Multiple Network Interface Cards Research Articles

An Optimization Method of Large-Scale Video Stream Concurrent Transmission for Edge Computing

Concurrent access to large-scale video data streams in edge computing is an important application scenario that currently faces a high cost of network access equipment and high data packet loss rate. To solve this problem, a low-cost link aggregation video stream data concurrent transmission method is proposed. Data Plane Development Kit (DPDK) technology supports the concurrent receiving and forwarding function of multiple Network Interface Cards (NICs). The Q-learning data stream scheduling model is proposed to solve the load scheduling of multiple queues of multiple NICs. The Central Processing Unit (CPU) transmission processing unit was dynamically selected by data stream classification, as well as a reward function, to achieve the dynamic load balancing of data stream transmission. The experiments conducted demonstrate that this method expands the bandwidth by 3.6 times over the benchmark scheme for a single network port, and reduces the average CPU load ratio by 18%. Compared to the UDP and DPDK schemes, it lowers the average system latency by 21%, reduces the data transmission packet loss rate by 0.48%, and improves the overall system transmission throughput. This transmission optimization scheme can be applied in data centers and edge computing clusters to improve the communication performance of big data processing.

Coorp: Satisfying Low-Latency and High-Throughput Requirements of Wireless Network for Coordinated Robotic Learning

In coordinated robotic learning, multiple robots share the same wireless channel for communication, and bring together latency-sensitive (LS) network flows for control and bandwidth-hungry (BH) flows for distributed learning. Unfortunately, existing wireless network supporting systems cannot coordinate these two network flows to meet their own requirements: 1) prioritized contention systems (e.g., EDCA) prevent LS messages from timely acquiring the wireless channel because multiple wireless network interface cards (WNICs) with BH messages are contending for the channel 2) global planning systems (e.g., SchedWiFi) have to reserve a notable time window in the shared channel for each LS flow, suffering from severe bandwidth degradation (up to 42%). We present the coordinated preemption method to meet both requirements for LS flows and BH flows. Globally (among multiple robots), coordinated preemption eliminates unnecessary contention of BH flows by making them transmit in a round-robin manner, such that LS flows have the highest chance to win the contention against BH flows, without sacrificing overall bandwidth from the perspective of coordinated robotic learning applications. Locally (within the same robot), coordinated preemption in real time predicts the periodic transmission of LS flows from the upper application and conservatively limits packets of BH flows buffered in the WNIC only before LS packets arriving, reducing the bandwidth devoted to preemption. COORP, our implementation of coordinated preemption, reduced the violation of latency requirements from 53.9% (EDCA) to 8.8% (comparable to SchedWiFi). Regarding learning quality, COORP achieved a comparable (at times the same) learning reward with EDCA, which grew up to 76% faster than SchedWiFi.

PSNet: Reconfigurable network topology design for accelerating parameter server architecture based distributed machine learning

The bottleneck of Distributed Machine Learning (DML) has shifted from computation to communication. Lots of works have focused on speeding up communication phase from perspective of Parameter Server (PS) architecture, for example resource scheduling. Nonetheless, the performance improvement of these schemes is limited due to the agnostic of the physical topology to the communication pattern of the applications. Concurrently, some articles have also pointed out the impact of topology on DML performance. Besides, our analysis and experimental results also indicate that the general topologies cannot match well with the communication characteristics of DML based on PS architecture. However, to the best of our knowledge, no special topology is tailored for DML. Therefore, in this paper, we propose PSNet, a reconfigurable modular network topology for DML with consideration of the communication characteristics of PS architecture. The main idea of PSNet is that servers are firstly divided into two categories, namely workers configured with high-performance computing capability and parameter servers equipped with multiple Network Interface Cards (NICs). Then Electrical Circuit Switch (ECS) is exploited to connect workers and Top of Rack (ToR) switches for flexibility and reconfigurability in each module. Our theoretical analysis proves that PSNet not only provides high performance for DML tasks, but also achieves high fault tolerance and flexibility. In order to validate the performance of PSNet, we conduct large-scale simulations and small-scale testbed experiments, and the results of experiments demonstrate that PSNet performs 1.89× and 1.92× faster than FatTree for VGG-16 and ResNet50, respectively.

Fog-Supported Delay-Constrained Energy-Saving Live Migration of VMs Over MultiPath TCP/IP 5G Connections

The incoming era of the fifth-generation fog computing-supported radio access networks (shortly, 5G FOGRANs) aims at exploiting computing/networking resource virtualization, in order to augment the limited resources of wireless devices through the seamless live migration of virtual machines (VMs) toward nearby fog data centers. For this purpose, the bandwidths of the multiple wireless network interface cards of the wireless devices may be aggregated under the control of the emerging MultiPathTCP (MPTCP) protocol. However, due to the fading and mobility-induced phenomena, the energy consumptions of the current state-of-the-art VM migration techniques may still offset their expected benefits. Motivated by these considerations, in this paper, we analytically characterize and implement in software and numerically test the optimal minimum-energy settable-complexity bandwidth manager (SCBM) for the live migration of VMs over 5G FOGRAN MPTCP connections. The key features of the proposed SCBM are that: 1) its implementation complexity is settable on-line on the basis of the target energy consumption versus implementation complexity tradeoff; 2) it minimizes the network energy consumed by the wireless device for sustaining the migration process under hard constraints on the tolerated migration times and downtimes; and 3) by leveraging a suitably designed adaptive mechanism, it is capable to quickly react to (possibly, unpredicted) fading and/or mobility-induced abrupt changes of the wireless environment without requiring forecasting. The actual effectiveness of the proposed SCBM is supported by extensive energy versus delay performance comparisons that cover: 1) a number of heterogeneous 3G/4G/WiFi FOGRAN scenarios; 2) synthetic and real-world workloads; and, 3) MPTCP and wireless connections.

Performance of IP-forwarding of Linux hosts with multiple network interfaces

This paper evaluates and compares the performance of IP-packet forwarding of a Linux host equipped with multiple network interface cards (NICs), namely two receiving NICs and one transmitting NIC. We consider a Linux host with SMP (Symmetric Multiprocessing) or multicore multiprocessor (MCMP) architecture. We measure IP forwarding by subjecting an MCMP Linux host to different traffic load conditions of up to 1Gbps. We used the IXIA hardware traffic generator to generate traffic with fixed- and variable-size packets. At the Linux host, generated packets are forwarded/routed from the two receiving NICs to the transmitting NIC. We consider two NIC affinity modes: (I) both receiving NICs are affinitized (or bound) to two cores of the same processor while the transmitting NIC is affinitized to a core on a separate processor, and (II) the transmitting NIC and one receiving NIC are affinitized to two cores of the same processor while the second receving NIC is affinitized to a core on a separate processor. For each affinity mode, we measure the performance for three packet reception mechanisms: NAPI (New API) with a default budget of 300, NAPI with a budget of 2, and Disable and Enable interrupt handling. The performance is measured and compared in terms of various key performance metrics which include throughput, packet loss, round-trip delay, interrupt rates, and CPU availability.

Distributed Multi-Interface Multichannel Random Access Using Convex Optimization

The aggregate capacity of wireless ad hoc networks can be increased substantially if each node is equipped with multiple network interface cards (NICs) and each NIC operates on a distinct frequency channel. Most of the recently proposed channel assignment algorithms are based on combinatorial techniques. Combinatorial channel assignment schemes may sometimes result in computationally complicated algorithms as well as inefficient utilization of the available frequency spectrum. In this paper, we analytically model channel and interface assignment problems as tractable continuous optimization problems within the framework of network utility maximization (NUM). In particular, the link data rate models for both single-channel reception and multichannel reception scenarios are derived. The assignment of both nonoverlapped and partially overlapped channels is also considered. We then propose two distributed multi-interface multichannel random access (DMMRA) algorithms for single-channel reception and multichannel reception scenarios. The DMMRA algorithms are fast, distributed, and easy to implement. Each algorithm solves the formulated NUM problem for each scenario. DMMRA requires each node to only iteratively solve a local, myopic, and convex optimization problem. Convergence and optimality properties of our algorithms are studied analytically. Simulation results show that our proposed algorithms significantly outperform utility-optimal combinatorial channel assignment algorithms in terms of both achieved network utility and throughput.

Always Best Packet Switching: the Mobile VoIP Case Study

Currently, a mobile device equipped with multiple heterogeneous wireless Network Interface Cards (NICs), cannot take fully advantage of its capabilities as the conventional mobility management approach allows it to select and use only one of its NICs at a time. In contrast to this approach, we propose the so-called Always Best Packet Switching (ABPS) model that allows applications to use simultaneously all the available NICs, and switch each given IP datagram through the most suitable NIC, depending on the characteristics of the datagram itself. Specifically, we show that the ABPS model enables mobile applications to create policies for load balancing and recovery purposes in order to support effectively mobile multimedia services. In particular, in this paper we describe a cross-layer mechanism, termed Robust Wireless Multi-Path Channel (RWMPC) that adopts the ABPS model in order to meet effectively interactivity and low packet loss Quality of Service (QoS) requirements of Voice over IP (VoIP) applications, running on mobile hosts equipped with multiple WLAN NICs. By Exploiting the RWMPC services, VoIP applications can establish and maintain separate wireless links with different access points providing access to, possibly independently managed, wireless networks, and select for each UDP datagram the best link to be used for communication purposes. In essence, the RWMPC mechanism monitors each link in use, and notifies the application if detects that a datagram has been lost. In this case, the application retransmits the datagram using an alternative link, available through one of the interfaces homed in the mobile host. We have carried out an experimental evaluation of our mechanism in a real wireless scenario through the emulation of a VoIP application. The results we have obtained from this evaluation are discussed in this paper and confirm the effectiveness of our approach.

Multiple WNIC-based handoff in IEEE 802.11 WLANs

We propose a novel scanning scheme for IEEE 802.11 by equipping Access Points (APs) with multiple Wireless Network Interface Cards (Multi-WNICs), one of which is set to operate in an exclusively reserved channel for the scanning purpose. In this environment, a STAtion (STA) can easily search neighboring APs by scanning the reserved channel. Our simulation results demonstrate that the proposed scheme ultimately reduces the overall scanning time to improve the handoff latency.

A Novel Approach to Fair Routing in Wireless Mesh Networks

Multiradio wireless mesh network (WMN) is a feasible choice for several applications, as routers with multiple network interface cards have become cheaper. Routing in any network has a great impact on the overall network performance, thus a routing protocol or algorithm for WMN should be carefully designed taking into account the specific characteristics of the network. In addition, in wireless networks, serious unfairness can occur between users if the issue is not addressed in the network protocols or algorithms. In this paper, we are proposing a novel centralized routing algorithm, called Subscriber Aware Fair Routing in WMN (SAFARI), for multiradio WMN that assures fairness, leads to a feasible scheduling, and does not collapse the aggregate network throughput with a strict fairness criterion. We show that our protocol is feasible and practical, and exhaustive simulations show that the performance is improved compared to traditional routing algorithms.

Cross-Layer Fair Bandwidth Sharing for Multi-Channel Wireless Mesh Networks

In a wireless mesh network (WMN) with a number of stationary wireless routers, the aggregate capacity can be increased when each router is equipped with multiple network interface cards (NICs) and each NIC is assigned to a distinct orthogonal frequency channel. In this paper, given the logical topology of the network, we mathematically formulate a crosslayer fair bandwidth sharing problem as a non-linear mixedinteger network utility maximization problem. An optimal joint design, based on exact binary linearization techniques, is proposed which leads to a global maximum. A near-optimal joint design, based on approximate dual decomposition techniques, is also proposed which is practical for deployment. Performance is assessed through several numerical examples in terms of network utility, aggregate network throughput, and fairness index. Results show that our proposed designs can lead to multi-channelWMNs which are more efficient and fair compared to their singlechannel counterparts. The performance gain on both efficiency and fairness increase as the number of available NICs per router or the number of available frequency channels increases.

Joint logical topology design, interface assignment, channel allocation, and routing for multi-channel wireless mesh networks

A multi-channel wireless mesh network (MC-WMN) consists of a number of stationary wireless routers, where each router is equipped with multiple network interface cards (NICs). Each NIC operates on a distinct frequency channel. Two neighboring routers establish a logical link if each one has an NIC operating on a common channel. Given the physical topology of the routers and other constraints, four important issues should be addressed in MC-WMNs: logical topology formation, interface assignment, channel allocation, and routing. Logical topology determines the set of logical links. Interface assignment decides how the logical links should be assigned to the NICs in each wireless router. Channel allocation selects the operating channel for each logical link. Finally, routing determines through which logical links the packets should be forwarded. In this paper, we mathematically formulate the logical topology design, interface assignment, channel allocation, and routing as a joint linear optimization problem. Our proposed MC-WMN architecture is called <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TiMesh</i> . Extensive ns-2 simulation experiments are conducted to evaluate the performance of <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TiMesh</i> and compare it with two other MC-WMN architectures <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Hyacinth</i> [1] and <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CLICA</i> [2]. Simulation results show that <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TiMesh</i> achieves higher aggregated network throughput and lower end-to-end delay than <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Hyacinth</i> and <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CLICA</i> for both TCP and UDP traffic. It also provides better fairness among different flows.

Centralized channel assignment and routing algorithms for multi-channel wireless mesh networks

The IEEE 802.11 Wireless LAN standards allow multiple non-overlapping frequency channels to be used simultaneously to increase the aggregate bandwidth available to end-users. Such bandwidth aggregation capability is routinely used in infrastructure mode operation, where the traffic to and from wireless nodes is distributed among multiple interfaces of an access point or among multiple access points to balance the traffic load. However, bandwidth aggregation is rarely used in the context of multi-hop 802.11-based LANs that operate in the ad hoc mode. Most past research efforts that attempt to exploit multiple radio channels require modifications to the MAC protocol and therefore do not work with commodity 802.11 interface hardware. In this paper, we propose and evaluate one of the first multi-channel multi-hop wireless ad-hoc network architectures that can be built using standard 802.11 hardware by equipping each node with multiple network interface cards (NICs) operating on different channels. We focus our attention on wireless mesh networks that serve as the backbone for relaying end-user traffic from wireless access points to the wired network. The idea of exploiting multiple channels is particularly appealing in wireless mesh networks because of their high capacity requirements to support backbone traffic. To reap the full performance potential of this architecture, we develop a set of centralized channel assignment, bandwidth allocation, and routing algorithms for multi-channel wireless mesh networks. A detailed performance evaluation shows that with intelligent channel and bandwidth assignment, equipping every wireless mesh network node with just 2 NICs operating on different channels can increase the total network goodput by a factor of up to 8 compared with the conventional single-channel ad hoc network architecture.

Design and performance of an enhanced IEEE 802.11 MAC protocol for multihop coverage extension

Ad hoc communication is gaining popularity, not only for pure ad hoc communication networks but also as a viable solution for coverage extension in wireless networks. Especially for upcoming WLAN hotspots, this is an interesting option to decrease installation costs. In this article we introduce a new MAC protocol that needs only marginal changes to the standard and enables efficient multihop networking. We advocate the use of multiple IEEE 802.11 channels, where one channel is reserved as a common signalling channel for the task of assigning the others (data channels) among wireless terminals. The proposed MAC protocols are based on a four-way handshake over the common signalling channel, while data transmission occurs on a dedicated channel. We propose a further optimization applying multiple wireless network interface cards. This improvement in performance comes at the price of a slightly more complex hardware. Two different simulation models are implemented to investigate our approach. The first model investigates the MAC protocol and its improvements, while the second model analyzes the multihop performance in terms of delivery ratio and transmission delay. BY means of numerous simulations we present the performance of our MAC approach in comparison with two standard approaches in terms of bandwidth, packet delivery, and transmission delay. For our performance evaluation we apply the IEEE 802.11a technology, but we note that our approach can also be used for IEEE 802.11b.