ABSTRACT The increasing demand for ultra‐reliable, low‐latency, and high‐throughput connectivity in dense urban environments presents significant challenges for next‐generation 6G networks. Traditional cellular networks, with their fixed cell boundaries and centralized base station control, are inadequate to meet the dynamic needs of such environments. A promising solution is the cell‐free network architecture, where a distributed set of access points (APs) jointly serve users without fixed cell boundaries. However, efficient access point selection and accurate user localization are crucial to achieving high performance in such networks. This paper presents a decentralized approach using Belief‐Desire‐Intention eXtended (BDIx) agents for dynamic AP selection and localization within a cluster‐based cell‐free 6G communications network. Various clustering algorithms (K‐means, DBSCAN, self‐organizing maps, MeanShift, ClusterGAN, and Autoencoders) are evaluated for their ability to optimize network throughput, energy efficiency, and spectral utilization. A hybrid localization framework, such as centroid‐based, differential circles, and multilateration methods, is employed to achieve accurate user positioning. The results demonstrate that machine learning‐based clustering methods, notably Gaussian mixture model (GMM), self‐organizing map (SOM), and ClusterGAN, offer significant improvements in throughput (up to 46.3%) and power reduction (up to 32.8%) over traditional methods. Regarding localization, deep learning models such as MLP, CNN, and TCN outperform deterministic methods, achieving sub‐meter accuracy with minimal errors (MeanDist < 1 m, > 0.999). Overall, the proposed solution enhances system scalability, energy efficiency, and positioning accuracy, establishing a promising foundation for future 6G networks. In our reference implementation, we instantiate the pipeline with a GMM for AP/UE clustering and a multilayer perceptron (MLP) regressor for localization.

Hospitals are rightfully considered a field of indoor logistic robotics of high commercial potential. However, today, only a handful of mobile robotic solutions for hospital logistics exist that have failed to trigger widespread acceptance by the market. This is because existing systems require costly infrastructure installation, they do not easily integrate to corporate IT solutions, are not adequately shielded from cybersecurity threats, and as a result, they do not fully automate procedures and traceability of the items they carry. Moreover, existing systems are limited on scope, focusing only on delivery services, and hence do not provide any other type of support to the medical and nursing staff. ENDORSE system will address the aforementioned technical challenges and functional limitations by pursuing four innovation pillars: (i) infrastructure-less multi-robot indoor navigation; (ii) advanced Human-Robot Interaction (HRI) for resolving deadlocks and achieving efficient sharing of space resources in crowded environments; (iii) deployment of the ENDORSE software as a cloud-based service facilitating its integration with corporate software solutions, complying with GDPR data security requirements; (iv) reconfigurable and modular hardware architectures so that diverse modules can be easily swapped. ENDORSE functionality will be demonstrated via the integration of an e-diagnostic support module for vital signs monitoring on a fleet of mobile robots, facilitating connectivity to cloud-based Electronic Health Records (EHR), and validated in an operational hospital environment for realistic assessment.

5G will require a number of Key Technological Components to meet its very ambitious goals, including Heterogeneous Networks a nd Small Cells. The Dense Deployme nt of Small Cell Base Stations (SBSs) will play a major role as they can be installed in a more targeted manner to relieve traffic in hot spot areas, increase coverage, and spectral efficiency. However, the current deployment of the SBS is static (examples include Femto, Pico, and Nano cells), normally deployed on demand around hotspots. In the scenario of unpredictable crowd movement, these static deployment of small cell can be inefficient with high CAPEX and OPEX. This paper focuses on the scenario where UE-based Virtual Small Cell Base Stations (UE-VBSs) can be dynamically selected among UEs to deal effectively with the non-stationary, non-uniform distribution of mobile traffic with respect to time and space domain. To implement this concept, we propose an efficient clustering technique (Affinity Propagation Clustering) to select the best set of UE-VBSs to supplement an overlay loaded SBS. Simulative evaluation highlights salient features of the technique, as well as its limitations with regard to scalability. Further, we discuss the modification of the algorithm according to our objec tive sc enario focusing on red ucing the message passing procedure to and from only a number of eligible UE-VBSs using the power received by a UE from the eligible UE-VBSs as a parameter. The algorithm is implemented and evaluated in MATLAB and, also validated using NS3 simulator.

This paper proposes the Cella Ecosystem (CelEc) concept for emerging 5G ultra dense Networks, to evolve and supplement the Mobile Radio Network by using the crowd's User Equipments (UEs), densely distributed in our physical world and environment, as an integral part of the Infrastructure. Towards this end, CelEc establishes a decentralized ecosystem (the CelEc Tier) of numerous, unbound and ubiquitous networking and computing elements offering their networking functionalities and computing and storage resources to bridge coverage gaps, supplement capacity, increase data rates, and boost computing, whenever the Network is stressed. This is in the same spirit as the introduction of smaller sized cells throughout the evolution of mobile telephony, to maximize spectrum resource efficiency. Specifically CelEc, by enhancing the UEs with eNodeB's functionalities and additional networking operation functions, realises the smallest, portable, and reconfigurable cells (i.e., the Cella cells) allowing for dynamic massive deployment, and enables the efficient flows of data, whenever and wherever needed. As such CelEc provides for a dynamic reconfiguration of the Mobile Network infrastructure, in an effortless, costless (in terms of CAPEX) and flexible manner, hence removing the restrains of existing Small Cells beyond their static positioning. A preliminary evaluation of some of the ideas discussed in this paper for CelEc, showed among others, scalable massive mobile support, and significant improvements on the overall capacity, data rates, energy and spectral efficiency, as envisioned for 5G.

As currently specified by 3GPP, MBMS services can be provided in a cell either by point-to-point (PtP) or point-to-multipoint (PtM) transmission mode, but not both at the same time. With PtP transmission mode, one dedicated channel (DCH) is established for each MBMS user within the cell. With PtM transmission mode one forward access channel (FACH) is established, covering the whole cellpsilas area and commonly shared by all the MBMS users within. In this paper we describe the existing 3GPP MBMS service provision approach, highlight its deficiencies, and propose a new approach to address them. To achieve this we introduce the ldquodual transmission mode cellsrdquo in which PtP and PtM transmissions can coexist and where FACHpsilas coverage range can be dynamically adapted (shrink or expand) through time based on the MBMS userspsila location within the cell. The performance evaluation performed, showed that our approach outperforms the existing 3GPP approach in terms of capacity, signaling and processing effort efficiency.

With MBMS, a mobile terminal (MT) that is on the move and receive an MBMS service may have to handover from a common to a dedicated channel when crossing the cellpsilas edge. In previous work, we highlighted the possible inefficiencies which might arise if the existing 3GPP handover control approach is adopted to execute these types of handovers and proposed a specific MBMS handover control approach that compensated for them. This approach, although effective in terms of capacity and QoS, was not very viable. Thus in this paper, using a different approach, we enhance previous work in order to address its deficiencies and make the whole solution practical. The performance evaluation showed that our enhanced proposed approach even with the enhancements made simplifying the whole handover procedure, still outperforms the existing 3GPP handover control approach in terms of capacity and QoS efficiency.

MBMS bearer services can be provided in each cell by either point-to-point or point-to-multipoint transmission mode but for efficiency a decision has to be made between the two approaches. Initially, the fundamental criterion used to make this decision was the number of MBMS users in a cell (UE counting). In this paper we extend our previous work, which proposed the power transmitted by the base station (BS) as the channel switching criterion (power counting). We evaluate our approach and illustrate its capability to dynamically adapt to continuously varying cell conditions by selecting the transmission mode in a more efficient way, preserving in this way the networkpsilas resources. At the same time we demonstrate the limitations of the conventional approach, in terms of radio resource efficiency. We show that by having the power used by the BS as the limiting factor we achieve optimized capacity during the transmission of MBMS bearer services in UTRAN.

Handover Control is one of the essential means to guarantee the continuity of mobile services to a user traveling in a cellular infrastructure, without interruption. In previous work we illustrated that using the current 3GPP specified handover control algorithm to provide continuity of MBMS (Multimedia Broadcast Multicast Service) services to a user crossing cell boundaries results either in capacity or QoS inefficiencies and proposed a new MEHO (Mobile Evaluated Handover) based MBMS handover control algorithm that compensated for them. This algorithm, although effective in terms of capacity and QoS, has some limitations concerning the way certain parameters vital for the efficient MBMS handover execution are estimated. In this paper, using a different approach (Network Evaluated Handover (NEHO)), we enhance previous work and propose a different method, that eliminates all of its predecessorpsilas deficiencies while achieving the same capacity and QoS efficiencies.

As currently specified by 3GPP, MBMS (multimedia broadcast multicast service) content can be provided in a cell by either point-to-point (P-t-P) or point-to-multipoint (P-t-M) transmission mode, but not both at the same time. In earlier work we highlighted the deficiencies of the current approach and proposed the concept of the ldquodual transmission mode cellrdquo, in which P-t-P (DCH) and P-t-M (FACH) transmissions can coexist and allowed to dynamically adapt through time, to address them. In this paper we further analyze the deficiencies of the current 3GPP approach and enhance our previous work to efficiently address the problem in high mobility scenarios as well. The proposed algorithm takes into consideration both the distribution and the movement of the MBMS userspsila within the cell (using the CPICH Ec/No signal strength as a reference) and dynamically decides which MBMS users should be served using FACH and which should be served using DCH. Simulation results show significant transmission power savings, considerable reduction on the aggregated signaling and processing effort introduced, while QoS requirements are still fulfilled.

Handover Control in a cellular infrastructure aims to provide continuity of mobile services to a user traveling over cell boundaries. So far, Handover Control is considered only between cells supporting the service using Dedicated Resources and the handover decision making is based on a comparison between an observed signal strength value and a predetermined threshold chosen in a manner so as to maximize the overall system capacity. With the introduction of Multimedia Broadcast Multicast Service (MBMS), for radio efficiency reasons, one cell can use either Common or Dedicated resources for the distribution of the same content in a Cell. Thus, the mobile users that are on the move may have to deal with dynamic changes of network resources when crossing the cell edge, introducing new types of handovers (MBMS Handovers). Using the current Handover Algorithm when an MBMS Handover is executing will not be so efficient. For the efficient execution of these new types of handover a different approach has to be followed. This paper proposes a new Handover Algorithm which efficiently maximizes the overall system capacity when mobile MBMS users have to deal with these new types of handovers.

With the introduction of Multimedia Broadcast Multicast Service (MBMS) in 3rd Generation (3G) Networks, the Radio Network Controller (RNC) for radio efficiency reasons can use either Dedicated or Common resources to distribute the same content in a Cell. Thus the mobile users that are on the move may have to deal with dynamic changes of network resources when crossing the cell edge, introducing new types of handovers (MBMS Handovers). Executing an MBMS Handover using the current Handover Algorithm will result in inefficiencies. Therefore, for efficient execution of these new types of handover a different approach has to be followed. This paper proposes a new Handover Algorithm which efficiently maximizes the overall system capacity when mobile MBMS users have to deal with these new types of handovers.