Single-path TCP Research Articles

An Online Learning Assisted Packet Scheduler for MPTCP in Mobile Networks

Multipath TCP is designed to utilize multiple network paths to achieve improved throughput and robustness against network failure. These features are supposed to make MPTCP preferable to single-path TCP in mobile networks. However, it fails to achieve the expected performance in practice. A key challenge of using MPTCP in mobile networks is how to effectively spread packets over heterogeneous and unstable network paths to mobile devices with limited buffers. If packets are not sent in an effective way, MPTCP may only provide equal or even lower throughput than single-path TCP. Several packet scheduling algorithms have been designed to tackle this challenge. Unfortunately, they still cannot achieve the expected performance in dynamic scenarios such as mobile networks. In this paper, we propose an Online-Learning Assisted Packet Scheduler (OLAPS) to solve the packet scheduling problem by modeling it as a multi-armed bandit problem. Over time, OLAPS can adaptively learn from current network conditions to make the best scheduling policy to provide the highest possible throughput in a dynamic environment. Moreover, when the inbuilt reward monitor detects the mismatch between network conditions and the learned policy, OLAPS aborts the outdated policy and switches to a new one swiftly. We implement OLAPS as a Linux kernel module and evaluate it over a wide range of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ns-3</i> -simulated network conditions. The results show that OLAPS retains MPTCP’s ability to provide higher throughput and also significantly improves the throughput performance of MPTCP when other in-kernel schedulers suffer a dramatic throughput decline.

Managing Energy Consumption of Devices with Multiconnectivity by Deep Learning and Software-Defined Networking.

Multiconnectivity allows user equipment/devices to connect to multiple radio access technologies simultaneously, including 5G, 4G (LTE), and WiFi. It is a necessity in meeting the increasing demand for mobile network services for the 5G and beyond wireless networks, while ensuring that mobile operators can still reap the benefits of their present investments. Multipath TCP (MPTCP) has been introduced to allow uninterrupted reliable data transmission over multiconnectivity links. However, energy consumption is a significant issue for multihomed wireless devices since most of them are battery-powered. This paper employs software-defined networking (SDN) and deep neural networks (DNNs) to manage the energy consumption of devices with multiconnectivity running MPTCP. The proposed method involves two lightweight algorithms implemented on an SDN controller, using a real hardware testbed of dual-homed wireless nodes connected to WiFi and cellular networks. The first algorithm determines whether a node should connect to a specific network or both networks. The second algorithm improves the selection made by the first by using a DNN trained on different scenarios, such as various network sizes and MPTCP congestion control algorithms. The results of our extensive experimentation show that this approach effectively reduces energy consumption while providing better network throughput performance compared to using single-path TCP or MPTCP Cubic or BALIA for all nodes.

An implementation and evaluation of MPTCP-based IoT router.

The evolving Internet of Things (IoT) promisingly improves the quality of life and transforms many industries. However, the IoT application challenges the wireless networks since the resource-constrained IoT devices typically need to send data to the cloud or edge server. Therefore, it is necessary to introduce an intermediate device between IoT devices and the servers, for example, to reduce the cost of direct communication between them. In another case, the device may move and collect the data from IoT devices before transmitting it to the server. The intermediate device should be designed to have resilient Internet connections and sufficient bandwidth in such a context. This work implements and evaluates a Multipath TCP (MPTCP) IoT router, which uses multiple radios to connect a server to address the demanding design. The router leverages MPTCP, an extension of TCP for simultaneous transmission over several paths on top of Wi-Fi interfaces. MPTCP has also supported several working modes for throughput and (or) resilience enhancements. First, we implement the MPTCP kernels, which can run on the popular IoT devices Raspberry Pi 3B+ and 4. Second, we extensively evaluate the performance of IoT routers in a static and mobility scenario. The static scenario's evaluation results show that the MPTCP-based router can achieve seamless handover and bandwidth aggregation. In the mobility scenario, the MPTCP router with one backup path performs better than the single-path TCP. Besides, the MPTCP routers are more energy-efficient than TCP on the same hardware.

Technical Comparison between MPTCP and TCP in Heterogeneous Networks

Multipath TCP (MPTCP) is a project that has proposed by IETF group to allow packet streams to be separated across multiple sub-flow paths. MPTCP brings a great benefit in throughput, reliability, and fairness. However, MPTCP can be implemented in a little Linux distribution where it requires compiling and installing to become available for an actual and simulation scenario. In the paper, the performance analysis and evaluation results in both TCP and MPTCP are achieved through PC computer connected to Wi-Fi access point and 3G in heterogeneous networks. The simulation results prove that MPTCP performs better than single-path TCP for heterogeneous networks. All experiments over MPTCP and TCP leads to same results in terms of the throughput in heterogeneous networks. In this paper, four congestion control methods are implemented in the kernel and compared with each other understand the behaviors of those methods. The result of the experiment proves that Linked Increased Algorithm (LIA) has the advantage over the others in light data traffic while Balanced LIA (BLIA) has the advantage the others when there is heavy data traffic

MuSher: An Agile Multipath-TCP Scheduler for Dual-Band 802.11ad/ac Wireless LANs

Future WLAN devices will combine both IEEE 802.11ad and 802.11ac interfaces. The former provides multi-Gbps rates but is susceptible to blockage, whereas the latter is slower but offers reliable connectivity. A fundamental challenge is thus how to combine those complementary technologies, to make the most of the advantages they offer. In this work, we leverage Multipath TCP (MPTCP) to use both interfaces simultaneously in order to achieve a higher overall throughput as well as seamlessly switch to a single interface when the other one fails. We find that standard MPTCP often performs sub-optimally and can yield a throughput much lower than that of single path TCP over the faster of the two interfaces. We analyze the cause of these performance issues in detail and then design <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MuSher</i> , an agile MPTCP scheduler that allows MPTCP to fully utilize the channel resources available to both interfaces. Our evaluation in realistic scenarios shows that <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MuSher</i> can provide a throughput improvement of 50%/130% under WLAN/Internet settings respectively, compared to the default MPTCP scheduler. It further speeds up the recovery of a traffic stream after disruption by a factor of 8x/75x.

ECN-based shared bottleneck detection for multi-path TCP

Multi-Path TCP (MPTCP) shows its unique advantages over single-path TCP thanks to its aggregate throughput from multiple paths, balancing efficiency and fairness over multipath transmission. However, MPTCP senders should tackle the friendliness issue carefully when sharing the same bottleneck with single-path TCP. Unfortunately, existing shared bottleneck detection schemes either utilize end-to-end delay without consideration of multiple-bottleneck scenarios, or identify subflows on switches with large operation overhead. In this paper, we propose a lightweight yet accurate approach, ECN-based MPTCP (EMPTCP), to detect shared bottleneck of multiple subflows. EMPTCP uses the widely deployed ECN scheme to capture the real congestion state of shared bottlenecks, while at the same time is compatible with various MPTCP congestion control algorithms. Through model analysis, simulation test and real experiment, we show that EMPTCP achieves higher than 85% accuracy in shared bottleneck detection, thus improving the network efficiency and fairness.

BA-MPCUBIC: Bottleneck-Aware Multipath CUBIC for Multipath-TCP.

The Congestion Control Algorithm (CCA) in the Multipath Transmission Control Protocol (MPTCP) is fundamental to controlling the flow of data through multiple subflows (SF) simultaneously. The MPTCP CCA has two design goals: first, always ensure better throughput than single path TCP (SPTCP) flows, and second, collectively, MPTCP SFs going through a shared bottleneck (SB) should occupy bandwidth fairly, i.e., close to the bandwidth occupied by an SPTCP flow. Although several MPTCP CCAs exist, they primarily focus on specific scenarios and could not satisfy the design goals in diverse and dynamic scenarios. Recently, CUBIC has become a widely used CCA for SPTCP for its better compatibility with high-speed internet. CUBIC’s effective implementation in the MPTCP is expected to provide improved throughput and fairer behavior, thus satisfying the design goals. However, although the current multipath CUBIC (MPCUBIC) implementation ensures better fairness, it fails to ensure better throughput. We believe the application of same rule for SFs going through an SB and non-shared bottleneck (NSB) makes it difficult for MPCUBIC to adapt to diverse and dynamically changing network scenarios, thus resulting in poor throughput. Therefore, we present an improved version of MPCUBIC, namely bottleneck-aware MPCUBIC (BA-MPCUBIC), to resolve the throughput issue. First, we deploy an innovative bottleneck detection method that successfully differentiates between an SB and NSB based on round-trip-time, enhanced congestion notification, and packet loss. Then, we implement SPTCP CUBIC and MPCUBIC as the CCAs for SFs going through NSBs and SBs, respectively. Extensive emulation experiments demonstrate that the BA-MPCUBIC successfully detects SBs and NSBs with the highest detection accuracy and the lowest detection time compared with other approaches. Moreover, BA-MPCUBIC successfully satisfies the MPTCP design goals in the considered diverse and dynamic scenarios by ensuring both better throughput and fairness.

Exploiting Client Inference in Multipath TCP Over Multiple Cellular Networks

In this article, we present a client-based multipath TCP (cMPTCP) framework that can cope with path heterogeneity across multiple LTE networks deployed by different operators. cMPTCP is the first work to apply the mobile client's inference based on our observation that an out-of-order queue in an MPTCP receiver (i.e., mobile client) builds up with increasing heterogeneity between different subflows and can significantly degrade throughput performance compared to that achieved by single-path TCP via the best path. For agile and accurate control for the existing MPTCP architecture, we argue that mobile clients are the best network entities to infer the bottleneck state of an end-to-end MPTCP connection. Our proposed cMPTCP consists of two main components: client-initiated multipath selection and subflow-level rate control mechanisms. These mechanisms are compatible with the default MPTCP architecture implemented in the Linux kernel. For performance evaluation, we prototype a complete LTE network testbed consisting of mobile phones, LTE base stations, LTE cores, and application servers. Our experimental results confirm that cMPTCP outperforms existing server-side schedulers in practical dynamic channel conditions.

Loss-Aware Throughput Estimation Scheduler for Multi-Path TCP in Heterogeneous Wireless Networks

Multi-path TCP (MPTCP) is increasingly popular with the widespread usage of multihomed devices. MPTCP allows data streams to be delivered across multiple simultaneous connections, providing higher bandwidth aggregation and throughput in comparison with single-path TCP. However, due to the path heterogeneity and packet losses, the occurrence of Out-of-Order (OFO) packets is inevitable for MPTCP. Although many approaches have been proposed to mitigate OFO, most of them focused on compensating path delay differences but not considered the impact of packet loss. In this paper, we take the first step towards analyzing the impact of packet loss on OFO, and propose Loss-Aware Throughput Estimation scheduler, LATE. LATE comprehensively considers each subflow's path characteristics and protocol parameters including Round Trip Time (RTT), congestion window (cwnd), and loss rate, to predict the data amount that can be sent over each subflow at a given time and determine wisely which segments should be allocated to which subflows. Experimental results show that LATE achieves a gain of 5.13% in mean goodput with long-lasting flows while reducing the completion time of short flows by about 26.68% compared to the state-of-the-art scheduler for MPTCP.

D-LIA: Dynamic congestion control algorithm for MPTCP

The congestion control algorithm (CCA) of Multipath TCP (MPTCP) mainly portrays​ two fundamental challenges to properly utilize the available bandwidth. First, MPTCP should provide an incentive over single-path TCP while not harming any existing single-path TCP flows when sharing the same bottleneck. Second, it should better utilize the paths by ensuring high throughput with low packet losses. We focus to improve the second goal by implementing a novel technique to dynamically control the decrease factor of the CCA depending on the interval between packet losses. We implemented it in Linux kernel and found a significant performance improvement by extensive the Mininet experiments.

Shared Bottleneck-Based Congestion Control and Packet Scheduling for Multipath TCP

In order to be TCP-friendly, the original Multipath TCP (MPTCP) congestion control algorithm is always restricted to gain no better throughput than a traditional single-path TCP on the best path. However, it is unable to maximize the throughput over all available paths when they do not go through a shared bottleneck. Also, bottleneck fairness based solutions detect the bottleneck and conduct different congestion control algorithms at different bottleneck sets to increase throughput while remaining fair to single TCP. However, existing solutions generally detect shared bottlenecks through delay correlation and loss correlation between two flows, which often lead to misjudgement in dynamic and complex network scenarios. Therefore, in this paper, we first propose a new Shared Bottleneck based Congestion Control scheme, called SB-CC, which leverages ECN (Explicit Congestion Notification) mechanism to detect shared bottlenecks among subflows and estimate the congestion degree of each subflow. Then, with the congestion degree, SB-CC balances the loads among all subflows, and smooths out congestion window fluctuation. Also, in order to prevent throughput degradation due to out-of-order packets, we propose a Shared Bottleneck based Forward Prediction packet Scheduling scheme, called SB-FPS. SB-FPS distributes data according to the window size changes of each subflow, and thus could more accurately schedule data in shared bottleneck scenarios. We implement our proposed scheme in the Linux kernel and simulation platform to evaluate the performance in different scenarios. Measurement results indicate that our scheme can detect the bottleneck more accurately and improve the overall network performance while still keeping bottleneck fairness.

Multipath congestion control with network assistance

The use of multiple transport flows over distinct, if possible, paths, is a well-known technique for enhancing the performance and stability of data transfer. Multipath TCP (MPTCP), the most popular multipath transport protocol in-use, allows a single receiver to exploit multiple paths from a single sender. Nevertheless, MPTCP cannot fully exploit the potential gains of multipath connectivity, as it must fairly share resources with regular, single-path TCP, without knowing whether the available paths are distinct or share bottleneck links, due to IP’s design choices. We introduce a hybrid congestion control algorithm for multipath transport that enables higher bandwidth utilization compared to MPTCP, while remaining friendly to TCP-like flows. Our solution employs (i) Normalized Multiflow Congestion Control (NMCC), a novel end-to-end congestion control algorithm and (ii) an in-network module that exposes routing information to the end-users in order to support the greedy friendliness technique. The end-to-end NMCC is architecture-independent and can be seamlessly integrated with MPTCP. The in-network module has been implemented for the PSI Information-Centric Networking architecture, but it can also be integrated with Multi-Protocol Label Switching (MPLS) and Software Defined Networking (SDN). Using an actual protocol implementation deployed on our testbed, as well as on a comprehensive packet-level simulator, we obtain experimental results which demonstrate clear gains for our design in terms of throughput and friendliness to other flows.

Low Latency Friendliness for Multipath TCP

Efficient congestion control is critical to the operation of MPTCP, the Multipath extension of TCP. Congestion control in such an environment primarily aims at enhancing the cumulative TCP throughput over the available paths, while preserving TCP-friendliness by fairly sharing the available bandwidth with single-path TCP flows in each path. While most existing multipath congestion control algorithms fulfill the TCP-friendliness objective in their steady state, their throughput convergence latency is high, rendering them ineffective for short-lived flows. We have proposed Normalized Multipath Congestion Control (NMCC), an MPTCP congestion control algorithm that achieves TCP-friendliness faster, by normalizing the growth of individual sub-flow throughput rather than the throughput itself. As NMCC can become unfriendly when it experiences sparse congestion events, in this paper we introduce the extended NMCC (e-NMCC) protocol that caters for TCP-friendliness upon both throughput growth and throughput reduction epochs. We analytically characterize e-NMCC in terms of TCP-friendliness and responsiveness and compare it with alternative algorithms. Finally, we assess the performance of e-NMCC through experimentation with the htsim simulator and a real Linux implementation. Our results confirm that e-NMCC accelerates throughput convergence, thus ensuring TCP-friendliness regardless of connection duration and underlying network conditions.

Coupled Multipath BBR (C-MPBBR): A Efficient Congestion Control Algorithm for Multipath TCP

Multipath transmission control protocol (MPTCP) is a promising transport layer protocol that enables a device to utilize multiple communication interfaces simultaneously, thereby achieving high throughput. A congestion control algorithm (CCA) employed in MPTCP constitutes a key part that controls the data flow through different subflows (SFs). There are two fundamental challenges associated with MPTCP CCAs. First, MPTCP flows should have an advantage over single-path flows; second, MPTCP flows should be fair, indicating that SFs sharing a common bottleneck should occupy a capacity fairly close to that occupied by a single-path flow. Several MPTCP CCAs have been developed; however, they have failed to satisfy these challenges in all scenarios. Recently, Google has introduced the bottleneck bandwidth and round-trip-time (BBR), a new CCA for single-path TCP, achieving high throughput with minimum delay by employing a network model. In the present paper, we propose a novel MPTCP CCA based on BBR named coupled multipath BBR (C-MPBBR) that satisfies the fundamental challenges by exploiting the concept of network modeling in BBR. C-MPBBR addresses the first challenge by closing the low-bandwidth SFs by tracking the delivery rate and bottleneck bandwidth (BtlBW). Then, it satisfies the second challenge through identifying those SFs that share a common bottleneck and dividing the BtlBW share corresponding to a SF among them. We implemented C-MPBBR in the Linux kernel, tested it on a wide range of scenarios by the Mininet emulation experiments, and the real-world Internet, and confirmed that the proposed C-MPBBR outperforms the existing MPTCP CCAs in terms of successfully satisfying the fundamental challenges by ensuring both throughput and fairness.

An Approach to Reinforce Multipath TCP with Path-Aware Information.

Multipath TCP (MPTCP), which enables the use of multiple wireless links (e.g., Wi-Fi and LTE) for data transmissions, is an excellent technology for evolving multi-homing devices in mobile wireless networks. This paper explores concepts and feasibility of realizing MPTCP with path awareness (PA), in which the path-aware information is leveraged to reinforce the MPTCP transmissions. In particular, when aware of a network situation, a device can facilitate a mechanism that dynamically shifts the MPTCP traffic to a single path and vice versa. As a result, MPTCP with PA could solve the significant problem of negative aggregation benefit when the MPTCP throughput over divergent paths is worse than the best one of single-path TCP. We illustrate the feasibility of the proposed concept through our new implementation of a so-called MPTCP-LA (i.e., MPTCP with Loss Awareness). MPTCP-LA keeps the aggregation benefits non-negative by temporarily switching an MPTCP transmission on a path to a standby condition when the on-device observed loss reaches a threshold. We extensively evaluate MPTCP-LA in comparison to the standard MPTCP in an emulated environment. The results show that MPTCP-LA has better performance regarding enhancing throughput and saving networking resources.

Tuning the Aggressive Slow-Start Behavior of MPTCP for Short Flows

With the widespread availability of multi-homed devices, enabling multiple paths by utilizing multipath TCP (MPTCP) in current networks is a common practice to improve the performance and robustness. Although MPTCP improves both bandwidth efficiency and network reliability, the transmission performance for short flows can become worse than regular single path TCP when the concurrent subflows transferred through a shared bottleneck due to MPTCP’s aggressive slow start behavior, which is uncoupled, and each subflow behaves independently as regular TCP, affecting MPTCP and concurrent traffic at the bottleneck. In this paper, we first reveal that the MPTCP’s aggressive behavior in slow start causes timeouts and throughput collapse. We further present the design and implementation of GSAM, which employs the theoretical analysis to derive the appropriate threshold for smoothing the congestion window growth in GSAM according to the network conditions in slow start phase and leverages congestion detection and control at end-host to avoid buffer overflow under concurrent MPTCP connections with multiple subflows sharing the bottleneck. The experimental results based on the real implementations show that the GSAM reduces the completion time by up to 80% while retaining high Goodput for large flows as MPTCP.

Modeling Transport Layer Protocol Behaviour to Improve Data Center Network Performance

Today, there is a generalized standard usage of internet for all.The devices via multiple technologies that facilitates to provide few communication methods to scholars to work with. By forming multiple paths in the data center network, latest generation data centers offer maximum bandwidth with robustness. To utilize this bandwidth, it is necessary that different data flows take separate paths. In brief, a single-path transport seems inappropriate for such networks. By using Multipath TCP, we must reconsider data center networks, with a diverse approach as to the association between topology, transport protocols, routing. Multipath TCP allows certain topologies that single path TCP cannot use. In newer generation data centers, Multipath TCP is already deployable using extensively deployed technologies such as Equal-cost multipath routing. But, major benefits will come when data centers are specifically designed for multipath transports. Due to manifold of technologies like Cloud computing, social networking, and information networks there is a need to deploy the number of large data centers. While Transport Control Protocol is the leading Layer-3 transport protocol in data center networks, the operating conditions like high bandwidth, small-buffered switches, and traffic patterns causes poor performance of TCP. Data Center TCP algorithm has newly been anticipated as a TCP option for data centers which address these limitations. It is worth noting that traditional TCP protocol.

Fast Coupled Retransmission for Multipath TCP in Data Center Networks

Multipath TCP (MPTCP) is emerging as a new potential candidate that replaces the existing single-path TCP (SPTCP). One applicable area of MPTCP is cloud data center networks, where multiple paths are often available between servers. However, it is observed that MPTCP may not fully leverage the multiple paths and sometimes perform even worse than SPTCP, especially for time-sensitive short flows in data center networks. To address this challenge, we propose a fast coupled retransmission mechanism for MPTCP. The key observation is that one of the paths is likely to be congested if an out-of-order packet exists even after all data packets have been transmitted. In this case, we forward the data packets from the congested path onto the noncongested path and quickly retransmit them. This mechanism effectively avoids network congestion and, hence, helps reduce the overall flow completion time. We implement the proposed scheme in the Linux kernel and evaluate it on our real data center testbed, and the results show that our proposal significantly outperforms the existing schemes.

Forward Delay-based Packet Scheduling Algorithm for Multipath TCP

Multipath TCP (MPTCP) is a transport layer protocol that allows network devices to transfer data over multiple concurrent paths, and hence, utilizes the network resources more effectively than does the traditional single-path TCP. However, as a reliable protocol, MPTCP still needs to deliver data packets (to the upper application) at the receiver in the same order they are transmitted at the sender. The out-of-order packet problem becomes more severe for MPTCP due to the heterogeneous nature of delay and bandwidth of each path. In this paper, we propose the forward-delay-based packet scheduling (FDPS) algorithm for MPTCP to address that problem. The main idea is that the sender dispatches packets via concurrent paths according to their estimated forward delay and throughput differences. Via simulations with various network conditions, the results show that our algorithm significantly maintains in-order arrival packets at the receiver compared with several previous algorithms.

OFPT: OpenFlow based Parallel Transport in Datacenters

Although the dense interconnection datacenter networks (DCNs) (e.g. FatTree) provide multiple paths and high bisection bandwidth for each server pair, the single-path TCP (SPT) and ECMP which are widely used currently neither achieve high bandwidth utilization nor have good load balancing. Due to only one available transmission path, SPT cannot make full use of all available bandwidth, while ECMP`s random hashing results in many collisions. In this paper, we present OFPT, an OpenFlow based Parallel Transport framework, which integrates precise routing and scheduling for better load balancing and higher network throughput. By adopting OpenFlow based centralized control mechanism, OFPT computes the optimal path and bandwidth provision for each flow according to the global network view. To guarantee high throughput, OFPT dynamically schedules flows with Seamless Flow Migration Mechanism (SFMM), which can avoid packet loss in flow rerouting. Finally, we test OFPT on Mininet and implement it in a real testbed. The experimental results show that the average network throughput in OFPT is up to 97.5% of bisection bandwidth, which is higher than ECMP by 36%. Besides, OFPT decreases the average flow completion time (AFCT) and achieves better scalability.