Artificial Intelligence for Cognitive Wireless Communications

This special issue is devoted to the new research addressing challenges in the areas of wireless computing and networking. Wireless computing and networking has enabled heterogeneous access technologies for providing services to ubiquitous users. The demanding networking environment of wireless communications imposes many challenges, such as channel estimation, network protocol design, resource management, and systematic design. Due to nonuniform spectrum allocation, various radio resource management policies, economic concerns, scarcity of radio resources, and user mobility, overcoming these issues becomes more demanding. This special issue includes ten research articles from five countries including the United States, China, South Korea, Norway, and India which covers various research issues in the areas of wireless computing and networking. These articles can be broadly classified into three categories: (1) data management and query processing in wireless networks; (2) backbone management in wireless networks; and (3) routing in wireless networks. A detailed description of the corresponding works in each category is given below.

The massive growth of data consumption and the variety of wireless technology emergence has made the handover (HO) an attractive research topic nowadays, mainly due to the popularity of Wireless Local Area Networks (WLANs), which allow users to reach high-speed data communication while they are in movement. Moreover, mobile devices such as tablets and smartphones have also become increasingly popular due to their low cost and ease of use, and an increase in mobile device use is expected to accelerate in the coming years, along with the availability and use of applications such as real-time services and online gaming. The traditional HO methods will likely not meet the requirements of mobile devices for modern applications due to the lack of intelligence, lack of awareness Quality of Service (QoS) and Quality of Experience (QoE) requirements of mobile users. We, therefore, introduce a novel architecture that supports horizontal HO in homogenous networks. This architecture is based on the Software-Defined Wireless Networking (SDWN) concept, where the wireless network is controlled centrally and the wireless Access Points (APs) are programmable. In this architecture, HO algorithms will assist wireless users to find the network that could best support the application requirements through Quality of Service (QoS) and Quality of Experience (QoE) management policies. The first HO algorithm proposed in this thesis is called Quality of Experience Oriented Handover Algorithm. This algorithm will guarantee the best possible connectivity to the users in terms of their QoE and QoS requirements and outperforms the traditional methods in a sparse network environment. The second contribution is called Optimised Handover Algorithm for Dense WLAN Environments. This algorithm has been designed to address dense network environments via taking into consideration the Adaptive Hysteresis Value (AHV). The AHV will help the Optimised Handover Algorithm via reducing the so-called ping-pong effect. This contribution shows promising performance results by selecting the best candidate AP, decreasing the number of redundant HO and avoiding the ping-pong effect. The final contribution is called Priority Based Handover Algorithm. We extended our proposed SDWN architecture in order to include the concept of prioritising users and make a smart decision during the process of HO. This algorithm will prioritise a certain class of users to avoid the effect of the over-congestion. The results show that the approach based on priority outperforms the state of the art and provides better QoE to the high priority users despite the over-congestion situation.

HTTP adaptive streaming (HAS) is a state-of-the-art technology for video streaming. Optimal adaptive streaming schemes should be designed to maximize the quality of experience (QoE) in network environments with unstable bandwidths such as wireless networks. QoE is degraded for Advanced Video Coding (AVC)-based HAS due to frequent quality switching and rebuffering in wireless networks. Meanwhile, Scalable Video Coding (SVC)-based HAS can maximize the QoE by flexibly requesting the base layer (BL) and enhancement layer (EL) based on variable network conditions. However, in SVC-based HAS, the required bandwidth is significantly high due to the encoding overhead. In this paper, we propose a layer-assisted video quality adaptation for improving QoE in wireless networks. The proposed scheme employs a video encoding method, composed of multiple BLs and ELs, using both AVC and SVC. The quality of the BL is determined using the buffer occupancy level and measured bandwidth to minimize rebuffering. The quality of the EL is determined using the buffer region and segment quality differences to minimize instability. enhancement dummy (ED) consists of the selected ELs. The layer scheduler decides the segment that is to be requested based on the QoE model according to the BL and ED to maximize the QoE. Experimental results show that the proposed scheme achieves high QoE compared to the existing schemes because the instability is low and no rebuffering occurs.

Recently, the evaluation on quality of the air interface in a wireless network has shifted from emphasis on QoS (quality of service) only to incorporation of QoE (quality of experience). However, it seems that QoE metrics have not been related to the surroundings of the served users so far, which may have a great influence on users' expected QoE. For instance, with a high level of QoS, a user's expectation of QoE could still be terrible because of the serious interference from the surroundings such as noise, ambient light or shaking of terminals due to mobility. From another perspective, it means that in such a case a high level of QoS may be helpless to enhance users' QoE and the requirement could be relaxed accordingly. In this paper, an approach called surrounding-adaptive QoE adjustment (SAQA) is proposed to optimize the capacity and the quality of air interface with voice service as an example. The basic idea of the approach is that user equipment (UE) detects the surroundings interference which may impact users' QoE and then adjusts QoS according to the detected results: a lower level of QoS is chosen in a bad environment to enhance the capacity, while a higher level of QoS is selected to guarantee the users' QoE in a better circumstance. Simulation results show that this method can remarkably enhance the voice capacity of the communication systems as well as guarantee users' QoE.

Artificial Intelligence (AI) improves resource management and energy conservation through machine learning, improved forecasting, and quicker data processing. Artificial intelligence (AI) and machine learning (ML) have become essential enablers of this integration in this context. Machine learning and artificial intelligence are necessary for an organization’s survival and expansion, not just a choice. This research explores the growing significance of machine learning and artificial intelligence in resource management. The proposed method, deep reinforcement learning (DRL) based on machine learning is an essential tool for addressing the issues of resource management. Resource management can ensure that certain QoS criteria are met for various applications, such as information or real-time video transmission. Reducing total transmit power allows optimal resource management, while following Quality of Service (QoS) criteria permits a better relay choice. In this paper, the numerical results show that it performs competitively in terms of bandwidth of 97.5%, power consumption of 96%, spectrum efficiency of 91%, and network lifespan of 93 percent. Costs are decreased and environmental responsibility is enhanced through resource management. This research examines how AI might increase bandwidth, power consumption, spectrum efficiency, and resource management, with a particular emphasis on automation, efficiency, and prediction via quality of service.

Recently, with the spread of smart devices and the development of networks, the demand for video streaming has increased, and HTTP adaptive streaming has been gaining attention. HTTP adaptive streaming can guarantee QoE (Quality of Experience) because it selects the video quality according to the network state. However, in wireless networks, delay and packet loss rates are high and the available bandwidth fluctuates sharply. Therefore, QoE is degraded when the quality is selected on the basis of the measured bandwidth. In this paper, we propose an adaptive quality control scheme to improve QoE of video streaming in wireless networks. The proposed scheme calculates two factors, the buffer underflow probability and the instability, by considering the buffer state and the changes of quality level. Using these factors, the proposed scheme defines a quality control region that consists of four sub-regions. The video quality is determined by applying different control strategy to each sub-region. The results of experiments have shown that the proposed scheme improves QoE compared to the existing quality control schemes by minimizing the buffer underflow and the unnecessary quality changes and maximizing the average video quality.

Quality of experience (QoE) over wireless networks has attracted attention from industry and academia due to an increase in video streaming applications. Several researchers have attempted to understand the factors affecting QoE and design appropriate quality control strategies. Normally, video streaming is initiated by a user who accesses video contents over wireless networks using a smart device held at various viewing distances. Each aforementioned factor has the potential to affect QoE of the viewed session. However, several studies explore the behavior of wireless networks on video streaming QoE. To understand the effects of other factors on QoE, this paper investigates the influence of the device's visual features, viewing distance, and content factors on video streaming. The study adopted an emulation technique to conduct multi-factor experiments designed using the Taguchi method. The 5-ways ANOVA analysis revealed that the effects of smart-device visual features, viewing distance, and content types are significant on video streaming QoE at p<0.05. Moreover, smart devices with a pixel density index of more than 200 ppi produce high QoE, with the viewing distance limited to 45 cm. Lastly, the video bitrate greater than 1024 kbps produced a good QoE regardless of the frame rates.

4 - QoE-based Power Efficient LTE Downlink Scheduler

Below the Media Access Control (MAC) layer is the Physical (PHY) layer which deals with the actual transmission of the bits received from the MAC layer above into electromagnetic signals. This layer is optimized to implore power management in wireless networks. Power management is a crucial issue in wireless and mobile networks. In this paper, we propose an Adaptive Context-Aware Rate Selection (ACARS) algorithm to handle the issue of power consumption in wireless networks. This algorithm is implemented by optimizing the PHY layer to transmit efficiently as the number of nodes changes and we estimate the Signal-to-Noise Ratio (SNR) to the PHY layer. Results show that by using the appropriate power management technique, ACARS is reliable and efficient for power consumption in wireless networks which is a high demand for vehicular networks.

Heterogeneous wireless network (HWN) is an overlay structure of different wireless networks (WN). The WNs may differ in terms of coverage, capacity, underlying technology, service types, and network operators. In such a HWN environment, a mobile user (MU) equipped with multi-mode or multi-home terminal always wish to maintain connectivity with a wireless network which can provide best quality of experience (QoE). Similarly, the WN may allow the connectivity only to a MU which can provide highest revenue. This may leads to an event, called vertical handoff, where the MU leaves current WN and connect to another different WN. The conflicting goals of maximizing QoE and revenue simultaneously while performing a VHO necessitates the selection of mutually best MU and WN. Game theory is an efficient mathematical tool to model such situations where specific actions of decision makers lead to mutually conflicting consequences to each other. This paper, using a tutorial style, presented the game theory concepts and its application for VHO, type of games, and game solutions. It proposes, in specific, the noncooperative game formulations for three different VHO situations and their solutions using NASH for HWNs.

The deployment of real-time and multimedia applications over Wireless LAN has gained a growing interest in this last decade. These applications, e.g. video streaming, require tight guarantee on Quality of Service (QoS). Also, they use multicast communication in order to reduce the bandwidth consumption. However, in WLAN, multicast packets are sent with the basic rate (lowest rate); which results in capacity wasting because of longer channel occupancy. Moreover the lack of feedback mechanism makes it difficult to deal with reliability or service quality. In this paper, we propose to rely on the WLAN multi-rate capability, in order to transmit multicast packets with higher and dynamic rate than the basic rate. Unlike other existing protocols that use a static-threshold to decide when to change transmission rate, we propose a novel dynamic rate-adaptation mechanism based on Quality of Experience (QoE), namely Q-DRAM. According to the clients' feedback on QoE, we adapt the multicast rate: (i) when users had bad QoE we reduce the multicast transmission rate; (ii) when users had good QoE, we increase the multicast transmission rate. Simulation results show that Q-DRAM increases the wireless channel utilization and maximizes users' QoE, compared to existing solutions as well as to the IEEE 802.11 standard.

Online video transmissions over wireless networks are rising in popularity and have already become part of our daily life. In the meantime, it is necessary to address a number of challenges ranging from the scarce resources, time-varying, and high error rates, to the fluctuating bandwidth, unveiling the need for an adaptive mechanism to ensure a good video transmission. Adaptive Forward Error Correction (FEC) techniques with Quality of Experience (QoE) assurance are appropriate to deliver QoE-aware video data to wireless users in dynamic and high error rates networks. This paper proposes an adaptive Video-aware FEC and Fuzzy Logic-based mechanism to shield realtime video transmissions against packet loss in wireless networks, improving both user experience and the usage of resources. The benefits and drawbacks of the proposed mechanism compared with exiting work are demonstrated through simulations and assessed with QoE metrics.

Wireless network security protocols are essential for enhancing security, privacy and confidentiality. However, network security protocols also require network resources in other to carry out authentication of users through the use of encryption keys and packet encryption. It is therefore relevant to investigate the effects of the amount of resources used by recommended wireless network security protocols in other to determine if user quality of experience and user quality of service is affected by the implementation wireless network security protocols. Our research investigates and examines the effect of security protocols on wireless network performance. The Wi-Fi Protected Access 2 - PreShared Key (WPA2-PSK) was used as the security protocol in focus while throughput was the network performance feature that was analyzed. Experiments were carried out which showed that throughput in a non-secured Wireless Local Area Network (WLAN) is a bit higher than throughput in a secured WLAN. Our research contributes to the future development of WLAN protocols with low network resource consumption in other to contribute to improved network performance.

The increasing popularity of video (i.e., audio-visual) applications or services over both wired and wireless links has prompted recent growing interests in the investigations of quality of experience (QoE) in online video transmission. Conventional video quality metrics, such as peak-signal-to-noise-ratio and quality of service, only focus on the reception quality from the systematic perspective. As a result, they cannot represent the true visual experience of an individual user. Instead, the QoE introduces a user experience-driven strategy which puts special emphasis on the contextual and human factors in addition to the transmission system. This advantage has raised the popularity and widespread usage of QoE in video transmission. In this paper, we present an overview of selected issues pertaining to QoE and its recent applications in video transmission, with consideration of the compelling features of QoE (i.e., context and human factors). The selected issues include QoE modeling with influence factors in the end-to-end chain of video transmission, QoE assessment (including subjective test and objective QoE monitoring) and QoE management of video transmission over different types of networks. Through the literature review, we observe that the context and human factors in QoE-aware video transmission have attracted significant attentions since the past two to three years. A vast number of high quality works were published in this area, and will be highlighted in this survey. In addition to a thorough summary of recent progresses, we also present an outlook of future developments on QoE assessment and management in video transmission, especially focusing on the context and human factors that have not been addressed yet and the technical challenges that have not been completely solved so far. We believe that our overview and findings can provide a timely perspective on the related issues and the future research directions in QoE-oriented services over video communications.

Wireless networking is a crucial component of communication in this era of digitization. The key characteristics that determine a wireless network's performance are smooth connectivity, quicker communication, and increased customer satisfaction. Scalability deals with the erratic workload and new resources that are added to the network. Scalability is crucial for both Quality of Experience (QoE) and Quality of Service (QoS) in such a power-constrained environment because wireless devices are battery-operated. Managing power consumption and network performance simultaneously in scalable networking scenario is quite challenging, especially during handover. This research proposed a methodology to assess the impact of scalability on wireless node power consumption and network performance in order to develop energy-efficient handoff mechanisms. The Type-I and Type-II wireless node sets were used between the WiFI and WiMAX networks in a vertical handover scenario. In the study, two distinct scalability scenarios were taken into account. Three distinct voltage levels—cutoff voltage, nominal voltage, and charge voltage —had been used to examine the consumption of power. Throughput, residual energy, and Packet Delivery Ratio (PDR) were computed to examine the network's performance in a scalable, power-constrained context. Two different scalability scenarios were considered in the study. The power consumption was investigated using three different voltage levels: charge voltage, nominal voltage, and cutoff voltage. The network's performance under scalable, power-constrained conditions was investigated by computing throughput, packet delivery ratio (PDR), and residual energy. The result obtained in the study showed the variation in battery drainage of wireless nodes under the effect of various scalability factors. This study will provide a blueprint for developing novel algorithms which eventually will improvise network performance and strengthen the base of Green Networking.