Predict, Manage and Monitor the call drops of cell towers using Cloud Pak for Data
Note: This code pattern is part of a series that explores telecom call-drop predictions using IBM Cloud Pak for Data, Data Virtualization, Watson OpenScale, and Cognos Analyics. Other assets included in the series include:
A call drop is a situation where a call on a wireless network is disconnected before the caller ends the call. Some of the main reasons for call drops are:
Inadequate coverage, which can be due to multiple reasons:
Overloaded cell towers – the number of subscribers grow each day and most of them are on smartphones. The network capacity is simply not being ramped up at the same pace, which results in overloaded networks.
Cityscape changes – there have been instances where newly-built multi-storied buildings cause adjacent building’s subscribers to lose cell reception. Such instances are very common with rapidly changing cityscapes and calls for routine network data analysis from service providers.
Switching between towers – this situation occurs when a person is traveling or moving around while talking. Chances of a dropped call increaase if a call handover takes place (transfer from one base transceiver station (BTS) to another), especially in the case of overloaded networks.
Technical failures – this is beyond anyone’s control and operators generally monitor down-times through well-equipped network operation centers.
This code pattern aims to create a model to predict call drops, trained on the above mentioned failures. With the help of an interactive dashboard, we use a time series model to better understand call drops. As a benefit to telecom providers and their customers, it can be used to identify issues at an earlier stage, allowing more time to take the necessary measures to mitigate problems. The main features of the solution include:
After completing this code pattern, you’ll learn how to:
Note: As mentioned earlier, this code pattern is part of a series of assets around predicted call-drops from cell towers. It assumes that you have completed the other assets in the series (as listed above in the
Prerequisitessection). Those assets take you through some set-up steps that must be completed before starting on this code pattern.
git clone https://github.com/IBM/icp4d-telco-manage-ml-projectcd icp4d-telco-manage-ml-project
To create the data set required for this code pattern, you have 2 options.
You can build the data yourself.
weather.csv and tower.csv files as the two files to be joined and virtualized. Both files are located in the /data directory.As a convinence, we have created a csv file version of this merged data wich you can use directly. The file is named Telco_training_final.csv and is also located in the data directory.
Note : Pls execute the below section(
Steps for obtaining DB Credentials for DB2 on Cloud) ONLY if you want to use DB2 on Cloud to store the output of the Time-Series model.
Once the instance is created, in the Service Credential tab, click on Open Console.
Click on New Credential and the Add.
Now the service credential will be created, click on the copy button and save the credentials.
Once you login to your Cloud Pak for Data instance. Click on the (☰) menu icon in the top left corner of your screen and click Projects.
When you reach the Project list, click on New Project. You will get a pop-up, make sure to have the Analytics Project option and enter the desired name. Once you click on Ok you will go to a new screen. Click on Create to complete your project creation.
Once the start-up page opens up. Click on Add to Project menu.
Once the pop-up opens up click on connection.
Click on the appropriate DB option. And enter the saved credentials.
NOTE: Click on DB2 on Cloud if you have did the
Steps for DB Credentials for DB2 on Cloud. For any other DB click other options and obtain the credentials.
Test and once it is succesful, click on Create.Select the Compose for MySQL Database connection.
Enter the credentials of the Database. Click on Test and then click on Create.
From your project page, click on Data set > Add Data Set. Select the Telco_training_final.csv file from the /data directory.
From your project page, select Notebooks > Add Notebook. From the From URL tab. Enter the Notebook URL- https://github.com/IBM/icp4d-telco-manage-ml-project/blob/master/notebooks/Multivariate_Time_Series.ipynb, enter a name and click on Create.
Note: Choose the Python 3.6 environment.
You will run cells individually by highlighting each cell, then either click the Run button at the top of the notebook. While the cell is running, an asterisk ([*]) will show up to the left of the cell. When that cell has finished executing a sequential number will show up (i.e. [17]).
NOTE: For reference, we have included a completed notebook in the
/examplesdirectory of this repo. This version of the notebook includes all the executed steps and outputs. See https://github.com/IBM/icp4d-telco-manage-ml-project/blob/master/examples/Multivariate_Time_Series-Example.ipynb
Insert your created DB credentials, below the section 2.1 Insert the DB Credentials in the notebook.
Note: Run the below step (
Add the Dataset) ONLY if you have not completed the Data Virtualization tutorial.
In section 2.2 Add Dataset, highlight the blank cell by clicking on it. Click on the 10/01 button to select a specific data set.
Choose the Local tab, and select the call_drop_data_train.csv file that you added to the project. Under the Insert to code option, click Insert Pandas DataFrame.
IMPORTANT: Ensure the variable name is set to
df_data_1.
Cell > Run all.Complete the previous code pattern in this code series -
Monitor your Open Source ML Models using Watson OpenScale.
It performs the setup of the deployments on Watson OpenScale.
Once data is generated and stored in the DB., and after running the Time Series notebook, follow the tutorial - Build dashboards in Cognos Analytics on IBM Cloud Pak for Data to generate the output as shown in the next section.
A map based selection of each tower. When a tower is selected, the graphics indicate the call-drop prediction over the next 24 hours, with the help of the Time Series Model. It also shows which factors affect the call-drop percentage at the tower and by how much.
This code pattern is licensed under the Apache License, Version 2. Separate third-party code objects invoked within this code pattern are licensed by their respective providers pursuant to their own separate licenses. Contributions are subject to the Developer Certificate of Origin, Version 1.1 and the Apache License, Version 2.