Patent Application
20220376782
The present disclosure relates to a method and system for configuring an optical time domain reflectometer (OTDR) in passive optical networks, more particularly in a gigabit passive optical networks (GPON) and other passive optical networks (PON) before scanning a network on the occurrence of fault.
Optical time domain reflectometer (OTDR) is used worldwide to characterize the optical fiber network in terms of different reflective events, bend losses, splice losses, link loss and optical return loss (ORL).
Some of the disclosures have indicated the implementation of OTDR such as:
D1: WO2017161963A1. D1 relates to a method and device for detecting an optical fiber state. In D1 the data acquired by OTDR is compared with a preset reference value to obtain a deviation value. In the method of D1 as mentioned in page no. 10, following steps are performed;
D2: U.S. Pat. No. 9,909,904B2. D2 discloses an optical fiber system comprises a plurality of activation cells adapted to react to components of a back scattered signals and label the disturbance. In D2, a label can be associated with the one or more features in the backscattered signal. The label will be input to the input devices and the input passes through a plurality of activation cells to produce output. The procedure is repeated for a different feature. The different feature creates a different structure. The learning procedure can then proceed using different ones of the feature. Once the learning is complete, own feature in the backscatter is complete. Thus, in D2 also prior determination of parameters is done by learning. Col. 10 lines 10-13 of D2 discloses that pattern recognition system can be trained to recognize a large number of patterns in the reflectogram using an unsupervised learning process.
D3: WO2016198683A1. D3 discloses a method and apparatus for monitoring pipeline using an optical fiber sensor system. Para [0009] of D3 proposes solution to the issue of incorrect identification of events that is to use an artificial neural network to train the system to recognize the event. Para [0012] of D3 addresses three learning paradigms: supervised learning, unsupervised learning and reinforcement learning.
As disclosed in above mentioned documents, in practice whenever OTDR is used to find the fault or used to characterize the network, OTDR has to be configured first in any case before using it for data acquisition.
OTDR has a few important parameters, such as pulse width, acquisition time and maximum range that need to be configured optimally for better characterization of the network under test. It is network administrator who configures the OTDR parameters based on his knowledge of the network under test, which also requires administrator to be skilled enough to choose correct set of parameters to get best characterization of link and this process needs to be repeated every time if there is any change in the network. Problem becomes worse in case of technology such as GPON, where one OTDR is used to cater more than one passive optical network (PON), which are entirely different optical point-to-multipoint (PMP) networks. In such cases choosing OTDR parameters manually is quite impractical.
To help in such situations, many OTDRs come with auto mode configuration. In auto mode OTDR tries to choose the parameters based on the fiber network. It is also known that most OTDRs are efficient in testing point-to-point (P2P) networks. For point-to-multipoint (PMP) networks such as PON, OTDRs may not be that efficient as the trace received at the central office (CO) is a linear sum of the backscattered and reflected powers from all network branches. In such a case, OTDRs, even in auto mode, which are based on the methods used to calculate parameters for point to point (P2P), do not give optimal set of parameters for PMP networks.
Primary object of the present disclosure is to develop a method and a system which configure OTDR with a set of parameters which are optimal in least square sense using machine learning approach.
The present disclosure provides a method for configuring an optical time domain reflectometer (OTDR) in a gigabit passive optical networks (PON), characterized by the steps of: collecting network data of the network to be scanned by switch controller to characterize said network; collecting data from various optical network terminals (ONTs) of the gigabit passive optical networks (GPON) by an OTDR and the Switch Controller to form a training database, the training data is used to train the method; optimizing the parameters of the optical time domain reflectometer (OTDR) based on the network data and the training database by a processor provided on the switching controller using machine learning. In an embodiment of the present disclosure, it is disclosed that the parameters of optical time domain reflectometer (OTDR) to be configured for better characterization of network, consist of pulse width, acquisition time and distance range.
In yet another embodiment of the present disclosure, it is disclosed that the OTDR parameters are selected on the basis of network data, consisting of maximum distance of the fiber from optical line terminal (OLT) in the GPON, link loss and optical return loss or a combination thereof.
In an embodiment of the present disclosure, there is disclosed a system (100) for configuring an optical time domain reflectometer (OTDR) in a gigabit passive optical networks (GPON) (110), the system includes: a switch controller (120) configured for collecting network data from a network to be scanned characterizing said network, the switch controller (120) having: an optical time domain reflectometer (OTDR) (121) to be configured, the OTDR (121) and the switching controller operable for collecting data from various optical network terminals (ONTs) of the gigabit passive optical networks (GPON) (110) to form a training database; an optical switch (122), and a processor (123) adapted to configure the optical time domain reflectometer (OTDR) (121) by optimizing the parameters of optical time domain reflectometer (OTDR) (121) based on the network data using the training database. In yet another embodiment of the present disclosure, it is disclosed that the optical switch is configured to receive signal from optical time domain reflectometer (OTDR) while scanning the network to be scanned.
In still another embodiment of the present disclosure, it is disclosed that the switch controller further comprises a plurality of wavelength division multiplexing (WDM) coupler to couple the output of the optical switch to the gigabit passive optical networks (GPON).
In another embodiment of the present disclosure, it is disclosed that the system (100) further comprises a plurality of passive power splitters (PS) (130) to split coupled output received from WDM coupler (124) towards various ONTs.
These and other features, aspects, and advantages of the present subject matter will become better understood with reference to the following description. This summary is provided to introduce a selection of concepts in a simplified form. This summary is not intended to identify key features or essential features of the subject matter, nor is it intended to be used to limit the scope of the subject matter.
The above and other features, aspects, and advantages of the subject matter will be better understood with regard to the following description, and accompanying drawings where:
An exemplary embodiment of the device as indicated in
Our proposed method runs in a card of switch controller (120), which is integrated to GPON solution as depicted in the
The switch controller (120) will take 16 PON inputs from OLT (110), and one input pulse from OTDR (121) embedded on the switch controller (120). WDM coupler (124) of switch controller (120) sends the multiplexed signal towards the PON side after coupling the signals from OLT (110) with OTDR pulse. All PON networks are independent and may have any number of ONTs (upto 128) and other components. The system may have various passive optical splitters (PS) (130) to split the multiplexed signal received from coupler towards various ONTs.
Whenever OLT detects no upstream power i.e., from ONT to OLT, it is declared as loss of signal (LOS). It is immediately sent to switch controller to acquire fault trace via control path. Switch controller, based on the PON number associated with the fault, selects the appropriated port of optical switch and triggers the OTDR to acquire the trace. Similarly, it switches the port and takes trace if any other fault in different PON is detected. So far OTDR parameters are configured only once by the user interface (UI) and remain same till it is changed again. If, for example, a particular pulse width, which decides the power injected into the fiber and thus decides the distance it can travel, is selected, it might be good enough to see one complete PON but it might not be able to see even half of the network for another PON. Similarly, other parameters may affect the accuracy and characterization of PON. Now the present disclosure provides a method to select optimum parameters for a particular network or PON based on the network configuration, before taking trace. Algorithm for predicting parameters is trained using machine learning approach.
Regression algorithms, a supervised machine learning approach are used in the present disclosure. Following is the brief introduction of the algorithm. Regression algorithms belong to family of Supervised Machine Learning algorithms. Purpose of supervised learning algorithms is to model the dependencies and relationships between the output and input features or dependent and independent variables, to predict the value for new data. The algorithm builds a model on the features of training data and using the model to predict value for new data. The simple linear regression attempts to establish a linear relationship between one independent variables and a dependent variable. In multiple linear regression model there are two or more independent variables and a dependent variable. Whereas in multivariate multiple linear regression both independent variables and dependent variable are two or more.
As there are three independent and three dependent variables i.e, there is a need to choose three OTDR parameters based on three network attributes, so multivariate multiple linear regression method is used to establish the relationship. The present disclosure is providing a brief introduction to multiple linear regression. The general model for multiple linear regression with k independent variables is of the form
y
i=β0+β1xi1+β2xi2+ . . . +βkxik+i, i=1,2, . . . ,n.
There are total n observations and above equation signifies ith observation, where y, is dependent variable, x=[xi1, xi2, xi3, . . . , xik] are the k independent variables, is the estimation or prediction error and β=[β0, β1, . . . , βk] is a vector of regression coefficients. To simplify the computation, we have written the multiple regression model in terms of the observations using matrix notation. Using matrices allows for a more compact framework in terms of vectors representing the independent variable, dependent variables, regression coefficients, and estimation or prediction errors. The model takes the following form
Y=Xβ+
and when written in matrix notation, we have
It can be noted that Y is an n×1 dimensional random vector consisting of the observations, X is an n×(k×1) matrix determined by the predictors, β is a (k×1)×1 vector of unknown parameters, and is an n×1 vector of random errors.
The first step in multiple linear regression analysis is to determine, using training data, the vector {circumflex over (β)}, which gives the linear combination ŷ that minimizes the length of the prediction error vector. In other words, the vector {circumflex over (β)} minimizes the sum of the squares difference between ŷ and y and later on this vector is used to predict dependent variable yi when any new test data come. Now, since the objective of multiple regression is to minimize the sum of the squared errors, the regression coefficients that meet this condition are determined by solving the least squares normal equation.
X
T
X{circumflex over (β)}=X
T
Y
An important assumption in multiple regression analysis is that the variables x1, x2, . . . , xn be linearly independent. Now if the variables x1, x2, . . . , xn are linearly independent, then the inverse of XTX will exist, and we can obtain
{circumflex over (β)}=(XTX)−1XTY
Similarly, regression coefficients for other dependent variables can be estimated.
Following are the description of OTDR parameters and their impact on characterization of network in the form of trace generated by OTDR. They have been chosen as dependent variables or output variables.
Following are the PON network attributes that have been chosen as independent variables or input variables.
Following are the various steps involved in the method.
Following are the different steps involved.
| Number | Date | Country | Kind |
|---|---|---|---|
| 201811037838 | Oct 2018 | IN | national |
| Filing Document | Filing Date | Country | Kind |
|---|---|---|---|
| PCT/IN2018/050833 | 12/12/2018 | WO |
