106376023A (en) * | 2016-10-10 | 2017-02-01 | 西北大学 | Data downloading method based on context awareness and system thereof |
CN106447201A (en) * | 2016-09-29 | 2017-02-22 | 国网山东省电力公司电力科学研究院 | Optimal maintenance decision method of power transmission and transformation equipment based on Markov decision process |
-
2017
- 2017-10-16 CN CN201710962155.7A patent/CN107734579B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105956968A (en) * | 2016-05-26 | 2016-09-21 | 程欧亚 | Artificial intelligent college entrance examination voluntary reporting system and method |
CN106447201A (en) * | 2016-09-29 | 2017-02-22 | 国网山东省电力公司电力科学研究院 | Optimal maintenance decision method of power transmission and transformation equipment based on Markov decision process |
CN106376023A (en) * | 2016-10-10 | 2017-02-01 | 西北大学 | Data downloading method based on context awareness and system thereof |
Non-Patent Citations (1)
Title |
---|
TANG LUNG CHEUNG 等: "Marcov decision process(MDP) framework for optimizing software on mobile phones", 《ACM & IEEE INTERNATIONAL CONFERENCE ON EMBEDDED SOFTWARE,EMSOFT 2009》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108509551A (en) * | 2018-03-19 | 2018-09-07 | 西北大学 | A kind of micro blog network key user digging system under the environment based on Spark and method |
CN108509551B (en) * | 2018-03-19 | 2022-03-01 | 西北大学 | Microblog network key user mining system and method based on Spark environment |
CN109511277A (en) * | 2018-08-01 | 2019-03-22 | 东莞理工学院 | The cooperative method and system of multimode Continuous action space |
WO2020024172A1 (en) * | 2018-08-01 | 2020-02-06 | 东莞理工学院 | Collaborative type method and system of multistate continuous action space |
CN109511277B (en) * | 2018-08-01 | 2023-06-13 | 东莞理工学院 | Cooperative method and system for multi-state continuous action space |
CN108966330A (en) * | 2018-09-21 | 2018-12-07 | 西北大学 | A kind of mobile terminal music player dynamic regulation energy consumption optimization method based on Q-learning |
CN109041187A (en) * | 2018-09-21 | 2018-12-18 | 西北大学 | A kind of mobile platform energy consumption optimization method based on network aware PCA-SVM blending algorithm |
CN110598906A (en) * | 2019-08-15 | 2019-12-20 | 珠海米枣智能科技有限公司 | Method and system for controlling energy consumption of superstores in real time based on deep reinforcement learning |
CN110598906B (en) * | 2019-08-15 | 2024-02-13 | 珠海米枣智能科技有限公司 | Large-scale commercial field energy consumption real-time control method and system based on deep reinforcement learning |
Also Published As
Publication number | Publication date |
---|---|
CN107734579B (en) | 2021-02-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107734579A (en) | A kind of mobile platform energy consumption optimization method based on Markovian decision process | |
CN103365663B (en) | It is used for developing terminal and the method for intention | |
CN103902630B (en) | Handle method, terminal and the system of message | |
CN104331404B (en) | A kind of user's behavior prediction method and apparatus based on user mobile phone Internet data | |
CN103945430B (en) | A kind of mobile terminal style recommends method and device | |
CN103259690B (en) | Information processing method and client | |
CN103501374A (en) | Telephone book sequencing method and device as well as terminal | |
CN103024066B (en) | Method for automatically pushing terminal themes | |
CN107105453B (en) | Cut-in method is selected based on the heterogeneous network of analytic hierarchy process (AHP) and evolutionary game theory | |
Wang et al. | Mobile traffic offloading by exploiting social network services and leveraging opportunistic device-to-device sharing | |
CN110263053A (en) | A kind of server obtaining mobile terminal portrait label based on mobile terminal data | |
CN104850966A (en) | Seat management method and system based on NFC | |
CN107911547A (en) | Interactive system, the method for interface layout | |
CN107135252A (en) | The user intent event recommendation method and apparatus of track are used based on mobile terminal | |
CN109710351A (en) | The display methods and device of notification message | |
CN106649743A (en) | Method and system for storing and sharing creative idea classified brain library resources | |
CN104753998A (en) | Terminal, social application server and information sharing method | |
CN104111926B (en) | The generation method and device of the concern recommendation list of address list | |
CN107402973A (en) | Picture upload, loading method, upper transmission terminal, server and storage medium | |
CN102750388A (en) | Network system based on digital resources and use method of network system | |
CN108965901A (en) | It is a kind of for the display methods and electronic equipment of platform to be broadcast live | |
CN107291543A (en) | Applied program processing method, device, storage medium and terminal | |
CN107493328A (en) | A kind of Cooperative caching method of feature based fusion | |
Siebra et al. | Towards a green mobile development and certification | |
CN109041187A (en) | A kind of mobile platform energy consumption optimization method based on network aware PCA-SVM blending algorithm |
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 |