As a computer scientist specializing in networking, my primary research focus is directed toward applying AI/ML-driven solutions, such as Deep Reinforcement Learning (DRL), Federated Learning, and Meta Learning, to address the dynamic nature and complexities of Multi-Agent Systems in Wireless Communication Networks. I developed [QECO] algorithm, a DRL-based QoE-Oriented Computation Offloading Algorithm for Mobile Edge Computing (MEC), which leverages Deep Q-Network (DQN) and LSTM to enable distributed decision-making in uncertain MEC environments. [Paper]
Currently, I have been working on three main research idea in MEC systems, which are as follows:
- Multi-Agent DRL for Cooperative Task Offloading in Partially Observable MEC Environment [Idea]
- Federated DRL for Continuous Improving Intradependente Task Offloading in MEC Network [Idea]
- Meta-RL for Optimized Task Scheduling in Heterogeneous MEC [Idea]
- General: Networking, MEC, DRL, Federated Learning
- Programming Languages: Python, R, Bash, C++
- Machine Learning: TensorFlow, PyTorch, Scikit-learn
- Data Analysis: Pandas, NumPy, Matplotlib
- Softwares: Mininet, Ns-3, Flask, Office, Visio
- Operating System: Linux
- Tools: Jupyter, LaTeX, Git