The key aspect in solving ML problems in telecom industry lies in continuous data collection and evaluation from different categories of customers and networks so as to track and dive into varying performance metrics. The KPIs form the basis of network monitoring helping network/telecom operators to automatically add and scale network resources. Such smart automated systems are built with the objective of increasing customer engagement through enhanced customer experience and tracking customer behavior anomaly with timely detection and correction. Further the system is designed to scale and serve current LTE, 4G and upcoming 5G networks with minimal non-effective cell site visits and quick identification of Root Cause Analysis (RCA).

Network congestion has remained an ever-increasing problem. Operators have attempted a variety of strategies to match the network demand capacity with existing infrastructure, as the cost of deploying additional network capacities is expensive. To keep the cost under control, operators apply control measures to attempt to allocate bandwidth fairly among users and throttle the bandwidth of users that consume excessive bandwidth. This approach had limited success. Alternatively, techniques that utilize extra bandwidth for quality of experience (QOE) efficiency by over-provisioning the network has proved to be ineffective and inefficient due to lack of proper estimation.

The evolution of 5G networks, would lead manufacturers and telecom operators to use high-data transfer rates, wide network coverage, low latency to build smart factories using automation, artificial intelligence and Internet of Things (IoT). The application of advanced data science and AI can provide better predictive insights to improve network capacity-planning accuracy. Better network provisioning would yield better network utilization for both next-generation networks based on 5G technology and current LTE and 4G networks. Further AI models can be designed to link application throughput with network performance, prompting users to plan their daily usage based on their current location and total monthly budget.

In this talk, we will understand the current challenges in telecom industry, the need for an AIOPS platform, and the mission held by telecom operators, communication service providers across the world for designing such AI frameworks, platforms and best practices. We will see how increasing operator collaborations are helping to create, deploy and productionize AI platforms for different AI use-cases. We will study one industrial use-case (with code) based on real-time field research to predict network capacity. In this respect we will investigate how deep learning networks can be used to train large volumes of data at scale (millions of network cells), and how its use can help the upcoming 5G networks. We will also examine an end to end pipeline of hosting the scalable framework on Google Cloud with special emphasis on Data Governance and Data Mangement. As data volume is huge and data needs to be stored in highly secured systems, we build our high-performing system with extra security features that can process millions of request in an order of few mili-secs. As the session highlights parameters and metrics in creating the neural network, it also discusses the challenges and some of the key aspects involved in designing and scaling the system.

 
 

Outline/Structure of the Demonstration

The presentation is structured as:

1. Current and Future Challenges in the Telecom industry - 2mins

3. Machine Learning use-cases related to network capacity and outage- 2 mins

4. Scalable ML architecture with Distributed Training -6 mins

5. Neural Network parameters and design to solve one industrial use-case - 5 mins

6. Demo - 4 mins

Learning Outcome

Understanding of :

1. How to overcome telecom industry challenges with different AI solutions and an AIOPS framework

2. Basic understanding of Google Cloud platform to build an end to end scalable ML pipeline

3. Modeling one industrial use case with deep learning (with code using python Keras)

5. How to improve ML model training and accuracy.

Target Audience

ML and Deep learning enthusiasts , Cloud Engineers and Experts , Managers, Anyone interested in Data Science and Telecom domain

Prerequisites for Attendees

1. Basic understanding of Cloud components

2. Basic understanding of Machine Learning/Data Science

schedule Submitted 6 months ago

Public Feedback

comment Suggest improvements to the Author
  • Kuldeep Jiwani
    By Kuldeep Jiwani  ~  5 months ago
    reply Reply

    Hi  Sharmistha,

    You have well emphasised the need of AI/ML in the telecom industry and that is well taken. But could you explain a bit more on what kind of problem are you planning to solve and how.

    In telecom world data is humongous in the order of TBs every day, so if you are planning to do some ML on such a huge volume of data then the most important question is what and how. We don't see the what part and about how you have hinted it but at a very high level. So could add more details on both what and how part.

    • Sharmistha Chatterjee
      By Sharmistha Chatterjee  ~  5 months ago
      reply Reply

      Hi Sudeep,

      Thanks for seeking the clarifications. If you refer to my slides 27 to 29 , and listen to my demo speech I have talked about how we solve one industrial use-case i.e. "determining network capacity" through LSTM based networks. 

      Yes as you have correctly said the data volume is large, so I talk about the challenges of aggregating data coming in from varying time zones, how we would preprocess that data before feeding that to LSTM.

      Our objective is to illustrate how do we combine different radio signal params along with network operator driven  parameters and feed to deep NN, to predict network capacity/congestion. And how that prediction can help in determining capacity of carrier aggregation.

      Please let me know if I have been able to explain or you would need more details. 

      Regards,

      Sharmistha

       

      • Kuldeep Jiwani
        By Kuldeep Jiwani  ~  5 months ago
        reply Reply

        Hi Sharmistha,

        Thanks for the elaborate reply. Since this is a 20 minutes talk, we would suggest that you take one topic and cover that properly than covering many topics.

        Would you prefer to talk more on Data Governance in telecom industry.

        Or you wish to talk about challenges faced in handling large scale data and than challenges in network capacity planning. How were you able to train an LSTM model on such huge data then based on model how did you solve the network capacity issue.

        We would suggest to restructure the outline of the talk accordingly.

        • Sharmistha Chatterjee
          By Sharmistha Chatterjee  ~  5 months ago
          reply Reply

          Hi Kuldeep,

          I would like to cover on "challenges faced in handling large scale data and than challenges in network capacity planning."..

          Yes , as you said that's also captured in slide 22, 23-- how we implemented distributed training mechanism.

          As suggested , I will eleminate first few slides that talk about data governance.

          Please let me know if you need any more eexplanation

          Regards,

          Sharmistha

           

          • Sharmistha Chatterjee
            By Sharmistha Chatterjee  ~  5 months ago
            reply Reply

            Hi Kuldeep,

            Thanks for giving me the pointers...I just updated the outline of the talk as:

            The presentation is structured as:

            1. Current and Future Challenges in the Telecom industry - 2mins

            3. Machine Learning use-cases related to network capacity and outage- 2 mins

            4. Scalable ML architecture with Distributed Training -6 mins

            5. Neural Network parameters and design to solve one industrial use-case - 5 mins

            6. Demo - 4 mins

            I would have loved to bring my collegue. But this project was done with my collegues and professors  at US, would check with them.

            Regards,

            Sharmistha

          • Kuldeep Jiwani
            By Kuldeep Jiwani  ~  5 months ago
            reply Reply

            Hi Sharmistha,

            Thanks for re-thinking, yes talking more on the technical and ML aspect is better for such a conference.

            Can you also update the outline accordingly.
            Also the talk can have 2 speakers in case you wish to bring your colleague along.

  • Deepti Tomar
    By Deepti Tomar  ~  5 months ago
    reply Reply

    Hello Sharmistha,

    Thanks for your time and efforts on the proposal! Could you answer the following questions to help the program committee understand your proposal better?

    • Are these demo(s) /use case(s) from your project work (industry-specific use cases)? Speaker's experience on the project helps people understand the concept better.
    • Did you use these techniques to help solve a particular problem? 
    • If yes, would you be sharing the Challenges faced in the implementation of the technique in your application and the workarounds?

    Thanks,

    Deepti

    • Sharmistha Chatterjee
      By Sharmistha Chatterjee  ~  5 months ago
      reply Reply

      Hi Deepti,

      Thanks for seeking the clarifications,

      Please find the answers here.

      • Are these demo(s) /use case(s) from your project work (industry-specific use cases)? Speaker's experience on the project helps people understand the concept better.   

        Yes , they are from a live deployed project, which is serving millions of customers real time.

      • Did you use these techniques to help solve a particular problem? 

      Yes we used the ML governance  techniques as well the architectural components to design the entire architecture framework.

      • If yes, would you be sharing the Challenges faced in the implementation of the technique in your application and the workarounds?

      Yes I would discuss about the challenges and broader scope of it , as much possible with the required time.

      Hope this answers your question. If you are looking for anything specific please let me know.

       

      Regards,

      Sharmistha

       

      • Deepti Tomar
        By Deepti Tomar  ~  5 months ago
        reply Reply

        Thanks for your response, Sharmistha! We will let you know in case if we have more questions.

  • Natasha Rodrigues
    By Natasha Rodrigues  ~  6 months ago
    reply Reply

    Hi Sharmistha,

    Thank you for your proposal and voice-over video, however to help the program committee understand your presentation style, can you provide a link to your past recording or record a small 1-2 mins trailer of your talk and share the link to the same?

    Thanks,

    Natasha

    • Sharmistha Chatterjee
      By Sharmistha Chatterjee  ~  6 months ago
      reply Reply

      Hi Natasha,

      I have already provided the video and link to one -drive.  i.e https://1drv.ms/v/s!AvdV41OMEdWicKVEPz-zqugAjkM?e=ajY6np

      If you are not able to access it, is there any email id , or specific link where I can upload it or send it.

       

      Regards,

      Sharmistha

       

       

       

       

      • Natasha Rodrigues
        By Natasha Rodrigues  ~  6 months ago
        reply Reply

        Hi Sharmistha,

        Kindly note, the main idea is to have you (the speaker) in the video and speak. We would require an actual video of the person talking so that the program committee can see the presentation style. Hence request you to record a 1-2 trailer presenting your topic.

        Many thanks,

        Natasha


  • Ravi Ranjan
    keyboard_arrow_down

    Ravi Ranjan - Deep Reinforcement Learning Based RecSys Using Distributed Q Table

    Ravi Ranjan
    Ravi Ranjan
    Senior Data Scientist
    Publicis Sapient
    schedule 11 months ago
    Sold Out!
    20 Mins
    Talk
    Intermediate

    Recommendation systems (RecSys) are the core engine for any personalized experience on eCommerce and online media websites. Most of the companies leverage RecSys to increase user interaction, to enrich shopping potential and to generate upsell & cross-sell opportunities. Amazon uses recommendations as a targeted marketing tool throughout its website that contributes 35% of its total revenue generation [1]. Netflix users watch ~75% of the recommended content and artwork [2]. Spotify employs a recommendation system to update personal playlists every week so that users won’t miss newly released music by artists they like. This has helped Spotify to increase its number of monthly users from 75 million to 100 million at a time [3]. YouTube's personalized recommendation helps users to find relevant videos quickly and easily which account for around 60% of video clicks from the homepage [4].

    In general, RecSys generates recommendations based on user browsing history and preferences, past purchases and item metadata. It turns out most existing recommendation systems are based on three paradigms: collaborative filtering (CF) and its variants, content-based recommendation engines, and hybrid recommendation engines that combine content-based and CF or exploit more information about users in content-based recommendation. However, they suffer from limitations like rapidly changing user data, user preferences, static recommendations, grey sheep, cold start and malicious user.

    Classical RecSys algorithm like content-based recommendation performs great on item to item similarities but will only recommend items related to one category and may not recommend anything in other categories as the user never viewed those items before. Collaborative filtering solves this problem by exploiting the user's behavior and preferences over the items in recommending items to the new users. However, collaborative filtering suffers from a few drawbacks like cold start, popularity bias, and sparsity. The classical recommendation models consider the recommendation as a static process. We can solve the static recommendation on rapidly changing user data by RL. RL based RecSys captures the user’s temporal intentions and responds promptly. However, as the user action and items matrix size increases, it becomes difficult to provide recommendations using RL. Deep RL based solutions like actor-critic and deep Q-networks overcome all the aforementioned drawbacks.

    Present systems suffer from two limitations, firstly considering the recommendation as a static procedure and ignoring the dynamic interactive nature between users and the recommender systems. Also, most of the works focus on the immediate feedback of recommended items and neglecting the long-term rewards based on reinforcement learning. We propose a recommendation system that uses the Q-learning method. We use ε-greedy policy combined with Q learning, a powerful method of reinforcement learning that handles those issues proficiently and gives the customer more chance to explore new pages or new products that are not so popular. Usually while implementing Reinforcement Learning (RL) to real-world problems both the state space and the action space are very vast. Therefore, to address the aforementioned challenges, we propose the multiple/distributed Q table approaches which can deal with large state-action space and that aides in actualizing the Q learning algorithm in the recommendation and huge state-action space.

    References:

    1. "https://www.mckinsey.com/industries/retail/our-insights/how-retailers-can-keep-up-with-consumers":https://www.mckinsey.com/industries/retail/our-insights/how-retailers-can-keep-up-with-consumers
    2. "https://medium.com/netflix-techblog/netflix-recommendations-beyond-the-5-stars-part-1-55838468f429":https://medium.com/netflix-techblog/netflix-recommendations-beyond-the-5-stars-part-1-55838468f429
    3. "https://www.bloomberg.com/news/articles/2016-09-21/spotify-is-perfecting-the-art-of-the-playlist":https://www.bloomberg.com/news/articles/2016-09-21/spotify-is-perfecting-the-art-of-the-playlist
    4. "https://dl.acm.org/citation.cfm?id=1864770":https://dl.acm.org/citation.cfm?id=1864770
    5. "Deep Reinforcement Learning based Recommendation with Explicit User-Item Interactions Modelling": https://arxiv.org/pdf/1810.12027.pdf
    6. "Deep Reinforcement Learning for Page-wise Recommendations": https://arxiv.org/pdf/1805.02343.pdf
    7. "Deep Reinforcement Learning for List-wise Recommendations": https://arxiv.org/pdf/1801.00209.pdf
    8. "Deep Reinforcement Learning Based RecSys Using Distributed Q Table": http://www.ieomsociety.org/ieom2020/papers/274.pdf