CN114189899A - User equipment selection method based on random aggregation beam forming - Google Patents
User equipment selection method based on random aggregation beam forming Download PDFInfo
- Publication number
- CN114189899A CN114189899A CN202111503756.4A CN202111503756A CN114189899A CN 114189899 A CN114189899 A CN 114189899A CN 202111503756 A CN202111503756 A CN 202111503756A CN 114189899 A CN114189899 A CN 114189899A
- Authority
- CN
- China
- Prior art keywords
- user equipment
- aggregation
- random
- central node
- tmp
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/06—Testing, supervising or monitoring using simulated traffic
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B7/00—Radio transmission systems, i.e. using radiation field
- H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
- H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
- H04B7/06—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station
- H04B7/0613—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission
- H04B7/0615—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal
- H04B7/0617—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal for beam forming
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B7/00—Radio transmission systems, i.e. using radiation field
- H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
- H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
- H04B7/08—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the receiving station
- H04B7/0837—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the receiving station using pre-detection combining
- H04B7/0842—Weighted combining
- H04B7/086—Weighted combining using weights depending on external parameters, e.g. direction of arrival [DOA], predetermined weights or beamforming
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/142—Network analysis or design using statistical or mathematical methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- 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)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Mathematical Physics (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Mathematical Analysis (AREA)
- Medical Informatics (AREA)
- Algebra (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Probability & Statistics with Applications (AREA)
- Mobile Radio Communication Systems (AREA)
- Radio Transmission System (AREA)
Abstract
The invention discloses a user equipment selection method based on random aggregation beamforming, which adopts an air calculation technology to improve the communication efficiency when a federal learning aggregation model is adopted, and the generated aggregation error has influence on the final learning performance. The goal of the problem is to achieve both the goals of minimizing aggregation errors and maximizing the number of user equipments by selecting user equipments and designing an aggregate beamforming vector. Then, a user equipment selection method based on random aggregation beamforming is proposed. When the number of the user equipment is increased, compared with the original algorithm, the algorithm of the invention can obtain lower aggregation error and select more user equipment, thereby obtaining better learning performance.
Description
Technical Field
The invention belongs to the field of wireless communication, and particularly relates to a user equipment selection method based on random aggregation beam forming.
Background
With the development of wireless communication and the breakthrough of artificial intelligence technology, the more and more intelligent services are undertaken by the edge of the wireless communication network. Usually, people will use traditional centralized training method to accomplish these tasks, but this method will bring high delay and privacy disclosure problems. In recent years, federal learning has attracted increasing researchers' attention as an emerging distributed learning approach. The learning mode does not need to transmit sensitive data when a global model is trained, so privacy disclosure is avoided, and transmission delay is reduced.
However, since the central node and the ue need to communicate frequently, and spectrum resources are very precious for an edge intelligent system, how to improve the communication efficiency becomes a bottleneck for the federal learning development. The traditional communication computation separation mechanism can only perform computation after decoding the signals, so that the efficiency is not high, and therefore, researchers introduce an emerging air computation technology into the framework of federal learning. The technology carries out analog modulation on signals, utilizes the waveform superposition principle, can complete calculation while transmitting, and has proved that under the same conditions, higher communication efficiency can be obtained than a digital modulation scheme based on a communication calculation separation mechanism.
However, due to the fading characteristics of the channel and the influence of noise, the over-the-air computation technique may also bring aggregation errors, and if the aggregation errors are too large, the model training may be negatively affected. On the other hand, selecting more user equipment to participate in model aggregation proves that the learning efficiency can be improved, and the model convergence is accelerated. Therefore, researchers have designed a joint optimization scheme of user equipment selection and aggregation beamforming vectors, which aims to reduce aggregation errors and select more user equipments at the same time, but this method is computationally complex and difficult to implement in practical applications. To solve the problem, a user equipment selection method based on random aggregation beamforming is provided, and the method has low complexity, can be realized in practical application and can ensure performance.
Disclosure of Invention
The invention aims to provide two user equipment selection methods based on random aggregation beamforming, which respectively aim at minimizing mean square error and maximizing the number of selected equipment users.
In order to solve the technical problems, the specific technical scheme of the invention is as follows:
a user equipment selection method based on random aggregation beamforming comprises the following steps:
step 1.1, in an edge intelligent system, K edge user devices equipped with an antenna and a central node equipped with N antennas, wherein N is less than K; the set of all user equipments is denoted asEach user equipment k has its own local data setThe global data set is formed by combining the local data setsThe user devices together implement an intelligent application;
step 1.2, adopting a federal learning distributed learning framework;
the minimum mean square error algorithm based on the random aggregation beamforming comprises the following steps:
step A, determining the number of user equipment to be selectedA random number of samples NmEach cycle generates an auxiliary variable tmp, tmpmaxIs a variable that records the maximum tmp cycled through to the current round, and initializes tmp max0; from 1 to NmContinuously circulating the following three steps B to D, namely executing N in totalmSecondly;
step B, from complex Gaussian distributionM is obtained by sampling at random oncerWhere I is an N × N dimensional identity matrix, and for mrPerform normalization mr=mr/‖mr‖;
Step C, calculating equivalent channel power for each user equipment kThen, all equivalent channel powers are arranged in a descending order, and the S-th value is selected and recorded as tmp;
step D, if tmp > tmpmaxLet tmpmaxTmp, and the subset of user equipments participating in the update to be selected for the round is then determined asAnd m is mr;
E, after the circulation execution is finished, obtaining the required user equipment subset participating in the updateAnd a beamforming vector m for the center node;
the maximized user equipment selection algorithm based on random aggregation beamforming comprises the following steps:
step a, firstly determining a threshold value for limiting MSENumber of random samplings Nm(ii) a And initializing the selectable maximum subset of user equipments to an empty set, i.e.From 1 to NmContinuously circulating the four steps from step b to step e, namely circulating NmSecondly;
step b, from complex Gaussian distributionM is obtained by sampling at random oncerWhere I is an N × N dimensional identity matrix, and for mrNormalization is carried out, i.e. mr=mr/‖mr‖;
Step f, obtaining the selectable maximum user equipment subset after the execution of the circulation process is finishedAnd an optimal beamforming vector m for the center node.
Further, the step 1.2 of adopting a federal learning distributed learning framework includes the following steps:
step 1.2.1, selecting a subset among all user equipmentsTo participate in the training of the round;
step 1.2.2, the selected user equipment updates the local model parameters for E times according to the local data set of the user equipment, and then uploads the parameters to the central node;
and step 1.2.3, the central node updates the global model according to the received parameters.
Further, in step 1.2.2, the specific update formula of the local model parameters of the kth ue in the nth round is:
wherein the gradient is accumulatedIs shown asWhile μiIs the learning rate of step i;is an average loss function, whereinIs in the sampleThe loss value on the jth data of (1);
let each user equipment have a local data set of the same size, then in the nth pass the global model parameters of the central node can be obtained by:
further, the specific steps of step 2 are: in the nth round, the symbol matrix transmitted by user equipment k is defined asAnd normalized by unit variance, i.e.Wherein I represents an identity matrix;and gkIs abbreviated as sk,wkAnd gk(ii) a Representing the selected set of user devices asThe ideal signal obtained by the central node is represented as:
skafter analog modulation, the transmission coefficient bkPerforming precoding, bkAmplitude of (2)Represents the transmission power of the user equipment k, whose phase can be used to help the central node to align the received signal; these signals are then superimposed in the air and multiplied by the beamforming vector of the central node; finally, amplifying by a scale factor eta; due to fading and noise in the wireless channel, the signal y actually received by the central node is represented as:
wherein h iskIs a channel vector from the user equipment k to the central node, subject to a complex Gaussian distribution of unity power, i.e.The channels are subject to independent equal distribution; the vector n being additive white Gaussian noise, i.e.mHRepresents the conjugate transpose of the beamforming vector, and therefore the aggregate error produced by the over-the-air computation technique is represented as:
order toWherein a iskIs the degree of deviation of the kth ue signal, the mean squared error is expressed as:
according to equation (6), the following conditions are ensured for eliminating fading related errors:
finally, the mean square error is written as follows:
further, the optimization problem of minimizing the mean square error specifically includes:
making the number of user equipments selected per round fixedWhereinIs a subset of user equipmentThe number of the elements in the optimization problem is determined by the scaling factor eta and the transmission coefficient bkSubset of user equipmentsAnd a beamforming vector m; since these variables are independent of the noise n, the optimization goal need only be reduced to η | m |)2The whole optimization problem can be expressed as:
transmission coefficient bkThe design is as follows:
the scale factor η is designed as:
where P is the maximum allowed transmit power of each ue, and equation (11) is replaced by equation (9a), since m exists in the numerator and denominator, the optimization problem is equivalent to:
s.t.‖m‖=1 (12)
further, the optimization problem of maximizing the number of user equipments specifically includes: setting a MSE threshold asThe objective of the optimization problem is to maximize the number of ues under this constraint; we redefine one for each user equipmentWherein m | 1, the final MSE is defined asThe transmission coefficient b is expressed as in the equations (10) and (11)kAnd the scale factor eta is taken as an optimal value, and the whole optimization problem is expressed as follows:
‖m‖=1 (13c)。
the two user equipment selection methods based on the random aggregation beam forming have the following advantages that:
1. the MSE minimizing algorithm based on the random aggregation beamforming adopts a random sampling mode to replace iterative computation to approach an optimal solution, so that the complexity of the algorithm is greatly reduced, the method can be realized in an actual application scene, and the performance is also ensured.
2. The algorithm for maximizing the number of the user equipment based on the random aggregation beamforming can select the equipment participating in updating as much as possible under the condition of ensuring that the MSE does not exceed a certain threshold value, so that the diversity of the equipment is increased, and the prediction capability of the model is improved.
Drawings
FIG. 1 is a schematic representation of a federated learning system model of the present invention;
FIG. 2 is a schematic diagram of pseudo code of the mean square error minimization algorithm based on random aggregation beamforming according to the present invention;
FIG. 3 is a pseudo code diagram of a UE number maximization algorithm based on random aggregation beamforming according to the present invention;
FIG. 4(a) shows an algorithm, a DC algorithm and l of the present invention1+ MSE result comparison of SDR algorithm;
FIG. 4(b) shows different random sampling times N according to the present inventionmA schematic diagram of the influence on the MSE result of the algorithm of the invention;
FIG. 5(a) shows the algorithm, DC algorithm and l of the present invention for different total numbers of user equipments1A comparison schematic diagram when the total number of the user equipment selected by the + SDR algorithm is 50;
FIG. 5(b) shows the algorithm, DC algorithm and l of the present invention for different total numbers of user equipments1A comparison schematic diagram when the total number of the user equipment selected by the + SDR algorithm is 100;
FIG. 5(c) shows the algorithm, DC algorithm and l of the present invention for different total numbers of user equipments1A comparison schematic diagram when the total number of the user equipment selected by the + SDR algorithm is 150;
FIG. 6(a) is a graph showing the effect of mean square error on MNIST10 data set on test accuracy;
FIG. 6(b) is a graph showing the effect of mean square error on CIFAR10 data set on test accuracy;
fig. 7(a) is a schematic diagram of the effect of user equipment count on the MNIST10 data set on test accuracy;
fig. 7(b) is a diagram illustrating the effect of the number of user equipments on the accuracy of the test on the CIFAR10 data set.
Detailed Description
For better understanding of the purpose, structure and function of the present invention, a method for selecting a ue based on random aggregation beamforming according to the present invention is described in further detail below with reference to the accompanying drawings.
The invention specifically comprises the following steps:
Step 1.1, the system model is as shown in fig. 1, in an edge intelligent system, there are K edge user equipments equipped with one antenna and a center node equipped with N antennas, where N is much smaller than K. The set of all user equipments is denoted asEach user equipment k has its own local data setThe global data set is composed of the local data setsAre combined to formThese user devices together implement an intelligent application. In general, the goal of a machine learning task is to find a set of model parameters woMake the loss functionAt a minimum, whereinIs a parameter of the model, whereinIs a D-dimensional real vector space.
Step 1.2, adopting a distributed learning framework of federal learning
Each round of federal learning can be divided into three phases: 1) selecting a subset of all user equipmentsTo participate in the training of the round; 2) the selected user equipment updates local model parameters for E times according to the local data set of the user equipment, and then uploads the parameters to the central node; 3) the central node updates the global model based on the received parameters.
The specific update formula of the local model parameters of the kth ue in the nth round is as follows:
wherein the gradient is accumulatedCan be expressed asWhileμiIs the learning rate of the ith step.Is an average loss function, whereinIs in the sampleThe loss value on the jth data of (1). Assuming that each user equipment has a local data set of the same size, then in the nth pass, the global model parameters of the central node can be obtained by:
and 2, training the distributed federal learning model constructed in the step 1, improving the communication efficiency by using an air computing technology, and determining an aggregation error generated by adopting the air computing technology.
In the nth round, the symbol matrix transmitted by user equipment k may be defined asAnd assuming normalization with unit variance, i.e.Where I is the identity matrix. For the sake of convenience of presentation,and gkThe d-th element of (a) can be abbreviated as sk,wkAnd gk. Representing the selected set of user devices asThe desired signal for the central node can be expressed as:
due to the use of over-the-air computing techniques, skAfter analog modulation, the transmission coefficient bkPerforming precoding, bkRepresents the transmission power of the user equipment k, whose phase can be used to help the central node align the received signal; these signals are then superimposed in the air and multiplied by the beamforming vector of the central node; finally, the amplification is carried out through a scaling factor eta. Due to fading and noise in the wireless channel, the signal y actually received by the central node can be expressed as:
wherein h iskIs a channel vector from the user equipment k to the central node, assumed to be a complex gaussian distribution with unity power, i.e.This also assumes that the channels follow independent co-distributions. The vector n being additive white Gaussian noise, i.e.mHIs a conjugate transpose of the beamforming vector. Thus, the aggregate error produced by the over-the-air computation technique can be expressed as:
wherein a iskIs the degree of deviation from the kth user equipment signal,is pair | e |2The mathematical expectation is obtained. First itemIs an error caused by fading, the second term | m |2σ2Is an error caused by noise.
To reduce MSE, we can eliminate errors due to fading while minimizing errors due to noise. Thus, although the resulting MSE is not optimal, if the error due to fading is dominant and the central node is equipped with multiple antennas, the resulting MSE is very close to the minimum. According to equation (6), the following conditions must be ensured for eliminating fading related errors:
finally, the MSE can be written as follows:
and 3, constructing two optimization problems according to the aggregation error determined in the step 2, wherein one optimization problem is the problem of minimizing the mean square error under the condition that the selection number of the user equipment is fixed, and the other optimization problem is the problem of maximizing the number of the selectable user equipment under the condition that the mean square error is ensured to be at a low level.
The minimization of the mean square error optimization problem specifically includes the following: to ensure the learning performance of the model, it is necessary to reduce the value of MSE as much as possible, assuming that the number of ues selected per round is fixedWhereinIs a subset of user equipmentNumber of elements in (1). The decision variables of the optimization problem then include the scaling factor η, the transmission coefficient bkSubset of user equipmentsAnd a beamforming vector m. Since these variables are independent of the noise n, the optimization goal need only be reduced to η | m |)2. The whole optimization problem can be expressed as:
according to the existing literature, the transmission coefficient bkCan be directly designed as follows:
then, the scale factor η can be designed as:
where P is the maximum allowed transmit power of each ue, and equation (11) is replaced by equation (9a), since m exists in the numerator and denominator, the optimization problem is equivalent to:
s.t.‖m‖=1 (12)
the optimization problem of maximizing the number of user equipments specifically includes the following: in a real-world situation, if the value of MSE is small, the aggregate error due to the over-the-air computation can be used as a regularization tool to prevent overfitting of the model. In case it is guaranteed that the value of MSE is maintained at a low level, as many user equipments as possible may be selected, which may improve the learning efficiency. Therefore, we set a threshold for MSE to be notedThe goal of the problem is to maximize the number of user equipments under this constraint. We redefine one for each user equipmentWherein m | 1, MSEkRepresents the mean square error of the kth user equipment, and the final MSE is defined asTransmission coefficient b is measured as abovekAnd the scale factor η takes an optimum value. The entire optimization problem can then be expressed as:
‖m‖=1 (13c)
random aggregation beamforming scheme:
the final learning performance of the Federal learning model established by the invention depends on the relevant hyper-parameters of machine learning, such as data quantity, data distribution, equipment computing capacity and the like, and relevant parameters under communication transmission, such as the number of user equipment participating in updatingTransmission coefficient bkA beamforming vector m for the center node, a scaling factor η, etc. The user equipments considered in this patent assume the same data volume, data distribution and computational power, but only differences in communication transmission related parameters exist. According to the prior art, we will refer to the transmission coefficient bkAnd the scale factor eta is designed to be an optimal value, and then the beam forming vector m of the central node and the user equipment selection scheme are carried outAnd (5) performing joint optimization.
For the problem of minimizing Mean Square Error (MSE), the algorithm for minimizing MSE based on random aggregation beamforming specifically includes the following steps, and the pseudo code of the algorithm is shown in fig. 2:
(1) determining number of user equipments per round selectionA random number of samples NmAnd initializing two auxiliary variables, tmp max0. From 1 to NmConstantly circulate below(2) To (4) three steps, i.e. a total of NmNext, the process is carried out.
(2) From complex Gaussian distributionM is obtained by sampling at random oncerWhere I is an N identity matrix. And to mrPerform normalization mr=mr/‖mr‖。
(3) For each user equipment k, calculating equivalent channel powerThen all the equivalent channel powers are sorted in descending order, and the S-th value is selected and recorded as tmp.
(4) If tmp > tmpmaxLet tmpmaxTmp, the subset of user equipment participating in the update to be selected for the round may then be determined asAnd m is mr。
(5) After the loop execution is completed, the required user equipment subset participating in the update can be obtainedAnd a beamforming vector m for the center node.
For the problem of maximizing the number of user equipments, the algorithm for maximizing the number of user equipments based on random aggregation beamforming specifically includes the following steps, and the pseudo code of the algorithm is shown in fig. 3:
(1) first, a threshold value limiting MSE is determinedA random number of samples Nm. And initializing the selectable maximum subset of user equipments to an empty set, i.e.From 1 to NmContinuously circulating the four steps (2) to (5),i.e. a common cycle NmNext, the process is carried out.
(2) From complex Gaussian distributionM is obtained by sampling at random oncerWhere I is an N identity matrix. And to mrNormalization is carried out, i.e. mr=mr/‖mr‖。
(6) After the loop process is executed, the selectable maximum user equipment subset can be obtainedAnd an optimal beamforming vector m for the center node.
To verify the performance advantage of the algorithm, an example flow of the invention is given below.
1. Experimental parameter settings
According to the research of practical situation, we set the maximum transmission power P allowed by each ue to 0 dB. In order to prove the effectiveness of the method, several most advanced algorithms are selected for comparison. For the problem of minimizing MSE, a ratioThe algorithm is an iterative user equipment selection scheme, the method optimizes a beam forming vector by using a convex difference function method, selects a user equipment subset by using the equivalent channel power, and continuously iterates until convergence; the second comparative algorithm is called random ue selection, which also uses the disparity function to optimize the beamforming vector, but the subset of ues is randomly selected. For the problem of maximizing the number of the user equipment selections, a comparative algorithm is a DC algorithm, sparsity is introduced by using a convex difference representation, and then an optimal beam forming vector is obtained; the second algorithm for comparison is l1+ SDR algorithm, use of such algorithmThe norm introduces sparsity and then a beam forming vector is obtained by using an SDR method.
2. The effect of the algorithm of the present invention in reducing mean square error
To fully illustrate the effectiveness of the algorithm of the present invention, we stipulate that under the experimental condition, the number of user equipments participating in updating per round S is 10, and the random sampling times N of the beamforming vector is providedm1, the total number of the user equipment in the system tests two cases of K1000 and K10000, and the number of the antennas of the central node is gradually increased from 2 to 12. The results of the tests are shown in fig. 4(a), and it can be seen that the present algorithm is significantly superior to the random ue selection scheme. In addition, although the MSE obtained by the algorithm is slightly higher than the iterative ue selection scheme, the computational complexity of the algorithm is significantly less than that of the iterative method, and the gap between them is smaller as the K value increases.
After that we change NmGradually increased from 1 to 100, and the test results are shown in fig. 4 (b). It can be seen from the figure that the larger the sampling times of the beamforming vector is, the smaller the value of MSE obtained by the algorithm is, and when N ismThe algorithm can even exceed the iterative user equipment selection scheme when the number N of the antennas of the central node is large.
3. The algorithm of the present invention increases the number of user equipments
In this experimental environment, we willIs limited to a value of [ -6, +6]Between dB, the number of antennas at the central node is 4. We consider three experimental scenarios in which the total number of user equipments K is 50, 100 and 150, respectively. The experimental results of different algorithms under the three scenes are shown in fig. 5, and it can be seen that under the same conditions, the algorithm can be obviously better than l1The + SDR algorithm selects more user equipments. And with NmAnd the performance of the algorithm is continuously improved due to the increase of K, and although the performance of the algorithm is comparable to that of the DC algorithm when K is 50, the performance of the algorithm is obviously better than that of the DC algorithm when K is 150.
4. Learning performance
We also tested how much the increasing number of ues can have an impact on the final machine learning task, in this experiment we selected two most classical machine learning datasets, MNIST10 and CIFAR10, respectively, and assumed that the datasets on each ue are not subject to independent and identical distributions. The MNIST10 data set contains ten-digit black and white handwritten digital pictures from 0 to 9, and for this data set we use a multi-layer perceptron neural network. CIFAR10 contains color pictures of class 10 objects and is therefore more difficult to train than MNIST10, so for this dataset we have adopted the ResNet18 neural network. To conveniently express the influence of aggregation errors on learning performance, we model the influence of aggregation errors as a model retransmission probability p, which is expressed as p-1-exp (-aMSE/σ)2) Wherein a is set to 1.
In the experiment, the total number of the user equipments is set to K as 100, 10 user equipments are selected to participate in the update in each round, and the number of the antennas of the central node is 4. MSE/sigma derived from the present algorithm, iterative and random UE selection schemes20.3221, 0.3410, and 1.3531, respectively. As shown in FIG. 6, the present algorithm and iterative user equipment selection scheme have comparable training results, while the random user equipment selection scheme is slightly lower than the first two, thereby resulting in a more or less robust algorithmReduced MSE/sigma may be found2The classification capability of the model can be improved to a certain extent.
Then we set the MSE threshold as MSE/σ2-2 dB. In this case, the present algorithm (N)m1000 case), DC algorithm and l1The maximum number of user equipments obtained by the + SDR algorithm is 30, 17 and 3, respectively. FIG. 7 shows the training effect of the three methods on MNIST10 and CIFAR10, which performs slightly better than the DC algorithm because the algorithm can select slightly more user equipments than the DC algorithm, and l1The + SDR algorithm performs far less than the first two.
It is to be understood that the present invention has been described with reference to certain embodiments, and that various changes in the features and embodiments, or equivalent substitutions may be made therein by those skilled in the art without departing from the spirit and scope of the invention. In addition, many modifications may be made to adapt a particular situation or material to the teachings of the invention without departing from the essential scope thereof. Therefore, it is intended that the invention not be limited to the particular embodiment disclosed, but that the invention will include all embodiments falling within the scope of the appended claims.
Claims (6)
1. A method for selecting user equipment based on Random Aggregation Beamforming (RABF), comprising the steps of:
step 1, constructing a federal learning system model;
step 1.1, in an edge intelligent system, K edge user devices equipped with an antenna and a central node equipped with N antennas, wherein N is less than K; the set of all user equipments is denoted asEach user equipment k has its own local data setThe global data set is composed of these local data setsAre combined to formThe user devices together implement an intelligent application;
step 1.2, adopting a federal learning distributed learning framework;
step 2, training the distributed federal learning model constructed in the step 1, improving the communication efficiency by using an air computing technology, and determining an aggregation error generated by adopting the air computing technology;
step 3, constructing two optimization problems according to the aggregation error determined in the step 2, wherein one optimization problem is the problem of minimizing the mean square error under the condition that the selection number of the user equipment is fixed, and the other optimization problem is the problem of maximizing the number of the selectable user equipment under the condition that the mean square error is ensured to be at a low level;
step 4, aiming at the two optimization problems constructed in the step 3, respectively providing a minimum mean square error algorithm based on random aggregation beam forming and a maximum user equipment selection algorithm based on random aggregation beam forming for solving;
the minimum mean square error algorithm based on the random aggregation beamforming comprises the following steps:
step A, determining the number of user equipment to be selectedA random number of samples NmEach cycle generates an auxiliary variable tmp, tmpmaxIs a variable that records the maximum tmp cycled through to the current round, and initializes tmpmax0; from 1 to NmContinuously circulating the following three steps B to D, namely executing N in totalmSecondly;
step B, from complex Gaussian distributionM is obtained by sampling at random oncerWhere I is an N × N dimensional identity matrix, and for mrPerform normalization mr=mr/||mr||;
Step C, calculating equivalent channel power for each user equipment kThen, all equivalent channel powers are arranged in a descending order, and the S-th value is selected and recorded as tmp;
step D, if tmp > tmpmaxLet tmpmaxTmp, and the subset of user equipments participating in the update to be selected for the round is then determined asAnd m is mr;
E, after the circulation execution is finished, obtaining the required user equipment subset participating in the updateAnd a beamforming vector m for the center node;
the maximized user equipment selection algorithm based on random aggregation beamforming comprises the following steps:
step a, firstly determining a threshold value for limiting MSENumber of random samplings Nm(ii) a And initializing the selectable maximum subset of user equipments to an empty set, i.e.From 1 to NmContinuously circulating the four steps from step b to step e, namely circulating NmSecondly;
step b, from complex Gaussian distributionM is obtained by sampling at random oncerWhere I is an N × N dimensional identity matrix, and for mrNormalization is carried out, i.e. mr=mr/||mr||;
2. The method of claim 1, wherein the step 1.2 of employing a federated learning distributed learning framework comprises the steps of:
step 1.2.1, selecting a subset among all user equipmentsTo participate in the training of the round;
step 1.2.2, the selected user equipment updates the local model parameters for E times according to the local data set of the user equipment, and then uploads the parameters to the central node;
and step 1.2.3, the central node updates the global model according to the received parameters.
3. The method of claim 1, wherein the specific update formula of the local model parameters of the kth ue in step 1.2.2 in the nth round is as follows:
wherein the gradient is accumulatedIs shown asWhile μiIs the learning rate of step i;is an average loss function, whereinIs in the sampleThe loss value on the jth data of (1);
let each user equipment have a local data set of the same size, then in the nth pass the global model parameters of the central node can be obtained by:
4. the method of claim 3, wherein the step 2 comprises the following steps: in the nth round, the symbol matrix transmitted by user equipment k is defined asAnd normalized by unit variance, i.e.Wherein I represents an identity matrix;and the d-th element of gk is abbreviated as sk,wkAnd gk(ii) a Representing the selected set of user devices asThe ideal signal obtained by the central node is represented as:
skafter analog modulation, the transmission coefficient bkPerforming precoding, bkRepresents the transmission power of the user equipment k, whose phase can be used to help the central node align the received signal; these signals are then superimposed in the air and multiplied by the beamforming vector of the central node; finally, amplifying by a scale factor eta; due to fading and noise in the wireless channel, the signal y actually received by the central node is represented as:
wherein h iskIs a channel vector from the user equipment k to the central node, subject to a complex Gaussian distribution of unity power, i.e.The channels are subject to independent equal distribution; the vector n being additive white Gaussian noise, i.e.mHRepresents the conjugate transpose of the beamforming vector, and therefore the aggregate error produced by the over-the-air computation technique is represented as:
order toWherein a iskIs the degree of deviation of the kth ue signal, the mean squared error is expressed as:
the first item ofIs an error caused by fading, the second term η m | | non-woven phosphor2σ2Is an error caused by noise;
according to equation (6), the following conditions are ensured for eliminating fading related errors:
finally, the mean square error is written as follows:
5. the method of claim 4, wherein the optimization problem of minimizing mean square error specifically comprises:
making the number of user equipments selected per round fixedWhereinIs a subset of user equipmentThe number of the elements in the optimization problem is determined by the scaling factor eta and the transmission coefficient bkSubset of user equipmentsAnd a beamforming vector m; since these variables are independent of the noise n, the optimization goal need only be reduced to η | | | m | | survival2The whole optimization problem can be expressed as:
transmission coefficient bkThe design is as follows:
the scale factor η is designed as:
where P is the maximum allowed transmit power of each ue, and equation (11) is replaced by equation (9a), since m exists in the numerator and denominator, the optimization problem is equivalent to:
s.t.||m||=1 (12b)
6. the method of claim 5, wherein the optimization problem of maximizing the number of ues specifically comprises: setting a MSE threshold asThe objective of the optimization problem is to maximize the number of ues under this constraint; we redefine one for each user equipmentWhere m 1, the final MSE is defined asThe transmission coefficient b is expressed as in the equations (10) and (11)kAnd the scale factor eta is taken as an optimal value, and the whole optimization problem is expressed as follows:
||m||=1 (13c)。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111503756.4A CN114189899B (en) | 2021-12-10 | 2021-12-10 | User equipment selection method based on random aggregation beam forming |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111503756.4A CN114189899B (en) | 2021-12-10 | 2021-12-10 | User equipment selection method based on random aggregation beam forming |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114189899A true CN114189899A (en) | 2022-03-15 |
CN114189899B CN114189899B (en) | 2023-03-31 |
Family
ID=80543012
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111503756.4A Active CN114189899B (en) | 2021-12-10 | 2021-12-10 | User equipment selection method based on random aggregation beam forming |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114189899B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116527173A (en) * | 2023-05-11 | 2023-08-01 | 山东大学 | Dynamic power control method and system for resisting multi-user parameter biased aggregation in federal learning |
WO2024060013A1 (en) * | 2022-09-20 | 2024-03-28 | 华为技术有限公司 | Data processing method and related device |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111340277A (en) * | 2020-02-19 | 2020-06-26 | 东南大学 | Popularity prediction model and method based on federal learning in fog wireless access network |
CN111626506A (en) * | 2020-05-27 | 2020-09-04 | 华北电力大学 | Regional photovoltaic power probability prediction method based on federal learning and cooperative regulation and control system thereof |
CN112464269A (en) * | 2020-12-14 | 2021-03-09 | 德清阿尔法创新研究院 | Data selection method in federated learning scene |
CN112911608A (en) * | 2021-01-14 | 2021-06-04 | 浙江大学 | Large-scale access method for edge-oriented intelligent network |
WO2021219080A1 (en) * | 2020-04-30 | 2021-11-04 | 深圳前海微众银行股份有限公司 | Federated learning model-based view display method, apparatus and device, and medium |
WO2021228404A1 (en) * | 2020-05-15 | 2021-11-18 | Huawei Technologies Co., Ltd. | Generating high-dimensional, high utility synthetic data |
-
2021
- 2021-12-10 CN CN202111503756.4A patent/CN114189899B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111340277A (en) * | 2020-02-19 | 2020-06-26 | 东南大学 | Popularity prediction model and method based on federal learning in fog wireless access network |
WO2021219080A1 (en) * | 2020-04-30 | 2021-11-04 | 深圳前海微众银行股份有限公司 | Federated learning model-based view display method, apparatus and device, and medium |
WO2021228404A1 (en) * | 2020-05-15 | 2021-11-18 | Huawei Technologies Co., Ltd. | Generating high-dimensional, high utility synthetic data |
CN111626506A (en) * | 2020-05-27 | 2020-09-04 | 华北电力大学 | Regional photovoltaic power probability prediction method based on federal learning and cooperative regulation and control system thereof |
CN112464269A (en) * | 2020-12-14 | 2021-03-09 | 德清阿尔法创新研究院 | Data selection method in federated learning scene |
CN112911608A (en) * | 2021-01-14 | 2021-06-04 | 浙江大学 | Large-scale access method for edge-oriented intelligent network |
Non-Patent Citations (5)
Title |
---|
CHUNMEI XU; SHENGHENG LIU; YONGMING HUANG; CHONGWEN HUANG; ZHAOY: "Over-the-air Learning Rate Optimization for Federated Learning", 《2021 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS WORKSHOPS (ICC WORKSHOPS) | 978-1-7281-9441-7/20/$31.00 ©2021 IEEE | DOI: 10.1109/ICCWORKSHOPS50388.2021.9473663》 * |
CHUNMEI XU; SHENGHENG LIU; ZHAOHUI YANG; YONGMING HUANG: "Learning Rate Optimization for Federated Learning Exploiting Over-the-Air Computation", 《IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, VOL. 39, NO. 12, DECEMBER 2021》 * |
SHUHAO XIA; JINGYANG ZHU; YUHAN YANG; YONG ZHOU; YUANMING SHI: "Fast Convergence Algorithm for Analog Federated Learning", 《ICC 2021 - IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS | 978-1-7281-7122-7/21/$31.00 ©2021 IEEE | DOI: 10.1109/ICC42927.2021.9500875》 * |
孙兵,刘艳,王田,彭绍亮,王国军,贾维嘉: "移动边缘网络中联邦学习效率优化综述", 《计算机研究与发展》 * |
朱光旭,李航: "面向高效通信边缘学习网络的", 《中兴通讯技术》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2024060013A1 (en) * | 2022-09-20 | 2024-03-28 | 华为技术有限公司 | Data processing method and related device |
CN116527173A (en) * | 2023-05-11 | 2023-08-01 | 山东大学 | Dynamic power control method and system for resisting multi-user parameter biased aggregation in federal learning |
CN116527173B (en) * | 2023-05-11 | 2023-11-24 | 山东大学 | Dynamic power control method and system for resisting multi-user parameter biased aggregation in federal learning |
US11956726B1 (en) | 2023-05-11 | 2024-04-09 | Shandong University | Dynamic power control method and system for resisting multi-user parameter biased aggregation in federated learning |
Also Published As
Publication number | Publication date |
---|---|
CN114189899B (en) | 2023-03-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109617584B (en) | MIMO system beam forming matrix design method based on deep learning | |
CN114189899B (en) | User equipment selection method based on random aggregation beam forming | |
CN106059972B (en) | A kind of Modulation Identification method under MIMO correlated channels based on machine learning algorithm | |
US8457240B2 (en) | Methods of selecting signal transmitting, receiving, and/or sensing devices with probabilistic evolutionary algorithms in information conveyance systems | |
Ozpoyraz et al. | Deep learning-aided 6G wireless networks: A comprehensive survey of revolutionary PHY architectures | |
CN110799995A (en) | Data recognizer training method, data recognizer training device, program, and training method | |
CN110113288B (en) | Design and demodulation method of OFDM demodulator based on machine learning | |
CN108052968B (en) | QSFLA-SVM perception intrusion detection method | |
WO2020253691A1 (en) | Deep learning signal detection method based on conjugate gradient descent method | |
Lin et al. | BsNet: A deep learning-based beam selection method for mmWave communications | |
Giri et al. | Eigenvalue-based cooperative spectrum sensing using kernel fuzzy c-means clustering | |
CN111224905B (en) | Multi-user detection method based on convolution residual error network in large-scale Internet of things | |
Sery et al. | COTAF: Convergent over-the-air federated learning | |
CN114204971B (en) | Iterative aggregate beam forming design and user equipment selection method | |
Li et al. | Deep learning for energy efficient beamforming in MU-MISO networks: A GAT-based approach | |
Mashhadi et al. | Fedrec: Federated learning of universal receivers over fading channels | |
CN113193896B (en) | Beam forming neural network decision method for maximizing sum of two receiving ends and rate | |
Chen et al. | Kernel-based nonlinear beamforming construction using orthogonal forward selection with the fisher ratio class separability measure | |
Xiao et al. | Joint sampling and reconstruction of time-varying signals over directed graphs | |
Zhang et al. | Blind source separation based on quantum slime mould algorithm in impulse noise | |
Zhang et al. | Federated multi-task learning with non-stationary heterogeneous data | |
CN113660016B (en) | EPA-based MIMO detection method, device, equipment and storage medium | |
CN113887806B (en) | Long-tail cascade popularity prediction model, training method and prediction method | |
Bobrov et al. | Machine learning methods for spectral efficiency prediction in massive mimo systems | |
Fantinato et al. | Multivariate PDF matching via kernel density estimation |
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 |