Search

A graph neural network (GNN) based access point (AP) selection algorithm for cell-free mas-sive multiple-input multiple-output (MIMO) systems is proposed. Two graphs, a homogeneous graph which includes only AP nodes representing the structure of the APs in the network, and a heterogeneous graph which includes both AP nodes and user equipment (UE) nodes are constructed to represent a cell-free massive MIMO network. A GNN based on the inductive graph learning framework GraphSAGE is used to obtain the embed-dings which are then used to predict the links between the nodes. The numerical results show that compared to the proximity-based AP selection algorithms, the proposed GNN based algorithm predicts the potential APs with more accuracy. Compared to the large scale fading coefficient based AP selection algorithms, the proposed algorithm does not require measured and sorted signal strengths of all the neighbouring APs. Furthermore, the proposed algorithm is scalable in terms of the number of users in the cell-free system.

How to meet the demand for increasing number of users, higher data rates, and stringent quality-of-service (QoS) in the beyond fifth-generation (B5G) networks? Cell-free massive multiple-input multiple-output (MIMO) is considered as a promising solution, in which many wireless access points cooperate to jointly serve the users by exploiting coherent signal processing. However, there are still many unsolved practical issues in cell-free massive MIMO systems, whereof scalable massive access implementation is one of the most vital. In this paper, we propose a new framework for structured massive access in cell-free massive MIMO systems, which comprises one initial access algorithm, a partial large-scale fading decoding (P-LSFD) strategy, two pilot assignment schemes, and one fractional power control policy. New closed-form spectral efficiency (SE) expressions with maximum ratio (MR) combining are derived. The simulation results show that our proposed framework provides high SE when using local partial minimum mean-square error (LP-MMSE) and MR combining. Specifically, the proposed initial access algorithm and pilot assignment schemes outperform their corresponding benchmarks, P-LSFD achieves scalability with a negligible performance loss compared to the conventional optimal large-scale fading decoding (LSFD), and scalable fractional power control provides a controllable trade-off between user fairness and the average SE., QC 20220615

This paper focuses on a heterogeneous scenario in which cellular and wireless local area technologies coexist and in which mobile devices are enabled with device-to-device communication capabilities. In this context, this paper assumes a network architecture in which a given user equipment (UE) can receive mobile service either by connecting directly to a cellular base station or by connecting through another UE that acts as an access point and relays the traffic from a cellular base station. The paper investigates the optimization of the connectivity of different UEs with the target to minimize the total transmission power. An optimization framework is presented, and a distributed strategy based on Q-learning and softmax decision making is proposed as a means to solve the considered problem with reduced complexity. The proposed strategy is evaluated under different conditions, and it is shown that the strategy achieves a performance very close to the optimum. Moreover, significant transmission power reductions of approximately 40% are obtained with respect to the classical approach, in which all UEs are connected to the cellular infrastructure. For multi-cell scenarios, in which the optimum solution cannot be easily known a priori, the proposed approach is compared against a centralized genetic algorithm. The proposed approach achieves similar performance in terms of total transmitted power, while exhibiting much lower computational requirements., Peer Reviewed, Postprint (author's final draft)

In traditional infrastructural wireless local area network (WLAN), the mobile node (MN) makes the decision of choosing an access point (AP). The MN creates a list of APs in range along with the received signal strength indicator (RSSI). It then solely uses the RSSI as a decision metric for selecting an AP to connect to as this is the only information available at the MN. We argue that a MN is not the correct entity in WLAN for making the choice of an AP when many APs are available as it does not have the complete view of the environment. Secondly, choosing an AP solely on the basis of RSSI is not an efficient algorithm. This can lead to concentration of MNs at single AP resulting in a decreased average throughput for every MN associated to that AP. In this thesis, we propose to transfer this decision to the AP in a transparent manner. While our solution exists for single administrative domain with a centralized controller, we propose a completely distributed architecture for personal WLANs where APs select to serve MNs based on the MN concentration, network load, throughput and effect of serving a new MN on the network. The APs in different networks collaborate among one another in a completely decentralized manner to provide unified network access to MNs with focus on maximizing the system capacity. The broadcast nature of wireless is used in an intelligent manner to select dynamic uplink and downlink paths between APs and MNs.