Nikolaos Prodromos
Short CV: Nikolaos P. Prodromos was born in the city of Patras in 2001 and graduated(with honours) in 2019 from the 13th Lyceum of Patras. He is currently a Student (on the 4th year) at the Computer Engineering and Informatics Department of the University of Patras.His Research Interests include 5th generation mobile telecommunications networks, resource allocation and machine learning. He also took part (as a conferrer) in the 3rd Panellenic Conference «Education through games and art in education and culture»(Athens, 5-6 November 2022). The topic of his paper was : «Digital technologies as a tool and learning enviroment in today’s school : The Podcasting case». A paper that was requested for publishing, by the Journal of Modern Education Review(NY,USA) (ISSN 2155-7993).
Conferences
Diasakos, Damianos; Prodromos, Nikolaos; Gkamas, Apostolos; Kokkinos, Vasileios; Bouras, Christos; Pouyioutas, Philippos
Distinguishing Signal from Noise in 5G MIMO Systems Using Generative Adversarial Networks Conference
2th International Conference on New Technologies, Mobility and Security, June 18 – 20, 2025, Paris, France, 2025, (To appear).
Abstract | Links | BibTeX | Tags:
@conference{,
title = {Distinguishing Signal from Noise in 5G MIMO Systems Using Generative Adversarial Networks},
author = {Damianos Diasakos and Nikolaos Prodromos and Apostolos Gkamas and Vasileios Kokkinos and Christos Bouras and Philippos Pouyioutas },
url = {https://telematics.upatras.gr/2025127023/},
year = {2025},
date = {2025-06-18},
urldate = {2025-06-18},
booktitle = {2th International Conference on New Technologies, Mobility and Security, June 18 – 20, 2025},
address = {Paris, France},
abstract = {In recent years, Generative Adversarial Networks (GANs) have emerged as powerful tools for improving signal processing in advanced communication systems, particularly in the context of 5G networks. In this paper, we present a novel approach for distinguishing signal from noise in 5G Multiple Input Multiple Output (MIMO) systems using GANs. Our method leverages the generative capabilities of GANs to
produce realistic noise signals and the discriminative power of GANs to accurately identify real signals amidst noise. By training the GAN on a combination of real-world noisy signals and pure noise, our model achieves robust signal detection and classification. We evaluate our approach using synthetic data, demonstrating significant improvements over other techniques such as the autoencoders. Our results highlight the potential of GANs in enhancing the reliability and performance of 5G MIMO communications.},
note = {To appear},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
In recent years, Generative Adversarial Networks (GANs) have emerged as powerful tools for improving signal processing in advanced communication systems, particularly in the context of 5G networks. In this paper, we present a novel approach for distinguishing signal from noise in 5G Multiple Input Multiple Output (MIMO) systems using GANs. Our method leverages the generative capabilities of GANs to
produce realistic noise signals and the discriminative power of GANs to accurately identify real signals amidst noise. By training the GAN on a combination of real-world noisy signals and pure noise, our model achieves robust signal detection and classification. We evaluate our approach using synthetic data, demonstrating significant improvements over other techniques such as the autoencoders. Our results highlight the potential of GANs in enhancing the reliability and performance of 5G MIMO communications.
produce realistic noise signals and the discriminative power of GANs to accurately identify real signals amidst noise. By training the GAN on a combination of real-world noisy signals and pure noise, our model achieves robust signal detection and classification. We evaluate our approach using synthetic data, demonstrating significant improvements over other techniques such as the autoencoders. Our results highlight the potential of GANs in enhancing the reliability and performance of 5G MIMO communications.
Diasakos, Damianos; Prodromos, Nikolaos; Gkamas, Apostolos; Kokkinos, Vasileios; Bouras, Christos; Pouyioutas, Philippos
A Reinforcement Learning Approach On Self – Optimizing Heterogeneous Networks Conference
9th IEEE Symposium on Computers and Communications (ISCC 2025), July 2 – 5, 2025, Bologna, Italy, 2025, (to appear).
Abstract | Links | BibTeX | Tags:
@conference{nokey,
title = {A Reinforcement Learning Approach On Self – Optimizing Heterogeneous Networks},
author = {Damianos Diasakos and Nikolaos Prodromos and Apostolos Gkamas and Vasileios Kokkinos and Christos Bouras and Philippos Pouyioutas },
url = {https://telematics.upatras.gr/2025125721/},
year = {2025},
date = {2025-06-02},
urldate = {2025-06-02},
booktitle = {9th IEEE Symposium on Computers and Communications (ISCC 2025), July 2 – 5, 2025},
address = {Bologna, Italy},
abstract = {This paper presents a reinforcement learningbased approach for optimizing the performance of 5G mobile networks. By leveraging Deep Q-Networks (DQN), our system autonomously tunes network parameters across macro, micro, and pico cells, adapting to the dynamic distribution in a heterogeneous network environment. The agent is tasked with optimizing several Key Performance Indicators (KPIs) such as throughput, latency, interference, and Quality of Service (QoS). Each cell in the network can perform actions such as adjusting power levels, changing handover thresholds, allocating bandwidth, and performing interference mitigation. Our approach demonstrates significant improvements in user experience, resource utilization, and network efficiency over traditional static optimization methods. The results show that the proposed reinforcement learning -based algorithm not only reduces latency and interference but also ensures better load balancing and throughput optimization across heterogeneous cells.
},
note = {to appear},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
This paper presents a reinforcement learningbased approach for optimizing the performance of 5G mobile networks. By leveraging Deep Q-Networks (DQN), our system autonomously tunes network parameters across macro, micro, and pico cells, adapting to the dynamic distribution in a heterogeneous network environment. The agent is tasked with optimizing several Key Performance Indicators (KPIs) such as throughput, latency, interference, and Quality of Service (QoS). Each cell in the network can perform actions such as adjusting power levels, changing handover thresholds, allocating bandwidth, and performing interference mitigation. Our approach demonstrates significant improvements in user experience, resource utilization, and network efficiency over traditional static optimization methods. The results show that the proposed reinforcement learning -based algorithm not only reduces latency and interference but also ensures better load balancing and throughput optimization across heterogeneous cells.
Bouras, Christos; Diasakos, Damianos; Gkamas, Apostolos; Kokkinos, Vasileios; Pouyioutas, Philippos; Prodromos, Nikolaos
Simulation – based Beamforming Optimization in Moving Drones Conference
15th IFIP Wireless and Mobile Computing (IFIP WMNC), November 11 – 12, 2024, Venice, Italy, pp 1-6 (to appear) , 2024.
Abstract | Links | BibTeX | Tags:
@conference{nokeyc,
title = {Simulation – based Beamforming Optimization in Moving Drones},
author = {Christos Bouras and Damianos Diasakos and Apostolos Gkamas and Vasileios Kokkinos and Philippos Pouyioutas and Nikolaos Prodromos},
url = {https://telematics.upatras.gr/simulation-based_beamforming_optimization_in_moving_drones/},
year = {2024},
date = {2024-11-12},
urldate = {2024-11-12},
booktitle = {15th IFIP Wireless and Mobile Computing (IFIP WMNC), November 11 – 12, 2024, Venice, Italy, pp 1-6 (to appear)
},
pages = {1 - 6},
abstract = {The integration of drone technology with 5G networks presents novel opportunities for enhancing wireless communication systems. This paper explores the application of beamforming optimization techniques in dynamic environments, specifically focusing on moving drones in a simulated environment based on the DeepMIMO O1 scenario. By leveraging the unique properties of the O1 drone setup of DeepMIMO simulation environment, which simulates realistic urban mobility patterns at millimeter-wave (mmWave) frequencies, we propose a novel beamforming algorithm designed to optimize the signal quality and stability in highly mobile aerial networks. Key performance metrics used in this study include Signal-to-Noise Ratio (SNR), battery consumption, and power consumption of both the drones and the base station. Our findings indicate that the adaptive beamforming algorithm not only enhances the SNR and reduces power consumption but also optimizes battery usage compared
to conventional beamforming methods. This study enhances the understanding of mmWave beamforming dynamics in aerial scenarios but also lays the groundwork for future advancements
in drone-based communication networks.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
The integration of drone technology with 5G networks presents novel opportunities for enhancing wireless communication systems. This paper explores the application of beamforming optimization techniques in dynamic environments, specifically focusing on moving drones in a simulated environment based on the DeepMIMO O1 scenario. By leveraging the unique properties of the O1 drone setup of DeepMIMO simulation environment, which simulates realistic urban mobility patterns at millimeter-wave (mmWave) frequencies, we propose a novel beamforming algorithm designed to optimize the signal quality and stability in highly mobile aerial networks. Key performance metrics used in this study include Signal-to-Noise Ratio (SNR), battery consumption, and power consumption of both the drones and the base station. Our findings indicate that the adaptive beamforming algorithm not only enhances the SNR and reduces power consumption but also optimizes battery usage compared
to conventional beamforming methods. This study enhances the understanding of mmWave beamforming dynamics in aerial scenarios but also lays the groundwork for future advancements
in drone-based communication networks.
to conventional beamforming methods. This study enhances the understanding of mmWave beamforming dynamics in aerial scenarios but also lays the groundwork for future advancements
in drone-based communication networks.
Prodromos, Nikolaos; Diasakos, Damianos; Kokkinos, Vasileios; Gkamas, Apostolos; Pouyioutas, Philippos; Bouras, Christos
Optimizing Network Slices: A Comparative Analysis of Allocation Algorithms for 5G Environments Conference
2024 International Conference on Future Communications and Networks (FCN 2024), November 18 - 22, 2024, Valetta, Malta (to appear), no. 1- 6, 2024.
Abstract | Links | BibTeX | Tags:
@conference{nokeyb,
title = {Optimizing Network Slices: A Comparative Analysis of Allocation Algorithms for 5G Environments},
author = {Nikolaos Prodromos and Damianos Diasakos and Vasileios Kokkinos and Apostolos Gkamas and Philippos Pouyioutas and Christos Bouras},
url = {https://telematics.upatras.gr/fcn2024_camera_ready-1/},
year = {2024},
date = {2024-09-30},
urldate = {2024-09-30},
booktitle = {2024 International Conference on Future Communications and Networks (FCN 2024), November 18 - 22, 2024, Valetta, Malta (to appear)},
number = {1- 6},
abstract = {In the realm of 5G networking, the optimization of user allocation through network slicing stands as a critical challenge, with the potential to substantially enhance the Quality of Service (QoS). This study examines three AI-based allocation algorithms—Simulated Annealing, which begins with a Randomized algorithm, Greedy, and Local Search with Hill Climbing—to efficiently distribute network resources. Next, we compare the algorithms for different user densities to understand how well each one can handle the situation at hand in terms of balance in allocation, consumption (time and memory) and complexity. Our research advances beyond conventional allocation techniques by offering different solutions for different needs thus improving QoS through the alignment of user demands with network capacity.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
In the realm of 5G networking, the optimization of user allocation through network slicing stands as a critical challenge, with the potential to substantially enhance the Quality of Service (QoS). This study examines three AI-based allocation algorithms—Simulated Annealing, which begins with a Randomized algorithm, Greedy, and Local Search with Hill Climbing—to efficiently distribute network resources. Next, we compare the algorithms for different user densities to understand how well each one can handle the situation at hand in terms of balance in allocation, consumption (time and memory) and complexity. Our research advances beyond conventional allocation techniques by offering different solutions for different needs thus improving QoS through the alignment of user demands with network capacity.
Prodromos, Nikolaos; Diasakos, Damianos; Kokkinos, Vasileios; Gkamas, Apostolos; Bouras, Christos; Pouyioutas, Philippos
Dynamic Bandwidth Allocation in MIMO 5G Networks Conference
The 20th International Wireless Communications & Mobile Computing Conference (IWCMC 2024), May 27 – 31, 2024, Ayia Napa, Cyprus, 2024.
Abstract | Links | BibTeX | Tags:
@conference{4662,
title = {Dynamic Bandwidth Allocation in MIMO 5G Networks},
author = {Nikolaos Prodromos and Damianos Diasakos and Vasileios Kokkinos and Apostolos Gkamas and Christos Bouras and Philippos Pouyioutas},
url = {https://telematics.upatras.gr/wp-content/uploads/2024/06/IWCMC2024_CR.pdf},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
booktitle = {The 20th International Wireless Communications & Mobile Computing Conference (IWCMC 2024), May 27 – 31, 2024, Ayia Napa, Cyprus},
pages = {97 - 102},
abstract = {The advent of 5G technology has ushered in a new era of wireless communication, characterized by its promise of high data rates, low latency, and enhanced connectivity. In this context, Multiple-Input Multiple-Output (MIMO) systems have emerged as a key enabler, leveraging advanced antenna arrays to simultaneously serve multiple users with increased spectral efficiency. This paper investigates the dynamic resource allocation problem in a MIMO 5G environment, where each user possesses distinct bandwidth requirements. The focus is on optimizing user allocation while considering the limited bandwidth and user capacity of base stations. By harnessing the
power of deep learning techniques, the proposed solution aims to efficiently manage the allocation of users to base station antennas, thereby maximizing overall network performance while accommodating heterogeneous user demands.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
The advent of 5G technology has ushered in a new era of wireless communication, characterized by its promise of high data rates, low latency, and enhanced connectivity. In this context, Multiple-Input Multiple-Output (MIMO) systems have emerged as a key enabler, leveraging advanced antenna arrays to simultaneously serve multiple users with increased spectral efficiency. This paper investigates the dynamic resource allocation problem in a MIMO 5G environment, where each user possesses distinct bandwidth requirements. The focus is on optimizing user allocation while considering the limited bandwidth and user capacity of base stations. By harnessing the
power of deep learning techniques, the proposed solution aims to efficiently manage the allocation of users to base station antennas, thereby maximizing overall network performance while accommodating heterogeneous user demands.
power of deep learning techniques, the proposed solution aims to efficiently manage the allocation of users to base station antennas, thereby maximizing overall network performance while accommodating heterogeneous user demands.