About me

My Research Interests:

Distributed Systems, Mobile Edge Computing, Deep Reinforcement Learning, Federated Learning, Software Defined Networking, Performance Evaluation

Currently I am juggling with:

  • Multi-Agent DRL

    Multi-Agent Deep Reinforcement Learning for Energy-Efficient Cooperative Computation Offloading in Heterogeneous Mobile Edge Computing

  • Federated DRL

    Federated Deep Reinforcement Learning Improves Dependent Task Offloading in Mobile Edge Computing

  • DRL-Based Rule Caching in SDN

    Deep Reinforcement Learning for Efficient Collaborative Rule Caching Through Pairing of P4 Switches in SDNs

  • QECO

    A QoE-Oriented Computation Offloading Algorithm based on Deep Reinforcement Learning for Mobile Edge Computing

  • MEC Env

    A Realistic Mobile Edge Computing environment; with matacouse conditions for deadline and energy Energy-Constrained

Daniel lewis
quote icon

Daniel lewis

Richard was hired to create a corporate identity. We were very pleased with the work done. She has a lot of experience and is very concerned about the needs of client. Lorem ipsum dolor sit amet, ullamcous cididt consectetur adipiscing elit, seds do et eiusmod tempor incididunt ut laborels dolore magnarels alia.

Download

My CV

Education

  1. Sharif University of Technology

    MSc. Computer Software Engineering
    Thesis Tilte:

    Optimizing Computational Task Offloading Problem in Energy-Constrained Mobile Edge Computing Systems with Deep Reinforcement Learning

    Supervisor: Prof. Ali Movaghar

    2019 — 2022

  2. Khajeh Nasir Toosi University of Technology

    BSc. Industrial Engineering 2013 - 2019

Academic Experience

  1. Research Engineer

    EdgeAI Lab
    Research Theme:

    Developing hierarchical multi-agent DRL-based approaches for compu- tation offloading decision-making in heterogeneous MEC, with an emphasis on centralized training and decentralized execution to achieve collaborative global optimization.

    2019 - Present

  2. Research Assistant

    Performance and Dependability Laboratory
    Research Theme:

    Designed and implemented an algorithm leveraging deep reinforcement learning to optimize computation offloading decisions within mobile edge computing, with a primary focus on enhancing the Quality of Experience (QoE) for end-users of mobile applications.

    2013 - 2019

  3. Teaching Assistant

    Sharif University of Technology
    Cources:

    Perance Evaluation of Computer Systems

    # Prof. Ali Movaghar and Dr. Mahdi Dolati

    2023

    Software Defined Networking

    # Prof. Ali Movaghar and Dr. Mohammad Hosseini

    2022

    Verification of Reactive Systems

    # Prof. Ali Movaghar

    2021

    Theory of Machines and Languages

    # Prof. Ali Movaghar

    2021

  4. Reviewer

    Computer Society of Iran

    27th International Computer Conference

    2022

Publication


# I. Rahmati, H. Shahmansouri, A. Movaghar, QECO: A QoE-Oriented Computation Offloading Algorithm based on Deep Reinforcement Learning for Mobile Edge Computing”, 2024.


# I. Rahmati, H. Shah-Mansouri, H. Kebriaei, A. Movaghar, Multi-Agent Deep Reinforcement Learning for Energy-Efficient Cooperative Computation Offloading in Heterogeneous Mobile Edge Computing, work in progress.


# I. Rahmati, A. Movaghar, Federated Deep Reinforcement Learning Improves Dependent Task Offloading in Mobile Edge Computing, work in progress.

My skills

  • Programming Languages:

    C, Python, LATEX

  • Frameworks & Tools:

    Linux

  • Languages:

    Farsi (Native), English (Working proficiency)

    • Project

    • Multi-Agent DRL

      Multi-Agent Deep Reinforcement Learning for Energy-Efficient Cooperative Computation Offloading in Heterogeneous Mobile Edge Computing

    • Federated DRL

      Federated Deep Reinforcement Learning Improves Dependent Task Offloading in Mobile Edge Computing

    • DRL-Based Rule Caching in SDN

      Deep Reinforcement Learning for Efficient Collaborative Rule Caching Through Pairing of P4 Switches in SDNs

    • QECO

      A QoE-Oriented Computation Offloading Algorithm based on Deep Reinforcement Learning for Mobile Edge Computing

    • MEC Env

      A Realistic Mobile Edge Computing environment; with matacouse conditions for deadline and energy Energy-Constrained

    Blog

    Contact

    Contact Form