Sanaa Sharafeddine

An optimized approach to video traffic splitting in heterogeneous wireless networks with energy and QoE considerations

Abstract Due to the exploding traffic demands with the ubiquitous anticipated spread of 5G and Internet of Things, research has been active to devise mechanisms for meeting these demands while maintaining high quality user experience. In support of this direction, 3GPP is working towards cellular/WiFi interworking in heterogeneous networks to boost throughput, capacity, coverage and quality of experience. However, the continuous use of multiple wireless interfaces will increase the system performance but at the expense of more energy. As a result, there is a need for a dynamic use of multiple interfaces to provide a balance between energy consumption, throughput and user experience. Previous work in this field has considered improving throughput and reducing energy consumption, but did not consider simultaneously quality of experience as perceived by the end user. In this work, we aim at devising real-time traffic splitting strategies between WiFi and cellular networks to maximize user experience, reduce delay, and balance the needed energy consumption. We develop solutions for cellular/WiFi network resource management using Lyapunov drift-plus-penalty optimization approach. We evaluate the proposed approach using parameters determined via experimental measurements from mobile devices, and using our own test bed implementation to provide an evaluation under realistic operation conditions. Results show the performance effectiveness of the proposed traffic splitting approach in terms of throughput, delay, queue stability, energy consumption and quality of user experience by monitoring the frequency and lengths of video stalls.

Optimized group owner selection in WiFi direct networks

Device-to-Device communication is an essential component in the evolution towards the Internet of Things. The relatively new WiFi-Direct standard allows devices to communicate directly over the well established IEEE 802.11 protocol without the need for an intermediate access point. The increased range and bandwidth advantage of WiFi-Direct over existing short-range technologies such as Bluetooth and Zigbee allows a whole new class of applications to benefit from cooperation. Within a WiFi-Direct network, one device is elected as the group owner and acts as a central hub for all communications. The standard does not dictate a group owner selection strategy and leaves the decision to be taken at the application layer. In this work, we present an optimized strategy for group owner selection within WiFi-Direct networks that aims at maximizing the overall network performance in terms of increased throughput. Moreover, we propose a low complexity multi-device group owner negotiation protocol that runs at the application layer and extends the existing WiFi-Direct protocol, which limits group owner negotiation to two devices only. Simulation results demonstrate the effectiveness of the proposed selection strategy in achieving near-optimum results.

Scalable Multimedia Streaming in Wireless Networks with Device-to-Device Cooperation

We present a scalable mobile multimedia streaming system with device-to-device cooperation that enables common content distribution in dense wireless networking environments. This is particularly applicable to use cases such as delivering real-time multimedia content to fans watching a soccer game in a stadium or to participants attending a major conference in a large auditorium. The key novel characteristics of our system include seamless neighbor discovery and link quality estimation, intelligent clustering and channel allocation algorithms based on constrained minimum spanning trees, robustness against device mobility, and device centric operation with no changes to existing wireless systems. We demonstrate the functionality of the proposed system on Android devices using heterogeneous networks (cellular/WiFi/WiFi-Direct) and show the formation of multiple clusters to allow for scalable operation. The gained insights will help bridge the gap between theoretical and simulation based research conducted in this area and practical operation taking into account the capabilities and limitations of existing wireless technologies and smartphones/tablets.

P2P Group Formation Enhancement for Opportunistic Networks with Wi-Fi Direct

The Wi-Fi Direct technology was proposed by Wi-Fi Alliance in order to facilitate device-to-device communications in Wi-Fi. The Wi-Fi Direct technology offers new possibilities to deploy opportunistic and cooperative networks. The actual state of the Wi-Fi Direct specification lacks optimization for P2P grouping and creating opportunistic networks. In this paper, we present a new P2P group formation method for opportunistic networks and we introduce the concept of nominating a backup group owner that can replace the group owner of a broken P2P group. In addition, we investigate required times to form a P2P group of variable number of nodes and we evaluate the efficiency of the backup group owner. Results show that our proposed P2P group formation method, in addition to the introduction of the backup group owner, can facilitate and accelerate opportunistic P2P grouping.

Dynamic single node failure recovery in distributed storage systems

Abstract With the emergence of many erasure coding techniques that help provide reliability in practical distributed storage systems, we use fractional repetition coding on the given data and optimize the allocation of data blocks on system nodes in a way that minimizes the system repair cost. We selected fractional repetition coding due to its simple repair mechanism that minimizes the repair and disk access bandwidths together with the property of un-coded repair process. To minimize the system repair cost, we formulate our problem using incidence matrices and solve it heuristically using genetic algorithms for all possible cases of single node failures. We then address three practical extensions that respectively account for newly arriving blocks, newly arriving nodes and variable priority files. A re-optimization mechanism for the storage allocation matrix is proposed for the first two extensions that can be easily implemented in real time without the need to redistribute original on-node blocks. The third extension is addressed by implementing variable fractional repetition codes which is shown to achieve significant cost reduction. The contributions of the paper are four fold: (i) generating an optimized block distribution scheme among the nodes of a given data center for fixed and variable size blocks; (ii) optimization of storage allocation under dynamic environments with data block arrivals; (iii) optimization of storage allocation with newly added storage nodes; and (iv) generating an effective block distribution scheme among the nodes by accounting for varying priorities among data blocks. We present a wide range of results for the various proposed algorithms and considered scenarios to quantify the achievable performance gains.

Practical multiple node failure recovery in distributed storage systems

As multiple node failures are becoming so frequent in distributed storage systems, many erasure coding techniques are emerging to handle such failures. In this paper we use the fractional repetition code to apply as a redundancy scheme for multiple failure recovery with optimized system cost. The fractional repetition (FR) code is a class of regenerating codes that consists of a concatenation of an outer maximum distance separable (MDS) code and an inner fractional repetition code that splits the data into several blocks and stores multiple replicas of each on different nodes in the system. We model the problem as an integer linear programming problem that uses modified versions of the fractional repetition code by allowing different block sizes, and minimizes the recovery cost of all dependent and independent multiple node failure scenarios. First, we generate an optimized block distribution scheme that minimizes the total system repair cost together with a full recovery plan with a node repair order for the system. Moreover, we account for the common scenario of having newcomer blocks. We allocate newcomers to nodes with minimal computations and without changing the original optimized plan. The problem is solved using genetic algorithms that search within the feasible solution space. Fast convergence validates the efficacy of our algorithms for different system parameters. Simulation results are shown to be close to optimal for the case of newly arriving blocks.

Failure recovery in wireless content distribution networks with device-to-device cooperation

Abstract Device-to-device cooperation has emerged as a prominent solution to a wide range of challenges in large-scale wireless networks. However, the ad hoc nature of cooperative networks and their proneness to failure are a major obstacle towards their real world deployment and wide adoption. In this work, we focus on failure recovery and scalability in wireless content distribution networks with device-to-device cooperation, where a number of mobile devices in a given geographical area are interested in downloading a common content from an application service provider. We present low complexity effective algorithms based on clustering and tree construction methods in order to address three different types of dynamic node behavior, namely new devices joining the network, existing devices leaving the network, and existing devices moving locally within the network. Moreover, we propose a constrained version of the minimum spanning tree algorithm with bounds on the height of the tree and the maximum degree per node, in order to capture practical operational constraints for device-to-device cooperation in wireless networks. We present results for various network scenarios using simulations and experimental test bed to demonstrate the effectiveness of the proposed algorithms in terms of performance efficiency, computational complexity, and practical implementation feasibility.

Practical Single Node Failure Recovery Using Fractional Repetition Codes in Data Centers

Node failures in distributed storage systems are becoming a critical issue, and many erasure codes are designed to handle such failures. The purpose of this paper is to evaluate fractional repetition (FR) codes, a class of regenerating codes for distributed storage systems, as a practical solution. FR codes consist of a concatenation of an outer maximum distance separable (MDS) code and an inner fractional repetition code that splits the data into several blocks and stores multiple replicas of each on different nodes in the system. We model the problem as an integer linear programming problem that uses modified versions of the fractional repetition code by allowing different block sizes, and minimizes the recovery cost of all single node failure scenarios. The contribution of this work is three fold: We generate an optimized block distribution schema that minimizes the total system repair cost in a data center and we present a full recovery plan for the system. In addition, we account for new-comer blocks and allocate them to nodes with minimal computations and without changing the original optimal schema. This makes our work practical to apply. Hence, a practical solution for node failures is presented by using a self-designed genetic algorithm that searches within the feasible solution space. We show that our results are close to optimal.

Toward dimensioning cooperative high-density wireless networks

The planning procedure of 802.11 WLAN networks is specific to each type of venue. In the case of large venues with high number and dense Wi-Fi devices, the network planning requires a deep investigation on: available channels, number of devices to associate, throughput per channels, etc. In addition, the WLAN planning of dense Wi-Fi devices becomes more complicated when adding collaboration between devices. The collaboration between devices is achieved by forwarding and sharing data through neighboring devices, named relays. In this paper, we provide guidelines for WLAN planning in high-dense collaborative environments. In addition, we study the network performance gains when content is distributed in cooperative manner through both unicast and multicast mode. Results show that using cooperative content distribution in dense environments leads to notable gain in network performance.

Traffic offloading with maximum user capacity in dense D2D cooperative networks

Ultra dense networks and device-to-device communications are expected to play a major role in 5G networks to meet tremendous traffic requirements. In our work, we address traffic offloading in dense device-to-device cooperative heterogeneous networks with focus on use cases where a very large number of users request simultaneously common streaming content from a remote server with quality of service guarantees. We formulate an optimization problem to maximize the number of users served and reduce the number of access points deployed while satisfying a set of system constraints. The solution determines the best strategy for downloading the content either over long range connectivity from the access points or short range connectivity from peer mobile devices. Results are presented for various scenarios in a stadium setting to demonstrate the significant gains of optimized traffic offloading in ultra dense wireless networks.