MPTCP has been proposed recently as a mechanism for supporting transparently multiple connections to the application layer. It is under discussion at the IETF. We show, however, that the current MPTCP suffers from two problems: (P1) Upgrading some TCP users to MPTCP can reduce the throughput of others without any benefit to the upgraded users, which is a symptom of not being Paretooptimal; and (P2) MPTCP users could be excessively aggressive towards TCP users. We attribute these problems to the linked-increases algorithm (LIA) of MPTCP and, more specifically, to an excessive amount of traffic transmitted over congested paths.The design of LIA forces a tradeoff between optimal resource pooling and responsiveness. We revisit the problem and show that it is possible to provide these two properties simultaneously. We implement the resulting algorithm, called opportunistic linked increases algorithm (OLIA), in the Linux kernel, and we study its performance over our testbed, by simulations and by theoretical analysis. We prove that OLIA is Pareto-optimal and satisfies the design goals of MPTCP. Hence it can avoid the problems P1 and P2. Our measurements and simulations indicate that MPTCP with OLIA is as responsive and non-flappy as MPTCP with LIA, and that it solves problems P1 and P2.

Neighbor discovery is one of the first steps in the initialization of a wireless ad hoc network. In this paper, we design and analyze practical algorithms for neighbor discovery in wireless networks. We first consider an ALOHA-like neighbor discovery algorithm in a synchronous system, proposed in an earlier work. When nodes do not have a collision detection mechanism, we show that this algorithm reduces to the classical Coupon Collector's Problem. Consequently, we show that each node discovers all its n neighbors in an expected time equal to ne(ln n+c), for some constant c. When nodes have a collision detection mechanism, we propose an algorithm based on receiver status feedback which yields a ln n improvement over the ALOHA-like algorithm.Our algorithms do not require nodes to have any estimate of the number of neighbors. In particular, we show that not knowing n results in no more than a factor of two slowdown in the algorithm performance. In the absence of node synchronization, we develop asynchronous neighbor discovery algorithms that are only a factor of two slower than their synchronous counterparts. We show that our algorithms can achieve neighbor discovery despite allowing nodes to begin execution at different time instants. Furthermore, our algorithms allow each node to detect when to terminate the neighbor discovery phase.

With the popularity of mobile devices and the pervasive use of cellular technology, there is widespread interest in hybrid networks and on how to achieve robustness and good performance from them. As most smart phones and mobile devices are equipped with dual interfaces (WiFi and 3G/4G), a promising approach is through the use of multi-path TCP, which leverages path diversity to improve performance and provide robust data transfers. In this paper we explore the performance of multi-path TCP in the wild, focusing on simple 2-path multi-path TCP scenarios. We seek to answer the following questions: How much can a user benefit from using multi-path TCP over cellular and WiFi relative to using the either interface alone? What is the impact of flow size on average latency? What is the effect of the rate/route control algorithm on performance? We are especially interested in understanding how application level performance is affected when path characteristics (e.g., round trip times and loss rates) are diverse. We address these questions by conducting measurements using one commercial Internet service provider and three major cellular carriers in the US.

Online video streaming through mobile devices has become extremely popular nowadays. YouTube, for example, reported that the percentage of its traffic streaming to mobile devices has soared from 6% to more than 40% over the past two years. Moreover, people are constantly seeking to stream high quality video for better experience while often suffering from limited bandwidth. Thanks to the rapid deployment of content delivery networks (CDNs), popular videos are now replicated at different sites, and users can stream videos from close-by locations with low latencies. As mobile devices nowadays are equipped with multiple wireless interfaces (e.g., WiFi and 3G/4G), aggregating band-width for high definition video streaming has become possible. We propose a client-based video streaming solution, MSPlayer, that takes advantage of multiple video sources as well as multiple network paths through different interfaces. MSPlayer reduces start-up latency and provides high quality video streaming and robust data transport in mobile scenarios. We experimentally demonstrate our solution on a testbed and through the YouTube video service.

Abstract-Neighbor discovery is essential for the process of self-organization of a wireless network, where almost all routing and medium access protocols need knowledge of one-hop neighbors. In this paper we study the problem of neighbor discovery in a static and synchronous network, where time is divided into slots, each of duration equal to the time required to transmit a hello message, and potentially, some sort of feedback message. Our main contributions lie in detailing the physical layer mechanism for how nodes in receive mode detect the channel status, describing algorithms at higher layers that exploit such a knowledge, and characterizing the significant gain obtained. In particular, we describe one possible physical layer architecture that allows receivers to detect collisions, and then introduce a feedback mechanism that makes the collision information available to the transmitters. This allows nodes to stop transmitting packets as soon as they learn about the successful reception of their discovery messages by the other nodes in the network. Hence, the number of nodes that need to transmit packets decreases over time. These nodes transmit with a probability that is inversely proportional to the number of active nodes in their neighborhood, which is estimated using the collision information available at the nodes. We show through analysis and simulations that our algorithm allows nodes to discover their neighbors in a significantly smaller amount of time compared to the case where reception status feedback is not available to the transmitters.