%0 Conference Paper %B The 36th International Conference on Advanced Information Networking and Applications (AINA – 2022), April 13 - 15, 2022, Sydney, Australia %D 2022 %T Applying Machine Learning and Dynamic Resource Allocation Techniques in Fifth Generation Networks %A Christos Bouras %A Evangelos Michos %A Ioannis Prokopiou %X According to Internet of Things (IoT) Analytics, soon, the online devices in IoT networks will range from 25 up to 50 billion. Thus, it is expected that IoT will require more effective and efficient analysis methods than ever before with the use of Machine Learning (ML) powered by Fifth Generation (5G) networks. In this paper, we incorporate the K-means algorithm inside a 5G network infrastructure to better associate devices with Base Stations (BSs). We use multiple datasets consisting of user distribution in our area of focus and propose a Dynamic Resource Allocation (DRA) technique to learn their movement and predict the optimal position, RB usage and optimize their resource allocation. Users can experience significantly higher data rates and extended coverage with minimized interference and in fact, the DRA mechanism can mitigate the need for small cell infrastructure and prove a cost-effective solution, due to the resources transferred within the network. %B The 36th International Conference on Advanced Information Networking and Applications (AINA – 2022), April 13 - 15, 2022, Sydney, Australia %V 1 %P 662-673 %G eng %0 Book Section %B Advances in Engineering Research, Nova Science Publishers %D 2022 %T An Introduction of Upcoming Radio Resource Management Techniques for 5G Networks %A Christos Bouras %A Vasileios Kokkinos %A Apostolos Gkamas %A Evangelos Michos %A Ioannis Sina %A Ioannis Prokopiou %A Foivos Allayiotis %X 5G networks are the next generation of mobile internet connectivity, that are able to offer vastly increased speeds, more reliable connections, minimal latency and more supported devices. 5G networks are expected to supercharge Internet of Things (IoT) technology, so as to provide the infrastructure needed in order to support and transfer large data amounts that will enable a smarter and more connected world. To this direction, 5G incorporates many technologies and mechanisms that aid towards the overall goal, such as Multiple-Input and Multiple-Output (MIMO), Downlink (DL) and Uplink (UL) Decoupling (DUDe) and Machine Learning (ML). These technologies can significantly help towards more efficient resource allocation inside the next generation networks, offering increased spectral efficiency and data rates, better signal coverage, reduced latencies and many more. In this chapter, we will provide insights over the aforementioned technologies through firstly a literature review and later on by analyzing their architecture and their models. We will explain how these technologies can be taken advantage of in order to support the 5G networks and why they are core components of future networks, as it is expected that also 5G and Beyond networks will capitalize on them. %B Advances in Engineering Research, Nova Science Publishers %V 46 %P 147-188 %G eng %& 3 %0 Conference Paper %B The Eighteenth International Conference on Wireless and Mobile Communications (ICWMC 2022), May 22 – 26, 2022, Venice, Italy %D 2022 %T Performance Analysis of MIMO using Machine Learning in 5G Networks %A Christos Bouras %A Ioannis Prokopiou %A Apostolos Gkamas %A Vasileios Kokkinos %X Massive Multiple-Input Multiple-output (MIMO) is an important radio antenna technology for mobile wireless networks, such as 5th Generation (5G) with high potential. The use of hybrid analog and digital precoding to minimize the energy consumption as well as the hardware complexity of mixed signal components is an essential strategy. Machine Learning (ML) could be able to boost 5G technologies due to the rising difficulty of configuring cellular networks. More than ever, a ML computational framework focused on successfully processing the expected huge data generated normally by 5G networks with high subscriber cell density, is required. In the Ultra-Dense Networks (UDNs) of 5G and beyond high demanding networks paired with beamforming and massive MIMO technologies, ML struggles to define network traffic aspects distinctively, especially when they are projected to be much more dynamic and complicated. This paper presents a state-of-the-art analysis of the combined and multiple uses of ML along with MIMO technology in 5G Networks. %B The Eighteenth International Conference on Wireless and Mobile Communications (ICWMC 2022), May 22 – 26, 2022, Venice, Italy %G eng