Hello, I'm

George Levis

I'm a Machine Learning Engineer & Research Associate — AI/ML & 6G Networks

I’m passionate about leveraging AI and machine learning to create innovative solutions across various industries, including 6G and telecommunications, smart homes, and more. I enjoy building intelligent systems that make technology smarter and more efficient. Always eager to learn, I seek out new challenges to grow my skills and contribute to groundbreaking projects.

Research Highlights

My research focuses on applying advanced machine learning and artificial intelligence techniques to solve complex problems in 6G networks and smart systems.

Deep Learning

Applying neural networks and deep learning techniques to solve complex problems in telecommunications and smart systems.

Learn more

Multi-Agent Systems

Creating distributed AI agents that collaborate to optimize complex systems such as energy management and network resources.

Learn more

6G Networks - O-RAN environment

Developing AI-powered solutions for next-generation wireless networks with a focus on energy efficiency and performance optimization.

Learn more

Featured Publication

My most recent research paper on conflict management in O-RAN environments.

View All Publications

A Peer-to-Peer Energy Management and Exchange Framework in Energy Communities via Actor-Critic Learning

George A. Levis, Sotirios T. Spantideas, Anastasios E. Giannopoulos, Member, IEEE, and Panagiotis Trakadas

The rapid growth of global energy consumption in buildings and the increasing adoption of renewable energy sources have created an urgent need for intelligent Home Energy Management Systems (HEMS). This work addresses the challenge of optimizing both individual home energy usage and community-wide energy distribution through peer-to-peer (P2P) trading. In the proposed framework, each smart home jointly optimizes the comfort maintenance, the energy cost and the community energy efficiency based on renewable generation, temperature dynamics, and grid prices. We propose a marketbased energy exchange mechanism with dynamic price setting and two complementary methods (threshold-based and rewardbased) to mitigate market manipulation in P2P energy trading. To enable decentralized coordination inside the energy community, the multi-agent Deep Reinforcement Learning (DRL) with actorcritic architecture is proposed to ensure the continuous and adaptive control of indoor temperature systems, battery storage, and price setting using real-world market prices and energy consumption data. The quantitative validation across multiple homes demonstrates a 39.3% reduction in grid dependency of the reward-based mechanism compared to unregulated trading. The framework maintains indoor temperatures consistently within comfort bounds while enabling intelligent battery management that adapts to price fluctuations, with state-of-charge levels peaking at 85% during low-price periods and decreasing to 40% during high-demand intervals. Overall, the approach establishes a self-sustaining energy ecosystem within residential communities, balancing market integrity and operational efficiency.

Featured Projects

Practical applications of my research in AI/ML, 6G networks, and smart systems.

View All Projects

Multi-Agent Energy Management System

Developed a distributed energy management simulation framework modeling multiple household HVAC systems and storage units. The system employs reinforcement learning algorithms to optimize energy distribution across the network while maintaining temperature constraints, featuring price-based coordination mechanisms between local agents and a central orchestrator for efficient grid interaction.

PythonPyTorchDRL

COMIX: Conflict Management in O-RAN

Developed a generalized conflict management framework for multi-channel power control in O-RAN xApps. The project implements DRL-based solutions for optimizing network power control and energy efficiency, featuring an evaluation framework using Network Digital Twin (NDT) that achieved significant energy savings.

PythonDeep LearningO-RAN

SnakeAI-DQN

This project implements a Deep Q-Network (DQN) to train an AI agent to play the classic Snake game. The agent learns to play the game by interacting with the environment, observing the state, and learning from rewards and penalties. The implementation uses PyTorch for the neural network, Gym for the environment interface, and Pygame for rendering the game.

PythonPyTorchGym

Let's Connect

I welcome the opportunity to engage in thoughtful discussions in AI/ML, 6G networks, and smart systems. Whether it’s sharing insights, contributing to research, or exploring industry developments, I look forward to connecting with professionals in these fields. Please feel free to reach out.

Contact Me