Class-of-service (CoS) network traffic classification (NTC) classifies a group of similar traffic applications. The CoS classification is advantageous in resource scheduling for Internet service providers and avoids the necessity of remodelling. Our goal is to find a robust, lightweight, and fast-converging CoS classifier that uses fewer data in modelling and does not require specialized tools in feature extraction. The commonality of statistical features among the network flow segments motivates us to propose novel segmented learning that includes essential vector representation and a simple-segment method of classification. We represent the segmented traffic in the vector form using the essential vector representation (EVR). Then, the segmented traffic is modelled for classification using random forest based simple-segment method of classification (S2MC). Our solution's success relies on finding the optimal segment size and a minimum number of segments required in modelling. The solution is validated on multiple datasets for various CoS services, including virtual reality (VR). Significant findings of the research work are i) Synchronous services that require acknowledgment and request to continue communication are classified with 99 % accuracy, ii) Initial 1,000 packets in any session are good enough to model a CoS traffic for promising results, and we therefore can quickly deploy a CoS classifier, and iii) Test results remain consistent even when trained on one dataset and tested on a different dataset. In summary, our solution is the first to propose segmentation learning NTC that uses fewer features to classify most CoS traffic with an accuracy of 99 %. The implementation of our solution is available on GitHub.

As one of the key technologies in 5G networks, Carrier Aggregation (CA) is studied in this paper. In CA, Component Carriers (CCs) can be activated and deactivated depending on multiple factors, e.g., energy consumption and Quality of Service (QoS) demand of users. We propose CC management strategies where each User Equipment (UE) minimizes its average delay and at the same time minimizes its power consumption while considering that CCs can be activated and deactivated only at certain times, as in real-world CA implementations. We first model the problem as a centralized multi-objective optimum CC management problem. Since centralized approaches would impose a large overhead on the system, we then develop a semi-distributed solution by modeling the problem as a stochastic game and propose a multi-agent Double Deep Q-Network (DDQN) based CC management algorithm to solve the stochastic game. We finally compare the proposed approaches with single CC activation and all-CC activation baseline schemes. Simulation results show that our proposed algorithms outperform the all-CC algorithm in terms of UE power consumption and have the capability of transmitting a number of bits with delay close to the all-CC scheme. Meanwhile, our DDQN-based algorithm decreases the UE power consumption by about 20% with respect to the all-CC scheme.

Carrier aggregation (CA) is considered a key enabler technology for delivering higher rates to users of LTE and 5G networks. However, the increased transmission rate comes with the price of higher energy consumption which stems from users continuously monitoring the control channel of the active component carriers (CCs) whether data transmission is ongoing or not. In order to reduce energy consumption, we exploit the activation-deactivation procedure at the medium access control (MAC) layer of LTE/5G network. In this paper, we propose a reinforcement learning-based algorithm to improve energy-efficiency by dynamically activating-deactivating secondary component carriers (SCCs) with awareness of the user traffic profiles. The proposed algorithm aims to predict the arrival of data and identify SCCs to activate for each user. In addition, a traffic splitting approach and an intelligent exploration strategy are proposed to balance users' load among CCs and improve the convergence of the algorithm, respectively. Results of the proposed algorithm are compared with three baseline algorithms. The first baseline always activates all CCs for each user, the second baseline activates one carrier only (i.e., the primary carrier) and the third baseline algorithm relies on a reactive method, where the activation-deactivation decision is performed after observing the arrival of data. Results show that Q-learning outperforms the baseline algorithms by achieving the highest sum throughput (and lowest average delay) with the lowest number of activated SCCs, which is obtained by learning to dynamically activate SCCs according to the traffic pattern. Hence, Q-learning is considered the most energy-efficient compared to the baseline algorithms.

Cloud virtual reality (VR) gaming traffic characteristics such as frame size, inter-arrival time, and latency need to be carefully studied as a first step toward scalable VR cloud service provisioning. To this end, in this paper we analyze the behavior of VR gaming traffic and Quality of Service (QoS) when VR rendering is conducted remotely in the cloud. We first build a VR testbed utilizing a cloud server, a commercial VR headset, and an off-the-shelf WiFi router. Using this testbed, we collect and process cloud VR gaming traffic data from different games under a number of network conditions and fixed and adaptive video encoding schemes. To analyze the application-level characteristics such as video frame size, frame inter-arrival time, frame loss and frame latency, we develop an interval threshold based identification method for video frames. Based on the frame identification results, we present two statistical models that capture the behaviour of the VR gaming video traffic. The models can be used by researchers and practitioners to generate VR traffic models for simulations and experiments - and are paramount in designing advanced radio resource management (RRM) and network optimization for cloud VR gaming services. To the best of the authors' knowledge, this is the first measurement study and analysis conducted using a commercial cloud VR gaming platform, and under both fixed and adaptive bitrate streaming. We make our VR traffic datasets publicly available for further research by the community.

Carrier Aggregation (CA) has been a breakthrough in LTE that led to increased throughput for users, and is still one of the key technologies in 5G that helps to enhance spectrum utilization. In CA, Component Carriers (CCs) are dynamically activated and deactivated depending on several performance factors. Optimal selection of CCs has been studied in the literature. However, the latency associated with activation and deactivation of CCs, control channel overhead for switching CCs, as well as the energy consumed for monitoring the active CCs have not been a part of the optimal CC selection problem. Nevertheless, those become stringent design constraints in practice. In this paper, we address optimal CC selection and resource allocation in 5G networks, where the above constraints are considered and the 5G network supports several service types with different 5G QoS Identifiers (5QI). The proposed optimum joint CC selection and Radio Resource Block (RB) allocation schemes maximize average throughput of users and satisfy QoS of users in terms of delay. In addition, the proposed schemes take CC activation and deactivation burden into consideration and aim to minimize the number of activations and deactivations. The simulation results demonstrate that our proposed solution outperforms the state of the art solution while satisfying the QoS requirements and creating close to 95.5% reduction on the number of CCs activations and deactivations.

Today deployments of massive Internet of Things (IoT) applications are expected from 5G networks. A primary challenge however is designing scalable wireless resource management schemes that can adapt to the varying temporal and spatial demand of IoT applications. As such, intelligence-based solutions that are agile to, and are able to exploit IoT traffic patterns are emerging as key enablers for 5G IoT applications. For example, Predictive Resource Allocation (PRA) has been proposed in wireless network literature as a mechanism to provide significant energy-savings and Quality of Experience (QoE) gains by leveraging predictions of the user location. While the results are very promising, further research is needed to 1) model and handle the inherent uncertainty in the predicted rates of PRA, and 2) develop low-complexity solutions for practical adoption. This is the topic of this paper, where we present a credibility-based chance-constrained fuzzy programming solution for PRA that enables the operator to control the energy efficiency-QoE tradeoff for different users and services. We demonstrate the use of a Kalman Filter (KF) to adaptively model rate prediction uncertainty by modifying the limits of the fuzzy membership functions in real-time. Our simulation results indicate that the proposed credibility-based framework provides a low-complexity solution for robust PRA.

Recent research on predictive video delivery promised optimal resource utilization and quality of service (QoS) satisfaction to both dynamic adaptive streaming over HTTP (DASH) providers and mobile users. These gains were attained while presuming an idealistic environment with perfect predictions. Thus, a robust QoS-aware predictive-DASH (P-DASH) is of paramount importance to handling the practical uncertainty implied in predicted information. In this paper, we propose a stochastic QoS-aware robust predictive-DASH (RP-DASH) scheme over future wireless networks that takes into account imperfect rate predictions. The objective is to achieve long-term quality fairness among the DASH users while capping the probability of service degradation by an operator predefined level. A deterministic formulation is then obtained using the scenario approximation, which adopts the probability density function (PDF) of predicted rates. A linear conservative approximation is introduced to provide an NP-complete formulation, which can be optimized by commercial solvers. Since exact PDF might not be available, Gaussian approximation is adopted by the introduced scheme to provide a closed form less complexity formulation. To support real-time implementations, a guided heuristic algorithm is devised to obtain near-optimal resource allocations and quality selections, while satisfying the predefined QoS level. Previous non-robust P-DASH schemes are evaluated in this paper, while considering typical error models in predicted rates. Such schemes resulted in increased QoS and the quality of experience degradations with the network load, which was avoided by the introduced RP-DASH. Results further revealed the ability of RP-DASH to reach optimal and fair QoS satisfactions.

The upsurge in data traffic pushed Wi-Fi operators to adopt wireless extenders to improve indoor coverage. Existing deployment approaches, however, focused on coordinated scenarios (managed by the same operator) with single-hop communication. In this paper, we propose a self-deployment approach for finding the optimal placement of extenders in which both the wireless back-haul and front-haul throughputs of the extender are optimized. To that end, we propose an AI-CBR framework to enable autonomous self-deployment that allows the network to learn the environment by means of sensing and perception. New actions, i.e. extender positions, are created by problem-specific optimization and semi-supervised learning algorithms that balance exploration and exploitation of the search space. Wi-Fi standard compliant ns-3 simulations evaluated the proposed self-deployment AI approach and compared its performance against existing conventional coverage maximization approaches under practical uncoordinated scenarios. Throughput fairness and ubiquitous QoS satisfaction are achieved which provide the impetus of applying the AI-driven self-deployment in practice.

The exploitation of mobility traces and rate predictions has enabled predictive delivery of video content that can achieve optimal resource utilization and long-term Quality of Service (QoS) satisfaction. The network recognizes users moving towards poor radio conditions in order to prioritize them over other users with better future conditions. In this paper, we propose a QoS-aware predictive Dynamic Adaptive Streaming over HTTP (DASH) scheme that leverages future information to select both the resource sharing and video qualities over a time horizon. The scheme minimizes the number of quality switches while achieving a minimal average quality level with no video stops. We firstly define the maximum prediction gains under idealistic conditions by a scheme referred to as Optimal QoS-Aware Predictive-DASH (OQP-DASH). Then, a robust stochastic based formulation is introduced to handle the practical uncertainty in predicted information, where the scheme is denoted by Robust QoS-Aware Predictive-DASH (RQP-DASH). A chance constraint programming model based on Scenario Approximation (SA) is adopted to cap the risk of service degradation while using the Probability Mass Function (PMF) of predicted rates. Under idealistic conditions, OQP-DASH outperforms the non-predictive opportunistic counterpart and results in fewer quality switches. Applying estimation errors, RQP-DASH avoids QoS degradation without compromising the prediction gains which supports the application of predictive DASH in future network.

Named Data Networking (NDN) is a promising paradigm for the future Internet to survive the growing data demand. Supporting seamless operation during user mobility is one of the main challenges in NDN. In this paper, we investigate optimal caching for producer mobility under prediction uncertainties. Mainly, we propose a stochastic optimization framework that exploits location and data requests' predictors to cache data proactively before handover. We model the problem using Chance Constraint Programming (CCP) that probabilistically incorporates the uncertainty in data prediction and models the trade-off between network overhead and Consumer satisfaction. A deterministic formulation is derived to obtain a closed form Integer Linear Programming model based on the prediction error model. The proposed framework is then implemented in ndnSIM and Gurobi, and simulation experiments are conducted to provide benchmark solutions for robust proactive caching. The results show that such robust scheme satisfies the consumers' quality of experience under imperfect prediction of future content requested from mobile producers. Hence, sustains the prediction gains over conventional non- predictive schemes without compromising the network overhead. We believe that such results drive incentives for deploying proactive mobility management in future NDN.

Highly predictable users' location and traffic have enabled a new video delivery paradigm over wireless networks referred to as Predictive Resource Allocation (PRA). Existing research assumes perfect prediction of information in order to derive the performance bounds of PRA and define its gains over conventional Resource Allocation (RA). In this paper we sustain the application of energy-efficient PRA under prediction uncertainties. To that end, we propose a stochastic robust PRA scheme that models the uncertainty in future demands and incorporates them in the mathematical formulation. A linear Recourse Programming (RP) model is adopted in order to represent the trade-off between the energy-savings and the risk of wasting resources while considering the probability of a user terminating or skipping the video session. Thus, avoids prebuffering the video chunks that might be skipped by the user. A low complexity near optimal algorithm is then introduced to provide real-time solutions for the formulated RP model. Simulation results demonstrate the ability of the introduced robust PRA to deliver energy-efficient video streaming with lower resources than the existing PRA while promising QoS satisfaction. These results provide the impetus to implement the robust PRA in future wireless networks.

Predictive resource allocations (PRAs) have recently gained attention in wireless network literature due to their significant energy-savings and quality of service (QoS) gains. This enhanced performance was primarily demonstrated while assuming the perfect prediction of both mobility traces and anticipated channel rates. While the results are very promising, several technical challenges need to be overcome before PRAs can be practically adopted. Techniques that model the prediction uncertainty and provide probabilistic quality of service (QoS) guarantees are among such challenges. This differs from the traditional robust optimization of wireless resources, as PRAs use a time horizon with predicted demands and anticipated data rates. In this paper, we tackle this problem and present an energy-efficient stochastic PRAs framework that is robust to prediction uncertainty under generic error probability density functions. The framework is applied for video delivery, where the desired video demands are modeled as probabilistic chance constraints over the prediction time horizon, and a deterministic closed form is then derived based on the Bernstein approximation (BA). In addition to handling prediction uncertainty, mechanisms that track the variance of the channel in real-time are practically needed. Towards this end, we demonstrate how a particle filter (PF) can be adopted to effectively achieve this functionality. A low complexity guided heuristic algorithm is also integrated with the BA-based allocations, and particle filter (PF), to provide a real-time solution. Extensive numerical simulations using a standard compliant long term evolution system are then presented to examine the developed solutions under various operating conditions. Results indicate the ability of our framework to significantly reduce base station energy consumption while satisfying users' QoS under practical prediction uncertainty.

Predictive Resource Allocation (PRA) has demonstrated its ability to provide smooth video delivery with minimal and fair interruptions. Recent work on PRA techniques exploited rate predictions to strategically allocate the limited radio resources for delivering video content. However, existing PRA techniques assume perfect prediction of future information in order to define the maximum attainable gains. In this paper, we introduce a probabilistic robust PRA framework that handles prediction errors. By adopting chance constraint programming we were able to define a probabilistic measure on the QoS degradation due to prediction uncertainties. A deterministic non-convex formulation is then obtained using the statistical parameters of predicted rates. Accordingly, we propose a convex approximation to the formulated fair PRA, which can be solved using optimal solvers to obtain a benchmark solution for future robust PRA schemes. We evaluate non-PRA and non-robust PRA schemes considering typical error models of the predicted rates. We found these schemes to result in suboptimal fairness and increased QoS degradations with the network load. Results further reveal the ability of the introduced robust fair PRA to reach the optimal and fair QoS satisfaction levels. Our approach provides a step towards applying PRA in future wireless networks to deliver video streaming content.

Predictive resource allocation (PRA) techniques that exploit knowledge of the future signal strength along roads have recently been recognized as promising approaches to save base station (BS) energy and improve user quality of service (QoS). Recent studies on human mobility patterns and wireless signal strength measurements along buses and trains have indeed supported the practical potential of PRA. An unresolved challenge, however, is modeling the uncertainty in the predictions, and developing real-time robust solutions that incorporate probabilistic QoS guarantees. This is of paramount importance in PRA due to the prediction time horizon that adds considerable complexity and increases the rate uncertainty in the problem. With these developments in mind, this paper addresses energy-efficient PRA applied to stored video streaming using chance constrained programming. The proposed solution incorporates: 1) uncertainty in predicted user rates; 2) a joint level of probabilistic constraint satisfaction over a time horizon; and 3) both optimal gradient-based and real-time guided heuristic solutions. Our framework fundamentally differs from previous PRA work in the literature where nonstochastic approaches with assumptions of perfect prediction were primarily used to demonstrate the potential energy savings and QoS gains. Numerical simulations based on a standard compliant long term evolution (LTE) system are provided to examine and compare the developed solution. Unlike existing energy-efficient PRA, the proposed framework achieves the desired QoS level under imperfect channel predictions. This robustness is attained without compromising the energy-efficiency compared to opportunistic schedulers, and thus supports PRA implementation in practice.

The promising energy saving and QoS gains of Predictive Resource Allocation (PRA) techniques have recently been recognized in the wireless network research community. These gains were primarily introduced in light of perfect prediction of both mobility traces and anticipated channel rates. However, under real world considerations of prediction errors, the reported gains cannot be guaranteed and further investigation is needed. In this paper, we demonstrate the practical potential of PRA by developing a robust, probabilistic framework that guarantees QoS satisfaction for video streaming under imperfect predictions, without compromising the energy saving gains. The proposed PRA framework uses chance-constrained programming to model video streaming QoS for all users during the foreseen time horizon. Closed form solutions are developed using the Gaussian and Bernstein approximations based on the channel statistical measures. Extensive numerical simulations using a standard compliant Long Term Evolution (LTE) system are presented to examine the developed solutions, for different user mobility scenarios and target QoS levels. The results demonstrate the various design trade-offs involved toward the practical deployment of predictive video streaming in future generation networks.

Novel mobility-aware resource allocation schemes have recently been introduced for efficient transmission of stored videos. The essence of such mechanisms is to lookahead at the future rates users will experience, and then strategically buffer content into user devices when they are at peak radio conditions. For example, a user approaching poor coverage will be preallocated additional video segments to ensure smooth streaming. Advances in mobility prediction and real-time radio environment map updates are driving forces for such Predictive Video Streaming (PVS) mechanisms. Although previous efforts have demonstrated the large potential gains of PVS, ideal channel predictions were assumed. This paper addresses the problem of channel uncertainty in PVS, and proposes a robust resource allocation framework that 1) models channel uncertainty, 2) solves the PVS problem with a tunable level of quality of service guarantees, and 3) learns the degree of uncertainty, and adapts the channel model accordingly. Numerical results demonstrate the effectiveness of the proposed approach for PVS under channel variability.

Novel radio access techniques that leverage mobility predictions are receiving increasing interest in recent literature. The essence of these schemes is to lookahead at the future rates users will experience, and then devise long-term resource allocation strategies. For instance, a YouTube video user moving towards the cell edge can be prioritized to pre-buffer additional video content before poor coverage commences. While the potential of mobility-aware resource allocation has recently been demonstrated, several practical design aspects and evaluation approaches have not yet been addressed due to the complexity of the problem. Furthermore, since prior works have focused on specific applications there is also a strong need for a unified framework that can support different user and network requirements. For this purpose, we present a novel two-stage Predictive Radio Access Network (P-RAN) framework that can efficiently leverage both future data rate predictions in the order of tens of seconds, and instantaneous fast fading at the millisecond level. We also show how the framework can be implemented within the open source Network Simulator 3 (ns-3) LTE module, and apply it to optimize stored video delivery. A thorough set of performance tests are then conducted to assess the performance gains and investigate sensitivity to various prediction errors. Our results indicate that P-RANs can jointly improve both service quality and transmission efficiency. Additionally, we also observe that P-RAN performance can be further improved by modeling prediction uncertainty and developing robust allocation techniques.

This paper aims to optimize the indoor planning of distributed antenna systems (DAS). The objective of the optimization is to find the number of deployed antennas, their optimal locations and the power transmitted from each antenna. The optimal configuration should minimize the deployment cost, maximize wireless coverage while minimizing power leakage outside a building. One of the main challenges in this problem is that in DAS all antennas are fed from the same base station. This means that the total power transmitted is constant and hence increasing the power assigned to one antenna would require decreasing the power on all other antennas. Similarly adding an antenna would require decreasing the power assigned to existing antennas. Previous approaches simplified the problem by assuming equal transmitted power from all antennas in the DAS, and they ignored the fact that the sum of these powers should remain constant. This paper provides a new multi-objective formulation for indoor DAS planning that considers a fixed total transmitted power constraint. The paper proposes a solution method that uses simulated annealing with smart neighborhood search steps to reach a near optimal solution. Results showed that the proposed formulation obtained better indoor DAS configuration and that including antenna power in the optimization provided a solution that contain less antennas and better average power compared to the equal power configuration.

Handover is the main technique that is responsible for the mobility management in the cellular network. The decisions of handover from each cell is only limited to a certain number of cells called neighbors and the list that contains these neighbors is called the neighboring cell list (NCL). Improper construction of NCL may result in either missing some important neighbors or choosing unnecessary neighbors that increase the number of drop calls, the blocking rate and the suboptimal handover decisions while decreases the signal quality. As a solution, NCL optimization is done to remove the effect of improper NCL construction where the missing neighbors to be added and the unnecessary neighbors to be removed are detected using the handover statistics and a new UMTS feature called the detected set reporting (DSR). In this paper, a novel formulation for the NCL optimization problem is introduced that contains new criteria for evaluating the reported DSR cells. The new criteria evaluates the cells according to their directional share (D), distance from the cell under optimization and drop calls in addition to the share (S) which already exist in literature. The criteria and the constraints in formulation ensure the connectivity of users as they move away from the serving cell towards any direction in addition to add the missing neighbors that cause call drops and prohibit the addition of the far neighbors to the NCL since they will suffer from downlink interference. Finally, a complete NCL optimization algorithm is introduced that removes the drawback of the previous optimizations and solves the constrained formulation by ranking the reported cells. The results showed a decreased drop call rate with a decreased DSR signaling traffic compared to the previous introduced algorithms.

Distributed Antenna System (DAS) promises an attractive solution to cope with the increasing demand for high data rate services inside building. DAS divides the indoor Base Station power among a group of spatially separated antennas that are connected to the BS. The power sharing makes the planning of (DAS) more challenging compared to other wireless networks. The previous To simplify the problem DAS planning approaches divided power equally among the antennas and focused on finding the optimal number and locations of antennas. This paper optimizes the transmitted power of the DAS antennas along with their location and shows that this will enhance the performance compared to the equal power structure. The paper formulates the DAS planning problem as an optimization problem that considers the power division among antennas. The optimization aims to minimize the deployment cost and the power leakage outside the building while the maximizing the average data rate and the indoor coverage. To deal with these conflicting objectives and with the non-convexity of the formulated function, the paper develops meta- heuristic genetic algorithm with novel mutation and crossover methods that are customized to this problem