CN114501525A - Wireless network interruption detection method based on condition generation countermeasure network - Google Patents
Wireless network interruption detection method based on condition generation countermeasure network Download PDFInfo
- Publication number
- CN114501525A CN114501525A CN202210108134.XA CN202210108134A CN114501525A CN 114501525 A CN114501525 A CN 114501525A CN 202210108134 A CN202210108134 A CN 202210108134A CN 114501525 A CN114501525 A CN 114501525A
- Authority
- CN
- China
- Prior art keywords
- label
- sample
- samples
- data
- training
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 23
- 238000012549 training Methods 0.000 claims abstract description 46
- 238000013528 artificial neural network Methods 0.000 claims abstract description 27
- 230000003042 antagnostic effect Effects 0.000 claims abstract description 4
- 230000002194 synthesizing effect Effects 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 43
- 208000018910 keratinopathic ichthyosis Diseases 0.000 claims description 37
- 230000006870 function Effects 0.000 claims description 24
- 210000002569 neuron Anatomy 0.000 claims description 12
- 238000005070 sampling Methods 0.000 claims description 12
- 239000000126 substance Substances 0.000 claims description 11
- 210000004027 cell Anatomy 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 4
- 239000002131 composite material Substances 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 238000006386 neutralization reaction Methods 0.000 claims description 3
- 101150049349 setA gene Proteins 0.000 claims description 3
- 230000017105 transposition Effects 0.000 claims description 2
- 230000001960 triggered effect Effects 0.000 claims description 2
- 230000008569 process Effects 0.000 description 12
- 230000004913 activation Effects 0.000 description 5
- 238000007792 addition Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 101150072047 nei1 gene Proteins 0.000 description 2
- 101150008002 nei2 gene Proteins 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 206010007776 catatonia Diseases 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/08—Testing, supervising or monitoring using real traffic
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Complex Calculations (AREA)
Abstract
The invention discloses a wireless network interruption detection method based on a condition generation countermeasure network, which can accurately detect interruption under the conditions of unbalanced data sets and overlapping data classes and correctly classify different types of interruption, and specifically comprises the following steps: the first step is as follows: collecting network key performance indexes and forming a data set S; the second step is that: training the improved condition by using a data set S to generate an antagonistic network, wherein the antagonistic network consists of a generator G and a discriminator D, and both G and D are of a fully-connected neural network structure; the third step: collecting wireless networks T2KPI information reported by users in time, and the fourth step: synthesizing interrupt data by using the model obtained in the second step, and balancing a data set H; the fifth step: calculating the inter-class overlap index of each sample in the training set V after calibration; and a sixth step: training a human using training set V and inter-class overlap exponent set OAn Artificial Neural Network (ANN) for obtaining an interruption detection model; the seventh step: according to KPI information x reported by users in network in real time (x belongs to R)n) Interrupt detection is performed.
Description
Technical Field
The invention belongs to the technical field of network interruption detection in a wireless network, and particularly relates to a wireless network interruption detection method for generating a countermeasure network based on conditions.
Background
As one of key technologies of the wireless network self-healing technology, the interruption detection has important significance for improving the operation and maintenance efficiency of the wireless network and reducing the operation and maintenance cost. However, a wireless network outage is a small probability event, and the amount of outage characteristic data that can be collected is much smaller than normal data, resulting in a severe imbalance of data sets. Furthermore, when there is more than one type of interruption in the network, there is often more severe inter-class coincidence between the different types of interruption data. These factors all contribute to a reduction in the performance of wireless network outage detection. Therefore, how to improve the wireless network interruption detection performance under the conditions of data imbalance and data type overlap is an important problem.
Disclosure of Invention
The technical problem is as follows: in order to solve the problems, the invention discloses a wireless network interrupt detection method for generating a countermeasure network based on conditions, which can accurately detect interrupts under the conditions of unbalanced data sets and overlapping of data classes and correctly classify different types of interrupts.
The technical scheme is as follows: the invention relates to a wireless network interruption detection method based on condition generation countermeasure network, which comprises the following steps:
the first step is as follows: collecting key performance indicators KPI of a network, and forming a data set S;
the second step is that: training an improved condition by using a data set S to generate an antagonistic network CGAN-W, wherein the CGAN-W consists of a generator G and a discriminator D, and both G and D are of a fully-connected neural network structure;
the third step: collecting wireless networks T2KPI information reported by users in time and stored as data set Wherein N isHRepresents the total number of samples in H, element (H)w,yw),w=1,2,…,NH,hw∈RnAnd representing n-dimensional KPI information reported by the user, wherein the specific value of n can be determined by the operator according to the number of users and the network operation condition, and ywIs hwThe value of the label (1) is 0,1,2, and 3. After acquiring the data set H, entering a fourth step;
the fourth step: synthesizing interrupt data by using the CGAN-W model obtained in the second step, and balancing a data set H;
the fifth step: calculating the inter-class overlap index of each sample in the training set V after calibration;
and a sixth step: training an Artificial Neural Network (ANN) by using a training set V and an inter-class overlap exponent set O to obtain an interruption detection model;
the seventh step: according to KPI information x reported by users in network in real time (x belongs to R)n) Interrupt detection is performed.
Wherein the content of the first and second substances,
the first step is as follows: collecting key performance indicators KPIs of the network, and forming a data set S, which specifically comprises the following steps:
step 1.1, obtaining time T in wireless network1KPI information reported by internal users;
step 1.2, storing KPI information reported by users as a data setIn the form of (a); wherein N isSIs the number of the element in S, the ith element (x) in Si,yi),i=1,2…,NS,xi∈RnThe method comprises the steps that n-dimensional KPI information reported by a user at a certain time is represented, and the n-dimensional KPI information specifically comprises reference signal receiving power and signal-to-interference-and-noise ratio of a service cell and a neighbor cell; the value of n can be determined by an operator according to the number of users and the network operation condition; y isiIs xiThe label of (a), which represents the state of the base station serving the user, takes values of 0,1,2, 3; wherein, yi0 represents that the base station is in a normal state and has the strongest communication capability; y isi1 indicates that the base station is in a light interruption state, the communication capability is slightly reduced, and y i2 means that the base station is in a medium interruption state, and the communication capability is seriously reduced, which may cause a communication failure phenomenon; y isiWhen the base station completely loses communication capability, a large number of link connection failure events and user handover events are triggered to acquire S.
The second step is specifically as follows:
step 2.1, normalizing the data in the data set S according to the formula (1) to ensure that the final data is distributed between-1 and 1;
wherein the content of the first and second substances,represents the ith data sample xiThe value of d-dimension characteristic is 1,2, …, n, n represents sample xiA feature dimension of (a);representing the normalized sample, and turning to the step 2.2 after acquiring a normalized data set S;
step 2.2, dividing S into four subsets according to the sample labels in the data set S: s0,S1,S2,S3(ii) a Wherein the subset S0The middle element is labeled 0 or yiSample of 0, representing normal data; subset S1,S2,S3The middle elements are samples with labels of 1,2 and 3 respectively and represent interrupt type data respectively; statistical subset SkTotal number of middle samples, denoted NkK 1,2,3, a subset S containing interrupt data is obtained1,S2,S3Then, the step 2.3 is carried out;
step 2.3, D and G loss functions in the CGAN-W are defined as shown in the formula (2) and the formula (3) respectively:
wherein L isDRepresents a discriminator loss, LGRepresents a generator loss; m represents the total number of samples used for training CGAN-W; z is a radical ofjTable sampled l-dimensional random noise samples, z, following a standard normal distributionj∈Rl,j=1,2,…,m;xjN-dimensional KPI information x reported on behalf of userj∈Rn;yjRepresents a sample label; using interrupt subsets S1,S2,S3Training the CGAN-W model to enable the CGAN-W model to learn the interrupt-like data characteristics, so that the sample (x)j,yj)∈Sk,G(zj,yj) Is input (z)j,yj) The generator outputs layer neuron output, namely a synthesized sample; d (x)j,yj) Is input as (x)j,yj) Then, the discriminator outputs the neuron output; d (G (z)j,yj),yj) Is an input (G (z)j,yj),yj) Then, the discriminator outputs the layer neuron output; after defining the loss function, turning to step 2.4;
step 2.4, setting parameters required by subsequent model training: the method specifically comprises the following steps: a learning rate α; the truncation coefficient c is used for limiting the weight range after the updating of the discriminator; the batch size m is used for setting the number of samples sampled in each round of training; number of discriminant training times ndisSetting the training times of D when G is trained once; the maximum iteration number iteration of the model; number of iterations t, t of the discriminator<ndis(ii) a Number of model iterations iter, iter<iteration; wherein, alpha, c, m, ndisThe numerical value of iteration is determined by the operator; after the setting is finished, the step 2.5 is carried out;
step 2.5, randomly initializing a generator G and a discriminator D in the CGAN-W model to obtain a weight vector WG,WDAnd an offset vector bG,bD(ii) a The number of iterations iter of the initialized model is 0, and the judgment is madeThe iteration time t is 0; after the model initialization is finished, entering step 2.6;
step 2.6, from the interruption subset SkRandomly sampling m samples to obtain a real sample set { (x)1,y1),(x2,y2),…,(xm,ym) }; wherein, the set { x1,x2,…,xmKPI information of sample is represented as real ═ x1,x2,…,xm}; set { y1,y2,…,ymRepresents the corresponding sample label, denoted label ═ y1,y2,…,ym}; from the l-dimensional random noise z (z ∈ R) that follows a standard normal distributionl) M noise samples are sampled to form a set noise ═ z1,z2,…,zm}; the set noise and the label set label are set to { y ═ y1,y2,…,ymCombine, i.e. for each noise sample zjAdding a label yjObtaining the element (z)j,yj),yjE.g. label; go through the m noise samples sampled as this operation z1,z2,…,zmGet the set { (z)1,y1),(z2,y2),…,(zm,ym) }; after sampling is finished, turning to the step 2.7;
step 2.7, set { (z)1,y1),(z2,y2),…,(zm,ym) Input generator, output composite sample setWherein the content of the first and second substances,combining the sample set And step 2.6, the label set label obtained in step (y) ═ y1,y2,…,ymCombining, i.e. for each synthesized sampleAdding label yj,yjBelongs to label to obtain elementsGo through the m samples generated according to the operationObtaining a set of synthetic samplesAfter a synthetic sample set is obtained, the step 2.8 is carried out;
step 2.8, set the real samples { (x)1,y1),(x2,y2),…,(xm,ym) And the resultant sample setAs the input of the discriminator, the discriminator parameter W is updated by using the small batch stochastic gradient descent algorithm maximization formula (2)D,bD(ii) a Making the iteration time t of the discriminator t equal to t +1, and turning to step 2.9;
step 2.9, the updated weight coefficient W of the discriminatorDTruncating to a value between-c and c, i.e. | WDC is less than or equal to l, wherein c is a truncation coefficient, and the specific numerical value can be determined by an operator;
step 2.10, repeat steps 2.6, 2.7, 2.8, 2.9 until the number of times of arbiter iteration t>ndis(ii) a The procedure is shifted to step 2.11;
step 2.11, again from the i-dimensional random noise z (z ∈ R) that follows the standard normal distributionl) M noise samples are sampled to form a set noise '═ z'1,z′2,…,z′mAnd (3) comparing the set noise' with the label set label obtained in the step 2.6, wherein the label set label is { y ═ y }1,y2,…,ymCombine, i.e. z 'for each noise sample'jAdding a label yj,yjE.g. label to obtain element (z'j,yj) (ii) a Operating as such, the sampled m noise samples { z'1,z′2,…,z′mObtaining a set { (z'1,y1),(z′2,y2),…,(z′m,ym) And inputting the data into a generator; updating generator parameters W using a small batch stochastic gradient descent algorithm minimization equation (3)G,bGMaking the iteration number iter of the model equal to iter +1, and turning to step 2.12;
step 2.12, if iter>iteration, ending training, recording generator G, and discriminator D weight vector WG_opt,WD_optOffset vector bG_opt,bD_optEntering the step 2.13, otherwise turning to the step 2.5, and starting a new round of training;
step 2.13, repeating the steps 2.3-2.12 until three interrupt subsets S1,S2,S3The training is completed, and the CGAN-W model with the learned interrupt characteristics is obtained.
The fourth step is specifically as follows:
step 4.1, sampling n from the random noise z of dimension I obeying the standard normal distributiongenNoise samples forming a setWherein n isgenRepresents the number of minority samples expected to be synthesized, ngen>0; because the number of the added synthetic samples can influence the imbalance proportion of the finally obtained training set samples and further influence the classification effect, the optimal n is searched by a grid search methodgenA value; sampling label information to obtain a label set Only a few classes of data are synthesized for the purpose of balancing the data set, so the labels only take values in the set {1,2,3}, i.e., yr∈{1,2,3},r=1,2,…,ngen(ii) a Combining noise setsAnd a set of labelsI.e. for the noise sample zr(r=1,2,…,ngen) Adding a label yr(r=1,2,…,ngen),yr∈labelgenObtaining the element (z)r,yr) (ii) a Go through all samples according to the operation to obtain a setTurning to step 4.2;
step 4.2, assembleAn input generator according to W obtained in the second stepG_opt,bG_optCalculation Generator output, noteWherein the content of the first and second substances, will be assembledAnd tag collectionsCombining, i.e. for producing samplesAdding a label yr,yr∈labelgenTo obtain the elementTraversing all the generated samples according to the operation to obtain a generated data setAfter the generated data set U is obtained, turning to the step 4.3;
and 4.3, merging the generated data set U and the original data set H to obtain a calibrated training set V ═ U ═ H.
The fifth step is specifically as follows:
step 5.1, for each piece of KPI information V in Ve,e=1,2,…,NV,NVRepresents the total number of samples in V, Ve∈RnSelecting q pieces of KPI information closest to the KPI information, and forming a sample set Neigh ═ v1,v2,…,vq}; turning to step 5.2;
step 5.2, calculating a neutralization sample v in the set NeigheThe number of samples with the same label is recorded as NN, wherein NN is more than or equal to 0 and less than or equal to q, and the step 5.3 is carried out;
step 5.3, if NN>0, then sample veInter-class overlap index of (a)eNN/q; if NN is equal to 0, then sample veInter-class overlap index of (a)eβ; wherein the content of the first and second substances,for adjusting coefficients, for adjusting the samples veThe specific value of beta can be determined by an operator, and the inter-class overlap index o obtained by calculationeIncorporating the set O, i.e. O ═ O & { Oe};
And 5.4, repeating the step 5.1, the step 5.2 and the step 5.3 until all samples in the V are traversed.
The sixth step is specifically as follows:
step 6.1, determining an ANN loss function according to V and O, wherein the ANN loss function is shown as a formula (4)
Wherein N isVRepresents the total number of samples, o, in the training set Ve(e=1,2,…,NV) Representative sample veOf (2) inter-class overlap index, yegAs a function of sign, if sample veIs equal to g, then 1 is taken, otherwise 0, θ is takenjRepresents the weight matrix and bias vector corresponding to the jth neuron of the output layergRepresenting a weight matrix and a bias vector corresponding to the g-th neuron of the output layer, using superscript T to represent transposition, defining a loss function, and then turning to the step 6.2;
step 6.2, solving the minimum value of the formula (4) by using a gradient descent algorithm to obtain a weight vector W of the ANN networkANN_optAnd bias bANN_opt。
The seventh step is specifically as follows:
step 7.1, inputting x into the ANN model obtained in the sixth step according to WANN_optAnd bANN_optCalculating output layer output pred, pred is equal to R4;
Step 7.2, calculate the final prediction tagWhere argmax denotes the vector (pred)1,pred2,pred3,pred4) The subscript index corresponding to the medium maximum value is numbered from 0 ifAnd judging x as an interrupt sample and determining the specific interrupt type, otherwise, judging the x as a normal sample.
Has the advantages that: according to the interrupt detection method of the countermeasure network based on condition generation, under the condition that the problems of unbalance and inter-class overlap exist in the data set, a small number of classes of data are sampled through the CGAN-W model, meanwhile, the problems of data unbalance and inter-class overlap are solved through calculating inter-class overlap indexes and weighting training ANN, and the overall improvement of the interrupt detection performance is brought. Compared with the traditional classification method and the data up-sampling method, the method has the advantage that the interruption detection performance is obviously improved.
Drawings
FIG. 1 is a schematic diagram of a CGAN-W model.
FIG. 2 is a schematic diagram of the structure of ANN.
Detailed Description
The invention relates to a wireless network interruption detection method for generating a countermeasure network based on conditions, which is used for collecting two types of KPI information: the Reference Signal Received Power (RSRP) and signal to interference and noise ratio (SINR) are exemplified for explanation. An embodiment of the method is given below, the steps of which are all performed in a monitoring center for monitoring the operation of the network.
The first step is as follows: network KPIs are gathered and a data set S is formed. The method comprises the following steps:
(1) and (4) acquiring KPI information reported by users in 80s in the wireless network, and switching to the step (2).
(2) Storing KPI information reported by users as data setsIn the form of (1). Wherein N isSIs the number of elements in S. I (i ═ 1,2 …, N) in SS) An element (x)i,yi),xi∈RnAnd the n-dimensional KPI information reported by the user at a certain time is represented. In this embodiment, the value of n is 8, and the KPI information includes RSRP and SINR of the serving cell and the three nearest neighbor cells. KPI information is specifically represented as xi={RSRPsev,SINRsev,RSRPnei1,SINRnei1,RSRPnei2,SINRnei2,RSRPnei3,SINRnei3}. Where subscript sev denotes the serving cell and subscripts nei1, nei2, nei3 denote the three nearest neighbor cells. y isiIs xiThe label of (b), which represents the state of the base station serving the user, takes values of 0,1,2, 3. Wherein, yi0 indicates that the base station is in a normal (normal) state. y isi1 indicates that the base station is in a light outage (degraded) state. y isi2 indicates that the base station is in a medium interruption (shredded) state. y isiAnd 3 indicates that the base station is in a severe outage (catatonic) state. After S is obtained, the second step is carried out.
The second step is that: CGAN-W is trained using data set S. The CGAN-W is composed of a generator G and a discriminator D. G and D are all full-connection neural network structures, and the specific structure is shown in figure 1. The method comprises the following steps:
(1) the data in S are normalized according to equation (1) so that the final data are distributed between-1 and 1. And (5) after the normalized data set S is obtained, switching to the process (2).
(2) Dividing S into four subsets according to the sample labels in S: s0,S1,S2,S3. Wherein the subset S0The middle element is labeled 0 (i.e., y)i0) sample, representing normal data. Subset S1,S2,S3The middle element is a sample with labels 1,2 and 3 respectively, and represents an interrupt type data respectively. Statistical subset Sk(k is 1,2,3) total number of samples, denoted as Nk(k is 1,2, 3). Obtaining a subset S containing interrupt data1,S2,S3Thereafter, the process proceeds to the step (3).
(3) D and G loss functions in CGAN-W are defined as shown in the formulas (2) and (3) respectively. After the loss function is defined, the process proceeds to the flow (4).
(4) And setting parameters required by subsequent model training. The method specifically comprises the following steps: learning rate α is 0.0005; the truncation coefficient c is 0.01 and is used for limiting the weight range after the updating of the discriminator; the batch size m is 64 and is used for setting the number of samples sampled in each round of training; number of discriminant training times ndis5, setting the number of times that D needs to be trained when G is trained once; the maximum iteration number iteration of the model is 20000; number of times t (t) of arbiter iterations<ndis) (ii) a Number of model iterations iter (iter)<iteration). In addition, in this embodiment, G and D are all configured as a fully-connected neural network structure including three hidden layers. G, D hidden layer activation functions all use the leak relu function, i.e., leak relu (x) ═ max (0, x) + γ × min (0, x), and G output layer activation functions use the tanh function, i.e., tan hThe D output layer does not use the activation function. And entering the flow (5) after the setting is finished.
(5) Randomly initializing weight vector W of generator G and discriminator D in CGAN-W modelG,WDAnd biasVector bG,bD. The number of iterations iter of the initialization model is 0, and the number of iterations t of the discriminator is 0. After the model initialization is completed, the flow (6) is entered.
(6) From the interrupt subset SkRandomly sampling m samples in (k is 1,2,3) to obtain a real sample set { (x)1,y1),(x2,y2),…,(xm,ym)}. Wherein, the set { x1,x2,…,xmKPI information of sample is represented as real ═ x1,x2,…,xm}. Set { y1,y2,…,ymRepresents the corresponding sample label, denoted label ═ y1,y2,…,ym}. From 100-dimensional random noise z (z ∈ R) that follows a standard normal distribution100) M noise samples are sampled to form a set noise ═ z1,z2,…,zm}. The set noise and the label set label are set to { y ═ y1,y2,…,ymCombine, i.e. for each noise sample zj(j-1, 2, …, m), appending a label yj(j=1,2,…,m),yjE.g. label, to obtain the element (z)j,yj). Go through the m noise samples sampled as this operation z1,z2,…,zmGet the set { (z)1,y1),(z2,y2),…,(zm,ym)}. And after sampling is finished, the process is switched to the flow (7).
(7) Set { (z)1,y1),(z2,y2),…,(zm,ym) Input generator, output composite sample setWherein the content of the first and second substances,combining the sample setAnd the label set label obtained in the procedure (6) ═ y1,y2,…,ymCombine, i.e. for each synthesized sampleAdding a label yj(j=1,2,…,m),yjBelongs to label to obtain elementsGo through the m samples generated according to the operationObtaining a set of synthetic samplesAfter the synthesis sample set is obtained, the procedure proceeds to (8).
(8) Set the real samples { (x)1,y1),(x2,y2),…,(xm,ym) And the resultant sample setAs the input of the discriminator, the discriminator parameter W is updated by using the small batch stochastic gradient descent algorithm maximization formula (2)D,bD. Let the discriminator iteration number t be t +1, and proceed to the process (9).
(9) For updated weight coefficient W of discriminatorDCut off to make | WD|≤0.01。
(10) And (5) repeating the steps (6), (7), (8) and (9) until the number t of times of iteration of the discriminator is greater than 5. Proceed to the flow (11).
(11) Again from 100-dimensional random noise z (z ∈ R) following a standard normal distribution100) M noise samples are sampled to form a set noise '═ z'1,z′2,…,z′m}. The set noise' and the label set label obtained in the flow (6) are set to { y ═ y1,y2,…,ymCombine, i.e. for each noise sample zj' (j-1, 2, …, m) with the addition of the label yj(j=1,2,…,m),yjE.g. label, to obtain the element (z)j′,yj). Go through the m noise sampled according to the operationSample { z'1,z′2,…,z′mObtaining a set { (z'1,y1),(z′2,y2),…,(z′m,ym) And input to the generator. Updating generator parameters W using a small batch stochastic gradient descent algorithm minimization equation (3)G,bG. Let the number of model iterations iter be iter + 1. Proceed to the procedure (12).
(12) If ter>20000, finish training. Record generator G, arbiter D weight vector WG_opt,WD_optOffset vector bG_opt,bD_optThen, the flow proceeds to (13). Otherwise, turning to the flow (5) and starting a new training round.
(13) Repeating the processes (3) to (12) until three interrupt subsets S1,S2,S3The training is completed, and the CGAN-W model with the learned interrupt characteristics is obtained. And entering the third step.
The third step: KPI information reported by users in wireless network 8s is collected and stored as data set Wherein N isHRepresents the total number of samples in H. Element (h)w,yw),w=1,2,…,NH,hw∈RnAnd the n-dimensional KPI information reported by the user is represented. In this embodiment, the value of n is 8, and the KPI information includes RSRP and SINR of the serving cell and the three nearest neighbor cells. KPI information is specifically expressed as hw={RSRPsev,SINRsev,RSRPnei1,SINRnei1,RSRPnei2,SINRnei2,RSRPnei3,SINRnei3}。ywIs hwThe value of the label (2) is 0,1,2, 3. After the data set H is acquired, the fourth step is entered.
The fourth step: and synthesizing the interrupt data by using the CGAN-W model obtained in the second step, and balancing the data set H. The method comprises the following steps:
(1) from 100 dimensions following a standard normal distributionSampling n in random noise zgenNoise samples forming a setWherein n isgen(ngen>0) Representing the number of samples of the few classes expected to be synthesized. Because the number of the added synthetic samples can influence the imbalance proportion of the finally obtained training set samples and further influence the classification effect, the optimal n can be searched by a grid search methodgenThe value is obtained. Sampling label information to obtain a label setIt should be noted that the method synthesizes only a few types of data to achieve the goal of balancing the data set. Thus, the label only takes values in the set {1,2,3}, i.e., yr∈{1,2,3},r=1,2,…,ngen. Combining noise setsAnd a set of labelsI.e. for the noise sample zr(r=1,2,…,ngen) Adding a label yr(r=1,2,…,ngen),yr∈labelgenObtaining the element (z)r,yr). Go through all samples according to the operation to obtain a setAnd (4) transferring to the process (2).
(2) Will be assembledAn input generator according to W obtained in the second stepG_opt,bG_optCalculation Generator output, noteWherein the content of the first and second substances, will be assembledAnd tag collections Combining, i.e. for producing samplesAdding label yr(r=1,2,…,ngen),yr∈labelgenTo obtain the elementTraversing all the generated samples according to the operation to obtain a generated data setAfter the generated data set U is obtained, the process proceeds to the flow (3).
(3) And merging the generated data set U and the original data set H to obtain a calibrated training set V ═ U @ H. And entering the fifth step.
The fifth step: the inter-class overlap index for each sample in the training set V after calibration is calculated. The method comprises the following steps:
(1) for each piece of KPI information V in Ve(e=1,2,…,NV,NVRepresenting the total number of samples in V), Ve∈R8Selecting 5 KPI information nearest to the Euclidean distance to form a sample set Neigh ═ v1,v2,…,v5}. And (3) transferring to the process (2).
(2) Calculating a neutralization sample v in the set NeigheThe number of samples with the same label is recorded as NN (NN is more than or equal to 0 and less than or equal to 5). The process proceeds to the step (3).
(3) If NN>0,Then the sample veInter-class overlap index of (a)eNN/5. If NN is equal to 0, then sample veInter-class overlap index of (a)e0.05. Will calculate the resulting inter-class overlap index oeIncorporating the set O, i.e. O ═ O & { Oe}。
(4) And repeating the processes (1), (2) and (3) until all the sample traversals in the V are completed. And entering the sixth step.
And a sixth step: and (4) training the ANN by using the training set V and the inter-class overlap index set O to obtain an interruption detection model. The method comprises the following steps:
(1) and determining an ANN loss function according to V and O. Specifically, the formula is shown in (4). In addition, in this embodiment, the ANN is set to have a three-layer fully-connected neural network structure, and the number of neurons in the input layer is a KPI feature dimension, that is, 8. The number of neurons in the output layer is the total number of sample categories, namely 4. The specific structure is shown in fig. 2. The hidden layer activation function uses the LeakyReLU function, and the output layer activation function uses the softmax function. After the setting is completed, the process proceeds to the flow (2).
(2) Solving the minimum value of the formula (4) by using a gradient descent algorithm to obtain a weight vector W of the ANN networkANN_optAnd bias bANN_opt. And entering the seventh step.
The seventh step: according to the real-time report of KPI information x (x belongs to R) by users in network8) Interrupt detection is performed. The method comprises the following steps:
(1) inputting x into ANN model obtained in the sixth step according to WANN_optAnd bANN_optCalculating output layer output pred, pred is equal to R4。
(2) Computing a final predicted labelWhere argmax denotes the vector (pred)1,pred2,pred3,pred4) The subscript index corresponding to the medium maximum value starts from 0. If it isJudging x as an interrupt sample and determining the specific interrupt type, otherwise, judging x as a normal sample
The specific embodiments described herein are merely illustrative of the spirit of the invention. Various modifications or additions may be made to the described embodiments or alternatives may be employed by those skilled in the art without departing from the spirit or ambit of the invention as defined in the appended claims.
Claims (7)
1. A wireless network interruption detection method for generating a countermeasure network based on conditions is characterized by comprising the following steps:
the first step is as follows: collecting key performance indicators KPIs of a network, and forming a data set S;
the second step is that: training an improved condition by using a data set S to generate an antagonistic network CGAN-W, wherein the CGAN-W consists of a generator G and a discriminator D, and both G and D are of a fully-connected neural network structure;
the third step: collecting wireless networks T2KPI information reported by users in time and stored as data set Wherein N isHRepresents the total number of samples in H, element (H)w,yw),w=1,2,...,NH,hw∈RnAnd representing n-dimensional KPI information reported by the user, wherein the specific value of n can be determined by the operator according to the number of users and the network operation condition, and ywIs hwThe value of the label is 0,1,2 and 3, and the fourth step is carried out after the data set H is obtained;
the fourth step: synthesizing interrupt data by using the CGAN-W model obtained in the second step, and balancing a data set H;
the fifth step: calculating the inter-class overlap index of each sample in the training set V after calibration;
and a sixth step: training an Artificial Neural Network (ANN) by using a training set V and an inter-class overlap exponent set O to obtain an interruption detection model;
the seventh step: according to KPI information x reported by users in network in real time (x belongs to R)n) Interrupt detection is performed.
2. The method for detecting interruption of a wireless network for generating a countermeasure network based on a condition according to claim 1, wherein the first step is: the method comprises the following steps of collecting key performance indicators KPI of a network, and forming a data set S, specifically:
step 1.1, obtaining time T in wireless network1KPI information reported by internal users;
step 1.2, storing KPI information reported by users as a data setIn the form of (a); wherein N isSIs the number of the element in S, the ith element (x) in Si,yi),i=1,2...,NS,xi∈RnThe method comprises the steps that n-dimensional KPI information reported by a user at a certain time is represented, and the n-dimensional KPI information specifically comprises reference signal receiving power and signal-to-interference-and-noise ratio of a service cell and a neighbor cell; the value of n can be determined by an operator according to the number of users and the network operation condition; y isiIs xiThe label of (b) indicates the state of the base station serving the user, and values are 0,1,2, and 3; wherein, yi0 represents that the base station is in a normal state and has the strongest communication capability; y isi1 indicates that the base station is in a light interruption state, the communication capability is slightly reduced, and yi2 means that the base station is in a medium interruption state, and the communication capability is seriously reduced, which may cause a communication failure phenomenon; y isiWhen the base station completely loses communication capability, a large number of link connection failure events and user handover events are triggered to acquire S.
3. The method for detecting interruption of a wireless network for generating a countermeasure network based on conditions as set forth in claim 1, wherein the second step is specifically:
step 2.1, normalizing the data in the data set S according to the formula (1) to enable the final data to be distributed between-1 and 1;
wherein the content of the first and second substances,represents the ith data sample xiThe value of d-dimension feature, d 1,2, n, n represents sample xiA feature dimension of (a);representing the normalized sample, and turning to the step 2.2 after acquiring a normalized data set S;
step 2.2, dividing S into four subsets according to the sample labels in the data set S: s0,S1,S2,S3(ii) a Wherein the subset S0The middle element is a sample with a label of 0, namely yi is 0, and represents normal data; subset S1,S2,S3The middle elements are samples with labels of 1,2 and 3 respectively and represent interrupt type data respectively; statistical subset SkTotal number of middle samples, denoted NkK 1,2,3, a subset S containing interrupt data is obtained1,S2,S3Then, the step 2.3 is carried out;
step 2.3, D and G loss functions in the CGAN-W are defined as shown in the formula (2) and the formula (3) respectively:
wherein L isDRepresents a discriminator loss, LGRepresents a generator loss; m stands for trainingTotal number of samples of CGAN-W; z is a radical ofjTable sampled l-dimensional random noise samples, z, following a standard normal distributionj∈Rl,j=1,2,...,m;xjN-dimensional KPI information x reported on behalf of userj∈Rn;yjRepresents a sample label; using interrupt subsets S1,S2,S3Training the CGAN-W model to enable the CGAN-W model to learn the interrupt-like data characteristics, so that the sample (x)j,yj)∈Sk,G(zj,yj) Is input (z)j,yj) The generator outputs layer neuron output, namely a synthesized sample; d (x)j,yj) Is input as (x)j,yj) Then, the discriminator outputs the neuron output; d (G (z)j,yj),yj) Is an input (G (z)j,yj),yj) Then, the discriminator outputs the neuron output; after defining the loss function, turning to step 2.4;
step 2.4, setting parameters required by subsequent model training: the method specifically comprises the following steps: a learning rate α; a truncation coefficient c for limiting the weight range of the updated discriminator; the batch size m is used for setting the number of samples sampled in each round of training; number of discriminant training times ndisSetting the number of times D needs to be trained when G is trained once; the maximum iteration number iteration of the model; the iterative times t of the discriminator, t < ndis(ii) a The iteration number iter of the model is less than iteration; wherein, alpha, c, m, ndisThe numerical value of iteration is determined by the operator; after the setting is finished, the step 2.5 is carried out;
step 2.5, randomly initializing a generator G and a discriminator D in the CGAN-W model to obtain a weight vector WG,WDAnd an offset vector bG,bD(ii) a Initializing the iteration times iter of the model to be 0, and the iteration times t of the discriminator to be 0; after the model initialization is finished, entering step 2.6;
step 2.6, from the interruption subset SkRandomly sampling m samples to obtain a real sample set { (x)1,y1),(x2,y2),...,(xm,ym) }; wherein, the set { x1,x2,...,xmKPI information of sample is represented as real ═ x1,x2,...,xm}; set { y1,y2,...,ymRepresents the corresponding sample label, denoted label ═ y1,y2,...,ym}; from the l-dimensional random noise z (z ∈ R) that follows a standard normal distributionl) M noise samples are sampled to form a set noise ═ z1,z2,...,zm}; the set noise and the label set label are set to { y ═ y1,y2,...,ymCombine, i.e. for each noise sample zjAdding a label yjObtaining the element (z)j,yj),yjE.g. label; go through the m noise samples sampled as this operation z1,z2,...,zmGet the set { (z)1,y1),(z2,y2),...,(zm,ym) }; after sampling is finished, turning to the step 2.7;
step 2.7, set { (z)1,y1),(z2,y2),...,(zm,ym) Input generator, output composite sample setWherein the content of the first and second substances,combining the sample set And step 2.6, the label set label obtained in step (y) ═ y1,y2,...,ymCombining, i.e. for each synthesized sampleAdding a label yj,yjBelongs to label to obtain elementsGo through the m samples generated according to the operationObtaining a set of synthetic samplesAfter a synthetic sample set is obtained, the step 2.8 is carried out;
step 2.8, set the real samples { (x)1,y1),(x2,y2),...,(xm,ym) And the resultant sample setAs the input of the discriminator, the discriminator parameter W is updated by using the small batch stochastic gradient descent algorithm maximization formula (2)D,bD(ii) a Making the iteration time t of the discriminator t equal to t +1, and turning to step 2.9;
step 2.9, the updated weight coefficient W of the discriminatorDTruncating to a value between-c and c, i.e. | WDC is less than or equal to l, wherein c is a truncation coefficient, and the specific numerical value can be determined by an operator;
step 2.10, repeating steps 2.6, 2.7, 2.8 and 2.9 until the iteration times t of the discriminator is more than ndis(ii) a The procedure is shifted to step 2.11;
step 2.11, again from the i-dimensional random noise z (z ∈ R) that follows the standard normal distributionl) M noise samples are sampled to form a set noise '═ z'1,z′2,...,z′mAnd (3) comparing the set noise' with the label set label obtained in the step 2.6, wherein the label set label is { y ═ y }1,y2,...,ymCombine, i.e. z 'for each noise sample'jAdding a label yj,yjE.g. label to obtain element (z'j,yj);Operating as such, the sampled m noise samples { z'1,z′2,...,z′mObtaining a set { (z'1,y1),(z′2,y2),...,(z′m,ym) And inputting the data into a generator; updating generator parameters W using a small batch stochastic gradient descent algorithm minimization equation (3)G,bGMaking the iteration number iter of the model equal to iter +1, and turning to step 2.12;
step 2.12, if iter > iteration, ending training, recording generator G, and discriminator D weight vector WG_opt,WD_optOffset vector bG_opt,bD_optEntering the step 2.13, otherwise turning to the step 2.5, and starting a new round of training;
step 2.13, repeating the steps 2.3-2.12 until three interrupt subsets S1,S2,S3The training is completed, and the CGAN-W model with the learned interrupt characteristics is obtained.
4. The method for detecting interruption of a wireless network for generating a countermeasure network based on conditions as set forth in claim 1, wherein the fourth step is specifically:
step 4.1, sampling n from the random noise z of dimension I obeying the standard normal distributiongenNoise samples forming a setWherein n isgenRepresents the number of minority samples expected to be synthesized, ngenIs greater than 0; because the number of the added synthetic samples can influence the imbalance proportion of the finally obtained training set samples and further influence the classification effect, the optimal n is searched by a grid search methodgenA value; sampling label information to obtain a label set Only a few classes of data are synthesized for the purpose of balancing the data set, so the label only takes values in the set {1,2,3}, i.e., yr∈{1,2,3},r=1,2,...,ngen(ii) a Combining noise sets And a set of labelsI.e. for the noise sample zr(r=1,2,...,ngen) Adding the label yr(r=1,2,...,ngen),yr∈labelgenObtaining the element (z)r,yr) (ii) a Go through all samples according to the operation to obtain a setTurning to the step 4.2;
step 4.2, assembleAn input generator according to W obtained in the second stepG_opt,bG_optCalculation Generator output, noteWherein the content of the first and second substances,r=1,2,...,ngen,will be assembledAnd tag collectionsCombining, i.e. for producing samplesAdding a label yr,yr∈labelgenTo obtain the elementTraversing all the generated samples according to the operation to obtain a generated data setAfter the generated data set U is obtained, turning to the step 4.3;
and 4.3, merging the generated data set U and the original data set H to obtain a calibrated training set V ═ U ═ H.
5. The method for detecting interruption of a wireless network for generating a countermeasure network based on conditions as set forth in claim 1, wherein the fifth step is specifically:
step 5.1, for each piece of KPI information V in Ve,e=1,2,...,NV,NVRepresents the total number of samples in V, Ve∈RnSelecting q pieces of KPI information closest to the KPI information, and forming a sample set Neigh ═ v1,v2,...,vq}; turning to step 5.2;
step 5.2, calculating a neutralization sample v in the set NeigheThe number of samples with the same label is recorded as NN, the NN is more than or equal to 0 and less than or equal to q, and the step 5.3 is carried out;
step 5.3, if NN > 0, then sample veInter-class overlap index of (a)eNN/q; if NN is equal to 0, then sample veInter-class overlap index of (a)eβ; wherein the content of the first and second substances,for adjusting the coefficients, for adjusting the samples veClass (D)The specific value of beta can be determined by the operator, and the inter-class overlap index o obtained by calculationeIncorporating the set O, i.e. O ═ O & { Oe};
And 5.4, repeating the step 5.1, the step 5.2 and the step 5.3 until all samples in the V are traversed.
6. The method for detecting interruption of a wireless network for generating a countermeasure network based on conditions according to claim 1, wherein the sixth step is specifically:
step 6.1, determining an ANN loss function according to V and O, wherein the ANN loss function is shown as a formula (4)
Wherein N isVRepresents the total number of samples, o, in the training set Ve(e=1,2,...,NV) Representative sample veOf (2) inter-class overlap index, yegAs a function of sign, if sample veIs equal to g, then 1 is taken, otherwise 0, θ is takenjRepresents the weight matrix and bias vector corresponding to the jth neuron of the output layer, thetagRepresenting a weight matrix and a bias vector corresponding to the g-th neuron of the output layer, using superscript T to represent transposition, defining a loss function, and then turning to the step 6.2;
step 6.2, solving the minimum value of the formula (4) by using a gradient descent algorithm to obtain a weight vector W of the ANN networkANN_optAnd bias bANN_opt。
7. The method for detecting interruption of a wireless network generating a countermeasure network based on conditions according to claim 1, wherein the seventh step is specifically:
step 7.1, inputting x into the ANN model obtained in the sixth step according to WANN_optAnd bANN_optCalculating output layer output pred, pred is equal to R4;
Step 7.2, calculate the final prediction tagWhere argmax denotes the vector (pred)1,pred2,pred3,pred4) The subscript index corresponding to the medium maximum value is numbered from 0 ifAnd judging x as an interrupt sample and determining the specific interrupt type, otherwise, judging the x as a normal sample.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210108134.XA CN114501525B (en) | 2022-01-28 | 2022-01-28 | Wireless network interruption detection method based on condition generation countermeasure network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210108134.XA CN114501525B (en) | 2022-01-28 | 2022-01-28 | Wireless network interruption detection method based on condition generation countermeasure network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114501525A true CN114501525A (en) | 2022-05-13 |
CN114501525B CN114501525B (en) | 2024-02-02 |
Family
ID=81477405
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210108134.XA Active CN114501525B (en) | 2022-01-28 | 2022-01-28 | Wireless network interruption detection method based on condition generation countermeasure network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114501525B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110972174A (en) * | 2019-12-02 | 2020-04-07 | 东南大学 | Wireless network interruption detection method based on sparse self-encoder |
WO2020193510A1 (en) * | 2019-03-26 | 2020-10-01 | Robert Bosch Gmbh | Training for artificial neural networks with better utilization of learning data records |
CN112039687A (en) * | 2020-07-14 | 2020-12-04 | 南京邮电大学 | Small sample feature-oriented fault diagnosis method based on improved generation countermeasure network |
CN113406437A (en) * | 2021-06-21 | 2021-09-17 | 西南交通大学 | Power transmission line fault detection method for generating countermeasure network based on auxiliary classification |
-
2022
- 2022-01-28 CN CN202210108134.XA patent/CN114501525B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020193510A1 (en) * | 2019-03-26 | 2020-10-01 | Robert Bosch Gmbh | Training for artificial neural networks with better utilization of learning data records |
CN110972174A (en) * | 2019-12-02 | 2020-04-07 | 东南大学 | Wireless network interruption detection method based on sparse self-encoder |
CN112039687A (en) * | 2020-07-14 | 2020-12-04 | 南京邮电大学 | Small sample feature-oriented fault diagnosis method based on improved generation countermeasure network |
CN113406437A (en) * | 2021-06-21 | 2021-09-17 | 西南交通大学 | Power transmission line fault detection method for generating countermeasure network based on auxiliary classification |
Non-Patent Citations (1)
Title |
---|
陈彦: "无线网络中断检测技术研究", 《中国优秀硕士论文全文数据库》 * |
Also Published As
Publication number | Publication date |
---|---|
CN114501525B (en) | 2024-02-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106650767B (en) | Flood forecasting method based on cluster analysis and real-time correction | |
CN112039687A (en) | Small sample feature-oriented fault diagnosis method based on improved generation countermeasure network | |
CN112791997B (en) | Method for cascade utilization and screening of retired battery | |
CN109886464A (en) | The low information loss short-term wind speed forecasting method of feature set is generated based on optimization singular value decomposition | |
CN110062410B (en) | Cell interruption detection positioning method based on self-adaptive resonance theory | |
CN112087442A (en) | Time sequence related network intrusion detection method based on attention mechanism | |
CN110972174B (en) | Wireless network interruption detection method based on sparse self-encoder | |
CN113037410A (en) | Channel identification method, device, transmission method, transmission equipment, base station and medium | |
CN111198820B (en) | Cross-project software defect prediction method based on shared hidden layer self-encoder | |
CN116090757A (en) | Method for evaluating capability demand satisfaction of information guarantee system | |
CN110177112B (en) | Network intrusion detection method based on double subspace sampling and confidence offset | |
CN102799902A (en) | Enhanced relationship classifier based on representative samples | |
CN113033678A (en) | Lithium battery pack fault diagnosis method based on adaptive countermeasure network | |
CN114501525A (en) | Wireless network interruption detection method based on condition generation countermeasure network | |
CN115659258B (en) | Power distribution network fault detection method based on multi-scale graph roll-up twin network | |
CN114970693B (en) | Charging pile user portrait method based on federal learning | |
CN113327047B (en) | Power marketing service channel decision method and system based on fuzzy comprehensive model | |
Yong et al. | Short-term building load forecasting based on similar day selection and LSTM network | |
CN115496153A (en) | Multi-head self-attention deep convolution embedded clustering wind-light-load combined scene method | |
CN109615142A (en) | A kind of wind farm wind velocity combination forecasting method based on wavelet analysis | |
CN114615685B (en) | Wireless network interruption detection method based on generation of countermeasures network up-sampling | |
CN117998364B (en) | XGBoost WSN intrusion detection system based on mixed feature selection | |
CN115996135B (en) | Industrial Internet malicious behavior real-time detection method based on feature combination optimization | |
CN117062136A (en) | Wireless network interruption detection method based on hybrid generation countermeasure network | |
CN117320150B (en) | Outdoor fingerprint positioning method, computer and storage medium based on mobile cellular network multi-feature |
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 |