Research
Research Focus
My research focuses on the application of machine learning and artificial intelligence techniques to solve complex problems in 6G networks and smart systems. I work at the intersection of telecommunications, deep learning, and optimization theory to develop innovative solutions for next-generation wireless networks.
Through my work, I aim to enhance network efficiency, reduce energy consumption, and optimize resource allocation using advanced AI/ML techniques. My research contributes to the development of intelligent and autonomous networking systems that can adapt to changing environments and user demands.
I collaborate with academic and industry partners to translate theoretical advances into practical applications that can address real-world challenges in telecommunications and smart infrastructure.
Academic Profiles
Research Areas
6G Networks & Intelligent Communication Systems
Developing AI-powered solutions for next-generation wireless networks with a focus on energy efficiency and performance optimization.
My research in 6G networks focuses on leveraging machine learning and artificial intelligence to create more efficient, secure, and adaptive communication systems. I work on:
- Conflict Management in O-RAN xApps: Developing frameworks like COMIX that detect and resolve conflicts between Deep Reinforcement Learning (DRL)-based xApps for power control.
- Energy Efficiency Optimization: Creating algorithms that reduce network energy consumption while maintaining quality of service.
- Network Digital Twins: Building simulation environments that can model and predict network behavior for testing and optimization.
- AI-Based Resource Allocation: Designing intelligent systems that dynamically allocate network resources based on real-time conditions and demands.
This research aims to address the increasing complexity of wireless networks and the growing demand for faster, more reliable connections with lower energy consumption. By integrating AI/ML techniques with telecommunications infrastructure, we can create smarter networks that adapt to changing conditions and user needs.
Featured Publication
COMIX: Generalized Conflict Management in O-RAN xApps -- Architecture, Workflow, and a Power Control case
This paper introduces a framework for detecting and resolving conflicts between AI-based applications in Open RAN networks, resulting in significant energy savings.
Multi-Agent Reinforcement Learning
Exploring cooperative and distributed learning approaches for complex environments with multiple agents.
My research in multi-agent reinforcement learning focuses on developing algorithms that enable multiple AI agents to learn and work together effectively. Key research directions include:
- Distributed Energy Management: Creating multi-agent systems for optimizing energy distribution across smart grids and household devices.
- Cooperative Learning Protocols: Developing communication and coordination mechanisms that allow agents to share information and learn collaboratively.
- Scalable MARL Architectures: Designing frameworks that can scale to large numbers of agents while maintaining performance and stability.
- Conflict Resolution Mechanisms: Building systems that can detect and resolve conflicts between agents with different objectives.
This research has applications in smart cities, energy management systems, autonomous vehicle coordination, and distributed control systems. By enabling multiple AI agents to work together effectively, we can tackle more complex problems and create more resilient and adaptive systems.
Featured Project
Multi-Agent Energy Management System
A distributed framework for optimizing energy distribution across household HVAC systems and storage units using reinforcement learning.
Smart Systems & IoT Applications
Developing intelligent infrastructure and systems that leverage AI to optimize resource utilization and user experience.
My research in smart systems focuses on integrating AI and machine learning into IoT devices and infrastructure to create more intelligent and responsive environments. Areas of focus include:
- Intelligent Resource Management: Developing systems that optimize the allocation and use of resources like energy, water, and computing power.
- Predictive Maintenance: Creating models that can predict equipment failures and schedule maintenance to prevent downtime.
- Context-Aware Applications: Building applications that adapt to user needs and environmental conditions in real-time.
- Data-Driven Decision Support: Designing systems that analyze large amounts of sensor data to provide actionable insights.
This research aims to make our physical infrastructure and devices more intelligent, efficient, and responsive to human needs. By embedding AI into the systems we interact with daily, we can create environments that adapt to our preferences, anticipate our needs, and use resources more efficiently.
Research Methodology
My approach combines simulation-based experimentation, real-world data analysis, and prototype development. I utilize digital twin technology to create high-fidelity models of physical systems before deploying solutions in real environments.
Research Collaboration Opportunities
I am open to exploring research opportunities within my areas of expertise, including 6G networks, machine learning, and smart systems. If you are interested in discussing a potential collaboration, please contact me.
Contact Me