Nasir Hussain

Supervised machine learning is a promising technique to achieve joint resource allocation and selection of mobile relays in cooperative heterogeneous networks. Joint resource allocation and mobile relay selection are NP-hard problems in the sense that they cannot be solved in polynomial time. To solve this problem, highly complex heuristic solutions based on channel conditions and physical-layer parameters have been considered. Our research explores an artificial neural network (ANN) approach to the joint allocation of resources and choice of a mobile relay with efficient utilization of resources in terms of energy efficiency (EE) and spectral efficiency (SE). To this, there exists a tradeoff between the two, i.e., EE and SE, and to consider this tradeoff, a new metric resource efficiency (RE) has already been introduced in the literature. This article addresses the problem of learning a regression model for determining optimal transmit power and resource allocation and choosing the appropriate relay for cooperative communication to maximize RE. Specifically, a multilayer fully connected ANN-based resource allocation and relay selection (ANN-RARS) algorithm is proposed, and a comparison of ANN-RARS with particle swarm optimization-based resource allocation and relay selection (PSO-RARS) algorithm is performed. Based on the performance analysis, ANN-RARS performs better than the PSO-RARS algorithm.

The microwave (lWave) spectrum or low frequency spectrum has become over crowded due to the ever increasing demand in bandwidth-intensive applications such as video streaming, gaming, etc. Owing to the fact that the spectral efficiency of microwave links is approaching its fundamental limits, there is a growing consensus in both industry and academia that millimeter wave (mmWave) will play an important role in increasing data rate and scarcity of spectrum. To redress the predicament and to ensure adequate availability of bandwidth, increasing attentions have been paid to the use of millimeter-wave (mmWave) spectrum for future broadband wireless networks. mmWave spectrum offers wider bandwidth compared with μWave spectrum and a promising solution to overcome the scarcity of spectrum while providing Gigabits per second (Gbps) of data rates. To fully exploit the high potential rates of mmWave in mobile networks, a number of technical problems must be addressed. mmWave signal transmission suffers from issue of blockage and deafness. The former challenge is characterized by the loss of Quality of Service (QoS) in Non-line-of-sight (NLOS) conditions, while the latter is characterized by the misalignment between the main lobe of transmitter and receiver beam. Two strategies can be adopted to deal with the issues, a) relaying: use of another path with the help of relay(s) providing line-of-sight (LOS) link(s), and b) fall back: in case of service interruption, switch back to μWave spectrumbased transmission switching between mmWave and lWave frequency bands can support higher rates and QoS requirements. However, trade-off exists in employing any of the aforementioned strategies. In this work, we study the joint spectrum allocation and relay selection problem to maximize the weighted sum rate relay selection (using resource block and time slot) along with a fall-back approach for spectrum allocation in a HMMC network. A fall-back approach is introduced to enable the hybrid transmission of lWave and mmWave and an iterative bipartite relay-spectrum selection algorithm is proposed to solve the problem. Performance evaluation results show that the proposed fall-back approach outperforms the conventional μWave or mmWave transmission schemes in terms of data rate, transmit power and number of users.

Cooperative communication can attain lower error probability in wireless networks by exploiting the inherent broadcast nature and taking advantage of multi-path propagation. In order to leverage performance gains achieved by virtual multiple- input multiple-output (MIMO) systems, we design a novel cooperative protocol, Decode-to-Cooperate (DCOOP). We evaluate its performance on a testbed implemented on Universal Software Radio Peripheral Reconfigurable Input/Output (USRPRIO) platform. The main challenge during the testbed deployment was to consider transmission under tightly synchronized nodes in a slow fading environment. Extensive experiments were performed to evaluate the performance of the testbed and the results show that it can operate at lower transmit power and increase the coverage area for a desired bit error rate (BER).

An opportunistic relay selection scheme improving cooperative diversity is devised using the concept of a virtual SIMO-MISO antenna array. By incorporating multiple users as a virtual distributed antenna, not only helps combat fading but also provides significant advantage in terms of energy consumption. The proposed efficient multiple relay selection uses the concept of the distributed Alamouti scheme in a time varying environment to realize cooperative networking in wireless relay networks and provides the platform for outage, Diversiy-Multiplexing Tradeoff (DMT) and Bit-Error-Rate (BER) analysis to conclude that it is capable of achieving promising diversity gains by operating at much lower SNR when compared with conventional relay selection methods. It also has the added advantage of conserving energy for the relays that are reachable but not selected for the cooperative communication.