A new era of wireless networks is evolving, thanks to the significant advances in communications and networking technologies. In parallel, wireless services are witnessing a tremendous change due to increasingly heterogeneous and stringent demands, whose quality of service requirements are expanding in several dimensions, putting pressure on mobile networks. Examples of those services are augmented and virtual reality, as well as self-driving cars. Furthermore, many physical systems are witnessing a dramatic shift into autonomy by enabling the devices of those systems to communicate and transfer control and data information among themselves. Examples of those systems are microgrids, vehicles, etc. As such, the mobile network indeed requires a revolutionary shift in the way radio resources are assigned to those services, i.e., RRM. In RRM, radio resources such as spectrum and power are assigned to users of the network according to various metrics such as throughput, latency, and reliability. Several methods have been adopted for RRM such as optimization-based methods, heuristics and so on. However, these methods are facing several challenges such as complexity, scalability, optimality, ability to learn dynamic environments. In particular, a common problem in conventional RRM methods is the failure to adapt to the changing situations. For example, optimization-based methods perform well under static network conditions, where an optimal solution is obtained for a snapshot of the network. This leads to higher complexity as the network is required to solve the optimization at every time slot. Machine learning constitutes a promising tool for RRM with the aim to address the conflicting objectives, i.e., KPIs, complexity, scalability, etc. In this thesis, we study the use of reinforcement learning and its derivatives for improving network KPIs. We highlight the advantages of each reinforcement learning method under the studied network scenarios. In addition, we highlight the gains and trade-offs among the proposed learning techniques as well as the baseline methods that rely on either optimization or heuristics. Finally, we present the challenges facing the application of reinforcement learning to wireless networks and propose some future directions and open problems toward an autonomous wireless network. The contributions of this thesis can be summarized as follows. First, reinforcement learning methods, and in particular model-free Q-learning, experience large convergence time due to the large state-action space. As such, deep reinforcement learning was employed to improve generalization and speed up the convergence. Second, the design of the state and reward functions impact the performance of the wireless network. Despite the simplicity of this observation, it turns out to be a key one for designing autonomous wireless systems. In particular, in order to facilitate autonomy, agents need to have the ability to learn/adjust their goals. In this thesis, we propose transfer in reinforcement learning to address this point, where knowledge is transferred between expert and learner agents with simple and complex tasks, respectively. As such, the learner agent aims to learn a more complex task using the knowledge transferred from an expert performing a simpler (partial) task.

Cellular Internet of Things (CIoT) has emerged as a promising technology to support applications that generate infrequent data. One requirement on these applications, often battery-powered devices, is low energy consumption to enable extended battery life. Narrowband IoT (NB-IoT) is a promising technology for IoT due to its low power consumption, which is essential for devices that need to run on battery power for extended periods. However, the current battery life of NB-IoT devices is only a few years, which is insufficient for many applications. This thesis investigates the impact of energy-saving mechanisms standardized by 3GPP on battery life of NB-IoT devices. The main research objective is to classify and analyze existing energy-saving solutions for CIoT and examine their limitations, to study the impact of standardized energy-saving mechanisms on the battery life of NB-IoT devices, both in isolation and combined, and to provide guidelines on how to configure NB-IoT devices to reduce energy consumption efficiently. The research aims to provide a deeper understanding of the effect of energy-saving mechanisms and best practices to balance energy efficiency and performance of NB-IoT devices. Applying the proposed solutions makes it possible to achieve a battery life of 10~years or more for CIoT devices.

This project aims to detect possible anomalies in the resource consumption of radio base stations within the 4G LTE Radio architecture. This has been done by analyzing the statistical data that each node generates every 15 minutes, in the form of "performance maintenance counters". In this thesis, we introduce methods that allow resources to be automatically monitored after software updates, in order to detect any anomalies in the consumption patterns of the different resources compared to the reference period before the update. Additionally, we also attempt to narrow down the origin of anomalies by pointing out parameters potentially linked to the issue. / Detta projekt syftar till att upptäcka möjliga anomalier i resursförbrukningen hos radiobasstationer inom 4G LTE Radio-arkitekturen. Detta har gjorts genom att analysera de statistiska data som varje nod genererar var 15:e minut, i form av PM-räknare (PM = Performance Maintenance). I denna avhandling introducerar vi metoder som låter resurser över-vakas automatiskt efter programuppdateringar, för att upptäcka eventuella avvikelser i resursförbrukningen jämfört med referensperioden före uppdateringen. Dessutom försöker vi också avgränsa ursprunget till anomalier genom att peka ut parametrar som är potentiellt kopplade till problemet.

This dissertation introduces the concept of an artificial society based on the use of an action based social language combined with the behavior-based approach to the construction of multi-agent systems to address the problem of developing decentralized, self-organizing networks that dynamically fit into their environment. In the course of accomplishing this, social language is defined as an efficient method for communicating coordination information among cognitive radios inspired by natural societies. This communication method connects the radios within a network in a way that allows the network to learn in a distributed holistic manner. The behavior-based approach to developing multi-agent systems from the field of robotics provides the framework for developing these learning networks. In this approach several behaviors are used to address the multiple objectives of a cognitive radio society and then combined to achieve emergent properties and behaviors. This work presents a prototype cognitive radio society. This society is implemented, using low complexity hardware, and evaluated. The work does not focus on the development of optimized techniques, but rather the complementary design of techniques and agents to create dynamic, decentralized self-organizing networks / Ph. D.

No description available.

No description available.

No / Multi-antenna(MIMO) techniques are reported to improve the performance of radio communication systems in terms of their capacity and spectral efficiency. In combination with appropriate receiver technologies they can also provide savings in the required transmit power with respect to target bit error rate. Long Term Evolution(LTE), one of the candidates for fourth generation(4G) mobile communication systems has MIMO as one of its underlying technologies and ITU defined channel models for its propagating environment. This paper undertakes a comprehensive verification of the performance of transmit diversity MIMO in the downlink sector of LTE. It uses models built using MATLAB to carry out simulations. It is deduced that generally increasing transmit diversity configuration from 2x2 to 4x4 offers SNR savings in flat fading channels though with a user equipment moving at 30km/hr, deploying 2x2 offers higher SNR saving below 7dB. Furthermore bandwidth variation has minimal effect on the BER performance of transmit MIMO except at SNR values above 9dB while the gains of higher modulation schemes come with a transmit power penalty.

Yes / A major drawback in deploying beamforming scheme in orthogonal frequency division multiplexing (OFDM) is to obtain the optimal weights that are associated with information beams. Two beam weighting methods, namely co-phasing and singular vector decomposition (SVD), are considered to maximize the signal beams for such beamforming scheme. Initially the system performance with and without interleaving is investigated using coded fast Fourier transform (FFT)-OFDM and wavelet-based OFDM. The two beamforming schemes are applied to the wavelet-based OFDM as confirmed to perform better than the FFT-OFDM. It is found that the beam-weight by SVD improves the performance of the system by about 2dB at the expense of the co-phasing method. The capacity performances of the weighting methods are also compared and discussed.

Yes / Much attention has been paid to making 5G developments more en-ergy efficient, especially in view of the need for using high data rates with more complex modulation schemes within a limited bandwidth. The concept of the Doherty power amplifier for improving amplifier efficiency is explained in addi-tion to a case study of a 70W asymmetrical Doherty power Amplifier using two GaN HEMTs transistors with peak power ratings of 45W and 25W. The rationale for this choice of power ratio is discussed. The designed circuit works in the 3.4GHz frequency band with 200 MHz bandwidth. Rogers RO4350B substrate with dielectric constant εr=4.66 and thickness 0.035 mm is used. The perfor-mance analysis of the Doherty power amplifier is simulated using AWR MWO software. The simulated results showed that 54-64% drain efficiency has been achieved at 8 dB back-off within the specified bandwidth with an average gain of 10.7 dB.

Vehicle-related communications are a key application to be enabled by Fifth Generation (5G) wireless systems. The communications enabled by the future Internet of Vehicles (IoV) that are connected to every wireless device are referred to as Vehicle-to-Everything (V2X) communications. A major application of V2X communication systems will be to provide emergency warnings. This thesis evaluates Long-Term Evolution (LTE) and Dedicated Short Range Communications (DSRC) in terms of service quality and latency, and provides guidelines for design of cooperative LTE-DSRC systems for V2X communications. An extensive simulation analysis shows that (1) the number of users in need of warning has an effect on latency, and more so for LTE than for DSRC, (2) the DSRC priority parameter has an impact on the latency, and (3) wider system bandwidths and smaller cell sizes reduce latency for LTE. The end-to-end latency of LTE can be as high as 1.3 s, whereas the DSRC latency is below 15 ms for up to 250 users. Also, improving performance of systems is as much as important as studying about latency. One method to improving performance is using a better suitable antenna for physical communication. The mobility of vehicles results in a highly variable propagation channel that complicates communication. Use of a smart, steerable antenna can be one solution. The most commonly used antennas for vehicular communication are omnidirectional. Such antennas have consistent performance over all angles in the horizontal plane; however, rapidly steerable directional antennas should perform better in a dynamic propagation environment. A linear array antenna can perform dynamical appropriate azimuth pattern by having different weights of each element. The later section includes (1) identifying beam pattern parameters based on locations of a vehicular transmitter and fixed receivers and (2) an approach to find weights of each element of linear array antenna. Through the simulations with our approach and realistic scenarios, the desired array pattern can be achieved and array element weights can be calculated for the desired beam pattern. Based on the simulation results, DSRC is preferred to use in the scenario which contains large number of users with setup of higher priority, and LTE is preferred to use with wider bandwidth and smaller cell size. Also, the approach to find the controllable array antenna can be developed to the actual implementation of hardware with USRP. / Master of Science