Abstract of doctoral thesis Pentaris Fragkiskos

Next generations (5G, 6G) wireless communication networks, are going to cover the different service requirements in many fields of human daily life, in work, transports, leisure, home. Design and optimization of these networks becomes very challenging because of high requirements of efficiency, user experience, performance and network complexity [1]. The future 5G network will require robust intelligent algorithms to adapt network protocols and resource management for different services in different scenarios. Artificial intelligence (AI), which is defined as any process or device that perceives its environment and take actions that maximize the chances of success for some predefined goal, is a feasible solution for the emerging complex communication system design. The recent advances in deep learning, convolutional neural networks and reinforcement learning hold significant promise for solving very complex problems considered intractable until now. It is now appropriate to apply AI technology to 5G wireless communications to tackle optimized physical layer design, complicated decision making, network management and resource optimization tasks in such networks. Improvement of spectral and energy efficiency is a necessity for new communication technologies. Wireless networks of sixth generation (6G) will be driven by on-demand self-reconfiguration in order to obtain many-fold increase in the network performance and service types [2]. Author Gao et. Al [3] refers that high speed and wide capacity of 5G technology can be achieved by Massive MIMO technology that demands intelligence tools.High demand of wireless data traffic creates quickly rising technical requirements. In order to face these coming challenges, 6G wireless communication is expected to post high technical standard in terms of spectrum and energy-efficiency transmission techniques [4]. Also literature [5-7], reveals that, in order to ensure high requirements of new wireless technologies,artificial intelligence is essential, for the efficient management of high data rates, high reliability and low latency.

This research aims to improve via Artificial Intelligence (AI) RF parameters such as the bandwidth of the transmission channels, the sensitivity of the antennas and the spectrum monitoring, in order to meet high requirements on new communication technologies.

According to above research aim, AI key objectives of this research could include a) design of deep-learning and convolutional neural network approaches for wireless system applications and services, b) design of machine-learning and pattern recognition algorithms for wireless communication technologies, c) applications of AI for optimizing wireless communication systems, including channel models, channel state estimation, beamforming, signal processing.