METHOD OF TRAINING A DEEP NEURAL NETWORK CLASSIFIER, A TRAINING MODULE AND A NETWORK ANALYZER

    公开(公告)号:EP3562047A1

    公开(公告)日:2019-10-30

    申请号:EP18169893.7

    申请日:2018-04-27

    IPC分类号: H04B3/46 H04M3/30 H04L12/24

    摘要: The present invention discloses a method for training a deep neural network classifier for use in detecting impairments in a communication network, the communication network comprising a plurality of communication lines, the method comprising: a) obtaining a measured loop frequency response for the respective communication lines comprised in the communication network, wherein, the loop frequency response is measured by a modem over the respective communication line; b) extracting a modem parasitic effect for the respective communication lines from the measured loop frequency response of the respective communication line; c) clustering the modem parasitic effect of the respective communication lines into a first number M of groups and determining a modem signature for respective ones of the first number M of groups; d) obtaining an original training data set comprising a second number N of loop frequency responses corresponding to a first set of communication lines and associated information on the presence of impairment on the first set of communication lines; e) determining an augmented training data set comprising a third number of loop frequency responses and associated information on the presence of impairment based on the original training data set and the modem signature for respective ones of the first number of groups, wherein, the third number is not greater than N*M; f) training the deep neural network classifier using the augmented training data set.

    PREDICTION OF A METRIC OF QUALITY OF A NETWORK

    公开(公告)号:EP4329256A1

    公开(公告)日:2024-02-28

    申请号:EP22192130.7

    申请日:2022-08-25

    摘要: An apparatus (100) for building a prediction model comprises means for collecting a plurality of high-paced telemetry traffic measurement values (4) representing traffic rates observed in a shared medium of the point-to-multipoint telecommunications network (1), means for fitting at least one traffic model (5) using the plurality of high-paced telemetry traffic measurement values (4) and computing at least one simulated value of the metric of the quality of the point-to-multipoint telecommunications network using the traffic model (5), wherein the metric of the quality relates to at least one individual user, and means for training a prediction model (7) on a simulated dataset (6), wherein the simulated dataset (6) comprises the descriptor of at least one network configuration and the at least one simulated value of the metric of the quality of the point-to-multipoint telecommunications network, the prediction model (7) being configured to compute the value of the metric of the quality of the point-to-multipoint telecommunications network.

    METHOD AND NETWORK ANALYZER OF EVALUATING A COMMUNICATION LINE

    公开(公告)号:EP3451642A1

    公开(公告)日:2019-03-06

    申请号:EP17189099.9

    申请日:2017-09-01

    IPC分类号: H04M3/30

    摘要: The present invention discloses a method, in a network analyzer, of evaluating a communication line in a Digital Subscriber Line, DSL, network, the communication line connecting an access node and an end-user Customer-Premises Equipment, CPE; the method comprising: a) obtaining a loop length (L) of a predetermined terminal section of the communication line; b) determining whether there is an impairment in the communication line; b1) if it is determined that there is no impairment in the communication line, classifying the communication line into the first group; b2) if it is determined that there is an impairment in the communication line, the method going on with: c) obtaining a location of the impairment in the communication line; d) determining whether the impairment is located in the predetermined terminal section of the communication line based on the loop length (L); d1) if so, classifying the communication line into a second group; d2) else, classifying the communication line into the first group; wherein, if the communication line is classified in the first group, it is qualified for an new broadband communication service, and if the communication line is classified in the second group, it is not qualified for the new broadband communication service, and wherein, the new broadband communication service is to be deployed over the predetermined terminal section of the communication line.

    APPARATUS AND METHOD FOR ALLOCATING BANDWIDTH

    公开(公告)号:EP4451639A1

    公开(公告)日:2024-10-23

    申请号:EP23168598.3

    申请日:2023-04-18

    摘要: An apparatus (201) comprises means for:
    obtaining an indication of contention (105) of a communications network (101);
    obtaining a historical bandwidth utilization indication parameter (302) of respective participants of the communications network (101) ;
    in response to determining, based on the indication of contention and the historical bandwidth utilization indication, that a participant meets an intensive capacity consumption condition, providing a reduced value of a scheduler parameter (304) and an increased value of a maximum bandwidth parameter (303) to an output of the apparatus (201), wherein the scheduler parameter and the maximum bandwidth parameter are related to allocating bandwidth to the participant meeting the intensive capacity consumption condition, wherein the scheduler parameter represents a proportion of a capacity of the communications network allocated to the participant when the communications network is congested, wherein the maximum bandwidth parameter represents a maximum bandwidth allocated to the participant.