In the user-centric cell-free massive MIMO (UC-mMIMO) network scheme, user mobility necessitates updating the set of serving access points to maintain the user-centric clustering. Such updates are typically performed through handoff (HO) operations; however, frequent HOs lead to overheads associated with the allocation and release of resources. This paper presents a deep reinforcement learning (DRL)-based solution to predict and manage these connections for mobile users. Our solution employs the Soft Actor-Critic algorithm, with continuous action space representation, to train a deep neural network to serve as the HO policy. We present a novel proposition for a reward function that integrates a HO penalty in order to balance the attainable rate and the associated overhead related to HOs. We develop two variants of our system; the first one uses mobility direction-assisted (DA) observations that are based on the user movement pattern, while the second one uses history-assisted (HA) observations that are based on the history of the large-scale fading (LSF). Simulation results show that our DRL-based continuous action space approach is more scalable than discrete space counterpart, and that our derived HO policy automatically learns to gather HOs in specific time slots to minimize the overhead of initiating HOs. Our solution can also operate in real time with a response time less than 0.4 ms.

In 5G cellular networks, Machine Learning (ML) can be exploited to predict if a user equipment (UE) is in the coverage area of a neighbouring cell. This could improve crucial cellular network functionalities, such as handovers, interference mitigation and carrier aggregation. In this paper, we study the enhancement of UEs’ privacy in a Differentially Private-Federated Learning (DP-FL) scheme relying on the sampled Gaussian mechanism, assuming honest-but-curious threat model. With this technique, the UE’s privacy is protected by perturbing the averaged updates conducted at the server; also, the usage of client subsampling results in an amplified privacy and a reduced overhead in terms of communication. We demonstrate that the models trained with our approach can achieve better privacy-utility tradeoff than previous works can. In addition, we conduct membership inference attack to study the factors that impact the empirical privacy protection to the training data. We make a novel observation that suggests that for coverage prediction task, larger datasets and/or smaller ML models would provide stronger empirical privacy protection to training data. Beyond the task we consider, this observation could be a useful insight for dataset curation or model architecture selection in other domains and warrants additional investigation.

In this paper, a downlink wireless communication channel is considered. The base station (BS) has common data for all users, unicast data for a set of intended users, and transmits the superposition of these messages. This setting neither falls into the non-orthogonal multiple access (NOMA) nor into the multi-group multicasting literatures. In NOMA systems, the BS has unicast data for all users, and multiple users share the same resources. In multi-group multicasting, there are non-overlapping groups, each demanding a different multicast message. This paper studies precoder design to achieve maximum weighted sum rate (WSR). It is first shown that the precoders designed for WSR maximization and weighted minimum mean square error (WMMSE) minimization are equivalent. Second, an iterative low complexity algorithm (named WMMSE), based on WMMSE transmit precoders and receivers, is proposed. Another low-complexity precoder, the phase aligned zero forcing (PAZF) precoder, is also introduced. The results show that both algorithms converge fast. The WMMSE algorithm outperforms both PAZF and the zero-forcing (ZF) precoder for all signal-to-noise ratio ranges. It offers better interference management and high coherent combining gains for common data while PAZF finds the optimal phase rotation on the ZF precoder, and increases coherent combining gains.

MU-MIMO transmission relies on exploiting multi-user diversity among a multitude of users. In this paper, to enhance MU-MIMO transmission, techniques for designing and exploiting reconfigurable antennas (RAs) are developed. A single-element RA is capable of generating modes with different radiation pattern and polarization states resulting in multiple different channel states for each user. This capability expands the search space for user-pairing optimization. To reduce complexity, an iterative user and antenna mode selection algorithm is proposed. Based on parasitic tuning, an RA optimized for MU-MIMO transmission and capable of creating four pattern types is designed using a genetic algorithm and full-wave electromagnetic analyses. Pattern- and channel-aware mode-set generation methods are developed, where mode groups are determined to reduce channel estimation overhead and mode selection complexity while achieving superior performance. Simulation results indicate that the proposed schemes need a lower number of users and/or relax user selection requirements to benefit from MU-MIMO transmissions. It is also seen that more legacy antennas are needed to achieve similar MU-MIMO performance provided by the RA system. Simulations show up to 16-dB signal-to-noise ratio gains for a single cell with 12 users, where the base station has four RAs and four single-antenna users are simultaneously served via MU-MIMO transmission.

This paper proposes an efficient downlink multi- user MIMO (MU-MIMO) scheme for multiple antenna transmission systems comprised of reconfigurable antenna (RA) elements. MU-MIMO schemes typically require a combined user pairing and precoding scheme where the channels of the selected users have to satisfy certain conditions to reduce interference among the users. Therefore, MU-MIMO typically requires a large number of users so that suitable user-tuples can be found. In this work, instead of relying on this requirement, we employ RAs at the transmitter to create multiple channel states for each user. An RA system accomplishes this by its dynamically changeable operation modes each of which creates a different channel realization. The availability of multiple channel states allow for an expanded search space for user pairing. We develop a joint user and antenna mode selection algorithm minimizing the error rates. A low-complexity iterative mode selection scheme is introduced to simplify the joint optimization problem. Simulation results indicate that one would need a lower number of users to benefit from MU-MIMO transmission if RAs are employed at the transmitter.

Multifunctional and reconfigurable multiple-input multiple-output (MR-MIMO) antennas are capable of dynamically changing the operation frequencies, polarizations, and radiation patterns, and can remarkably enhance system capabilities. However, in coherent communication systems, using MR-MIMO antennas with a large number of operational modes may incur prohibitive complexity due to the need for channel state estimation for each mode. To address this issue, we derive an explicit relation among the radiation patterns for the antenna modes and the resulting channel gains. We propose a joint channel estimation/prediction scheme where only a subset of all the antenna modes is trained for estimation, and then, the channels associated with the modes that are not trained are predicted using the correlations among the different antenna modes. We propose various training mechanisms with reduced overhead and improved estimation performance, and study the impact of channel estimation error and training overhead on the MR-MIMO system performance. We demonstrate that one can achieve significantly improved data rates and lower error probabilities utilizing the proposed approaches. For instance, under practical settings, we observe about 25% throughput increase or about 3-dB signal-to-noise ratio improvement under the same training overhead with respect to non-reconfigurable antenna systems.

We propose user-aware deployment strategies for femto-cell access points (FAPs) in heterogeneous networks where users' spatial distribution and long-term signal-to-interference plus noise ratios (SINRs) are available to a control centre. Assuming basestations are already deployed, the information on user density and long-term rate coverage is utilized to generate spatial throughput metrics for determining FAP locations. In one approach, regions with the smallest per-user rate coverage are determined as FAP locations where we attempt to find high-user density regions with little coverage from existing infrastructure. In another approach, enhancements from deploying FAPs to candidate locations are predicted based on channel measurements and realistic propagation models. We also investigate step-by-step deployment approaches taking into account the impact of existing FAPs to determine additional FAP locations. Simulations under 3GPP LTE-A heterogeneous network model show that user-aware femto-cell deployment strategies can achieve up to 25% 5-percentile throughput gain, and 80% aggregate throughput gains.

In the above-named work (ibid., vol. 49, no. 10, pp. 2669-2681, Oct. 2003) the authors developed performance bounds for multiple antenna systems that use receive antenna selection and proved results regarding the diversity and coding gains in such systems. In reference to above correspondence, the probability density function given by eq. (30) should not include the scaling factor of 1/L. This is shown via a short derivation. As a result, the factor 1/L should be omitted from the pairwise error probability expressions, and (32), (34), (35), and (38)-(41) are corrected herein. The main results regarding the diversity gain of the system are not effected by the absence of this scaling factor, while the ones on the coding gain should be modified accordingly.

We propose a joint source-channel coding scheme for wireless communication systems with multiple transmit and receive antennas. The source coder is realized by a multiple description encoder that generates multiple bit streams. Each description is then separately turbo coded and transmitted using multiple antennas. For the receiver, we describe a suitable iterative joint source-channel decoding technique that exploits the correlations between the descriptions. We present several examples that illustrate the performance of the proposed system, and compare it with other approaches.

In a previous paper by Bahceci et al., antenna selection ' for multiple-antenna transmission systems under the assumption that the subchannels between antenna pairs fade independently was studied. In this paper, the performance of such systems when the subchannels experience correlated fading is considered. It is assumed that the channel-state information (CSI) is available only at the receiver, the antenna selection is performed only at the receiver, and the selection is based on the instantaneous received signal power. The effects of channel correlations on the diversity and coding gain when the receiver system is a subset of the antennas are quantified. Theoretical results indicate that the correlations in the channel do not degrade the diversity order, provided that the channel is full rank. However, it does result in some performance loss in the coding gain.

Parallel distributed detection for wireless sensor networks is studied in this paper. The network consists of a set of local sensors and a fusion center. Each local sensor makes a binary (single-bit) or M-ary (multi-bit) decision and passes it to the fusion center where a final decision is made. The links between the local sensors and the fusion center are subject to fading and additive noise resulting in corruption of the transmitted decisions. We analyze the performance of the decision fusion based on likelihood ratio tests and derive false alarm and detection probabilities. Based on the theoretical probability expressions, we design optimal decision rules for the local sensors and the fusion center. Finally, we illustrate the performance of the parallel fusion by numerical examples

Serial distributed detection for wireless sensor networks is studied in this paper. Unlike the traditional serial distributed detection schemes where it is assumed that the sensor decision at one stage is known exactly to the subsequent sensor node, we assume that the links between the consecutive sensor nodes are subject to fading and additive noise resulting in corruption of the transmitted decisions. Incorporating the effect of fading in the detection process, a decision fusion rule based on likelihood ratio tests is derived. Optimality of likelihood ratio test is also investigated. By numerical examples, we illustrate the performance of the proposed serial detection scheme and compare it with that of the parallel distributed detection

In I. Bahceci et al. (Oct 2003), antenna selection for multiple antenna transmission systems has been studied under the assumption that the subchannels between antenna pairs fade independently. In this paper, we consider the performance of such systems when the subchannels experience correlated fading. We assume that the channel state information is available only at the receiver, the antenna selection is performed only at the receiver, and the selection is based on the instantaneous received signal power. We quantify the effects of channel correlation on the diversity and coding gain when the receiver system uses all or a subset of the antennas. Theoretical results indicate that the correlations in the channel does not degrade the diversity order provided that the channel is full-rank. However, it does result in some performance loss in the coding gain. Furthermore, for non-full-rank channels, the diversity order of the system degrades significantly and is determined by the rank of the channel correlation matrix.

In this paper, turbo-based coding scheme for relay systems together with iterative decoding algorithms is designed. The performance of the proposed schemes is about 1.0-1.5 dB away from the information theoretical limits for various channel models.

This paper studies the antenna selection for space-time coded orthogonal frequency division multiplexing (OFDM) systems that employ multiple transmit and receive antennas. We assume that the channel state information (CSI) is exactly known at the receiver, and hence the selection is available only at the receiver. The selection criterion is based on the instantaneous signal-to-noise ratio at each receive antenna averaged over all carrier frequencies. We also assume that space-time codes are used at the transmitter. We analyze the performance of such systems by deriving explicit upper bounds on the pairwise error probability (PEP). Closed form expressions for the PEP hounds are derived for special cases. We also present numerical examples and simulation results that validate our analysis. It turns out that it is difficult to make remarks about the diversity order since the expressions are not simple, however, for some special cases with M = 2, N = 2 antennas, we show that using antenna selection, one can achieve the same diversity gain as the one obtained by using all the receive antennas, provided that the underlying space-time code has full spatial diversity.

Space-time coding is well established for high data rate communications over wireless channels with perfect channel state information. On the other hand, the case where the channel state information is unknown has received limited attention. Recently, a new signaling scheme called unitary space-time modulation that is suitable for the latter case has been proposed. We describe the use and design of trellis-coded space-time modulation schemes that use unitary space-time constellations. We construct these codes using a novel suboptimal code design criteria and study the performance of trellis-coded unitary space-time modulation for block fading channels under the assumption of no channel state information. Simulation results show that the proposed schemes improve the performance compared to uncoded transmission with the same spectral efficiency. The results are also compared with the turbo-coded modulation scheme Bahceci (2002) and the differential detection scheme described Jafarkhani (2001) under the same assumptions.

We propose a joint source-channel coding scheme for wireless communication systems with multiple transmit and receive antennas. The source coder is realized by a multiple description encoder that generates multiple bit streams for the same source. Each description is then separately turbo coded and transmitted using multiple antennas. For the receiver, we describe a suitable iterative joint source-channel decoding technique that exploits the correlations between the descriptions. Finally, we present several examples that illustrate the performance of the proposed system and compare it with other approaches.

This correspondence studies antenna selection for wireless communications systems that employ multiple transmit and receive antennas. We assume that (1) the channel is characterized by quasi-static Rayleigh flat fading, and the subchannels fade independently, (2) the channel state information (CSI) is exactly known at the receiver, (3) the selection is available only at the receiver, and it is based on the instantaneous signal-to-noise ratio (SNR) at each receive antenna, and (4) space-time codes are used at the transmitter. We analyze the performance of such systems by deriving explicit upper bounds on the pairwise error probability (PEP). This performance analysis shows that (1) by selecting the set of antennas that observe the largest instantaneous SNR, one can achieve the same diversity gain as the one obtained by using all the receive antennas, provided that the underlying space-time code has full spatial diversity, and (2) in the case of rank-deficient space-time codes, the diversity gain may be dramatically reduced when antenna selection is used. However, we emphasize that in both cases the coding gain is reduced with antenna selection compared to the full complexity system. Based on the upper bounds derived, we describe code design principles suitable for antenna selection. Specifically, for systems with two transmit antennas, we design space-time codes that perform better than the known ones when antenna selection is employed. Finally, we present numerical examples and simulation results that validate our analysis and code design principles.

Space-time coding is well understood for high data rate communications over wireless channels with perfect channel state information. On the other hand, channel coding for multiple transmit antennas when channel state information is unknown has only received limited attention. A new signaling scheme, named unitary space-time modulation, has been proposed for the latter case. In this paper, we consider the use of turbo coding together with unitary space-time modulation. We demonstrate that turbo coded space-time modulation systems are well suited to wireless communication systems when there is no channel state information, in the sense that the turbo coding improves the bit error rate (BER) performance of the system considerably. In particular, we observe that the turbo-coded system provides 10-15 dB coding gain at a BER of 10/sup -5/ compared to the unitary space-time modulation for various transmit and receive antenna diversity cases.

Space-time coding is well established for high data rate communications in wireless channels with perfect channel state information. On the other hand, the case where channel state information is unknown has received limited attention. Recently, a new signaling scheme called unitary space-time modulation has been proposed for the latter case. In this paper, we describe the use and design of trellis coded space-time modulation schemes that use unitary space-time constellations. Simulation results show that the proposed schemes improve the performance compared to uncoded transmission with the same spectral efficiency.