Quantum Machine Learning for 6G Communication Networks: State-of-the-Art and Vision for the Future

in IEEE Access (2019)

The upcoming 5th Generation (5G) of wireless networks is expected to lay a foundation of intelligent networks with the provision of some isolated Artificial Intelligence (AI) operations. However, fully ... [more ▼]

The upcoming 5th Generation (5G) of wireless networks is expected to lay a foundation of intelligent networks with the provision of some isolated Artificial Intelligence (AI) operations. However, fully-intelligent network orchestration and management for providing innovative services will only be realized in Beyond 5G (B5G) networks. To this end, we envisage that the 6th Generation (6G) of wireless networks will be driven by on-demand self-reconfiguration to ensure a many-fold increase in the network performanceandservicetypes.Theincreasinglystringentperformancerequirementsofemergingnetworks may finally trigger the deployment of some interesting new technologies such as large intelligent surfaces, electromagnetic-orbital angular momentum, visible light communications and cell-free communications – tonameafew.Ourvisionfor6Gis–amassivelyconnectedcomplexnetworkcapableofrapidlyresponding to the users’ service calls through real-time learning of the network state as described by the network-edge (e.g., base-station locations, cache contents, etc.), air interface (e.g., radio spectrum, propagation channel, etc.), and the user-side (e.g., battery-life, locations, etc.). The multi-state, multi-dimensional nature of the network state, requiring real-time knowledge, can be viewed as a quantum uncertainty problem. In this regard, the emerging paradigms of Machine Learning (ML), Quantum Computing (QC), and Quantum ML (QML) and their synergies with communication networks can be considered as core 6G enablers. Considering these potentials, starting with the 5G target services and enabling technologies, we provide a comprehensivereviewoftherelatedstate-of-the-artinthedomainsofML(includingdeeplearning),QCand QML, and identify their potential benefits, issues and use cases for their applications in the B5G networks. Subsequently,weproposeanovelQC-assistedandQML-basedframeworkfor6Gcommunicationnetworks whilearticulatingitschallengesandpotentialenablingtechnologiesatthenetwork-infrastructure,networkedge, air interface and user-end. Finally, some promising future research directions for the quantum- and QML-assisted B5G networks are identified and discussed. [less ▲]

Superimposed Training based Estimation of Sparse MIMO Channels for Emerging Wireless Networks

in Proceedings of ICT 2016 (2016, May)

Multiple-input multiple-output (MIMO) systems constitute an important part of todays wireless communication standards and these systems are expected to take a fundamental role in both the access and ... [more ▼]

Multiple-input multiple-output (MIMO) systems constitute an important part of todays wireless communication standards and these systems are expected to take a fundamental role in both the access and backhaul sides of the emerging wireless cellular networks. Recently, reported measurement campaigns have established that various outdoor radio propagation environments exhibit sparsely structured channel impulse response (CIR). We propose a novel superimposed training (SiT) based up-link channels’ estimation technique for multipath sparse MIMO communication channels using a matching pursuit (MP) algorithm; the proposed technique is herein named as superimposed matching pursuit (SI-MP). Subsequently, we evaluate the performance of the proposed technique in terms of mean-square error (MSE) and bit-error-rate (BER), and provide its comparison with that of the notable first order statistics based superimposed least squares (SI-LS) estimation. It is established that the proposed SI-MP provides an improvement of about 2dB in the MSE at signal-to-noise ratio (SNR) of 12dB as compared to SI-LS, for channel sparsity level of 21.5%. For BER = 10^−2, the proposed SI-MP compared to SI-LS offers a gain of about 3dB in the SNR. Moreover, our results demonstrate that an increase in the channel sparsity further enhances the performance gain [less ▲]

Repeater for 5G Wireless: A Complementary Contender for Spectrum Sensing Intelligence

in Proceedings of International Conference on Communications 2015 (2015, June)

Exploring innovative cellular architectures to achieve enhanced system capacity and good coverage has become a critical issue towards realizing the fifth generation (5G) of wireless communications. In ... [more ▼]

Exploring innovative cellular architectures to achieve enhanced system capacity and good coverage has become a critical issue towards realizing the fifth generation (5G) of wireless communications. In this context, this paper proposes a novel concept of an intelligent Amplify and Forward (AF) 5G repeater for enabling the densification of future cellular networks. The proposed repeater features a Spectrum Sensing (SS) intelligence capability and utilizes such intelligence in a complementary fashion in comparison to its existing counterpart (e.g., Cognitive Radio) by detecting the active channels within the assigned spectrum. This intelligence allows the proposed repeater to carry out selective amplification of the active channels in contrast to the full amplification in conventional AF repeaters. Furthermore, the performance of a Frequency Division Multiple Access (FDMA) based two hop cellular network utilizing the proposed repeater is evaluated in terms of the system throughput. Simulation results demonstrate up to 13 % increase when compared with the conventional repeaters. Moreover, the effect of SS errors on the system capacity is analyzed. [less ▲]

Enhanced information throughput in multiple input multiple output orthogonal frequency division multiplexing based systems using fractional sampling and iterative signal processing

in Transactions on Emerging Telecommunications Technologies (2013)

Herein, we study the feasibility of enhanced information throughput capability of multiple input multiple output orthogonal frequency division multiplexing (MIMO-OFDM) based wireless communication systems ... [more ▼]

Herein, we study the feasibility of enhanced information throughput capability of multiple input multiple output orthogonal frequency division multiplexing (MIMO-OFDM) based wireless communication systems in the context of increasing wireless capacity demand. The concept of fractional sampling (FS) is exploited for this purpose to take advantage of diversity created because of it. Furthermore, a novel channel adaptive iterative sequence detector is proposed using the FS technique. The performance analysis of the proposed receiver is carried out, and a tighter performance bound is derived. It is found that the FS technique can improve bit error rate performance of MIMO and OFDM based systems provided that the noise samples are uncorrelated up to a certain level of FS rate. Moreover, it is observed that the performance improvement is a non-linear function of the FS rate. Besides this, the simulation results show that the proposed iterative receiver can significantly enhance the information throughput of MIMO-OFDM based wireless communication systems in comparison to conventional non-iterative receivers. [less ▲]