1. Home »
  2. Supervisor: Dr. Moazam Ali
Supervisor: Dr. Moazam Ali

 

AI-Driven Architecture for Future Heterogeneous Networks

 

Supervisor: Dr. Moazam Ali, Sr. Assistant Professor

Campus/School/Dept: BUIC-E8/BSEAS/CS

Supervisory Record:  

  • PhD Produced: 0
  • PhD Enrolled: 0
  • MS/MPhil Produced: 08
  • MS/MPhil Enrolled: 05

 

Topic Brief Description:

The AI-Driven Architecture for Future Heterogeneous Networks, discusses how networks of the next generation that will incorporate heterogeneous technologies, such as 5G, Wi-Fi, satellite communication system, and IoT can be designed and automated with the use of Artificial Intelligence (AI) technologies. Such networks which are termed as Heterogeneous Networks (HetNets) tend to be complex in nature and most often require intelligent solutions to cope with their diversity, requirements and ever changing user needs.

 

Research Objectives/Deliverables:

  1. To design and develop AI algorithms (e.g., machine learning, reinforcement learning) for dynamic resource allocation, such as spectrum, bandwidth, and power, across heterogeneous network layers.
  2. To explore the use of various AI-driven self-organizing networks (SON) that autonomously adjust to network traffic, mobility of devices, failures of devices and networks, and varying environmental conditions.
  3. To design and apply AI-based techniques for intelligent traffic prediction and load management across various network technologies (e.g., 5G, Wi-Fi, IoT) to ensure seamless connectivity and optimal performance.

 

Research Questions: 

  1. How the AI algorithms will allocate dynamic resources across the heterogeneous network? Applying machine and reinforcement learning techniques, targets dynamic and real time allocation of the resources like spectrum, bandwidth and power.
  2. How to deal with the network traffic, mobile devices and the failure of network devices in a changing environment conditions? To reduce manual network management and enhancing the network adaptability and fault tolerance without human intervention.
  3. How to predict the network traffic and provide the optimum solution for load balancing across the various networks? preventing network congestion and ensure efficient data flow across all access technologies in a heterogeneous network.

 

Candidate’s Eligibility Profile:

  1. The applicant must have an MS/MPhil/Equivalent degree in electrical engineering with CGPA >0. Besides, applicants must have a strong background in mathematics, optimization theory and related fields.
  2. Experience with programming languages such as python, C/C++, OMNET++, or java is advantageous. Candidates should thrive in an international environment and have excellent communication skills to actively contribute to team research efforts.
  3. Proficiency in spoken and written English is essential. We value independence and responsibility while promoting teamwork and collaboration among colleagues.