CN104113903A - Interactive cognitive learning based downlink power adjusting method and device - Google Patents
Interactive cognitive learning based downlink power adjusting method and device Download PDFInfo
- Publication number
- CN104113903A CN104113903A CN201410373841.7A CN201410373841A CN104113903A CN 104113903 A CN104113903 A CN 104113903A CN 201410373841 A CN201410373841 A CN 201410373841A CN 104113903 A CN104113903 A CN 104113903A
- Authority
- CN
- China
- Prior art keywords
- case
- power
- learning
- information
- interactive
- 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
Landscapes
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses an interactive cognitive learning based downlink power adjusting method and device and relates to the communication technology. Femtocells which are served as intelligent agents having learning capabilities, set improvement of networking performance to be a learning target and perform network optimization due to adjustment of power distribution of a resource block. The femtocells can perform interactive learning according to the communication similarity and the specialized knowledge to improve the learning efficiency and meanwhile save long-time energy consumption caused by learning experience accumulation through an air interface individually except self-learning development. Network optimization through adjustment of power distribution of the resource bock can reduce interference from the hybrid networking and improve the handling capacity. Femtocell gateways are served as case libraries, the femtocells can perform interactive learning to improve the learning efficiency and meanwhile save the long-time energy consumption caused by learning experience accumulation through the air interface except self-learning.
Description
Technical field
The present invention relates to the communication technology, especially relate to a kind of descending power method of adjustment and device based on interactive cognitive learning.
Background technology
Document < < Femtocells:technologies and deployment > > (Zhang, J., & De la Roche, G. (2010) .Femtocells:technologies and deployment (pp.1-13) .New York:Wiley.), investigation shows, in traditional cellular cell, have the data service of 2/3 voice service and 90% to occur in indoor, it is especially important that the covering of indoor wireless Access Network and capacity seem.And macro base station price is very expensive, and choosing of site, the installation of equipment, debugging and maintenance all will expend a large amount of manpowers, financial resources, material resources and time, by increasing macro base station, solve the network planning problem that this problem can increase the spending of operator and bring large amount of complex.Under such overall background, the emerging equipment such as Home eNodeB arises at the historic moment.
Home eNodeB claims again femtocell base station, it is a kind of low-power wireless access point, work in mandate frequency range, by user's existing broadband (as DSL, wire cable, optical fiber) access, long-rangely by dedicated gateway, realize the connection from IP network to mobile core network.It has the features such as with low cost, easy for installation, automatic configuration, plug and play, and with the same standard in other mobile base station of operator, same frequency range, so the mobile terminal such as mobile phone can be general.Its transmitting power and Wi-Fi equipment are more or less the same, and are about 10～100mW, and covering radius is 10～50m, support several active users, and for improving neatly, the wireless signal of indoor and outdoor covers and increase network capacity.But, in the mixed networking of macro base station and Home eNodeB, inevitably exist and disturb.On the one hand, Home eNodeB, as a kind of commodity, is freely bought and installed by user, causes operator not know its position distribution situation; On the other hand, along with popularizing of Home eNodeB, it quantitatively will surmount the scale of traditional macro base station comprehensively, and this will affect the performance of whole net further.From the angle of power, if do not carry out interference management, descendingly may there is following negative condition:
(1) signal gets too small of Home eNodeB and being covered by macrocellular signal is flooded, and causes the overlay area of Home eNodeB very little, poor signal quality;
(2) if Home eNodeB signal is excessive with respect to macro base station signal, may cause macrocellular user to lose and enter a blind area (dead band) being connected of macro base station, be that macrocellular user had not both accessed the authority of the Home eNodeB under closed mode, can not be connected to macro base station again; Also may make macrocellular user be subject to Home eNodeB interference excessive, performance reduces.
Traditional LTE Home eNodeB descending power method of adjustment mainly contains following several:
The fix power allocation of mentioning in document < < Improved Decentralized Q-learning Algorithm for Interference Reduction in LTE-Femtocells > > (Serrano A M G.Self-organized Femtocells:a Time Difference Learning Approach[J] .2012.).
Document < < Interference control for LTE Rel-9HeNB cells > > (Jeju, Interference control for LTE Rel-9HeNB cells[S], 3GPP TSG RAN WG4, R4-094245, November 9th-13th, 2009) middle intelligent power control (SPC) method proposing.
Document < < Cognition and docition in OFDMA-based femtocell networks > > (Galindo-Serrano A, Giupponi L, Dohler M.Cognition and docition in OFDMA-based femtocell networks[C] //Global Telecommunications Conference (GLOBECOM 2010), 2010IEEE.IEEE, 2010:1-6.) in the iteration water-filling algorithm mentioned.
These methods have following deficiency:
(1) first, the minimum time-frequency unit that definition can be distributed to user in LTE is Resource Block, and most of conventional method is only adjusted maximum total transmitter power (dBm), there is no the power adjustment of consideration based on Resource Block;
(2) secondly, in distributed management, support that the power regulating method based on Resource Block is seldom considered the interactive learning between Home eNodeB, the raising self performance of only take is sole purpose.
Summary of the invention
The object of the present invention is to provide a kind of interference producing for macrocellular user in order to reduce Home eNodeB, and accelerate descending power method of adjustment and the device based on interactive cognitive learning of this process implementation.
The described descending power method of adjustment based on interactive cognitive learning, comprises two processes:
1. based on interactive cognitive descending power adjustment, comprising:
(1) each Home eNodeB is safeguarded a descending power information table, and described descending power information table be take Resource Block as least unit, for determining the transmitting power of each Resource Block, all data of descending power information table is carried out to initialization;
(2) disturbed condition that the configuration of periodically perception current transmit power of Home eNodeB causes, then upgrades corresponding data in descending power information table according to the information of perception and corresponding update rule;
(3) distribution method of the descending power information table after use renewal and regulation determines the transmitting power configuration in next cycle;
(4) repeat step (2) and (3), final goal is to make each transmitting power of distributing according to perception information best;
2. the descending power adjustment based on interactive learning, comprising:
(1) Home eNodeB periodically reports the terminal equipment with aggregation feature using information such as the power information table of self maintained, similarity parameter, professional knowledge degree as a case, described terminal equipment adopts femto gateway, femto gateway is a life span of each case setting, case surpasses after life span, automatically deletes;
(2) Home eNodeB carries out Active Learning, and femto gateway carries out active professor, and two kinds of modes are carried out simultaneously, for descending power is adjusted;
Described Active Learning refers to: for the opening time, be less than the Home eNodeB of threshold value, initiatively to femto gateway, send study application, and report similarity parameter and professional knowledge degree; Gateway is according to the similarity of each case in the similarity calculation of parameter reporting and case library, case using similarity more than threshold value is as alternative case, the professional knowledge degree of more alternative case again, get soprano as selecting eventually case, the corresponding form of this case is sent to the Home eNodeB that sends study application, and this case is being deleted from case library, base station is used this form data to carry out based on after interactive cognitive power adjustment, if professional knowledge degree improves, to gateway, send confirmation signal and cover original form, finishing learning process; Otherwise gateway selects the case that in current alternative case, professional knowledge degree is the highest to select case as whole, sends to the Home eNodeB that sends study application to learn, until alternative case is empty, gateway sends feedback information to base station, stops learning process.
Described active professor refers to: for the up-to-date case reporting, femto gateway calculates the similarity of each case in this case and case library, selects the highest case of similarity, relatively reports case and the professional knowledge degree of selecting case; If differ in threshold value, stop professor's process; Otherwise the form of the larger case of professional knowledge degree is sent to Home eNodeB corresponding to that case that professional knowledge degree is less, to carry out based on interactive cognitive power adjustment, if professional knowledge degree improves after carrying out, to gateway, send confirmation signal and cover original form, finishing professor's process; Otherwise, retain original form, finish professor's process.This process does not need all cases that newly report to carry out.
The execution that circulates in practical operation of the above descending power method of adjustment interactive cognitive and study.
The described descending power adjusting device based on interactive cognitive learning, comprises three modular units in base station side: information storage module, information sending/receiving module, message processing module;
The major function of described information storage module is: the power information table that 1) storage is safeguarded based on interactive cognitive power adjustment, and message processing module will be used power information table, the information storage module of restoring after processing; 2) temporarily store the case information obtaining in the power adjustment based on interactive learning the form that determines current use;
The major function of described information sending/receiving module is: 1) periodically receive the various information by adjacent area macrocellular user feedback, and reception value is reported to message processing module, for interfere information, if there is not adjacent area macrocellular user's interference or disturb minimum (being less than certain predetermined threshold value), can ignore, the regulation value of reporting is 0 artificially; If there is a plurality of adjacent area macrocellular users' interference, therefrom choose and disturb maximum conduct value of reporting, final process result is met all macrocellular users' interference is down to below threshold value; 2) be responsible for sending self case and other relevant information to femto gateway;
The major function of described message processing module is: 1) in adjusting based on interactive cognitive power,, with processing storage information and reporting information periodically, specifically refer to updating form lattice information and determine Resource Block transmitting power with information receiving module; 2), in the power based on interactive learning is adjusted, self maintained form, similarity parameter, professional knowledge degree and other information needed are formed to case and give information sending/receiving module.
The present invention carries out the network optimization by the power division of adjustresources piece, can reduce the interference of mixed networking, improves throughput.Except self learns, using femto gateway as case library, Home eNodeB can, according to similarity and professional knowledge degree, come interactive learning to improve learning efficiency, to save the long-time energy loss by air interface accumulation learning experience simultaneously.
Accompanying drawing explanation
Fig. 1 is the system architecture diagram of LTE macro base station and Home eNodeB mixed networking in example of the present invention.
Fig. 2 is the power adjustment apparatus functions of modules graph of a relation of the interactive cognitive learning of Home eNodeB.
Fig. 3 is that Home eNodeB is adjusted flow chart based on interactive cognitive power.
Fig. 4 is the Active Learning flow chart of Home eNodeB based on interactive learning.
What Fig. 5 was femto gateway based on interactive learning initiatively teaches flow chart.
Embodiment
Below in conjunction with accompanying drawing, describe the present invention.
It is example that the invention process scene be take LTE macro base station and Home eNodeB mixed networking, and LTE macro base station and Home eNodeB mixed networking system architecture are as shown in Figure 1.
The present invention is the descending power method of adjustment based on interactive cognitive learning, and the main process of the method is: 1, based on interactive cognitive descending power adjustment; 2, the descending power adjustment based on interactive learning; Process 1,2 execution that circulates in practical operation, and based on 1, information storage module; 2, sending/receiving module; 3, message processing module is realized, and functions of modules relation as shown in Figure 2.
The major function of information storage module is: the power information table that 1) storage is safeguarded based on interactive cognitive power adjustment, and message processing module will be used power information table, the information storage module of restoring after processing; 2) temporarily store the case information obtaining in the power adjustment based on interactive learning the form that determines current use.
The major function of sending/receiving module is: 1) periodically receive the various information by adjacent area macrocellular user feedback, and reception value is reported to message processing module, for interfere information, if there is not adjacent area macrocellular user's interference or disturb minimum (being less than certain predetermined threshold value), can ignore, the regulation value of reporting is 0 artificially; If there is a plurality of adjacent area macrocellular users' interference, therefrom choose and disturb maximum conduct value of reporting, final process result is met all macrocellular users' interference is down to below threshold value; 2) be responsible for sending self case and other relevant information to femto gateway.
The major function of message processing module is: 1) in adjusting based on interactive cognitive power,, with processing storage information and reporting information periodically, specifically refer to updating form lattice information and determine Resource Block transmitting power with information receiving module; 2), in the power based on interactive learning is adjusted, self maintained form, similarity parameter, professional knowledge degree and other information needed are formed to case and give information sending/receiving module.
The invention provides an embodiment, the Home eNodeB resource distribution adoption rate fair algorithm in this example is given different users by resource block assignments independently; Descending power adjustment based on interactive cognitive in this example be take Q study and is described as example.
Intelligent body in Q study, state, action, return is defined as follows:
Intelligent body: Home eNodeB, base station number i={1,2 ..., N}, the Resource Block r={1 of each base station, 2 ..., R}.
State s:s on r Resource Block of i Home eNodeB
i,r={ I
i,r, Pow
i, wherein, I
i,rfor Signal to Interference plus Noise Ratio designator.
SINR_I
i,rfor the adjacent area macrocellular user that the reports Signal to Interference plus Noise Ratio to r Resource Block of i Home eNodeB, from adjacent macro base station obtain the concrete grammar of counterpart terminal user profile can referenced patent CN 102045795A < < method from target BS obtaining information and device > > described in realize, SINR
thfor the interference threshold of regulation, x is a constant (unit is dB), for scope, finely tunes;
Pow
ibe i Home eNodeB actual emission power, Pow
thfor the specified maximum transmission power of Home eNodeB, y is a constant (unit is dBm), for scope fine setting, in the middle of actual conditions, if distribute power sum to surpass maximum transmission power, the proportional distribution of power that adopts maximum transmission power to distribute by Q study, but in Q value table, the state of record is constant, and this situation can be tending towards 0 gradually along with the process probability of convergence.
I
i,rand Pow
iquantified precision can adjust according to actual conditions.
Action a: the power grade a that can distribute to each Resource Block
i, r∈ { a
1, a
2..., a
m, unit is dBm.
Return value re on r Resource Block of i Home eNodeB:
In addition, in this example, all Signal to Interference plus Noise Ratio (SINR) also can be used CQI (CQI) to replace.
Referring to Fig. 3, the descending power adjustment performing step that the present invention is based on interactive cognition is as follows:
(1) Home eNodeB is safeguarded a Three-Dimensional Q-Value table, and Q value table, Resource Block status s and action a are carried out to initialization.Wherein, Q value table the first dimension is state s, and the second dimension is action a, and the third dimension is Resource Block r;
(2) Home eNodeB periodically obtains the Signal to Interference plus Noise Ratio (SINR) by adjacent area macrocellular user feedback;
(3) according to the SINR value receiving and corresponding state quantizing rule, obtain the quantized value s' of current state, and calculate return value re,
(4) adopt following rule to upgrade Q value table:
Wherein, γ ∈ (0,1) is constant discount factor, and it has embodied the importance of the relatively current return of future returns, and lf ∈ [0,1) be the constant study factor, it is for controlling the speed of convergence;
(5), to each Resource Block, according to current Q value table and state s', adopt e-greedy algorithm to choose and carry out this action a' within this cycle.Concrete grammar is: e is the less constant between 0-1, produces a random number p between 0-1, if p<e chooses an action at random; Otherwise, in selection mode s', the maximum action of corresponding Q value;
(6) more new state and action s=s', a=a', and go to step (2).
Similarity parameter in power adjustment based on interactive learning in this example, professional knowledge degree is defined as follows:
Similarity parameter s im:sim
i,r={ en
i,r, act_en
i,r, en wherein
i,rbe the environment similarity on the Resource Block r of corresponding Home eNodeB i, use SINR here
i,rrepresent, but be not limited in other embodiments, use SINR
i,rrepresent; Act_en
i,raction on the Resource Block r of the corresponding Home eNodeB i similarity that affects on environment,
a
i,rfor the action in the upper Q study of corresponding Resource Block r of respective base station i, subscript t and t-1 represent respectively current period and previous cycle.
Professional knowledge degree exp:exp
i, r=θ
1η
i+ θ
2con
i, rθ wherein
1, θ
2for weights, θ
1+ θ
2=1; η
ibe the efficiency utilance of i Home eNodeB,
c is Home eNodeB throughput, and P is actual transmission power, and w is utilized bandwidth; con
i,rfor the degree of convergence of the Q value table on the Resource Block r of corresponding Home eNodeB i,
q
i,rfor the Q value table on the Resource Block r of corresponding Home eNodeB i, subscript t and t-1 represent respectively current period and previous cycle.
Referring to Figure 4 and 5, the descending power adjustment performing step that the present invention is based on interactive learning is as follows:
(1) Home eNodeB is periodically that a case reports corresponding femto gateway by S1 interface by information combination such as Q value table, similarity parameter, professional knowledge degree, deposits in case library, and case surpasses after life span, automatically from case library, deletes.Suppose that time monocycle based on interactive cognitive power adjustment is T, Home eNodeB report cycle is 1000T, and the life span of each case is 1200T, deletes the case of life span below set point (as 500T) when case library is filled with;
(2) Home eNodeB sends study application to gateway, reports similarity parameter s im
1with professional knowledge degree exp
1; Gateway is according to sim
1the similarity δ of each case in calculating and case library, computing formula is as follows:
υ wherein
ifor weights, | p
i1-p
i2| represent the absolute value of the difference of the corresponding similarity parameter of two cases, N is the quantity of similarity parameter, gets 2 in this example;
(3) similarity is greater than to threshold value d
thcorresponding case is as alternative case.If without alternative case, gateway sends respective feedback information to base station, stop learning process, otherwise, choose the highest case of exp value in alternative case, corresponding Q value table is sent to base station, and case is deleted from alternative case, base station is used this Q value table to carry out power adjustment, after 100T, detect professional knowledge degree and whether improve, if improve, cover original Q value table, to gateway, send confirmation signal, gateway discharges alternative case, finishes learning process; If improve, again do not send study application, gateway is selected the highest case of exp value in current alternative case, sends to base station to learn in corresponding Q value table, until alternative case is empty, if still, without the case satisfying condition, gateway sends feedback information to base station, stop learning process.
(4) choose the up-to-date case c1 reporting, gateway calculates the similarity of each case in this case and case library, and the same step of method (2) is described.Select the highest case c2 of corresponding similarity, relatively the professional knowledge degree of c1 and c2.If | exp
1-exp
2|≤exp
th, stop professor's process; If exp
1-exp
2> exp
th, the Q value table of c1 being sent to the Home eNodeB that c2 is corresponding, the base station that c2 is corresponding is used this Q value table to carry out power adjustment, if professional knowledge degree gets a promotion, to gateway, send confirmation signal and cover original Q value table, otherwise still using original Q value table, finishing professor's process; If exp
2-exp
1> exp
th, the Q value table of c2 being sent to the Home eNodeB that c1 is corresponding, the base station that c1 is corresponding is used this Q value table to carry out power adjustment, if professional knowledge degree gets a promotion, to gateway, send confirmation signal and cover original Q value table, otherwise still using original Q value table, finishing professor's process.Exp
ththreshold value for the difference of professional knowledge degree.
Be appreciated that a kind of descending power method of adjustment based on interactive cognition provided by the invention, comprise the following steps:
Step 101: periodically receive by adjacent area macrocellular user feedback based on Resource Block information;
Step 102: according to the described Signal to Interference plus Noise Ratio of determining single Resource Block based on Resource Block information;
Step 103: upgrade power information table according to described Signal to Interference plus Noise Ratio, and determine the transmitting power of Resource Block according to power information table;
Step 104: give corresponding Home eNodeB by definite Resource Block transmit power allocations.
Preferably, definite Resource Block transmit power allocations, to Home eNodeB corresponding to adjacent area macrocellular user, is specifically comprised the following steps, definite Resource Block transmitting power is sent to Home eNodeB corresponding to adjacent area macrocellular user; Wherein, described power information table at least comprises state dimension parameter s, action dimension parameter a, Resource Block dimension parameter r, wherein, state dimension parameter s is: the set of the corresponding transmitting power of the Signal to Interference plus Noise Ratio based on Home eNodeB user resources piece and this Home eNodeB user; A is for distributing to the power grade of each Resource Block for action dimension parameter.
In the embodiment of the present invention, according to described Signal to Interference plus Noise Ratio, upgrade power information table and specifically comprise the following steps in addition:
Wherein, Q (s, a, r) is the current power information table configuration rule based on state dimension parameter s, action dimension parameter a, Resource Block dimension parameter r; Lf is the constant study factor, for controlling the speed of convergence, lf ∈ [0,1); γ is constant discount factor, γ ∈ (0,1); S' is the quantized value of last next state dimension parameter, and a ' is the quantized value of front one-off dimension parameter.Be appreciated that the renewal power information table in the embodiment of the present invention can also comprise other update rules, as used the parameter of different range, or add other Effects of Factors.
A kind of descending power method of adjustment based on interactive learning provided by the invention, comprises the following steps:
Step 201: Home eNodeB is combined as a case by relevant information, deposits in case library, and case is deleted after surpassing life span automatically;
Step 202: Home eNodeB sends study application to gateway, reports after relevant information; Case library calculates case similarity in itself and case library;
Step 203: choose applicable case according to similarity and professional knowledge degree, the corresponding form of this case is sent to the Home eNodeB that sends study application, after base station is used this form data to carry out to adjust based on interactive cognitive power, according to the variation of professional knowledge degree, whether determine continue studying process;
Step 204: for the up-to-date case reporting, femto gateway is chosen relatively professional knowledge degree of similar cases, if differ in threshold value, stops professor's process; Otherwise the form of the larger case of professional knowledge degree is sent to Home eNodeB corresponding to that case that professional knowledge degree is less, to carry out based on interactive cognitive power adjustment, if professional knowledge degree improves after carrying out, to gateway, send confirmation signal and cover original form; Otherwise, retain original form, finish professor's process.
By such scheme, in the embodiment of the present invention, the minimum time-frequency unit that can distribute to user is Resource Block, and then, by the power adjustment based on Resource Block, make the interactive learning between Home eNodeB, improved the self performance of Home eNodeB.
One of ordinary skill in the art will appreciate that all or part of flow process realizing in above-described embodiment method, to complete by related hardwares such as computer program instructions, described program can be stored in a computer-readable recording medium, when this program is carried out, can comprise as the flow process of the embodiment of above-mentioned each side method.Wherein, described storage medium can be magnetic disc, CD, read-only store-memory body (Read-Only Memory, ROM) or random store-memory body (Random Access Memory, RAM) etc.
As can be seen here, the invention provides descending power method of adjustment and device, and provide plurality of optional adaptation scheme, above embodiment unrestricted technical scheme described in the invention, therefore,, although this specification is illustrated the present invention with reference to each above-mentioned embodiment, the related personnel of this area is to be understood that, all do not depart from technical scheme and the improvement thereof of the spirit and scope of the present invention, and it all should be encompassed in the middle of claim scope of the present invention.
Claims (10)
1. the descending power method of adjustment based on interactive cognitive learning, is characterized in that comprising following process:
Process 1. is based on interactive cognitive descending power adjustment;
The descending power adjustment of process 2. based on interactive learning.
2. the descending power method of adjustment based on interactive cognitive learning as claimed in claim 1, is characterized in that in process 1, described based on interactive cognitive descending power adjustment, comprising:
(1) each Home eNodeB is safeguarded a descending power information table, and described descending power information table be take Resource Block as least unit, for determining the transmitting power of each Resource Block, all data of descending power information table is carried out to initialization;
(2) disturbed condition that the configuration of periodically perception current transmit power of Home eNodeB causes, then upgrades corresponding data in descending power information table according to the information of perception and corresponding update rule;
(3) distribution method of the descending power information table after use renewal and regulation determines the transmitting power configuration in next cycle;
(4) repeat step (2) and (3), final goal is to make each transmitting power of distributing according to perception information best.
3. the descending power method of adjustment based on interactive cognitive learning as claimed in claim 1, is characterized in that in process 2, and the described descending power adjustment based on interactive learning, comprising:
(1) Home eNodeB periodically reports the terminal equipment with aggregation feature using the power information table of self maintained, similarity parameter, professional knowledge degree as a case, described terminal equipment adopts femto gateway, femto gateway is a life span of each case setting, case surpasses after life span, automatically deletes;
(2) Home eNodeB carries out Active Learning, and femto gateway carries out active professor, and two kinds of modes are carried out simultaneously, for descending power is adjusted.
4. the descending power method of adjustment based on interactive cognitive learning as claimed in claim 3, it is characterized in that in step (2), described Active Learning refers to: the Home eNodeB that is less than threshold value for the opening time, initiatively to femto gateway, send study application, and report similarity parameter and professional knowledge degree; Gateway is according to the similarity of each case in the similarity calculation of parameter reporting and case library, case using similarity more than threshold value is as alternative case, the professional knowledge degree of more alternative case again, get soprano as selecting eventually case, the corresponding form of this case is sent to the Home eNodeB that sends study application, and this case is being deleted from case library, base station is used this form data to carry out based on after interactive cognitive power adjustment, if professional knowledge degree improves, to gateway, send confirmation signal and cover original form, finishing learning process; Otherwise gateway selects the case that in current alternative case, professional knowledge degree is the highest to select case as whole, sends to the Home eNodeB that sends study application to learn, until alternative case is empty, gateway sends feedback information to base station, stops learning process.
5. the descending power method of adjustment based on interactive cognitive learning as claimed in claim 3, it is characterized in that in step (2), described active professor refers to: for the up-to-date case reporting, femto gateway calculates the similarity of each case in this case and case library, select the highest case of similarity, relatively report case and the professional knowledge degree of selecting case; If differ in threshold value, stop professor's process; Otherwise the form of the larger case of professional knowledge degree is sent to Home eNodeB corresponding to that case that professional knowledge degree is less, to carry out based on interactive cognitive power adjustment, if professional knowledge degree improves after carrying out, to gateway, send confirmation signal and cover original form, finishing professor's process; Otherwise, retain original form, finish professor's process, this process does not need all cases that newly report to carry out.
6. the descending power method of adjustment based on interactive cognitive learning as claimed in claim 1, the descending power that it is characterized in that described interactive cognitive descending power adjustment and interactive learning is adjusted at circulation in practical operation and carries out.
7. the descending power adjusting device based on interactive cognitive learning, is characterized in that comprising three modular units in base station side: information storage module, information sending/receiving module, message processing module.
8. the descending power adjusting device based on interactive cognitive learning as claimed in claim 7, is characterized in that:
The major function of described information storage module is: the power information table that 1) storage is safeguarded based on interactive cognitive power adjustment, and message processing module will be used power information table, the information storage module of restoring after processing; 2) temporarily store the case information obtaining in the power adjustment based on interactive learning the form that determines current use;
The major function of described information sending/receiving module is: 1) periodically receive the various information by adjacent area macrocellular user feedback, and reception value is reported to message processing module, for interfere information, if do not exist adjacent area macrocellular user's interference or interference to be less than predetermined threshold value, can ignore, the regulation value of reporting is 0 artificially; If there is a plurality of adjacent area macrocellular users' interference, therefrom choose and disturb maximum conduct value of reporting, final process result is met all macrocellular users' interference is down to below threshold value; 2) be responsible for sending self case and other relevant information to femto gateway;
The major function of described message processing module is: 1) in adjusting based on interactive cognitive power,, with processing storage information and reporting information periodically, specifically refer to updating form lattice information and determine Resource Block transmitting power with information receiving module; 2), in the power based on interactive learning is adjusted, self maintained form, similarity parameter, professional knowledge degree and other information needed are formed to case and give information sending/receiving module.
9. a descending power method of adjustment, is characterized in that, comprises the following steps:
(1) periodically receive by adjacent area macrocellular user feedback based on Resource Block information;
(2) according to the described Signal to Interference plus Noise Ratio of determining single Resource Block based on Resource Block information;
(3) according to described Signal to Interference plus Noise Ratio, upgrade power information table, and according to power information table, determine the transmitting power of Resource Block;
(4) by definite Resource Block transmit power allocations, give corresponding Home eNodeB user.
10. method as claimed in claim 9, is characterized in that: by definite Resource Block transmit power allocations, to adjacent area macrocellular user, concrete steps are as follows: definite Resource Block transmitting power is sent to adjacent area macrocellular user; Wherein, described power information table at least comprises state dimension parameter s, action dimension parameter a, Resource Block dimension parameter r, wherein, state dimension parameter s is: the set of the corresponding transmitting power of the Signal to Interference plus Noise Ratio based on Home eNodeB user resources piece and this Home eNodeB user; A is for distributing to the power grade of each Resource Block for action dimension parameter;
The concrete steps of upgrading power information table according to described Signal to Interference plus Noise Ratio are as follows:
Wherein, Q (s, a, r) is the current power information table configuration rule based on state dimension parameter s, action dimension parameter a, Resource Block dimension parameter r; Lf is the constant study factor, for controlling the speed of convergence, lf ∈ [0,1); γ is constant discount factor, γ ∈ (0,1); S' is the quantized value of last next state dimension parameter, and a ' is the quantized value of front one-off dimension parameter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410373841.7A CN104113903B (en) | 2014-07-31 | 2014-07-31 | Descending power method of adjustment and device based on interactive cognitive study |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410373841.7A CN104113903B (en) | 2014-07-31 | 2014-07-31 | Descending power method of adjustment and device based on interactive cognitive study |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104113903A true CN104113903A (en) | 2014-10-22 |
| CN104113903B CN104113903B (en) | 2018-01-16 |
Family
ID=51710499
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410373841.7A Active CN104113903B (en) | 2014-07-31 | 2014-07-31 | Descending power method of adjustment and device based on interactive cognitive study |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104113903B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106358308A (en) * | 2015-07-14 | 2017-01-25 | 北京化工大学 | Resource allocation method for reinforcement learning in ultra-dense network |
| CN108833423A (en) * | 2018-06-25 | 2018-11-16 | 厦门大学 | A kind of multipath confidential information communication means based on intensified learning |
| CN110191489A (en) * | 2019-05-17 | 2019-08-30 | 北京科技大学 | Resource allocation methods and device based on intensified learning in a kind of super-intensive network |
| CN110546028A (en) * | 2017-02-03 | 2019-12-06 | 宾利汽车有限公司 | Regenerative braking system |
| CN113810986A (en) * | 2020-06-12 | 2021-12-17 | 深圳市万普拉斯科技有限公司 | Method, device, terminal and storage medium for dynamically adjusting transmission power |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100118844A1 (en) * | 2008-11-12 | 2010-05-13 | At&T Intellectual Property I, Lp | Dynamic lightweight remote management of hybrid femtocell gateways |
| CN102811443A (en) * | 2012-07-27 | 2012-12-05 | 南京邮电大学 | Interference management method based on spectrum allocation and power control in family base station system |
-
2014
- 2014-07-31 CN CN201410373841.7A patent/CN104113903B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100118844A1 (en) * | 2008-11-12 | 2010-05-13 | At&T Intellectual Property I, Lp | Dynamic lightweight remote management of hybrid femtocell gateways |
| CN102811443A (en) * | 2012-07-27 | 2012-12-05 | 南京邮电大学 | Interference management method based on spectrum allocation and power control in family base station system |
Non-Patent Citations (4)
| Title |
|---|
| A. GALINDO-SERRANO AND L. GIUPPONI: "Distributed Q-learning for interference control in OFDMA-based femtocell networks", 《PROCEEDINGS OF THE 71ST IEEE VEHICULAR TECHNOLOGY CONFERENCE》 * |
| H. SAAD, A. MOHAMED AND T. ELBATT: "A Cooperative Q-learning Approach for Online Power Allocation in Femtocell Networks", 《2013 IEEE 78TH VEHICULAR TECHNOLOGY CONFERENCE(VTC FALL)》 * |
| 季祥芬: "基于强化学习的家庭基站干扰协调算法研究", 《中国优秀硕士论文电子期刊网》 * |
| 宁海芹: "基于机器学习的Femtocell系统功率控制算法研究及优化", 《中国优秀硕士论文电子期刊网》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106358308A (en) * | 2015-07-14 | 2017-01-25 | 北京化工大学 | Resource allocation method for reinforcement learning in ultra-dense network |
| CN110546028A (en) * | 2017-02-03 | 2019-12-06 | 宾利汽车有限公司 | Regenerative braking system |
| US12030469B2 (en) | 2017-02-03 | 2024-07-09 | Bentley Motors Limited | Regenerative braking system |
| CN108833423A (en) * | 2018-06-25 | 2018-11-16 | 厦门大学 | A kind of multipath confidential information communication means based on intensified learning |
| CN108833423B (en) * | 2018-06-25 | 2020-07-31 | 厦门大学 | Multi-path secret information communication method based on reinforcement learning |
| CN110191489A (en) * | 2019-05-17 | 2019-08-30 | 北京科技大学 | Resource allocation methods and device based on intensified learning in a kind of super-intensive network |
| CN113810986A (en) * | 2020-06-12 | 2021-12-17 | 深圳市万普拉斯科技有限公司 | Method, device, terminal and storage medium for dynamically adjusting transmission power |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104113903B (en) | 2018-01-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10055682B2 (en) | Self-optimizing deployment cascade control scheme and device based on TDMA for indoor small cell in interference environments | |
| Galindo-Serrano et al. | Distributed Q-learning for interference control in OFDMA-based femtocell networks | |
| CN113597799B (en) | Apparatus, method and computer readable medium for adjusting a beamforming profile | |
| Gao et al. | Q-learning-based power control for LTE enterprise femtocell networks | |
| CN103856947B (en) | The disturbance coordination method that a kind of combined channel selects and power controls | |
| CN104113903A (en) | Interactive cognitive learning based downlink power adjusting method and device | |
| CN103781118A (en) | Heterogeneous wireless network access control and resource distribution joint method based on multiple services | |
| CN103648102B (en) | Heterogeneous network interference coordination method based on dynamic zone expansion and power control | |
| CN103260192A (en) | Home base station and macro base station heterogeneous double-layer network power distribution method based on double utilities | |
| Chandrasekhar et al. | Distributed power control in femtocell-underlay cellular networks | |
| Al-Zahrani et al. | A game theory approach for inter-cell interference management in OFDM networks | |
| Yan et al. | Self-imitation learning-based inter-cell interference coordination in autonomous HetNets | |
| CN102905302A (en) | Method for controlling uplink interference in hybrid network | |
| Zheng et al. | Distributed power optimization for spectrum-sharing femtocell networks: A fictitious game approach | |
| Abdelnasser et al. | Joint subchannel and power allocation in two-tier OFDMA HetNets with clustered femtocells | |
| Çakir et al. | Power adjustment based interference management in dense heterogeneous femtocell networks | |
| Yang et al. | Green heterogeneous networks: a cognitive radio idea | |
| CN105764068A (en) | Small base station capacity and coverage optimization method based on tabu search | |
| Galiotto et al. | Effect of LOS/NLOS propagation on area spectral efficiency and energy efficiency of small-cells | |
| US9055539B2 (en) | Method and a device for adjusting the transmission power of signals transferred by plural mobile terminals | |
| Sallakh et al. | Multi-parameter q-learning for downlink inter-cell interference coordination in lte son | |
| EP2760237A1 (en) | Network Node and Method to adjust user association in HetNets | |
| Vlacheas et al. | Operator-governed SON coordination in downlink LTE networks | |
| TWI624168B (en) | An intelligent deployment cascade control device based on an fdd-ofdma indoor small cell in multi-user and interference environments | |
| Li et al. | User scheduling and slicing resource allocation in industrial Internet of Things |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210901 Address after: Siming District of Xiamen city in Fujian Province, 361000 South Siming Road No. 422 Patentee after: XIAMEN University Patentee after: Jingxin Network System Co.,Ltd. Address before: Xiamen City, Fujian Province, 361005 South Siming Road No. 422 Patentee before: XIAMEN University Patentee before: COMBA TELECOM SYSTEMS (GUANGZHOU) Ltd. |